*/
#include <linux/cpu.h>
-#include <linux/irq.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/hrtimer.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>
-/**
- * ktime_get - get the monotonic time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get(void)
-{
- struct timespec now;
-
- ktime_get_ts(&now);
-
- return timespec_to_ktime(now);
-}
-EXPORT_SYMBOL_GPL(ktime_get);
-
-/**
- * ktime_get_real - get the real (wall-) time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get_real(void)
-{
- struct timespec now;
-
- getnstimeofday(&now);
-
- return timespec_to_ktime(now);
-}
-
-EXPORT_SYMBOL_GPL(ktime_get_real);
+#include <trace/events/timer.h>
/*
* The timer bases:
}
};
-/**
- * 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);
-}
-EXPORT_SYMBOL_GPL(ktime_get_ts);
-
/*
* Get the coarse grained time at the softirq based on xtime and
* wall_to_monotonic.
for (;;) {
base = timer->base;
if (likely(base != NULL)) {
- spin_lock_irqsave(&base->cpu_base->lock, *flags);
+ raw_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->cpu_base->lock, *flags);
+ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
}
cpu_relax();
}
}
+
+/*
+ * 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
/* See the comment in lock_timer_base() */
timer->base = NULL;
- spin_unlock(&base->cpu_base->lock);
- spin_lock(&new_base->cpu_base->lock);
+ raw_spin_unlock(&base->cpu_base->lock);
+ raw_spin_lock(&new_base->cpu_base->lock);
+
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ raw_spin_unlock(&new_base->cpu_base->lock);
+ raw_spin_lock(&base->cpu_base->lock);
+ timer->base = base;
+ goto again;
+ }
timer->base = new_base;
}
return new_base;
{
struct hrtimer_clock_base *base = timer->base;
- spin_lock_irqsave(&base->cpu_base->lock, *flags);
+ raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
return base;
}
-# define switch_hrtimer_base(t, b) (b)
+# define switch_hrtimer_base(t, b, p) (b)
#endif /* !CONFIG_SMP */
return res;
}
+EXPORT_SYMBOL_GPL(ktime_add_safe);
+
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static struct debug_obj_descr hrtimer_debug_descr;
debug_object_init_on_stack(timer, &hrtimer_debug_descr);
__hrtimer_init(timer, clock_id, mode);
}
+EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif
-/*
- * Check, whether the timer is on the callback pending list
- */
-static inline int hrtimer_cb_pending(const struct hrtimer *timer)
+static inline void
+debug_init(struct hrtimer *timer, clockid_t clockid,
+ enum hrtimer_mode mode)
{
- return timer->state & HRTIMER_STATE_PENDING;
+ debug_hrtimer_init(timer);
+ trace_hrtimer_init(timer, clockid, mode);
}
-/*
- * Remove a timer from the callback pending list
- */
-static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
+static inline void debug_activate(struct hrtimer *timer)
{
- list_del_init(&timer->cb_entry);
+ debug_hrtimer_activate(timer);
+ trace_hrtimer_start(timer);
+}
+
+static inline void debug_deactivate(struct hrtimer *timer)
+{
+ debug_hrtimer_deactivate(timer);
+ trace_hrtimer_cancel(timer);
}
/* High resolution timer related functions */
* next event
* Called with interrupts disabled and base->lock held
*/
-static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
+static void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
int i;
struct hrtimer_clock_base *base = cpu_base->clock_base;
- ktime_t expires;
+ ktime_t expires, expires_next;
- cpu_base->expires_next.tv64 = KTIME_MAX;
+ expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
continue;
timer = rb_entry(base->first, struct hrtimer, node);
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
- if (expires.tv64 < cpu_base->expires_next.tv64)
- cpu_base->expires_next = expires;
+ /*
+ * 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 < expires_next.tv64)
+ expires_next = expires;
}
+ if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
+ return;
+
+ cpu_base->expires_next.tv64 = expires_next.tv64;
+
if (cpu_base->expires_next.tv64 != KTIME_MAX)
tick_program_event(cpu_base->expires_next, 1);
}
static int hrtimer_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
- ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
int res;
if (expires.tv64 < 0)
return -ETIME;
- if (expires.tv64 >= expires_next->tv64)
+ if (expires.tv64 >= cpu_base->expires_next.tv64)
+ return 0;
+
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * do not schedule a timer which is earlier than the expiry
+ * which we enforced in the hang detection. We want the system
+ * to make progress.
