posix-cpu-timers.c

/*
 * Implement CPU time clocks for the POSIX clock interface.
 */

#include <linux/sched.h>
#include <linux/posix-timers.h>
#include <asm/uaccess.h>
#include <linux/errno.h>

static int check_clock(clockid_t which_clock)
{
	int error = 0;
	struct task_struct *p;
	const pid_t pid = CPUCLOCK_PID(which_clock);

	if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX)
		return -EINVAL;

	if (pid == 0)
		return 0;

	read_lock(&tasklist_lock);
	p = find_task_by_pid(pid);
	if (!p || (CPUCLOCK_PERTHREAD(which_clock) ?
		   p->tgid != current->tgid : p->tgid != pid)) {
		error = -EINVAL;
	}
	read_unlock(&tasklist_lock);

	return error;
}

static inline union cpu_time_count
timespec_to_sample(clockid_t which_clock, const struct timespec *tp)
{
	union cpu_time_count ret;
	ret.sched = 0;		/* high half always zero when .cpu used */
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		ret.sched = tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
	} else {
		ret.cpu = timespec_to_cputime(tp);
	}
	return ret;
}

static void sample_to_timespec(clockid_t which_clock,
			       union cpu_time_count cpu,
			       struct timespec *tp)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		tp->tv_sec = div_long_long_rem(cpu.sched,
					       NSEC_PER_SEC, &tp->tv_nsec);
	} else {
		cputime_to_timespec(cpu.cpu, tp);
	}
}

static inline int cpu_time_before(clockid_t which_clock,
				  union cpu_time_count now,
				  union cpu_time_count then)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		return now.sched < then.sched;
	}  else {
		return cputime_lt(now.cpu, then.cpu);
	}
}
static inline void cpu_time_add(clockid_t which_clock,
				union cpu_time_count *acc,
			        union cpu_time_count val)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		acc->sched += val.sched;
	}  else {
		acc->cpu = cputime_add(acc->cpu, val.cpu);
	}
}
static inline union cpu_time_count cpu_time_sub(clockid_t which_clock,
						union cpu_time_count a,
						union cpu_time_count b)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		a.sched -= b.sched;
	}  else {
		a.cpu = cputime_sub(a.cpu, b.cpu);
	}
	return a;
}

/*
 * Update expiry time from increment, and increase overrun count,
 * given the current clock sample.
 */
static inline void bump_cpu_timer(struct k_itimer *timer,
				  union cpu_time_count now)
{
	int i;

	if (timer->it.cpu.incr.sched == 0)
		return;

	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
		unsigned long long delta, incr;

		if (now.sched < timer->it.cpu.expires.sched)
			return;
		incr = timer->it.cpu.incr.sched;
		delta = now.sched + incr - timer->it.cpu.expires.sched;
		/* Don't use (incr*2 < delta), incr*2 might overflow. */
		for (i = 0; incr < delta - incr; i++)
			incr = incr << 1;
		for (; i >= 0; incr >>= 1, i--) {
			if (delta <= incr)
				continue;
			timer->it.cpu.expires.sched += incr;
			timer->it_overrun += 1 << i;
			delta -= incr;
		}
	} else {
		cputime_t delta, incr;

		if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
			return;
		incr = timer->it.cpu.incr.cpu;
		delta = cputime_sub(cputime_add(now.cpu, incr),
				    timer->it.cpu.expires.cpu);
		/* Don't use (incr*2 < delta), incr*2 might overflow. */
		for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
			     incr = cputime_add(incr, incr);
		for (; i >= 0; incr = cputime_halve(incr), i--) {
			if (cputime_le(delta, incr))
				continue;
			timer->it.cpu.expires.cpu =
				cputime_add(timer->it.cpu.expires.cpu, incr);
			timer->it_overrun += 1 << i;
			delta = cputime_sub(delta, incr);
		}
	}
}

static inline cputime_t prof_ticks(struct task_struct *p)
{
	return cputime_add(p->utime, p->stime);
}
static inline cputime_t virt_ticks(struct task_struct *p)
{
	return p->utime;
}
static inline unsigned long long sched_ns(struct task_struct *p)
{
	return (p == current) ? current_sched_time(p) : p->sched_time;
}

int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp)
{
	int error = check_clock(which_clock);
	if (!error) {
		tp->tv_sec = 0;
		tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ);
		if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
			/*
			 * If sched_clock is using a cycle counter, we
			 * don't have any idea of its true resolution
			 * exported, but it is much more than 1s/HZ.
			 */
			tp->tv_nsec = 1;
		}
	}
	return error;
}

int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp)
{
	/*
	 * You can never reset a CPU clock, but we check for other errors
	 * in the call before failing with EPERM.
	 */
	int error = check_clock(which_clock);
	if (error == 0) {
		error = -EPERM;
	}
	return error;
}


/*
 * Sample a per-thread clock for the given task.
 */
static int cpu_clock_sample(clockid_t which_clock, struct task_struct *p,
			    union cpu_time_count *cpu)
{
	switch (CPUCLOCK_WHICH(which_clock)) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		cpu->cpu = prof_ticks(p);
		break;
	case CPUCLOCK_VIRT:
		cpu->cpu = virt_ticks(p);
		break;
	case CPUCLOCK_SCHED:
		cpu->sched = sched_ns(p);
		break;
	}
	return 0;
}

/*
 * Sample a process (thread group) clock for the given group_leader task.
 * Must be called with tasklist_lock held for reading.
 * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
 */
static int cpu_clock_sample_group_locked(unsigned int clock_idx,
					 struct task_struct *p,
					 union cpu_time_count *cpu)
{
	struct task_struct *t = p;
 	switch (clock_idx) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		cpu->cpu = cputime_add(p->signal->utime, p->signal->stime);
		do {
			cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t));
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_VIRT:
		cpu->cpu = p->signal->utime;
		do {
			cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t));
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_SCHED:
		cpu->sched = p->signal->sched_time;
		/* Add in each other live thread.  */
		while ((t = next_thread(t)) != p) {
			cpu->sched += t->sched_time;
		}
		if (p->tgid == current->tgid) {
			/*
			 * We're sampling ourselves, so include the
			 * cycles not yet banked.  We still omit
			 * other threads running on other CPUs,
			 * so the total can always be behind as
			 * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ).
			 */
			cpu->sched += current_sched_time(current);
		} else {
			cpu->sched += p->sched_time;
		}
		break;
	}
	return 0;
}

/*
 * Sample a process (thread group) clock for the given group_leader task.
 * Must be called with tasklist_lock held for reading.
 */
static int cpu_clock_sample_group(clockid_t which_clock,
				  struct task_struct *p,
				  union cpu_time_count *cpu)
{
	int ret;
	unsigned long flags;
	spin_lock_irqsave(&p->sighand->siglock, flags);
	ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
					    cpu);
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	return ret;
}


int posix_cpu_clock_get(clockid_t which_clock, struct timespec *tp)
{
	const pid_t pid = CPUCLOCK_PID(which_clock);
	int error = -EINVAL;
	union cpu_time_count rtn;

	if (pid == 0) {
		/*
		 * Special case constant value for our own clocks.
		 * We don't have to do any lookup to find ourselves.
		 */
		if (CPUCLOCK_PERTHREAD(which_clock)) {
			/*
			 * Sampling just ourselves we can do with no locking.
			 */
			error = cpu_clock_sample(which_clock,
						 current, &rtn);
		} else {
			read_lock(&tasklist_lock);
			error = cpu_clock_sample_group(which_clock,
						       current, &rtn);
			read_unlock(&tasklist_lock);
		}
	} else {
		/*
		 * Find the given PID, and validate that the caller
		 * should be able to see it.
		 */
		struct task_struct *p;
		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);
		if (p) {
			if (CPUCLOCK_PERTHREAD(which_clock)) {
				if (p->tgid == current->tgid) {
					error = cpu_clock_sample(which_clock,
								 p, &rtn);
				}
			} else if (p->tgid == pid && p->signal) {
				error = cpu_clock_sample_group(which_clock,
							       p, &rtn);
			}
		}
		read_unlock(&tasklist_lock);
	}

	if (error)
		return error;
	sample_to_timespec(which_clock, rtn, tp);
	return 0;
}


/*
 * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
 * This is called from sys_timer_create with the new timer already locked.
 */
int posix_cpu_timer_create(struct k_itimer *new_timer)
{
	int ret = 0;
	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
	struct task_struct *p;

	if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX)
		return -EINVAL;

	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
	new_timer->it.cpu.incr.sched = 0;
	new_timer->it.cpu.expires.sched = 0;

	read_lock(&tasklist_lock);
	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
		if (pid == 0) {
			p = current;
		} else {
			p = find_task_by_pid(pid);
			if (p && p->tgid != current->tgid)
				p = NULL;
		}
	} else {
		if (pid == 0) {
			p = current->group_leader;
		} else {
			p = find_task_by_pid(pid);
			if (p && p->tgid != pid)
				p = NULL;
		}
	}
	new_timer->it.cpu.task = p;
	if (p) {
		get_task_struct(p);
	} else {
		ret = -EINVAL;
	}
	read_unlock(&tasklist_lock);

	return ret;
}

/*
 * Clean up a CPU-clock timer that is about to be destroyed.
 * This is called from timer deletion with the timer already locked.
 * 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_del(struct k_itimer *timer)
{
	struct task_struct *p = timer->it.cpu.task;

	if (timer->it.cpu.firing)
		return TIMER_RETRY;

	if (unlikely(p == NULL))
		return 0;

	spin_lock(&p->sighand->siglock);
	if (!list_empty(&timer->it.cpu.entry)) {
		/*
		 * Take us off the task's timer list.  We don't need to
		 * take tasklist_lock and check for the task being reaped.
		 * If it was reaped, it already called posix_cpu_timers_exit
		 * and posix_cpu_timers_exit_group to clear all the timers
		 * that pointed to it.
		 */
		list_del(&timer->it.cpu.entry);
		put_task_struct(p);
	}
	spin_unlock(&p->sighand->siglock);

	return 0;
}

/*
 * Clean out CPU timers still ticking when a thread exited.  The task
 * pointer is cleared, and the expiry time is replaced with the residual
 * time for later timer_gettime calls to return.
 * This must be called with the siglock held.
 */
static void cleanup_timers(struct list_head *head,
			   cputime_t utime, cputime_t stime,
			   unsigned long long sched_time)
{
	struct cpu_timer_list *timer, *next;
	cputime_t ptime = cputime_add(utime, stime);

	list_for_each_entry_safe(timer, next, head, entry) {
		put_task_struct(timer->task);
		timer->task = NULL;
		list_del_init(&timer->entry);
		if (cputime_lt(timer->expires.cpu, ptime)) {
			timer->expires.cpu = cputime_zero;
		} else {
			timer->expires.cpu = cputime_sub(timer->expires.cpu,
							 ptime);
		}
	}

	++head;
	list_for_each_entry_safe(timer, next, head, entry) {
		put_task_struct(timer->task);
		timer->task = NULL;
		list_del_init(&timer->entry);
		if (cputime_lt(timer->expires.cpu, utime)) {
			timer->expires.cpu = cputime_zero;
		} else {
			timer->expires.cpu = cputime_sub(timer->expires.cpu,
							 utime);
		}
	}

	++head;
	list_for_each_entry_safe(timer, next, head, entry) {
		put_task_struct(timer->task);
		timer->task = NULL;
		list_del_init(&timer->entry);
		if (timer->expires.sched < sched_time) {
			timer->expires.sched = 0;
		} else {
			timer->expires.sched -= sched_time;
		}
	}
}

/*
 * These are both called with the siglock held, when the current thread
 * is being reaped.  When the final (leader) thread in the group is reaped,
 * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit.
 */
void posix_cpu_timers_exit(struct task_struct *tsk)
{
	cleanup_timers(tsk->cpu_timers,
		       tsk->utime, tsk->stime, tsk->sched_time);

}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
	cleanup_timers(tsk->signal->cpu_timers,
		       cputime_add(tsk->utime, tsk->signal->utime),
		       cputime_add(tsk->stime, tsk->signal->stime),
		       tsk->sched_time + tsk->signal->sched_time);
}


/*
 * Set the expiry times of all the threads in the process so one of them
 * will go off before the process cumulative expiry total is reached.
 */
static void process_timer_rebalance(struct task_struct *p,
				    unsigned int clock_idx,
				    union cpu_time_count expires,
				    union cpu_time_count val)
{
	cputime_t ticks, left;
	unsigned long long ns, nsleft;
 	struct task_struct *t = p;
	unsigned int nthreads = atomic_read(&p->signal->live);

	switch (clock_idx) {
	default:
		BUG();
		break;
	case CPUCLOCK_PROF:
		left = cputime_div(cputime_sub(expires.cpu, val.cpu),
				   nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ticks = cputime_add(prof_ticks(t), left);
				if (cputime_eq(t->it_prof_expires,
					       cputime_zero) ||
				    cputime_gt(t->it_prof_expires, ticks)) {
					t->it_prof_expires = ticks;
				}
			}
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_VIRT:
		left = cputime_div(cputime_sub(expires.cpu, val.cpu),
				   nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ticks = cputime_add(virt_ticks(t), left);
				if (cputime_eq(t->it_virt_expires,
					       cputime_zero) ||
				    cputime_gt(t->it_virt_expires, ticks)) {
					t->it_virt_expires = ticks;
				}
			}
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_SCHED:
		nsleft = expires.sched - val.sched;
		do_div(nsleft, nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ns = t->sched_time + nsleft;
				if (t->it_sched_expires == 0 ||
				    t->it_sched_expires > ns) {
					t->it_sched_expires = ns;
				}
			}
			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) {
				listpos = &next->entry;
				break;
			}
		}
	} else {
		list_for_each_entry(next, head, entry) {
			if (cputime_gt(next->expires.cpu, nt->expires.cpu)) {
				listpos = &next->entry;
				break;
			}
		}
	}
	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());
	spin_lock(&p->sighand->siglock);
	old_expires = timer->it.cpu.expires;
	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(timer->it.cpu.firing)) {
		/*
		 * 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);
		timer->it.cpu.firing = -1;
		ret = TIMER_RETRY;
		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)
{
	struct list_head *timers = tsk->cpu_timers;

	tsk->it_prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (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;
	tsk->it_virt_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (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;
	tsk->it_sched_expires = 0;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (tsk->sched_time < t->expires.sched) {
			tsk->it_sched_expires = t->expires.sched;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}
}