X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fhrtimer.c;h=d2f9239dc6ba51f7d2652f948b46fb01153f8aa6;hb=f653398c86a1c104f0992bd788dd4bb065449be4;hp=01fa2ae98a8571d7e2d7a4e71c03a423792a0d67;hpb=8d16b76421f0b3216012ee2d7819355e1cb847e5;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 01fa2ae..d2f9239 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1,8 +1,9 @@ /* * linux/kernel/hrtimer.c * - * Copyright(C) 2005, Thomas Gleixner - * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2005-2006, Thomas Gleixner + * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar + * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * @@ -36,39 +37,18 @@ #include #include #include +#include #include +#include +#include +#include +#include +#include +#include #include -/** - * ktime_get - get the monotonic time in ktime_t format - * - * returns the time in ktime_t format - */ -static ktime_t ktime_get(void) -{ - struct timespec now; - - ktime_get_ts(&now); - - return timespec_to_ktime(now); -} - -/** - * ktime_get_real - get the real (wall-) time in ktime_t format - * - * returns the time in ktime_t format - */ -static ktime_t ktime_get_real(void) -{ - struct timespec now; - - getnstimeofday(&now); - - return timespec_to_ktime(now); -} - -EXPORT_SYMBOL_GPL(ktime_get_real); +#include /* * The timer bases: @@ -79,67 +59,45 @@ EXPORT_SYMBOL_GPL(ktime_get_real); * This ensures that we capture erroneous accesses to these clock ids * rather than moving them into the range of valid clock id's. */ - -#define MAX_HRTIMER_BASES 2 - -static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) = +DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { + + .clock_base = { - .index = CLOCK_REALTIME, - .get_time = &ktime_get_real, - .resolution = KTIME_REALTIME_RES, - }, - { - .index = CLOCK_MONOTONIC, - .get_time = &ktime_get, - .resolution = KTIME_MONOTONIC_RES, - }, + { + .index = CLOCK_REALTIME, + .get_time = &ktime_get_real, + .resolution = KTIME_LOW_RES, + }, + { + .index = CLOCK_MONOTONIC, + .get_time = &ktime_get, + .resolution = KTIME_LOW_RES, + }, + } }; -/** - * ktime_get_ts - get the monotonic clock in timespec format - * - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime - * clock and the wall_to_monotonic offset and stores the result - * in normalized timespec format in the variable pointed to by ts. - */ -void ktime_get_ts(struct timespec *ts) -{ - struct timespec tomono; - unsigned long seq; - - do { - seq = read_seqbegin(&xtime_lock); - getnstimeofday(ts); - tomono = wall_to_monotonic; - - } while (read_seqretry(&xtime_lock, seq)); - - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, - ts->tv_nsec + tomono.tv_nsec); -} -EXPORT_SYMBOL_GPL(ktime_get_ts); - /* * Get the coarse grained time at the softirq based on xtime and * wall_to_monotonic. */ -static void hrtimer_get_softirq_time(struct hrtimer_base *base) +static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) { ktime_t xtim, tomono; + struct timespec xts, tom; unsigned long seq; do { seq = read_seqbegin(&xtime_lock); - xtim = timespec_to_ktime(xtime); - tomono = timespec_to_ktime(wall_to_monotonic); - + xts = current_kernel_time(); + tom = wall_to_monotonic; } while (read_seqretry(&xtime_lock, seq)); - base[CLOCK_REALTIME].softirq_time = xtim; - base[CLOCK_MONOTONIC].softirq_time = ktime_add(xtim, tomono); + xtim = timespec_to_ktime(xts); + tomono = timespec_to_ktime(tom); + base->clock_base[CLOCK_REALTIME].softirq_time = xtim; + base->clock_base[CLOCK_MONOTONIC].softirq_time = + ktime_add(xtim, tomono); } /* @@ -148,8 +106,6 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base) */ #ifdef CONFIG_SMP -#define set_curr_timer(b, t) do { (b)->curr_timer = (t); } while (0) - /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are @@ -162,37 +118,84 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base) * possible to set timer->base = NULL and drop the lock: the timer remains * locked. */ -static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer, - unsigned long *flags) +static +struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, + unsigned long *flags) { - struct hrtimer_base *base; + struct hrtimer_clock_base *base; for (;;) { base = timer->base; if (likely(base != NULL)) { - spin_lock_irqsave(&base->lock, *flags); + spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ - spin_unlock_irqrestore(&base->lock, *flags); + spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } + +/* + * Get the preferred target CPU for NOHZ + */ +static int hrtimer_get_target(int this_cpu, int pinned) +{ +#ifdef CONFIG_NO_HZ + if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) { + int preferred_cpu = get_nohz_load_balancer(); + + if (preferred_cpu >= 0) + return preferred_cpu; + } +#endif + return this_cpu; +} + +/* + * With HIGHRES=y we do not migrate the timer when it is expiring + * before the next event on the target cpu because we cannot reprogram + * the target cpu hardware and we would cause it to fire late. + * + * Called with cpu_base->lock of target cpu held. + */ +static int +hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + ktime_t expires; + + if (!new_base->cpu_base->hres_active) + return 0; + + expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); + return expires.tv64 <= new_base->cpu_base->expires_next.tv64; +#else + return 0; +#endif +} + /* * Switch the timer base to the current CPU when possible. */ -static inline struct hrtimer_base * -switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base) +static inline struct hrtimer_clock_base * +switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, + int pinned) { - struct hrtimer_base *new_base; + struct hrtimer_clock_base *new_base; + struct hrtimer_cpu_base *new_cpu_base; + int this_cpu = smp_processor_id(); + int cpu = hrtimer_get_target(this_cpu, pinned); - new_base = &__get_cpu_var(hrtimer_bases[base->index]); +again: + new_cpu_base = &per_cpu(hrtimer_bases, cpu); + new_base = &new_cpu_base->clock_base[base->index]; if (base != new_base) { /* - * We are trying