posix-cpu-timers.c

linux 2.6.19 kernel source code before patching

/*
 * 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(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;
}

static inline union cpu_time_count
timespec_to_sample(const 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 = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
	} else {
		ret.cpu = timespec_to_cputime(tp);
	}
	return ret;
}

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 inline int cpu_time_before(const 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(const 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(const 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;
}

/*
 * Divide and limit the result to res >= 1
 *
 * This is necessary to prevent signal delivery starvation, when the result of
 * the division would be rounded down to 0.
 */
static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
{
	cputime_t res = cputime_div(time, div);

	return max_t(cputime_t, res, 1);
}

/*
 * Update expiry time from increment, and increase overrun count,
 * given the current clock sample.
 */
static 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_lt(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(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;
}

int posix_cpu_clock_set(const 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(const 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;
		}
		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.
 */
static int cpu_clock_sample_group(const 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(const 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;
		rcu_read_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 {
				read_lock(&tasklist_lock);
				if (p->tgid == pid && p->signal) {
					error =
					    cpu_clock_sample_group(which_clock,
							           p, &rtn);
				}
				read_unlock(&tasklist_lock);
			}
		}
		rcu_read_unlock();
	}

	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;
	int ret = 0;

	if (likely(p != NULL)) {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * We raced with the reaping of the task.
			 * The deletion should have cleared us off the list.
			 */
			BUG_ON(!list_empty(&timer->it.cpu.entry));
		} else {
			spin_lock(&p->sighand->siglock);
			if (timer->it.cpu.firing)
				ret = TIMER_RETRY;
			else
				list_del(&timer->it.cpu.entry);
			spin_unlock(&p->sighand->siglock);
		}
		read_unlock(&tasklist_lock);

		if (!ret)
			put_task_struct(p);
	}

	return ret;
}

/*
 * 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) {
		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) {
		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) {
		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);

	if (!nthreads)
		return;

	switch (clock_idx) {
	default:
		BUG();
		break;
	case CPUCLOCK_PROF:
		left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
				       nthreads);
		do {
			if (likely(!(t->flags & PF_EXITING))) {
				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_non_zero(cputime_sub(expires.cpu, val.cpu),
				       nthreads);
		do {
			if (likely(!(t->flags & PF_EXITING))) {
				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);
		nsleft = max_t(unsigned long long, nsleft, 1);
		do {
			if (likely(!(t->flags & PF_EXITING))) {
				ns = t->sched_time + nsleft;
				if (t->it_sched_expires == 0 ||
				    t->it_sched_expires > ns) {
					t->it_sched_expires = ns;
				}
			}