static struct task_struct *pick_next_task_fair(struct rq *rq)
{
    struct task_struct *p;
    /*从CPU 的就绪队列找到公平调度队列*/
    struct cfs_rq *cfs_rq = &rq->cfs;
    struct sched_entity *se;
    /*如果公平调度类没有可运行的进程，直接返回*/
    if (!cfs_rq->nr_running)
        return NULL;
     /*如果调度的是一组进程，则需要进行循环设置，否则执行一次就退出了*/
    do {
        /*从公平调度类中找到一个可运行的实体*/
        se = pick_next_entity(cfs_rq);
        /*设置红黑树中下一个实体，并标记cfs_rq->curr为se*/
        set_next_entity(cfs_rq, se);
        cfs_rq = group_cfs_rq(se);
    } while (cfs_rq);
    /*获取到具体的task_struct*/
    p = task_of(se);
    if (hrtick_enabled(rq))
        hrtick_start_fair(rq, p);

    return p;
}

static void __sched __schedule(void)
{
    struct task_struct *prev, *next;
    unsigned long *switch_count;
    struct rq *rq;
    int cpu;

need_resched:
    /*禁止内核抢占*/
    preempt_disable();
    cpu = smp_processor_id();
    /*获取CPU 的调度队列*/
    rq = cpu_rq(cpu);
    rcu_note_context_switch(cpu);
    /*保存当前任务*/
    prev = rq->curr;

    schedule_debug(prev);

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

    /*
     * Make sure that signal_pending_state()->signal_pending() below
     * can‘t be reordered with __set_current_state(TASK_INTERRUPTIBLE)
     * done by the caller to avoid the race with signal_wake_up().
     */
    smp_mb__before_spinlock();
    raw_spin_lock_irq(&rq->lock);

    switch_count = &prev->nivcsw;
     /*  如果内核态没有被抢占, 并且内核抢占有效
        即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 (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
        if (unlikely(signal_pending_state(prev->state, prev))) {
            prev->state = TASK_RUNNING;
        } else {
            deactivate_task(rq, prev, DEQUEUE_SLEEP);
            prev->on_rq = 0;

            /*
             * If a worker went to sleep, notify and ask workqueue
             * whether it wants to wake up a task to maintain
             * concurrency.
             */
            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);
            }
        }
        switch_count = &prev->nvcsw;
    }

    pre_schedule(rq, prev);

    if (unlikely(!rq->nr_running))
        idle_balance(cpu, rq);
    /*告诉调度器prev进程即将被调度出去*/
    put_prev_task(rq, prev);
    /*挑选下一个可运行的进程*/
    next = pick_next_task(rq);
    /*清除pre的TIF_NEED_RESCHED标志*/
    clear_tsk_need_resched(prev);
    rq->skip_clock_update = 0;
   /*如果next和当前进程不一致，就可以调度*/
    if (likely(prev != next)) {
        rq->nr_switches++;
        /*设置当前调度进程为next*/
        rq->curr = next;
        ++*switch_count;
        /*切换进程上下文*/
        context_switch(rq, prev, next); /* unlocks the rq */
        /*
         * 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
        raw_spin_unlock_irq(&rq->lock);

    post_schedule(rq);
  
    sched_preempt_enable_no_resched();
    if (need_resched())
        goto need_resched;
}

static inline struct task_struct *
pick_next_task(struct rq *rq)
{
    const struct sched_class *class;
    struct task_struct *p;

    /*
     * Optimization: we know that if all tasks are in
     * the fair class we can call that function directly:
     */
     /*如果所有任务都处于完全公平调度类，则可以直接选择下一个任务*/
    if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
        p = fair_sched_class.pick_next_task(rq);
        if (likely(p))
            return p;
    }
    /*从优先级最高的调度器类开始遍历，顺序为stop_sched_class->rt_scheduled_class->fair_schedled_class->idle_sched_class*/
    /*
    #define for_each_class(class)    for (class = sched_class_highest; class; class = class->next)
    */
    for_each_class(class) {
        p = class->pick_next_task(rq);
        if (p)
            return p;
    }

    BUG(); /* the idle class will always have a runnable task */
}