posix-timers.c

linux 2.6.19 kernel source code before patching

/*
 * linux/kernel/posix-timers.c
 *
 *
 * 2002-10-15  Posix Clocks & timers
 *                           by George Anzinger [e-mail]
 *
 *			     Copyright (C) 2002 2003 by MontaVista Software.
 *
 * 2004-06-01  Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
 *			     Copyright (C) 2004 Boris Hu
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or (at
 * your option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.

 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA
 */

/* These are all the functions necessary to implement
 * POSIX clocks & timers
 */
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/mutex.h>

#include <asm/uaccess.h>
#include <asm/semaphore.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/idr.h>
#include <linux/posix-timers.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <linux/module.h>

/*
 * Management arrays for POSIX timers.	 Timers are kept in slab memory
 * Timer ids are allocated by an external routine that keeps track of the
 * id and the timer.  The external interface is:
 *
 * void *idr_find(struct idr *idp, int id);           to find timer_id <id>
 * int idr_get_new(struct idr *idp, void *ptr);       to get a new id and
 *                                                    related it to <ptr>
 * void idr_remove(struct idr *idp, int id);          to release <id>
 * void idr_init(struct idr *idp);                    to initialize <idp>
 *                                                    which we supply.
 * The idr_get_new *may* call slab for more memory so it must not be
 * called under a spin lock.  Likewise idr_remore may release memory
 * (but it may be ok to do this under a lock...).
 * idr_find is just a memory look up and is quite fast.  A -1 return
 * indicates that the requested id does not exist.
 */

/*
 * Lets keep our timers in a slab cache :-)
 */
static struct kmem_cache *posix_timers_cache;
static struct idr posix_timers_id;
static DEFINE_SPINLOCK(idr_lock);

/*
 * we assume that the new SIGEV_THREAD_ID shares no bits with the other
 * SIGEV values.  Here we put out an error if this assumption fails.
 */
#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \
                       ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
#endif


/*
 * The timer ID is turned into a timer address by idr_find().
 * Verifying a valid ID consists of:
 *
 * a) checking that idr_find() returns other than -1.
 * b) checking that the timer id matches the one in the timer itself.
 * c) that the timer owner is in the callers thread group.
 */

/*
 * CLOCKs: The POSIX standard calls for a couple of clocks and allows us
 *	    to implement others.  This structure defines the various
 *	    clocks and allows the possibility of adding others.	 We
 *	    provide an interface to add clocks to the table and expect
 *	    the "arch" code to add at least one clock that is high
 *	    resolution.	 Here we define the standard CLOCK_REALTIME as a
 *	    1/HZ resolution clock.
 *
 * RESOLUTION: Clock resolution is used to round up timer and interval
 *	    times, NOT to report clock times, which are reported with as
 *	    much resolution as the system can muster.  In some cases this
 *	    resolution may depend on the underlying clock hardware and
 *	    may not be quantifiable until run time, and only then is the
 *	    necessary code is written.	The standard says we should say
 *	    something about this issue in the documentation...
 *
 * FUNCTIONS: The CLOCKs structure defines possible functions to handle
 *	    various clock functions.  For clocks that use the standard
 *	    system timer code these entries should be NULL.  This will
 *	    allow dispatch without the overhead of indirect function
 *	    calls.  CLOCKS that depend on other sources (e.g. WWV or GPS)
 *	    must supply functions here, even if the function just returns
 *	    ENOSYS.  The standard POSIX timer management code assumes the
 *	    following: 1.) The k_itimer struct (sched.h) is used for the
 *	    timer.  2.) The list, it_lock, it_clock, it_id and it_process
 *	    fields are not modified by timer code.
 *
 *          At this time all functions EXCEPT clock_nanosleep can be
 *          redirected by the CLOCKS structure.  Clock_nanosleep is in
 *          there, but the code ignores it.
 *
 * Permissions: It is assumed that the clock_settime() function defined
 *	    for each clock will take care of permission checks.	 Some
 *	    clocks may be set able by any user (i.e. local process
 *	    clocks) others not.	 Currently the only set able clock we
 *	    have is CLOCK_REALTIME and its high res counter part, both of
 *	    which we beg off on and pass to do_sys_settimeofday().
 */

static struct k_clock posix_clocks[MAX_CLOCKS];

/*
 * These ones are defined below.
 */
static int common_nsleep(const clockid_t, int flags, struct timespec *t,
			 struct timespec __user *rmtp);
static void common_timer_get(struct k_itimer *, struct itimerspec *);
static int common_timer_set(struct k_itimer *, int,
			    struct itimerspec *, struct itimerspec *);
static int common_timer_del(struct k_itimer *timer);

static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);

static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);

static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
{
	spin_unlock_irqrestore(&timr->it_lock, flags);
}

/*
 * Call the k_clock hook function if non-null, or the default function.
 */
#define CLOCK_DISPATCH(clock, call, arglist) \
 	((clock) < 0 ? posix_cpu_##call arglist : \
 	 (posix_clocks[clock].call != NULL \
 	  ? (*posix_clocks[clock].call) arglist : common_##call arglist))

/*
 * Default clock hook functions when the struct k_clock passed
 * to register_posix_clock leaves a function pointer null.
 *
 * The function common_CALL is the default implementation for
 * the function pointer CALL in struct k_clock.
 */

static inline int common_clock_getres(const clockid_t which_clock,
				      struct timespec *tp)
{
	tp->tv_sec = 0;
	tp->tv_nsec = posix_clocks[which_clock].res;
	return 0;
}

/*
 * Get real time for posix timers
 */
static int common_clock_get(clockid_t which_clock, struct timespec *tp)
{
	ktime_get_real_ts(tp);
	return 0;
}

static inline int common_clock_set(const clockid_t which_clock,
				   struct timespec *tp)
{
	return do_sys_settimeofday(tp, NULL);
}

static int common_timer_create(struct k_itimer *new_timer)
{
	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
	return 0;
}

/*
 * Return nonzero if we know a priori this clockid_t value is bogus.
 */
static inline int invalid_clockid(const clockid_t which_clock)
{
	if (which_clock < 0)	/* CPU clock, posix_cpu_* will check it */
		return 0;
	if ((unsigned) which_clock >= MAX_CLOCKS)
		return 1;
	if (posix_clocks[which_clock].clock_getres != NULL)
		return 0;
	if (posix_clocks[which_clock].res != 0)
		return 0;
	return 1;
}

/*
 * Get monotonic time for posix timers
 */
static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
{
	ktime_get_ts(tp);
	return 0;
}

/*
 * Initialize everything, well, just everything in Posix clocks/timers ;)
 */
static __init int init_posix_timers(void)
{
	struct k_clock clock_realtime = {
		.clock_getres = hrtimer_get_res,
	};
	struct k_clock clock_monotonic = {
		.clock_getres = hrtimer_get_res,
		.clock_get = posix_ktime_get_ts,
		.clock_set = do_posix_clock_nosettime,
	};

	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);

	posix_timers_cache = kmem_cache_create("posix_timers_cache",
					sizeof (struct k_itimer), 0, 0, NULL, NULL);
	idr_init(&posix_timers_id);
	return 0;
}

__initcall(init_posix_timers);

static void schedule_next_timer(struct k_itimer *timr)
{
	struct hrtimer *timer = &timr->it.real.timer;

	if (timr->it.real.interval.tv64 == 0)
		return;

	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
					    timr->it.real.interval);

	timr->it_overrun_last = timr->it_overrun;
	timr->it_overrun = -1;
	++timr->it_requeue_pending;
	hrtimer_restart(timer);
}

/*
 * This function is exported for use by the signal deliver code.  It is
 * called just prior to the info block being released and passes that
 * block to us.  It's function is to update the overrun entry AND to
 * restart the timer.  It should only be called if the timer is to be
 * restarted (i.e. we have flagged this in the sys_private entry of the
 * info block).
 *
 * To protect aginst the timer going away while the interrupt is queued,
 * we require that the it_requeue_pending flag be set.
 */
void do_schedule_next_timer(struct siginfo *info)
{
	struct k_itimer *timr;
	unsigned long flags;

	timr = lock_timer(info->si_tid, &flags);

	if (timr && timr->it_requeue_pending == info->si_sys_private) {
		if (timr->it_clock < 0)
			posix_cpu_timer_schedule(timr);
		else
			schedule_next_timer(timr);

		info->si_overrun = timr->it_overrun_last;
	}

	if (timr)
		unlock_timer(timr, flags);
}

int posix_timer_event(struct k_itimer *timr,int si_private)
{
	memset(&timr->sigq->info, 0, sizeof(siginfo_t));
	timr->sigq->info.si_sys_private = si_private;
	/* Send signal to the process that owns this timer.*/

	timr->sigq->info.si_signo = timr->it_sigev_signo;
	timr->sigq->info.si_errno = 0;
	timr->sigq->info.si_code = SI_TIMER;
	timr->sigq->info.si_tid = timr->it_id;
	timr->sigq->info.si_value = timr->it_sigev_value;

	if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
		struct task_struct *leader;
		int ret = send_sigqueue(timr->it_sigev_signo, timr->sigq,
					timr->it_process);

		if (likely(ret >= 0))
			return ret;

		timr->it_sigev_notify = SIGEV_SIGNAL;
		leader = timr->it_process->group_leader;
		put_task_struct(timr->it_process);
		timr->it_process = leader;
	}

	return send_group_sigqueue(timr->it_sigev_signo, timr->sigq,
				   timr->it_process);
}
EXPORT_SYMBOL_GPL(posix_timer_event);

/*
 * This function gets called when a POSIX.1b interval timer expires.  It
 * is used as a callback from the kernel internal timer.  The
 * run_timer_list code ALWAYS calls with interrupts on.

 * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers.
 */
static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
{
	struct k_itimer *timr;
	unsigned long flags;
	int si_private = 0;
	enum hrtimer_restart ret = HRTIMER_NORESTART;

	timr = container_of(timer, struct k_itimer, it.real.timer);
	spin_lock_irqsave(&timr->it_lock, flags);

	if (timr->it.real.interval.tv64 != 0)
		si_private = ++timr->it_requeue_pending;

	if (posix_timer_event(timr, si_private)) {
		/*
		 * signal was not sent because of sig_ignor
		 * we will not get a call back to restart it AND
		 * it should be restarted.
		 */
		if (timr->it.real.interval.tv64 != 0) {
			ktime_t now = hrtimer_cb_get_time(timer);

			/*
			 * FIXME: What we really want, is to stop this
			 * timer completely and restart it in case the
			 * SIG_IGN is removed. This is a non trivial
			 * change which involves sighand locking
			 * (sigh !), which we don't want to do late in
			 * the release cycle.
			 *
			 * For now we just let timers with an interval
			 * less than a jiffie expire every jiffie to
			 * avoid softirq starvation in case of SIG_IGN
			 * and a very small interval, which would put
			 * the timer right back on the softirq pending
			 * list. By moving now ahead of time we trick
			 * hrtimer_forward() to expire the timer
			 * later, while we still maintain the overrun
			 * accuracy, but have some inconsistency in
			 * the timer_gettime() case. This is at least
			 * better than a starved softirq. A more
			 * complex fix which solves also another related
			 * inconsistency is already in the pipeline.
			 */
#ifdef CONFIG_HIGH_RES_TIMERS
			{
				ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ);

				if (timr->it.real.interval.tv64 < kj.tv64)
					now = ktime_add(now, kj);
			}
#endif
			timr->it_overrun +=
				hrtimer_forward(timer, now,
						timr->it.real.interval);
			ret = HRTIMER_RESTART;
			++timr->it_requeue_pending;
		}
	}

	unlock_timer(timr, flags);
	return ret;
}

static struct task_struct * good_sigevent(sigevent_t * event)
{
	struct task_struct *rtn = current->group_leader;

	if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
		(!(rtn = find_task_by_pid(event->sigev_notify_thread_id)) ||
		 rtn->tgid != current->tgid ||
		 (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
		return NULL;

	if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
	    ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
		return NULL;

	return rtn;
}

void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
{
	if ((unsigned) clock_id >= MAX_CLOCKS) {
		printk("POSIX clock register failed for clock_id %d\n",
		       clock_id);
		return;
	}

	posix_clocks[clock_id] = *new_clock;
}
EXPORT_SYMBOL_GPL(register_posix_clock);

static struct k_itimer * alloc_posix_timer(void)
{
	struct k_itimer *tmr;
	tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
	if (!tmr)
		return tmr;
	if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
		kmem_cache_free(posix_timers_cache, tmr);
		tmr = NULL;
	}
	return tmr;
}

#define IT_ID_SET	1
#define IT_ID_NOT_SET	0
static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
{
	if (it_id_set) {
		unsigned long flags;
		spin_lock_irqsave(&idr_lock, flags);
		idr_remove(&posix_timers_id, tmr->it_id);
		spin_unlock_irqrestore(&idr_lock, flags);
	}
	sigqueue_free(tmr->sigq);
	if (unlikely(tmr->it_process) &&
	    tmr->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
		put_task_struct(tmr->it_process);
	kmem_cache_free(posix_timers_cache, tmr);
}

/* Create a POSIX.1b interval timer. */

asmlinkage long
sys_timer_create(const clockid_t which_clock,
		 struct sigevent __user *timer_event_spec,
		 timer_t __user * created_timer_id)
{
	int error = 0;
	struct k_itimer *new_timer = NULL;
	int new_timer_id;
	struct task_struct *process = NULL;
	unsigned long flags;
	sigevent_t event;
	int it_id_set = IT_ID_NOT_SET;

	if (invalid_clockid(which_clock))
		return -EINVAL;

	new_timer = alloc_posix_timer();
	if (unlikely(!new_timer))
		return -EAGAIN;

	spin_lock_init(&new_timer->it_lock);
 retry:
	if (unlikely(!idr_pre_get(&posix_timers_id, GFP_KERNEL))) {
		error = -EAGAIN;
		goto out;
	}
	spin_lock_irq(&idr_lock);
	error = idr_get_new(&posix_timers_id, (void *) new_timer,
			    &new_timer_id);
	spin_unlock_irq(&idr_lock);
	if (error == -EAGAIN)
		goto retry;
	else if (error) {
		/*
		 * Wierd looking, but we return EAGAIN if the IDR is
		 * full (proper POSIX return value for this)
		 */
		error = -EAGAIN;
		goto out;
	}

	it_id_set = IT_ID_SET;
	new_timer->it_id = (timer_t) new_timer_id;
	new_timer->it_clock = which_clock;
	new_timer->it_overrun = -1;
	error = CLOCK_DISPATCH(which_clock, timer_create, (new_timer));
	if (error)
		goto out;

	/*
	 * return the timer_id now.  The next step is hard to
	 * back out if there is an error.
	 */
	if (copy_to_user(created_timer_id,