X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftimer.c;h=e3b8c697bde44b75b76fb23c059a4b4a3942411d;hb=cc106eb35ed4abea675bce0d8fe40a46ff0b4a72;hp=672ca25fbc43a9c151f48be2ec6fab222337d357;hpb=925d519ab82b6dd7aca9420d809ee83819c08db2;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/timer.c b/kernel/timer.c index 672ca25..e3b8c69 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -37,7 +37,9 @@ #include #include #include -#include +#include +#include +#include #include #include @@ -45,6 +47,9 @@ #include #include +#define CREATE_TRACE_POINTS +#include + u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); @@ -71,6 +76,7 @@ struct tvec_base { spinlock_t lock; struct timer_list *running_timer; unsigned long timer_jiffies; + unsigned long next_timer; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -313,6 +319,24 @@ unsigned long round_jiffies_up_relative(unsigned long j) } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); +/** + * set_timer_slack - set the allowed slack for a timer + * @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 inline void set_running_timer(struct tvec_base *base, struct timer_list *timer) @@ -379,6 +403,8 @@ static void timer_stats_account_timer(struct timer_list *timer) { unsigned int flag = 0; + if (likely(!timer->start_site)) + return; if (unlikely(tbase_get_deferrable(timer->base))) flag |= TIMER_STATS_FLAG_DEFERRABLE; @@ -517,12 +543,32 @@ static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(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); +} + +static inline void debug_deactivate(struct timer_list *timer) +{ + debug_timer_deactivate(timer); + trace_timer_cancel(timer); +} + static void __init_timer(struct timer_list *timer, const char *name, struct lock_class_key *key) { timer->entry.next = NULL; timer->base = __raw_get_cpu_var(tvec_bases); + timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; timer->start_pid = -1; @@ -532,17 +578,20 @@ static void __init_timer(struct timer_list *timer, } /** - * init_timer - initialize a timer. + * init_timer_key - initialize a timer * @timer: the timer to be initialized + * @name: name of the timer + * @key: lockdep class key of the fake lock used for tracking timer + * sync lock dependencies * - * init_timer() must be done to a timer prior calling *any* of the + * 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, const char *name, struct lock_class_key *key) { - debug_timer_init(timer); + debug_init(timer); __init_timer(timer, name, key); } EXPORT_SYMBOL(init_timer_key); @@ -561,7 +610,7 @@ static inline void detach_timer(struct timer_list *timer, { struct list_head *entry = &timer->entry; - debug_timer_deactivate(timer); + debug_deactivate(timer); __list_del(entry->prev, entry->next); if (clear_pending) @@ -602,13 +651,12 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) +__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; - - ret = 0; + int ret = 0 , cpu; timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); @@ -617,15 +665,28 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) if (timer_pending(timer)) { detach_timer(timer, 0); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } else { if (pending_only) goto out_unlock; } - debug_timer_activate(timer); + debug_activate(timer, expires); - new_base = __get_cpu_var(tvec_bases); + cpu = smp_processor_id(); + +#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) + if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) { + int preferred_cpu = get_nohz_load_balancer(); + + if (preferred_cpu >= 0) + cpu = preferred_cpu; + } +#endif + new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { /* @@ -646,6 +707,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } timer->expires = expires; + if (time_before(timer->expires, base->next_timer) && + !tbase_get_deferrable(timer->base)) + base->next_timer = timer->expires; internal_add_timer(base, timer); out_unlock: @@ -666,10 +730,46 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true); + 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; + + expires_limit = expires; + + if (timer->slack > -1) + expires_limit = expires + timer->slack; + else if (time_after(expires, jiffies)) /* auto slack: use 0.4% */ + expires_limit = expires + (expires - jiffies)/256; + + mask = expires ^ expires_limit; + if (mask == 0) + return expires; + + bit = find_last_bit(&mask, BITS_PER_LONG); + + mask = (1 << bit) - 1; + + expires_limit = expires_limit & ~(mask); + + return expires_limit; +} + /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified @@ -697,14 +797,38 @@ int mod_timer(struct timer_list *timer, unsigned long expires) * networking code - if the timer is re-modified * to be the same thing then just return: */ - if (timer->expires == expires && timer_pending(timer)) + if (timer_pending(timer) && timer->expires == expires) return 1; - return __mod_timer(timer, expires, false); + expires = apply_slack(timer, expires); + + 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 not allow the timer to be migrated to a different CPU. + * + * 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 * @@ -741,7 +865,10 @@ void add_timer_on(struct timer_list *timer, int cpu) BUG_ON(timer_pending(timer) || !timer->function); spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); - debug_timer_activate(timer); + debug_activate(timer, timer->expires); + if (time_before(timer->expires, base->next_timer) && + !tbase_get_deferrable(timer->base)) + base->next_timer = timer->expires; internal_add_timer(base, timer); /* * Check whether the other CPU is idle and needs to be @@ -754,6 +881,7 @@ void add_timer_on(struct timer_list *timer, int cpu) wake_up_idle_cpu(cpu); spin_unlock_irqrestore(&base->lock, flags); } +EXPORT_SYMBOL_GPL(add_timer_on); /** * del_timer - deactive a timer. @@ -777,6 +905,9 @@ int del_timer(struct timer_list *timer) base = lock_timer_base(timer, &flags); if (timer_pending(timer)) { detach_timer(timer, 1); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } spin_unlock_irqrestore(&base->lock, flags); @@ -807,9 +938,13 @@ int try_to_del_timer_sync(struct timer_list *timer) if (base->running_timer == timer) goto out; + timer_stats_timer_clear_start_info(timer); ret = 0; if (timer_pending(timer)) { detach_timer(timer, 1); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } out: @@ -877,6 +1012,47 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index) return index; } +static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), + unsigned long data) +{ + int preempt_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 = 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 (preempt_count != preempt_count()) { + WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n", + fn, preempt_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() = preempt_count; + } +} + #define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) /** @@ -920,43 +1096,7 @@ static inline void __run_timers(struct tvec_base *base) detach_timer(timer, 1); spin_unlock_irq(&base->lock); - { - int preempt_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 = - 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); - - fn(data); - - lock_map_release(&lockdep_map); - - if (preempt_count != preempt_count()) { - printk(KERN_ERR "huh, entered %p " - "with preempt_count %08x, exited" - " with %08x?\n", - fn, preempt_count, - preempt_count()); - BUG(); - } - } + call_timer_fn(timer, fn, data); spin_lock_irq(&base->lock); } } @@ -967,8 +1107,8 @@ static inline void __run_timers(struct tvec_base *base) #ifdef CONFIG_NO_HZ /* * Find out when the next timer event is due to happen. This - * is used on S/390 to stop all activity when a cpus is idle. - * This functions needs to be called disabled. + * 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) { @@ -1013,6 +1153,9 @@ cascade: index = slot = timer_jiffies & TVN_MASK; do { list_for_each_entry(nte, varp->vec + slot, entry) { + if (tbase_get_deferrable(nte->base)) + continue; + found = 1; if (time_before(nte->expires, expires)) expires = nte->expires; @@ -1091,7 +1234,9 @@ unsigned long get_next_timer_interrupt(unsigned long now) unsigned long expires; spin_lock(&base->lock); - expires = __next_timer_interrupt(base); + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; spin_unlock(&base->lock); if (time_before_eq(expires, now)) @@ -1113,63 +1258,20 @@ void update_process_times(int user_tick) /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); - if (rcu_pending(cpu)) - rcu_check_callbacks(cpu, user_tick); + rcu_check_callbacks(cpu, user_tick); printk_tick(); + perf_event_do_pending(); scheduler_tick(); run_posix_cpu_timers(p); } /* - * Nr