posix-cpu-timers.c

		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

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

	/*
	 * Check for the special case thread timers.
	 */
	soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
	if (soft != RLIM_INFINITY) {
		unsigned long hard =
			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);

		if (hard != RLIM_INFINITY &&
		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
			/*
			 * At the hard limit, we just die.
			 * No need to calculate anything else now.
			 */
			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
			return;
		}
		if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
			/*
			 * At the soft limit, send a SIGXCPU every second.
			 */
			if (soft < hard) {
				soft += USEC_PER_SEC;
				sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
			}
			printk(KERN_INFO
				"RT Watchdog Timeout: %s[%d]\n",
				tsk->comm, task_pid_nr(tsk));
			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
		}
	}
}

static void stop_process_timers(struct task_struct *tsk)
{
	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
	unsigned long flags;

	if (!cputimer->running)
		return;

	spin_lock_irqsave(&cputimer->lock, flags);
	cputimer->running = 0;
	spin_unlock_irqrestore(&cputimer->lock, flags);
}

static u32 onecputick;

static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
			     cputime_t *expires, cputime_t cur_time, int signo)
{
	if (cputime_eq(it->expires, cputime_zero))
		return;

	if (cputime_ge(cur_time, it->expires)) {
		if (!cputime_eq(it->incr, cputime_zero)) {
			it->expires = cputime_add(it->expires, it->incr);
			it->error += it->incr_error;
			if (it->error >= onecputick) {
				it->expires = cputime_sub(it->expires,
							  cputime_one_jiffy);
				it->error -= onecputick;
			}
		} else {
			it->expires = cputime_zero;
		}

		trace_itimer_expire(signo == SIGPROF ?
				    ITIMER_PROF : ITIMER_VIRTUAL,
				    tsk->signal->leader_pid, cur_time);
		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
	}

	if (!cputime_eq(it->expires, cputime_zero) &&
	    (cputime_eq(*expires, cputime_zero) ||
	     cputime_lt(it->expires, *expires))) {
		*expires = it->expires;
	}
}

/*
 * 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, ptime, virt_expires, prof_expires;
	unsigned long long sum_sched_runtime, sched_expires;
	struct list_head *timers = sig->cpu_timers;
	struct task_cputime cputime;
	unsigned long soft;

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

	/*
	 * Collect the current process totals.
	 */
	thread_group_cputimer(tsk, &cputime);
	utime = cputime.utime;
	ptime = cputime_add(utime, cputime.stime);
	sum_sched_runtime = cputime.sum_exec_runtime;
	maxfire = 20;
	prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *tl = list_first_entry(timers,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
			prof_expires = tl->expires.cpu;
			break;
		}
		tl->firing = 1;
		list_move_tail(&tl->entry, firing);
	}

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

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

	/*
	 * Check for the special case process timers.
	 */
	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
			 SIGPROF);
	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
			 SIGVTALRM);
	soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
	if (soft != RLIM_INFINITY) {
		unsigned long psecs = cputime_to_secs(ptime);
		unsigned long hard =
			ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
		cputime_t x;
		if (psecs >= hard) {
			/*
			 * At the hard limit, we just die.
			 * No need to calculate anything else now.
			 */
			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
			return;
		}
		if (psecs >= soft) {
			/*
			 * At the soft limit, send a SIGXCPU every second.
			 */
			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
			if (soft < hard) {
				soft++;
				sig->rlim[RLIMIT_CPU].rlim_cur = soft;
			}
		}
		x = secs_to_cputime(soft);
		if (cputime_eq(prof_expires, cputime_zero) ||
		    cputime_lt(x, prof_expires)) {
			prof_expires = x;
		}
	}

	if (!cputime_eq(prof_expires, cputime_zero) &&
	    (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) ||
	     cputime_gt(sig->cputime_expires.prof_exp, prof_expires)))
		sig->cputime_expires.prof_exp = prof_expires;
	if (!cputime_eq(virt_expires, cputime_zero) &&
	    (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) ||
	     cputime_gt(sig->cputime_expires.virt_exp, virt_expires)))
		sig->cputime_expires.virt_exp = virt_expires;
	if (sched_expires != 0 &&
	    (sig->cputime_expires.sched_exp == 0 ||
	     sig->cputime_expires.sched_exp > sched_expires))
		sig->cputime_expires.sched_exp = sched_expires;
}

/*
 * This is called from the signal code (via do_schedule_next_timer)
 * when the last timer signal was delivered and we have to reload the timer.
 */
void posix_cpu_timer_schedule(struct k_itimer *timer)
{
	struct task_struct *p = timer->it.cpu.task;
	union cpu_time_count now;

	if (unlikely(p == NULL))
		/*
		 * The task was cleaned up already, no future firings.
		 */
		goto out;

	/*
	 * Fetch the current sample and update the timer's expiry time.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &now);
		bump_cpu_timer(timer, now);
		if (unlikely(p->exit_state)) {
			clear_dead_task(timer, now);
			goto out;
		}
		read_lock(&tasklist_lock); /* arm_timer needs it.  */
	} else {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * The process has been reaped.
			 * We can't even collect a sample any more.
			 */
			put_task_struct(p);
			timer->it.cpu.task = p = NULL;
			timer->it.cpu.expires.sched = 0;
			goto out_unlock;
		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
			/*
			 * 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 out_unlock;
		}
		cpu_timer_sample_group(timer->it_clock, p, &now);
		bump_cpu_timer(timer, now);
		/* Leave the tasklist_lock locked for the call below.  */
	}

	/*
	 * Now re-arm for the new expiry time.
	 */
	arm_timer(timer, now);

out_unlock:
	read_unlock(&tasklist_lock);

out:
	timer->it_overrun_last = timer->it_overrun;
	timer->it_overrun = -1;
	++timer->it_requeue_pending;
}

/**
 * task_cputime_zero - Check a task_cputime struct for all zero fields.
 *
 * @cputime:	The struct to compare.
 *
 * Checks @cputime to see if all fields are zero.  Returns true if all fields
 * are zero, false if any field is nonzero.
 */
static inline int task_cputime_zero(const struct task_cputime *cputime)
{
	if (cputime_eq(cputime->utime, cputime_zero) &&
	    cputime_eq(cputime->stime, cputime_zero) &&
	    cputime->sum_exec_runtime == 0)
		return 1;
	return 0;
}

/**
 * task_cputime_expired - Compare two task_cputime entities.
 *
 * @sample:	The task_cputime structure to be checked for expiration.
 * @expires:	Expiration times, against which @sample will be checked.
 *
 * Checks @sample against @expires to see if any field of @sample has expired.
 * Returns true if any field of the former is greater than the corresponding
 * field of the latter if the latter field is set.  Otherwise returns false.
 */
static inline int task_cputime_expired(const struct task_cputime *sample,
					const struct task_cputime *expires)
{
	if (!cputime_eq(expires->utime, cputime_zero) &&
	    cputime_ge(sample->utime, expires->utime))
		return 1;
	if (!cputime_eq(expires->stime, cputime_zero) &&
	    cputime_ge(cputime_add(sample->utime, sample->stime),
		       expires->stime))
		return 1;
	if (expires->sum_exec_runtime != 0 &&
	    sample->sum_exec_runtime >= expires->sum_exec_runtime)
		return 1;
	return 0;
}

/**
 * fastpath_timer_check - POSIX CPU timers fast path.
 *
 * @tsk:	The task (thread) being checked.
 *
 * Check the task and thread group timers.  If both are zero (there are no
 * timers set) return false.  Otherwise snapshot the task and thread group
 * timers and compare them with the corresponding expiration times.  Return
 * true if a timer has expired, else return false.
 */
static inline int fastpath_timer_check(struct task_struct *tsk)
{
	struct signal_struct *sig;

	/* tsk == current, ensure it is safe to use ->signal/sighand */
	if (unlikely(tsk->exit_state))
		return 0;

	if (!task_cputime_zero(&tsk->cputime_expires)) {
		struct task_cputime task_sample = {
			.utime = tsk->utime,
			.stime = tsk->stime,
			.sum_exec_runtime = tsk->se.sum_exec_runtime
		};

		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
			return 1;
	}

	sig = tsk->signal;
	if (!task_cputime_zero(&sig->cputime_expires)) {
		struct task_cputime group_sample;

		thread_group_cputimer(tsk, &group_sample);
		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
			return 1;
	}

	return 0;
}

/*
 * This is called from the timer interrupt handler.  The irq handler has
 * already updated our counts.  We need to check if any timers fire now.
 * Interrupts are disabled.
 */
void run_posix_cpu_timers(struct task_struct *tsk)
{
	LIST_HEAD(firing);
	struct k_itimer *timer, *next;

	BUG_ON(!irqs_disabled());

	/*
	 * The fast path checks that there are no expired thread or thread
	 * group timers.  If that's so, just return.
	 */
	if (!fastpath_timer_check(tsk))
		return;

	spin_lock(&tsk->sighand->siglock);
	/*
	 * Here we take off tsk->signal->cpu_timers[N] and
	 * tsk->cpu_timers[N] all the timers that are firing, and
	 * put them on the firing list.
	 */
	check_thread_timers(tsk, &firing);
	check_process_timers(tsk, &firing);

	/*
	 * We must release these locks before taking any timer's lock.
	 * There is a potential race with timer deletion here, as the
	 * siglock now protects our private firing list.  We have set
	 * the firing flag in each timer, so that a deletion attempt
	 * that gets the timer lock before we do will give it up and
	 * spin until we've taken care of that timer below.
	 */
	spin_unlock(&tsk->sighand->siglock);

	/*
	 * Now that all the timers on our list have the firing flag,
	 * noone will touch their list entries but us.  We'll take
	 * each timer's lock before clearing its firing flag, so no
	 * timer call will interfere.
	 */
	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
		int cpu_firing;

		spin_lock(&timer->it_lock);
		list_del_init(&timer->it.cpu.entry);
		cpu_firing = timer->it.cpu.firing;
		timer->it.cpu.firing = 0;
		/*
		 * The firing flag is -1 if we collided with a reset
		 * of the timer, which already reported this
		 * almost-firing as an overrun.  So don't generate an event.
		 */
		if (likely(cpu_firing >= 0))
			cpu_timer_fire(timer);
		spin_unlock(&timer->it_lock);
	}
}

/*
 * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
 * The tsk->sighand->siglock must be held by the caller.
 */
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
			   cputime_t *newval, cputime_t *oldval)
{
	union cpu_time_count now;

	BUG_ON(clock_idx == CPUCLOCK_SCHED);
	cpu_timer_sample_group(clock_idx, tsk, &now);

	if (oldval) {
		/*
		 * We are setting itimer. The *oldval is absolute and we update
		 * it to be relative, *newval argument is relative and we update
		 * it to be absolute.
		 */
		if (!cputime_eq(*oldval, cputime_zero)) {
			if (cputime_le(*oldval, now.cpu)) {
				/* Just about to fire. */
				*oldval = cputime_one_jiffy;
			} else {
				*oldval = cputime_sub(*oldval, now.cpu);
			}
		}

		if (cputime_eq(*newval, cputime_zero))
			return;
		*newval = cputime_add(*newval, now.cpu);
	}

	/*
	 * Update expiration cache if we are the earliest timer, or eventually
	 * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
	 */
	switch (clock_idx) {
	case CPUCLOCK_PROF:
		if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
			tsk->signal->cputime_expires.prof_exp = *newval;
		break;
	case CPUCLOCK_VIRT:
		if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
			tsk->signal->cputime_expires.virt_exp = *newval;
		break;
	}
}

static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
			    struct timespec *rqtp, struct itimerspec *it)
{
	struct k_itimer timer;
	int error;

	/*
	 * Set up a temporary timer and then wait for it to go off.
	 */
	memset(&timer, 0, sizeof timer);
	spin_lock_init(&timer.it_lock);
	timer.it_clock = which_clock;
	timer.it_overrun = -1;
	error = posix_cpu_timer_create(&timer);
	timer.it_process = current;
	if (!error) {
		static struct itimerspec zero_it;

		memset(it, 0, sizeof *it);
		it->it_value = *rqtp;

		spin_lock_irq(&timer.it_lock);
		error = posix_cpu_timer_set(&timer, flags, it, NULL);
		if (error) {
			spin_unlock_irq(&timer.it_lock);
			return error;
		}

		while (!signal_pending(current)) {
			if (timer.it.cpu.expires.sched == 0) {
				/*
				 * Our timer fired and was reset.
				 */
				spin_unlock_irq(&timer.it_lock);
				return 0;
			}

			/*
			 * Block until cpu_timer_fire (or a signal) wakes us.
			 */
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&timer.it_lock);
			schedule();
			spin_lock_irq(&timer.it_lock);
		}

		/*
		 * We were interrupted by a signal.
		 */
		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
		posix_cpu_timer_set(&timer, 0, &zero_it, it);
		spin_unlock_irq(&timer.it_lock);

		if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
			/*
			 * It actually did fire already.
			 */
			return 0;
		}

		error = -ERESTART_RESTARTBLOCK;
	}

	return error;
}

int posix_cpu_nsleep(const clockid_t which_clock, int flags,
		     struct timespec *rqtp, struct timespec __user *rmtp)
{
	struct restart_block *restart_block =
	    &current_thread_info()->restart_block;
	struct itimerspec it;
	int error;

	/*
	 * Diagnose required errors first.
	 */
	if (CPUCLOCK_PERTHREAD(which_clock) &&
	    (CPUCLOCK_PID(which_clock) == 0 ||
	     CPUCLOCK_PID(which_clock) == current->pid))
		return -EINVAL;

	error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);

	if (error == -ERESTART_RESTARTBLOCK) {

	       	if (flags & TIMER_ABSTIME)
			return -ERESTARTNOHAND;
		/*
	 	 * Report back to the user the time still remaining.
	 	 */
		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
			return -EFAULT;

		restart_block->fn = posix_cpu_nsleep_restart;
		restart_block->arg0 = which_clock;
		restart_block->arg1 = (unsigned long) rmtp;
		restart_block->arg2 = rqtp->tv_sec;
		restart_block->arg3 = rqtp->tv_nsec;
	}
	return error;
}

long posix_cpu_nsleep_restart(struct restart_block *restart_block)
{
	clockid_t which_clock = restart_block->arg0;
	struct timespec __user *rmtp;
	struct timespec t;
	struct itimerspec it;
	int error;

	rmtp = (struct timespec __user *) restart_block->arg1;
	t.tv_sec = restart_block->arg2;
	t.tv_nsec = restart_block->arg3;

	restart_block->fn = do_no_restart_syscall;
	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);

	if (error == -ERESTART_RESTARTBLOCK) {
		/*
	 	 * Report back to the user the time still remaining.
	 	 */
		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
			return -EFAULT;

		restart_block->fn = posix_cpu_nsleep_restart;
		restart_block->arg0 = which_clock;
		restart_block->arg1 = (unsigned long) rmtp;
		restart_block->arg2 = t.tv_sec;
		restart_block->arg3 = t.tv_nsec;
	}
	return error;

}


#define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
#define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)

static int process_cpu_clock_getres(const clockid_t which_clock,
				    struct timespec *tp)
{
	return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
}
static int process_cpu_clock_get(const clockid_t which_clock,
				 struct timespec *tp)
{
	return posix_cpu_clock_get(PROCESS_CLOCK, tp);
}
static int process_cpu_timer_create(struct k_itimer *timer)
{
	timer->it_clock = PROCESS_CLOCK;
	return posix_cpu_timer_create(timer);
}
static int process_cpu_nsleep(const clockid_t which_clock, int flags,
			      struct timespec *rqtp,
			      struct timespec __user *rmtp)
{
	return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
}
static long process_cpu_nsleep_restart(struct restart_block *restart_block)
{
	return -EINVAL;
}
static int thread_cpu_clock_getres(const clockid_t which_clock,
				   struct timespec *tp)
{
	return posix_cpu_clock_getres(THREAD_CLOCK, tp);
}
static int thread_cpu_clock_get(const clockid_t which_clock,
				struct timespec *tp)
{
	return posix_cpu_clock_get(THREAD_CLOCK, tp);
}
static int thread_cpu_timer_create(struct k_itimer *timer)
{
	timer->it_clock = THREAD_CLOCK;
	return posix_cpu_timer_create(timer);
}
static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
			      struct timespec *rqtp, struct timespec __user *rmtp)
{
	return -EINVAL;
}
static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
{
	return -EINVAL;
}

static __init int init_posix_cpu_timers(void)
{
	struct k_clock process = {
		.clock_getres = process_cpu_clock_getres,
		.clock_get = process_cpu_clock_get,
		.clock_set = do_posix_clock_nosettime,
		.timer_create = process_cpu_timer_create,
		.nsleep = process_cpu_nsleep,
		.nsleep_restart = process_cpu_nsleep_restart,
	};
	struct k_clock thread = {
		.clock_getres = thread_cpu_clock_getres,
		.clock_get = thread_cpu_clock_get,
		.clock_set = do_posix_clock_nosettime,
		.timer_create = thread_cpu_timer_create,
		.nsleep = thread_cpu_nsleep,
		.nsleep_restart = thread_cpu_nsleep_restart,
	};
	struct timespec ts;

	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);

	cputime_to_timespec(cputime_one_jiffy, &ts);
	onecputick = ts.tv_nsec;
	WARN_ON(ts.tv_sec != 0);

	return 0;
}
__initcall(init_posix_cpu_timers);