*/
#include <linux/cpu.h>
-#include <linux/irq.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/seq_file.h>
#include <linux/err.h>
+#include <linux/debugobjects.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
#include <asm/uaccess.h>
}
/*
- * 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;
-}
-
-/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
*/
}
}
+
+/*
+ * Get the preferred target CPU for NOHZ
+ */
+static int hrtimer_get_target(int this_cpu, int pinned)
+{
+#ifdef CONFIG_NO_HZ
+ if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
+ int preferred_cpu = get_nohz_load_balancer();
+
+ if (preferred_cpu >= 0)
+ return preferred_cpu;
+ }
+#endif
+ return this_cpu;
+}
+
+/*
+ * With HIGHRES=y we do not migrate the timer when it is expiring
+ * before the next event on the target cpu because we cannot reprogram
+ * the target cpu hardware and we would cause it to fire late.
+ *
+ * Called with cpu_base->lock of target cpu held.
+ */
+static int
+hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+ ktime_t expires;
+
+ if (!new_base->cpu_base->hres_active)
+ return 0;
+
+ expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
+ return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+#else
+ return 0;
+#endif
+}
+
/*
* Switch the timer base to the current CPU when possible.
*/
static inline struct hrtimer_clock_base *
-switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
+ int pinned)
{
struct hrtimer_clock_base *new_base;
struct hrtimer_cpu_base *new_cpu_base;
+ int this_cpu = smp_processor_id();
+ int cpu = hrtimer_get_target(this_cpu, pinned);
- new_cpu_base = &__get_cpu_var(hrtimer_bases);
+again:
+ new_cpu_base = &per_cpu(hrtimer_bases, cpu);
new_base = &new_cpu_base->clock_base[base->index];
if (base != new_base) {
/*
- * We are trying to schedule the timer on the local CPU.
+ * We are trying to move timer to new_base.
* 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
timer->base = NULL;
spin_unlock(&base->cpu_base->lock);
spin_lock(&new_base->cpu_base->lock);
+
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ spin_unlock(&new_base->cpu_base->lock);
+ spin_lock(&base->cpu_base->lock);
+ timer->base = base;
+ goto again;
+ }
timer->base = new_base;
}
return new_base;
return base;
}
-# define switch_hrtimer_base(t, b) (b)
+# define switch_hrtimer_base(t, b, p) (b)
#endif /* !CONFIG_SMP */
*/
u64 ktime_divns(const ktime_t kt, s64 div)
{
- u64 dclc, inc, dns;
+ u64 dclc;
int sft = 0;
- dclc = dns = ktime_to_ns(kt);
- inc = div;
+ dclc = ktime_to_ns(kt);
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
#endif /* BITS_PER_LONG >= 64 */
/*
- * Check, whether the timer is on the callback pending list
+ * Add two ktime values and do a safety check for overflow:
+ */
+ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
+{
+ ktime_t res = ktime_add(lhs, rhs);
+
+ /*
+ * We use KTIME_SEC_MAX here, the maximum timeout which we can
+ * return to user space in a timespec:
+ */
+ if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
+ res = ktime_set(KTIME_SEC_MAX, 0);
+
+ return res;
+}
+
+EXPORT_SYMBOL_GPL(ktime_add_safe);
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+
+static struct debug_obj_descr hrtimer_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int hrtimer_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct hrtimer *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ hrtimer_cancel(timer);
+ debug_object_init(timer, &hrtimer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
*/
-static inline int hrtimer_cb_pending(const struct hrtimer *timer)
+static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
{
- return timer->state & HRTIMER_STATE_PENDING;
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
}
/*
- * Remove a timer from the callback pending list
+ * fixup_free is called when:
+ * - an active object is freed
*/
-static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
+static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct hrtimer *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ hrtimer_cancel(timer);
+ debug_object_free(timer, &hrtimer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr hrtimer_debug_descr = {
+ .name = "hrtimer",
+ .fixup_init = hrtimer_fixup_init,
+ .fixup_activate = hrtimer_fixup_activate,
+ .fixup_free = hrtimer_fixup_free,
+};
+
+static inline void debug_hrtimer_init(struct hrtimer *timer)
+{
+ debug_object_init(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_activate(struct hrtimer *timer)
+{
+ debug_object_activate(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
+{
+ debug_object_deactivate(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_free(struct hrtimer *timer)
+{
+ debug_object_free(timer, &hrtimer_debug_descr);
+}
+
+static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode);
+
+void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
{
- list_del_init(&timer->cb_entry);
+ debug_object_init_on_stack(timer, &hrtimer_debug_descr);
+ __hrtimer_init(timer, clock_id, mode);
}
+void destroy_hrtimer_on_stack(struct hrtimer *timer)
+{
+ debug_object_free(timer, &hrtimer_debug_descr);
+}
+
+#else
+static inline void debug_hrtimer_init(struct hrtimer *timer) { }
+static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
+static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
+#endif
+
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
if (!base->first)
continue;
timer = rb_entry(base->first, struct hrtimer, node);
- expires = ktime_sub(timer->expires, base->offset);
+ expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+ /*
+ * clock_was_set() has changed base->offset so the
+ * result might be negative. Fix it up to prevent a
+ * false positive in clockevents_program_event()
+ */
+ if (expires.tv64 < 0)
+ expires.tv64 = 0;
if (expires.tv64 < cpu_base->expires_next.tv64)
cpu_base->expires_next = expires;
}
struct hrtimer_clock_base *base)
{
ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
- ktime_t expires = ktime_sub(timer->expires, base->offset);
+ ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
int res;
+ WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
+
/*
* When the callback is running, we do not reprogram the clock event
* device. The timer callback is either running on a different CPU or
if (hrtimer_callback_running(timer))
return 0;
+ /*
+ * CLOCK_REALTIME timer might be requested with an absolute
+ * expiry time which is less than base->offset. Nothing wrong
+ * about that, just avoid to call into the tick code, which
+ * has now objections against negative expiry values.
+ */
+ if (expires.tv64 < 0)
+ return -ETIME;
+
if (expires.tv64 >= expires_next->tv64)
return 0;
void clock_was_set(void)
{
/* Retrigger the CPU local events everywhere */
- on_each_cpu(retrigger_next_event, NULL, 0, 1);
+ on_each_cpu(retrigger_next_event, NULL, 1);
}
/*
*/
void hres_timers_resume(void)
{
- WARN_ON_ONCE(num_online_cpus() > 1);
+ WARN_ONCE(!irqs_disabled(),
+ KERN_INFO "hres_timers_resume() called with IRQs enabled!");
- /* Retrigger the CPU local events: */
retrigger_next_event(NULL);
}
{
}
+
/*
* When High resolution timers are active, try to reprogram. Note, that in case
* the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
* and expiry check is done in the hrtimer_interrupt or in the softirq.
*/
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
+ if (wakeup) {
+ spin_unlock(&base->cpu_base->lock);
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ spin_lock(&base->cpu_base->lock);
+ } else
+ __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- /* Timer is expired, act upon the callback mode */
- switch(timer->cb_mode) {
- case HRTIMER_CB_IRQSAFE_NO_RESTART:
- /*
- * We can call the callback from here. No restart
- * happens, so no danger of recursion
- */
- BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
- return 1;
- case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
- /*
- * This is solely for the sched tick emulation with
- * dynamic tick support to ensure that we do not
- * restart the tick right on the edge and end up with
- * the tick timer in the softirq ! The calling site
- * takes care of this.
- */
- return 1;
- case HRTIMER_CB_IRQSAFE:
- case HRTIMER_CB_SOFTIRQ:
- /*
- * Move everything else into the softirq pending list !
