/* * linux/kernel/timer.c * * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "tick-internal.h" #define CREATE_TRACE_POINTS #include __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * per-CPU timer vector definitions: */ #define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6) #define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8) #define TVN_SIZE (1 << TVN_BITS) #define TVR_SIZE (1 << TVR_BITS) #define TVN_MASK (TVN_SIZE - 1) #define TVR_MASK (TVR_SIZE - 1) #define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) struct tvec { struct hlist_head vec[TVN_SIZE]; }; struct tvec_root { struct hlist_head vec[TVR_SIZE]; }; struct tvec_base { spinlock_t lock; struct timer_list *running_timer; unsigned long timer_jiffies; unsigned long next_timer; unsigned long active_timers; unsigned long all_timers; int cpu; bool migration_enabled; bool nohz_active; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; struct tvec tv4; struct tvec tv5; } ____cacheline_aligned; static DEFINE_PER_CPU(struct tvec_base, tvec_bases); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) unsigned int sysctl_timer_migration = 1; void timers_update_migration(bool update_nohz) { bool on = sysctl_timer_migration && tick_nohz_active; unsigned int cpu; /* Avoid the loop, if nothing to update */ if (this_cpu_read(tvec_bases.migration_enabled) == on) return; for_each_possible_cpu(cpu) { per_cpu(tvec_bases.migration_enabled, cpu) = on; per_cpu(hrtimer_bases.migration_enabled, cpu) = on; if (!update_nohz) continue; per_cpu(tvec_bases.nohz_active, cpu) = true; per_cpu(hrtimer_bases.nohz_active, cpu) = true; } } int timer_migration_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { static DEFINE_MUTEX(mutex); int ret; mutex_lock(&mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(false); mutex_unlock(&mutex); return ret; } static inline struct tvec_base *get_target_base(struct tvec_base *base, int pinned) { if (pinned || !base->migration_enabled) return this_cpu_ptr(&tvec_bases); return per_cpu_ptr(&tvec_bases, get_nohz_timer_target()); } #else static inline struct tvec_base *get_target_base(struct tvec_base *base, int pinned) { return this_cpu_ptr(&tvec_bases); } #endif static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffie is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, false); } EXPORT_SYMBOL_GPL(__round_jiffies); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, true); } EXPORT_SYMBOL_GPL(__round_jiffies_up); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); /** * set_timer_slack - set the allowed slack for a timer * @timer: the timer to be modified * @slack_hz: the amount of time (in jiffies) allowed for rounding * * Set the amount of time, in jiffies, that a certain timer has * in terms of slack. By setting this value, the timer subsystem * will schedule the actual timer somewhere between * the time mod_timer() asks for, and that time plus the slack. * * By setting the slack to -1, a percentage of the delay is used * instead. */ void set_timer_slack(struct timer_list *timer, int slack_hz) { timer->slack = slack_hz; } EXPORT_SYMBOL_GPL(set_timer_slack); static void __internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; unsigned long idx = expires - base->timer_jiffies; struct hlist_head *vec; if (idx < TVR_SIZE) { int i = expires & TVR_MASK; vec = base->tv1.vec + i; } else if (idx < 1 << (TVR_BITS + TVN_BITS)) { int i = (expires >> TVR_BITS) & TVN_MASK; vec = base->tv2.vec + i; } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) { int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK; vec = base->tv3.vec + i; } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) { int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK; vec = base->tv4.vec + i; } else if ((signed long) idx < 0) { /* * Can happen if you add a timer with expires == jiffies, * or you set a timer to go off in the past */ vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); } else { int i; /* If the timeout is larger than MAX_TVAL (on 64-bit * architectures or with CONFIG_BASE_SMALL=1) then we * use the maximum timeout. */ if (idx > MAX_TVAL) { idx = MAX_TVAL; expires = idx + base->timer_jiffies; } i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; vec = base->tv5.vec + i; } hlist_add_head(&timer->entry, vec); } static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { /* Advance base->jiffies, if the base is empty */ if (!base->all_timers++) base->timer_jiffies = jiffies; __internal_add_timer(base, timer); /* * Update base->active_timers and base->next_timer */ if (!(timer->flags & TIMER_DEFERRABLE)) { if (!base->active_timers++ || time_before(timer->expires, base->next_timer)) base->next_timer = timer->expires; } /* * Check whether the other CPU is in dynticks mode and needs * to be triggered to reevaluate the timer wheel. * We are protected against the other CPU fiddling * with the timer by holding the timer base lock. This also * makes sure that a CPU on the way to stop its tick can not * evaluate the timer wheel. * * Spare the IPI for deferrable timers on idle targets though. * The next busy ticks will take care of it. Except full dynticks * require special care against races with idle_cpu(), lets deal * with that later. */ if (base->nohz_active) { if (!(timer->flags & TIMER_DEFERRABLE) || tick_nohz_full_cpu(base->cpu)) wake_up_nohz_cpu(base->cpu); } } #ifdef CONFIG_TIMER_STATS void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) { if (timer->start_site) return; timer->start_site = addr; memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); timer->start_pid = current->pid; } static void timer_stats_account_timer(struct timer_list *timer) { void *site; /* * start_site can be concurrently reset by * timer_stats_timer_clear_start_info() */ site = READ_ONCE(timer->start_site); if (likely(!site)) return; timer_stats_update_stats(timer, timer->start_pid, site, timer->function, timer->start_comm, timer->flags); } #else static void timer_stats_account_timer(struct timer_list *timer) {} #endif #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static struct debug_obj_descr timer_debug_descr; static void *timer_debug_hint(void *addr) { return ((struct timer_list *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(unsigned long data) { WARN_ON(1); } /* * fixup_activate is called when: * - an active object is activated * - an unknown object is activated (might be a statically initialized object) */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: /* * This is not really a fixup. The timer was * statically initialized. We just make sure that it * is tracked in the object tracker. */ if (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC) { debug_object_init(timer, &timer_debug_descr); debug_object_activate(timer, &timer_debug_descr); return false; } else { setup_timer(timer, stub_timer, 0); return true; } return false; case ODEBUG_STATE_ACTIVE: WARN_ON(1); default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * 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) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: if (timer->entry.next == TIMER_ENTRY_STATIC) { /* * This is not really a fixup. The timer was * statically initialized. We just make sure that it * is tracked in the object tracker. */ debug_object_init(timer, &timer_debug_descr); return false; } else { setup_timer(timer, stub_timer, 0); return true; } default: return false; } } static struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_free(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_timer_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_activate(struct timer_list *timer, unsigned long expires) { debug_timer_activate(timer); trace_timer_start(timer, expires, timer->flags); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->flags = flags | raw_smp_processor_id(); timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; timer->start_pid = -1; memset(timer->start_comm, 0, TASK_COMM_LEN); #endif lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @flags: timer flags * @name: name of the 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 * other timer functions. */ void init_timer_key(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, flags, name, key); } EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static inline void detach_expired_timer(struct timer_list *timer, struct tvec_base *base) { detach_timer(timer, true); if (!(timer->flags & TIMER_DEFERRABLE)) base->active_timers--; base->all_timers--; } static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, bool clear_pending) { if (!timer_pending(timer)) return 0; detach_timer(timer, clear_pending); if (!(timer->flags & TIMER_DEFERRABLE)) { base->active_timers--; if (timer->expires == base->next_timer) base->next_timer = base->timer_jiffies; } /* If this was the last timer, advance base->jiffies */ if (!--base->all_timers) base->timer_jiffies = jiffies; return 1; } /* * We are using hashed locking: holding per_cpu(tvec_bases).lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on ->tvX lists. * * When the timer's base is locked and removed from the list, the * TIMER_MIGRATING flag is set, FIXME */ static struct tvec_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { u32 tf = timer->flags; struct tvec_base *base; if (!(tf & TIMER_MIGRATING)) { base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK); spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } static inline int __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only, int pinned) { struct tvec_base *base, *new_base; unsigned long flags; int ret = 0; timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, false); if (!ret && pending_only) goto out_unlock; debug_activate(timer, expires); new_base = get_target_base(base, pinned); if (base != new_base) { /* * We are trying to schedule the timer on the local CPU. * However we can't change timer's base while it is running, * otherwise del_timer_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that * the timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; spin_unlock(&base->lock); base = new_base; spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); } } timer->expires = expires; internal_add_timer(base, timer); out_unlock: spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - modify a pending timer's timeout * @timer: the pending timer to be modified * @expires: new timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), * but will not re-activate and modify already deleted timers. * * It is useful for unserialized use of timers. */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); } EXPORT_SYMBOL(mod_timer_pending); /* * Decide where to put the timer while taking the slack into account * * Algorithm: * 1) calculate the maximum (absolute) time * 2) calculate the highest bit where the expires and new max are different * 3) use this bit to make a mask * 4) use the bitmask to round down the maximum time, so that all last * bits are zeros */ static inline unsigned long apply_slack(struct timer_list *timer, unsigned long expires) { unsigned long expires_limit, mask; int bit; if (timer->slack >= 0) { expires_limit = expires + timer->slack; } else { long delta = expires - jiffies; if (delta < 256) return expires; expires_limit = expires + delta / 256; } mask = expires ^ expires_limit; if (mask == 0) return expires; bit = __fls(mask); mask = (1UL << bit) - 1; expires_limit = expires_limit & ~(mask); return expires_limit; } /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified * @expires: new timeout in jiffies * * mod_timer() is a more efficient way to update the expire field of an * active timer (if the timer is inactive it will be activated) * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * The function returns whether it has modified a pending timer or not. * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an * active timer returns 1.) */ int mod_timer(struct timer_list *timer, unsigned long expires) { expires = apply_slack(timer, expires); /* * This is a common optimization triggered by the * networking code - if the timer is re-modified * to be the same thing then just return: */ if (timer_pending(timer) && timer->expires == expires) return 1; return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); } EXPORT_SYMBOL(mod_timer); /** * mod_timer_pinned - modify a timer's timeout * @timer: the timer to be modified * @expires: new timeout in jiffies * * mod_timer_pinned() is a way to update the expire field of an * active timer (if the timer is inactive it will be activated) * and to ensure that the timer is scheduled on the current CPU. * * Note that this does not prevent the timer from being migrated * when the current CPU goes offline. If this is a problem for * you, use CPU-hotplug notifiers to handle it correctly, for * example, cancelling the timer when the corresponding CPU goes * offline. * * mod_timer_pinned(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); */ int mod_timer_pinned(struct timer_list *timer, unsigned long expires) { if (timer->expires == expires && timer_pending(timer)) return 1; return __mod_timer(timer, expires, false, TIMER_PINNED); } EXPORT_SYMBOL(mod_timer_pinned); /** * add_timer - start a timer * @timer: the timer to be added * * The kernel will do a ->function(->data) callback from the * timer interrupt at the ->expires point in the future. The * current time is 'jiffies'. * * The timer's ->expires, ->function (and if the handler uses it, ->data) * fields must be set prior calling this function. * * Timers with an ->expires field in the past will be executed in the next * timer tick. */ void add_timer(struct timer_list *timer) { BUG_ON(timer_pending(timer)); mod_timer(timer, timer->expires); } EXPORT_SYMBOL(add_timer); /** * add_timer_on - start a timer on a particular CPU * @timer: the timer to be added * @cpu: the CPU to start it on * * This is not very scalable on SMP. Double adds are not possible. */ void add_timer_on(struct timer_list *timer, int cpu) { struct tvec_base *new_base = per_cpu_ptr(&tvec_bases, cpu); struct tvec_base *base; unsigned long flags; timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); if (base != new_base) { timer->flags |= TIMER_MIGRATING; spin_unlock(&base->lock); base = new_base; spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } debug_activate(timer, timer->expires); internal_add_timer(base, timer); spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * del_timer - deactive a timer. * @timer: the timer to be deactivated * * del_timer() deactivates a timer - this works on both active and inactive * timers. * * The function returns whether it has deactivated a pending timer or not. * (ie. del_timer() of an inactive timer returns 0, del_timer() of an * active timer returns 1.) */ int del_timer(struct timer_list *timer) { struct tvec_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); spin_unlock_irqrestore(&base->lock, flags); } return ret; } EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: timer do del * * This function tries to deactivate a timer. Upon successful (ret >= 0) * exit the timer is not queued and the handler is not running on any CPU. */ int try_to_del_timer_sync(struct timer_list *timer) { struct tvec_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) { timer_stats_timer_clear_start_info(timer); ret = detach_if_pending(timer, base, true); } spin_unlock_irqrestore(&base->lock, flags); return ret; } EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_SMP /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated * * This function only differs from del_timer() on SMP: besides deactivating * the timer it also makes sure the handler has finished executing on other * CPUs. * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's * handler. The timer's handler must not call add_timer_on(). Upon exit the * timer is not queued and the handler is not running on any CPU. * * Note: For !irqsafe timers, you must not hold locks that are held in * interrupt context while calling this function. Even if the lock has * nothing to do with the timer in question. Here's why: * * CPU0 CPU1 * ---- ---- * * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * * spin_lock(somelock); * del_timer_sync(mytimer); * while (base->running_timer == mytimer); * * Now del_timer_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but * it has interrupted the softirq that CPU0 is waiting to finish. * * The function returns whether it has deactivated a pending timer or not. */ int del_timer_sync(struct timer_list *timer) { #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; cpu_relax(); } } EXPORT_SYMBOL(del_timer_sync); #endif static int cascade(struct tvec_base *base, struct tvec *tv, int index) { /* cascade all the timers from tv up one level */ struct timer_list *timer; struct hlist_node *tmp; struct hlist_head tv_list; hlist_move_list(tv->vec + index, &tv_list); /* * We are removing _all_ timers from the list, so we * don't have to detach them individually. */ hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) { /* No accounting, while moving them */ __internal_add_timer(base, timer); } return index; } static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), unsigned long data) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * del_timer_sync() by acquiring the lock_map around the fn() * call here and in del_timer_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer); fn(data); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } #define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. * * This function cascades all vectors and executes all expired timer * vectors. */ static inline void __run_timers(struct tvec_base *base) { struct timer_list *timer; spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->timer_jiffies)) { struct hlist_head work_list; struct hlist_head *head = &work_list; int index; if (!base->all_timers) { base->timer_jiffies = jiffies; break; } index = base->timer_jiffies & TVR_MASK; /* * Cascade timers: */ if (!index && (!cascade(base, &base->tv2, INDEX(0))) && (!cascade(base, &base->tv3, INDEX(1))) && !cascade(base, &base->tv4, INDEX(2))) cascade(base, &base->tv5, INDEX(3)); ++base->timer_jiffies; hlist_move_list(base->tv1.vec + index, head); while (!hlist_empty(head)) { void (*fn)(unsigned long); unsigned long data; bool irqsafe; timer = hlist_entry(head->first, struct timer_list, entry); fn = timer->function; data = timer->data; irqsafe = timer->flags & TIMER_IRQSAFE; timer_stats_account_timer(timer); base->running_timer = timer; detach_expired_timer(timer, base); if (irqsafe) { spin_unlock(&base->lock); call_timer_fn(timer, fn, data); spin_lock(&base->lock); } else { spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); spin_lock_irq(&base->lock); } } } base->running_timer = NULL; spin_unlock_irq(&base->lock); } #ifdef CONFIG_NO_HZ_COMMON /* * Find out when the next timer event is due to happen. This * is used on S/390 to stop all activity when a CPU is idle. * This function needs to be called with interrupts disabled. */ static unsigned long __next_timer_interrupt(struct tvec_base *base) { unsigned long timer_jiffies = base->timer_jiffies; unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA; int index, slot, array, found = 0; struct timer_list *nte; struct tvec *varray[4]; /* Look for timer events in tv1. */ index = slot = timer_jiffies & TVR_MASK; do { hlist_for_each_entry(nte, base->tv1.vec + slot, entry) { if (nte->flags & TIMER_DEFERRABLE) continue; found = 1; expires = nte->expires; /* Look at the cascade bucket(s)? */ if (!index || slot < index) goto cascade; return expires; } slot = (slot + 1) & TVR_MASK; } while (slot != index); cascade: /* Calculate the next cascade event */ if (index) timer_jiffies += TVR_SIZE - index; timer_jiffies >>= TVR_BITS; /* Check tv2-tv5. */ varray[0] = &base->tv2; varray[1] = &base->tv3; varray[2] = &base->tv4; varray[3] = &base->tv5; for (array = 0; array < 4; array++) { struct tvec *varp = varray[array]; index = slot = timer_jiffies & TVN_MASK; do { hlist_for_each_entry(nte, varp->vec + slot, entry) { if (nte->flags & TIMER_DEFERRABLE) continue; found = 1; if (time_before(nte->expires, expires)) expires = nte->expires; } /* * Do we still search for the first timer or are * we looking up the cascade buckets ? */ if (found) { /* Look at the cascade bucket(s)? */ if (!index || slot < index) break; return expires; } slot = (slot + 1) & TVN_MASK; } while (slot != index); if (index) timer_jiffies += TVN_SIZE - index; timer_jiffies >>= TVN_BITS; } return expires; } /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffie. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } /** * 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. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { struct tvec_base *base = this_cpu_ptr(&tvec_bases); u64 expires = KTIME_MAX; unsigned long nextevt; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) return expires; spin_lock(&base->lock); if (base->active_timers) { if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); nextevt = base->next_timer; if (time_before_eq(nextevt, basej)) expires = basem; else expires = basem + (nextevt - basej) * TICK_NSEC; } spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } #endif /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_check_callbacks(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif scheduler_tick(); run_posix_cpu_timers(p); } /* * This function runs timers and the timer-tq in bottom half context. */ static void run_timer_softirq(struct softirq_action *h) { struct tvec_base *base = this_cpu_ptr(&tvec_bases); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } /* * Called by the local, per-CPU timer interrupt on SMP. */ void run_local_timers(void) { hrtimer_run_queues(); raise_softirq(TIMER_SOFTIRQ); } #ifdef __ARCH_WANT_SYS_ALARM /* * For backwards compatibility? This can be done in libc so Alpha * and all newer ports shouldn't need it. */ SYSCALL_DEFINE1(alarm, unsigned int, seconds) { return alarm_setitimer(seconds); } #endif static void process_timeout(unsigned long __data) { wake_up_process((struct task_struct *)__data); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have * 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 jiffies are guaranteed to * pass before the routine returns. The routine will return 0 * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task. In this case the remaining time * in jiffies will be returned, or 0 if the timer expired in time * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * In all cases the return value is guaranteed to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct timer_list timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { printk(KERN_ERR "schedule_timeout: wrong timeout " "value %lx\n", timeout); dump_stack(); current->state = TASK_RUNNING; goto out; } } expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); schedule(); del_singleshot_timer_sync(&timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* * Like schedule_timeout_uninterruptible(), except this task will not contribute * to load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); /* We ignore the accounting on the dying cpu */ detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } static void migrate_timers(int cpu) { struct tvec_base *old_base; struct tvec_base *new_base; int i; BUG_ON(cpu_online(cpu)); old_base = per_cpu_ptr(&tvec_bases, cpu); new_base = get_cpu_ptr(&tvec_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); for (i = 0; i < TVR_SIZE; i++) migrate_timer_list(new_base, old_base->tv1.vec + i); for (i = 0; i < TVN_SIZE; i++) { migrate_timer_list(new_base, old_base->tv2.vec + i); migrate_timer_list(new_base, old_base->tv3.vec + i); migrate_timer_list(new_base, old_base->tv4.vec + i); migrate_timer_list(new_base, old_base->tv5.vec + i); } old_base->active_timers = 0; old_base->all_timers = 0; spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); put_cpu_ptr(&tvec_bases); } static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { switch (action) { case CPU_DEAD: case CPU_DEAD_FROZEN: migrate_timers((long)hcpu); break; default: break; } return NOTIFY_OK; } static inline void timer_register_cpu_notifier(void) { cpu_notifier(timer_cpu_notify, 0); } #else static inline void timer_register_cpu_notifier(void) { } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu); base->cpu = cpu; spin_lock_init(&base->lock); base->timer_jiffies = jiffies; base->next_timer = base->timer_jiffies; } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init init_timers(void) { init_timer_cpus(); init_timer_stats(); timer_register_cpu_notifier(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); static void __sched do_usleep_range(unsigned long min, unsigned long max) { ktime_t kmin; u64 delta; kmin = ktime_set(0, min * NSEC_PER_USEC); delta = (u64)(max - min) * NSEC_PER_USEC; schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); } /** * usleep_range - Drop in replacement for udelay where wakeup is flexible * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep */ void __sched usleep_range(unsigned long min, unsigned long max) { __set_current_state(TASK_UNINTERRUPTIBLE); do_usleep_range(min, max); } EXPORT_SYMBOL(usleep_range);