* Credits:
* based on kernel/timer.c
*
+ * Help, testing, suggestions, bugfixes, improvements were
+ * provided by:
+ *
+ * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
+ * et. al.
+ *
* For licencing details see kernel-base/COPYING
*/
/*
* The timer bases:
+ *
+ * Note: If we want to add new timer bases, we have to skip the two
+ * clock ids captured by the cpu-timers. We do this by holding empty
+ * entries rather than doing math adjustment of the clock ids.
+ * 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
}
EXPORT_SYMBOL_GPL(ktime_get_ts);
+/*
+ * 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)
+{
+ ktime_t xtim, tomono;
+ unsigned long seq;
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ xtim = timespec_to_ktime(xtime);
+ tomono = timespec_to_ktime(wall_to_monotonic);
+
+ } while (read_seqretry(&xtime_lock, seq));
+
+ base[CLOCK_REALTIME].softirq_time = xtim;
+ base[CLOCK_MONOTONIC].softirq_time = ktime_add(xtim, tomono);
+}
+
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
/*
* Divide a ktime value by a nanosecond value
*/
-static unsigned long ktime_divns(const ktime_t kt, nsec_t div)
+static unsigned long ktime_divns(const ktime_t kt, s64 div)
{
u64 dclc, inc, dns;
int sft = 0;
* hrtimer_forward - forward the timer expiry
*
* @timer: hrtimer to forward
+ * @now: forward past this time
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire in the future.
* Returns the number of overruns.
*/
unsigned long
-hrtimer_forward(struct hrtimer *timer, ktime_t interval)
+hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
unsigned long orun = 1;
- ktime_t delta, now;
-
- now = timer->base->get_time();
+ ktime_t delta;
delta = ktime_sub(now, timer->expires);
interval.tv64 = timer->base->resolution.tv64;
if (unlikely(delta.tv64 >= interval.tv64)) {
- nsec_t incr = ktime_to_ns(interval);
+ s64 incr = ktime_to_ns(interval);
orun = ktime_divns(delta, incr);
timer->expires = ktime_add_ns(timer->expires, incr * orun);
rb_link_node(&timer->node, parent, link);
rb_insert_color(&timer->node, &base->active);
- timer->state = HRTIMER_PENDING;
-
if (!base->first || timer->expires.tv64 <
rb_entry(base->first, struct hrtimer, node)->expires.tv64)
base->first = &timer->node;
if (base->first == &timer->node)
base->first = rb_next(&timer->node);
rb_erase(&timer->node, &base->active);
+ timer->node.rb_parent = HRTIMER_INACTIVE;
}
/*
{
if (hrtimer_active(timer)) {
__remove_hrtimer(timer, base);
- timer->state = HRTIMER_INACTIVE;
return 1;
}
return 0;
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base);
- if (mode == HRTIMER_REL)
+ if (mode == HRTIMER_REL) {
tim = ktime_add(tim, new_base->get_time());
+ /*
+ * CONFIG_TIME_LOW_RES is a temporary way for architectures
+ * to signal that they simply return xtime in
+ * do_gettimeoffset(). In this case we want to round up by
+ * resolution when starting a relative timer, to avoid short
+ * timeouts. This will go away with the GTOD framework.
+ */
+#ifdef CONFIG_TIME_LOW_RES
+ tim = ktime_add(tim, base->resolution);
+#endif
+ }
timer->expires = tim;
enqueue_hrtimer(timer, new_base);
return rem;
}
+#ifdef CONFIG_NO_IDLE_HZ
/**
- * hrtimer_rebase - rebase an initialized hrtimer to a different base
+ * hrtimer_get_next_event - get the time until next expiry event
*
- * @timer: the timer to be rebased
- * @clock_id: the clock to be used
+ * Returns the delta to the next expiry event or KTIME_MAX if no timer
+ * is pending.
*/
-void hrtimer_rebase(struct hrtimer *timer, const clockid_t clock_id)
+ktime_t hrtimer_get_next_event(void)
{
- struct hrtimer_base *bases;
+ struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+ ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+ unsigned long flags;
+ int i;
- bases = per_cpu(hrtimer_bases, raw_smp_processor_id());
- timer->base = &bases[clock_id];
+ for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
+ struct hrtimer *timer;
+
+ spin_lock_irqsave(&base->lock, flags);
+ if (!base->first) {
+ spin_unlock_irqrestore(&base->lock, flags);
+ 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;
+ }
+ if (mindelta.tv64 < 0)
+ mindelta.tv64 = 0;
+ return mindelta;
}
+#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, const clockid_t clock_id)
+void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
{
+ struct hrtimer_base *bases;
+
memset(timer, 0, sizeof(struct hrtimer));
- hrtimer_rebase(timer, clock_id);
+
+ bases = per_cpu(hrtimer_bases, raw_smp_processor_id());
+
+ if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS)
+ clock_id = CLOCK_MONOTONIC;
+
+ timer->base = &bases[clock_id];
+ timer->node.rb_parent = HRTIMER_INACTIVE;
}
/**
*/
static inline void run_hrtimer_queue(struct hrtimer_base *base)
{
- ktime_t now = base->get_time();
struct rb_node *node;
+ if (base->get_softirq_time)
+ base->softirq_time = base->get_softirq_time();
+
spin_lock_irq(&base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
- int (*fn)(void *);
+ int (*fn)(struct hrtimer *);
int restart;
- void *data;
timer = rb_entry(node, struct hrtimer, node);
- if (now.tv64 <= timer->expires.tv64)
+ if (base->softirq_time.tv64 <= timer->expires.tv64)
break;
fn = timer->function;
- data = timer->data;
set_curr_timer(base, timer);
- timer->state = HRTIMER_RUNNING;
__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);
+ restart = fn(timer);
spin_lock_irq(&base->lock);
- /* Another CPU has added back the timer */
- if (timer->state != HRTIMER_RUNNING)
- continue;
-
- if (restart == HRTIMER_RESTART)
+ if (restart != HRTIMER_NORESTART) {
+ BUG_ON(hrtimer_active(timer));
enqueue_hrtimer(timer, base);
- else
- timer->state = HRTIMER_EXPIRED;
+ }
}
set_curr_timer(base, NULL);
spin_unlock_irq(&base->lock);
struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
int i;
+ hrtimer_get_softirq_time(base);
+
for (i = 0; i < MAX_HRTIMER_BASES; i++)
run_hrtimer_queue(&base[i]);
}
* Sleep related functions:
*/
-/**
- * schedule_hrtimer - sleep until timeout
- *
- * @timer: hrtimer variable initialized with the correct clock base
- * @mode: timeout value is abs/rel
- *
- * Make the current task sleep until @timeout is
- * elapsed.
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout is guaranteed to
- * pass before the routine returns. The routine will return 0
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task. In this case the remaining time
- * will be returned
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- */
-static ktime_t __sched
-schedule_hrtimer(struct hrtimer *timer, const enum hrtimer_mode mode)
-{
- /* fn stays NULL, meaning single-shot wakeup: */
- timer->data = current;
+struct sleep_hrtimer {
+ struct hrtimer timer;
+ struct task_struct *task;
+ int expired;
+};
- hrtimer_start(timer, timer->expires, mode);
+static int nanosleep_wakeup(struct hrtimer *timer)
+{
+ struct sleep_hrtimer *t =
+ container_of(timer, struct sleep_hrtimer, timer);
- schedule();
- hrtimer_cancel(timer);
+ t->expired = 1;
+ wake_up_process(t->task);
- /* Return the remaining time: */
- if (timer->state != HRTIMER_EXPIRED)
- return ktime_sub(timer->expires, timer->base->get_time());
- else
- return (ktime_t) {.tv64 = 0 };
+ return HRTIMER_NORESTART;
}
-static inline ktime_t __sched
-schedule_hrtimer_interruptible(struct hrtimer *timer,
- const enum hrtimer_mode mode)
+static int __sched do_nanosleep(struct sleep_hrtimer *t, enum hrtimer_mode mode)
{
- set_current_state(TASK_INTERRUPTIBLE);
+ t->timer.function = nanosleep_wakeup;
+ t->task = current;
+ t->expired = 0;
+
+ do {
+ set_current_state(TASK_INTERRUPTIBLE);
+ hrtimer_start(&t->timer, t->timer.expires, mode);
- return schedule_hrtimer(timer, mode);
+ schedule();
+
+ if (unlikely(!t->expired)) {
+ hrtimer_cancel(&t->timer);
+ mode = HRTIMER_ABS;
+ }
+ } while (!t->expired && !signal_pending(current));
+
+ return t->expired;
}
-static long __sched
-nanosleep_restart(struct restart_block *restart, clockid_t clockid)
+static long __sched nanosleep_restart(struct restart_block *restart)
{
+ struct sleep_hrtimer t;
struct timespec __user *rmtp;
struct timespec tu;
- void *rfn_save = restart->fn;
- struct hrtimer timer;
- ktime_t rem;
+ ktime_t time;
restart->fn = do_no_restart_syscall;
- hrtimer_init(&timer, clockid);
+ hrtimer_init(&t.timer, restart->arg3, HRTIMER_ABS);
+ t.timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0;
- timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0;
-
- rem = schedule_hrtimer_interruptible(&timer, HRTIMER_ABS);
-
- if (rem.tv64 <= 0)
+ if (do_nanosleep(&t, HRTIMER_ABS))
return 0;
rmtp = (struct timespec __user *) restart->arg2;
- tu = ktime_to_timespec(rem);
- if (rmtp && copy_to_user(rmtp, &tu, sizeof(tu)))
- return -EFAULT;
+ if (rmtp) {
+ time = ktime_sub(t.timer.expires, t.timer.base->get_time());
+ if (time.tv64 <= 0)
+ return 0;
+ tu = ktime_to_timespec(time);
+ if (copy_to_user(rmtp, &tu, sizeof(tu)))
+ return -EFAULT;
+ }
- restart->fn = rfn_save;
+ restart->fn = nanosleep_restart;
/* The other values in restart are already filled in */
return -ERESTART_RESTARTBLOCK;
}
-static long __sched nanosleep_restart_mono(struct restart_block *restart)
-{
- return nanosleep_restart(restart, CLOCK_MONOTONIC);
-}
-
-static long __sched nanosleep_restart_real(struct restart_block *restart)
-{
- return nanosleep_restart(restart, CLOCK_REALTIME);
-}
-
long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
const enum hrtimer_mode mode, const clockid_t clockid)
{
struct restart_block *restart;
- struct hrtimer timer;
+ struct sleep_hrtimer t;
struct timespec tu;
ktime_t rem;
- hrtimer_init(&timer, clockid);
-
- timer.expires = timespec_to_ktime(*rqtp);
-
- rem = schedule_hrtimer_interruptible(&timer, mode);
- if (rem.tv64 <= 0)
+ hrtimer_init(&t.timer, clockid, mode);
+ t.timer.expires = timespec_to_ktime(*rqtp);
+ if (do_nanosleep(&t, mode))
return 0;
- /* Absolute timers do not update the rmtp value: */
+ /* Absolute timers do not update the rmtp value and restart: */
if (mode == HRTIMER_ABS)
return -ERESTARTNOHAND;
- tu = ktime_to_timespec(rem);
-
- if (rmtp && copy_to_user(rmtp, &tu, sizeof(tu)))
- return -EFAULT;
+ if (rmtp) {
+ rem = ktime_sub(t.timer.expires, t.timer.base->get_time());
+ if (rem.tv64 <= 0)
+ return 0;
+ tu = ktime_to_timespec(rem);
+ if (copy_to_user(rmtp, &tu, sizeof(tu)))
+ return -EFAULT;
+ }
restart = ¤t_thread_info()->restart_block;
- restart->fn = (clockid == CLOCK_MONOTONIC) ?
- nanosleep_restart_mono : nanosleep_restart_real;
- restart->arg0 = timer.expires.tv64 & 0xFFFFFFFF;
- restart->arg1 = timer.expires.tv64 >> 32;
+ restart->fn = nanosleep_restart;
+ restart->arg0 = t.timer.expires.tv64 & 0xFFFFFFFF;
+ restart->arg1 = t.timer.expires.tv64 >> 32;
restart->arg2 = (unsigned long) rmtp;
+ restart->arg3 = (unsigned long) t.timer.base->index;
return -ERESTART_RESTARTBLOCK;
}
struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu);
int i;
- for (i = 0; i < MAX_HRTIMER_BASES; i++) {
+ for (i = 0; i < MAX_HRTIMER_BASES; i++, base++)
spin_lock_init(&base->lock);
- base++;
- }
}
#ifdef CONFIG_HOTPLUG_CPU