- */
- list_add_tail(&timer->cb_entry,
- &base->cpu_base->cb_pending);
- timer->state = HRTIMER_STATE_PENDING;
- raise_softirq(HRTIMER_SOFTIRQ);
- return 1;
- default:
- BUG();
- }
+ return 1;
}
+
return 0;
}
static inline int hrtimer_switch_to_hres(void) { return 0; }
static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
-static inline int hrtimer_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
-{
- return 0;
-}
#endif /* CONFIG_HIGH_RES_TIMERS */
u64 orun = 1;
ktime_t delta;
- delta = ktime_sub(now, timer->expires);
+ delta = ktime_sub(now, hrtimer_get_expires(timer));
if (delta.tv64 < 0)
return 0;
s64 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)
+ hrtimer_add_expires_ns(timer, incr * orun);
+ if (hrtimer_get_expires_tv64(timer) > now.tv64)
return orun;
/*
* This (and the ktime_add() below) is the
*/
orun++;
}
- timer->expires = ktime_add(timer->expires, interval);
- /*
- * Make sure, that the result did not wrap with a very large
- * interval.
- */
- if (timer->expires.tv64 < 0)
- timer->expires = ktime_set(KTIME_SEC_MAX, 0);
+ hrtimer_add_expires(timer, interval);
return orun;
}
*
* The timer is inserted in expiry order. Insertion into the
* red black tree is O(log(n)). Must hold the base lock.
+ *
+ * Returns 1 when the new timer is the leftmost timer in the tree.
*/
-static void enqueue_hrtimer(struct hrtimer *timer,
- struct hrtimer_clock_base *base, int reprogram)
+static int enqueue_hrtimer(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
{
struct rb_node **link = &base->active.rb_node;
struct rb_node *parent = NULL;
struct hrtimer *entry;
int leftmost = 1;
+ debug_hrtimer_activate(timer);
+
/*
* Find the right place in the rbtree:
*/
* We dont care about collisions. Nodes with
* the same expiry time stay together.
*/
- if (timer->expires.tv64 < entry->expires.tv64) {
+ if (hrtimer_get_expires_tv64(timer) <
+ hrtimer_get_expires_tv64(entry)) {
link = &(*link)->rb_left;
} else {
link = &(*link)->rb_right;
* Insert the timer to the rbtree and check whether it
* replaces the first pending timer
*/
- if (leftmost) {
- /*
- * Reprogram the clock event device. When the timer is already
- * expired hrtimer_enqueue_reprogram has either called the
- * callback or added it to the pending list and raised the
- * softirq.
- *
- * This is a NOP for !HIGHRES
- */
- if (reprogram && hrtimer_enqueue_reprogram(timer, base))
- return;
-
+ if (leftmost)
base->first = &timer->node;
- }
rb_link_node(&timer->node, parent, link);
rb_insert_color(&timer->node, &base->active);
* state of a possibly running callback.
*/
timer->state |= HRTIMER_STATE_ENQUEUED;
+
+ return leftmost;
}
/*
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
- /* High res. callback list. NOP for !HIGHRES */
- if (hrtimer_cb_pending(timer))
- hrtimer_remove_cb_pending(timer);
- else {
+ if (timer->state & HRTIMER_STATE_ENQUEUED) {
/*
* Remove the timer from the rbtree and replace the
* first entry pointer if necessary.
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
+ debug_hrtimer_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
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)
+int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode,
+ int wakeup)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
- int ret;
+ int ret, leftmost;
base = lock_hrtimer_base(timer, &flags);
ret = remove_hrtimer(timer, base);
/* Switch the timer base, if necessary: */
- new_base = switch_hrtimer_base(timer, base);
+ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
- if (mode == HRTIMER_MODE_REL) {
- tim = ktime_add(tim, new_base->get_time());
+ if (mode & HRTIMER_MODE_REL) {
+ tim = ktime_add_safe(tim, new_base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
* to signal that they simply return xtime in
* timeouts. This will go away with the GTOD framework.
*/
#ifdef CONFIG_TIME_LOW_RES
- tim = ktime_add(tim, base->resolution);
+ tim = ktime_add_safe(tim, base->resolution);
#endif
- /*
- * Careful here: User space might have asked for a
- * very long sleep, so the add above might result in a
- * negative number, which enqueues the timer in front
- * of the queue.
- */
- if (tim.tv64 < 0)
- tim.tv64 = KTIME_MAX;
}
- timer->expires = tim;
+
+ hrtimer_set_expires_range_ns(timer, tim, delta_ns);
timer_stats_hrtimer_set_start_info(timer);
+ leftmost = enqueue_hrtimer(timer, new_base);
+
/*
* Only allow reprogramming if the new base is on this CPU.
* (it might still be on another CPU if the timer was pending)
+ *
+ * XXX send_remote_softirq() ?
*/
- enqueue_hrtimer(timer, new_base,
- new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
+ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
+ hrtimer_enqueue_reprogram(timer, new_base, wakeup);
unlock_hrtimer_base(timer, &flags);
return ret;
}
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @delta_ns: "slack" range for the timer
+ * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ * 0 on success
+ * 1 when the timer was active
+ */
+int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode)
+{
+ return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
+}
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an hrtimer 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)
+{
+ return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
+}
EXPORT_SYMBOL_GPL(hrtimer_start);
+
/**
* hrtimer_try_to_cancel - try to deactivate a timer
* @timer: hrtimer to stop
ktime_t rem;
base = lock_hrtimer_base(timer, &flags);
- rem = ktime_sub(timer->expires, base->get_time());
+ rem = hrtimer_expires_remaining(timer);
unlock_hrtimer_base(timer, &flags);
return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
-#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
+#ifdef CONFIG_NO_HZ
/**
* hrtimer_get_next_event - get the time until next expiry event
*
continue;
timer = rb_entry(base->first, struct hrtimer, node);
- delta.tv64 = timer->expires.tv64;
+ delta.tv64 = hrtimer_get_expires_tv64(timer);
delta = ktime_sub(delta, base->get_time());
if (delta.tv64 < mindelta.tv64)
mindelta.tv64 = delta.tv64;
}
#endif
-/**
- * hrtimer_init - initialize a timer to the given clock
- * @timer: the timer to be initialized
- * @clock_id: the clock to be used
- * @mode: timer mode abs/rel
- */
-void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
- enum hrtimer_mode mode)
+static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
{
struct hrtimer_cpu_base *cpu_base;
memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
}
+
+/**
+ * hrtimer_init - initialize a timer to the given clock
+ * @timer: the timer to be initialized
+ * @clock_id: the clock to be used
+ * @mode: timer mode abs/rel
+ */
+void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
+{
+ debug_hrtimer_init(timer);
+ __hrtimer_init(timer, clock_id, mode);
+}
EXPORT_SYMBOL_GPL(hrtimer_init);
/**
}
EXPORT_SYMBOL_GPL(hrtimer_get_res);
-static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
-{
- spin_lock_irq(&cpu_base->lock);
-
- while (!list_empty(&cpu_base->cb_pending)) {
- enum hrtimer_restart (*fn)(struct hrtimer *);
- struct hrtimer *timer;
- int restart;
-
- timer = list_entry(cpu_base->cb_pending.next,
- struct hrtimer, cb_entry);
-
- timer_stats_account_hrtimer(timer);
-
- fn = timer->function;
- __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
- spin_unlock_irq(&cpu_base->lock);
-
- restart = fn(timer);
-
- spin_lock_irq(&cpu_base->lock);
-
- timer->state &= ~HRTIMER_STATE_CALLBACK;
- if (restart == HRTIMER_RESTART) {
- BUG_ON(hrtimer_active(timer));
- /*
- * Enqueue the timer, allow reprogramming of the event
- * device
- */
- enqueue_hrtimer(timer, timer->base, 1);
- } else if (hrtimer_active(timer)) {
- /*
- * If the timer was rearmed on another CPU, reprogram
- * the event device.
- */
- if (timer->base->first == &timer->node)
- hrtimer_reprogram(timer, timer->base);
- }
- }
- spin_unlock_irq(&cpu_base->lock);
-}
-
static void __run_hrtimer(struct hrtimer *timer)
{
struct hrtimer_clock_base *base = timer->base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
+ WARN_ON(!irqs_disabled());
+
+ debug_hrtimer_deactivate(timer);
__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
timer_stats_account_hrtimer(timer);
-
fn = timer->function;
- if (timer->cb_mode == HRTIMER_CB_IRQSAFE_NO_SOFTIRQ) {
- /*
- * Used for scheduler timers, avoid lock inversion with
- * rq->lock and tasklist_lock.
- *
- * These timers are required to deal with enqueue expiry
- * themselves and are not allowed to migrate.
- */
- spin_unlock(&cpu_base->lock);
- restart = fn(timer);
- spin_lock(&cpu_base->lock);
- } else
- restart = fn(timer);
/*
- * Note: We clear the CALLBACK bit after enqueue_hrtimer to avoid
- * reprogramming of the event hardware. This happens at the end of this
- * function anyway.
+ * Because we run timers from hardirq context, there is no chance
+ * they get migrated to another cpu, therefore its safe to unlock
+ * the timer base.
+ */
+ spin_unlock(&cpu_base->lock);
+ restart = fn(timer);
+ spin_lock(&cpu_base->lock);
+
+ /*
+ * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+ * we do not reprogramm the event hardware. Happens either in
+ * hrtimer_start_range_ns() or in hrtimer_interrupt()
*/
if (restart != HRTIMER_NORESTART) {
BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
- enqueue_hrtimer(timer, base, 0);
+ enqueue_hrtimer(timer, base);
}
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
#ifdef CONFIG_HIGH_RES_TIMERS
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+ ktime_t try_time)
+{
+ force_clock_reprogram = 1;
+ dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+ printk(KERN_WARNING "hrtimer: interrupt too slow, "
+ "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
/*
* High resolution timer interrupt
* Called with interrupts disabled
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
ktime_t expires_next, now;
- int i, raise = 0;
+ int nr_retries = 0;
+ int i;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
retry:
+ /* 5 retries is enough to notice a hang */
+ if (!(++nr_retries % 5))
+ hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
now = ktime_get();
expires_next.tv64 = KTIME_MAX;
+ spin_lock(&cpu_base->lock);
+ /*
+ * We set expires_next to KTIME_MAX here with cpu_base->lock
+ * held to prevent that a timer is enqueued in our queue via
+ * the migration code. This does not affect enqueueing of
+ * timers which run their callback and need to be requeued on
+ * this CPU.
+ */
+ cpu_base->expires_next.tv64 = KTIME_MAX;
+
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
- spin_lock(&cpu_base->lock);
-
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
timer = rb_entry(node, struct hrtimer, node);
- if (basenow.tv64 < timer->expires.tv64) {
+ /*
+ * The immediate goal for using the softexpires is
+ * minimizing wakeups, not running timers at the
+ * earliest interrupt after their soft expiration.
+ * This allows us to avoid using a Priority Search
+ * Tree, which can answer a stabbing querry for
+ * overlapping intervals and instead use the simple
+ * BST we already have.
+ * We don't add extra wakeups by delaying timers that
+ * are right-of a not yet expired timer, because that
+ * timer will have to trigger a wakeup anyway.
+ */
+
+ if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
ktime_t expires;
- expires = ktime_sub(timer->expires,
+ expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
- /* Move softirq callbacks to the pending list */
- if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
- __remove_hrtimer(timer, base,
- HRTIMER_STATE_PENDING, 0);
- list_add_tail(&timer->cb_entry,
- &base->cpu_base->cb_pending);
- raise = 1;
- continue;
- }
-
__run_hrtimer(timer);
}
- spin_unlock(&cpu_base->lock);
base++;
}
+ /*
+ * Store the new expiry value so the migration code can verify
+ * against it.
+ */
cpu_base->expires_next = expires_next;
+ spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {
- if (tick_program_event(expires_next, 0))
+ if (tick_program_event(expires_next, force_clock_reprogram))
goto retry;
}
+}
+
+/*
+ * local version of hrtimer_peek_ahead_timers() called with interrupts
+ * disabled.
+ */
+static void __hrtimer_peek_ahead_timers(void)
+{
+ struct tick_device *td;
+
+ if (!hrtimer_hres_active())
+ return;
+
+ td = &__get_cpu_var(tick_cpu_device);
+ if (td && td->evtdev)
+ hrtimer_interrupt(td->evtdev);
+}
+
+/**
+ * hrtimer_peek_ahead_timers -- run soft-expired timers now
+ *
+ * hrtimer_peek_ahead_timers will peek at the timer queue of
+ * the current cpu and check if there are any timers for which
+ * the soft expires time has passed. If any such timers exist,
+ * they are run immediately and then removed from the timer queue.
+ *
+ */
+void hrtimer_peek_ahead_timers(void)
+{
+ unsigned long flags;
- /* Raise softirq ? */
- if (raise)
- raise_softirq(HRTIMER_SOFTIRQ);
+ local_irq_save(flags);
+ __hrtimer_peek_ahead_timers();
+ local_irq_restore(flags);
}
static void run_hrtimer_softirq(struct softirq_action *h)
{
- run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
+ hrtimer_peek_ahead_timers();
}
-#endif /* CONFIG_HIGH_RES_TIMERS */
+#else /* CONFIG_HIGH_RES_TIMERS */
+
+static inline void __hrtimer_peek_ahead_timers(void) { }
+
+#endif /* !CONFIG_HIGH_RES_TIMERS */
/*
* Called from timer softirq every jiffy, expire hrtimers:
*/
void hrtimer_run_pending(void)
{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
if (hrtimer_hres_active())
return;
*/
if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
hrtimer_switch_to_hres();
-
- run_hrtimer_pending(cpu_base);
}
/*
* Called from hardirq context every jiffy
*/
-static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
- int index)
+void hrtimer_run_queues(void)
{
struct rb_node *node;
- struct hrtimer_clock_base *base = &cpu_base->clock_base[index];
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ struct hrtimer_clock_base *base;
+ int index, gettime = 1;
- if (!base->first)
+ if (hrtimer_hres_active())
return;
- if (base->get_softirq_time)
- base->softirq_time = base->get_softirq_time();
-
- spin_lock(&cpu_base->lock);
-
- while ((node = base->first)) {
- struct hrtimer *timer;
-
- timer = rb_entry(node, struct hrtimer, node);
- if (base->softirq_time.tv64 <= timer->expires.tv64)
- break;
+ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+ base = &cpu_base->clock_base[index];
- if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
- __remove_hrtimer(timer, base, HRTIMER_STATE_PENDING, 0);
- list_add_tail(&timer->cb_entry,
- &base->cpu_base->cb_pending);
+ if (!base->first)
continue;
- }
- __run_hrtimer(timer);
- }
- spin_unlock(&cpu_base->lock);
-}
+ if (gettime) {
+ hrtimer_get_softirq_time(cpu_base);
+ gettime = 0;
+ }
-void hrtimer_run_queues(void)
-{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
- int i;
+ spin_lock(&cpu_base->lock);
- if (hrtimer_hres_active())
- return;
+ while ((node = base->first)) {
+ struct hrtimer *timer;
- hrtimer_get_softirq_time(cpu_base);
+ timer = rb_entry(node, struct hrtimer, node);
+ if (base->softirq_time.tv64 <=
+ hrtimer_get_expires_tv64(timer))
+ break;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
- run_hrtimer_queue(cpu_base, i);
+ __run_hrtimer(timer);
+ }
+ spin_unlock(&cpu_base->lock);
+ }
}
/*
{
sl->timer.function = hrtimer_wakeup;
sl->task = task;
-#ifdef CONFIG_HIGH_RES_TIMERS
- sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
-#endif
}
static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
do {
set_current_state(TASK_INTERRUPTIBLE);
