linux内核情景分析之强制性调度

从系统调用返回到用户空间是否调度,从ret_with_reschedule可看出,是否真正调度,取决于当前进程的pcb中的need_resched是否设置为1,那如何设置为1取决于以下几种情况:

时间中断处理程序,发现当前进程运行时间过长:每次发生时间中断,都要递减该进程的时间片,一旦count为0,强制调度,剥夺当前进程运行

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);//统计信息而已
	if (p->pid) {
		if (--p->counter <= 0) {
			p->counter = 0;
			p->need_resched = 1;//强制调度
		}
		if (p->nice > 0)
			kstat.per_cpu_nice[cpu] += user_tick;
		else
			kstat.per_cpu_user[cpu] += user_tick;
		kstat.per_cpu_system[cpu] += system;
	} else if (local_bh_count(cpu) || local_irq_count(cpu) > 1)
		kstat.per_cpu_system[cpu] += system;
}

 如果此时在用户态发生中断，进入内核态，p->counter减为0，那么p->need_resched就置为1，中断返回时就会强制调度。

如果此时发生系统调用，进入内核态，再发生中断，p->counter减为0，那么p->need_resched就置为1，中断返回后，然后系统调用返回时就会强制调度。

如果此时在用户态发生异常，进入内核态，再发生中断，p->counter减为0，那么p->need_resched就置为1，中断返回后，然后异常返回时就会强制调度。

第二种情况

唤醒一个睡眠进程,发现被唤醒的进程比当前进程权值高,need_sched设置为1

/*
 * Wake up a process. Put it on the run-queue if it's not
 * already there.  The "current" process is always on the
 * run-queue (except when the actual re-schedule is in
 * progress), and as such you're allowed to do the simpler
 * "current->state = TASK_RUNNING" to mark yourself runnable
 * without the overhead of this.
 */
inline void wake_up_process(struct task_struct * p)
{
	unsigned long flags;

	/*
	 * We want the common case fall through straight, thus the goto.
	 */
	spin_lock_irqsave(&runqueue_lock, flags);
	p->state = TASK_RUNNING;//设置为可执行状态
	if (task_on_runqueue(p))//如果已经到run队列
		goto out;
	add_to_runqueue(p);//加入run队列
	reschedule_idle(p);//将唤醒进程与当前进程比较,如果唤醒进程比当前进程权值高,那就把当前进程的need_resched设置为1
out:
	spin_unlock_irqrestore(&runqueue_lock, flags);
}

static void reschedule_idle(struct task_struct * p)
{
        ......
	int this_cpu = smp_processor_id();
	struct task_struct *tsk;

	tsk = cpu_curr(this_cpu);//获取当前进程的task_struct数据结构
	if (preemption_goodness(tsk, p, this_cpu) > 1)//比较当前进程和被唤醒的进程的综合权值
		tsk->need_resched = 1;//如果被唤醒的进程的综合权值比当前进程的大，那么强制调度

}

对于第三种情况，实际上应被视为自愿的让出。但是，从内核代码的形式上看，也是通过相同的办法，将当前进程的need_resched标志置为1，使得在进程返回用户空间前夕发生调度，所以也放在这一节。此类系统调用有两个，一个是sched_setscheduler()，另一个是sched_yield()。

系统调用sched_setscheduler()的作用是改变进程的调度政策。用户登录到系统后，第一个进程的适用调度政策为SCHED_OTHER，也就是默认为无实时要求的交互式应用。在fork()创建新进程时则将此进程适用的调度政策遗传给了子进程。但是，用户可以通过系统调用sched_setscheduler()改变其适用调度政策。

sched_setscheduler，内核态对应的代码如下：

asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, 
				      struct sched_param *param)
{
	return setscheduler(pid, policy, param);
}

asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param *param)
{
	return setscheduler(pid, -1, param);
}

static int setscheduler(pid_t pid, int policy, 
			struct sched_param *param)
{
	struct sched_param lp;
	struct task_struct *p;
	int retval;

	retval = -EINVAL;
	if (!param || pid < 0)
		goto out_nounlock;

	retval = -EFAULT;
	if (copy_from_user(&lp, param, sizeof(struct sched_param)))//从用户空间把sched_param结构拷贝到lp
		goto out_nounlock;

	/*
	 * We play safe to avoid deadlocks.
	 */
	read_lock_irq(&tasklist_lock);
	spin_lock(&runqueue_lock);

	p = find_process_by_pid(pid);//通过pid找到task_struct

	retval = -ESRCH;
	if (!p)
		goto out_unlock;
			
	if (policy < 0)//policy为-1
		policy = p->policy;//维持原来的政策
	else {
		retval = -EINVAL;
		if (policy != SCHED_FIFO && policy != SCHED_RR &&
				policy != SCHED_OTHER)//必须是这三种政策之一
			goto out_unlock;
	}
	
	/*
	 * Valid priorities for SCHED_FIFO and SCHED_RR are 1..99, valid
	 * priority for SCHED_OTHER is 0.
	 */
	retval = -EINVAL;
	if (lp.sched_priority < 0 || lp.sched_priority > 99)//实时进程的priority必须处于0-99
		goto out_unlock;
	if ((policy == SCHED_OTHER) != (lp.sched_priority == 0))//如果政策是SCHED_OTHER，sched_priority必须是0
		goto out_unlock;

	retval = -EPERM;
	if ((policy == SCHED_FIFO || policy == SCHED_RR) && 
	    !capable(CAP_SYS_NICE))
		goto out_unlock;
	if ((current->euid != p->euid) && (current->euid != p->uid) &&
	    !capable(CAP_SYS_NICE))
		goto out_unlock;

	retval = 0;
	p->policy = policy;
	p->rt_priority = lp.sched_priority;
	if (task_on_runqueue(p))
		move_first_runqueue(p);//从可执行进程队列的当前位置移到队列的前部，使其在调度时处于较为有利的地位

	current->need_resched = 1;//强制调度

out_unlock:
	spin_unlock(&runqueue_lock);
	read_unlock_irq(&tasklist_lock);

out_nounlock:
	return retval;
}

  另一个系统调用sched_yield()，使运行中的进程可以为其他进程"让路"，但并不进入睡眠。内核的实现sys_sched_yield，代码如下：

asmlinkage long sys_sched_yield(void)
{
	/*
	 * Trick. sched_yield() first counts the number of truly 
	 * 'pending' runnable processes, then returns if it's
	 * only the current processes. (This test does not have
	 * to be atomic.) In threaded applications this optimization
	 * gets triggered quite often.
	 */

	int nr_pending = nr_running;

#if CONFIG_SMP
	int i;

	// Substract non-idle processes running on other CPUs.
	for (i = 0; i < smp_num_cpus; i++)
		if (aligned_data[i].schedule_data.curr != idle_task(i))
			nr_pending--;
#else
	// on UP this process is on the runqueue as well
	nr_pending--;
#endif
	if (nr_pending) {//正在等待的运行的进程数
		/*
		 * This process can only be rescheduled by us,
		 * so this is safe without any locking.
		 */
		if (current->policy == SCHED_OTHER)//当前进程调度策略为sched_other
			current->policy |= SCHED_YIELD;//SCHED_YIELD标志位置1，在_schedule_tail清0
		current->need_resched = 1;//强制调度
	}
	return 0;
}

来自为知笔记(Wiz)