diff options
Diffstat (limited to 'kernel/timer.c')
| -rw-r--r-- | kernel/timer.c | 2123 |
1 files changed, 1081 insertions, 1042 deletions
diff --git a/kernel/timer.c b/kernel/timer.c index c1c7fbcffec..3bb01a323b2 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 * * Copyright (C) 1991, 1992 Linus Torvalds * @@ -20,12 +20,13 @@ */ #include <linux/kernel_stat.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> +#include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> @@ -34,6 +35,13 @@ #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> +#include <linux/tick.h> +#include <linux/kallsyms.h> +#include <linux/irq_work.h> +#include <linux/sched.h> +#include <linux/sched/sysctl.h> +#include <linux/slab.h> +#include <linux/compat.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -41,7 +49,10 @@ #include <asm/timex.h> #include <asm/io.h> -u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; +#define CREATE_TRACE_POINTS +#include <trace/events/timer.h> + +__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); @@ -54,41 +65,295 @@ EXPORT_SYMBOL(jiffies_64); #define TVR_SIZE (1 << TVR_BITS) #define TVN_MASK (TVN_SIZE - 1) #define TVR_MASK (TVR_SIZE - 1) +#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) -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; + unsigned long next_timer; + unsigned long active_timers; + unsigned long all_timers; + 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; +/* Functions below help us manage 'deferrable' flag */ +static inline unsigned int tbase_get_deferrable(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE); +} -tvec_base_t boot_tvec_bases; -EXPORT_SYMBOL(boot_tvec_bases); -static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = &boot_tvec_bases; +static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); +} -static inline void set_running_timer(tvec_base_t *base, - struct timer_list *timer) +static inline struct tvec_base *tbase_get_base(struct tvec_base *base) { -#ifdef CONFIG_SMP - base->running_timer = timer; -#endif + return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); +} + +static inline void +timer_set_base(struct timer_list *timer, struct tvec_base *new_base) +{ + unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK; + + timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags); +} + +static unsigned long round_jiffies_common(unsigned long j, int cpu, + bool force_up) +{ + int rem; + unsigned long original = j; + + /* + * We don't want all cpus firing their timers at once hitting the + * same lock or cachelines, so we skew each extra cpu with an extra + * 3 jiffies. This 3 jiffies came originally from the mm/ code which + * already did this. + * The skew is done by adding 3*cpunr, then round, then subtract this + * extra offset again. + */ + j += cpu * 3; + + rem = j % HZ; + + /* + * If the target jiffie is just after a whole second (which can happen + * due to delays of the timer irq, long irq off times etc etc) then + * we should round down to the whole second, not up. Use 1/4th second + * as cutoff for this rounding as an extreme upper bound for this. + * But never round down if @force_up is set. + */ + if (rem < HZ/4 && !force_up) /* round down */ + j = j - rem; + else /* round up */ + j = j - rem + HZ; + + /* now that we have rounded, subtract the extra skew again */ + j -= cpu * 3; + + /* + * Make sure j is still in the future. Otherwise return the + * unmodified value. + */ + return time_is_after_jiffies(j) ? j : original; +} + +/** + * __round_jiffies - function to round jiffies to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * __round_jiffies() rounds an absolute time in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The exact rounding is skewed for each processor to avoid all + * processors firing at the exact same time, which could lead + * to lock contention or spurious cache line bouncing. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long __round_jiffies(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, false); +} +EXPORT_SYMBOL_GPL(__round_jiffies); + +/** + * __round_jiffies_relative - function to round jiffies to a full second + * @j: the time in (relative) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * __round_jiffies_relative() rounds a time delta in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The exact rounding is skewed for each processor to avoid all + * processors firing at the exact same time, which could lead + * to lock contention or spurious cache line bouncing. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long __round_jiffies_relative(unsigned long j, int cpu) +{ + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, false) - j0; +} +EXPORT_SYMBOL_GPL(__round_jiffies_relative); + +/** + * round_jiffies - function to round jiffies to a full second + * @j: the time in (absolute) jiffies that should be rounded + * + * round_jiffies() rounds an absolute time in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long round_jiffies(unsigned long j) +{ + return round_jiffies_common(j, raw_smp_processor_id(), false); +} +EXPORT_SYMBOL_GPL(round_jiffies); + +/** + * round_jiffies_relative - function to round jiffies to a full second + * @j: the time in (relative) jiffies that should be rounded + * + * round_jiffies_relative() rounds a time delta in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long round_jiffies_relative(unsigned long j) +{ + return __round_jiffies_relative(j, raw_smp_processor_id()); +} +EXPORT_SYMBOL_GPL(round_jiffies_relative); + +/** + * __round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, true); +} +EXPORT_SYMBOL_GPL(__round_jiffies_up); + +/** + * __round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) +{ + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, true) - j0; +} +EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); + +/** + * round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * + * This is the same as round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up(unsigned long j) +{ + return round_jiffies_common(j, raw_smp_processor_id(), true); +} +EXPORT_SYMBOL_GPL(round_jiffies_up); + +/** + * round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * + * This is the same as round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up_relative(unsigned long j) +{ + return __round_jiffies_up_relative(j, raw_smp_processor_id()); +} +EXPORT_SYMBOL_GPL(round_jiffies_up_relative); + +/** + * set_timer_slack - set the allowed slack for a timer + * @timer: the timer to be modified + * @slack_hz: the amount of time (in jiffies) allowed for rounding + * + * Set the amount of time, in jiffies, that a certain timer has + * in terms of slack. By setting this value, the timer subsystem + * will schedule the actual timer somewhere between + * the time mod_timer() asks for, and that time plus the slack. + * + * By setting the slack to -1, a percentage of the delay is used + * instead. + */ +void set_timer_slack(struct timer_list *timer, int slack_hz) +{ + timer->slack = slack_hz; } +EXPORT_SYMBOL_GPL(set_timer_slack); -static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) +/* + * If the list is empty, catch up ->timer_jiffies to the current time. + * The caller must hold the tvec_base lock. Returns true if the list + * was empty and therefore ->timer_jiffies was updated. + */ +static bool catchup_timer_jiffies(struct tvec_base *base) +{ + if (!base->all_timers) { + base->timer_jiffies = jiffies; + return true; + } + return false; +} + +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; @@ -114,11 +379,12 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); } else { int i; - /* If the timeout is larger than 0xffffffff on 64-bit - * architectures then we use the maximum timeout: + /* If the timeout is larger than MAX_TVAL (on 64-bit + * architectures or with CONFIG_BASE_SMALL=1) then we + * use the maximum timeout. */ - if (idx > 0xffffffffUL) { - idx = 0xffffffffUL; + if (idx > MAX_TVAL) { + idx = MAX_TVAL; expires = idx + base->timer_jiffies; } i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; @@ -130,31 +396,319 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) list_add_tail(&timer->entry, vec); } +static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +{ + (void)catchup_timer_jiffies(base); + __internal_add_timer(base, timer); + /* + * Update base->active_timers and base->next_timer + */ + if (!tbase_get_deferrable(timer->base)) { + if (!base->active_timers++ || + time_before(timer->expires, base->next_timer)) + base->next_timer = timer->expires; + } + base->all_timers++; +} + +#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 (likely(!timer->start_site)) + return; + 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; + +static void *timer_debug_hint(void *addr) +{ + return ((struct timer_list *) addr)->function; +} + +/* + * 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; + } +} + +/* Stub timer callback for improperly used timers. */ +static void stub_timer(unsigned long data) +{ + WARN_ON(1); +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static 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 { + setup_timer(timer, stub_timer, 0); + return 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; + } +} + +/* + * fixup_assert_init is called when: + * - an untracked/uninit-ed object is found + */ +static int timer_fixup_assert_init(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + case ODEBUG_STATE_NOTAVAILABLE: + if (timer->entry.prev == TIMER_ENTRY_STATIC) { + /* + * This is not really a fixup. The timer was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + debug_object_init(timer, &timer_debug_descr); + return 0; + } else { + setup_timer(timer, stub_timer, 0); + return 1; + } + default: + return 0; + } +} + +static struct debug_obj_descr timer_debug_descr = { + .name = "timer_list", + .debug_hint = timer_debug_hint, + .fixup_init = timer_fixup_init, + .fixup_activate = timer_fixup_activate, + .fixup_free = timer_fixup_free, + .fixup_assert_init = timer_fixup_assert_init, +}; + +static inline void debug_timer_init(struct timer_list *timer) +{ + debug_object_init(timer, &timer_debug_descr); +} + +static inline void debug_timer_activate(struct timer_list *timer) +{ + debug_object_activate(timer, &timer_debug_descr); +} + +static inline void debug_timer_deactivate(struct timer_list *timer) +{ + debug_object_deactivate(timer, &timer_debug_descr); +} + +static inline void debug_timer_free(struct timer_list *timer) +{ + debug_object_free(timer, &timer_debug_descr); +} + +static inline void debug_timer_assert_init(struct timer_list *timer) +{ + debug_object_assert_init(timer, &timer_debug_descr); +} + +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key); + +void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) +{ + debug_object_init_on_stack(timer, &timer_debug_descr); + do_init_timer(timer, flags, name, key); +} +EXPORT_SYMBOL_GPL(init_timer_on_stack_key); + +void destroy_timer_on_stack(struct timer_list *timer) +{ + debug_object_free(timer, &timer_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_timer_on_stack); + +#else +static inline void debug_timer_init(struct timer_list *timer) { } +static inline void debug_timer_activate(struct timer_list *timer) { } +static inline void debug_timer_deactivate(struct timer_list *timer) { } +static inline void debug_timer_assert_init(struct timer_list *timer) { } +#endif + +static inline void debug_init(struct timer_list *timer) +{ + debug_timer_init(timer); + trace_timer_init(timer); +} + +static inline void +debug_activate(struct timer_list *timer, unsigned long expires) +{ + debug_timer_activate(timer); + trace_timer_start(timer, expires); +} + +static inline void debug_deactivate(struct timer_list *timer) +{ + debug_timer_deactivate(timer); + trace_timer_cancel(timer); +} + +static inline void debug_assert_init(struct timer_list *timer) +{ + debug_timer_assert_init(timer); +} + +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) +{ + struct tvec_base *base = __raw_get_cpu_var(tvec_bases); + + timer->entry.next = NULL; + timer->base = (void *)((unsigned long)base | flags); + timer->slack = -1; +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; + timer->start_pid = -1; + memset(timer->start_comm, 0, TASK_COMM_LEN); +#endif + lockdep_init_map(&timer->lockdep_map, name, key, 0); +} + /** - * init_timer - initialize a timer. + * init_timer_key - initialize a timer * @timer: the timer to be initialized + * @flags: timer flags + * @name: name of the timer + * @key: lockdep class key of the fake lock used for tracking timer + * sync lock dependencies * - * init_timer() 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 fastcall init_timer(struct timer_list *timer) +void init_timer_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) { - timer->entry.next = NULL; - timer->base = __raw_get_cpu_var(tvec_bases); + debug_init(timer); + do_init_timer(timer, flags, name, key); } -EXPORT_SYMBOL(init_timer); +EXPORT_SYMBOL(init_timer_key); -static inline void detach_timer(struct timer_list *timer, - int clear_pending) +static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct list_head *entry = &timer->entry; + debug_deactivate(timer); + __list_del(entry->prev, entry->next); if (clear_pending) entry->next = NULL; entry->prev = LIST_POISON2; } +static inline void +detach_expired_timer(struct timer_list *timer, struct tvec_base *base) +{ + detach_timer(timer, true); + if (!tbase_get_deferrable(timer->base)) + base->active_timers--; + base->all_timers--; + (void)catchup_timer_jiffies(base); +} + +static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, + bool clear_pending) +{ + if (!timer_pending(timer)) + return 0; + + detach_timer(timer, clear_pending); + if (!tbase_get_deferrable(timer->base)) { + base->active_timers--; + if (timer->expires == base->next_timer) + base->next_timer = base->timer_jiffies; + } + base->all_timers--; + (void)catchup_timer_jiffies(base); + return 1; +} + /* * We are using hashed locking: holding per_cpu(tvec_bases).lock * means that all timers which are tied to this base via timer->base are @@ -167,17 +721,18 @@ 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); @@ -186,22 +741,27 @@ static tvec_base_t *lock_timer_base(struct timer_list *timer, } } -int __mod_timer(struct timer_list *timer, unsigned long expires) +static inline int +__mod_timer(struct timer_list *timer, unsigned long expires, + bool pending_only, int pinned) { - tvec_base_t *base, *new_base; + struct tvec_base *base, *new_base; unsigned long flags; - int ret = 0; + int ret = 0 , cpu; + timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 0); - ret = 1; - } + ret = detach_if_pending(timer, base, false); + if (!ret && pending_only) + goto out_unlock; + + debug_activate(timer, expires); - new_base = __get_cpu_var(tvec_bases); + cpu = get_nohz_timer_target(pinned); + new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { /* @@ -213,49 +773,84 @@ 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); } } timer->expires = expires; internal_add_timer(base, timer); + +out_unlock: spin_unlock_irqrestore(&base->lock, flags); return ret; } -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 + * mod_timer_pending - modify a pending timer's timeout + * @timer: the pending timer to be modified + * @expires: new timeout in jiffies * - * This is not very scalable on SMP. Double adds are not possible. + * mod_timer_pending() is the same for pending timers as mod_timer(), + * but will not re-activate and modify already deleted timers. + * + * It is useful for unserialized use of timers. */ -void add_timer_on(struct timer_list *timer, int cpu) +int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - tvec_base_t *base = per_cpu(tvec_bases, cpu); - unsigned long flags; - - BUG_ON(timer_pending(timer) || !timer->function); - spin_lock_irqsave(&base->lock, flags); - timer->base = base; - internal_add_timer(base, timer); - spin_unlock_irqrestore(&base->lock, flags); + return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); } +EXPORT_SYMBOL(mod_timer_pending); + +/* + * Decide where to put the timer while taking the slack into account + * + * Algorithm: + * 1) calculate the maximum (absolute) time + * 2) calculate the highest bit where the expires and new max are different + * 3) use this bit to make a mask + * 4) use the bitmask to round down the maximum time, so that all last + * bits are zeros + */ +static inline +unsigned long apply_slack(struct timer_list *timer, unsigned long expires) +{ + unsigned long expires_limit, mask; + int bit; + + if (timer->slack >= 0) { + expires_limit = expires + timer->slack; + } else { + long delta = expires - jiffies; + + if (delta < 256) + return expires; + + expires_limit = expires + delta / 256; + } + mask = expires ^ expires_limit; + if (mask == 0) + return expires; + bit = find_last_bit(&mask, BITS_PER_LONG); + + mask = (1UL << bit) - 1; + + expires_limit = expires_limit & ~(mask); + + return expires_limit; +} /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified * @expires: new timeout in jiffies * - * mod_timer is a more efficient way to update the expire field of an + * 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: @@ -272,20 +867,106 @@ void add_timer_on(struct timer_list *timer, int cpu) */ int mod_timer(struct timer_list *timer, unsigned long expires) { - BUG_ON(!timer->function); + expires = apply_slack(timer, expires); /* * This is a common optimization triggered by the * networking code - if the timer is re-modified * to be the same thing then just return: */ + if (timer_pending(timer) && timer->expires == expires) + return 1; + + return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); +} +EXPORT_SYMBOL(mod_timer); + +/** + * mod_timer_pinned - modify a timer's timeout + * @timer: the timer to be modified + * @expires: new timeout in jiffies + * + * mod_timer_pinned() is a way to update the expire field of an + * active timer (if the timer is inactive it will be activated) + * and to ensure that the timer is scheduled on the current CPU. + * + * Note that this does not prevent the timer from being migrated + * when the current CPU goes offline. If this is a problem for + * you, use CPU-hotplug notifiers to handle it correctly, for + * example, cancelling the timer when the corresponding CPU goes + * offline. + * + * mod_timer_pinned(timer, expires) is equivalent to: + * + * del_timer(timer); timer->expires = expires; add_timer(timer); + */ +int mod_timer_pinned(struct timer_list *timer, unsigned long expires) +{ if (timer->expires == expires && timer_pending(timer)) return 1; - return __mod_timer(timer, expires); + return __mod_timer(timer, expires, false, TIMER_PINNED); } +EXPORT_SYMBOL(mod_timer_pinned); -EXPORT_SYMBOL(mod_timer); +/** + * add_timer - start a timer + * @timer: the timer to be added + * + * The kernel will do a ->function(->data) callback from the + * timer interrupt at the ->expires point in the future. The + * current time is 'jiffies'. + * + * The timer's ->expires, ->function (and if the handler uses it, ->data) + * fields must be set prior calling this function. + * + * Timers with an ->expires field in the past will be executed in the next + * timer tick. + */ +void add_timer(struct timer_list *timer) +{ + BUG_ON(timer_pending(timer)); + mod_timer(timer, timer->expires); +} +EXPORT_SYMBOL(add_timer); + +/** + * add_timer_on - start a timer on a particular CPU + * @timer: the timer to be added + * @cpu: the CPU to start it on + * + * This is not very scalable on SMP. Double adds are not possible. + */ +void add_timer_on(struct timer_list *timer, int cpu) +{ + struct tvec_base *base = per_cpu(tvec_bases, cpu); + unsigned long flags; + + timer_stats_timer_set_start_info(timer); + BUG_ON(timer_pending(timer) || !timer->function); + spin_lock_irqsave(&base->lock, flags); + timer_set_base(timer, base); + debug_activate(timer, timer->expires); + internal_add_timer(base, timer); + /* + * Check whether the other CPU is in dynticks mode and needs + * to be triggered to reevaluate the timer wheel. + * We are protected against the other CPU fiddling + * with the timer by holding the timer base lock. This also + * makes sure that a CPU on the way to stop its tick can not + * evaluate the timer wheel. + * + * Spare the IPI for deferrable timers on idle targets though. + * The next busy ticks will take care of it. Except full dynticks + * require special care against races with idle_cpu(), lets deal + * with that later. + */ + if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu)) + wake_up_nohz_cpu(cpu); + + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(add_timer_on); /** * del_timer - deactive a timer. @@ -300,56 +981,51 @@ 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; + debug_assert_init(timer); + + timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 1); - ret = 1; - } + ret = detach_if_pending(timer, base, true); spin_unlock_irqrestore(&base->lock, flags); } return ret; } - 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. - * - * It must not be called from interrupt contexts. */ int try_to_del_timer_sync(struct timer_list *timer) { - tvec_base_t *base; + struct tvec_base *base; unsigned long flags; int ret = -1; - base = lock_timer_base(timer, &flags); + debug_assert_init(timer); - if (base->running_timer == timer) - goto out; + base = lock_timer_base(timer, &flags); - ret = 0; - if (timer_pending(timer)) { - detach_timer(timer, 1); - ret = 1; + if (base->running_timer != timer) { + timer_stats_timer_clear_start_info(timer); + ret = detach_if_pending(timer, base, true); } -out: spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL(try_to_del_timer_sync); +#ifdef CONFIG_SMP /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -358,17 +1034,53 @@ 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 - * add_timer_on(). Upon exit the timer is not queued and the handler is - * not running on any CPU. + * interrupt contexts unless the timer is an irqsafe one. The caller must + * not hold locks which would prevent completion of the timer's + * handler. The timer's handler must not call add_timer_on(). Upon exit the + * timer is not queued and the handler is not running on any CPU. + * + * Note: For !irqsafe timers, you must not hold locks that are held in + * interrupt context while calling this function. Even if the lock has + * nothing to do with the timer in question. Here's why: + * + * CPU0 CPU1 + * ---- ---- + * <SOFTIRQ> + * call_timer_fn(); + * base->running_timer = mytimer; + * spin_lock_irq(somelock); + * <IRQ> + * spin_lock(somelock); + * del_timer_sync(mytimer); + * while (base->running_timer == mytimer); + * + * Now del_timer_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but + * it has interrupted the softirq that CPU0 is waiting to finish. * * The function returns whether it has deactivated a pending timer or not. */ int del_timer_sync(struct timer_list *timer) { +#ifdef CONFIG_LOCKDEP + unsigned long flags; + + /* + * If lockdep gives a backtrace here, please reference + * the synchronization rules above. + */ + local_irq_save(flags); + lock_map_acquire(&timer->lockdep_map); + lock_map_release(&timer->lockdep_map); + local_irq_restore(flags); +#endif + /* + * don't use it in hardirq context, because it + * could lead to deadlock. + */ + WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base)); for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) @@ -376,11 +1088,10 @@ int del_timer_sync(struct timer_list *timer) 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; @@ -393,13 +1104,57 @@ 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); - internal_add_timer(base, timer); + BUG_ON(tbase_get_base(timer->base) != base); + /* No accounting, while moving them */ + __internal_add_timer(base, timer); } return index; } +static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), + unsigned long data) +{ + int count = preempt_count(); + +#ifdef CONFIG_LOCKDEP + /* + * It is permissible to free the timer from inside the + * function that is called from it, this we need to take into + * account for lockdep too. To avoid bogus "held lock freed" + * warnings as well as problems when looking into + * timer->lockdep_map, make a copy and use that here. + */ + struct lockdep_map lockdep_map; + + lockdep_copy_map(&lockdep_map, &timer->lockdep_map); +#endif + /* + * Couple the lock chain with the lock chain at + * del_timer_sync() by acquiring the lock_map around the fn() + * call here and in del_timer_sync(). + */ + lock_map_acquire(&lockdep_map); + + trace_timer_expire_entry(timer); + fn(data); + trace_timer_expire_exit(timer); + + lock_map_release(&lockdep_map); + + if (count != preempt_count()) { + WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n", + fn, count, preempt_count()); + /* + * Restore the preempt count. That gives us a decent + * chance to survive and extract information. If the + * callback kept a lock held, bad luck, but not worse + * than the BUG() we had. + */ + preempt_count_set(count); + } +} + #define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) /** @@ -409,15 +1164,19 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index) * This function cascades all vectors and executes all expired timer * vectors. */ -static inline void __run_timers(tvec_base_t *base) +static inline void __run_timers(struct tvec_base *base) { struct timer_list *timer; spin_lock_irq(&base->lock); + if (catchup_timer_jiffies(base)) { + spin_unlock_irq(&base->lock); + return; + } 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: @@ -428,538 +1187,190 @@ static inline void __run_timers(tvec_base_t *base) !cascade(base, &base->tv4, INDEX(2))) cascade(base, &base->tv5, INDEX(3)); ++base->timer_jiffies; - list_replace_init(base->tv1.vec + index, &work_list); + list_replace_init(base->tv1.vec + index, head); while (!list_empty(head)) { void (*fn)(unsigned long); unsigned long data; - - timer = list_entry(head->next,struct timer_list,entry); - fn = timer->function; - data = timer->data; - - set_running_timer(base, timer); - detach_timer(timer, 1); - spin_unlock_irq(&base->lock); - { - int preempt_count = preempt_count(); - fn(data); - if (preempt_count != preempt_count()) { - printk(KERN_WARNING "huh, entered %p " - "with preempt_count %08x, exited" - " with %08x?\n", - fn, preempt_count, - preempt_count()); - BUG(); - } + bool irqsafe; + + timer = list_first_entry(head, struct timer_list,entry); + fn = timer->function; + data = timer->data; + irqsafe = tbase_get_irqsafe(timer->base); + + timer_stats_account_timer(timer); + + base->running_timer = timer; + detach_expired_timer(timer, base); + + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock_irq(&base->lock); } - spin_lock_irq(&base->lock); } } - set_running_timer(base, NULL); + base->running_timer = NULL; spin_unlock_irq(&base->lock); } -#ifdef CONFIG_NO_IDLE_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Find out when the next timer event is due to happen. This - * is used on S/390 to stop all activity when a 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. */ -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); - do { - if (list_empty(varray[i]->vec + j)) { - j = (j + 1) & TVN_MASK; - continue; - } - list_for_each_entry(nte, varray[i]->vec + j, entry) - 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; - - return expires; -} -#endif - -/******************************************************************/ - -/* - * 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); - - -/* XXX - all of this timekeeping code should be later moved to time.c */ -#include <linux/clocksource.h> -static struct clocksource *clock; /* pointer to current clocksource */ - -#ifdef CONFIG_GENERIC_TIME -/** - * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook - * - * private function, must hold xtime_lock lock when being - * called. Returns the number of nanoseconds since the - * last call to update_wall_time() (adjusted by NTP scaling) - */ -static inline s64 __get_nsec_offset(void) -{ - cycle_t cycle_now, cycle_delta; - s64 ns_offset; - - /* read clocksource: */ - cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - - /* convert to nanoseconds: */ - ns_offset = cyc2ns(clock, cycle_delta); - - return ns_offset; -} - -/** - * __get_realtime_clock_ts - Returns the time of day in a timespec - * @ts: pointer to the timespec to be set - * - * Returns the time of day in a timespec. Used by - * do_gettimeofday() and get_realtime_clock_ts(). - */ -static inline void __get_realtime_clock_ts(struct timespec *ts) -{ - unsigned long seq; - s64 nsecs; - - do { - seq = read_seqbegin(&xtime_lock); - - *ts = xtime; - nsecs = __get_nsec_offset(); - - } while (read_seqretry(&xtime_lock, seq)); - - timespec_add_ns(ts, nsecs); -} - -/** - * getnstimeofday - Returns the time of day in a timespec - * @ts: pointer to the timespec to be set - * - * Returns the time of day in a timespec. - */ -void getnstimeofday(struct timespec *ts) -{ - __get_realtime_clock_ts(ts); -} -EXPORT_SYMBOL(getnstimeofday); + for (array = 0; array < 4; array++) { + struct tvec *varp = varray[array]; -/** - * do_gettimeofday - Returns the time of day in a timeval - * @tv: pointer to the timeval to be set - * - * NOTE: Users should be converted to using get_realtime_clock_ts() - */ -void do_gettimeofday(struct timeval *tv) -{ - struct timespec now; - - __get_realtime_clock_ts(&now); - tv->tv_sec = now.tv_sec; - tv->tv_usec = now.tv_nsec/1000; -} - -EXPORT_SYMBOL(do_gettimeofday); -/** - * do_settimeofday - Sets the time of day - * @tv: pointer to the timespec variable containing the new time - * - * Sets the time of day to the new time and update NTP and notify hrtimers - */ -int do_settimeofday(struct timespec *tv) -{ - unsigned long flags; - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; - - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) - return -EINVAL; - - write_seqlock_irqsave(&xtime_lock, flags); - - nsec -= __get_nsec_offset(); - - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); - - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - - clock->error = 0; - ntp_clear(); - - write_sequnlock_irqrestore(&xtime_lock, flags); - - /* signal hrtimers about time change */ - clock_was_set(); - - return 0; -} + index = slot = timer_jiffies & TVN_MASK; + do { + list_for_each_entry(nte, varp->vec + slot, entry) { + if (tbase_get_deferrable(nte->base)) + continue; -EXPORT_SYMBOL(do_settimeofday); + found = 1; + if (time_before(nte->expires, expires)) + expires = nte->expires; + } + /* + * Do we still search for the first timer or are + * we looking up the cascade buckets ? + */ + if (found) { + /* Look at the cascade bucket(s)? */ + if (!index || slot < index) + break; + return expires; + } + slot = (slot + 1) & TVN_MASK; + } while (slot != index); -/** - * change_clocksource - Swaps clocksources if a new one is available - * - * Accumulates current time interval and initializes new clocksource - */ -static int change_clocksource(void) -{ - struct clocksource *new; - cycle_t now; - u64 nsec; - new = clocksource_get_next(); - if (clock != new) { - now = clocksource_read(new); - nsec = __get_nsec_offset(); - timespec_add_ns(&xtime, nsec); - - clock = new; - clock->cycle_last = now; - printk(KERN_INFO "Time: %s clocksource has been installed.\n", - clock->name); - return 1; - } else if (clock->update_callback) { - return clock->update_callback(); + if (index) + timer_jiffies += TVN_SIZE - index; + timer_jiffies >>= TVN_BITS; } - return 0; -} -#else -#define change_clocksource() (0) -#endif - -/** - * timeofday_is_continuous - check to see if timekeeping is free running - */ -int timekeeping_is_continuous(void) -{ - unsigned long seq; - int ret; - - do { - seq = read_seqbegin(&xtime_lock); - - ret = clock->is_continuous; - - } while (read_seqretry(&xtime_lock, seq)); - - return ret; + return expires; } /* - * timekeeping_init - Initializes the clocksource and common timekeeping values + * Check, if the next hrtimer event is before the next timer wheel + * event: */ -void __init timekeeping_init(void) +static unsigned long cmp_next_hrtimer_event(unsigned long now, + unsigned long expires) { - unsigned long flags; - - write_seqlock_irqsave(&xtime_lock, flags); - - ntp_clear(); + ktime_t hr_delta = hrtimer_get_next_event(); + struct timespec tsdelta; + unsigned long delta; - clock = clocksource_get_next(); - clocksource_calculate_interval(clock, tick_nsec); - clock->cycle_last = clocksource_read(clock); + if (hr_delta.tv64 == KTIME_MAX) + return expires; - write_sequnlock_irqrestore(&xtime_lock, flags); -} - - -static int timekeeping_suspended; -/** - * timekeeping_resume - Resumes the generic timekeeping subsystem. - * @dev: unused - * - * This is for the generic clocksource timekeeping. - * xtime/wall_to_monotonic/jiffies/etc are - * still managed by arch specific suspend/resume code. - */ -static int timekeeping_resume(struct sys_device *dev) -{ - unsigned long flags; - - write_seqlock_irqsave(&xtime_lock, flags); - /* restart the last cycle value */ - clock->cycle_last = clocksource_read(clock); - clock->error = 0; - timekeeping_suspended = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); - return 0; -} - -static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) -{ - unsigned long flags; - - write_seqlock_irqsave(&xtime_lock, flags); - timekeeping_suspended = 1; - write_sequnlock_irqrestore(&xtime_lock, flags); - return 0; -} - -/* sysfs resume/suspend bits for timekeeping */ -static struct sysdev_class timekeeping_sysclass = { - .resume = timekeeping_resume, - .suspend = timekeeping_suspend, - set_kset_name("timekeeping"), -}; - -static struct sys_device device_timer = { - .id = 0, - .cls = &timekeeping_sysclass, -}; - -static int __init timekeeping_init_device(void) -{ - int error = sysdev_class_register(&timekeeping_sysclass); - if (!error) - error = sysdev_register(&device_timer); - return error; -} + /* + * Expired timer available, let it expire in the next tick + */ + if (hr_delta.tv64 <= 0) + return now + 1; -device_initcall(timekeeping_init_device); - -/* - * If the error is already larger, we look ahead even further - * to compensate for late or lost adjustments. - */ -static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, s64 *offset) -{ - s64 tick_error, i; - u32 look_ahead, adj; - s32 error2, mult; + tsdelta = ktime_to_timespec(hr_delta); + delta = timespec_to_jiffies(&tsdelta); /* - * Use the current error value to determine how much to look ahead. - * The larger the error the slower we adjust for it to avoid problems - * with losing too many ticks, otherwise we would overadjust and - * produce an even larger error. The smaller the adjustment the - * faster we try to adjust for it, as lost ticks can do less harm - * here. This is tuned so that an error of about 1 msec is adusted - * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). + * Limit the delta to the max value, which is checked in + * tick_nohz_stop_sched_tick(): */ - error2 = clock->error >> (TICK_LENGTH_SHIFT + 22 - 2 * SHIFT_HZ); - error2 = abs(error2); - for (look_ahead = 0; error2 > 0; look_ahead++) - error2 >>= 2; + if (delta > NEXT_TIMER_MAX_DELTA) + delta = NEXT_TIMER_MAX_DELTA; /* - * Now calculate the error in (1 << look_ahead) ticks, but first - * remove the single look ahead already included in the error. + * 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 */ - tick_error = current_tick_length() >> (TICK_LENGTH_SHIFT - clock->shift + 1); - tick_error -= clock->xtime_interval >> 1; - error = ((error - tick_error) >> look_ahead) + tick_error; - - /* Finally calculate the adjustment shift value. */ - i = *interval; - mult = 1; - if (error < 0) { - error = -error; - *interval = -*interval; - *offset = -*offset; - mult = -1; - } - for (adj = 0; error > i; adj++) - error >>= 1; - - *interval <<= adj; - *offset <<= adj; - return mult << adj; -} - -/* - * Adjust the multiplier to reduce the error value, - * this is optimized for the most common adjustments of -1,0,1, - * for other values we can do a bit more work. - */ -static void clocksource_adjust(struct clocksource *clock, s64 offset) -{ - s64 error, interval = clock->cycle_interval; - int adj; - - error = clock->error >> (TICK_LENGTH_SHIFT - clock->shift - 1); - if (error > interval) { - error >>= 2; - if (likely(error <= interval)) - adj = 1; - else - adj = clocksource_bigadjust(error, &interval, &offset); - } else if (error < -interval) { - error >>= 2; - if (likely(error >= -interval)) { - adj = -1; - interval = -interval; - offset = -offset; - } else - adj = clocksource_bigadjust(error, &interval, &offset); - } else - return; - - clock->mult += adj; - clock->xtime_interval += interval; - clock->xtime_nsec -= offset; - clock->error -= (interval - offset) << (TICK_LENGTH_SHIFT - clock->shift); + if (delta < 1) + delta = 1; + now += delta; + if (time_before(now, expires)) + return now; + return expires; } /** - * update_wall_time - Uses the current clocksource to increment the wall time - * - * Called from the timer interrupt, must hold a write on xtime_lock. + * get_next_timer_interrupt - return the jiffy of the next pending timer + * @now: current time (in jiffies) */ -static void update_wall_time(void) +unsigned long get_next_timer_interrupt(unsigned long now) { - cycle_t offset; + struct tvec_base *base = __this_cpu_read(tvec_bases); + unsigned long expires = now + NEXT_TIMER_MAX_DELTA; - /* Make sure we're fully resumed: */ - if (unlikely(timekeeping_suspended)) - return; - -#ifdef CONFIG_GENERIC_TIME - offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask; -#else - offset = clock->cycle_interval; -#endif - clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift; - - /* normally this loop will run just once, however in the - * case of lost or late ticks, it will accumulate correctly. + /* + * Pretend that there is no timer pending if the cpu is offline. + * Possible pending timers will be migrated later to an active cpu. */ - while (offset >= clock->cycle_interval) { - /* accumulate one interval */ - clock->xtime_nsec += clock->xtime_interval; - clock->cycle_last += clock->cycle_interval; - offset -= clock->cycle_interval; - - if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { - clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; - xtime.tv_sec++; - second_overflow(); - } - - /* interpolator bits */ - time_interpolator_update(clock->xtime_interval - >> clock->shift); + if (cpu_is_offline(smp_processor_id())) + return expires; - /* accumulate error between NTP and clock interval */ - clock->error += current_tick_length(); - clock->error -= clock->xtime_interval << (TICK_LENGTH_SHIFT - clock->shift); + spin_lock(&base->lock); + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; } + spin_unlock(&base->lock); - /* correct the clock when NTP error is too big */ - clocksource_adjust(clock, offset); - - /* store full nanoseconds into xtime */ - xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift; - clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; + if (time_before_eq(expires, now)) + return now; - /* check to see if there is a new clocksource to use */ - if (change_clocksource()) { - clock->error = 0; - clock->xtime_nsec = 0; - clocksource_calculate_interval(clock, tick_nsec); - } + return cmp_next_hrtimer_event(now, expires); } +#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) @@ -968,72 +1379,26 @@ 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); + rcu_check_callbacks(cpu, user_tick); +#ifdef CONFIG_IRQ_WORK + if (in_irq()) + irq_work_run(); +#endif 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; - - active_tasks = count_active_tasks(); - for (count -= ticks; count < 0; count += LOAD_FREQ) { - CALC_LOAD(avenrun[0], EXP_1, active_tasks); - CALC_LOAD(avenrun[1], EXP_5, active_tasks); - CALC_LOAD(avenrun[2], EXP_15, active_tasks); - } + run_posix_cpu_timers(p); } /* - * This read-write spinlock protects us from races in SMP while - * playing with xtime and avenrun. - */ -#ifndef ARCH_HAVE_XTIME_LOCK -__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - -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 = __this_cpu_read(tvec_bases); + + hrtimer_run_pending(); - hrtimer_run_queues(); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } @@ -1043,30 +1408,8 @@ static void run_timer_softirq(struct softirq_action *h) */ void run_local_timers(void) { + hrtimer_run_queues(); raise_softirq(TIMER_SOFTIRQ); - softlockup_tick(); -} - -/* - * 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... - */ - -void do_timer(unsigned long ticks) -{ - jiffies_64 += ticks; - update_times(ticks); } #ifdef __ARCH_WANT_SYS_ALARM @@ -1075,77 +1418,13 @@ void do_timer(unsigned long ticks) * For backwards compatibility? This can be done in libc so Alpha * and all newer ports shouldn't need it. */ -asmlinkage unsigned long sys_alarm(unsigned int seconds) +SYSCALL_DEFINE1(alarm, unsigned int, seconds) { return alarm_setitimer(seconds); } #endif -#ifndef __alpha__ - -/* - * The Alpha uses getxpid, getxuid, and getxgid instead. Maybe this - * should be moved into arch/i386 instead? - */ - -/** - * sys_getpid - return the thread group id of the current process - * - * Note, despite the name, this returns the tgid not the pid. The tgid and - * the pid are identical unless CLONE_THREAD was specified on clone() in - * which case the tgid is the same in all threads of the same group. - * - * This is SMP safe as current->tgid does not change. - */ -asmlinkage long sys_getpid(void) -{ - return current->tgid; -} - -/* - * 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; - - rcu_read_lock(); - pid = rcu_dereference(current->real_parent)->tgid; - rcu_read_unlock(); - - return pid; -} - -asmlinkage long sys_getuid(void) -{ - /* Only we change this so SMP safe */ - return current->uid; -} - -asmlinkage long sys_geteuid(void) -{ - /* Only we change this so SMP safe */ - return current->euid; -} - -asmlinkage long sys_getgid(void) -{ - /* Only we change this so SMP safe */ - return current->gid; -} - -asmlinkage long sys_getegid(void) -{ - /* Only we change this so SMP safe */ - return current->egid; -} - -#endif - static void process_timeout(unsigned long __data) { wake_up_process((struct task_struct *)__data); @@ -1177,7 +1456,7 @@ 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; @@ -1202,11 +1481,10 @@ 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; } @@ -1214,11 +1492,14 @@ fastcall signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; - setup_timer(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire); + setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); + __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); schedule(); del_singleshot_timer_sync(&timer); + /* Remove the timer from the object tracker */ + destroy_timer_on_stack(&timer); + timeout = expire - jiffies; out: @@ -1237,121 +1518,25 @@ signed long __sched schedule_timeout_interruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_interruptible); -signed long __sched schedule_timeout_uninterruptible(signed long timeout) +signed long __sched schedule_timeout_killable(signed long timeout) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } -EXPORT_SYMBOL(schedule_timeout_uninterruptible); - -/* Thread ID - the internal kernel "pid" */ -asmlinkage long sys_gettid(void) -{ - return current->pid; -} +EXPORT_SYMBOL(schedule_timeout_killable); -/** - * sys_sysinfo - fill in sysinfo struct - * @info: pointer to buffer to fill - */ -asmlinkage long sys_sysinfo(struct sysinfo __user *info) +signed long __sched schedule_timeout_uninterruptible(signed long timeout) { - struct sysinfo val; - unsigned long mem_total, sav_total; - unsigned int mem_unit, bitcount; - unsigned long seq; - - memset((char *)&val, 0, sizeof(struct sysinfo)); - - do { - struct timespec tp; - seq = read_seqbegin(&xtime_lock); - - /* - * 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. - */ - - getnstimeofday(&tp); - tp.tv_sec += wall_to_monotonic.tv_sec; - tp.tv_nsec += wall_to_monotonic.tv_nsec; - 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); - - 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); - - val.procs = nr_threads; - } while (read_seqretry(&xtime_lock, seq)); - - si_meminfo(&val); - si_swapinfo(&val); - - /* - * If the sum of all the available memory (i.e. ram + swap) - * is less than can be stored in a 32 bit unsigned long then - * we can be binary compatible with 2.2.x kernels. If not, - * well, in that case 2.2.x was broken anyways... - * - * -Erik Andersen <andersee@debian.org> - */ - - mem_total = val.totalram + val.totalswap; - if (mem_total < val.totalram || mem_total < val.totalswap) - goto out; - bitcount = 0; - mem_unit = val.mem_unit; - while (mem_unit > 1) { - bitcount++; - mem_unit >>= 1; - sav_total = mem_total; - mem_total <<= 1; - if (mem_total < sav_total) - goto out; - } - - /* - * If mem_total did not overflow, multiply all memory values by - * val.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; - - out: - if (copy_to_user(info, &val, sizeof(struct sysinfo))) - return -EFAULT; - - return 0; + __set_current_state(TASK_UNINTERRUPTIBLE); + return schedule_timeout(timeout); } +EXPORT_SYMBOL(schedule_timeout_uninterruptible); -/* - * lockdep: we want to track each per-CPU base as a separate lock-class, - * but timer-bases are kmalloc()-ed, so we need to attach separate - * keys to them: - */ -static struct lock_class_key base_lock_keys[NR_CPUS]; - -static int __devinit init_timers_cpu(int cpu) +static int 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 tvec_base_done[NR_CPUS]; if (!tvec_base_done[cpu]) { static char boot_done; @@ -1360,11 +1545,16 @@ static int __devinit init_timers_cpu(int cpu) /* * The APs use this path later in boot */ - base = kmalloc_node(sizeof(*base), GFP_KERNEL, - cpu_to_node(cpu)); + base = kzalloc_node(sizeof(*base), GFP_KERNEL, + cpu_to_node(cpu)); if (!base) return -ENOMEM; - memset(base, 0, sizeof(*base)); + + /* Make sure tvec_base has TIMER_FLAG_MASK bits free */ + if (WARN_ON(base != tbase_get_base(base))) { + kfree(base); + return -ENOMEM; + } per_cpu(tvec_bases, cpu) = base; } else { /* @@ -1376,13 +1566,12 @@ static int __devinit init_timers_cpu(int cpu) boot_done = 1; base = &boot_tvec_bases; } + spin_lock_init(&base->lock); tvec_base_done[cpu] = 1; } else { base = per_cpu(tvec_bases, cpu); } - spin_lock_init(&base->lock); - lockdep_set_class(&base->lock, base_lock_keys + cpu); for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); @@ -1394,35 +1583,41 @@ static int __devinit init_timers_cpu(int cpu) INIT_LIST_HEAD(base->tv1.vec + j); base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; + base->active_timers = 0; + base->all_timers = 0; return 0; } #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); - detach_timer(timer, 0); - timer->base = new_base; + timer = list_first_entry(head, struct timer_list, entry); + /* We ignore the accounting on the dying cpu */ + detach_timer(timer, false); + timer_set_base(timer, new_base); internal_add_timer(new_base, timer); } } -static void __devinit migrate_timers(int cpu) +static void 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)); old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); - - local_irq_disable(); - spin_lock(&new_base->lock); - spin_lock(&old_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); @@ -1436,23 +1631,27 @@ static void __devinit migrate_timers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ -static int __cpuinit timer_cpu_notify(struct notifier_block *self, +static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; + int err; + switch(action) { case CPU_UP_PREPARE: - if (init_timers_cpu(cpu) < 0) - return NOTIFY_BAD; + case CPU_UP_PREPARE_FROZEN: + err = init_timers_cpu(cpu); + if (err < 0) + return notifier_from_errno(err); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: + case CPU_DEAD_FROZEN: migrate_timers(cpu); break; #endif @@ -1462,208 +1661,26 @@ static int __cpuinit timer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata timers_nb = { +static struct notifier_block timers_nb = { .notifier_call = timer_cpu_notify, }; void __init init_timers(void) { - int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - - BUG_ON(err == NOTIFY_BAD); - register_cpu_notifier(&timers_nb); - open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); -} + int err; -#ifdef CONFIG_TIME_INTERPOLATION + /* ensure there are enough low bits for flags in timer->base pointer */ + BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); -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 - -void time_interpolator_update(long delta_nsec) -{ - u64 counter; - unsigned long offset; + err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + BUG_ON(err != NOTIFY_OK); - /* 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); + init_timer_stats(); + register_cpu_notifier(&timers_nb); + open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } -#endif /* CONFIG_TIME_INTERPOLATION */ /** * msleep - sleep safely even with waitqueue interruptions @@ -1693,3 +1710,25 @@ unsigned long msleep_interruptible(unsigned int msecs) } EXPORT_SYMBOL(msleep_interruptible); + +static int __sched do_usleep_range(unsigned long min, unsigned long max) +{ + ktime_t kmin; + unsigned long delta; + + kmin = ktime_set(0, min * NSEC_PER_USEC); + delta = (max - min) * NSEC_PER_USEC; + return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); +} + +/** + * usleep_range - Drop in replacement for udelay where wakeup is flexible + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + */ +void usleep_range(unsigned long min, unsigned long max) +{ + __set_current_state(TASK_UNINTERRUPTIBLE); + do_usleep_range(min, max); +} +EXPORT_SYMBOL(usleep_range); |