- hrtimer_start(&t->timer, t->timer.expires, mode);
+ hrtimer_start_expires(&t->timer, mode);
if (!hrtimer_active(&t->timer))
t->task = NULL;
struct timespec rmt;
ktime_t rem;
- rem = ktime_sub(timer->expires, timer->base->get_time());
+ rem = hrtimer_expires_remaining(timer);
if (rem.tv64 <= 0)
return 0;
rmt = ktime_to_timespec(rem);
{
struct hrtimer_sleeper t;
struct timespec __user *rmtp;
+ int ret = 0;
- restart->fn = do_no_restart_syscall;
-
- hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
- t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
+ hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
+ HRTIMER_MODE_ABS);
+ hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
if (do_nanosleep(&t, HRTIMER_MODE_ABS))
- return 0;
+ goto out;
- rmtp = (struct timespec __user *)restart->arg1;
+ rmtp = restart->nanosleep.rmtp;
if (rmtp) {
- int ret = update_rmtp(&t.timer, rmtp);
+ ret = update_rmtp(&t.timer, rmtp);
if (ret <= 0)
- return ret;
+ goto out;
}
- restart->fn = hrtimer_nanosleep_restart;
-
/* The other values in restart are already filled in */
- return -ERESTART_RESTARTBLOCK;
+ ret = -ERESTART_RESTARTBLOCK;
+out:
+ destroy_hrtimer_on_stack(&t.timer);
+ return ret;
}
long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
{
struct restart_block *restart;
struct hrtimer_sleeper t;
+ int ret = 0;
+ unsigned long slack;
- hrtimer_init(&t.timer, clockid, mode);
- t.timer.expires = timespec_to_ktime(*rqtp);
+ slack = current->timer_slack_ns;
+ if (rt_task(current))
+ slack = 0;
+
+ hrtimer_init_on_stack(&t.timer, clockid, mode);
+ hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
if (do_nanosleep(&t, mode))
- return 0;
+ goto out;
/* Absolute timers do not update the rmtp value and restart: */
- if (mode == HRTIMER_MODE_ABS)
- return -ERESTARTNOHAND;
+ if (mode == HRTIMER_MODE_ABS) {
+ ret = -ERESTARTNOHAND;
+ goto out;
+ }
if (rmtp) {
- int ret = update_rmtp(&t.timer, rmtp);
+ ret = update_rmtp(&t.timer, rmtp);
if (ret <= 0)
- return ret;
+ goto out;
}
restart = ¤t_thread_info()->restart_block;
restart->fn = hrtimer_nanosleep_restart;
- restart->arg0 = (unsigned long) t.timer.base->index;
- restart->arg1 = (unsigned long) rmtp;
- restart->arg2 = t.timer.expires.tv64 & 0xFFFFFFFF;
- restart->arg3 = t.timer.expires.tv64 >> 32;
+ restart->nanosleep.index = t.timer.base->index;
+ restart->nanosleep.rmtp = rmtp;
+ restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
- return -ERESTART_RESTARTBLOCK;
+ ret = -ERESTART_RESTARTBLOCK;
+out:
+ destroy_hrtimer_on_stack(&t.timer);
+ return ret;
}
-asmlinkage long
-sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
+SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
+ struct timespec __user *, rmtp)
{
struct timespec tu;
int i;
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;
- INIT_LIST_HEAD(&cpu_base->cb_pending);
hrtimer_init_hres(cpu_base);
}
while ((node = rb_first(&old_base->active))) {
timer = rb_entry(node, struct hrtimer, node);
BUG_ON(hrtimer_callback_running(timer));
- __remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0);
+ debug_hrtimer_deactivate(timer);
+
+ /*
+ * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+ * timer could be seen as !active and just vanish away
+ * under us on another CPU
+ */
+ __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
timer->base = new_base;
/*
- * Enqueue the timer. Allow reprogramming of the event device
+ * Enqueue the timers on the new cpu. This does not
+ * reprogram the event device in case the timer
+ * expires before the earliest on this CPU, but we run
+ * hrtimer_interrupt after we migrated everything to
+ * sort out already expired timers and reprogram the
+ * event device.
