我们知道,报文经过网卡驱动处理后,调用net_receive_skb传递给具体的协议处理函数,对于IPv4报文来说,其协议处理函数就是ip_rcv了,ip_rcv在进行一些健康检查等操作后,会调用ip_rcv_finish来处理报文。这也是IPv4协议对报文接收处理的开始。
我们先看下ip_rcv_finish源代码:
ip_rcv_finish:
//ip数据报文的主要处理程序(ip_rcv仅仅只是对ip数据报做一些健康性检查)
//ip_rcv_finish 其实是进行路由表查询,,决定报文经过IP层处理后,是继续向上传递,还是进行转发,还是丢弃。
//1.决定报文在本地传递或者转发,如果是转发还需要找到出口设备和下一跳节点
//2.分析和处理一些选项
static int ip_rcv_finish(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
/*
* Initialise the virtual path cache for the packet. It describe
* how the packet travels inside Linux networking.
* 刚开始没有进行路由表查询,所以还没有相应的路由表项:skb_dst(skb) == NULL。
* 则在路由表中查找ip_route_input(),关于内核的路由表
*/
if (skb_dst(skb) == NULL) {
int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
skb->dev); //这里面进行了一些初始化操作,比较重要,与ip报文接下来的走向有关
if (unlikely(err)) {
if (err == -EHOSTUNREACH)
IP_INC_STATS_BH(dev_net(skb->dev),
IPSTATS_MIB_INADDRERRORS);
else if (err == -ENETUNREACH)
IP_INC_STATS_BH(dev_net(skb->dev),
IPSTATS_MIB_INNOROUTES);
goto drop;
}
}
#ifdef CONFIG_NET_CLS_ROUTE
//更新traffic cotrol(qos层)所使用的统计数据
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id());
u32 idx = skb_dst(skb)->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes += skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes += skb->len;
}
#endif
if (iph->ihl > 5 && ip_rcv_options(skb))
goto drop;
rt = skb_rtable(skb); /* skb->dst包含路由信息。根据路由类型更新SNMP统计数据 */
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCAST,
skb->len);
} else if (rt->rt_type == RTN_BROADCAST)
IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INBCAST,
skb->len);
/*
* dst_input实际上会调用skb->dst->input(skb).input函数会根据路由信息设置为合适的
* 函数指针,如果是递交到本地的则为ip_local_deliver,若是转发则为ip_forward.
* 暂时仅先考虑ip_local_deliver。
*/
return dst_input(skb);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
ip_route_input会进行路由表查询,该函数直接或间接决定了报文之后要往何处传递。是进行本地传递还是转发。
我们可以看到如果报文没有被drop掉,那么报文最终会被dst_input(skb)处理。dst_input(skb)实际上执行的是skb->dst->input(skb)。而这里的input函数其实就是由ip_route_input决定的。
对于应该本地传递的报文,input指针会指向ip_local_deliver。对于该转发的报文,input会指向ip_forward。
本地传递
/*
* Deliver IP Packets to the higher protocol layers.
*/
int ip_local_deliver(struct sk_buff *skb)
{
/*
* Reassemble IP fragments.
*/
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER))
return 0;
}
return NF_HOOK(PF_INET, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
我们知道,IPv4要将报文传送给上层协议(本地传递),那它需要对分段的报文进行重组,ip_defrag即完成报文重组。
然后由调用Netfilter决定是否调用ip_local_deliver_finish。
ip_local_deliver_finish
static int ip_local_deliver_finish(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
__skb_pull(skb, ip_hdrlen(skb)); /* 跳过IP头部 */
/* Point into the IP datagram, just past the header. */
/* 设置传输层头部位置 */
skb_reset_transport_header(skb);
rcu_read_lock();
{
int protocol = ip_hdr(skb)->protocol; //取出ip头中的协议.
int hash, raw;
const struct net_protocol *ipprot;
resubmit:
// 若是raw socket发送的,需要做相应的处理,clone数据包
raw = raw_local_deliver(skb, protocol); //得到raw socket, 如果不是raw socket,则返回0
hash = protocol & (MAX_INET_PROTOS - 1); // 计算传输层协议处理结构在inet_protos数组hash表中的位置
ipprot = rcu_dereference(inet_protos[hash]); // 获取传输层协议处理指针
if (ipprot != NULL) {
int ret;
//主要是ipprot是否有被当前主机注册
if (!net_eq(net, &init_net) && !ipprot->netns_ok) { // 若获取到了对应传输层的处理结构
if (net_ratelimit())
printk("%s: proto %d isn't netns-ready\n",
__func__, protocol);
kfree_skb(skb);
goto out;
}
//判断ipsec,并进行相关处理.
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
goto out;
}
nf_reset(skb);
}
//调用handler,进入相应的4层协议的处理.
ret = ipprot->handler(skb);
if (ret < 0) { // 处理数据包失败,再次尝试
protocol = -ret;
goto resubmit;
}
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);// 添加数据包处理统计信息
} else {// 若没有找到相应传输层的处理函数
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP_INC_STATS_BH(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
} else
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
out:
rcu_read_unlock();
return 0;
}
转发
报文转发有下面几个步骤完成:
1. 处理IP选项
2. 确定封包可以被转发
3.递减封包头部的TTL字段,如果TTL字段为0,则丢弃该封包
4.根据路径相关MTU,在必要时处理分段
5.把封包传送至外出设备
IPv4协议中,报文的转发从ip_forward开始:
ip_forward
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) //处理Router_Alert选项(重要)
return NET_RX_SUCCESS;
//确定二层目的是发往本机的,这步检查是多余的,因为在二层接收的时候,不是二层地址不是本机的包已经被丢弃
//对于二层地址为本机的数据帧,skb->pkt_type 赋值为PACKET_HOST
if (skb->pkt_type != PACKET_HOST)//
goto drop;
skb_forward_csum(skb);//这里只是转发封包,因而不关系L4层检验和
skb_forward_csum(skb);//这里只是转发封包,因而不关系L4层检验和
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
//如果报头含有strictroute选项,且选项中的下一跳与路由子系统的网关不同
//则表示选项失败,封包丢弃
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
ip_forward检查结束,如果进入ip_forward_finish说明该封包已经可以真正的传给另一个系统了。转发真正工作在ip_forward_finish,中完成。
ip_forward_finish
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
//ip_forward已经处理了两个可能的选项,ROute_Alert 和 Strict Source Routing
//这里还需要处理其他选项(由ip_rcv_finish通过ip_options_compile进行初始化
if (unlikely(opt->optlen))
ip_forward_options(skb);
return dst_output(skb);
}
/* Output packet to network from transport. */
static inline int dst_output(struct sk_buff *skb)
{
return skb_dst(skb)->output(skb);
}
output是虚拟函数,对于单播封包,会初始化为ip_output,对于多播封包,会初始化为ip_mc_output。这两函数也会处理分段,并在最后调用ip_finish_output.
ip_output
int ip_output(struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
ip_mc_output
int ip_mc_output(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->u.dst.dev;
/*
* If the indicated interface is up and running, send the packet.
*/
IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
/*
* Multicasts are looped back for other local users
*/
if (rt->rt_flags&RTCF_MULTICAST) {
if ((!sk || inet_sk(sk)->mc_loop)
#ifdef CONFIG_IP_MROUTE
/* Small optimization: do not loopback not local frames,
which returned after forwarding; they will be dropped
by ip_mr_input in any case.
Note, that local frames are looped back to be delivered
to local recipients.
This check is duplicated in ip_mr_input at the moment.
*/
&& ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED))
#endif
) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb,
NULL, newskb->dev,
ip_dev_loopback_xmit);
}
/* Multicasts with ttl 0 must not go beyond the host */
if (ip_hdr(skb)->ttl == 0) {
kfree_skb(skb);
return 0;
}
}
if (rt->rt_flags&RTCF_BROADCAST) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, NULL,
newskb->dev, ip_dev_loopback_xmit);
}
return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
ip_finish_output
static int ip_finish_output(struct sk_buff *skb)
{
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm != NULL) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(skb);
}
#endif
if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
return ip_fragment(skb, ip_finish_output2);//分段
else
return ip_finish_output2(skb);
}
ip_finish_output会和邻居子系统进行衔接。细节看 ipv4 传输的博文。