to schedule the timer on the local CPU. + * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq @@ -200,13 +203,21 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base) * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ - if (unlikely(base->curr_timer == timer)) + if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_timer_base() */ timer->base = NULL; - spin_unlock(&base->lock); - spin_lock(&new_base->lock); + spin_unlock(&base->cpu_base->lock); + spin_lock(&new_base->cpu_base->lock); + + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + spin_unlock(&new_base->cpu_base->lock); + spin_lock(&base->cpu_base->lock); + timer->base = base; + goto again; + } timer->base = new_base; } return new_base; @@ -214,19 +225,17 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base) #else /* CONFIG_SMP */ -#define set_curr_timer(b, t) do { } while (0) - -static inline struct hrtimer_base * +static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) { - struct hrtimer_base *base = timer->base; + struct hrtimer_clock_base *base = timer->base; - spin_lock_irqsave(&base->lock, *flags); + spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } -#define switch_hrtimer_base(t, b) (b) +# define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ @@ -238,7 +247,6 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) # ifndef CONFIG_KTIME_SCALAR /** * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * * @kt: addend * @nsec: the scalar nsec value to add * @@ -259,20 +267,42 @@ ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) return ktime_add(kt, tmp); } -#else /* CONFIG_KTIME_SCALAR */ +EXPORT_SYMBOL_GPL(ktime_add_ns); + +/** + * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable + * @kt: minuend + * @nsec: the scalar nsec value to subtract + * + * Returns the subtraction of @nsec from @kt in ktime_t format + */ +ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec) +{ + ktime_t tmp; + + if (likely(nsec < NSEC_PER_SEC)) { + tmp.tv64 = nsec; + } else { + unsigned long rem = do_div(nsec, NSEC_PER_SEC); + + tmp = ktime_set((long)nsec, rem); + } + + return ktime_sub(kt, tmp); +} +EXPORT_SYMBOL_GPL(ktime_sub_ns); # endif /* !CONFIG_KTIME_SCALAR */ /* * Divide a ktime value by a nanosecond value */ -static unsigned long ktime_divns(const ktime_t kt, s64 div) +u64 ktime_divns(const ktime_t kt, s64 div) { - u64 dclc, inc, dns; + u64 dclc; int sft = 0; - dclc = dns = ktime_to_ns(kt); - inc = div; + dclc = ktime_to_ns(kt); /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; @@ -281,25 +311,490 @@ static unsigned long ktime_divns(const ktime_t kt, s64 div) dclc >>= sft; do_div(dclc, (unsigned long) div); - return (unsigned long) dclc; + return dclc; } - -#else /* BITS_PER_LONG < 64 */ -# define ktime_divns(kt, div) (unsigned long)((kt).tv64 / (div)) #endif /* BITS_PER_LONG >= 64 */ /* - * Counterpart to lock_timer_base above: + * Add two ktime values and do a safety check for overflow: + */ +ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) +{ + ktime_t res = ktime_add(lhs, rhs); + + /* + * We use KTIME_SEC_MAX here, the maximum timeout which we can + * return to user space in a timespec: + */ + if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64) + res = ktime_set(KTIME_SEC_MAX, 0); + + return res; +} + +EXPORT_SYMBOL_GPL(ktime_add_safe); + +#ifdef CONFIG_DEBUG_OBJECTS_TIMERS + +static struct debug_obj_descr hrtimer_debug_descr; + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int hrtimer_fixup_init(void *addr, enum debug_obj_state state) +{ + struct hrtimer *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + hrtimer_cancel(timer); + debug_object_init(timer, &hrtimer_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state) +{ + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + WARN_ON_ONCE(1); + return 0; + + case ODEBUG_STATE_ACTIVE: + WARN_ON(1); + + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int hrtimer_fixup_free(void *addr, enum debug_obj_state state) +{ + struct hrtimer *timer = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + hrtimer_cancel(timer); + debug_object_free(timer, &hrtimer_debug_descr); + return 1; + default: + return 0; + } +} + +static struct debug_obj_descr hrtimer_debug_descr = { + .name = "hrtimer", + .fixup_init = hrtimer_fixup_init, + .fixup_activate = hrtimer_fixup_activate, + .fixup_free = hrtimer_fixup_free, +}; + +static inline void debug_hrtimer_init(struct hrtimer *timer) +{ + debug_object_init(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_activate(struct hrtimer *timer) +{ + debug_object_activate(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_deactivate(struct hrtimer *timer) +{ + debug_object_deactivate(timer, &hrtimer_debug_descr); +} + +static inline void debug_hrtimer_free(struct hrtimer *timer) +{ + debug_object_free(timer, &hrtimer_debug_descr); +} + +static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode); + +void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + debug_object_init_on_stack(timer, &hrtimer_debug_descr); + __hrtimer_init(timer, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); + +void destroy_hrtimer_on_stack(struct hrtimer *timer) +{ + debug_object_free(timer, &hrtimer_debug_descr); +} + +#else +static inline void debug_hrtimer_init(struct hrtimer *timer) { } +static inline void debug_hrtimer_activate(struct hrtimer *timer) { } +static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } +#endif + +static inline void +debug_init(struct hrtimer *timer, clockid_t clockid, + enum hrtimer_mode mode) +{ + debug_hrtimer_init(timer); + trace_hrtimer_init(timer, clockid, mode); +} + +static inline void debug_activate(struct hrtimer *timer) +{ + debug_hrtimer_activate(timer); + trace_hrtimer_start(timer); +} + +static inline void debug_deactivate(struct hrtimer *timer) +{ + debug_hrtimer_deactivate(timer); + trace_hrtimer_cancel(timer); +} + +/* High resolution timer related functions */ +#ifdef CONFIG_HIGH_RES_TIMERS + +/* + * High resolution timer enabled ? + */ +static int hrtimer_hres_enabled __read_mostly = 1; + +/* + * Enable / Disable high resolution mode + */ +static int __init setup_hrtimer_hres(char *str) +{ + if (!strcmp(str, "off")) + hrtimer_hres_enabled = 0; + else if (!strcmp(str, "on")) + hrtimer_hres_enabled = 1; + else + return 0; + return 1; +} + +__setup("highres=", setup_hrtimer_hres); + +/* + * hrtimer_high_res_enabled - query, if the highres mode is enabled + */ +static inline int hrtimer_is_hres_enabled(void) +{ + return hrtimer_hres_enabled; +} + +/* + * Is the high resolution mode active ? + */ +static inline int hrtimer_hres_active(void) +{ + return __get_cpu_var(hrtimer_bases).hres_active; +} + +/* + * Reprogram the event source with checking both queues for the + * next event + * Called with interrupts disabled and base->lock held + */ +static void +hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) +{ + int i; + struct hrtimer_clock_base *base = cpu_base->clock_base; + ktime_t expires, expires_next; + + expires_next.tv64 = KTIME_MAX; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + struct hrtimer *timer; + + if (!base->first) + continue; + timer = rb_entry(base->first, struct hrtimer, node); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + /* + * clock_was_set() has changed base->offset so the + * result might be negative. Fix it up to prevent a + * false positive in clockevents_program_event() + */ + if (expires.tv64 < 0) + expires.tv64 = 0; + if (expires.tv64 < expires_next.tv64) + expires_next = expires; + } + + if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) + return; + + cpu_base->expires_next.tv64 = expires_next.tv64; + + if (cpu_base->expires_next.tv64 != KTIME_MAX) + tick_program_event(cpu_base->expires_next, 1); +} + +/* + * Shared reprogramming for clock_realtime and clock_monotonic + * + * When a timer is enqueued and expires earlier than the already enqueued + * timers, we have to check, whether it expires earlier than the timer for + * which the clock event device was armed. + * + * Called with interrupts disabled and base->cpu_base.lock held + */ +static int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + int res; + + WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); + + /* + * When the callback is running, we do not reprogram the clock event + * device. The timer callback is either running on a different CPU or + * the callback is executed in the hrtimer_interrupt context. The + * reprogramming is handled either by the softirq, which called the + * callback or at the end of the hrtimer_interrupt. + */ + if (hrtimer_callback_running(timer)) + return 0; + + /* + * CLOCK_REALTIME timer might be requested with an absolute + * expiry time which is less than base->offset. Nothing wrong + * about that, just avoid to call into the tick code, which + * has now objections against negative expiry values. + */ + if (expires.tv64 < 0) + return -ETIME; + + if (expires.tv64 >= cpu_base->expires_next.tv64) + return 0; + + /* + * If a hang was detected in the last timer interrupt then we + * do not schedule a timer which is earlier than the expiry + * which we enforced in the hang detection. We want the system + * to make progress. + */ + if (cpu_base->hang_detected) + return 0; + + /* + * Clockevents returns -ETIME, when the event was in the past. + */ + res = tick_program_event(expires, 0); + if (!IS_ERR_VALUE(res)) + cpu_base->expires_next = expires; + return res; +} + + +/* + * Retrigger next event is called after clock was set + * + * Called with interrupts disabled via on_each_cpu() + */ +static void retrigger_next_event(void *arg) +{ + struct hrtimer_cpu_base *base; + struct timespec realtime_offset; + unsigned long seq; + + if (!hrtimer_hres_active()) + return; + + do { + seq = read_seqbegin(&xtime_lock); + set_normalized_timespec(&realtime_offset, + -wall_to_monotonic.tv_sec, + -wall_to_monotonic.tv_nsec); + } while (read_seqretry(&xtime_lock, seq)); + + base = &__get_cpu_var(hrtimer_bases); + + /* Adjust CLOCK_REALTIME offset */ + spin_lock(&base->lock); + base->clock_base[CLOCK_REALTIME].offset = + timespec_to_ktime(realtime_offset); + + hrtimer_force_reprogram(base, 0); + spin_unlock(&base->lock); +} + +/* + * Clock realtime was set + * + * Change the offset of the realtime clock vs. the monotonic + * clock. + * + * We might have to reprogram the high resolution timer interrupt. On + * SMP we call the architecture specific code to retrigger _all_ high + * resolution timer interrupts. On UP we just disable interrupts and + * call the high resolution interrupt code. + */ +void clock_was_set(void) +{ + /* Retrigger the CPU local events everywhere */ + on_each_cpu(retrigger_next_event, NULL, 1); +} + +/* + * During resume we might have to reprogram the high resolution timer + * interrupt (on the local CPU): + */ +void hres_timers_resume(void) +{ + WARN_ONCE(!irqs_disabled(), + KERN_INFO "hres_timers_resume() called with IRQs enabled!"); + + retrigger_next_event(NULL); +} + +/* + * Initialize the high resolution related parts of cpu_base + */ +static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) +{ + base->expires_next.tv64 = KTIME_MAX; + base->hres_active = 0; +} + +/* + * Initialize the high resolution related parts of a hrtimer + */ +static inline void hrtimer_init_timer_hres(struct hrtimer *timer) +{ +} + + +/* + * When High resolution timers are active, try to reprogram. Note, that in case + * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry + * check happens. The timer gets enqueued into the rbtree. The reprogramming + * and expiry check is done in the hrtimer_interrupt or in the softirq. + */ +static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base, + int wakeup) +{ + if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { + if (wakeup) { + spin_unlock(&base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + spin_lock(&base->cpu_base->lock); + } else + __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + + return 1; + } + + return 0; +} + +/* + * Switch to high resolution mode + */ +static int hrtimer_switch_to_hres(void) +{ + int cpu = smp_processor_id(); + struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu); + unsigned long flags; + + if (base->hres_active) + return 1; + + local_irq_save(flags); + + if (tick_init_highres()) { + local_irq_restore(flags); + printk(KERN_WARNING "Could not switch to high resolution " + "mode on CPU %d\n", cpu); + return 0; + } + base->hres_active = 1; + base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES; + base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES; + + tick_setup_sched_timer(); + + /* "Retrigger" the interrupt to get things going */ + retrigger_next_event(NULL); + local_irq_restore(flags); + return 1; +} + +#else + +static inline int hrtimer_hres_active(void) { return 0; } +static inline int hrtimer_is_hres_enabled(void) { return 0; } +static inline int hrtimer_switch_to_hres(void) { return 0; } +static inline void +hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } +static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base, + int wakeup) +{ + return 0; +} +static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } +static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { } + +#endif /* CONFIG_HIGH_RES_TIMERS */ + +static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + if (timer->start_site) + return; + timer->start_site = __builtin_return_address(0); + memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); + timer->start_pid = current->pid; +#endif +} + +static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; +#endif +} + +static inline void timer_stats_account_hrtimer(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + if (likely(!timer_stats_active)) + return; + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm, 0); +#endif +} + +/* + * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) { - spin_unlock_irqrestore(&timer->base->lock, *flags); + spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward - forward the timer expiry - * * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward @@ -307,13 +802,12 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * Forward the timer expiry so it will expire in the future. * Returns the number of overruns. */ -unsigned long -hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) +u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { - unsigned long orun = 1; + u64 orun = 1; ktime_t delta; - delta = ktime_sub(now, timer->expires); + delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta.tv64 < 0) return 0; @@ -325,8 +819,8 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); - timer->expires = ktime_add_ns(timer->expires, incr * orun); - if (timer->expires.tv64 > now.tv64) + hrtimer_add_expires_ns(timer, incr * orun); + if (hrtimer_get_expires_tv64(timer) > now.tv64) return orun; /* * This (and the ktime_add() below) is the @@ -334,22 +828,29 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) */ orun++; } - timer->expires = ktime_add(timer->expires, interval); + hrtimer_add_expires(timer, interval); return orun; } +EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. + * + * Returns 1 when the new timer is the leftmost timer in the tree. */ -static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +static int enqueue_hrtimer(struct hrtimer *timer, + struct hrtimer_clock_base *base) { struct rb_node **link = &base->active.rb_node; struct rb_node *parent = NULL; struct hrtimer *entry; + int leftmost = 1; + + debug_activate(timer); /* * Find the right place in the rbtree: @@ -361,71 +862,107 @@ static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) * We dont care about collisions. Nodes with * the same expiry time stay together. */ - if (timer->expires.tv64 < entry->expires.tv64) + if (hrtimer_get_expires_tv64(timer) < + hrtimer_get_expires_tv64(entry)) { link = &(*link)->rb_left; - else + } else { link = &(*link)->rb_right; + leftmost = 0; + } } /* * Insert the timer to the rbtree and check whether it * replaces the first pending timer */ + if (leftmost) + base->first = &timer->node; + rb_link_node(&timer->node, parent, link); rb_insert_color(&timer->node, &base->active); + /* + * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the + * state of a possibly running callback. + */ + timer->state |= HRTIMER_STATE_ENQUEUED; - if (!base->first || timer->expires.tv64 < - rb_entry(base->first, struct hrtimer, node)->expires.tv64) - base->first = &timer->node; + return leftmost; } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. + * + * High resolution timer mode reprograms the clock event device when the + * timer is the one which expires next. The caller can disable this by setting + * reprogram to zero. This is useful, when the context does a reprogramming + * anyway (e.g. timer interrupt) */ -static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +static void __remove_hrtimer(struct hrtimer *timer, + struct hrtimer_clock_base *base, + unsigned long newstate, int reprogram) { + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + /* - * Remove the timer from the rbtree and replace the - * first entry pointer if necessary. + * Remove the timer from the rbtree and replace the first + * entry pointer if necessary. */ - if (base->first == &timer->node) + if (base->first == &timer->node) { base->first = rb_next(&timer->node); +#ifdef CONFIG_HIGH_RES_TIMERS + /* Reprogram the clock event device. if enabled */ + if (reprogram && hrtimer_hres_active()) { + ktime_t expires; + + expires = ktime_sub(hrtimer_get_expires(timer), + base->offset); + if (base->cpu_base->expires_next.tv64 == expires.tv64) + hrtimer_force_reprogram(base->cpu_base, 1); + } +#endif + } rb_erase(&timer->node, &base->active); - timer->node.rb_parent = HRTIMER_INACTIVE; +out: + timer->state = newstate; } /* * remove hrtimer, called with base lock held */ static inline int -remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) { - if (hrtimer_active(timer)) { - __remove_hrtimer(timer, base); + if (hrtimer_is_queued(timer)) { + int reprogram; + + /* + * Remove the timer and force reprogramming when high + * resolution mode is active and the timer is on the current + * CPU. If we remove a timer on another CPU, reprogramming is + * skipped. The interrupt event on this CPU is fired and + * reprogramming happens in the interrupt handler. This is a + * rare case and less expensive than a smp call. + */ + debug_deactivate(timer); + timer_stats_hrtimer_clear_start_info(timer); + reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases); + __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, + reprogram); return 1; } return 0; } -/** - * hrtimer_start - (re)start an relative timer on the current CPU - * - * @timer: the timer to be added - * @tim: expiry time - * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) - * - * Returns: - * 0 on success - * 1 when the timer was active - */ -int -hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, const enum hrtimer_mode mode, + int wakeup) { - struct hrtimer_base *base, *new_base; + struct hrtimer_clock_base *base, *new_base; unsigned long flags; - int ret; + int ret, leftmost; base = lock_hrtimer_base(timer, &flags); @@ -433,10 +970,10 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) ret = remove_hrtimer(timer, base); /* Switch the timer base, if necessary: */ - new_base = switch_hrtimer_base(timer, base); + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); - if (mode == HRTIMER_REL) { - tim = ktime_add(tim, new_base->get_time()); + if (mode & HRTIMER_MODE_REL) { + tim = ktime_add_safe(tim, new_base->get_time()); /* * CONFIG_TIME_LOW_RES is a temporary way for architectures * to signal that they simply return xtime in @@ -445,39 +982,85 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) * timeouts. This will go away with the GTOD framework. */ #ifdef CONFIG_TIME_LOW_RES - tim = ktime_add(tim, base->resolution); + tim = ktime_add_safe(tim, base->resolution); #endif } - timer->expires = tim; - enqueue_hrtimer(timer, new_base); + hrtimer_set_expires_range_ns(timer, tim, delta_ns); + + timer_stats_hrtimer_set_start_info(timer); + + leftmost = enqueue_hrtimer(timer, new_base); + + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) + hrtimer_enqueue_reprogram(timer, new_base, wakeup); unlock_hrtimer_base(timer, &flags); return ret; } + +/** + * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @delta_ns: "slack" range for the timer + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, const enum hrtimer_mode mode) +{ + return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1); +} +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + return __hrtimer_start_range_ns(timer, tim, 0, mode, 1); +} EXPORT_SYMBOL_GPL(hrtimer_start); + /** * hrtimer_try_to_cancel - try to deactivate a timer - * * @timer: hrtimer to stop * * Returns: * 0 when the timer was not active * 1 when the timer was active * -1 when the timer is currently excuting the callback function and - * can not be stopped + * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { - struct hrtimer_base *base; + struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; base = lock_hrtimer_base(timer, &flags); - if (base->curr_timer != timer) + if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base); unlock_hrtimer_base(timer, &flags); @@ -489,7 +1072,6 @@ EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. - * * @timer: the timer to be cancelled * * Returns: @@ -510,24 +1092,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer - * * @timer: the timer to read */ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { - struct hrtimer_base *base; + struct hrtimer_clock_base *base; unsigned long flags; ktime_t rem; base = lock_hrtimer_base(timer, &flags); - rem = ktime_sub(timer->expires, timer->base->get_time()); + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(hrtimer_get_remaining); -#ifdef CONFIG_NO_IDLE_HZ +#ifdef CONFIG_NO_HZ /** * hrtimer_get_next_event - get the time until next expiry event * @@ -536,35 +1117,61 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining); */ ktime_t hrtimer_get_next_event(void) { - struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + struct hrtimer_clock_base *base = cpu_base->clock_base; ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; unsigned long flags; int i; - for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) { - struct hrtimer *timer; + spin_lock_irqsave(&cpu_base->lock, flags); - spin_lock_irqsave(&base->lock, flags); - if (!base->first) { - spin_unlock_irqrestore(&base->lock, flags); - continue; + if (!hrtimer_hres_active()) { + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + struct hrtimer *timer; + + if (!base->first) + continue; + + timer = rb_entry(base->first, struct hrtimer, node); + delta.tv64 = hrtimer_get_expires_tv64(timer); + delta = ktime_sub(delta, base->get_time()); + if (delta.tv64 < mindelta.tv64) + mindelta.tv64 = delta.tv64; } - timer = rb_entry(base->first, struct hrtimer, node); - delta.tv64 = timer->expires.tv64; - spin_unlock_irqrestore(&base->lock, flags); - delta = ktime_sub(delta, base->get_time()); - if (delta.tv64 < mindelta.tv64) - mindelta.tv64 = delta.tv64; } + + spin_unlock_irqrestore(&cpu_base->lock, flags); + if (mindelta.tv64 < 0) mindelta.tv64 = 0; return mindelta; } #endif +static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + struct hrtimer_cpu_base *cpu_base; + + memset(timer, 0, sizeof(struct hrtimer)); + + cpu_base = &__raw_get_cpu_var(hrtimer_bases); + + if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS) + clock_id = CLOCK_MONOTONIC; + + timer->base = &cpu_base->clock_base[clock_id]; + hrtimer_init_timer_hres(timer); + +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; + timer->start_pid = -1; + memset(timer->start_comm, 0, TASK_COMM_LEN); +#endif +} + /** * hrtimer_init - initialize a timer to the given clock - * * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel @@ -572,100 +1179,304 @@ ktime_t hrtimer_get_next_event(void) void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { - struct hrtimer_base *bases; - - memset(timer, 