*/ if (time_before_eq(nextevt, basej + 1)) { /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * This is required for the remote check only but it doesn't * hurt, when it is done for both call sites: * * * The remote callers will only take care of the global timers * as local timers will be handled by CPU itself. When not * updating tevt->global with the already missed first global * timer, it is possible that it will be missed completely. * * * The local callers will ignore the tevt->global anyway, when * nextevt is max. one tick away. */ if (!local_first) tevt->global = tevt->local; return nextevt; } /* * Update tevt.* values: * * If the local queue expires first, then the global event can be * ignored. If the global queue is empty, nothing to do either. */ if (!local_first && base_global->timers_pending) tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; if (base_local->timers_pending) tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; return nextevt;} # ifdef CONFIG_SMP/** * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic * @tevt: Pointer to the storage for the expiry values * @cpu: Remote CPU * * Stores the next pending local and global timer expiry values in the * struct pointed to by @tevt. If a queue is empty the corresponding * field is set to KTIME_MAX. If local event expires before global * event, global event is set to KTIME_MAX as well. * * Caller needs to make sure timer base locks are held (use * timer_lock_remote_bases() for this purpose). */void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, struct timer_events *tevt, unsigned int cpu){ struct timer_base *base_local, *base_global; /* Preset local / global events */ tevt->local = tevt->global = KTIME_MAX; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_held(&base_local->lock); lockdep_assert_held(&base_global->lock); fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt);} /** * timer_unlock_remote_bases - unlock timer bases of cpu * @cpu: Remote CPU * * Unlocks the remote timer bases. */void timer_unlock_remote_bases(unsigned int cpu) __releases(timer_bases[BASE_LOCAL]->lock) __releases(timer_bases[BASE_GLOBAL]->lock){ struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock);} /** * timer_lock_remote_bases - lock timer bases of cpu * @cpu: Remote CPU * * Locks the remote timer bases. */void timer_lock_remote_bases(unsigned int cpu) __acquires(timer_bases[BASE_LOCAL]->lock) __acquires(timer_bases[BASE_GLOBAL]->lock){ struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_irqs_disabled(); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);} /** * timer_base_is_idle() - Return whether timer base is set idle * * Returns value of local timer base is_idle value. */bool timer_base_is_idle(void){ return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle);} static void __run_timer_base(struct timer_base *base); /** * timer_expire_remote() - expire global timers of cpu * @cpu: Remote CPU * * Expire timers of global base of remote CPU. */void timer_expire_remote(unsigned int cpu){ struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); __run_timer_base(base);} static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt){ u64 next_tmigr; if (timer_base_idle) next_tmigr = tmigr_cpu_new_timer(tevt->global); else if (tick_stop_path) next_tmigr = tmigr_cpu_deactivate(tevt->global); else next_tmigr = tmigr_quick_check(tevt->global); /* * If the CPU is the last going idle in timer migration hierarchy, make * sure the CPU will wake up in time to handle remote timers. * next_tmigr == KTIME_MAX if other CPUs are still active. */ if (next_tmigr < tevt->local) { u64 tmp; /* If we missed a tick already, force 0 delta */ if (next_tmigr < basem) next_tmigr = basem; tmp = div_u64(next_tmigr - basem, TICK_NSEC); *nextevt = basej + (unsigned long)tmp; tevt->local = next_tmigr; }}# elsestatic void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt){ /* * Make sure first event is written into tevt->local to not miss a * timer on !SMP systems. */ tevt->local = min_t(u64, tevt->local, tevt->global);}# endif /* CONFIG_SMP */ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle){ struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; struct timer_base *base_local, *base_global; unsigned long nextevt; bool idle_is_possible; /* * When the CPU is offline, the tick is cancelled and nothing is supposed * to try to stop it. */ if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { if (idle) *idle = true; return tevt.local; } base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); nextevt = fetch_next_timer_interrupt(basej, basem, base_local, base_global, &tevt); /* * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. * * The proper timer migration hierarchy function depends on the callsite * and whether timer base is idle or not. @nextevt will be updated when * this CPU needs to handle the first timer migration hierarchy * event. See timer_use_tmigr() for detailed information. */ idle_is_possible = time_after(nextevt, basej + 1); if (idle_is_possible) timer_use_tmigr(basej, basem, &nextevt, idle, base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ __forward_timer_base(base_local, basej); __forward_timer_base(base_global, basej); /* * Set base->is_idle only when caller is timer_base_try_to_set_idle() */ if (idle) { /* * Bases are idle if the next event is more than a tick * away. Caution: @nextevt could have changed by enqueueing a * global timer into timer migration hierarchy. Therefore a new * check is required here. * * If the base is marked idle then any timer add operation must * forward the base clk itself to keep granularity small. This * idle logic is only maintained for the BASE_LOCAL and * BASE_GLOBAL base, deferrable timers may still see large * granularity skew (by design). */ if (!base_local->is_idle && time_after(nextevt, basej + 1)) { base_local->is_idle = true; /* * Global timers queued locally while running in a task * in nohz_full mode need a self-IPI to kick reprogramming * in IRQ tail. */ if (tick_nohz_full_cpu(base_local->cpu)) base_global->is_idle = true; trace_timer_base_idle(true, base_local->cpu); } *idle = base_local->is_idle; /* * When timer base is not set idle, undo the effect of * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be * changed here. */ if (!base_local->is_idle && idle_is_possible) tmigr_cpu_activate(); } raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); return cmp_next_hrtimer_event(basem, tevt.local);} /** * get_next_timer_interrupt() - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. If timer of global base was queued into * timer migration hierarchy, first global timer is not taken into account. If * it was the last CPU of timer migration hierarchy going idle, first global * event is taken into account. */u64 get_next_timer_interrupt(unsigned long basej, u64 basem){ return __get_next_timer_interrupt(basej, basem, NULL);} /** * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases * @basej: base time jiffies * @basem: base time clock monotonic * @idle: pointer to store the value of timer_base->is_idle on return; * *idle contains the information whether tick was already stopped * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is * returned as well. */u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle){ if (*idle) return KTIME_MAX; return __get_next_timer_interrupt(basej, basem, idle);} /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */void timer_clear_idle(void){ int this_cpu = smp_processor_id(); /* * We do this unlocked. The worst outcome is a remote pinned timer * enqueue sending a pointless IPI, but taking the lock would just * make the window for sending the IPI a few instructions smaller * for the cost of taking the lock in the exit from idle * path. Required for BASE_LOCAL only. */ __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); if (tick_nohz_full_cpu(this_cpu)) __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); trace_timer_base_idle(false, this_cpu); /* Activate without holding the timer_base->lock */ tmigr_cpu_activate();}#endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */static inline void __run_timers(struct timer_base *base){ struct hlist_head heads[LVL_DEPTH]; int levels; lockdep_assert_held(&base->lock); if (base->running_timer) return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * TIMER_NEXT_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); /* * While executing timers, base->clk is set 1 offset ahead of * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); }} static void __run_timer_base(struct timer_base *base){ /* Can race against a remote CPU updating next_expiry under the lock */ if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base);} static void run_timer_base(int index){ struct timer_base *base = this_cpu_ptr(&timer_bases[index]); __run_timer_base(base);} /* * This function runs timers and the timer-tq in bottom half context. */static __latent_entropy void run_timer_softirq(void){ run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { run_timer_base(BASE_GLOBAL); run_timer_base(BASE_DEF); if (is_timers_nohz_active()) tmigr_handle_remote(); }} /* * Called by the local, per-CPU timer interrupt on SMP. */static void run_local_timers(void){ struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { /* * Raise the softirq only if required. * * timer_base::next_expiry can be written by a remote CPU while * holding the lock. If this write happens at the same time than * the lockless local read, sanity checker could complain about * data corruption. * * There are two possible situations where * timer_base::next_expiry is written by a remote CPU: * * 1. Remote CPU expires global timers of this CPU and updates * timer_base::next_expiry of BASE_GLOBAL afterwards in * next_timer_interrupt() or timer_recalc_next_expiry(). The * worst outcome is a superfluous raise of the timer softirq * when the not yet updated value is read. * * 2. A new first pinned timer is enqueued by a remote CPU * and therefore timer_base::next_expiry of BASE_LOCAL is * updated. When this update is missed, this isn't a * problem, as an IPI is executed nevertheless when the CPU * was idle before. When the CPU wasn't idle but the update * is missed, then the timer would expire one jiffy late - * bad luck. * * Those unlikely corner cases where the worst outcome is only a * one jiffy delay or a superfluous raise of the softirq are * not that expensive as doing the check always while holding * the lock. * * Possible remote writers are using WRITE_ONCE(). Local reader * uses therefore READ_ONCE(). */ if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_timer_softirq(TIMER_SOFTIRQ); return; } }} /* * 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_sched_clock_irq(user_tick);#ifdef CONFIG_IRQ_WORK if (in_hardirq()) irq_work_tick();#endif sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers();} #ifdef CONFIG_HOTPLUG_CPUstatic void migrate_timer_list(struct timer_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); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); }} int timers_prepare_cpu(unsigned int cpu){Lines 2001–2500 of 2580. Previous lines Load more
*/ if (time_before_eq(nextevt, basej + 1)) { /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * This is required for the remote check only but it doesn't * hurt, when it is done for both call sites: * * * The remote callers will only take care of the global timers * as local timers will be handled by CPU itself. When not * updating tevt->global with the already missed first global * timer, it is possible that it will be missed completely. * * * The local callers will ignore the tevt->global anyway, when * nextevt is max. one tick away. */ if (!local_first) tevt->global = tevt->local; return nextevt; } /* * Update tevt.* values: * * If the local queue expires first, then the global event can be * ignored. If the global queue is empty, nothing to do either. */ if (!local_first && base_global->timers_pending) tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; if (base_local->timers_pending) tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; return nextevt; } # ifdef CONFIG_SMP /** * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic * @tevt: Pointer to the storage for the expiry values * @cpu: Remote CPU * * Stores the next pending local and global timer expiry values in the * struct pointed to by @tevt. If a queue is empty the corresponding * field is set to KTIME_MAX. If local event expires before global * event, global event is set to KTIME_MAX as well. * * Caller needs to make sure timer base locks are held (use * timer_lock_remote_bases() for this purpose). */ void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, struct timer_events *tevt, unsigned int cpu) { struct timer_base *base_local, *base_global; /* Preset local / global events */ tevt->local = tevt->global = KTIME_MAX; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_held(&base_local->lock); lockdep_assert_held(&base_global->lock); fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt); } /** * timer_unlock_remote_bases - unlock timer bases of cpu * @cpu: Remote CPU * * Unlocks the remote timer bases. */ void timer_unlock_remote_bases(unsigned int cpu) __releases(timer_bases[BASE_LOCAL]->lock) __releases(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); } /** * timer_lock_remote_bases - lock timer bases of cpu * @cpu: Remote CPU * * Locks the remote timer bases. */ void timer_lock_remote_bases(unsigned int cpu) __acquires(timer_bases[BASE_LOCAL]->lock) __acquires(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_irqs_disabled(); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); } /** * timer_base_is_idle() - Return whether timer base is set idle * * Returns value of local timer base is_idle value. */ bool timer_base_is_idle(void) { return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); } static void __run_timer_base(struct timer_base *base); /** * timer_expire_remote() - expire global timers of cpu * @cpu: Remote CPU * * Expire timers of global base of remote CPU. */ void timer_expire_remote(unsigned int cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); __run_timer_base(base); } static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { u64 next_tmigr; if (timer_base_idle) next_tmigr = tmigr_cpu_new_timer(tevt->global); else if (tick_stop_path) next_tmigr = tmigr_cpu_deactivate(tevt->global); else next_tmigr = tmigr_quick_check(tevt->global); /* * If the CPU is the last going idle in timer migration hierarchy, make * sure the CPU will wake up in time to handle remote timers. * next_tmigr == KTIME_MAX if other CPUs are still active. */ if (next_tmigr < tevt->local) { u64 tmp; /* If we missed a tick already, force 0 delta */ if (next_tmigr < basem) next_tmigr = basem; tmp = div_u64(next_tmigr - basem, TICK_NSEC); *nextevt = basej + (unsigned long)tmp; tevt->local = next_tmigr; } } # else static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { /* * Make sure first event is written into tevt->local to not miss a * timer on !SMP systems. */ tevt->local = min_t(u64, tevt->local, tevt->global); } # endif /* CONFIG_SMP */ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle) { struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; struct timer_base *base_local, *base_global; unsigned long nextevt; bool idle_is_possible; /* * When the CPU is offline, the tick is cancelled and nothing is supposed * to try to stop it. */ if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { if (idle) *idle = true; return tevt.local; } base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); nextevt = fetch_next_timer_interrupt(basej, basem, base_local, base_global, &tevt); /* * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. * * The proper timer migration hierarchy function depends on the callsite * and whether timer base is idle or not. @nextevt will be updated when * this CPU needs to handle the first timer migration hierarchy * event. See timer_use_tmigr() for detailed information. */ idle_is_possible = time_after(nextevt, basej + 1); if (idle_is_possible) timer_use_tmigr(basej, basem, &nextevt, idle, base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ __forward_timer_base(base_local, basej); __forward_timer_base(base_global, basej); /* * Set base->is_idle only when caller is timer_base_try_to_set_idle() */ if (idle) { /* * Bases are idle if the next event is more than a tick * away. Caution: @nextevt could have changed by enqueueing a * global timer into timer migration hierarchy. Therefore a new * check is required here. * * If the base is marked idle then any timer add operation must * forward the base clk itself to keep granularity small. This * idle logic is only maintained for the BASE_LOCAL and * BASE_GLOBAL base, deferrable timers may still see large * granularity skew (by design). */ if (!base_local->is_idle && time_after(nextevt, basej + 1)) { base_local->is_idle = true; /* * Global timers queued locally while running in a task * in nohz_full mode need a self-IPI to kick reprogramming * in IRQ tail. */ if (tick_nohz_full_cpu(base_local->cpu)) base_global->is_idle = true; trace_timer_base_idle(true, base_local->cpu); } *idle = base_local->is_idle; /* * When timer base is not set idle, undo the effect of * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be * changed here. */ if (!base_local->is_idle && idle_is_possible) tmigr_cpu_activate(); } raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); return cmp_next_hrtimer_event(basem, tevt.local); } /** * get_next_timer_interrupt() - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. If timer of global base was queued into * timer migration hierarchy, first global timer is not taken into account. If * it was the last CPU of timer migration hierarchy going idle, first global * event is taken into account. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { return __get_next_timer_interrupt(basej, basem, NULL); } /** * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases * @basej: base time jiffies * @basem: base time clock monotonic * @idle: pointer to store the value of timer_base->is_idle on return; * *idle contains the information whether tick was already stopped * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is * returned as well. */ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) { if (*idle) return KTIME_MAX; return __get_next_timer_interrupt(basej, basem, idle); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { int this_cpu = smp_processor_id(); /* * We do this unlocked. The worst outcome is a remote pinned timer * enqueue sending a pointless IPI, but taking the lock would just * make the window for sending the IPI a few instructions smaller * for the cost of taking the lock in the exit from idle * path. Required for BASE_LOCAL only. */ __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); if (tick_nohz_full_cpu(this_cpu)) __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); trace_timer_base_idle(false, this_cpu); /* Activate without holding the timer_base->lock */ tmigr_cpu_activate(); } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; lockdep_assert_held(&base->lock); if (base->running_timer) return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * TIMER_NEXT_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); /* * While executing timers, base->clk is set 1 offset ahead of * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); } } static void __run_timer_base(struct timer_base *base) { /* Can race against a remote CPU updating next_expiry under the lock */ if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } static void run_timer_base(int index) { struct timer_base *base = this_cpu_ptr(&timer_bases[index]); __run_timer_base(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { run_timer_base(BASE_GLOBAL); run_timer_base(BASE_DEF); if (is_timers_nohz_active()) tmigr_handle_remote(); } } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { /* * Raise the softirq only if required. * * timer_base::next_expiry can be written by a remote CPU while * holding the lock. If this write happens at the same time than * the lockless local read, sanity checker could complain about * data corruption. * * There are two possible situations where * timer_base::next_expiry is written by a remote CPU: * * 1. Remote CPU expires global timers of this CPU and updates * timer_base::next_expiry of BASE_GLOBAL afterwards in * next_timer_interrupt() or timer_recalc_next_expiry(). The * worst outcome is a superfluous raise of the timer softirq * when the not yet updated value is read. * * 2. A new first pinned timer is enqueued by a remote CPU * and therefore timer_base::next_expiry of BASE_LOCAL is * updated. When this update is missed, this isn't a * problem, as an IPI is executed nevertheless when the CPU * was idle before. When the CPU wasn't idle but the update * is missed, then the timer would expire one jiffy late - * bad luck. * * Those unlikely corner cases where the worst outcome is only a * one jiffy delay or a superfluous raise of the softirq are * not that expensive as doing the check always while holding * the lock. * * Possible remote writers are using WRITE_ONCE(). Local reader * uses therefore READ_ONCE(). */ if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_timer_softirq(TIMER_SOFTIRQ); return; } } } /* * 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_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_hardirq()) irq_work_tick(); #endif sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_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); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) {