schedule()函数分析：
/*
* '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))
/*
* 如果采用轮转法调度，则重新检查counter是否为0, 若是则将其挂到运行队列的最后
*/
if (!prev->counter) {
prev->counter = NICE_TO_TICKS(prev->nice);
move_last_runqueue(prev);
}
switch (prev->state) {
case TASK_INTERRUPTIBLE:
/*
* 如果是TASK_INTERRUPTIBLE,并且能够唤醒它的信号已经来临,
* 则将状态置为TASK_RUNNING
*/
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) {
/*
* 遍历运行队列,查找优先级最高的进程, 优先级最高的进程将获得CPU
*/
p = list_entry(tmp, struct task_struct, run_list);
if (can_schedule(p, this_cpu)) {
/*
* goodness()中，如果是实时进程，则weight = 1000 + p->rt_priority,
* 使实时进程的优先级永远比非实时进程高
*/
int weight = goodness(p, this_cpu, prev->active_mm);
if (weight > c) //注意这里是”>”而不是”>=”，如果权值相同，则先来的先上
c = weight, next = p;
}
}
/* Do we need to re-calculate counters? */
if (unlikely(!c)) {
/*
* 如果当前优先级为0,那么整个运行队列中的进程将重新计算优先权
*/
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);
read_unlock(&tasklist_lock);
spin_lock_irq(&runqueue_lock);
goto repeat_schedule;
}
/*
* 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;
}
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) { //如果是内核线程的切换，则不做页表处理
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); //如果是用户进程，切换页表
}
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;
}
