linux内核网络收包过程—IP协议处理

admin管理员组

文章数量:1642163

目录

网络协议栈

IP协议层处理

---

网络协议栈

netif_receive_skb_list_internal->__netif_receive_skb_list->__netif_receive_skb_list_core

函数会根据包的协议，假如是 udp 包，会将包依次送到 ip_rcv(), udp_rcv() 协议处理函数中进⾏处

static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
				    struct packet_type **ppt_prev)
{

	//将数据送入抓包点，tcpdump
	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		if (pt_prev)
			ret = deliver_skb(skb, pt_prev, orig_dev);
		pt_prev = ptype;
	}

    //取出协议
	type = skb->protocol;

	/* deliver only exact match when indicated */
	if (likely(!deliver_exact)) {
		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
				       &ptype_base[ntohs(type) &
						   PTYPE_HASH_MASK]);
	}
...
	return ret;
}

//遍历list
static inline void deliver_ptype_list_skb(struct sk_buff *skb,
					  struct packet_type **pt,
					  struct net_device *orig_dev,
					  __be16 type,
					  struct list_head *ptype_list)
{
	struct packet_type *ptype, *pt_prev = *pt;

	list_for_each_entry_rcu(ptype, ptype_list, list) {
		if (ptype->type != type)
			continue;
		if (pt_prev)
			deliver_skb(skb, pt_prev, orig_dev);
		pt_prev = ptype;
	}
	*pt = pt_prev;
}

//fun
static inline int deliver_skb(struct sk_buff *skb,
			      struct packet_type *pt_prev,
			      struct net_device *orig_dev)
{

	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}

函数处理的任务

1. type = skb->protocol取出协议信息，
2. 遍历注册在这个协议上的回调函数列表， ptype_base 是 hash table初始化时注册的
3. pt_prev->func 协议层注册的处理函数ip_rcv

IP协议层处理

int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
	   struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);
	skb = ip_rcv_core(skb, net);

	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip_rcv_finish);
}

static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	int ret;

	skb = l3mdev_ip_rcv(skb);
	ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);

	if (ret != NET_RX_DROP)
		ret = dst_input(skb);
	return ret;
}

NF_HOOK 是⼀个钩⼦函数，执行ip_rcv_finish

函数调用关系 ip_rcv_finish_core         ip_route_input_noref                 ip_route_input_rcu                         ip_route_input_mc                                 rt_dst_alloc

struct rtable *rt_dst_alloc(struct net_device *dev,
			    unsigned int flags, u16 type,
			    bool nopolicy, bool noxfrm, bool will_cache)
{
		rt->dst.output = ip_output;
		if (flags & RTCF_LOCAL)
			rt->dst.input = ip_local_deliver;
        ...
}

skb_dst(skb)->input 调⽤的 input ⽅法就是路由⼦系统赋的 ip_local_deliver

int ip_local_deliver(struct sk_buff *skb)
{

	struct net *net = dev_net(skb->dev);
    ...
	return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
		       net, NULL, skb, skb->dev, NULL,
		       ip_local_deliver_finish);
}

static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	__skb_pull(skb, skb_network_header_len(skb));

	ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);

	return 0;
}

void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
	const struct net_protocol *ipprot;
	int raw, ret;

resubmit:
	raw = raw_local_deliver(skb, protocol);
	ipprot = rcu_dereference(inet_protos[protocol]);
	if (ipprot) {
		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv,skb);
        ...
		__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
	}
...
}

inet_protos 中保存着 tcp_v4_rcv() 和 udp_rcv() 的函数地址。

 参考

GitHub - yanfeizhang/coder-kung-fu: 开发内功修炼

---

本文标签： 内核协议过程网络Linux