diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 3 | ||||
-rw-r--r-- | kernel/hrtimer.c | 679 | ||||
-rw-r--r-- | kernel/timer.c | 1 |
3 files changed, 682 insertions, 1 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 1e03970..3551266 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,7 +7,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ sysctl.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o intermodule.o extable.o params.o posix-timers.o \ - kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o + kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ + hrtimer.o obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o obj-$(CONFIG_FUTEX) += futex.o diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c new file mode 100644 index 0000000..690efd9 --- /dev/null +++ b/kernel/hrtimer.c @@ -0,0 +1,679 @@ +/* + * linux/kernel/hrtimer.c + * + * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar + * + * High-resolution kernel timers + * + * In contrast to the low-resolution timeout API implemented in + * kernel/timer.c, hrtimers provide finer resolution and accuracy + * depending on system configuration and capabilities. + * + * These timers are currently used for: + * - itimers + * - POSIX timers + * - nanosleep + * - precise in-kernel timing + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * Credits: + * based on kernel/timer.c + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/cpu.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/hrtimer.h> +#include <linux/notifier.h> +#include <linux/syscalls.h> +#include <linux/interrupt.h> + +#include <asm/uaccess.h> + +/** + * ktime_get - get the monotonic time in ktime_t format + * + * returns the time in ktime_t format + */ +static ktime_t ktime_get(void) +{ + struct timespec now; + + ktime_get_ts(&now); + + return timespec_to_ktime(now); +} + +/** + * ktime_get_real - get the real (wall-) time in ktime_t format + * + * returns the time in ktime_t format + */ +static ktime_t ktime_get_real(void) +{ + struct timespec now; + + getnstimeofday(&now); + + return timespec_to_ktime(now); +} + +EXPORT_SYMBOL_GPL(ktime_get_real); + +/* + * The timer bases: + */ + +#define MAX_HRTIMER_BASES 2 + +static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) = +{ + { + .index = CLOCK_REALTIME, + .get_time = &ktime_get_real, + .resolution = KTIME_REALTIME_RES, + }, + { + .index = CLOCK_MONOTONIC, + .get_time = &ktime_get, + .resolution = KTIME_MONOTONIC_RES, + }, +}; + +/** + * ktime_get_ts - get the monotonic clock in timespec format + * + * @ts: pointer to timespec variable + * + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by ts. + */ +void ktime_get_ts(struct timespec *ts) +{ + struct timespec tomono; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + getnstimeofday(ts); + tomono = wall_to_monotonic; + + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, + ts->tv_nsec + tomono.tv_nsec); +} + +/* + * Functions and macros which are different for UP/SMP systems are kept in a + * single place + */ +#ifdef CONFIG_SMP + +#define set_curr_timer(b, t) do { (b)->curr_timer = (t); } while (0) + +/* + * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].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 the lists/queues. + * + * 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 hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer, + unsigned long *flags) +{ + struct hrtimer_base *base; + + for (;;) { + base = timer->base; + if (likely(base != NULL)) { + spin_lock_irqsave(&base->lock, *flags); + if (likely(base == timer->base)) + return base; + /* The timer has migrated to another CPU: */ + spin_unlock_irqrestore(&base->lock, *flags); + } + cpu_relax(); + } +} + +/* + * Switch the timer base to the current CPU when possible. + */ +static inline struct hrtimer_base * +switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base) +{ + struct hrtimer_base *new_base; + + new_base = &__get_cpu_var(hrtimer_bases[base->index]); + + 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, + * so we keep it on the same CPU. No hassle vs. reprogramming + * the event source in the high resolution case. The softirq + * code will take care of this when the timer function has + * completed. There is no conflict as we hold the lock until + * the timer is enqueued. + */ + if (unlikely(base->curr_timer == timer)) + return base; + + /* See the comment in lock_timer_base() */ + timer->base = NULL; + spin_unlock(&base->lock); + spin_lock(&new_base->lock); + timer->base = new_base; + } + return new_base; +} + +#else /* CONFIG_SMP */ + +#define set_curr_timer(b, t) do { } while (0) + +static inline struct hrtimer_base * +lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + struct hrtimer_base *base = timer->base; + + spin_lock_irqsave(&base->lock, *flags); + + return base; +} + +#define switch_hrtimer_base(t, b) (b) + +#endif /* !CONFIG_SMP */ + +/* + * Functions for the union type storage format of ktime_t which are + * too large for inlining: + */ +#if BITS_PER_LONG < 64 +# ifndef CONFIG_KTIME_SCALAR +/** + * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable + * + * @kt: addend + * @nsec: the scalar nsec value to add + * + * Returns the sum of kt and nsec in ktime_t format + */ +ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) +{ + ktime_t tmp; + + if (likely(nsec < NSEC_PER_SEC)) { + tmp.tv64 = nsec; + } else { + unsigned long rem = do_div(nsec, NSEC_PER_SEC); + + tmp = ktime_set((long)nsec, rem); + } + + return ktime_add(kt, tmp); +} + +#else /* CONFIG_KTIME_SCALAR */ + +# endif /* !CONFIG_KTIME_SCALAR */ + +/* + * Divide a ktime value by a nanosecond value + */ +static unsigned long ktime_divns(const ktime_t kt, nsec_t div) +{ + u64 dclc, inc, dns; + int sft = 0; + + dclc = dns = ktime_to_ns(kt); + inc = div; + /* Make sure the divisor is less than 2^32: */ + while (div >> 32) { + sft++; + div >>= 1; + } + dclc >>= sft; + do_div(dclc, (unsigned long) div); + + return (unsigned long) dclc; +} + +#else /* BITS_PER_LONG < 64 */ +# define ktime_divns(kt, div) (unsigned long)((kt).tv64 / (div)) +#endif /* BITS_PER_LONG >= 64 */ + +/* + * Counterpart to lock_timer_base above: + */ +static inline +void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + spin_unlock_irqrestore(&timer->base->lock, *flags); +} + +/** + * hrtimer_forward - forward the timer expiry + * + * @timer: hrtimer to forward + * @interval: the interval to forward + * + * Forward the timer expiry so it will expire in the future. + * The number of overruns is added to the overrun field. + */ +unsigned long +hrtimer_forward(struct hrtimer *timer, const ktime_t interval) +{ + unsigned long orun = 1; + ktime_t delta, now; + + now = timer->base->get_time(); + + delta = ktime_sub(now, timer->expires); + + if (delta.tv64 < 0) + return 0; + + if (unlikely(delta.tv64 >= interval.tv64)) { + nsec_t incr = ktime_to_ns(interval); + + orun = ktime_divns(delta, incr); + timer->expires = ktime_add_ns(timer->expires, incr * orun); + if (timer->expires.tv64 > now.tv64) + return orun; + /* + * This (and the ktime_add() below) is the + * correction for exact: + */ + orun++; + } + timer->expires = ktime_add(timer->expires, interval); + + return orun; +} + +/* + * enqueue_hrtimer - internal function to (re)start a timer + * + * The timer is inserted in expiry order. Insertion into the + * red black tree is O(log(n)). Must hold the base lock. + */ +static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + struct rb_node **link = &base->active.rb_node; + struct list_head *prev = &base->pending; + struct rb_node *parent = NULL; + struct hrtimer *entry; + + /* + * Find the right place in the rbtree: + */ + while (*link) { + parent = *link; + entry = rb_entry(parent, struct hrtimer, node); + /* + * We dont care about collisions. Nodes with + * the same expiry time stay together. + */ + if (timer->expires.tv64 < entry->expires.tv64) + link = &(*link)->rb_left; + else { + link = &(*link)->rb_right; + prev = &entry->list; + } + } + + /* + * Insert the timer to the rbtree and to the sorted list: + */ + rb_link_node(&timer->node, parent, link); + rb_insert_color(&timer->node, &base->active); + list_add(&timer->list, prev); + + timer->state = HRTIMER_PENDING; +} + + +/* + * __remove_hrtimer - internal function to remove a timer + * + * Caller must hold the base lock. + */ +static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + /* + * Remove the timer from the sorted list and from the rbtree: + */ + list_del(&timer->list); + rb_erase(&timer->node, &base->active); +} + +/* + * remove hrtimer, called with base lock held + */ +static inline int +remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + if (hrtimer_active(timer)) { + __remove_hrtimer(timer, base); + timer->state = HRTIMER_INACTIVE; + return 1; + } + return 0; +} + +/** + * hrtimer_start - (re)start an relative timer on the current CPU + * + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + struct hrtimer_base *base, *new_base; + unsigned long flags; + int ret; + + base = lock_hrtimer_base(timer, &flags); + + /* Remove an active timer from the queue: */ + ret = remove_hrtimer(timer, base); + + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base); + + if (mode == HRTIMER_REL) + tim = ktime_add(tim, new_base->get_time()); + timer->expires = tim; + + enqueue_hrtimer(timer, new_base); + + unlock_hrtimer_base(timer, &flags); + + return ret; +} + +/** + * hrtimer_try_to_cancel - try to deactivate a timer + * + * @timer: hrtimer to stop + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + * -1 when the timer is currently excuting the callback function and + * can not be stopped + */ +int hrtimer_try_to_cancel(struct hrtimer *timer) +{ + struct hrtimer_base *base; + unsigned long flags; + int ret = -1; + + base = lock_hrtimer_base(timer, &flags); + + if (base->curr_timer != timer) + ret = remove_hrtimer(timer, base); + + unlock_hrtimer_base(timer, &flags); + + return ret; + +} + +/** + * hrtimer_cancel - cancel a timer and wait for the handler to finish. + * + * @timer: the timer to be cancelled + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + */ +int hrtimer_cancel(struct hrtimer *timer) +{ + for (;;) { + int ret = hrtimer_try_to_cancel(timer); + + if (ret >= 0) + return ret; + } +} + +/** + * hrtimer_get_remaining - get remaining time for the timer + * + * @timer: the timer to read + */ +ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + struct hrtimer_base *base; + unsigned long flags; + ktime_t rem; + + base = lock_hrtimer_base(timer, &flags); + rem = ktime_sub(timer->expires, timer->base->get_time()); + unlock_hrtimer_base(timer, &flags); + + return rem; +} + +/** + * hrtimer_rebase - rebase an initialized hrtimer to a different base + * + * @timer: the timer to be rebased + * @clock_id: the clock to be used + */ +void hrtimer_rebase(struct hrtimer *timer, const clockid_t clock_id) +{ + struct hrtimer_base *bases; + + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); + timer->base = &bases[clock_id]; +} + +/** + * hrtimer_init - initialize a timer to the given clock + * + * @timer: the timer to be initialized + * @clock_id: the clock to be used + */ +void hrtimer_init(struct hrtimer *timer, const clockid_t clock_id) +{ + memset(timer, 0, sizeof(struct hrtimer)); + hrtimer_rebase(timer, clock_id); +} + +/** + * hrtimer_get_res - get the timer resolution for a clock + * + * @which_clock: which clock to query + * @tp: pointer to timespec variable to store the resolution + * + * Store the resolution of the clock selected by which_clock in the + * variable pointed to by tp. + */ +int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) +{ + struct hrtimer_base *bases; + + tp->tv_sec = 0; + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); + tp->tv_nsec = bases[which_clock].resolution; + + return 0; +} + +/* + * Expire the per base hrtimer-queue: + */ +static inline void run_hrtimer_queue(struct hrtimer_base *base) +{ + ktime_t now = base->get_time(); + + spin_lock_irq(&base->lock); + + while (!list_empty(&base->pending)) { + struct hrtimer *timer; + int (*fn)(void *); + int restart; + void *data; + + timer = list_entry(base->pending.next, struct hrtimer, list); + if (now.tv64 <= timer->expires.tv64) + break; + + fn = timer->function; + data = timer->data; + set_curr_timer(base, timer); + __remove_hrtimer(timer, base); + spin_unlock_irq(&base->lock); + + /* + * fn == NULL is special case for the simplest timer + * variant - wake up process and do not restart: + */ + if (!fn) { + wake_up_process(data); + restart = HRTIMER_NORESTART; + } else + restart = fn(data); + + spin_lock_irq(&base->lock); + + if (restart == HRTIMER_RESTART) + enqueue_hrtimer(timer, base); + else + timer->state = HRTIMER_EXPIRED; + } + set_curr_timer(base, NULL); + spin_unlock_irq(&base->lock); +} + +/* + * Called from timer softirq every jiffy, expire hrtimers: + */ +void hrtimer_run_queues(void) +{ + struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++) + run_hrtimer_queue(&base[i]); +} + +/* + * Functions related to boot-time initialization: + */ +static void __devinit init_hrtimers_cpu(int cpu) +{ + struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++) { + spin_lock_init(&base->lock); + INIT_LIST_HEAD(&base->pending); + base++; + } +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void migrate_hrtimer_list(struct hrtimer_base *old_base, + struct hrtimer_base *new_base) +{ + struct hrtimer *timer; + struct rb_node *node; + + while ((node = rb_first(&old_base->active))) { + timer = rb_entry(node, struct hrtimer, node); + __remove_hrtimer(timer, old_base); + timer->base = new_base; + enqueue_hrtimer(timer, new_base); + } +} + +static void migrate_hrtimers(int cpu) +{ + struct hrtimer_base *old_base, *new_base; + int i; + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu(hrtimer_bases, cpu); + new_base = get_cpu_var(hrtimer_bases); + + local_irq_disable(); + + for (i = 0; i < MAX_HRTIMER_BASES; i++) { + + spin_lock(&new_base->lock); + spin_lock(&old_base->lock); + + BUG_ON(old_base->curr_timer); + + migrate_hrtimer_list(old_base, new_base); + + spin_unlock(&old_base->lock); + spin_unlock(&new_base->lock); + old_base++; + new_base++; + } + + local_irq_enable(); + put_cpu_var(hrtimer_bases); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +static int __devinit hrtimer_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + + case CPU_UP_PREPARE: + init_hrtimers_cpu(cpu); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + migrate_hrtimers(cpu); + break; +#endif + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block __devinitdata hrtimers_nb = { + .notifier_call = hrtimer_cpu_notify, +}; + +void __init hrtimers_init(void) +{ + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); +} + diff --git a/kernel/timer.c b/kernel/timer.c index 074b4bd..80bf2ac 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -858,6 +858,7 @@ static void run_timer_softirq(struct softirq_action *h) { tvec_base_t *base = &__get_cpu_var(tvec_bases); + hrtimer_run_queues(); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } |