/*
- * linux/kernel/posix_timers.c
+ * linux/kernel/posix-timers.c
*
*
* 2002-10-15 Posix Clocks & timers
* POSIX clocks & timers
*/
#include <linux/mm.h>
-#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/mutex.h>
#include <asm/uaccess.h>
-#include <asm/semaphore.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>
/*
* Lets keep our timers in a slab cache :-)
*/
-static kmem_cache_t *posix_timers_cache;
+static struct kmem_cache *posix_timers_cache;
static struct idr posix_timers_id;
static DEFINE_SPINLOCK(idr_lock);
struct itimerspec *, struct itimerspec *);
static int common_timer_del(struct k_itimer *timer);
-static int posix_timer_fn(void *data);
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);
return 0;
}
+static int no_timer_create(struct k_itimer *new_timer)
+{
+ return -EOPNOTSUPP;
+}
+
/*
* Return nonzero if we know a priori this clockid_t value is bogus.
*/
}
/*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+ getrawmonotonic(tp);
+ return 0;
+}
+
+/*
* Initialize everything, well, just everything in Posix clocks/timers ;)
*/
static __init int init_posix_timers(void)
.clock_get = posix_ktime_get_ts,
.clock_set = do_posix_clock_nosettime,
};
+ struct k_clock clock_monotonic_raw = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_monotonic_raw,
+ .clock_set = do_posix_clock_nosettime,
+ .timer_create = no_timer_create,
+ };
register_posix_clock(CLOCK_REALTIME, &clock_realtime);
register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
+ register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
posix_timers_cache = kmem_cache_create("posix_timers_cache",
- sizeof (struct k_itimer), 0, 0, NULL, NULL);
+ sizeof (struct k_itimer), 0, SLAB_PANIC,
+ NULL);
idr_init(&posix_timers_id);
return 0;
}
if (timr->it.real.interval.tv64 == 0)
return;
- timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
- timr->it.real.interval);
+ timr->it_overrun += (unsigned int) hrtimer_forward(timer,
+ timer->base->get_time(),
+ timr->it.real.interval);
timr->it_overrun_last = timr->it_overrun;
timr->it_overrun = -1;
else
schedule_next_timer(timr);
- info->si_overrun = timr->it_overrun_last;
+ info->si_overrun += timr->it_overrun_last;
}
if (timr)
unlock_timer(timr, flags);
}
-int posix_timer_event(struct k_itimer *timr,int si_private)
+int posix_timer_event(struct k_itimer *timr, int si_private)
{
- memset(&timr->sigq->info, 0, sizeof(siginfo_t));
+ int shared, ret;
+ /*
+ * FIXME: if ->sigq is queued we can race with
+ * dequeue_signal()->do_schedule_next_timer().
+ *
+ * If dequeue_signal() sees the "right" value of
+ * si_sys_private it calls do_schedule_next_timer().
+ * We re-queue ->sigq and drop ->it_lock().
+ * do_schedule_next_timer() locks the timer
+ * and re-schedules it while ->sigq is pending.
+ * Not really bad, but not that we want.
+ */
timr->sigq->info.si_sys_private = si_private;
- /* Send signal to the process that owns this timer.*/
-
- timr->sigq->info.si_signo = timr->it_sigev_signo;
- timr->sigq->info.si_errno = 0;
- timr->sigq->info.si_code = SI_TIMER;
- timr->sigq->info.si_tid = timr->it_id;
- timr->sigq->info.si_value = timr->it_sigev_value;
-
- if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
- struct task_struct *leader;
- int ret = send_sigqueue(timr->it_sigev_signo, timr->sigq,
- timr->it_process);
-
- if (likely(ret >= 0))
- return ret;
-
- timr->it_sigev_notify = SIGEV_SIGNAL;
- leader = timr->it_process->group_leader;
- put_task_struct(timr->it_process);
- timr->it_process = leader;
- }
- return send_group_sigqueue(timr->it_sigev_signo, timr->sigq,
- timr->it_process);
+ shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+ ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+ /* If we failed to send the signal the timer stops. */
+ return ret > 0;
}
EXPORT_SYMBOL_GPL(posix_timer_event);
* This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers.
*/
-static int posix_timer_fn(void *data)
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
{
- struct k_itimer *timr = data;
- struct hrtimer *timer = &timr->it.real.timer;
+ struct k_itimer *timr;
unsigned long flags;
int si_private = 0;
- int ret = HRTIMER_NORESTART;
+ enum hrtimer_restart ret = HRTIMER_NORESTART;
+ timr = container_of(timer, struct k_itimer, it.real.timer);
spin_lock_irqsave(&timr->it_lock, flags);
if (timr->it.real.interval.tv64 != 0)
* it should be restarted.
*/
if (timr->it.real.interval.tv64 != 0) {
- timr->it_overrun +=
- hrtimer_forward(timer,
- timer->base->softirq_time,
+ ktime_t now = hrtimer_cb_get_time(timer);
+
+ /*
+ * FIXME: What we really want, is to stop this
+ * timer completely and restart it in case the
+ * SIG_IGN is removed. This is a non trivial
+ * change which involves sighand locking
+ * (sigh !), which we don't want to do late in
+ * the release cycle.
+ *
+ * For now we just let timers with an interval
+ * less than a jiffie expire every jiffie to
+ * avoid softirq starvation in case of SIG_IGN
+ * and a very small interval, which would put
+ * the timer right back on the softirq pending
+ * list. By moving now ahead of time we trick
+ * hrtimer_forward() to expire the timer
+ * later, while we still maintain the overrun
+ * accuracy, but have some inconsistency in
+ * the timer_gettime() case. This is at least
+ * better than a starved softirq. A more
+ * complex fix which solves also another related
+ * inconsistency is already in the pipeline.
+ */
+#ifdef CONFIG_HIGH_RES_TIMERS
+ {
+ ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ);
+
+ if (timr->it.real.interval.tv64 < kj.tv64)
+ now = ktime_add(now, kj);
+ }
+#endif
+ timr->it_overrun += (unsigned int)
+ hrtimer_forward(timer, now,
timr->it.real.interval);
ret = HRTIMER_RESTART;
++timr->it_requeue_pending;
struct task_struct *rtn = current->group_leader;
if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
- (!(rtn = find_task_by_pid(event->sigev_notify_thread_id)) ||
- rtn->tgid != current->tgid ||
+ (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
+ !same_thread_group(rtn, current) ||
(event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
return NULL;
static struct k_itimer * alloc_posix_timer(void)
{
struct k_itimer *tmr;
- tmr = kmem_cache_alloc(posix_timers_cache, GFP_KERNEL);
+ tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
if (!tmr)
return tmr;
- memset(tmr, 0, sizeof (struct k_itimer));
if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
kmem_cache_free(posix_timers_cache, tmr);
- tmr = NULL;
+ return NULL;
}
+ memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
return tmr;
}
spin_unlock_irqrestore(&idr_lock, flags);
}
sigqueue_free(tmr->sigq);
- if (unlikely(tmr->it_process) &&
- tmr->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
- put_task_struct(tmr->it_process);
kmem_cache_free(posix_timers_cache, tmr);
}
struct sigevent __user *timer_event_spec,
timer_t __user * created_timer_id)
{
- int error = 0;
- struct k_itimer *new_timer = NULL;
- int new_timer_id;
- struct task_struct *process = NULL;
- unsigned long flags;
+ struct k_itimer *new_timer;
+ int error, new_timer_id;
+ struct task_struct *process;
sigevent_t event;
int it_id_set = IT_ID_NOT_SET;
goto out;
}
spin_lock_irq(&idr_lock);
- error = idr_get_new(&posix_timers_id, (void *) new_timer,
- &new_timer_id);
+ error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id);
spin_unlock_irq(&idr_lock);
- if (error == -EAGAIN)
- goto retry;
- else if (error) {
+ if (error) {
+ if (error == -EAGAIN)
+ goto retry;
/*
- * Wierd looking, but we return EAGAIN if the IDR is
+ * Weird looking, but we return EAGAIN if the IDR is
* full (proper POSIX return value for this)
*/
error = -EAGAIN;
error = -EFAULT;
goto out;
}
- new_timer->it_sigev_notify = event.sigev_notify;
- new_timer->it_sigev_signo = event.sigev_signo;
- new_timer->it_sigev_value = event.sigev_value;
-
- read_lock(&tasklist_lock);
- if ((process = good_sigevent(&event))) {
- /*
- * We may be setting up this process for another
- * thread. It may be exiting. To catch this
- * case the we check the PF_EXITING flag. If
- * the flag is not set, the siglock will catch
- * him before it is too late (in exit_itimers).
- *
- * The exec case is a bit more invloved but easy
- * to code. If the process is in our thread
- * group (and it must be or we would not allow
- * it here) and is doing an exec, it will cause
- * us to be killed. In this case it will wait
- * for us to die which means we can finish this
- * linkage with our last gasp. I.e. no code :)
- */
- spin_lock_irqsave(&process->sighand->siglock, flags);
- if (!(process->flags & PF_EXITING)) {
- new_timer->it_process = process;
- list_add(&new_timer->list,
- &process->signal->posix_timers);
- spin_unlock_irqrestore(&process->sighand->siglock, flags);
- if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
- get_task_struct(process);
- } else {
- spin_unlock_irqrestore(&process->sighand->siglock, flags);
- process = NULL;
- }
- }
- read_unlock(&tasklist_lock);
+ rcu_read_lock();
+ process = good_sigevent(&event);
+ if (process)
+ get_task_struct(process);
+ rcu_read_unlock();
if (!process) {
error = -EINVAL;
goto out;
}
} else {
- new_timer->it_sigev_notify = SIGEV_SIGNAL;
- new_timer->it_sigev_signo = SIGALRM;
- new_timer->it_sigev_value.sival_int = new_timer->it_id;
+ event.sigev_notify = SIGEV_SIGNAL;
+ event.sigev_signo = SIGALRM;
+ event.sigev_value.sival_int = new_timer->it_id;
process = current->group_leader;
- spin_lock_irqsave(&process->sighand->siglock, flags);
- new_timer->it_process = process;
- list_add(&new_timer->list, &process->signal->posix_timers);
- spin_unlock_irqrestore(&process->sighand->siglock, flags);
+ get_task_struct(process);
}
+ new_timer->it_sigev_notify = event.sigev_notify;
+ new_timer->sigq->info.si_signo = event.sigev_signo;
+ new_timer->sigq->info.si_value = event.sigev_value;
+ new_timer->sigq->info.si_tid = new_timer->it_id;
+ new_timer->sigq->info.si_code = SI_TIMER;
+
+ spin_lock_irq(¤t->sighand->siglock);
+ new_timer->it_process = process;
+ list_add(&new_timer->list, ¤t->signal->posix_timers);
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ return 0;
/*
* In the case of the timer belonging to another task, after
* the task is unlocked, the timer is owned by the other task
* and may cease to exist at any time. Don't use or modify
* new_timer after the unlock call.
*/
-
out:
- if (error)
- release_posix_timer(new_timer, it_id_set);
-
+ release_posix_timer(new_timer, it_id_set);
return error;
}
* the find to the timer lock. To avoid a dead lock, the timer id MUST
* be release with out holding the timer lock.
*/
-static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
{
struct k_itimer *timr;
/*
* flags part over to the timer lock. Must not let interrupts in
* while we are moving the lock.
*/
-
spin_lock_irqsave(&idr_lock, *flags);
- timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id);
+ timr = idr_find(&posix_timers_id, (int)timer_id);
if (timr) {
spin_lock(&timr->it_lock);
- spin_unlock(&idr_lock);
-
- if ((timr->it_id != timer_id) || !(timr->it_process) ||
- timr->it_process->tgid != current->tgid) {
- unlock_timer(timr, *flags);
- timr = NULL;
+ if (timr->it_process &&
+ same_thread_group(timr->it_process, current)) {
+ spin_unlock(&idr_lock);
+ return timr;
}
- } else
- spin_unlock_irqrestore(&idr_lock, *flags);
+ spin_unlock(&timr->it_lock);
+ }
+ spin_unlock_irqrestore(&idr_lock, *flags);
- return timr;
+ return NULL;
}
/*
static void
common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
{
- ktime_t remaining;
+ ktime_t now, remaining, iv;
struct hrtimer *timer = &timr->it.real.timer;
memset(cur_setting, 0, sizeof(struct itimerspec));
- remaining = hrtimer_get_remaining(timer);
- /* Time left ? or timer pending */
- if (remaining.tv64 > 0 || hrtimer_active(timer))
- goto calci;
+ iv = timr->it.real.interval;
+
/* interval timer ? */
- if (timr->it.real.interval.tv64 == 0)
+ if (iv.tv64)
+ cur_setting->it_interval = ktime_to_timespec(iv);
+ else if (!hrtimer_active(timer) &&
+ (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
return;
+
+ now = timer->base->get_time();
+
/*
- * When a requeue is pending or this is a SIGEV_NONE timer
- * move the expiry time forward by intervals, so expiry is >
- * now.
+ * When a requeue is pending or this is a SIGEV_NONE
+ * timer move the expiry time forward by intervals, so
+ * expiry is > now.
*/
- if (timr->it_requeue_pending & REQUEUE_PENDING ||
- (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
- timr->it_overrun +=
- hrtimer_forward(timer, timer->base->get_time(),
- timr->it.real.interval);
- remaining = hrtimer_get_remaining(timer);
- }
- calci:
- /* interval timer ? */
- if (timr->it.real.interval.tv64 != 0)
- cur_setting->it_interval =
- ktime_to_timespec(timr->it.real.interval);
+ if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
+ (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
+ timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+
+ remaining = ktime_sub(hrtimer_get_expires(timer), now);
/* Return 0 only, when the timer is expired and not pending */
- if (remaining.tv64 <= 0)
- cur_setting->it_value.tv_nsec = 1;
- else
+ if (remaining.tv64 <= 0) {
+ /*
+ * A single shot SIGEV_NONE timer must return 0, when
+ * it is expired !
+ */
+ if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ cur_setting->it_value.tv_nsec = 1;
+ } else
cur_setting->it_value = ktime_to_timespec(remaining);
}
{
struct k_itimer *timr;
int overrun;
- long flags;
+ unsigned long flags;
timr = lock_timer(timer_id, &flags);
if (!timr)
if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
return 0;
- mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL;
+ mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL;
hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
- timr->it.real.timer.data = timr;
timr->it.real.timer.function = posix_timer_fn;
- timer->expires = timespec_to_ktime(new_setting->it_value);
+ hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));
/* Convert interval */
timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
/* SIGEV_NONE timers are not queued ! See common_timer_get */
if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
/* Setup correct expiry time for relative timers */
- if (mode == HRTIMER_REL)
- timer->expires = ktime_add(timer->expires,
- timer->base->get_time());
+ if (mode == HRTIMER_MODE_REL) {
+ hrtimer_add_expires(timer, timer->base->get_time());
+ }
return 0;
}
- hrtimer_start(timer, timer->expires, mode);
+ hrtimer_start_expires(timer, mode);
return 0;
}
struct k_itimer *timr;
struct itimerspec new_spec, old_spec;
int error = 0;
- long flag;
+ unsigned long flag;
struct itimerspec *rtn = old_setting ? &old_spec : NULL;
if (!new_setting)
sys_timer_delete(timer_t timer_id)
{
struct k_itimer *timer;
- long flags;
+ unsigned long flags;
retry_delete:
timer = lock_timer(timer_id, &flags);
* This keeps any tasks waiting on the spin lock from thinking
* they got something (see the lock code above).
*/
- if (timer->it_process) {
- if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
- put_task_struct(timer->it_process);
- timer->it_process = NULL;
- }
+ put_task_struct(timer->it_process);
+ timer->it_process = NULL;
+
unlock_timer(timer, flags);
release_posix_timer(timer, IT_ID_SET);
return 0;
* This keeps any tasks waiting on the spin lock from thinking
* they got something (see the lock code above).
*/
- if (timer->it_process) {
- if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
- put_task_struct(timer->it_process);
- timer->it_process = NULL;
- }
+ put_task_struct(timer->it_process);
+ timer->it_process = NULL;
+
unlock_timer(timer, flags);
release_posix_timer(timer, IT_ID_SET);
}
struct timespec *tsave, struct timespec __user *rmtp)
{
return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
- HRTIMER_ABS : HRTIMER_REL, which_clock);
+ HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+ which_clock);
}
asmlinkage long
return CLOCK_DISPATCH(which_clock, nsleep,
(which_clock, flags, &t, rmtp));
}
+
+/*
+ * nanosleep_restart for monotonic and realtime clocks
+ */
+static int common_nsleep_restart(struct restart_block *restart_block)
+{
+ return hrtimer_nanosleep_restart(restart_block);
+}
+
+/*
+ * This will restart clock_nanosleep. This is required only by
+ * compat_clock_nanosleep_restart for now.
+ */
+long
+clock_nanosleep_restart(struct restart_block *restart_block)
+{
+ clockid_t which_clock = restart_block->arg0;
+
+ return CLOCK_DISPATCH(which_clock, nsleep_restart,
+ (restart_block));
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff