/*
 * Insert the timer on the appropriate list before any timers that
 * expire later.  This must be called with the sighand lock held.
 */
static void arm_timer(struct k_itimer *timer)
{
	struct task_struct *p = timer->it.cpu.task;
	struct list_head *head, *listpos;
	struct task_cputime *cputime_expires;
	struct cpu_timer_list *const nt = &timer->it.cpu;
	struct cpu_timer_list *next;

	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		head = p->cpu_timers;
		cputime_expires = &p->cputime_expires;
	} else {
		head = p->signal->cpu_timers;
		cputime_expires = &p->signal->cputime_expires;
	}
	head += CPUCLOCK_WHICH(timer->it_clock);

	listpos = head;
	list_for_each_entry(next, head, entry) {
		if (nt->expires < next->expires)
			break;
		listpos = &next->entry;
	}
	list_add(&nt->entry, listpos);

	if (listpos == head) {
		unsigned long long exp = nt->expires;

		/*
		 * We are the new earliest-expiring POSIX 1.b timer, hence
		 * need to update expiration cache. Take into account that
		 * for process timers we share expiration cache with itimers
		 * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
		 */

		switch (CPUCLOCK_WHICH(timer->it_clock)) {
		case CPUCLOCK_PROF:
			if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
				cputime_expires->prof_exp = expires_to_cputime(exp);
			break;
		case CPUCLOCK_VIRT:
			if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
				cputime_expires->virt_exp = expires_to_cputime(exp);
			break;
		case CPUCLOCK_SCHED:
			if (cputime_expires->sched_exp == 0 ||
			    cputime_expires->sched_exp > exp)
				cputime_expires->sched_exp = exp;
			break;
		}
		if (CPUCLOCK_PERTHREAD(timer->it_clock))
			tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER);
		else
			tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER);
	}
}

/* Set CLOCK to value TP.  */
int
__clock_settime (clockid_t clock_id, const struct timespec *tp)
{
  int retval;

  /* Make sure the time cvalue is OK.  */
  if (tp->tv_nsec < 0 || tp->tv_nsec >= 1000000000)
    {
      __set_errno (EINVAL);
      return -1;
    }

  switch (clock_id)
    {
#define HANDLE_REALTIME \
      do {								      \
	struct timeval tv;						      \
	TIMESPEC_TO_TIMEVAL (&tv, tp);					      \
									      \
	retval = settimeofday (&tv, NULL);				      \
      } while (0)

#ifdef SYSDEP_SETTIME
      SYSDEP_SETTIME;
#endif

#ifndef HANDLED_REALTIME
    case CLOCK_REALTIME:
      HANDLE_REALTIME;
      break;
#endif

    default:
#ifdef SYSDEP_SETTIME_CPU
      SYSDEP_SETTIME_CPU;
#endif
#ifndef HANDLED_CPUTIME
# if HP_TIMING_AVAIL
      if (CPUCLOCK_WHICH (clock_id) == CLOCK_PROCESS_CPUTIME_ID
	  || CPUCLOCK_WHICH (clock_id) == CLOCK_THREAD_CPUTIME_ID)
	retval = hp_timing_settime (clock_id, tp);
      else
# endif
	{
	  __set_errno (EINVAL);
	  retval = -1;
	}
#endif
      break;
    }

  return retval;
}

static void sample_to_timespec(const clockid_t which_clock,
			       unsigned long long expires,
			       struct timespec *tp)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
		*tp = ns_to_timespec(expires);
	else
		cputime_to_timespec((__force cputime_t)expires, tp);
}

static void sample_to_timespec(const 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 int
posix_cpu_clock_getres(const 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;
}

/*
 * Sample a per-thread clock for the given task.
 */
static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
			    unsigned long long *sample)
{
	switch (CPUCLOCK_WHICH(which_clock)) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		*sample = prof_ticks(p);
		break;
	case CPUCLOCK_VIRT:
		*sample = virt_ticks(p);
		break;
	case CPUCLOCK_SCHED:
		*sample = task_sched_runtime(p);
		break;
	}
	return 0;
}

/*
 * Sample a process (thread group) timer for the given group_leader task.
 * Must be called with task sighand lock held for safe while_each_thread()
 * traversal.
 */
static int cpu_timer_sample_group(const clockid_t which_clock,
				  struct task_struct *p, u64 *sample)
{
	struct task_cputime cputime;

	thread_group_cputimer(p, &cputime);
	switch (CPUCLOCK_WHICH(which_clock)) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		*sample = cputime.utime + cputime.stime;
		break;
	case CPUCLOCK_VIRT:
		*sample = cputime.utime;
		break;
	case CPUCLOCK_SCHED:
		*sample = cputime.sum_exec_runtime;
		break;
	}
	return 0;
}

static int check_clock(const 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;
}

/*
 * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
 * This is called from sys_timer_create() and do_cpu_nanosleep() with the
 * new timer already all-zeros initialized.
 */
static 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);

	rcu_read_lock();
	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
		if (pid == 0) {
			p = current;
		} else {
			p = find_task_by_vpid(pid);
			if (p && !same_thread_group(p, current))
				p = NULL;
		}
	} else {
		if (pid == 0) {
			p = current->group_leader;
		} else {
			p = find_task_by_vpid(pid);
			if (p && !has_group_leader_pid(p))
				p = NULL;
		}
	}
	new_timer->it.cpu.task = p;
	if (p) {
		get_task_struct(p);
	} else {
		ret = -EINVAL;
	}
	rcu_read_unlock();

	return ret;
}

/*
 * Sample a process (thread group) clock for the given group_leader task.
 * Must be called with task sighand lock held for safe while_each_thread()
 * traversal.
 */
static int cpu_clock_sample_group(const clockid_t which_clock,
				  struct task_struct *p,
				  unsigned long long *sample)
{
	struct task_cputime cputime;

	switch (CPUCLOCK_WHICH(which_clock)) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		thread_group_cputime(p, &cputime);
		*sample = cputime_to_expires(cputime.utime + cputime.stime);
		break;
	case CPUCLOCK_VIRT:
		thread_group_cputime(p, &cputime);
		*sample = cputime_to_expires(cputime.utime);
		break;
	case CPUCLOCK_SCHED:
		thread_group_cputime(p, &cputime);
		*sample = cputime.sum_exec_runtime;
		break;
	}
	return 0;
}