timer.c

Linux2.4.20针对三星公司的s3c2410开发板的内核改造。

    /* Compensate for (HZ==100) != (1 << SHIFT_HZ).
     * Add 25% and 3.125% to get 128.125; => only 0.125% error (p. 14)
     */
    if (time_adj < 0)
	time_adj -= (-time_adj >> 2) + (-time_adj >> 5);
    else
	time_adj += (time_adj >> 2) + (time_adj >> 5);
#endif
}

/* in the NTP reference this is called "hardclock()" */
static void update_wall_time_one_tick(void)
{
	if ( (time_adjust_step = time_adjust) != 0 ) {
	    /* We are doing an adjtime thing. 
	     *
	     * Prepare time_adjust_step to be within bounds.
	     * Note that a positive time_adjust means we want the clock
	     * to run faster.
	     *
	     * Limit the amount of the step to be in the range
	     * -tickadj .. +tickadj
	     */
	     if (time_adjust > tickadj)
		time_adjust_step = tickadj;
	     else if (time_adjust < -tickadj)
		time_adjust_step = -tickadj;
	     
	    /* Reduce by this step the amount of time left  */
	    time_adjust -= time_adjust_step;
	}
	xtime.tv_usec += tick + time_adjust_step;
	/*
	 * Advance the phase, once it gets to one microsecond, then
	 * advance the tick more.
	 */
	time_phase += time_adj;
	if (time_phase <= -FINEUSEC) {
		long ltemp = -time_phase >> SHIFT_SCALE;
		time_phase += ltemp << SHIFT_SCALE;
		xtime.tv_usec -= ltemp;
	}
	else if (time_phase >= FINEUSEC) {
		long ltemp = time_phase >> SHIFT_SCALE;
		time_phase -= ltemp << SHIFT_SCALE;
		xtime.tv_usec += ltemp;
	}
}

/*
 * Using a loop looks inefficient, but "ticks" is
 * usually just one (we shouldn't be losing ticks,
 * we're doing this this way mainly for interrupt
 * latency reasons, not because we think we'll
 * have lots of lost timer ticks
 */
static void update_wall_time(unsigned long ticks)
{
	do {
		ticks--;
		update_wall_time_one_tick();
	} while (ticks);

	if (xtime.tv_usec >= 1000000) {
	    xtime.tv_usec -= 1000000;
	    xtime.tv_sec++;
	    second_overflow();
	}
}

static inline void do_process_times(struct task_struct *p,
	unsigned long user, unsigned long system)
{
	unsigned long psecs;

	psecs = (p->times.tms_utime += user);
	psecs += (p->times.tms_stime += system);
	if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_cur) {
		/* Send SIGXCPU every second.. */
		if (!(psecs % HZ))
			send_sig(SIGXCPU, p, 1);
		/* and SIGKILL when we go over max.. */
		if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_max)
			send_sig(SIGKILL, p, 1);
	}
}

static inline void do_it_virt(struct task_struct * p, unsigned long ticks)
{
	unsigned long it_virt = p->it_virt_value;

	if (it_virt) {
		it_virt -= ticks;
		if (!it_virt) {
			it_virt = p->it_virt_incr;
			send_sig(SIGVTALRM, p, 1);
		}
		p->it_virt_value = it_virt;
	}
}

static inline void do_it_prof(struct task_struct *p)
{
	unsigned long it_prof = p->it_prof_value;

	if (it_prof) {
		if (--it_prof == 0) {
			it_prof = p->it_prof_incr;
			send_sig(SIGPROF, p, 1);
		}
		p->it_prof_value = it_prof;
	}
}

void update_one_process(struct task_struct *p, unsigned long user,
			unsigned long system, int cpu)
{
	p->per_cpu_utime[cpu] += user;
	p->per_cpu_stime[cpu] += system;
	do_process_times(p, user, system);
	do_it_virt(p, user);
	do_it_prof(p);
}	

/*
 * Called from the timer interrupt handler to charge one tick to the current 
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
	struct task_struct *p = current;
	int cpu = smp_processor_id(), system = user_tick ^ 1;

	update_one_process(p, user_tick, system, cpu);
	scheduler_tick(user_tick, system);
}

/*
 * Nr of active tasks - counted in fixed-point numbers
 */
static unsigned long count_active_tasks(void)
{
	return (nr_running() + nr_uninterruptible()) * FIXED_1;
}

/*
 * Hmm.. Changed this, as the GNU make sources (load.c) seems to
 * imply that avenrun[] is the standard name for this kind of thing.
 * Nothing else seems to be standardized: the fractional size etc
 * all seem to differ on different machines.
 */
unsigned long avenrun[3];

static inline void calc_load(unsigned long ticks)
{
	unsigned long active_tasks; /* fixed-point */
	static int count = LOAD_FREQ;

	count -= ticks;
	if (count < 0) {
		count += LOAD_FREQ;
		active_tasks = count_active_tasks();
		CALC_LOAD(avenrun[0], EXP_1, active_tasks);
		CALC_LOAD(avenrun[1], EXP_5, active_tasks);
		CALC_LOAD(avenrun[2], EXP_15, active_tasks);
	}
}

/* jiffies at the most recent update of wall time */
unsigned long wall_jiffies;

/*
 * This spinlock protect us from races in SMP while playing with xtime. -arca
 */
rwlock_t xtime_lock = RW_LOCK_UNLOCKED;

static inline void update_times(void)
{
	unsigned long ticks;

	/*
	 * update_times() is run from the raw timer_bh handler so we
	 * just know that the irqs are locally enabled and so we don't
	 * need to save/restore the flags of the local CPU here. -arca
	 */
	write_lock_irq(&xtime_lock);
	vxtime_lock();

	ticks = jiffies - wall_jiffies;
	if (ticks) {
		wall_jiffies += ticks;
		update_wall_time(ticks);
	}
	vxtime_unlock();
	write_unlock_irq(&xtime_lock);
	calc_load(ticks);
}

void timer_bh(void)
{
	TRACE_EVENT(TRACE_EV_KERNEL_TIMER, NULL);
	update_times();
	run_timer_list();
}

void do_timer(struct pt_regs *regs)
{
	(*(unsigned long *)&jiffies)++;
#ifndef CONFIG_SMP
	/* SMP process accounting uses the local APIC timer */

	update_process_times(user_mode(regs));
#endif
	mark_bh(TIMER_BH);
	if (TQ_ACTIVE(tq_timer))
		mark_bh(TQUEUE_BH);
}

#if !defined(__alpha__) && !defined(__ia64__)

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
asmlinkage unsigned long sys_alarm(unsigned int seconds)
{
	struct itimerval it_new, it_old;
	unsigned int oldalarm;

	it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
	it_new.it_value.tv_sec = seconds;
	it_new.it_value.tv_usec = 0;
	do_setitimer(ITIMER_REAL, &it_new, &it_old);
	oldalarm = it_old.it_value.tv_sec;
	/* ehhh.. We can't return 0 if we have an alarm pending.. */
	/* And we'd better return too much than too little anyway */
	if (it_old.it_value.tv_usec)
		oldalarm++;
	return oldalarm;
}

#endif

#ifndef __alpha__

/*
 * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
 * should be moved into arch/i386 instead?
 */

/**
 * sys_getpid - return the thread group id of the current process
 *
 * Note, despite the name, this returns the tgid not the pid.  The tgid and
 * the pid are identical unless CLONE_THREAD was specified on clone() in
 * which case the tgid is the same in all threads of the same group.
 *
 * This is SMP safe as current->tgid does not change.
 */
asmlinkage long sys_getpid(void)
{
	return current->tgid;
}

/*
 * This is not strictly SMP safe: p_opptr could change
 * from under us. However, rather than getting any lock
 * we can use an optimistic algorithm: get the parent
 * pid, and go back and check that the parent is still
 * the same. If it has changed (which is extremely unlikely
 * indeed), we just try again..
 *
 * NOTE! This depends on the fact that even if we _do_
 * get an old value of "parent", we can happily dereference
 * the pointer: we just can't necessarily trust the result
 * until we know that the parent pointer is valid.
 *
 * The "mb()" macro is a memory barrier - a synchronizing
 * event. It also makes sure that gcc doesn't optimize
 * away the necessary memory references.. The barrier doesn't
 * have to have all that strong semantics: on x86 we don't
 * really require a synchronizing instruction, for example.
 * The barrier is more important for code generation than
 * for any real memory ordering semantics (even if there is
 * a small window for a race, using the old pointer is
 * harmless for a while).
 */
asmlinkage long sys_getppid(void)
{
	int pid;
	struct task_struct * me = current;
	struct task_struct * parent;

	parent = me->p_opptr;
	for (;;) {
		pid = parent->pid;
#if CONFIG_SMP
{
		struct task_struct *old = parent;
		mb();
		parent = me->p_opptr;
		if (old != parent)
			continue;
}
#endif
		break;
	}
	return pid;
}

asmlinkage long sys_getuid(void)
{
	/* Only we change this so SMP safe */
	return current->uid;
}

asmlinkage long sys_geteuid(void)
{
	/* Only we change this so SMP safe */
	return current->euid;
}

asmlinkage long sys_getgid(void)
{
	/* Only we change this so SMP safe */
	return current->gid;
}

asmlinkage long sys_getegid(void)
{
	/* Only we change this so SMP safe */
	return  current->egid;
}

#endif

static void process_timeout(unsigned long __data)
{
	TRACE_TIMER(TRACE_EV_TIMER_EXPIRED, 0, 0, 0);
	wake_up_process((task_t *)__data);
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns. The routine will return 0
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task. In this case the remaining time
 * in jiffies will be returned, or 0 if the timer expired in time
 *
 * The current task state is guaranteed to be TASK_RUNNING when this 
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * In all cases the return value is guaranteed to be non-negative.
 */
signed long schedule_timeout(signed long timeout)
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT:
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default:
		/*
		 * Another bit of PARANOID. Note that the retval will be
		 * 0 since no piece of kernel is supposed to do a check
		 * for a negative retval of schedule_timeout() (since it
		 * should never happens anyway). You just have the printk()
		 * that will tell you if something is gone wrong and where.
		 */
		if (timeout < 0)
		{
			printk(KERN_ERR "schedule_timeout: wrong timeout "
			       "value %lx from %p\n", timeout,
			       __builtin_return_address(0));
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	TRACE_TIMER(TRACE_EV_TIMER_SETTIMEOUT, 0, timeout, 0);

	expire = timeout + jiffies;

	init_timer(&timer);
	timer.expires = expire;
	timer.data = (unsigned long) current;
	timer.function = process_timeout;

	add_timer(&timer);
	schedule();
	del_timer_sync(&timer);

	timeout = expire - jiffies;

 out:
	return timeout < 0 ? 0 : timeout;
}

/* Thread ID - the internal kernel "pid" */
asmlinkage long sys_gettid(void)
{
	return current->pid;
}

asmlinkage long sys_nanosleep(struct timespec *rqtp, struct timespec *rmtp)
{
	struct timespec t;
	unsigned long expire;

	if(copy_from_user(&t, rqtp, sizeof(struct timespec)))
		return -EFAULT;

	if (t.tv_nsec >= 1000000000L || t.tv_nsec < 0 || t.tv_sec < 0)
		return -EINVAL;


	if (t.tv_sec == 0 && t.tv_nsec <= 2000000L &&
	    current->policy != SCHED_OTHER)
	{
		/*
		 * Short delay requests up to 2 ms will be handled with
		 * high precision by a busy wait for all real-time processes.
		 *
		 * Its important on SMP not to do this holding locks.
		 */
		udelay((t.tv_nsec + 999) / 1000);
		return 0;
	}

	expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);

	current->state = TASK_INTERRUPTIBLE;
	expire = schedule_timeout(expire);

	if (expire) {
		if (rmtp) {
			jiffies_to_timespec(expire, &t);
			if (copy_to_user(rmtp, &t, sizeof(struct timespec)))
				return -EFAULT;
		}
		return -EINTR;
	}
	return 0;
}