linux内核线程migration_thread和kthreadd的创建

linux内核中两大重要的线程，migration_thread负责cpu的负载均衡(将进程从本地队列移动到目标cpu的队列)，kthreadd负责为kthread_create_list链表中的成员创建内核线程。

内核版本2.6.24中的引导部分，start_kernel()->rest_init():

点击(此处)折叠或打开

static void noinline __init_refok rest_init(void)
        __releases(kernel_lock)
{
        int pid;

        kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
        numa_default_policy();
        pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
        kthreadd_task = find_task_by_pid(pid);
……
}

以上依次创建了kernel_init线程和kthreadd线程，rest_init()是在禁用抢占(preempt_disable)的情况下运行，因此保证了kernel_init()运行时kthreadd_task 已经指向ktheadd线程。

kernel_init（）调用do_pre_smp_initcalls()->migration_init();创建了负责将进程在cpu间移动(cpu负载均衡)的内核线程migration_thread(每个cpu一个)，创建线程是通过将包含待运行函数及参数的kthread_create_info结构挂入kthread_create_list链表，然后唤醒kthreadd_task(即ktheadd线程)，而ktheadd线程负责为链表上的每个结构创建相应的线程。

点击(此处)折叠或打开

void __init migration_init(void)
{
        void *cpu = (void *)(long)smp_processor_id();
        int err;

        /* Start one for the boot CPU: */
        err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
        BUG_ON(err == NOTIFY_BAD);
    migration_call(&migration_notifier, CPU_ONLINE, cpu);
    register_cpu_notifier(&migration_notifier);
}

首先直接调用migration_call两次创建了引导cpu的migration_thread线程并唤醒，然后调用register_cpu_notifier()将migration_notifier挂入cpu_chain链表，在之后kernel_init()->smp_init()中将依次对其余未上线的cpu调用cpu_up()->_cpu_up(),该函数分别以参数CPU_UP_PREPARE和CPU_ONLINE调用两次__raw_notifier_call_chain(),实则是运行cpu_chain链表上的函数，也包括了migration_call(),因此其余cpu的migration_thread也得以创建，最终是每个cpu上都有一个migration_thread线程。

点击(此处)折叠或打开

static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
{
    int ret, nr_calls = 0;
    void *hcpu = (void *)(long)cpu;
    unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;

    if (cpu_online(cpu) || !cpu_present(cpu))
        return -EINVAL;

    raw_notifier_call_chain(&cpu_chain, CPU_LOCK_ACQUIRE, hcpu);
    ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE | mod, hcpu,
                            -1, &nr_calls);
……
/* Now call notifier in preparation. */
    raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
……
}

/*

1、以CPU_UP_PREPARE为参数调用时，创建migration_thread线程，并绑定到cpu，设置调用策略为实时进程SCHED_FIFO，

优先级99,cpu运行队列的migration_thread指向该内核线程，此时线程是不可中断睡眠状态。

2、以CPU_ONLINE为参数调用时，唤醒cpu_rq(cpu)->migration_thread指向的migration_thread线程。

*/

点击(此处)折叠或打开

static int __cpuinit
migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
        struct task_struct *p;
        int cpu = (long)hcpu;
        unsigned long flags;
        struct rq *rq;

        switch (action) {
        case CPU_LOCK_ACQUIRE:
                mutex_lock(&sched_hotcpu_mutex);
                break;

        case CPU_UP_PREPARE:
            case CPU_UP_PREPARE_FROZEN:
        p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
        if (IS_ERR(p))
            return NOTIFY_BAD;
        kthread_bind(p, cpu);
        /* Must be high prio: stop_machine expects to yield to it. */
        rq = task_rq_lock(p, &flags);
        __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
        task_rq_unlock(rq, &flags);
        cpu_rq(cpu)->migration_thread = p;
        break;

    case CPU_ONLINE:
    case CPU_ONLINE_FROZEN:
        /* Strictly unnecessary, as first user will wake it. */
        wake_up_process(cpu_rq(cpu)->migration_thread);
        break;
……
}

/*创建线程是通过将包含线程运行函数和参数的kthread_create_info结构挂入kthread_create_list链表，

并唤醒内核线程kthreadd_task对链表上的各个线程创建需求进行处理来实现的，当创建成功后返回进程指针，

这是通过wait_for_completion(&create.done)进行同步的。此内核线程创建函数不负责将线程绑定到cpu,绑定工作

须由调用函数负责。

*/

点击(此处)折叠或打开

struct task_struct *kthread_create(int (*threadfn)(void *data),
                                   void *data,
                                   const char namefmt[],
                                   ...)
{
        struct kthread_create_info create;

        create.threadfn = threadfn;
        create.data = data;
        init_completion(&create.started);
        init_completion(&create.done);

        spin_lock(&kthread_create_lock);
        list_add_tail(&create.list, &kthread_create_list);
        wake_up_process(kthreadd_task);
        spin_unlock(&kthread_create_lock);

    wait_for_completion(&create.done);
……
        return create.result;
}