0, sizeof(struct hrtimer)); - - bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); - - if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS) - clock_id = CLOCK_MONOTONIC; - - timer->base = &bases[clock_id]; - timer->node.rb_parent = HRTIMER_INACTIVE; + debug_init(timer, clock_id, mode); + __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /** * hrtimer_get_res - get the timer resolution for a clock - * * @which_clock: which clock to query * @tp: pointer to timespec variable to store the resolution * - * Store the resolution of the clock selected by which_clock in the - * variable pointed to by tp. + * Store the resolution of the clock selected by @which_clock in the + * variable pointed to by @tp. */ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) { - struct hrtimer_base *bases; + struct hrtimer_cpu_base *cpu_base; - bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); - *tp = ktime_to_timespec(bases[which_clock].resolution); + cpu_base = &__raw_get_cpu_var(hrtimer_bases); + *tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution); return 0; } EXPORT_SYMBOL_GPL(hrtimer_get_res); +static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) +{ + struct hrtimer_clock_base *base = timer->base; + struct hrtimer_cpu_base *cpu_base = base->cpu_base; + enum hrtimer_restart (*fn)(struct hrtimer *); + int restart; + + WARN_ON(!irqs_disabled()); + + debug_deactivate(timer); + __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + timer_stats_account_hrtimer(timer); + fn = timer->function; + + /* + * Because we run timers from hardirq context, there is no chance + * they get migrated to another cpu, therefore its safe to unlock + * the timer base. + */ + spin_unlock(&cpu_base->lock); + trace_hrtimer_expire_entry(timer, now); + restart = fn(timer); + trace_hrtimer_expire_exit(timer); + spin_lock(&cpu_base->lock); + + /* + * Note: We clear the CALLBACK bit after enqueue_hrtimer and + * we do not reprogramm the event hardware. Happens either in + * hrtimer_start_range_ns() or in hrtimer_interrupt() + */ + if (restart != HRTIMER_NORESTART) { + BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); + enqueue_hrtimer(timer, base); + } + timer->state &= ~HRTIMER_STATE_CALLBACK; +} + +#ifdef CONFIG_HIGH_RES_TIMERS + /* - * Expire the per base hrtimer-queue: + * High resolution timer interrupt + * Called with interrupts disabled */ -static inline void run_hrtimer_queue(struct hrtimer_base *base) +void hrtimer_interrupt(struct clock_event_device *dev) { - struct rb_node *node; + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + struct hrtimer_clock_base *base; + ktime_t expires_next, now, entry_time, delta; + int i, retries = 0; - if (!base->first) - return; + BUG_ON(!cpu_base->hres_active); + cpu_base->nr_events++; + dev->next_event.tv64 = KTIME_MAX; + + entry_time = now = ktime_get(); +retry: + expires_next.tv64 = KTIME_MAX; + + spin_lock(&cpu_base->lock); + /* + * We set expires_next to KTIME_MAX here with cpu_base->lock + * held to prevent that a timer is enqueued in our queue via + * the migration code. This does not affect enqueueing of + * timers which run their callback and need to be requeued on + * this CPU. + */ + cpu_base->expires_next.tv64 = KTIME_MAX; - if (base->get_softirq_time) - base->softirq_time = base->get_softirq_time(); + base = cpu_base->clock_base; - spin_lock_irq(&base->lock); + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + ktime_t basenow; + struct rb_node *node; - while ((node = base->first)) { - struct hrtimer *timer; - int (*fn)(struct hrtimer *); - int restart; + basenow = ktime_add(now, base->offset); - timer = rb_entry(node, struct hrtimer, node); - if (base->softirq_time.tv64 <= timer->expires.tv64) - break; + while ((node = base->first)) { + struct hrtimer *timer; - fn = timer->function; - set_curr_timer(base, timer); - __remove_hrtimer(timer, base); - spin_unlock_irq(&base->lock); + timer = rb_entry(node, struct hrtimer, node); - restart = fn(timer); + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the + * earliest interrupt after their soft expiration. + * This allows us to avoid using a Priority Search + * Tree, which can answer a stabbing querry for + * overlapping intervals and instead use the simple + * BST we already have. + * We don't add extra wakeups by delaying timers that + * are right-of a not yet expired timer, because that + * timer will have to trigger a wakeup anyway. + */ - spin_lock_irq(&base->lock); + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { + ktime_t expires; - if (restart != HRTIMER_NORESTART) { - BUG_ON(hrtimer_active(timer)); - enqueue_hrtimer(timer, base); + expires = ktime_sub(hrtimer_get_expires(timer), + base->offset); + if (expires.tv64 < expires_next.tv64) + expires_next = expires; + break; + } + + __run_hrtimer(timer, &basenow); } + base++; + } + + /* + * Store the new expiry value so the migration code can verify + * against it. + */ + cpu_base->expires_next = expires_next; + spin_unlock(&cpu_base->lock); + + /* Reprogramming necessary ? */ + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; + return; } - set_curr_timer(base, NULL); - spin_unlock_irq(&base->lock); + + /* + * The next timer was already expired due to: + * - tracing + * - long lasting callbacks + * - being scheduled away when running in a VM + * + * We need to prevent that we loop forever in the hrtimer + * interrupt routine. We give it 3 attempts to avoid + * overreacting on some spurious event. + */ + now = ktime_get(); + cpu_base->nr_retries++; + if (++retries < 3) + goto retry; + /* + * Give the system a chance to do something else than looping + * here. We stored the entry time, so we know exactly how long + * we spent here. We schedule the next event this amount of + * time away. + */ + cpu_base->nr_hangs++; + cpu_base->hang_detected = 1; + delta = ktime_sub(now, entry_time); + if (delta.tv64 > cpu_base->max_hang_time.tv64) + cpu_base->max_hang_time = delta; + /* + * Limit it to a sensible value as we enforce a longer + * delay. Give the CPU at least 100ms to catch up. + */ + if (delta.tv64 > 100 * NSEC_PER_MSEC) + expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); + else + expires_next = ktime_add(now, delta); + tick_program_event(expires_next, 1); + printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", + ktime_to_ns(delta)); +} + +/* + * local version of hrtimer_peek_ahead_timers() called with interrupts + * disabled. + */ +static void __hrtimer_peek_ahead_timers(void) +{ + struct tick_device *td; + + if (!hrtimer_hres_active()) + return; + + td = &__get_cpu_var(tick_cpu_device); + if (td && td->evtdev) + hrtimer_interrupt(td->evtdev); +} + +/** + * hrtimer_peek_ahead_timers -- run soft-expired timers now + * + * hrtimer_peek_ahead_timers will peek at the timer queue of + * the current cpu and check if there are any timers for which + * the soft expires time has passed. If any such timers exist, + * they are run immediately and then removed from the timer queue. + * + */ +void hrtimer_peek_ahead_timers(void) +{ + unsigned long flags; + + local_irq_save(flags); + __hrtimer_peek_ahead_timers(); + local_irq_restore(flags); +} + +static void run_hrtimer_softirq(struct softirq_action *h) +{ + hrtimer_peek_ahead_timers(); } +#else /* CONFIG_HIGH_RES_TIMERS */ + +static inline void __hrtimer_peek_ahead_timers(void) { } + +#endif /* !CONFIG_HIGH_RES_TIMERS */ + /* * Called from timer softirq every jiffy, expire hrtimers: + * + * For HRT its the fall back code to run the softirq in the timer + * softirq context in case the hrtimer initialization failed or has + * not been done yet. + */ +void hrtimer_run_pending(void) +{ + if (hrtimer_hres_active()) + return; + + /* + * This _is_ ugly: We have to check in the softirq context, + * whether we can switch to highres and / or nohz mode. The + * clocksource switch happens in the timer interrupt with + * xtime_lock held. Notification from there only sets the + * check bit in the tick_oneshot code, otherwise we might + * deadlock vs. xtime_lock. + */ + if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) + hrtimer_switch_to_hres(); +} + +/* + * Called from hardirq context every jiffy */ void hrtimer_run_queues(void) { - struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); - int i; + struct rb_node *node; + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + struct hrtimer_clock_base *base; + int index, gettime = 1; + + if (hrtimer_hres_active()) + return; + + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { + base = &cpu_base->clock_base[index]; + + if (!base->first) + continue; + + if (gettime) { + hrtimer_get_softirq_time(cpu_base); + gettime = 0; + } - hrtimer_get_softirq_time(base); + spin_lock(&cpu_base->lock); - for (i = 0; i < MAX_HRTIMER_BASES; i++) - run_hrtimer_queue(&base[i]); + while ((node = base->first)) { + struct hrtimer *timer; + + timer = rb_entry(node, struct hrtimer, node); + if (base->softirq_time.tv64 <= + hrtimer_get_expires_tv64(timer)) + break; + + __run_hrtimer(timer, &base->softirq_time); + } + spin_unlock(&cpu_base->lock); + } } /* * Sleep related functions: */ -static int hrtimer_wakeup(struct hrtimer *timer) +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); @@ -678,11 +1489,12 @@ static int hrtimer_wakeup(struct hrtimer *timer) return HRTIMER_NORESTART; } -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, task_t *task) +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) { sl->timer.function = hrtimer_wakeup; sl->task = task; } +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { @@ -690,47 +1502,64 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod do { set_current_state(TASK_INTERRUPTIBLE); - hrtimer_start(&t->timer, t->timer.expires, mode); + hrtimer_start_expires(&t->timer, mode); + if (!hrtimer_active(&t->timer)) + t->task = NULL; - schedule(); + if (likely(t->task)) + schedule(); hrtimer_cancel(&t->timer); - mode = HRTIMER_ABS; + mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); + __set_current_state(TASK_RUNNING); + return t->task == NULL; } -static long __sched nanosleep_restart(struct restart_block *restart) +static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) { - struct hrtimer_sleeper t; - struct timespec __user *rmtp; - struct timespec tu; - ktime_t time; + struct timespec rmt; + ktime_t rem; - restart->fn = do_no_restart_syscall; + rem = hrtimer_expires_remaining(timer); + if (rem.tv64 <= 0) + return 0; + rmt = ktime_to_timespec(rem); - hrtimer_init(&t.timer, restart->arg3, HRTIMER_ABS); - t.timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0; + if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) + return -EFAULT; - if (do_nanosleep(&t, HRTIMER_ABS)) - return 0; + return 1; +} + +long __sched hrtimer_nanosleep_restart(struct restart_block *restart) +{ + struct hrtimer_sleeper t; + struct timespec __user *rmtp; + int ret = 0; - rmtp = (struct timespec __user *) restart->arg2; + hrtimer_init_on_stack(&t.timer, restart->nanosleep.index, + HRTIMER_MODE_ABS); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); + + if (do_nanosleep(&t, HRTIMER_MODE_ABS)) + goto out; + + rmtp = restart->nanosleep.rmtp; if (rmtp) { - time = ktime_sub(t.timer.expires, t.timer.base->get_time()); - if (time.tv64 <= 0) - return 0; - tu = ktime_to_timespec(time); - if (copy_to_user(rmtp, &tu, sizeof(tu))) - return -EFAULT; + ret = update_rmtp(&t.timer, rmtp); + if (ret <= 0) + goto out; } - restart->fn = nanosleep_restart; - /* The other values in restart are already filled in */ - return -ERESTART_RESTARTBLOCK; + ret = -ERESTART_RESTARTBLOCK; +out: + destroy_hrtimer_on_stack(&t.timer); + return ret; } long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, @@ -738,39 +1567,44 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, { struct restart_block *restart; struct hrtimer_sleeper t; - struct timespec tu; - ktime_t rem; + int ret = 0; + unsigned long slack; - hrtimer_init(&t.timer, clockid, mode); - t.timer.expires = timespec_to_ktime(*rqtp); + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; + + hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); if (do_nanosleep(&t, mode)) - return 0; + goto out; /* Absolute timers do not update the rmtp value and restart: */ - if (mode == HRTIMER_ABS) - return -ERESTARTNOHAND; + if (mode == HRTIMER_MODE_ABS) { + ret = -ERESTARTNOHAND; + goto out; + } if (rmtp) { - rem = ktime_sub(t.timer.expires, t.timer.base->get_time()); - if (rem.tv64 <= 0) - return 0; - tu = ktime_to_timespec(rem); - if (copy_to_user(rmtp, &tu, sizeof(tu))) - return -EFAULT; + ret = update_rmtp(&t.timer, rmtp); + if (ret <= 0) + goto out; } restart = ¤t_thread_info()->restart_block; - restart->fn = nanosleep_restart; - restart->arg0 = t.timer.expires.tv64 & 0xFFFFFFFF; - restart->arg1 = t.timer.expires.tv64 >> 32; - restart->arg2 = (unsigned long) rmtp; - restart->arg3 = (unsigned long) t.timer.base->index; - - return -ERESTART_RESTARTBLOCK; + restart->fn = hrtimer_nanosleep_restart; + restart->nanosleep.index = t.timer.base->index; + restart->nanosleep.rmtp = rmtp; + restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); + + ret = -ERESTART_RESTARTBLOCK; +out: + destroy_hrtimer_on_stack(&t.timer); + return ret; } -asmlinkage long -sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp) +SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, + struct timespec __user *, rmtp) { struct timespec tu; @@ -780,83 +1614,117 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp) if (!timespec_valid(&tu)) return -EINVAL; - return hrtimer_nanosleep(&tu, rmtp, HRTIMER_REL, CLOCK_MONOTONIC); + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); } /* * Functions related to boot-time initialization: */ -static void __devinit init_hrtimers_cpu(int cpu) +static void __cpuinit init_hrtimers_cpu(int cpu) { - struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); + struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; - for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) - spin_lock_init(&base->lock); + spin_lock_init(&cpu_base->lock); + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) + cpu_base->clock_base[i].cpu_base = cpu_base; + + hrtimer_init_hres(cpu_base); } #ifdef CONFIG_HOTPLUG_CPU -static void migrate_hrtimer_list(struct hrtimer_base *old_base, - struct hrtimer_base *new_base) +static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, + struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct rb_node *node; while ((node = rb_first(&old_base->active))) { timer = rb_entry(node, struct hrtimer, node); - __remove_hrtimer(timer, old_base); + BUG_ON(hrtimer_callback_running(timer)); + debug_deactivate(timer); + + /* + * Mark it as STATE_MIGRATE not INACTIVE otherwise the + * timer could be seen as !active and just vanish away + * under us on another CPU + */ + __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0); timer->base = new_base; + /* + * Enqueue the timers on the new cpu. This does not + * reprogram the event device in case the timer + * expires before the earliest on this CPU, but we run + * hrtimer_interrupt after we migrated everything to + * sort out already expired timers and reprogram the + * event device. + */ enqueue_hrtimer(timer, new_base); + + /* Clear the migration state bit */ + timer->state &= ~HRTIMER_STATE_MIGRATE; } } -static void migrate_hrtimers(int cpu) +static void migrate_hrtimers(int scpu) { - struct hrtimer_base *old_base, *new_base; + struct hrtimer_cpu_base *old_base, *new_base; int i; - BUG_ON(cpu_online(cpu)); - old_base = per_cpu(hrtimer_bases, cpu); - new_base = get_cpu_var(hrtimer_bases); + BUG_ON(cpu_online(scpu)); + tick_cancel_sched_timer(scpu); local_irq_disable(); + old_base = &per_cpu(hrtimer_bases, scpu); + new_base = &__get_cpu_var(hrtimer_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock(&new_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); - for (i = 0; i < MAX_HRTIMER_BASES; i++) { - - spin_lock(&new_base->lock); - spin_lock(&old_base->lock); - - BUG_ON(old_base->curr_timer); - - migrate_hrtimer_list(old_base, new_base); - - spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - old_base++; - new_base++; + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + migrate_hrtimer_list(&old_base->clock_base[i], + &new_base->clock_base[i]); } + spin_unlock(&old_base->lock); + spin_unlock(&new_base->lock); + + /* Check, if we got expired work to do */ + __hrtimer_peek_ahead_timers(); local_irq_enable(); - put_cpu_var(hrtimer_bases); } + #endif /* CONFIG_HOTPLUG_CPU */ -static int hrtimer_cpu_notify(struct notifier_block *self, +static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { - long cpu = (long)hcpu; + int scpu = (long)hcpu; switch (action) { case CPU_UP_PREPARE: - init_hrtimers_cpu(cpu); + case CPU_UP_PREPARE_FROZEN: + init_hrtimers_cpu(scpu); break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_DYING: + case CPU_DYING_FROZEN: + clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); + break; case CPU_DEAD: - migrate_hrtimers(cpu); + case CPU_DEAD_FROZEN: + { + clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu); + migrate_hrtimers(scpu); break; + } #endif default: @@ -866,7 +1734,7 @@ static int hrtimer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block hrtimers_nb = { +static struct notifier_block __cpuinitdata hrtimers_nb = { .notifier_call = hrtimer_cpu_notify, }; @@ -875,5 +1743,108 @@ void __init hrtimers_init(void) hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); +#ifdef CONFIG_HIGH_RES_TIMERS + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); +#endif +} + +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && !expires->tv64) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "inifinte" + */ + if (!expires) { + schedule(); + __set_current_state(TASK_RUNNING); + return -EINTR; + } + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + + hrtimer_init_sleeper(&t, current); + + hrtimer_start_expires(&t.timer, mode); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; } +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout(ktime_t *expires, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout);