posix-cpu-timers.c

linux 2.6.19 kernel source code before patching

			t = next_thread(t);
		} while (t != p);
		break;
	}
}

static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
{
	/*
	 * That's all for this thread or process.
	 * We leave our residual in expires to be reported.
	 */
	put_task_struct(timer->it.cpu.task);
	timer->it.cpu.task = NULL;
	timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
					     timer->it.cpu.expires,
					     now);
}

/*
 * Insert the timer on the appropriate list before any timers that
 * expire later.  This must be called with the tasklist_lock held
 * for reading, and interrupts disabled.
 */
static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
{
	struct task_struct *p = timer->it.cpu.task;
	struct list_head *head, *listpos;
	struct cpu_timer_list *const nt = &timer->it.cpu;
	struct cpu_timer_list *next;
	unsigned long i;

	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
		p->cpu_timers : p->signal->cpu_timers);
	head += CPUCLOCK_WHICH(timer->it_clock);

	BUG_ON(!irqs_disabled());
	spin_lock(&p->sighand->siglock);

	listpos = head;
	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
		list_for_each_entry(next, head, entry) {
			if (next->expires.sched > nt->expires.sched)
				break;
			listpos = &next->entry;
		}
	} else {
		list_for_each_entry(next, head, entry) {
			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
				break;
			listpos = &next->entry;
		}
	}
	list_add(&nt->entry, listpos);

	if (listpos == head) {
		/*
		 * We are the new earliest-expiring timer.
		 * If we are a thread timer, there can always
		 * be a process timer telling us to stop earlier.
		 */

		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
			switch (CPUCLOCK_WHICH(timer->it_clock)) {
			default:
				BUG();
			case CPUCLOCK_PROF:
				if (cputime_eq(p->it_prof_expires,
					       cputime_zero) ||
				    cputime_gt(p->it_prof_expires,
					       nt->expires.cpu))
					p->it_prof_expires = nt->expires.cpu;
				break;
			case CPUCLOCK_VIRT:
				if (cputime_eq(p->it_virt_expires,
					       cputime_zero) ||
				    cputime_gt(p->it_virt_expires,
					       nt->expires.cpu))
					p->it_virt_expires = nt->expires.cpu;
				break;
			case CPUCLOCK_SCHED:
				if (p->it_sched_expires == 0 ||
				    p->it_sched_expires > nt->expires.sched)
					p->it_sched_expires = nt->expires.sched;
				break;
			}
		} else {
			/*
			 * For a process timer, we must balance
			 * all the live threads' expirations.
			 */
			switch (CPUCLOCK_WHICH(timer->it_clock)) {
			default:
				BUG();
			case CPUCLOCK_VIRT:
				if (!cputime_eq(p->signal->it_virt_expires,
						cputime_zero) &&
				    cputime_lt(p->signal->it_virt_expires,
					       timer->it.cpu.expires.cpu))
					break;
				goto rebalance;
			case CPUCLOCK_PROF:
				if (!cputime_eq(p->signal->it_prof_expires,
						cputime_zero) &&
				    cputime_lt(p->signal->it_prof_expires,
					       timer->it.cpu.expires.cpu))
					break;
				i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
				if (i != RLIM_INFINITY &&
				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
					break;
				goto rebalance;
			case CPUCLOCK_SCHED:
			rebalance:
				process_timer_rebalance(
					timer->it.cpu.task,
					CPUCLOCK_WHICH(timer->it_clock),
					timer->it.cpu.expires, now);
				break;
			}
		}
	}

	spin_unlock(&p->sighand->siglock);
}

/*
 * The timer is locked, fire it and arrange for its reload.
 */
static void cpu_timer_fire(struct k_itimer *timer)
{
	if (unlikely(timer->sigq == NULL)) {
		/*
		 * This a special case for clock_nanosleep,
		 * not a normal timer from sys_timer_create.
		 */
		wake_up_process(timer->it_process);
		timer->it.cpu.expires.sched = 0;
	} else if (timer->it.cpu.incr.sched == 0) {
		/*
		 * One-shot timer.  Clear it as soon as it's fired.
		 */
		posix_timer_event(timer, 0);
		timer->it.cpu.expires.sched = 0;
	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
		/*
		 * The signal did not get queued because the signal
		 * was ignored, so we won't get any callback to
		 * reload the timer.  But we need to keep it
		 * ticking in case the signal is deliverable next time.
		 */
		posix_cpu_timer_schedule(timer);
	}
}

/*
 * Guts of sys_timer_settime for CPU timers.
 * This is called with the timer locked and interrupts disabled.
 * If we return TIMER_RETRY, it's necessary to release the timer's lock
 * and try again.  (This happens when the timer is in the middle of firing.)
 */
int posix_cpu_timer_set(struct k_itimer *timer, int flags,
			struct itimerspec *new, struct itimerspec *old)
{
	struct task_struct *p = timer->it.cpu.task;
	union cpu_time_count old_expires, new_expires, val;
	int ret;

	if (unlikely(p == NULL)) {
		/*
		 * Timer refers to a dead task's clock.
		 */
		return -ESRCH;
	}

	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);

	read_lock(&tasklist_lock);
	/*
	 * We need the tasklist_lock to protect against reaping that
	 * clears p->signal.  If p has just been reaped, we can no
	 * longer get any information about it at all.
	 */
	if (unlikely(p->signal == NULL)) {
		read_unlock(&tasklist_lock);
		put_task_struct(p);
		timer->it.cpu.task = NULL;
		return -ESRCH;
	}

	/*
	 * Disarm any old timer after extracting its expiry time.
	 */
	BUG_ON(!irqs_disabled());

	ret = 0;
	spin_lock(&p->sighand->siglock);
	old_expires = timer->it.cpu.expires;
	if (unlikely(timer->it.cpu.firing)) {
		timer->it.cpu.firing = -1;
		ret = TIMER_RETRY;
	} else
		list_del_init(&timer->it.cpu.entry);
	spin_unlock(&p->sighand->siglock);

	/*
	 * We need to sample the current value to convert the new
	 * value from to relative and absolute, and to convert the
	 * old value from absolute to relative.  To set a process
	 * timer, we need a sample to balance the thread expiry
	 * times (in arm_timer).  With an absolute time, we must
	 * check if it's already passed.  In short, we need a sample.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &val);
	} else {
		cpu_clock_sample_group(timer->it_clock, p, &val);
	}

	if (old) {
		if (old_expires.sched == 0) {
			old->it_value.tv_sec = 0;
			old->it_value.tv_nsec = 0;
		} else {
			/*
			 * Update the timer in case it has
			 * overrun already.  If it has,
			 * we'll report it as having overrun
			 * and with the next reloaded timer
			 * already ticking, though we are
			 * swallowing that pending
			 * notification here to install the
			 * new setting.
			 */
			bump_cpu_timer(timer, val);
			if (cpu_time_before(timer->it_clock, val,
					    timer->it.cpu.expires)) {
				old_expires = cpu_time_sub(
					timer->it_clock,
					timer->it.cpu.expires, val);
				sample_to_timespec(timer->it_clock,
						   old_expires,
						   &old->it_value);
			} else {
				old->it_value.tv_nsec = 1;
				old->it_value.tv_sec = 0;
			}
		}
	}

	if (unlikely(ret)) {
		/*
		 * We are colliding with the timer actually firing.
		 * Punt after filling in the timer's old value, and
		 * disable this firing since we are already reporting
		 * it as an overrun (thanks to bump_cpu_timer above).
		 */
		read_unlock(&tasklist_lock);
		goto out;
	}

	if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
		cpu_time_add(timer->it_clock, &new_expires, val);
	}

	/*
	 * Install the new expiry time (or zero).
	 * For a timer with no notification action, we don't actually
	 * arm the timer (we'll just fake it for timer_gettime).
	 */
	timer->it.cpu.expires = new_expires;
	if (new_expires.sched != 0 &&
	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
	    cpu_time_before(timer->it_clock, val, new_expires)) {
		arm_timer(timer, val);
	}

	read_unlock(&tasklist_lock);

	/*
	 * Install the new reload setting, and
	 * set up the signal and overrun bookkeeping.
	 */
	timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
						&new->it_interval);

	/*
	 * This acts as a modification timestamp for the timer,
	 * so any automatic reload attempt will punt on seeing
	 * that we have reset the timer manually.
	 */
	timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
		~REQUEUE_PENDING;
	timer->it_overrun_last = 0;
	timer->it_overrun = -1;

	if (new_expires.sched != 0 &&
	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
	    !cpu_time_before(timer->it_clock, val, new_expires)) {
		/*
		 * The designated time already passed, so we notify
		 * immediately, even if the thread never runs to
		 * accumulate more time on this clock.
		 */
		cpu_timer_fire(timer);
	}

	ret = 0;
 out:
	if (old) {
		sample_to_timespec(timer->it_clock,
				   timer->it.cpu.incr, &old->it_interval);
	}
	return ret;
}

void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
	union cpu_time_count now;
	struct task_struct *p = timer->it.cpu.task;
	int clear_dead;

	/*
	 * Easy part: convert the reload time.
	 */
	sample_to_timespec(timer->it_clock,
			   timer->it.cpu.incr, &itp->it_interval);

	if (timer->it.cpu.expires.sched == 0) {	/* Timer not armed at all.  */
		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
		return;
	}

	if (unlikely(p == NULL)) {
		/*
		 * This task already died and the timer will never fire.
		 * In this case, expires is actually the dead value.
		 */
	dead:
		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
				   &itp->it_value);
		return;
	}

	/*
	 * Sample the clock to take the difference with the expiry time.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &now);
		clear_dead = p->exit_state;
	} else {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * The process has been reaped.
			 * We can't even collect a sample any more.
			 * Call the timer disarmed, nothing else to do.
			 */
			put_task_struct(p);
			timer->it.cpu.task = NULL;
			timer->it.cpu.expires.sched = 0;
			read_unlock(&tasklist_lock);
			goto dead;
		} else {
			cpu_clock_sample_group(timer->it_clock, p, &now);
			clear_dead = (unlikely(p->exit_state) &&
				      thread_group_empty(p));
		}
		read_unlock(&tasklist_lock);
	}

	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
		if (timer->it.cpu.incr.sched == 0 &&
		    cpu_time_before(timer->it_clock,
				    timer->it.cpu.expires, now)) {
			/*
			 * Do-nothing timer expired and has no reload,
			 * so it's as if it was never set.
			 */
			timer->it.cpu.expires.sched = 0;
			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
			return;
		}
		/*
		 * Account for any expirations and reloads that should
		 * have happened.
		 */
		bump_cpu_timer(timer, now);
	}

	if (unlikely(clear_dead)) {
		/*
		 * We've noticed that the thread is dead, but
		 * not yet reaped.  Take this opportunity to
		 * drop our task ref.
		 */
		clear_dead_task(timer, now);
		goto dead;
	}

	if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
		sample_to_timespec(timer->it_clock,
				   cpu_time_sub(timer->it_clock,
						timer->it.cpu.expires, now),
				   &itp->it_value);
	} else {
		/*
		 * The timer should have expired already, but the firing
		 * hasn't taken place yet.  Say it's just about to expire.
		 */
		itp->it_value.tv_nsec = 1;
		itp->it_value.tv_sec = 0;
	}
}

/*
 * Check for any per-thread CPU timers that have fired and move them off
 * the tsk->cpu_timers[N] list onto the firing list.  Here we update the
 * tsk->it_*_expires values to reflect the remaining thread CPU timers.
 */
static void check_thread_timers(struct task_struct *tsk,
				struct list_head *firing)
{
	int maxfire;
	struct list_head *timers = tsk->cpu_timers;

	maxfire = 20;
	tsk->it_prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
			tsk->it_prof_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	tsk->it_virt_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
			tsk->it_virt_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	tsk->it_sched_expires = 0;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || tsk->sched_time < t->expires.sched) {
			tsk->it_sched_expires = t->expires.sched;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}
}

/*
 * Check for any per-thread CPU timers that have fired and move them
 * off the tsk->*_timers list onto the firing list.  Per-thread timers
 * have already been taken off.
 */
static void check_process_timers(struct task_struct *tsk,
				 struct list_head *firing)
{
	int maxfire;
	struct signal_struct *const sig = tsk->signal;
	cputime_t utime, stime, ptime, virt_expires, prof_expires;
	unsigned long long sched_time, sched_expires;
	struct task_struct *t;
	struct list_head *timers = sig->cpu_timers;

	/*
	 * Don't sample the current process CPU clocks if there are no timers.
	 */
	if (list_empty(&timers[CPUCLOCK_PROF]) &&
	    cputime_eq(sig->it_prof_expires, cputime_zero) &&
	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
	    list_empty(&timers[CPUCLOCK_VIRT]) &&
	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
	    list_empty(&timers[CPUCLOCK_SCHED]))
		return;

	/*
	 * Collect the current process totals.
	 */
	utime = sig->utime;
	stime = sig->stime;
	sched_time = sig->sched_time;
	t = tsk;
	do {
		utime = cputime_add(utime, t->utime);
		stime = cputime_add(stime, t->stime);
		sched_time += t->sched_time;
		t = next_thread(t);
	} while (t != tsk);
	ptime = cputime_add(utime, stime);

	maxfire = 20;
	prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(ptime, t->expires.cpu)) {
			prof_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	virt_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(utime, t->expires.cpu)) {
			virt_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	sched_expires = 0;