diff options
Diffstat (limited to 'kernel/timer.c')
| -rw-r--r-- | kernel/timer.c | 1734 |
1 files changed, 0 insertions, 1734 deletions
diff --git a/kernel/timer.c b/kernel/timer.c deleted file mode 100644 index 3bb01a323b2a..000000000000 --- a/kernel/timer.c +++ /dev/null @@ -1,1734 +0,0 @@ -/* - * linux/kernel/timer.c - * - * Kernel internal timers - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. - * - * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 - * "A Kernel Model for Precision Timekeeping" by Dave Mills - * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to - * serialize accesses to xtime/lost_ticks). - * Copyright (C) 1998 Andrea Arcangeli - * 1999-03-10 Improved NTP compatibility by Ulrich Windl - * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love - * 2000-10-05 Implemented scalable SMP per-CPU timer handling. - * Copyright (C) 2000, 2001, 2002 Ingo Molnar - * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar - */ - -#include <linux/kernel_stat.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> -#include <linux/jiffies.h> -#include <linux/posix-timers.h> -#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> -#include <asm/div64.h> -#include <asm/timex.h> -#include <asm/io.h> - -#define CREATE_TRACE_POINTS -#include <trace/events/timer.h> - -__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; - -EXPORT_SYMBOL(jiffies_64); - -/* - * per-CPU timer vector definitions: - */ -#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6) -#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8) -#define TVN_SIZE (1 << TVN_BITS) -#define TVR_SIZE (1 << TVR_BITS) -#define TVN_MASK (TVN_SIZE - 1) -#define TVR_MASK (TVR_SIZE - 1) -#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) - -struct tvec { - struct list_head vec[TVN_SIZE]; -}; - -struct tvec_root { - struct list_head vec[TVR_SIZE]; -}; - -struct tvec_base { - spinlock_t lock; - struct timer_list *running_timer; - unsigned long timer_jiffies; - unsigned long next_timer; - unsigned long active_timers; - unsigned long all_timers; - 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; - -/* 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); -} - -static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) -{ - return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); -} - -static inline struct tvec_base *tbase_get_base(struct tvec_base *base) -{ - 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); - -/* - * 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; - struct list_head *vec; - - if (idx < TVR_SIZE) { - int i = expires & TVR_MASK; - vec = base->tv1.vec + i; - } else if (idx < 1 << (TVR_BITS + TVN_BITS)) { - int i = (expires >> TVR_BITS) & TVN_MASK; - vec = base->tv2.vec + i; - } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK; - vec = base->tv3.vec + i; - } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK; - vec = base->tv4.vec + i; - } else if ((signed long) idx < 0) { - /* - * Can happen if you add a timer with expires == jiffies, - * or you set a timer to go off in the past - */ - vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); - } else { - int i; - /* If the timeout is larger than MAX_TVAL (on 64-bit - * architectures or with CONFIG_BASE_SMALL=1) then we - * use the maximum timeout. - */ - if (idx > MAX_TVAL) { - idx = MAX_TVAL; - expires = idx + base->timer_jiffies; - } - i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; - vec = base->tv5.vec + i; - } - /* - * Timers are FIFO: - */ - 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_key - initialize a timer - * @timer: the timer to be initialized - * @flags: timer flags - * @name: name of the timer - * @key: lockdep class key of the fake lock used for tracking timer - * sync lock dependencies - * - * init_timer_key() must be done to a timer prior calling *any* of the - * other timer functions. - */ -void init_timer_key(struct timer_list *timer, unsigned int flags, - const char *name, struct lock_class_key *key) -{ - debug_init(timer); - do_init_timer(timer, flags, name, key); -} -EXPORT_SYMBOL(init_timer_key); - -static inline void detach_timer(struct timer_list *timer, bool clear_pending) -{ - struct 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 - * locked, and the base itself is locked too. - * - * So __run_timers/migrate_timers can safely modify all timers which could - * be found on ->tvX lists. - * - * When the timer's base is locked, and the timer removed from list, it is - * possible to set timer->base = NULL and drop the lock: the timer remains - * locked. - */ -static struct tvec_base *lock_timer_base(struct timer_list *timer, - unsigned long *flags) - __acquires(timer->base->lock) -{ - struct tvec_base *base; - - for (;;) { - 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(prelock_base == timer->base)) - return base; - /* The timer has migrated to another CPU */ - spin_unlock_irqrestore(&base->lock, *flags); - } - cpu_relax(); - } -} - -static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, - bool pending_only, int pinned) -{ - struct tvec_base *base, *new_base; - unsigned long flags; - int ret = 0 , cpu; - - timer_stats_timer_set_start_info(timer); - BUG_ON(!timer->function); - - base = lock_timer_base(timer, &flags); - - ret = detach_if_pending(timer, base, false); - if (!ret && pending_only) - goto out_unlock; - - debug_activate(timer, expires); - - cpu = get_nohz_timer_target(pinned); - new_base = per_cpu(tvec_bases, cpu); - - if (base != new_base) { - /* - * We are trying to schedule the timer on the local CPU. - * However we can't change timer's base while it is running, - * otherwise del_timer_sync() can't detect that the timer's - * handler yet has not finished. This also guarantees that - * the timer is serialized wrt itself. - */ - if (likely(base->running_timer != timer)) { - /* See the comment in lock_timer_base() */ - timer_set_base(timer, NULL); - spin_unlock(&base->lock); - base = new_base; - spin_lock(&base->lock); - timer_set_base(timer, base); - } - } - - timer->expires = expires; - internal_add_timer(base, timer); - -out_unlock: - spin_unlock_irqrestore(&base->lock, flags); - - return ret; -} - -/** - * mod_timer_pending - modify a pending timer's timeout - * @timer: the pending timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer_pending() is the same for pending timers as mod_timer(), - * but will not re-activate and modify already deleted timers. - * - * It is useful for unserialized use of timers. - */ -int mod_timer_pending(struct timer_list *timer, unsigned long expires) -{ - return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); -} -EXPORT_SYMBOL(mod_timer_pending); - -/* - * Decide where to put the timer while taking the slack into account - * - * Algorithm: - * 1) calculate the maximum (absolute) time - * 2) calculate the highest bit where the expires and new max are different - * 3) use this bit to make a mask - * 4) use the bitmask to round down the maximum time, so that all last - * bits are zeros - */ -static inline -unsigned long apply_slack(struct timer_list *timer, unsigned long expires) -{ - unsigned long expires_limit, mask; - int bit; - - if (timer->slack >= 0) { - expires_limit = expires + timer->slack; - } else { - long delta = expires - jiffies; - - if (delta < 256) - return expires; - - expires_limit = expires + delta / 256; - } - mask = expires ^ expires_limit; - if (mask == 0) - return expires; - - bit = 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 - * active timer (if the timer is inactive it will be activated) - * - * mod_timer(timer, expires) is equivalent to: - * - * del_timer(timer); timer->expires = expires; add_timer(timer); - * - * Note that if there are multiple unserialized concurrent users of the - * same timer, then mod_timer() is the only safe way to modify the timeout, - * since add_timer() cannot modify an already running timer. - * - * The function returns whether it has modified a pending timer or not. - * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an - * active timer returns 1.) - */ -int mod_timer(struct timer_list *timer, unsigned long expires) -{ - expires = apply_slack(timer, expires); - - /* - * This is a common optimization triggered by the - * networking code - if the timer is re-modified - * to be the same thing then just return: - */ - if (timer_pending(timer) && timer->expires == expires) - return 1; - - return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); -} -EXPORT_SYMBOL(mod_timer); - -/** - * mod_timer_pinned - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer_pinned() is a way to update the expire field of an - * active timer (if the timer is inactive it will be activated) - * and to ensure that the timer is scheduled on the current CPU. - * - * Note that this does not prevent the timer from being migrated - * when the current CPU goes offline. If this is a problem for - * you, use CPU-hotplug notifiers to handle it correctly, for - * example, cancelling the timer when the corresponding CPU goes - * offline. - * - * mod_timer_pinned(timer, expires) is equivalent to: - * - * del_timer(timer); timer->expires = expires; add_timer(timer); - */ -int mod_timer_pinned(struct timer_list *timer, unsigned long expires) -{ - if (timer->expires == expires && timer_pending(timer)) - return 1; - - return __mod_timer(timer, expires, false, TIMER_PINNED); -} -EXPORT_SYMBOL(mod_timer_pinned); - -/** - * add_timer - start a timer - * @timer: the timer to be added - * - * The kernel will do a ->function(->data) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. - * - * The timer's ->expires, ->function (and if the handler uses it, ->data) - * fields must be set prior calling this function. - * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. - */ -void add_timer(struct timer_list *timer) -{ - BUG_ON(timer_pending(timer)); - mod_timer(timer, timer->expires); -} -EXPORT_SYMBOL(add_timer); - -/** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on - * - * This is not very scalable on SMP. Double adds are not possible. - */ -void add_timer_on(struct timer_list *timer, int cpu) -{ - struct tvec_base *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. - * @timer: the timer to be deactivated - * - * del_timer() deactivates a timer - this works on both active and inactive - * timers. - * - * The function returns whether it has deactivated a pending timer or not. - * (ie. del_timer() of an inactive timer returns 0, del_timer() of an - * active timer returns 1.) - */ -int del_timer(struct timer_list *timer) -{ - struct tvec_base *base; - unsigned long flags; - int ret = 0; - - debug_assert_init(timer); - - timer_stats_timer_clear_start_info(timer); - if (timer_pending(timer)) { - base = lock_timer_base(timer, &flags); - ret = detach_if_pending(timer, base, true); - spin_unlock_irqrestore(&base->lock, flags); - } - - return ret; -} -EXPORT_SYMBOL(del_timer); - -/** - * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer do del - * - * This function tries to deactivate a timer. Upon successful (ret >= 0) - * exit the timer is not queued and the handler is not running on any CPU. - */ -int try_to_del_timer_sync(struct timer_list *timer) -{ - struct tvec_base *base; - unsigned long flags; - int ret = -1; - - debug_assert_init(timer); - - base = lock_timer_base(timer, &flags); - - if (base->running_timer != timer) { - timer_stats_timer_clear_start_info(timer); - ret = detach_if_pending(timer, base, true); - } - spin_unlock_irqrestore(&base->lock, flags); - - return ret; -} -EXPORT_SYMBOL(try_to_del_timer_sync); - -#ifdef CONFIG_SMP -/** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated - * - * This function only differs from del_timer() on SMP: besides deactivating - * the timer it also makes sure the handler has finished executing on other - * CPUs. - * - * Synchronization rules: Callers must prevent restarting of the timer, - * otherwise this function is meaningless. It must not be called from - * interrupt contexts unless the timer is an irqsafe one. The caller must - * not hold locks which would prevent completion of the timer's - * handler. The timer's handler must not call add_timer_on(). Upon exit the - * timer is not queued and the handler is not running on any CPU. - * - * Note: For !irqsafe timers, you must not hold locks that are held in - * interrupt context while calling this function. Even if the lock has - * nothing to do with the timer in question. Here's why: - * - * CPU0 CPU1 - * ---- ---- - * <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) - return ret; - cpu_relax(); - } -} -EXPORT_SYMBOL(del_timer_sync); -#endif - -static int cascade(struct tvec_base *base, struct tvec *tv, int index) -{ - /* cascade all the timers from tv up one level */ - struct timer_list *timer, *tmp; - struct list_head tv_list; - - list_replace_init(tv->vec + index, &tv_list); - - /* - * We are removing _all_ timers from the list, so we - * don't have to detach them individually. - */ - list_for_each_entry_safe(timer, tmp, &tv_list, entry) { - BUG_ON(tbase_get_b |