Linux数据报文接收发送总结4

二、系统初始化

 

Linux驱动，内核协议栈等等模块在具备接收网卡数据包之前，要做很多的准备工作才行。比如要提前创建好ksoftirqd内核线程，要注册好各个协议对应的处理函数，网络设备子系统要提前初始化好，网卡要启动好。只有这些都Ready之后，我们才能真正开始接收数据包。那么我们现在来看看这些准备工作都是怎么做的。

 

Linux的子系统、模块均定义了一定的启动级别，在start_kernel函数中，按顺序启动

/* initcalls are now grouped by functionality into separate 
 * subsections. Ordering inside the subsections is determined
 * by link order. 
 * For backwards compatibility, initcall() puts the call in 
 * the device init subsection.
 *
 * The `id' arg to __define_initcall() is needed so that multiple initcalls
 * can point at the same handler without causing duplicate-symbol build errors.
 */

#define __define_initcall(fn, id) \
	static initcall_t __initcall_##fn##id __used \
	__attribute__((__section__(".initcall" #id ".init"))) = fn; \
	LTO_REFERENCE_INITCALL(__initcall_##fn##id)

/*
 * Early initcalls run before initializing SMP.
 *
 * Only for built-in code, not modules.
 */
#define early_initcall(fn)		__define_initcall(fn, early)

/*
 * A "pure" initcall has no dependencies on anything else, and purely
 * initializes variables that couldn't be statically initialized.
 *
 * This only exists for built-in code, not for modules.
 * Keep main.c:initcall_level_names[] in sync.
 */
#define pure_initcall(fn)		__define_initcall(fn, 0)

#define core_initcall(fn)		__define_initcall(fn, 1)
#define core_initcall_sync(fn)		__define_initcall(fn, 1s)
#define postcore_initcall(fn)		__define_initcall(fn, 2)
#define postcore_initcall_sync(fn)	__define_initcall(fn, 2s)
#define arch_initcall(fn)		__define_initcall(fn, 3)
#define arch_initcall_sync(fn)		__define_initcall(fn, 3s)
#define subsys_initcall(fn)		__define_initcall(fn, 4)
#define subsys_initcall_sync(fn)	__define_initcall(fn, 4s)
#define fs_initcall(fn)			__define_initcall(fn, 5)
#define fs_initcall_sync(fn)		__define_initcall(fn, 5s)
#define rootfs_initcall(fn)		__define_initcall(fn, rootfs)
#define device_initcall(fn)		__define_initcall(fn, 6)
#define device_initcall_sync(fn)	__define_initcall(fn, 6s)
#define late_initcall(fn)		__define_initcall(fn, 7)
#define late_initcall_sync(fn)		__define_initcall(fn, 7s)

#define __initcall(fn) device_initcall(fn)

2.1 创建ksoftirqd内核线程

 

Linux的软中断都是在专门的内核线程（ksoftirqd）中进行的，因此我们非常有必要看一下这些进程是怎么初始化的，这样我们才能在后面更准确地了解收包过程。该进程数量不是1个，而是N个，其中N等于你的机器的核数。

 

系统初始化的时候执行spawn_ksoftirq -> smpboot_register_percpu_thread->smpboot_register_percpu_thread_cpumask->__smpboot_create_thread，

该函数创建出softirqd内核线程（位于kernel/softirq.c， 线程主函数smpboot_thread_fn）。

 

相关代码如下：

//file: kernel/softirq.c
static struct smp_hotplug_thread softirq_threads = {
    .store          = &ksoftirqd,
    .thread_should_run  = ksoftirqd_should_run,
    .thread_fn      = run_ksoftirqd,
    .thread_comm        = "ksoftirqd/%u",};
static __init int spawn_ksoftirqd(void){
    register_cpu_notifier(&cpu_nfb); // 为每个CPU创建一个处理软件中断的线程

    BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
    return 0;
}
early_initcall(spawn_ksoftirqd);  // 将函数放至对应级别的初始化位置

//file : kernel/smp_boot.c
static int smpboot_thread_fn(void *data)
{
	struct smpboot_thread_data *td = data;
	struct smp_hotplug_thread *ht = td->ht;

	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);
		preempt_disable();
		if (kthread_should_stop()) {
			__set_current_state(TASK_RUNNING);
			preempt_enable();
			/* cleanup must mirror setup */
			if (ht->cleanup && td->status != HP_THREAD_NONE)
				ht->cleanup(td->cpu, cpu_online(td->cpu));
			kfree(td);
			return 0;
		}

		if (kthread_should_park()) {
			__set_current_state(TASK_RUNNING);
			preempt_enable();
			if (ht->park && td->status == HP_THREAD_ACTIVE) {
				BUG_ON(td->cpu != smp_processor_id());
				ht->park(td->cpu);
				td->status = HP_THREAD_PARKED;
			}
			kthread_parkme();
			/* We might have been woken for stop */
			continue;
		}

		BUG_ON(td->cpu != smp_processor_id());

		/* Check for state change setup */
		switch (td->status) {
		case HP_THREAD_NONE:
			__set_current_state(TASK_RUNNING);
			preempt_enable();
			if (ht->setup)
				ht->setup(td->cpu);
			td->status = HP_THREAD_ACTIVE;
			continue;

		case HP_THREAD_PARKED:
			__set_current_state(TASK_RUNNING);
			preempt_enable();
			if (ht->unpark)
				ht->unpark(td->cpu);
			td->status = HP_THREAD_ACTIVE;
			continue;
		}

		if (!ht->thread_should_run(td->cpu)) {  // 检测软件是否有可运行软中断
			preempt_enable_no_resched();
			schedule();
		} else {
			__set_current_state(TASK_RUNNING);
			preempt_enable();
			ht->thread_fn(td->cpu);   // 执行注册的软件中断函数
		}
	}
}

当ksoftirqd被创建出来以后，它就会进入自己的线程循环函数ksoftirqd_should_run和run_ksoftirqd了。不停地判断有没有软中断需要被处理。这里需要注意的一点是，软中断不仅仅只有网络软中断，还有其它类型。

//file: include/linux/interrupt.h
enum{
    HI_SOFTIRQ=0,
    TIMER_SOFTIRQ,
    NET_TX_SOFTIRQ,
    NET_RX_SOFTIRQ,
    BLOCK_SOFTIRQ,
    BLOCK_IOPOLL_SOFTIRQ,
    TASKLET_SOFTIRQ,
    SCHED_SOFTIRQ,
    HRTIMER_SOFTIRQ,
    RCU_SOFTIRQ,  
};