+ */
+ if (cpu_base->hang_detected)
return 0;
/*
*/
res = tick_program_event(expires, 0);
if (!IS_ERR_VALUE(res))
- *expires_next = expires;
+ cpu_base->expires_next = expires;
return res;
}
base = &__get_cpu_var(hrtimer_bases);
/* Adjust CLOCK_REALTIME offset */
- spin_lock(&base->lock);
+ raw_spin_lock(&base->lock);
base->clock_base[CLOCK_REALTIME].offset =
timespec_to_ktime(realtime_offset);
- hrtimer_force_reprogram(base);
- spin_unlock(&base->lock);
+ hrtimer_force_reprogram(base, 0);
+ raw_spin_unlock(&base->lock);
}
/*
*/
void hres_timers_resume(void)
{
- /* Retrigger the CPU local events: */
+ WARN_ONCE(!irqs_disabled(),
+ KERN_INFO "hres_timers_resume() called with IRQs enabled!");
+
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) {
+ raw_spin_unlock(&base->cpu_base->lock);
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ raw_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_PERCPU:
- case HRTIMER_CB_IRQSAFE_UNLOCKED:
- /*
- * 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. Also used for hrtimer sleeper !
- */
- debug_hrtimer_deactivate(timer);
- return 1;
- 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;
- return 1;
- default:
- BUG();
- }
+ return 1;
}
+
return 0;
}
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
local_irq_restore(flags);
- printk(KERN_DEBUG "Switched to high resolution mode on CPU %d\n",
- smp_processor_id());
return 1;
}
-static inline void hrtimer_raise_softirq(void)
-{
- raise_softirq(HRTIMER_SOFTIRQ);
-}
-
#else
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { 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 void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
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;
-}
-static inline void hrtimer_raise_softirq(void) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
-#ifdef CONFIG_TIMER_STATS
-void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
+static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
+#ifdef CONFIG_TIMER_STATS
if (timer->start_site)
return;
-
- timer->start_site = addr;
+ timer->start_site = __builtin_return_address(0);
memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
timer->start_pid = current->pid;
+#endif
}
+
+static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ timer->start_site = NULL;
#endif
+}
+
+static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ if (likely(!timer_stats_active))
+ return;
+ timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+ timer->function, timer->start_comm, 0);
+#endif
+}
/*
* Counterpart to lock_hrtimer_base above:
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
- spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
+ raw_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.
+ *
+ * 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);
+ debug_activate(timer);
/*
* Find the right place in the rbtree:
* 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 {
- /*
- * Remove the timer from the rbtree and replace the
- * first entry pointer if necessary.
- */
- if (base->first == &timer->node) {
- base->first = rb_next(&timer->node);
- /* Reprogram the clock event device. if enabled */
- if (reprogram && hrtimer_hres_active())
- hrtimer_force_reprogram(base->cpu_base);
+ if (!(timer->state & HRTIMER_STATE_ENQUEUED))
+ goto out;
+
+ /*
+ * Remove the timer from the rbtree and replace the first
+ * entry pointer if necessary.
+ */
+ if (base->first == &timer->node) {
+ base->first = rb_next(&timer->node);
+#ifdef CONFIG_HIGH_RES_TIMERS
+ /* Reprogram the clock event device. if enabled */
+ if (reprogram && hrtimer_hres_active()) {
+ ktime_t expires;
+
+ expires = ktime_sub(hrtimer_get_expires(timer),
+ base->offset);
+ if (base->cpu_base->expires_next.tv64 == expires.tv64)
+ hrtimer_force_reprogram(base->cpu_base, 1);
}
- rb_erase(&timer->node, &base->active);
+#endif
}
+ rb_erase(&timer->node, &base->active);
+out:
timer->state = newstate;
}
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
- debug_hrtimer_deactivate(timer);
+ debug_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_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)
+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, raise;
+ 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) {
+ if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, new_base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
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));
-
- /*
- * The timer may be expired and moved to the cb_pending
- * list. We can not raise the softirq with base lock held due
- * to a possible deadlock with runqueue lock.
- */
- raise = timer->state == HRTIMER_STATE_PENDING;
-
- /*
- * We use preempt_disable to prevent this task from migrating after
- * setting up the softirq and raising it. Otherwise, if me migrate
- * we will raise the softirq on the wrong CPU.
- */
- preempt_disable();
+ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
+ hrtimer_enqueue_reprogram(timer, new_base, wakeup);
unlock_hrtimer_base(timer, &flags);
- if (raise)
- hrtimer_raise_softirq();
- preempt_enable();
-
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);
/**
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
- return hrtimer_start_range_ns(timer, tim, 0, mode);
+ return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start);
unsigned long flags;
int i;
- spin_lock_irqsave(&cpu_base->lock, flags);
+ raw_spin_lock_irqsave(&cpu_base->lock, flags);
if (!hrtimer_hres_active()) {
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
}
}
- spin_unlock_irqrestore(&cpu_base->lock, flags);
+ raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
if (mindelta.tv64 < 0)
mindelta.tv64 = 0;
clock_id = CLOCK_MONOTONIC;
timer->base = &cpu_base->clock_base[clock_id];
- INIT_LIST_HEAD(&timer->cb_entry);
hrtimer_init_timer_hres(timer);
#ifdef CONFIG_TIMER_STATS
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)
{
- debug_hrtimer_init(timer);
+ debug_init(timer, clock_id, mode);
__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;
- int emulate_hardirq_ctx = 0;
-
- timer = list_entry(cpu_base->cb_pending.next,
- struct hrtimer, cb_entry);
-
- debug_hrtimer_deactivate(timer);
- timer_stats_account_hrtimer(timer);
-
- fn = timer->function;
- /*
- * A timer might have been added to the cb_pending list
- * when it was migrated during a cpu-offline operation.
- * Emulate hardirq context for such timers.
- */
- if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
- timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
- emulate_hardirq_ctx = 1;
-
- __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
- spin_unlock_irq(&cpu_base->lock);
-
- if (unlikely(emulate_hardirq_ctx)) {
- local_irq_disable();
- restart = fn(timer);
- local_irq_enable();
- } else
- 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.
- */
- struct hrtimer_clock_base *base = timer->base;
-
- if (base->first == &timer->node &&
- hrtimer_reprogram(timer, base)) {
- /*
- * Timer is expired. Thus move it from tree to
- * pending list again.
- */
- __remove_hrtimer(timer, base,
- HRTIMER_STATE_PENDING, 0);
- list_add_tail(&timer->cb_entry,
- &base->cpu_base->cb_pending);
- }
- }
- }
- spin_unlock_irq(&cpu_base->lock);
-}
-
-static void __run_hrtimer(struct hrtimer *timer)
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
{
struct hrtimer_clock_base *base = timer->base;
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
- debug_hrtimer_deactivate(timer);
+ WARN_ON(!irqs_disabled());
+
+ debug_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_PERCPU ||
- timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
- /*
- * 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.
+ */
+ raw_spin_unlock(&cpu_base->lock);
+ trace_hrtimer_expire_entry(timer, now);
+ restart = fn(timer);
+ trace_hrtimer_expire_exit(timer);
+ raw_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;
}
{
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;
+ ktime_t expires_next, now, entry_time, delta;
+ int i, retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
- retry:
- now = ktime_get();
-
+ entry_time = now = ktime_get();
+retry:
expires_next.tv64 = KTIME_MAX;
+ raw_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)) {
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);
+ __run_hrtimer(timer, &basenow);
}
- 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;
+ raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
- if (expires_next.tv64 != KTIME_MAX) {
- if (tick_program_event(expires_next, 0))
- goto retry;
+ if (expires_next.tv64 == KTIME_MAX ||
+ !tick_program_event(expires_next, 0)) {
+ cpu_base->hang_detected = 0;
+ return;
}
- /* Raise softirq ? */
- if (raise)
- raise_softirq(HRTIMER_SOFTIRQ);
+ /*
+ * The next timer was already expired due to:
+ * - tracing
+ * - long lasting callbacks
+ * - being scheduled away when running in a VM
+ *
+ * We need to prevent that we loop forever in the hrtimer
+ * interrupt routine. We give it 3 attempts to avoid
+ * overreacting on some spurious event.
+ */
+ now = ktime_get();
+ cpu_base->nr_retries++;
+ if (++retries < 3)
+ goto retry;
+ /*
+ * Give the system a chance to do something else than looping
+ * here. We stored the entry time, so we know exactly how long
+ * we spent here. We schedule the next event this amount of
+ * time away.
+ */
+ cpu_base->nr_hangs++;
+ cpu_base->hang_detected = 1;
+ delta = ktime_sub(now, entry_time);
+ if (delta.tv64 > cpu_base->max_hang_time.tv64)
+ cpu_base->max_hang_time = delta;
+ /*
+ * Limit it to a sensible value as we enforce a longer
+ * delay. Give the CPU at least 100ms to catch up.
