#define SM_NONE            0x0  // 主动调度
#define SM_PREEMPT        0x1
#define SM_RTLOCK_WAIT        0x2

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

    cpu = smp_processor_id();
    rq = cpu_rq(cpu); // 找到当前CPU的运行队列
    prev = rq->curr; // 记录要切换出去的任务

    schedule_debug(prev, !!sched_mode);

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

    local_irq_disable();
    rcu_note_context_switch(!!sched_mode);

    rq_lock(rq, &rf);
    smp_mb__after_spinlock();

    /* Promote REQ to ACT */
    rq->clock_update_flags <<= 1;
    update_rq_clock(rq);

    switch_count = &prev->nivcsw; // Context involuntary switch counter，此任务上下文非主动切换计数

    prev_state = READ_ONCE(prev->__state);
    if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) { // 主动调度，并且要切换出去的任务不是运行态（非运行态prev_state是非零，通常主调度之前会提前设置当前进程的
　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　//　运行状态为 TASK_INTERRUPTIBLE 或者 TASK_UNINTERRUPTIBLE）
        if (signal_pending_state(prev_state, prev)) {
            WRITE_ONCE(prev->__state, TASK_RUNNING);
        } else {
            prev->sched_contributes_to_load =
                (prev_state & TASK_UNINTERRUPTIBLE) &&
                !(prev_state & TASK_NOLOAD) &&
                !(prev->flags & PF_FROZEN);

            if (prev->sched_contributes_to_load)
                rq->nr_uninterruptible++;

            deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); // 设置 prev->on_rq 为0，表示此任务不在运行队列里；并把此任务从运行队列移除

            if (prev->in_iowait) {
                atomic_inc(&rq->nr_iowait);
                delayacct_blkio_start();
            }
        }
        switch_count = &prev->nvcsw; // Context voluntary switch counter，此任务上下文主动切换计数
    } // 抢占调度，要切换的任务还是在运行队列

    next = pick_next_task(rq, prev, &rf); // 根据prev任务的调度类选一个最高优先级的任务返回
    clear_tsk_need_resched(prev); // 清楚prev任务的 TIF_NEED_RESCHED 的标记
    clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
    rq->last_seen_need_resched_ns = 0;
#endif

    if (likely(prev != next)) {
        rq->nr_switches++; // 队列内的任务切换次数统计

        RCU_INIT_POINTER(rq->curr, next);

        ++*switch_count; // 任务上下文切换统计

        migrate_disable_switch(rq, prev);
        psi_sched_switch(prev, next, !task_on_rq_queued(prev));

        trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);

        /* Also unlocks the rq: */
        rq = context_switch(rq, prev, next, &rf);
    } else {
        rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);

        rq_unpin_lock(rq, &rf);
        __balance_callbacks(rq);
        raw_spin_rq_unlock_irq(rq);
    }
}

/*
 * context_switch - switch to the new MM and the new thread's register state.
 */
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
           struct task_struct *next, struct rq_flags *rf)
{
    prepare_task_switch(rq, prev, next);

    /*
     * For paravirt, this is coupled with an exit in switch_to to
     * combine the page table reload and the switch backend into
     * one hypercall.
     */
    arch_start_context_switch(prev);

    /*
     * kernel -> kernel   lazy + transfer active
     *   user -> kernel   lazy + mmgrab() active
     *
     * kernel ->   user   switch + mmdrop() active
     *   user ->   user   switch
     */
    if (!next->mm) {                                // 切换到内核线程
        enter_lazy_tlb(prev->active_mm, next);

        next->active_mm = prev->active_mm; // 指向要被切换出去线程的内存描述符
        if (prev->mm)                           // 被切换出去线程属于用户线程
            mmgrab(prev->active_mm); // 由于被切换出去线程的内存描述符被要运行的内核线程使用，内存描述符的引用计数加一
        else
            prev->active_mm = NULL; // 被切换出去线程属于内核线程，其内存描述符指向NULL
    } else {                                        // 切换到用户线程
        membarrier_switch_mm(rq, prev->active_mm, next->mm);
        /*
         * sys_membarrier() requires an smp_mb() between setting
         * rq->curr / membarrier_switch_mm() and returning to userspace.
         *
         * The below provides this either through switch_mm(), or in
         * case 'prev->active_mm == next->mm' through
         * finish_task_switch()'s mmdrop().
         */
        switch_mm_irqs_off(prev->active_mm, next->mm, next); // 设置 MMU 的页表首地址为准备运行的用户线程的页表首地址

        if (!prev->mm) {                        // from kernel
            /* will mmdrop() in finish_task_switch(). */
            rq->prev_mm = prev->active_mm;
            prev->active_mm = NULL;
        }
    }

    rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);

    prepare_lock_switch(rq, next, rf);

    /* Here we just switch the register state and the stack. */
    switch_to(prev, next, prev); // 切换CPU寄存器
    barrier();

    return finish_task_switch(prev);
}