/*
* linux/kernel/hrtimer.c
*
- * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de>
- * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
*
* High-resolution kernel timers
*
*
* returns the time in ktime_t format
*/
-static ktime_t ktime_get(void)
+ktime_t ktime_get(void)
{
struct timespec now;
*
* returns the time in ktime_t format
*/
-static ktime_t ktime_get_real(void)
+ktime_t ktime_get_real(void)
{
struct timespec now;
* This ensures that we capture erroneous accesses to these clock ids
* rather than moving them into the range of valid clock id's.
*/
-
-#define MAX_HRTIMER_BASES 2
-
-static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) =
+static DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
+
+ .clock_base =
{
- .index = CLOCK_REALTIME,
- .get_time = &ktime_get_real,
- .resolution = KTIME_REALTIME_RES,
- },
- {
- .index = CLOCK_MONOTONIC,
- .get_time = &ktime_get,
- .resolution = KTIME_MONOTONIC_RES,
- },
+ {
+ .index = CLOCK_REALTIME,
+ .get_time = &ktime_get_real,
+ .resolution = KTIME_REALTIME_RES,
+ },
+ {
+ .index = CLOCK_MONOTONIC,
+ .get_time = &ktime_get,
+ .resolution = KTIME_MONOTONIC_RES,
+ },
+ }
};
/**
* Get the coarse grained time at the softirq based on xtime and
* wall_to_monotonic.
*/
-static void hrtimer_get_softirq_time(struct hrtimer_base *base)
+static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
{
ktime_t xtim, tomono;
+ struct timespec xts;
unsigned long seq;
do {
seq = read_seqbegin(&xtime_lock);
- xtim = timespec_to_ktime(xtime);
- tomono = timespec_to_ktime(wall_to_monotonic);
-
+#ifdef CONFIG_NO_HZ
+ getnstimeofday(&xts);
+#else
+ xts = xtime;
+#endif
} while (read_seqretry(&xtime_lock, seq));
- base[CLOCK_REALTIME].softirq_time = xtim;
- base[CLOCK_MONOTONIC].softirq_time = ktime_add(xtim, tomono);
+ xtim = timespec_to_ktime(xts);
+ tomono = timespec_to_ktime(wall_to_monotonic);
+ base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
+ base->clock_base[CLOCK_MONOTONIC].softirq_time =
+ ktime_add(xtim, tomono);
+}
+
+/*
+ * Helper function to check, whether the timer is on one of the queues
+ */
+static inline int hrtimer_is_queued(struct hrtimer *timer)
+{
+ return timer->state & HRTIMER_STATE_ENQUEUED;
+}
+
+/*
+ * Helper function to check, whether the timer is running the callback
+ * function
+ */
+static inline int hrtimer_callback_running(struct hrtimer *timer)
+{
+ return timer->state & HRTIMER_STATE_CALLBACK;
}
/*
*/
#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
* 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)
+static
+struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
+ unsigned long *flags)
{
- struct hrtimer_base *base;
+ struct hrtimer_clock_base *base;
for (;;) {
base = timer->base;
if (likely(base != NULL)) {
- spin_lock_irqsave(&base->lock, *flags);
+ spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
/* The timer has migrated to another CPU: */
- spin_unlock_irqrestore(&base->lock, *flags);
+ spin_unlock_irqrestore(&base->cpu_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)
+static inline struct hrtimer_clock_base *
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
- struct hrtimer_base *new_base;
+ struct hrtimer_clock_base *new_base;
+ struct hrtimer_cpu_base *new_cpu_base;
- new_base = &__get_cpu_var(hrtimer_bases)[base->index];
+ new_cpu_base = &__get_cpu_var(hrtimer_bases);
+ new_base = &new_cpu_base->clock_base[base->index];
if (base != new_base) {
/*
* completed. There is no conflict as we hold the lock until
* the timer is enqueued.
*/
- if (unlikely(base->curr_timer == timer))
+ if (unlikely(timer->state & HRTIMER_STATE_CALLBACK))
return base;
/* See the comment in lock_timer_base() */
timer->base = NULL;
- spin_unlock(&base->lock);
- spin_lock(&new_base->lock);
+ spin_unlock(&base->cpu_base->lock);
+ spin_lock(&new_base->cpu_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 *
+static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
- struct hrtimer_base *base = timer->base;
+ struct hrtimer_clock_base *base = timer->base;
- spin_lock_irqsave(&base->lock, *flags);
+ spin_lock_irqsave(&base->cpu_base->lock, *flags);
return base;
}
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
- spin_unlock_irqrestore(&timer->base->lock, *flags);
+ spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}
/**
* 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)
+static void enqueue_hrtimer(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
{
struct rb_node **link = &base->active.rb_node;
struct rb_node *parent = NULL;
*/
rb_link_node(&timer->node, parent, link);
rb_insert_color(&timer->node, &base->active);
+ /*
+ * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
+ * state of a possibly running callback.
+ */
+ timer->state |= HRTIMER_STATE_ENQUEUED;
if (!base->first || timer->expires.tv64 <
rb_entry(base->first, struct hrtimer, node)->expires.tv64)
*
* Caller must hold the base lock.
*/
-static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+static void __remove_hrtimer(struct hrtimer *timer,
+ struct hrtimer_clock_base *base,
+ unsigned long newstate)
{
/*
* Remove the timer from the rbtree and replace the
if (base->first == &timer->node)
base->first = rb_next(&timer->node);
rb_erase(&timer->node, &base->active);
- rb_set_parent(&timer->node, &timer->node);
+ timer->state = newstate;
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
- if (hrtimer_active(timer)) {
- __remove_hrtimer(timer, base);
+ if (hrtimer_is_queued(timer)) {
+ __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE);
return 1;
}
return 0;
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
- struct hrtimer_base *base, *new_base;
+ struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
int ret;
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base);
- if (mode == HRTIMER_REL) {
+ if (mode == HRTIMER_MODE_REL) {
tim = ktime_add(tim, new_base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
*/
int hrtimer_try_to_cancel(struct hrtimer *timer)
{
- struct hrtimer_base *base;
+ struct hrtimer_clock_base *base;
unsigned long flags;
int ret = -1;
base = lock_hrtimer_base(timer, &flags);
- if (base->curr_timer != timer)
+ if (!hrtimer_callback_running(timer))
ret = remove_hrtimer(timer, base);
unlock_hrtimer_base(timer, &flags);
*/
ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
{
- struct hrtimer_base *base;
+ struct hrtimer_clock_base *base;
unsigned long flags;
ktime_t rem;
base = lock_hrtimer_base(timer, &flags);
- rem = ktime_sub(timer->expires, timer->base->get_time());
+ rem = ktime_sub(timer->expires, base->get_time());
unlock_hrtimer_base(timer, &flags);
return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
-#ifdef CONFIG_NO_IDLE_HZ
+#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
/**
* hrtimer_get_next_event - get the time until next expiry event
*
*/
ktime_t hrtimer_get_next_event(void)
{
- struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ struct hrtimer_clock_base *base = cpu_base->clock_base;
ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
unsigned long flags;
int i;
- for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
+ spin_lock_irqsave(&cpu_base->lock, flags);
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
- spin_lock_irqsave(&base->lock, flags);
- if (!base->first) {
- spin_unlock_irqrestore(&base->lock, flags);
+ if (!base->first)
continue;
- }
+
timer = rb_entry(base->first, struct hrtimer, node);
delta.tv64 = timer->expires.tv64;
- spin_unlock_irqrestore(&base->lock, flags);
delta = ktime_sub(delta, base->get_time());
if (delta.tv64 < mindelta.tv64)
mindelta.tv64 = delta.tv64;
}
+
+ spin_unlock_irqrestore(&cpu_base->lock, flags);
+
if (mindelta.tv64 < 0)
mindelta.tv64 = 0;
return mindelta;
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)
{
- struct hrtimer_base *bases;
+ struct hrtimer_cpu_base *cpu_base;
memset(timer, 0, sizeof(struct hrtimer));
- bases = __raw_get_cpu_var(hrtimer_bases);
+ cpu_base = &__raw_get_cpu_var(hrtimer_bases);
- if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS)
+ if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
clock_id = CLOCK_MONOTONIC;
- timer->base = &bases[clock_id];
- rb_set_parent(&timer->node, &timer->node);
+ timer->base = &cpu_base->clock_base[clock_id];
}
EXPORT_SYMBOL_GPL(hrtimer_init);
*/
int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
{
- struct hrtimer_base *bases;
+ struct hrtimer_cpu_base *cpu_base;
- bases = __raw_get_cpu_var(hrtimer_bases);
- *tp = ktime_to_timespec(bases[which_clock].resolution);
+ cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+ *tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
return 0;
}
/*
* Expire the per base hrtimer-queue:
*/
-static inline void run_hrtimer_queue(struct hrtimer_base *base)
+static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
+ int index)
{
struct rb_node *node;
+ struct hrtimer_clock_base *base = &cpu_base->clock_base[index];
if (!base->first)
return;
if (base->get_softirq_time)
base->softirq_time = base->get_softirq_time();
- spin_lock_irq(&base->lock);
+ spin_lock_irq(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
- int (*fn)(struct hrtimer *);
+ enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
timer = rb_entry(node, struct hrtimer, node);
break;
fn = timer->function;
- set_curr_timer(base, timer);
- __remove_hrtimer(timer, base);
- spin_unlock_irq(&base->lock);
+ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK);
+ spin_unlock_irq(&cpu_base->lock);
restart = fn(timer);
- spin_lock_irq(&base->lock);
+ spin_lock_irq(&cpu_base->lock);
+ timer->state &= ~HRTIMER_STATE_CALLBACK;
if (restart != HRTIMER_NORESTART) {
BUG_ON(hrtimer_active(timer));
enqueue_hrtimer(timer, base);
}
}
- set_curr_timer(base, NULL);
- spin_unlock_irq(&base->lock);
+ spin_unlock_irq(&cpu_base->lock);
}
/*
*/
void hrtimer_run_queues(void)
{
- struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
int i;
- hrtimer_get_softirq_time(base);
+ hrtimer_get_softirq_time(cpu_base);
- for (i = 0; i < MAX_HRTIMER_BASES; i++)
- run_hrtimer_queue(&base[i]);
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+ run_hrtimer_queue(cpu_base, i);
}
/*
* Sleep related functions:
*/
-static int hrtimer_wakeup(struct hrtimer *timer)
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
{
struct hrtimer_sleeper *t =
container_of(timer, struct hrtimer_sleeper, timer);
schedule();
hrtimer_cancel(&t->timer);
- mode = HRTIMER_ABS;
+ mode = HRTIMER_MODE_ABS;
} while (t->task && !signal_pending(current));
restart->fn = do_no_restart_syscall;
- hrtimer_init(&t.timer, restart->arg0, HRTIMER_ABS);
+ hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
- if (do_nanosleep(&t, HRTIMER_ABS))
+ if (do_nanosleep(&t, HRTIMER_MODE_ABS))
return 0;
rmtp = (struct timespec __user *) restart->arg1;
return 0;
/* Absolute timers do not update the rmtp value and restart: */
- if (mode == HRTIMER_ABS)
+ if (mode == HRTIMER_MODE_ABS)
return -ERESTARTNOHAND;
if (rmtp) {
if (!timespec_valid(&tu))
return -EINVAL;
- return hrtimer_nanosleep(&tu, rmtp, HRTIMER_REL, CLOCK_MONOTONIC);
+ return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
/*
*/
static void __devinit init_hrtimers_cpu(int cpu)
{
- struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu);
+ struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
- for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
- spin_lock_init(&base->lock);
- lockdep_set_class(&base->lock, &base->lock_key);
- }
+ spin_lock_init(&cpu_base->lock);
+ lockdep_set_class(&cpu_base->lock, &cpu_base->lock_key);
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+ cpu_base->clock_base[i].cpu_base = cpu_base;
+
}
#ifdef CONFIG_HOTPLUG_CPU
-static void migrate_hrtimer_list(struct hrtimer_base *old_base,
- struct hrtimer_base *new_base)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+ struct hrtimer_clock_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);
+ BUG_ON(timer->state & HRTIMER_STATE_CALLBACK);
+ __remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE);
timer->base = new_base;
enqueue_hrtimer(timer, new_base);
}
static void migrate_hrtimers(int cpu)
{
- struct hrtimer_base *old_base, *new_base;
+ struct hrtimer_cpu_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);
+ 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_lock(&new_base->lock);
+ spin_lock(&old_base->lock);
- spin_unlock(&old_base->lock);
- spin_unlock(&new_base->lock);
- old_base++;
- new_base++;
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+ migrate_hrtimer_list(&old_base->clock_base[i],
+ &new_base->clock_base[i]);
}
+ spin_unlock(&old_base->lock);
+ spin_unlock(&new_base->lock);
local_irq_enable();
put_cpu_var(hrtimer_bases);
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DEAD:
+ clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
migrate_hrtimers(cpu);
break;
#endif