*/
- enqueue_hrtimer(timer, new_base, 1);
+ enqueue_hrtimer(timer, new_base);
+
+ /* Clear the migration state bit */
+ timer->state &= ~HRTIMER_STATE_MIGRATE;
}
}
-static void migrate_hrtimers(int cpu)
+static void migrate_hrtimers(int scpu)
{
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);
-
- tick_cancel_sched_timer(cpu);
+ BUG_ON(cpu_online(scpu));
+ tick_cancel_sched_timer(scpu);
local_irq_disable();
- double_spin_lock(&new_base->lock, &old_base->lock,
- smp_processor_id() < cpu);
+ old_base = &per_cpu(hrtimer_bases, scpu);
+ new_base = &__get_cpu_var(hrtimer_bases);
+ /*
+ * The caller is globally serialized and nobody else
+ * takes two locks at once, deadlock is not possible.
+ */
+ spin_lock(&new_base->lock);
+ spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
migrate_hrtimer_list(&old_base->clock_base[i],
&new_base->clock_base[i]);
}
- double_spin_unlock(&new_base->lock, &old_base->lock,
- smp_processor_id() < cpu);
+ spin_unlock(&old_base->lock);
+ spin_unlock(&new_base->lock);
+
+ /* Check, if we got expired work to do */
+ __hrtimer_peek_ahead_timers();
local_irq_enable();
- put_cpu_var(hrtimer_bases);
}
+
#endif /* CONFIG_HOTPLUG_CPU */
static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
- unsigned int cpu = (long)hcpu;
+ int scpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- init_hrtimers_cpu(cpu);
+ init_hrtimers_cpu(scpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+ break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
- migrate_hrtimers(cpu);
+ {
+ clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
+ migrate_hrtimers(scpu);
break;
+ }
#endif
default:
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
#ifdef CONFIG_HIGH_RES_TIMERS
- open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
+ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
}
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires: timeout value (ktime_t)
+ * @delta: slack in expires timeout (ktime_t)
+ * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+ const enum hrtimer_mode mode)
+{
+ struct hrtimer_sleeper t;
+
+ /*
+ * Optimize when a zero timeout value is given. It does not
+ * matter whether this is an absolute or a relative time.
+ */
+ if (expires && !expires->tv64) {
+ __set_current_state(TASK_RUNNING);
+ return 0;
+ }
+
+ /*
+ * A NULL parameter means "inifinte"
+ */
+ if (!expires) {
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ return -EINTR;
+ }
+
+ hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+ hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
+
+ hrtimer_init_sleeper(&t, current);
+
+ hrtimer_start_expires(&t.timer, mode);
+ if (!hrtimer_active(&t.timer))
+ t.task = NULL;
+
+ if (likely(t.task))
+ schedule();
+
+ hrtimer_cancel(&t.timer);
+ destroy_hrtimer_on_stack(&t.timer);
+
+ __set_current_state(TASK_RUNNING);
+
+ return !t.task ? 0 : -EINTR;
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires: timeout value (ktime_t)
+ * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+ const enum hrtimer_mode mode)
+{
+ return schedule_hrtimeout_range(expires, 0, mode);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout);