X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftimer.c;h=03bc7f1f159350d2ad29ca45d3b3a28fc275f296;hb=36223a399f639b13b7a454349565934e6d3e2db0;hp=f35b3939e9372c5139f0588a9f728b681d225d17;hpb=3439dd86e34580384d3b58cf8d54a9283cd7a342;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/timer.c b/kernel/timer.c index f35b393..03bc7f1 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1,7 +1,7 @@ /* * linux/kernel/timer.c * - * Kernel internal timers, kernel timekeeping, basic process system calls + * Kernel internal timers, basic process system calls * * Copyright (C) 1991, 1992 Linus Torvalds * @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -34,6 +35,8 @@ #include #include #include +#include +#include #include #include @@ -41,12 +44,6 @@ #include #include -#ifdef CONFIG_TIME_INTERPOLATION -static void time_interpolator_update(long delta_nsec); -#else -#define time_interpolator_update(x) -#endif - u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); @@ -61,32 +58,193 @@ EXPORT_SYMBOL(jiffies_64); #define TVN_MASK (TVN_SIZE - 1) #define TVR_MASK (TVR_SIZE - 1) -typedef struct tvec_s { +struct tvec { struct list_head vec[TVN_SIZE]; -} tvec_t; +}; -typedef struct tvec_root_s { +struct tvec_root { struct list_head vec[TVR_SIZE]; -} tvec_root_t; +}; -struct tvec_t_base_s { +struct tvec_base { spinlock_t lock; struct timer_list *running_timer; unsigned long timer_jiffies; - tvec_root_t tv1; - tvec_t tv2; - tvec_t tv3; - tvec_t tv4; - tvec_t tv5; -} ____cacheline_aligned_in_smp; + struct tvec_root tv1; + struct tvec tv2; + struct tvec tv3; + struct tvec tv4; + struct tvec tv5; +} ____cacheline_aligned; + +struct tvec_base boot_tvec_bases; +EXPORT_SYMBOL(boot_tvec_bases); +static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; -typedef struct tvec_t_base_s tvec_base_t; +/* + * Note that all tvec_bases are 2 byte aligned and lower bit of + * base in timer_list is guaranteed to be zero. Use the LSB for + * the new flag to indicate whether the timer is deferrable + */ +#define TBASE_DEFERRABLE_FLAG (0x1) -tvec_base_t boot_tvec_bases; -EXPORT_SYMBOL(boot_tvec_bases); -static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = { &boot_tvec_bases }; +/* Functions below help us manage 'deferrable' flag */ +static inline unsigned int tbase_get_deferrable(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG); +} + +static inline struct tvec_base *tbase_get_base(struct tvec_base *base) +{ + return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG)); +} + +static inline void timer_set_deferrable(struct timer_list *timer) +{ + timer->base = ((struct tvec_base *)((unsigned long)(timer->base) | + TBASE_DEFERRABLE_FLAG)); +} + +static inline void +timer_set_base(struct timer_list *timer, struct tvec_base *new_base) +{ + timer->base = (struct tvec_base *)((unsigned long)(new_base) | + tbase_get_deferrable(timer->base)); +} + +/** + * __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) +{ + 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. + */ + if (rem < HZ/4) /* 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; -static inline void set_running_timer(tvec_base_t *base, + if (j <= jiffies) /* rounding ate our timeout entirely; */ + return original; + return j; +} +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) +{ + /* + * In theory the following code can skip a jiffy in case jiffies + * increments right between the addition and the later subtraction. + * However since the entire point of this function is to use approximate + * timeouts, it's entirely ok to not handle that. + */ + return __round_jiffies(j + jiffies, cpu) - jiffies; +} +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(j, raw_smp_processor_id()); +} +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); + + +static inline void set_running_timer(struct tvec_base *base, struct timer_list *timer) { #ifdef CONFIG_SMP @@ -94,7 +252,7 @@ static inline void set_running_timer(tvec_base_t *base, #endif } -static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) +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; @@ -136,25 +294,194 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) list_add_tail(&timer->entry, vec); } -/*** +#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) +{ + unsigned int flag = 0; + + if (unlikely(tbase_get_deferrable(timer->base))) + flag |= TIMER_STATS_FLAG_DEFERRABLE; + + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm, flag); +} + +#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; + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int 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 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 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.next == NULL && + timer->entry.prev == TIMER_ENTRY_STATIC) { + debug_object_init(timer, &timer_debug_descr); + debug_object_activate(timer, &timer_debug_descr); + return 0; + } else { + 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 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 1; + default: + return 0; + } +} + +static struct debug_obj_descr timer_debug_descr = { + .name = "timer_list", + .fixup_init = timer_fixup_init, + .fixup_activate = timer_fixup_activate, + .fixup_free = timer_fixup_free, +}; + +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 void __init_timer(struct timer_list *timer); + +void init_timer_on_stack(struct timer_list *timer) +{ + debug_object_init_on_stack(timer, &timer_debug_descr); + __init_timer(timer); +} +EXPORT_SYMBOL_GPL(init_timer_on_stack); + +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) { } +#endif + +static void __init_timer(struct timer_list *timer) +{ + timer->entry.next = NULL; + timer->base = __raw_get_cpu_var(tvec_bases); +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; + timer->start_pid = -1; + memset(timer->start_comm, 0, TASK_COMM_LEN); +#endif +} + +/** * init_timer - initialize a timer. * @timer: the timer to be initialized * * init_timer() must be done to a timer prior calling *any* of the * other timer functions. */ -void fastcall init_timer(struct timer_list *timer) +void init_timer(struct timer_list *timer) { - timer->entry.next = NULL; - timer->base = per_cpu(tvec_bases, raw_smp_processor_id()); + debug_timer_init(timer); + __init_timer(timer); } EXPORT_SYMBOL(init_timer); +void init_timer_deferrable(struct timer_list *timer) +{ + init_timer(timer); + timer_set_deferrable(timer); +} +EXPORT_SYMBOL(init_timer_deferrable); + static inline void detach_timer(struct timer_list *timer, - int clear_pending) + int clear_pending) { struct list_head *entry = &timer->entry; + debug_timer_deactivate(timer); + __list_del(entry->prev, entry->next); if (clear_pending) entry->next = NULL; @@ -173,16 +500,18 @@ static inline void detach_timer(struct timer_list *timer, * possible to set timer->base = NULL and drop the lock: the timer remains * locked. */ -static tvec_base_t *lock_timer_base(struct timer_list *timer, +static struct tvec_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) + __acquires(timer->base->lock) { - tvec_base_t *base; + struct tvec_base *base; for (;;) { - base = timer->base; + struct tvec_base *prelock_base = timer->base; + base = tbase_get_base(prelock_base); if (likely(base != NULL)) { spin_lock_irqsave(&base->lock, *flags); - if (likely(base == timer->base)) + if (likely(prelock_base == timer->base)) return base; /* The timer has migrated to another CPU */ spin_unlock_irqrestore(&base->lock, *flags); @@ -193,10 +522,11 @@ static tvec_base_t *lock_timer_base(struct timer_list *timer, int __mod_timer(struct timer_list *timer, unsigned long expires) { - tvec_base_t *base, *new_base; + 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); @@ -206,6 +536,8 @@ int __mod_timer(struct timer_list *timer, unsigned long expires) ret = 1; } + debug_timer_activate(timer); + new_base = __get_cpu_var(tvec_bases); if (base != new_base) { @@ -218,11 +550,11 @@ int __mod_timer(struct timer_list *timer, unsigned long expires) */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ - timer->base = NULL; + timer_set_base(timer, NULL); spin_unlock(&base->lock); base = new_base; spin_lock(&base->lock); - timer->base = base; + timer_set_base(timer, base); } } @@ -235,7 +567,7 @@ int __mod_timer(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(__mod_timer); -/*** +/** * add_timer_on - start a timer on a particular CPU * @timer: the timer to be added * @cpu: the CPU to start it on @@ -244,22 +576,33 @@ EXPORT_SYMBOL(__mod_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - tvec_base_t *base = per_cpu(tvec_bases, cpu); - unsigned long flags; + struct tvec_base *base = per_cpu(tvec_bases, cpu); + unsigned long flags; - BUG_ON(timer_pending(timer) || !timer->function); + timer_stats_timer_set_start_info(timer); + BUG_ON(timer_pending(timer) || !timer->function); spin_lock_irqsave(&base->lock, flags); - timer->base = base; + timer_set_base(timer, base); + debug_timer_activate(timer); internal_add_timer(base, timer); + /* + * Check whether the other CPU is idle and needs to be + * triggered to reevaluate the timer wheel when nohz is + * active. 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 idle can not evaluate + * the timer wheel. + */ + wake_up_idle_cpu(cpu); spin_unlock_irqrestore(&base->lock, flags); } - -/*** +/** * 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 + * 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: @@ -278,6 +621,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires) { BUG_ON(!timer->function); + timer_stats_timer_set_start_info(timer); /* * This is a common optimization triggered by the * networking code - if the timer is re-modified @@ -291,7 +635,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(mod_timer); -/*** +/** * del_timer - deactive a timer. * @timer: the timer to be deactivated * @@ -304,10 +648,11 @@ EXPORT_SYMBOL(mod_timer); */ int del_timer(struct timer_list *timer) { - tvec_base_t *base; + struct tvec_base *base; unsigned long flags; int ret = 0; + timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); if (timer_pending(timer)) { @@ -323,7 +668,10 @@ int del_timer(struct timer_list *timer) EXPORT_SYMBOL(del_timer); #ifdef CONFIG_SMP -/* +/** + * 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. * @@ -331,7 +679,7 @@ EXPORT_SYMBOL(del_timer); */ int try_to_del_timer_sync(struct timer_list *timer) { - tvec_base_t *base; + struct tvec_base *base; unsigned long flags; int ret = -1; @@ -351,7 +699,9 @@ out: return ret; } -/*** +EXPORT_SYMBOL(try_to_del_timer_sync); + +/** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated * @@ -359,7 +709,7 @@ out: * the timer it also makes sure the handler has finished executing on other * CPUs. * - * Synchronization rules: callers must prevent restarting of the timer, + * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts. The caller must not hold locks which would prevent * completion of the timer's handler. The timer's handler must not call @@ -374,13 +724,14 @@ int del_timer_sync(struct timer_list *timer) int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; + cpu_relax(); } } EXPORT_SYMBOL(del_timer_sync); #endif -static int cascade(tvec_base_t *base, tvec_t *tv, int index) +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, *tmp; @@ -393,23 +744,23 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index) * don't have to detach them individually. */ list_for_each_entry_safe(timer, tmp, &tv_list, entry) { - BUG_ON(timer->base != base); + BUG_ON(tbase_get_base(timer->base) != base); internal_add_timer(base, timer); } return index; } -/*** +#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. */ -#define INDEX(N) (base->timer_jiffies >> (TVR_BITS + N * TVN_BITS)) & TVN_MASK - -static inline void __run_timers(tvec_base_t *base) +static inline void __run_timers(struct tvec_base *base) { struct timer_list *timer; @@ -417,7 +768,7 @@ static inline void __run_timers(tvec_base_t *base) while (time_after_eq(jiffies, base->timer_jiffies)) { struct list_head work_list; struct list_head *head = &work_list; - int index = base->timer_jiffies & TVR_MASK; + int index = base->timer_jiffies & TVR_MASK; /* * Cascade timers: @@ -433,9 +784,11 @@ static inline void __run_timers(tvec_base_t *base) void (*fn)(unsigned long); unsigned long data; - timer = list_entry(head->next,struct timer_list,entry); - fn = timer->function; - data = timer->data; + timer = list_first_entry(head, struct timer_list,entry); + fn = timer->function; + data = timer->data; + + timer_stats_account_timer(timer); set_running_timer(base, timer); detach_timer(timer, 1); @@ -444,7 +797,7 @@ static inline void __run_timers(tvec_base_t *base) int preempt_count = preempt_count(); fn(data); if (preempt_count != preempt_count()) { - printk(KERN_WARNING "huh, entered %p " + printk(KERN_ERR "huh, entered %p " "with preempt_count %08x, exited" " with %08x?\n", fn, preempt_count, @@ -459,361 +812,160 @@ static inline void __run_timers(tvec_base_t *base) spin_unlock_irq(&base->lock); } -#ifdef CONFIG_NO_IDLE_HZ +#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. */ -unsigned long next_timer_interrupt(void) +static unsigned long __next_timer_interrupt(struct tvec_base *base) { - tvec_base_t *base; - struct list_head *list; + 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; - unsigned long expires; - unsigned long hr_expires = MAX_JIFFY_OFFSET; - ktime_t hr_delta; - tvec_t *varray[4]; - int i, j; - - hr_delta = hrtimer_get_next_event(); - if (hr_delta.tv64 != KTIME_MAX) { - struct timespec tsdelta; - tsdelta = ktime_to_timespec(hr_delta); - hr_expires = timespec_to_jiffies(&tsdelta); - if (hr_expires < 3) - return hr_expires + jiffies; - } - hr_expires += jiffies; - - base = __get_cpu_var(tvec_bases); - spin_lock(&base->lock); - expires = base->timer_jiffies + (LONG_MAX >> 1); - list = NULL; + struct tvec *varray[4]; /* Look for timer events in tv1. */ - j = base->timer_jiffies & TVR_MASK; + index = slot = timer_jiffies & TVR_MASK; do { - list_for_each_entry(nte, base->tv1.vec + j, entry) { + list_for_each_entry(nte, base->tv1.vec + slot, entry) { + if (tbase_get_deferrable(nte->base)) + continue; + + found = 1; expires = nte->expires; - if (j < (base->timer_jiffies & TVR_MASK)) - list = base->tv2.vec + (INDEX(0)); - goto found; + /* Look at the cascade bucket(s)? */ + if (!index || slot < index) + goto cascade; + return expires; } - j = (j + 1) & TVR_MASK; - } while (j != (base->timer_jiffies & TVR_MASK)); + 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 (i = 0; i < 4; i++) { - j = INDEX(i); + + for (array = 0; array < 4; array++) { + struct tvec *varp = varray[array]; + + index = slot = timer_jiffies & TVN_MASK; do { - if (list_empty(varray[i]->vec + j)) { - j = (j + 1) & TVN_MASK; - continue; - } - list_for_each_entry(nte, varray[i]->vec + j, entry) + list_for_each_entry(nte, varp->vec + slot, entry) { + found = 1; if (time_before(nte->expires, expires)) expires = nte->expires; - if (j < (INDEX(i)) && i < 3) - list = varray[i + 1]->vec + (INDEX(i + 1)); - goto found; - } while (j != (INDEX(i))); - } -found: - if (list) { - /* - * The search wrapped. We need to look at the next list - * from next tv element that would cascade into tv element - * where we found the timer element. - */ - list_for_each_entry(nte, list, entry) { - if (time_before(nte->expires, expires)) - expires = nte->expires; - } - } - spin_unlock(&base->lock); - - /* - * It can happen that other CPUs service timer IRQs and increment - * jiffies, but we have not yet got a local timer tick to process - * the timer wheels. In that case, the expiry time can be before - * jiffies, but since the high-resolution timer here is relative to - * jiffies, the default expression when high-resolution timers are - * not active, - * - * time_before(MAX_JIFFY_OFFSET + jiffies, expires) - * - * would falsely evaluate to true. If that is the case, just - * return jiffies so that we can immediately fire the local timer - */ - if (time_before(expires, jiffies)) - return jiffies; - - if (time_before(hr_expires, expires)) - return hr_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; } -#endif - -/******************************************************************/ - -/* - * Timekeeping variables - */ -unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */ -unsigned long tick_nsec = TICK_NSEC; /* ACTHZ period (nsec) */ - -/* - * The current time - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - */ -struct timespec xtime __attribute__ ((aligned (16))); -struct timespec wall_to_monotonic __attribute__ ((aligned (16))); - -EXPORT_SYMBOL(xtime); - -/* Don't completely fail for HZ > 500. */ -int tickadj = 500/HZ ? : 1; /* microsecs */ - /* - * phase-lock loop variables + * Check, if the next hrtimer event is before the next timer wheel + * event: */ -/* TIME_ERROR prevents overwriting the CMOS clock */ -int time_state = TIME_OK; /* clock synchronization status */ -int time_status = STA_UNSYNC; /* clock status bits */ -long time_offset; /* time adjustment (us) */ -long time_constant = 2; /* pll time constant */ -long time_tolerance = MAXFREQ; /* frequency tolerance (ppm) */ -long time_precision = 1; /* clock precision (us) */ -long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */ -long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */ -static long time_phase; /* phase offset (scaled us) */ -long time_freq = (((NSEC_PER_SEC + HZ/2) % HZ - HZ/2) << SHIFT_USEC) / NSEC_PER_USEC; - /* frequency offset (scaled ppm)*/ -static long time_adj; /* tick adjust (scaled 1 / HZ) */ -long time_reftime; /* time at last adjustment (s) */ -long time_adjust; -long time_next_adjust; - -/* - * this routine handles the overflow of the microsecond field - * - * The tricky bits of code to handle the accurate clock support - * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. - * They were originally developed for SUN and DEC kernels. - * All the kudos should go to Dave for this stuff. - * - */ -static void second_overflow(void) +static unsigned long cmp_next_hrtimer_event(unsigned long now, + unsigned long expires) { - long ltemp; + ktime_t hr_delta = hrtimer_get_next_event(); + struct timespec tsdelta; + unsigned long delta; - /* Bump the maxerror field */ - time_maxerror += time_tolerance >> SHIFT_USEC; - if (time_maxerror > NTP_PHASE_LIMIT) { - time_maxerror = NTP_PHASE_LIMIT; - time_status |= STA_UNSYNC; - } + if (hr_delta.tv64 == KTIME_MAX) + return expires; /* - * Leap second processing. If in leap-insert state at the end of the - * day, the system clock is set back one second; if in leap-delete - * state, the system clock is set ahead one second. The microtime() - * routine or external clock driver will insure that reported time is - * always monotonic. The ugly divides should be replaced. + * Expired timer available, let it expire in the next tick */ - switch (time_state) { - case TIME_OK: - if (time_status & STA_INS) - time_state = TIME_INS; - else if (time_status & STA_DEL) - time_state = TIME_DEL; - break; - case TIME_INS: - if (xtime.tv_sec % 86400 == 0) { - xtime.tv_sec--; - wall_to_monotonic.tv_sec++; - /* - * The timer interpolator will make time change - * gradually instead of an immediate jump by one second - */ - time_interpolator_update(-NSEC_PER_SEC); - time_state = TIME_OOP; - clock_was_set(); - printk(KERN_NOTICE "Clock: inserting leap second " - "23:59:60 UTC\n"); - } - break; - case TIME_DEL: - if ((xtime.tv_sec + 1) % 86400 == 0) { - xtime.tv_sec++; - wall_to_monotonic.tv_sec--; - /* - * Use of time interpolator for a gradual change of - * time - */ - time_interpolator_update(NSEC_PER_SEC); - time_state = TIME_WAIT; - clock_was_set(); - printk(KERN_NOTICE "Clock: deleting leap second " - "23:59:59 UTC\n"); - } - break; - case TIME_OOP: - time_state = TIME_WAIT; - break; - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - } + if (hr_delta.tv64 <= 0) + return now + 1; - /* - * Compute the phase adjustment for the next second. In PLL mode, the - * offset is reduced by a fixed factor times the time constant. In FLL - * mode the offset is used directly. In either mode, the maximum phase - * adjustment for each second is clamped so as to spread the adjustment - * over not more than the number of seconds between updates. - */ - ltemp = time_offset; - if (!(time_status & STA_FLL)) - ltemp = shift_right(ltemp, SHIFT_KG + time_constant); - ltemp = min(ltemp, (MAXPHASE / MINSEC) << SHIFT_UPDATE); - ltemp = max(ltemp, -(MAXPHASE / MINSEC) << SHIFT_UPDATE); - time_offset -= ltemp; - time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE); + tsdelta = ktime_to_timespec(hr_delta); + delta = timespec_to_jiffies(&tsdelta); /* - * Compute the frequency estimate and additional phase adjustment due - * to frequency error for the next second. + * Limit the delta to the max value, which is checked in + * tick_nohz_stop_sched_tick(): */ - ltemp = time_freq; - time_adj += shift_right(ltemp,(SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE)); + if (delta > NEXT_TIMER_MAX_DELTA) + delta = NEXT_TIMER_MAX_DELTA; -#if HZ == 100 - /* - * Compensate for (HZ==100) != (1 << SHIFT_HZ). Add 25% and 3.125% to - * get 128.125; => only 0.125% error (p. 14) - */ - time_adj += shift_right(time_adj, 2) + shift_right(time_adj, 5); -#endif -#if HZ == 250 - /* - * Compensate for (HZ==250) != (1 << SHIFT_HZ). Add 1.5625% and - * 0.78125% to get 255.85938; => only 0.05% error (p. 14) - */ - time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7); -#endif -#if HZ == 1000 /* - * Compensate for (HZ==1000) != (1 << SHIFT_HZ). Add 1.5625% and - * 0.78125% to get 1023.4375; => only 0.05% error (p. 14) + * Take rounding errors in to account and make sure, that it + * expires in the next tick. Otherwise we go into an endless + * ping pong due to tick_nohz_stop_sched_tick() retriggering + * the timer softirq */ - time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7); -#endif + if (delta < 1) + delta = 1; + now += delta; + if (time_before(now, expires)) + return now; + return expires; } -/* - * Returns how many microseconds we need to add to xtime this tick - * in doing an adjustment requested with adjtime. +/** + * get_next_timer_interrupt - return the jiffy of the next pending timer + * @now: current time (in jiffies) */ -static long adjtime_adjustment(void) +unsigned long get_next_timer_interrupt(unsigned long now) { - long time_adjust_step; - - time_adjust_step = time_adjust; - if (time_adjust_step) { - /* - * We are doing an adjtime thing. Prepare time_adjust_step to - * be within bounds. Note that a positive time_adjust means we - * want the clock to run faster. - * - * Limit the amount of the step to be in the range - * -tickadj .. +tickadj - */ - time_adjust_step = min(time_adjust_step, (long)tickadj); - time_adjust_step = max(time_adjust_step, (long)-tickadj); - } - return time_adjust_step; -} + struct tvec_base *base = __get_cpu_var(tvec_bases); + unsigned long expires; -/* in the NTP reference this is called "hardclock()" */ -static void update_wall_time_one_tick(void) -{ - long time_adjust_step, delta_nsec; + spin_lock(&base->lock); + expires = __next_timer_interrupt(base); + spin_unlock(&base->lock); - time_adjust_step = adjtime_adjustment(); - if (time_adjust_step) - /* Reduce by this step the amount of time left */ - time_adjust -= time_adjust_step; - delta_nsec = tick_nsec + time_adjust_step * 1000; - /* - * Advance the phase, once it gets to one microsecond, then - * advance the tick more. - */ - time_phase += time_adj; - if ((time_phase >= FINENSEC) || (time_phase <= -FINENSEC)) { - long ltemp = shift_right(time_phase, (SHIFT_SCALE - 10)); - time_phase -= ltemp << (SHIFT_SCALE - 10); - delta_nsec += ltemp; - } - xtime.tv_nsec += delta_nsec; - time_interpolator_update(delta_nsec); + if (time_before_eq(expires, now)) + return now; - /* Changes by adjtime() do not take effect till next tick. */ - if (time_next_adjust != 0) { - time_adjust = time_next_adjust; - time_next_adjust = 0; - } + return cmp_next_hrtimer_event(now, expires); } +#endif -/* - * Return how long ticks are at the moment, that is, how much time - * update_wall_time_one_tick will add to xtime next time we call it - * (assuming no calls to do_adjtimex in the meantime). - * The return value is in fixed-point nanoseconds with SHIFT_SCALE-10 - * bits to the right of the binary point. - * This function has no side-effects. - */ -u64 current_tick_length(void) +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +void account_process_tick(struct task_struct *p, int user_tick) { - long delta_nsec; - - delta_nsec = tick_nsec + adjtime_adjustment() * 1000; - return ((u64) delta_nsec << (SHIFT_SCALE - 10)) + time_adj; -} + cputime_t one_jiffy = jiffies_to_cputime(1); -/* - * Using a loop looks inefficient, but "ticks" is - * usually just one (we shouldn't be losing ticks, - * we're doing this this way mainly for interrupt - * latency reasons, not because we think we'll - * have lots of lost timer ticks - */ -static void update_wall_time(unsigned long ticks) -{ - do { - ticks--; - update_wall_time_one_tick(); - if (xtime.tv_nsec >= 1000000000) { - xtime.tv_nsec -= 1000000000; - xtime.tv_sec++; - second_overflow(); - } - } while (ticks); + if (user_tick) { + account_user_time(p, one_jiffy); + account_user_time_scaled(p, cputime_to_scaled(one_jiffy)); + } else { + account_system_time(p, HARDIRQ_OFFSET, one_jiffy); + account_system_time_scaled(p, cputime_to_scaled(one_jiffy)); + } } +#endif /* - * Called from the timer interrupt handler to charge one tick to the current + * 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) @@ -822,15 +974,12 @@ void update_process_times(int user_tick) int cpu = smp_processor_id(); /* Note: this timer irq context must be accounted for as well. */ - if (user_tick) - account_user_time(p, jiffies_to_cputime(1)); - else - account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1)); + account_process_tick(p, user_tick); run_local_timers(); if (rcu_pending(cpu)) rcu_check_callbacks(cpu, user_tick); scheduler_tick(); - run_posix_cpu_timers(p); + run_posix_cpu_timers(p); } /* @@ -863,36 +1012,26 @@ static inline void calc_load(unsigned long ticks) static int count = LOAD_FREQ; count -= ticks; - if (count < 0) { - count += LOAD_FREQ; + if (unlikely(count < 0)) { active_tasks = count_active_tasks(); - CALC_LOAD(avenrun[0], EXP_1, active_tasks); - CALC_LOAD(avenrun[1], EXP_5, active_tasks); - CALC_LOAD(avenrun[2], EXP_15, 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); } } -/* jiffies at the most recent update of wall time */ -unsigned long wall_jiffies = INITIAL_JIFFIES; - -/* - * This read-write spinlock protects us from races in SMP while - * playing with xtime and avenrun. - */ -#ifndef ARCH_HAVE_XTIME_LOCK -seqlock_t xtime_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED; - -EXPORT_SYMBOL(xtime_lock); -#endif - /* * This function runs timers and the timer-tq in bottom half context. */ static void run_timer_softirq(struct softirq_action *h) { - tvec_base_t *base = __get_cpu_var(tvec_bases); + struct tvec_base *base = __get_cpu_var(tvec_bases); + + hrtimer_run_pending(); - hrtimer_run_queues(); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } @@ -902,6 +1041,7 @@ static void run_timer_softirq(struct softirq_action *h) */ void run_local_timers(void) { + hrtimer_run_queues(); raise_softirq(TIMER_SOFTIRQ); softlockup_tick(); } @@ -910,30 +1050,22 @@ 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(void) +static inline void update_times(unsigned long ticks) { - unsigned long ticks; - - ticks = jiffies - wall_jiffies; - if (ticks) { - wall_jiffies += ticks; - update_wall_time(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... */ -void do_timer(struct pt_regs *regs) +void do_timer(unsigned long ticks) { - jiffies_64++; - /* prevent loading jiffies before storing new jiffies_64 value. */ - barrier(); - update_times(); + jiffies_64 += ticks; + update_times(ticks); } #ifdef __ARCH_WANT_SYS_ALARM @@ -967,50 +1099,23 @@ asmlinkage unsigned long sys_alarm(unsigned int seconds) */ asmlinkage long sys_getpid(void) { - return current->tgid; + return task_tgid_vnr(current); } /* - * Accessing ->group_leader->real_parent is not SMP-safe, it could - * change from under us. However, rather than getting any lock - * we can use an optimistic algorithm: get the parent - * pid, and go back and check that the parent is still - * the same. If it has changed (which is extremely unlikely - * indeed), we just try again.. - * - * NOTE! This depends on the fact that even if we _do_ - * get an old value of "parent", we can happily dereference - * the pointer (it was and remains a dereferencable kernel pointer - * no matter what): we just can't necessarily trust the result - * until we know that the parent pointer is valid. - * - * NOTE2: ->group_leader never changes from under us. + * Accessing ->real_parent is not SMP-safe, it could + * change from under us. However, we can use a stale + * value of ->real_parent under rcu_read_lock(), see + * release_task()->call_rcu(delayed_put_task_struct). */ asmlinkage long sys_getppid(void) { int pid; - struct task_struct *me = current; - struct task_struct *parent; - parent = me->group_leader->real_parent; - for (;;) { - pid = parent->tgid; -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) -{ - struct task_struct *old = parent; + rcu_read_lock(); + pid = task_tgid_vnr(current->real_parent); + rcu_read_unlock(); - /* - * Make sure we read the pid before re-reading the - * parent pointer: - */ - smp_rmb(); - parent = me->group_leader->real_parent; - if (old != parent) - continue; -} -#endif - break; - } return pid; } @@ -1042,7 +1147,7 @@ asmlinkage long sys_getegid(void) static void process_timeout(unsigned long __data) { - wake_up_process((task_t *)__data); + wake_up_process((struct task_struct *)__data); } /** @@ -1071,7 +1176,7 @@ static void process_timeout(unsigned long __data) * * In all cases the return value is guaranteed to be non-negative. */ -fastcall signed long __sched schedule_timeout(signed long timeout) +signed long __sched schedule_timeout(signed long timeout) { struct timer_list timer; unsigned long expire; @@ -1096,11 +1201,10 @@ fastcall signed long __sched schedule_timeout(signed long timeout) * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ - if (timeout < 0) - { + if (timeout < 0) { printk(KERN_ERR "schedule_timeout: wrong timeout " - "value %lx from %p\n", timeout, - __builtin_return_address(0)); + "value %lx\n", timeout); + dump_stack(); current->state = TASK_RUNNING; goto out; } @@ -1108,11 +1212,14 @@ fastcall signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; - setup_timer(&timer, process_timeout, (unsigned long)current); + setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); __mod_timer(&timer, expire); schedule(); del_singleshot_timer_sync(&timer); + /* Remove the timer from the object tracker */ + destroy_timer_on_stack(&timer); + timeout = expire - jiffies; out: @@ -1131,6 +1238,13 @@ signed long __sched schedule_timeout_interruptible(signed long 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); @@ -1141,20 +1255,20 @@ EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* Thread ID - the internal kernel "pid" */ asmlinkage long sys_gettid(void) { - return current->pid; + return task_pid_vnr(current); } -/* - * sys_sysinfo - fill in sysinfo struct - */ -asmlinkage long sys_sysinfo(struct sysinfo __user *info) +/** + * do_sysinfo - fill in sysinfo struct + * @info: pointer to buffer to fill + */ +int do_sysinfo(struct sysinfo *info) { - struct sysinfo val; unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; unsigned long seq; - memset((char *)&val, 0, sizeof(struct sysinfo)); + memset(info, 0, sizeof(struct sysinfo)); do { struct timespec tp; @@ -1170,21 +1284,22 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) 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++; } - val.uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); + info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); - val.loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT); - val.loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT); - val.loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT); + 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); - val.procs = nr_threads; + info->procs = nr_threads; } while (read_seqretry(&xtime_lock, seq)); - si_meminfo(&val); - si_swapinfo(&val); + si_meminfo(info); + si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) @@ -1195,11 +1310,11 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) * -Erik Andersen */ - mem_total = val.totalram + val.totalswap; - if (mem_total < val.totalram || mem_total < val.totalswap) + mem_total = info->totalram + info->totalswap; + if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; - mem_unit = val.mem_unit; + mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; @@ -1211,33 +1326,42 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) /* * If mem_total did not overflow, multiply all memory values by - * val.mem_unit and set it to 1. This leaves things compatible + * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ - val.mem_unit = 1; - val.totalram <<= bitcount; - val.freeram <<= bitcount; - val.sharedram <<= bitcount; - val.bufferram <<= bitcount; - val.totalswap <<= bitcount; - val.freeswap <<= bitcount; - val.totalhigh <<= bitcount; - val.freehigh <<= bitcount; + info->mem_unit = 1; + info->totalram <<= bitcount; + info->freeram <<= bitcount; + info->sharedram <<= bitcount; + info->bufferram <<= bitcount; + info->totalswap <<= bitcount; + info->freeswap <<= bitcount; + info->totalhigh <<= bitcount; + info->freehigh <<= bitcount; + +out: + return 0; +} + +asmlinkage long sys_sysinfo(struct sysinfo __user *info) +{ + struct sysinfo val; + + do_sysinfo(&val); - out: if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } -static int __devinit init_timers_cpu(int cpu) +static int __cpuinit init_timers_cpu(int cpu) { int j; - tvec_base_t *base; - static char __devinitdata tvec_base_done[NR_CPUS]; + struct tvec_base *base; + static char __cpuinitdata tvec_base_done[NR_CPUS]; if (!tvec_base_done[cpu]) { static char boot_done; @@ -1246,11 +1370,18 @@ static int __devinit init_timers_cpu(int cpu) /* * The APs use this path later in boot */ - base = kmalloc_node(sizeof(*base), GFP_KERNEL, + base = kmalloc_node(sizeof(*base), + GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); if (!base) return -ENOMEM; - memset(base, 0, sizeof(*base)); + + /* Make sure that tvec_base is 2 byte aligned */ + if (tbase_get_deferrable(base)) { + WARN_ON(1); + kfree(base); + return -ENOMEM; + } per_cpu(tvec_bases, cpu) = base; } else { /* @@ -1268,6 +1399,7 @@ static int __devinit init_timers_cpu(int cpu) } spin_lock_init(&base->lock); + for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); INIT_LIST_HEAD(base->tv4.vec + j); @@ -1282,22 +1414,22 @@ static int __devinit init_timers_cpu(int cpu) } #ifdef CONFIG_HOTPLUG_CPU -static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head) +static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) { struct timer_list *timer; while (!list_empty(head)) { - timer = list_entry(head->next, struct timer_list, entry); + timer = list_first_entry(head, struct timer_list, entry); detach_timer(timer, 0); - timer->base = new_base; + timer_set_base(timer, new_base); internal_add_timer(new_base, timer); } } -static void __devinit migrate_timers(int cpu) +static void __cpuinit migrate_timers(int cpu) { - tvec_base_t *old_base; - tvec_base_t *new_base; + struct tvec_base *old_base; + struct tvec_base *new_base; int i; BUG_ON(cpu_online(cpu)); @@ -1306,7 +1438,7 @@ static void __devinit migrate_timers(int cpu) local_irq_disable(); spin_lock(&new_base->lock); - spin_lock(&old_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); @@ -1326,17 +1458,19 @@ static void __devinit migrate_timers(int cpu) } #endif /* CONFIG_HOTPLUG_CPU */ -static int timer_cpu_notify(struct notifier_block *self, +static int __cpuinit timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; switch(action) { case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: if (init_timers_cpu(cpu) < 0) return NOTIFY_BAD; break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: + case CPU_DEAD_FROZEN: migrate_timers(cpu); break; #endif @@ -1346,206 +1480,22 @@ static int timer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block timers_nb = { +static struct notifier_block __cpuinitdata timers_nb = { .notifier_call = timer_cpu_notify, }; void __init init_timers(void) { - timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, + int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); - register_cpu_notifier(&timers_nb); - open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); -} - -#ifdef CONFIG_TIME_INTERPOLATION - -struct time_interpolator *time_interpolator __read_mostly; -static struct time_interpolator *time_interpolator_list __read_mostly; -static DEFINE_SPINLOCK(time_interpolator_lock); - -static inline u64 time_interpolator_get_cycles(unsigned int src) -{ - unsigned long (*x)(void); - - switch (src) - { - case TIME_SOURCE_FUNCTION: - x = time_interpolator->addr; - return x(); - - case TIME_SOURCE_MMIO64 : - return readq_relaxed((void __iomem *)time_interpolator->addr); - - case TIME_SOURCE_MMIO32 : - return readl_relaxed((void __iomem *)time_interpolator->addr); - - default: return get_cycles(); - } -} - -static inline u64 time_interpolator_get_counter(int writelock) -{ - unsigned int src = time_interpolator->source; - - if (time_interpolator->jitter) - { - u64 lcycle; - u64 now; - - do { - lcycle = time_interpolator->last_cycle; - now = time_interpolator_get_cycles(src); - if (lcycle && time_after(lcycle, now)) - return lcycle; - - /* When holding the xtime write lock, there's no need - * to add the overhead of the cmpxchg. Readers are - * force to retry until the write lock is released. - */ - if (writelock) { - time_interpolator->last_cycle = now; - return now; - } - /* Keep track of the last timer value returned. The use of cmpxchg here - * will cause contention in an SMP environment. - */ - } while (unlikely(cmpxchg(&time_interpolator->last_cycle, lcycle, now) != lcycle)); - return now; - } - else - return time_interpolator_get_cycles(src); -} - -void time_interpolator_reset(void) -{ - time_interpolator->offset = 0; - time_interpolator->last_counter = time_interpolator_get_counter(1); -} - -#define GET_TI_NSECS(count,i) (((((count) - i->last_counter) & (i)->mask) * (i)->nsec_per_cyc) >> (i)->shift) - -unsigned long time_interpolator_get_offset(void) -{ - /* If we do not have a time interpolator set up then just return zero */ - if (!time_interpolator) - return 0; - - return time_interpolator->offset + - GET_TI_NSECS(time_interpolator_get_counter(0), time_interpolator); -} -#define INTERPOLATOR_ADJUST 65536 -#define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST + init_timer_stats(); -static void time_interpolator_update(long delta_nsec) -{ - u64 counter; - unsigned long offset; - - /* If there is no time interpolator set up then do nothing */ - if (!time_interpolator) - return; - - /* - * The interpolator compensates for late ticks by accumulating the late - * time in time_interpolator->offset. A tick earlier than expected will - * lead to a reset of the offset and a corresponding jump of the clock - * forward. Again this only works if the interpolator clock is running - * slightly slower than the regular clock and the tuning logic insures - * that. - */ - - counter = time_interpolator_get_counter(1); - offset = time_interpolator->offset + - GET_TI_NSECS(counter, time_interpolator); - - if (delta_nsec < 0 || (unsigned long) delta_nsec < offset) - time_interpolator->offset = offset - delta_nsec; - else { - time_interpolator->skips++; - time_interpolator->ns_skipped += delta_nsec - offset; - time_interpolator->offset = 0; - } - time_interpolator->last_counter = counter; - - /* Tuning logic for time interpolator invoked every minute or so. - * Decrease interpolator clock speed if no skips occurred and an offset is carried. - * Increase interpolator clock speed if we skip too much time. - */ - if (jiffies % INTERPOLATOR_ADJUST == 0) - { - if (time_interpolator->skips == 0 && time_interpolator->offset > tick_nsec) - time_interpolator->nsec_per_cyc--; - if (time_interpolator->ns_skipped > INTERPOLATOR_MAX_SKIP && time_interpolator->offset == 0) - time_interpolator->nsec_per_cyc++; - time_interpolator->skips = 0; - time_interpolator->ns_skipped = 0; - } -} - -static inline int -is_better_time_interpolator(struct time_interpolator *new) -{ - if (!time_interpolator) - return 1; - return new->frequency > 2*time_interpolator->frequency || - (unsigned long)new->drift < (unsigned long)time_interpolator->drift; -} - -void -register_time_interpolator(struct time_interpolator *ti) -{ - unsigned long flags; - - /* Sanity check */ - BUG_ON(ti->frequency == 0 || ti->mask == 0); - - ti->nsec_per_cyc = ((u64)NSEC_PER_SEC << ti->shift) / ti->frequency; - spin_lock(&time_interpolator_lock); - write_seqlock_irqsave(&xtime_lock, flags); - if (is_better_time_interpolator(ti)) { - time_interpolator = ti; - time_interpolator_reset(); - } - write_sequnlock_irqrestore(&xtime_lock, flags); - - ti->next = time_interpolator_list; - time_interpolator_list = ti; - spin_unlock(&time_interpolator_lock); -} - -void -unregister_time_interpolator(struct time_interpolator *ti) -{ - struct time_interpolator *curr, **prev; - unsigned long flags; - - spin_lock(&time_interpolator_lock); - prev = &time_interpolator_list; - for (curr = *prev; curr; curr = curr->next) { - if (curr == ti) { - *prev = curr->next; - break; - } - prev = &curr->next; - } - - write_seqlock_irqsave(&xtime_lock, flags); - if (ti == time_interpolator) { - /* we lost the best time-interpolator: */ - time_interpolator = NULL; - /* find the next-best interpolator */ - for (curr = time_interpolator_list; curr; curr = curr->next) - if (is_better_time_interpolator(curr)) - time_interpolator = curr; - time_interpolator_reset(); - } - write_sequnlock_irqrestore(&xtime_lock, flags); - spin_unlock(&time_interpolator_lock); + BUG_ON(err == NOTIFY_BAD); + register_cpu_notifier(&timers_nb); + open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } -#endif /* CONFIG_TIME_INTERPOLATION */ /** * msleep - sleep safely even with waitqueue interruptions