of active tasks - counted in fixed-point numbers - */ -static unsigned long count_active_tasks(void) -{ - return nr_active() * FIXED_1; -} - -/* - * Hmm.. Changed this, as the GNU make sources (load.c) seems to - * imply that avenrun[] is the standard name for this kind of thing. - * Nothing else seems to be standardized: the fractional size etc - * all seem to differ on different machines. - * - * Requires xtime_lock to access. - */ -unsigned long avenrun[3]; - -EXPORT_SYMBOL(avenrun); - -/* - * calc_load - given tick count, update the avenrun load estimates. - * This is called while holding a write_lock on xtime_lock. - */ -static inline void calc_load(unsigned long ticks) -{ - unsigned long active_tasks; /* fixed-point */ - static int count = LOAD_FREQ; - - count -= ticks; - if (unlikely(count < 0)) { - active_tasks = count_active_tasks(); - do { - CALC_LOAD(avenrun[0], EXP_1, active_tasks); - CALC_LOAD(avenrun[1], EXP_5, active_tasks); - CALC_LOAD(avenrun[2], EXP_15, active_tasks); - count += LOAD_FREQ; - } while (count < 0); - } -} - -/* * 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 = __get_cpu_var(tvec_bases); - perf_counter_do_pending(); - hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) @@ -1187,16 +1289,6 @@ void run_local_timers(void) } /* - * Called by the timer interrupt. xtime_lock must already be taken - * by the timer IRQ! - */ -static inline void update_times(unsigned long ticks) -{ - update_wall_time(); - calc_load(ticks); -} - -/* * The 64-bit jiffies value is not atomic - you MUST NOT read it * without sampling the sequence number in xtime_lock. * jiffies is defined in the linker script... @@ -1205,7 +1297,8 @@ static inline void update_times(unsigned long ticks) void do_timer(unsigned long ticks) { jiffies_64 += ticks; - update_times(ticks); + update_wall_time(); + calc_global_load(); } #ifdef __ARCH_WANT_SYS_ALARM @@ -1353,7 +1446,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false); + __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); schedule(); del_singleshot_timer_sync(&timer); @@ -1406,37 +1499,17 @@ int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; - unsigned long seq; + struct timespec tp; memset(info, 0, sizeof(struct sysinfo)); - do { - struct timespec tp; - seq = read_seqbegin(&xtime_lock); + ktime_get_ts(&tp); + monotonic_to_bootbased(&tp); + info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); - /* - * This is annoying. The below is the same thing - * posix_get_clock_monotonic() does, but it wants to - * take the lock which we want to cover the loads stuff - * too. - */ + get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); - getnstimeofday(&tp); - tp.tv_sec += wall_to_monotonic.tv_sec; - tp.tv_nsec += wall_to_monotonic.tv_nsec; - monotonic_to_bootbased(&tp); - if (tp.tv_nsec - NSEC_PER_SEC >= 0) { - tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC; - tp.tv_sec++; - } - info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); - - info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT); - info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT); - info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT); - - info->procs = nr_threads; - } while (read_seqretry(&xtime_lock, seq)); + info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); @@ -1550,6 +1623,7 @@ static int __cpuinit init_timers_cpu(int cpu) INIT_LIST_HEAD(base->tv1.vec + j); base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; return 0; } @@ -1562,6 +1636,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea timer = list_first_entry(head, struct timer_list, entry); detach_timer(timer, 0); timer_set_base(timer, new_base); + if (time_before(timer->expires, new_base->next_timer) && + !tbase_get_deferrable(timer->base)) + new_base->next_timer = timer->expires; internal_add_timer(new_base, timer); } } @@ -1603,11 +1680,14 @@ static int __cpuinit timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; + int err; + switch(action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - if (init_timers_cpu(cpu) < 0) - return NOTIFY_BAD; + err = init_timers_cpu(cpu); + if (err < 0) + return notifier_from_errno(err); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: