sched.c

如果您在研究linux内核

{
#ifdef CONFIG_SMP
	int policy;

	/*
	 * prev->policy can be written from here only before `prev'
	 * can be scheduled (before setting prev->cpus_runnable to ~0UL).
	 * Of course it must also be read before allowing prev
	 * to be rescheduled, but since the write depends on the read
	 * to complete, wmb() is enough. (the spin_lock() acquired
	 * before setting cpus_runnable is not enough because the spin_lock()
	 * common code semantics allows code outside the critical section
	 * to enter inside the critical section)
	 */
	policy = prev->policy;
	prev->policy = policy & ~SCHED_YIELD;
	wmb();

	/*
	 * fast path falls through. We have to clear cpus_runnable before
	 * checking prev->state to avoid a wakeup race. Protect against
	 * the task exiting early.
	 */
	task_lock(prev);
	task_release_cpu(prev);
	mb();
	if (prev->state == TASK_RUNNING)
		goto needs_resched;

out_unlock:
	task_unlock(prev);	/* Synchronise here with release_task() if prev is TASK_ZOMBIE */
	return;

	/*
	 * Slow path - we 'push' the previous process and
	 * reschedule_idle() will attempt to find a new
	 * processor for it. (but it might preempt the
	 * current process as well.) We must take the runqueue
	 * lock and re-check prev->state to be correct. It might
	 * still happen that this process has a preemption
	 * 'in progress' already - but this is not a problem and
	 * might happen in other circumstances as well.
	 */
needs_resched:
	{
		unsigned long flags;

		/*
		 * Avoid taking the runqueue lock in cases where
		 * no preemption-check is necessery:
		 */
		if ((prev == idle_task(smp_processor_id())) ||
						(policy & SCHED_YIELD))
			goto out_unlock;

		spin_lock_irqsave(&runqueue_lock, flags);
		if ((prev->state == TASK_RUNNING) && !task_has_cpu(prev))
			reschedule_idle(prev);
		spin_unlock_irqrestore(&runqueue_lock, flags);
		goto out_unlock;
	}
#else
	prev->policy &= ~SCHED_YIELD;
#endif /* CONFIG_SMP */
}

asmlinkage void schedule_tail(struct task_struct *prev)
{
	__schedule_tail(prev);
}

/*
 *  'schedule()' is the scheduler function. It's a very simple and nice
 * scheduler: it's not perfect, but certainly works for most things.
 *
 * The goto is "interesting".
 *
 *   NOTE!!  Task 0 is the 'idle' task, which gets called when no other
 * tasks can run. It can not be killed, and it cannot sleep. The 'state'
 * information in task[0] is never used.
 */
asmlinkage void schedule(void)
{
	struct schedule_data * sched_data;
	struct task_struct *prev, *next, *p;
	struct list_head *tmp;
	int this_cpu, c;


	spin_lock_prefetch(&runqueue_lock);

	if (!current->active_mm) BUG();
need_resched_back:
	prev = current;
	this_cpu = prev->processor;

	if (unlikely(in_interrupt())) {
		printk("Scheduling in interrupt\n");
		BUG();
	}

	release_kernel_lock(prev, this_cpu);

	/*
	 * 'sched_data' is protected by the fact that we can run
	 * only one process per CPU.
	 */
	sched_data = & aligned_data[this_cpu].schedule_data;

	spin_lock_irq(&runqueue_lock);

	/* move an exhausted RR process to be last.. */
	if (unlikely(prev->policy == SCHED_RR))
		if (!prev->counter) {
			prev->counter = NICE_TO_TICKS(prev->nice);
			move_last_runqueue(prev);
		}

	switch (prev->state) {
		case TASK_INTERRUPTIBLE:
			if (signal_pending(prev)) {
				prev->state = TASK_RUNNING;
				break;
			}
		default:
			del_from_runqueue(prev);
		case TASK_RUNNING:;
	}
	prev->need_resched = 0;

	/*
	 * this is the scheduler proper:
	 */

repeat_schedule:
	/*
	 * Default process to select..
	 */
	next = idle_task(this_cpu);
	c = -1000;
	list_for_each(tmp, &runqueue_head) {
		p = list_entry(tmp, struct task_struct, run_list);
		if (can_schedule(p, this_cpu)) {
			int weight = goodness(p, this_cpu, prev->active_mm);
			if (weight > c)
				c = weight, next = p;
		}
	}

	/* Do we need to re-calculate counters? */
	if (unlikely(!c)) {
		struct task_struct *p;

		spin_unlock_irq(&runqueue_lock);
/*
		read_lock(&tasklist_lock);
		for_each_task(p)
			p->counter = (p->counter >> 1) + NICE_TO_TICKS(p->nice);
*/



                if (fairsched) {
 			struct user_struct *up;
 			long oldcounter;
 			if (!spin_trylock(&recalc_lock)) {
				spin_lock_irq(&runqueue_lock);
 				goto skipped_recalculate;
 			}
 			read_lock(&uidhash_lock);
 			for_each_user_struct(up)
 				up->move_task = NULL;
 
 			write_lock(&tasklist_lock);
 			for_each_task(p) {
 			    up = p->user;
 			    if (!up) {
 		 		p->counter = (p->counter >> 1) + NICE_TO_TICKS(p->nice);
 			 	continue;
 			    }
 			    if (!up->cpu_ticks)
 				continue;
 			    /* never dirty a cacheline needlessly */
 			    if (p->counter >> 1 != NICE_TO_TICKS(p->nice)) {
 					oldcounter = p->counter;
 					p->counter = (p->counter >> 1) + NICE_TO_TICKS(p->nice);
 					up->cpu_ticks += oldcounter;
 					up->cpu_ticks -= p->counter;
 			    	if (!up->move_task)
 					   up->move_task = p;
 					if (up->cpu_ticks < 0)
 					   up->cpu_ticks = 0;
 			    }
 			}
 
 			for_each_user_struct(up) {
 			    if (!up->cpu_ticks) {
 			    	move_task_last(up);
 			    }
 			    up->cpu_ticks = (up->cpu_ticks >> 1) + DEF_COUNTER;
 			}
 			write_unlock(&tasklist_lock);
 			read_unlock(&uidhash_lock);
 			spin_unlock(&recalc_lock);
		} else
#endif /* CONFIG_FAIRSCHED */
 		{
 		    read_lock(&tasklist_lock);
 		    for_each_task(p) {
 			/* never dirty a cache line needlessly */
 			if (p->counter >> 1 != NICE_TO_TICKS(p->nice))
 				p->counter = (p->counter >> 1) + NICE_TO_TICKS(p->nice);
 		    }

		    read_unlock(&tasklist_lock);
                }
		spin_lock_irq(&runqueue_lock);
		goto repeat_schedule;
	}
        skipped_recalculate:

	/*
	 * from this point on nothing can prevent us from
	 * switching to the next task, save this fact in
	 * sched_data.
	 */
	sched_data->curr = next;
	task_set_cpu(next, this_cpu);
	spin_unlock_irq(&runqueue_lock);

	if (unlikely(prev == next)) {
		/* We won't go through the normal tail, so do this by hand */
		prev->policy &= ~SCHED_YIELD;
		goto same_process;
	}

#ifdef CONFIG_SMP
 	/*
 	 * maintain the per-process 'last schedule' value.
 	 * (this has to be recalculated even if we reschedule to
 	 * the same process) Currently this is only used on SMP,
	 * and it's approximate, so we do not have to maintain
	 * it while holding the runqueue spinlock.
 	 */
 	sched_data->last_schedule = get_cycles();

	/*
	 * We drop the scheduler lock early (it's a global spinlock),
	 * thus we have to lock the previous process from getting
	 * rescheduled during switch_to().
	 */

#endif /* CONFIG_SMP */

	kstat.context_swtch++;
	/*
	 * there are 3 processes which are affected by a context switch:
	 *
	 * prev == .... ==> (last => next)
	 *
	 * It's the 'much more previous' 'prev' that is on next's stack,
	 * but prev is set to (the just run) 'last' process by switch_to().
	 * This might sound slightly confusing but makes tons of sense.
	 */
	prepare_to_switch();
	{
		struct mm_struct *mm = next->mm;
		struct mm_struct *oldmm = prev->active_mm;
		if (!mm) {
			if (next->active_mm) BUG();
			next->active_mm = oldmm;
			atomic_inc(&oldmm->mm_count);
			enter_lazy_tlb(oldmm, next, this_cpu);
		} else {
			if (next->active_mm != mm) BUG();
			switch_mm(oldmm, mm, next, this_cpu);
		}

		if (!prev->mm) {
			prev->active_mm = NULL;
			mmdrop(oldmm);
		}
	}

	/*
	 * This just switches the register state and the
	 * stack.
	 */
	switch_to(prev, next, prev);
	__schedule_tail(prev);

same_process:
	reacquire_kernel_lock(current);
	if (current->need_resched)
		goto need_resched_back;
	return;
}

/*
 * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just wake everything
 * up.  If it's an exclusive wakeup (nr_exclusive == small +ve number) then we wake all the
 * non-exclusive tasks and one exclusive task.
 *
 * There are circumstances in which we can try to wake a task which has already
 * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns zero
 * in this (rare) case, and we handle it by contonuing to scan the queue.
 */
static inline void __wake_up_common (wait_queue_head_t *q, unsigned int mode,
			 	     int nr_exclusive, const int sync)
{
	struct list_head *tmp;
	struct task_struct *p;

	CHECK_MAGIC_WQHEAD(q);
	WQ_CHECK_LIST_HEAD(&q->task_list);
	
	list_for_each(tmp,&q->task_list) {
		unsigned int state;
                wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);

		CHECK_MAGIC(curr->__magic);
		p = curr->task;
		state = p->state;
		if (state & mode) {
			WQ_NOTE_WAKER(curr);
			if (try_to_wake_up(p, sync) && (curr->flags&WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
				break;
		}
	}
}

void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr)
{
	if (q) {
		unsigned long flags;
		wq_read_lock_irqsave(&q->lock, flags);
		__wake_up_common(q, mode, nr, 0);
		wq_read_unlock_irqrestore(&q->lock, flags);
	}
}

void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr)
{
	if (q) {
		unsigned long flags;
		wq_read_lock_irqsave(&q->lock, flags);
		__wake_up_common(q, mode, nr, 1);
		wq_read_unlock_irqrestore(&q->lock, flags);
	}
}

void complete(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done++;
	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1, 0);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}

void wait_for_completion(struct completion *x)
{
	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			__set_current_state(TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			schedule();
			spin_lock_irq(&x->wait.lock);
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
	spin_unlock_irq(&x->wait.lock);
}

#define	SLEEP_ON_VAR				\
	unsigned long flags;			\
	wait_queue_t wait;			\
	init_waitqueue_entry(&wait, current);

#define	SLEEP_ON_HEAD					\
	wq_write_lock_irqsave(&q->lock,flags);		\
	__add_wait_queue(q, &wait);			\
	wq_write_unlock(&q->lock);

#define	SLEEP_ON_TAIL						\
	wq_write_lock_irq(&q->lock);				\
	__remove_wait_queue(q, &wait);				\
	wq_write_unlock_irqrestore(&q->lock,flags);

void interruptible_sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

long interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

void sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR
	
	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

long sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	SLEEP_ON_VAR
	
	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

void scheduling_functions_end_here(void) { }

#ifndef __alpha__

/*
 * This has been replaced by sys_setpriority.  Maybe it should be
 * moved into the arch dependent tree for those ports that require
 * it for backward compatibility?
 */

asmlinkage long sys_nice(int increment)
{
	long newprio;

	/*
	 *	Setpriority might change our priority at the same moment.
	 *	We don't have to worry. Conceptually one call occurs first
	 *	and we have a single winner.
	 */
	if (increment < 0) {
		if (!capable(CAP_SYS_NICE))
			return -EPERM;
		if (increment < -40)
			increment = -40;
	}