+ */
+ if (delta.tv64 > 100 * NSEC_PER_MSEC)
+ expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
+ else
+ expires_next = ktime_add(now, delta);
+ tick_program_event(expires_next, 1);
+ printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
+ ktime_to_ns(delta));
+}
+
+/*
+ * 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);
}
/**
*/
void hrtimer_peek_ahead_timers(void)
{
- struct tick_device *td;
unsigned long flags;
- if (!hrtimer_hres_active())
- return;
-
local_irq_save(flags);
- td = &__get_cpu_var(tick_cpu_device);
- if (td && td->evtdev)
- hrtimer_interrupt(td->evtdev);
+ __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);
}
/*
gettime = 0;
}
- spin_lock(&cpu_base->lock);
+ raw_spin_lock(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
hrtimer_get_expires_tv64(timer))
break;
- 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);
- continue;
- }
-
- __run_hrtimer(timer);
+ __run_hrtimer(timer, &base->softirq_time);
}
- spin_unlock(&cpu_base->lock);
+ raw_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_UNLOCKED;
-#endif
}
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
{
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;
struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
- spin_lock_init(&cpu_base->lock);
+ raw_spin_lock_init(&cpu_base->lock);
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);
}
#ifdef CONFIG_HOTPLUG_CPU
-static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
- struct hrtimer_clock_base *new_base, int dcpu)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+ struct hrtimer_clock_base *new_base)
{
struct hrtimer *timer;
struct rb_node *node;
- int raise = 0;
while ((node = rb_first(&old_base->active))) {
timer = rb_entry(node, struct hrtimer, node);
BUG_ON(hrtimer_callback_running(timer));
- debug_hrtimer_deactivate(timer);
-
- /*
- * Should not happen. Per CPU timers should be
- * canceled _before_ the migration code is called
- */
- if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
- __remove_hrtimer(timer, old_base,
- HRTIMER_STATE_INACTIVE, 0);
- WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
- timer, timer->function, dcpu);
- continue;
- }
+ debug_deactivate(timer);
/*
* Mark it as STATE_MIGRATE not INACTIVE otherwise the
__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);
-#ifdef CONFIG_HIGH_RES_TIMERS
- /*
- * Happens with high res enabled when the timer was
- * already expired and the callback mode is
- * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
- * enqueue code does not move them to the soft irq
- * pending list for performance/latency reasons, but
- * in the migration state, we need to do that
- * otherwise we end up with a stale timer.
- */
- if (timer->state == HRTIMER_STATE_MIGRATE) {
- timer->state = HRTIMER_STATE_PENDING;
- list_add_tail(&timer->cb_entry,
- &new_base->cpu_base->cb_pending);
- raise = 1;
- }
-#endif
/* Clear the migration state bit */
timer->state &= ~HRTIMER_STATE_MIGRATE;
}
- return raise;
}
-#ifdef CONFIG_HIGH_RES_TIMERS
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
- struct hrtimer_cpu_base *new_base)
-{
- struct hrtimer *timer;
- int raise = 0;
-
- while (!list_empty(&old_base->cb_pending)) {
- timer = list_entry(old_base->cb_pending.next,
- struct hrtimer, cb_entry);
-
- __remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
- timer->base = &new_base->clock_base[timer->base->index];
- list_add_tail(&timer->cb_entry, &new_base->cb_pending);
- raise = 1;
- }
- return raise;
-}
-#else
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
- struct hrtimer_cpu_base *new_base)
-{
- return 0;
-}
-#endif
-
-static void migrate_hrtimers(int cpu)
+static void migrate_hrtimers(int scpu)
{
struct hrtimer_cpu_base *old_base, *new_base;
- int i, raise = 0;
+ int i;
- BUG_ON(cpu_online(cpu));
- old_base = &per_cpu(hrtimer_bases, cpu);
- new_base = &get_cpu_var(hrtimer_bases);
+ BUG_ON(cpu_online(scpu));
+ tick_cancel_sched_timer(scpu);
- tick_cancel_sched_timer(cpu);
+ local_irq_disable();
+ 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_irq(&new_base->lock);
- spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&new_base->lock);
+ raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- if (migrate_hrtimer_list(&old_base->clock_base[i],
- &new_base->clock_base[i], cpu))
- raise = 1;
+ migrate_hrtimer_list(&old_base->clock_base[i],
+ &new_base->clock_base[i]);
}
- if (migrate_hrtimer_pending(old_base, new_base))
- raise = 1;
+ raw_spin_unlock(&old_base->lock);
+ raw_spin_unlock(&new_base->lock);
- spin_unlock(&old_base->lock);
- spin_unlock_irq(&new_base->lock);
- put_cpu_var(hrtimer_bases);
-
- if (raise)
- hrtimer_raise_softirq();
+ /* Check, if we got expired work to do */
+ __hrtimer_peek_ahead_timers();
+ local_irq_enable();
}
+
#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:
}
/**
- * schedule_hrtimeout_range - sleep until timeout
+ * schedule_hrtimeout_range_clock - 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
+ * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
*/
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
- const enum hrtimer_mode mode)
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+ const enum hrtimer_mode mode, int clock)
{
struct hrtimer_sleeper t;
return -EINTR;
}
- hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+ hrtimer_init_on_stack(&t.timer, clock, mode);
hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
hrtimer_init_sleeper(&t, current);
return !t.task ? 0 : -EINTR;
}
+
+/**
+ * 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)
+{
+ return schedule_hrtimeout_range_clock(expires, delta, mode,
+ CLOCK_MONOTONIC);
+}
EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
/**
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff