schedule()函数篇

     内核中schedule()函数用来实现进程的调度（kenel/sched.c中）。函数代码以及注释如下：

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
	struct task_struct *prev, *next;
	unsigned long *switch_count;
	struct rq *rq;
	int cpu;

need_resched:
	preempt_disable();    //禁止内核抢占
	cpu = smp_processor_id(); //获取当前CPU
	rq = cpu_rq(cpu);    //获取该CPU维护的运行队列（run queue)
	rcu_note_context_switch(cpu);  //更新全局状态，标识当前CPU发生上下文的切换。
	prev = rq->curr;    //运行队列中的curr指针赋予prev。

	schedule_debug(prev); 

	if (sched_feat(HRTICK))
		hrtick_clear(rq);

	raw_spin_lock_irq(&rq->lock); //锁住该队列

	switch_count = &prev->nivcsw;  //记录当前进程的切换次数
	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {     //是否同时满足以下条件：1该进程处于停止状态，2该进程没有在内核态被抢占。
		if (unlikely(signal_pending_state(prev->state, prev))) {  //若不是非挂起信号，则将该进程状态设置成TASK_RUNNING
			prev->state = TASK_RUNNING;
		} else {   //若为非挂起信号则将其从队列中移出
			/*
			 * If a worker is going to sleep, notify and
			 * ask workqueue whether it wants to wake up a
			 * task to maintain concurrency.  If so, wake
			 * up the task.
			 */
			if (prev->flags & PF_WQ_WORKER) {     
				struct task_struct *to_wakeup;

				to_wakeup = wq_worker_sleeping(prev, cpu);
				if (to_wakeup)
					try_to_wake_up_local(to_wakeup);
			}
			deactivate_task(rq, prev, DEQUEUE_SLEEP);  //从运行队列中移出

			/*
			 * If we are going to sleep and we have plugged IO queued, make
			 * sure to submit it to avoid deadlocks.
			 */
			if (blk_needs_flush_plug(prev)) {
				raw_spin_unlock(&rq->lock);
				blk_schedule_flush_plug(prev);
				raw_spin_lock(&rq->lock);
			}
		}
		switch_count = &prev->nvcsw;  //切换次数记录
	}

	pre_schedule(rq, prev); 

	if (unlikely(!rq->nr_running))
		idle_balance(cpu, rq);

	put_prev_task(rq, prev);  
	next = pick_next_task(rq);  //挑选一个优先级最高的任务将其排进队列。
	clear_tsk_need_resched(prev); //清除pre的TIF_NEED_RESCHED标志。
	rq->skip_clock_update = 0;

	if (likely(prev != next)) { //如果prev和next非同一个进程
		rq->nr_switches++;  //队列切换次数更新
		rq->curr = next;
		++*switch_count;  //进程切换次数更新

		context_switch(rq, prev, next); /* unlocks the rq */   //进程之间上下文切换
		/*
		 * The context switch have flipped the stack from under us
		 * and restored the local variables which were saved when
		 * this task called schedule() in the past. prev == current
		 * is still correct, but it can be moved to another cpu/rq.
		 */
		cpu = smp_processor_id();
		rq = cpu_rq(cpu);
	} else   //如果prev和next为同一进程，则不进行进程切换。
		raw_spin_unlock_irq(&rq->lock);  

	post_schedule(rq);

	preempt_enable_no_resched();
	if (need_resched())  //如果该进程被其他进程设置了TIF_NEED_RESCHED标志，则函数重新执行进行调度
		goto need_resched;
}

注：以上内核代码版本为2.6.39。