IP 层收发报文简要剖析1-ip报文的输入

/*
 * ip_rcv_finish()在ip_rcv()中当IP数据包经过netfilter模块
 * 处理后被调用。完成的主要功能是，如果
 * 还没有为该数据包查找输入路由缓存，则
 * 调用ip_route_input()为其查找输入路由缓存。
 * 接着处理IP数据包首部中的选项，最后
 * 根据输入路由缓存输入到本地或转发发。
 */
static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
    const struct iphdr *iph = ip_hdr(skb);
    struct rtable *rt;

    /* if ingress device is enslaved to an L3 master device pass the
     * skb to its handler for processing
     */
    skb = l3mdev_ip_rcv(skb);
    if (!skb)
        return NET_RX_SUCCESS;
/* 
        启用了early_demux
        skb路由缓存为空
        skb的sock为空
        不是分片包
    */
    if (net->ipv4.sysctl_ip_early_demux &&
        !skb_dst(skb) &&
        !skb->sk &&
        !ip_is_fragment(iph)) {
        const struct net_protocol *ipprot;
        int protocol = iph->protocol;
         /* 找到上层协议 */
         /* 获取协议对应的prot */
        ipprot = rcu_dereference(inet_protos[protocol]);
         /* 找到early_demux函数，如tcp_v4_early_demux */
        if (ipprot && ipprot->early_demux) {
             /* 调用该函数，将路由信息缓存到skb->refdst */
            ipprot->early_demux(skb); 
            
            /* must reload iph, skb->head might have changed */
            /* 重新取ip头 */
            iph = ip_hdr(skb);
        }
    }

    /*
     *    Initialise the virtual path cache for the packet. It describes
     *    how the packet travels inside Linux networking.
     */
     /*
     * 如果还没有为该数据包查找输入路由缓存，
     * 则调用ip_route_input_noref()为其查找输入路由缓存。
     * 若查找失败，则将该数据包丢弃。
     */
    if (!skb_valid_dst(skb)) {
        int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
                           iph->tos, skb->dev);
        if (unlikely(err)) {
            if (err == -EXDEV)
                __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
            goto drop;
        }
    }

#ifdef CONFIG_IP_ROUTE_CLASSID
    if (unlikely(skb_dst(skb)->tclassid)) {
        struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
        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
    /*
     * 根据长度判断IP首部中是否存在选项，如果有，
     * 则调用ip_rcv_options()处理IP选项。
     */
    if (iph->ihl > 5 && ip_rcv_options(skb))
        goto drop;
    /*
     * 最后根据输入路由缓存决定输入到本地或
     * 转发，最终前者调用ip_local_deliver()，后者调用
     * ip_forward()。
     * 对于输入到本地或转发的组播报文，在经过netfilter处理
     * 之后会调用ip_rcv_finish()正式进入输入的处理。先调用
     * ip_route_input()进行输入路由的查询，如果发现目的地址
     * 为组播地址，就会按照组播地址的规则查找路由，查找
     * 到组播的输入路由后，组播报文接收处理函数为ip_mr_input()。
     */
    rt = skb_rtable(skb);
    if (rt->rt_type == RTN_MULTICAST) {
        __IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len);
    } else if (rt->rt_type == RTN_BROADCAST) {
        __IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
    } else if (skb->pkt_type == PACKET_BROADCAST ||
           skb->pkt_type == PACKET_MULTICAST) {
        struct in_device *in_dev = __in_dev_get_rcu(skb->dev);

        /* RFC 1122 3.3.6:
         *
         *   When a host sends a datagram to a link-layer broadcast
         *   address, the IP destination address MUST be a legal IP
         *   broadcast or IP multicast address.
         *
         *   A host SHOULD silently discard a datagram that is received
         *   via a link-layer broadcast (see Section 2.4) but does not
         *   specify an IP multicast or broadcast destination address.
         *
         * This doesn‘t explicitly say L2 *broadcast*, but broadcast is
         * in a way a form of multicast and the most common use case for
         * this is 802.11 protecting against cross-station spoofing (the
         * so-called "hole-196" attack) so do it for both.
         */
        if (in_dev &&
            IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
            goto drop;
    }
    /* 调用路由项的input函数，可能为ip_local_deliver或者ip_forward */
    return dst_input(skb);

drop:
    kfree_skb(skb);
    return NET_RX_DROP;
}