2.2 网络子系统初始化

linux内核通过调用subsys_initcall来初始化各个子系统，在源代码目录里你可以grep出许多对这个函数的调用。这里我们要说的是网络子系统的初始化，会执行到net_dev_init函数。

/*
 *	Initialize the DEV module. At boot time this walks the device list and
 *	unhooks any devices that fail to initialise (normally hardware not
 *	present) and leaves us with a valid list of present and active devices.
 *
 */

/*
 *       This is called single threaded during boot, so no need
 *       to take the rtnl semaphore.
 */
static int __init net_dev_init(void)
{
	int i, rc = -ENOMEM;

	BUG_ON(!dev_boot_phase);

	if (dev_proc_init())
		goto out;

	if (netdev_kobject_init())
		goto out;

	INIT_LIST_HEAD(&ptype_all);
	for (i = 0; i < PTYPE_HASH_SIZE; i++)   // 初始化网络协议hash链表，如ip/ipv6/icmp/arp等协议，用于接收报文协议处理ptype_base
		INIT_LIST_HEAD(&ptype_base[i]);

	INIT_LIST_HEAD(&offload_base);

	if (register_pernet_subsys(&netdev_net_ops))
		goto out;

	/*
	 *	Initialise the packet receive queues.
	 */

	for_each_possible_cpu(i) {
		struct softnet_data *sd = &per_cpu(softnet_data, i);

		skb_queue_head_init(&sd->input_pkt_queue);
		skb_queue_head_init(&sd->process_queue);
		INIT_LIST_HEAD(&sd->poll_list);
		sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
		sd->csd.func = rps_trigger_softirq;
		sd->csd.info = sd;
		sd->cpu = i;
#endif

		sd->backlog.poll = process_backlog;
		sd->backlog.weight = weight_p;
	}

	dev_boot_phase = 0;

	/* The loopback device is special if any other network devices
	 * is present in a network namespace the loopback device must
	 * be present. Since we now dynamically allocate and free the
	 * loopback device ensure this invariant is maintained by
	 * keeping the loopback device as the first device on the
	 * list of network devices.  Ensuring the loopback devices
	 * is the first device that appears and the last network device
	 * that disappears.
	 */
	if (register_pernet_device(&loopback_net_ops))
		goto out;

	if (register_pernet_device(&default_device_ops))
		goto out;

	open_softirq(NET_TX_SOFTIRQ, net_tx_action);
	open_softirq(NET_RX_SOFTIRQ, net_rx_action);

	hotcpu_notifier(dev_cpu_callback, 0);
	dst_subsys_init();
	rc = 0;
out:
	return rc;
}

subsys_initcall(net_dev_init);


//file : linux/netdevice.h
/*
 *	The list of packet types we will receive (as opposed to discard)
 *	and the routines to invoke.
 *
 *	Why 16. Because with 16 the only overlap we get on a hash of the
 *	low nibble of the protocol value is RARP/SNAP/X.25.
 *
 *      NOTE:  That is no longer true with the addition of VLAN tags.  Not
 *             sure which should go first, but I bet it won't make much
 *             difference if we are running VLANs.  The good news is that
 *             this protocol won't be in the list unless compiled in, so
 *             the average user (w/out VLANs) will not be adversely affected.
 *             --BLG
 *
 *		0800	IP
 *		8100    802.1Q VLAN
 *		0001	802.3
 *		0002	AX.25
 *		0004	802.2
 *		8035	RARP
 *		0005	SNAP
 *		0805	X.25
 *		0806	ARP
 *		8137	IPX
 *		0009	Localtalk
 *		86DD	IPv6
 */
#define PTYPE_HASH_SIZE	(16)
#define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)

在这个函数里，会为每个CPU都申请一个softnet_data数据结构，在这个数据结构里的poll_list是等待驱动程序将其poll函数注册进来，稍后网卡驱动初始化的时候我们可以看到这一过程。

另外open_softirq注册了每一种软中断都注册一个处理函数。NET_TX_SOFTIRQ的处理函数为net_tx_action，NET_RX_SOFTIRQ的为net_rx_action。继续跟踪open_softirq后发现这个注册的方式是记录在softirq_vec变量里的。后面ksoftirqd线程收到软中断的时候，也会使用这个变量来找到每一种软中断对应的处理函数。

//file: kernel/softirq.c
void open_softirq(int nr, void (*action)(struct softirq_action *)){
    softirq_vec[nr].action = action;
}

static void run_ksoftirqd(unsigned int cpu)
{
	local_irq_disable();
	if (local_softirq_pending()) {
		/*
		 * We can safely run softirq on inline stack, as we are not deep
		 * in the task stack here.
		 */
		__do_softirq();
		local_irq_enable();
		cond_resched_rcu_qs();
		return;
	}
	local_irq_enable();
}

asmlinkage __visible void __do_softirq(void)
{
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;
	struct softirq_action *h;
	bool in_hardirq;
	__u32 pending;
	int softirq_bit;

	/*
	 * Mask out PF_MEMALLOC s current task context is borrowed for the
	 * softirq. A softirq handled such as network RX might set PF_MEMALLOC
	 * again if the socket is related to swap
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending();
	account_irq_enter_time(current);

	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
	in_hardirq = lockdep_softirq_start();

restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	local_irq_enable();

	h = softirq_vec; // 软件中断向量

	while ((softirq_bit = ffs(pending))) {
		unsigned int vec_nr;
		int prev_count;

		h += softirq_bit - 1;

		vec_nr = h - softirq_vec;
#ifdef IP_SPEEDUP_DEBUG
		g_vec_nr[smp_processor_id()] = vec_nr;
#endif
		prev_count = preempt_count();

		kstat_incr_softirqs_this_cpu(vec_nr);

#ifdef CONFIG_RTK_HOST_SPEEDUP
		if (isHostSpeedUpEnable())
			send_delay_ack_timer();
#endif
		trace_softirq_entry(vec_nr);
		h->action(h); // 中断处理函数
		trace_softirq_exit(vec_nr);
		if (unlikely(prev_count != preempt_count())) {
			pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
			       vec_nr, softirq_to_name[vec_nr], h->action,
			       prev_count, preempt_count());
			preempt_count_set(prev_count);
		}
		h++;
		pending >>= softirq_bit;
	}

	rcu_bh_qs();
	local_irq_disable();

	pending = local_softirq_pending();
#ifdef CONFIG_RTK_HOST_SPEEDUP
	if (isHostSpeedUpEnable())
	{
		int unAckSegment;
		
		unAckSegment = send_delay_ack_timer();
		if (unAckSegment)
		{
			if (pending || time_before(jiffies, end))
				goto restart;

			//printk("unAck in softirq!\n");
		}
	}
#endif
	if (pending) {
		if (time_before(jiffies, end) && !need_resched() &&
		    --max_restart)
			goto restart;

		wakeup_softirqd();
	}

	lockdep_softirq_end(in_hardirq);
	account_irq_exit_time(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
	WARN_ON_ONCE(in_interrupt());
	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}