IP 层收发报文简要剖析6--ip报文输出3 ip_push_pending_frames

/*
 *    Combined all pending IP fragments on the socket as one IP datagram
 *    and push them out.
 */
struct sk_buff *__ip_make_skb(struct sock *sk,
                  struct flowi4 *fl4,
                  struct sk_buff_head *queue,
                  struct inet_cork *cork)
{
    struct sk_buff *skb, *tmp_skb;
    struct sk_buff **tail_skb;
    struct inet_sock *inet = inet_sk(sk);
    struct net *net = sock_net(sk);
    struct ip_options *opt = NULL;
    struct rtable *rt = (struct rtable *)cork->dst;
    struct iphdr *iph;
    __be16 df = 0;
    __u8 ttl;

    skb = __skb_dequeue(queue);/* 发送队列可能为空 */
    if (!skb)
        goto out;
    tail_skb = &(skb_shinfo(skb)->frag_list); /* 获得分片链表 */

    /* move skb->data to ip header from ext header */
    if (skb->data < skb_network_header(skb)) /* 调整data指针位置 */
        __skb_pull(skb, skb_network_offset(skb));
    while ((tmp_skb = __skb_dequeue(queue)) != NULL) { /* 调整所有发送缓冲中的sk_buff的data指针位置，并更新第一个sk_buff的数据长度 */
        __skb_pull(tmp_skb, skb_network_header_len(skb));
        *tail_skb = tmp_skb;
        tail_skb = &(tmp_skb->next);
        skb->len += tmp_skb->len;
        skb->data_len += tmp_skb->len;
        skb->truesize += tmp_skb->truesize;
        tmp_skb->destructor = NULL;
        tmp_skb->sk = NULL;
    }

    /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow
     * to fragment the frame generated here. No matter, what transforms
     * how transforms change size of the packet, it will come out.
     */
    skb->ignore_df = ip_sk_ignore_df(sk);

    /* DF bit is set when we want to see DF on outgoing frames.
     * If ignore_df is set too, we still allow to fragment this frame
     * locally. */
    if (inet->pmtudisc == IP_PMTUDISC_DO ||
        inet->pmtudisc == IP_PMTUDISC_PROBE ||
        (skb->len <= dst_mtu(&rt->dst) &&
         ip_dont_fragment(sk, &rt->dst))) /* 不允许分片，或者不需要分片 */
        df = htons(IP_DF);

    if (cork->flags & IPCORK_OPT)/* ip option 保存在cork中， 则使用cork中的option */
        opt = cork->opt;

    if (cork->ttl != 0)/* 选择合适的TTL值 */
        ttl = cork->ttl;
    else if (rt->rt_type == RTN_MULTICAST)
        ttl = inet->mc_ttl;
    else
        ttl = ip_select_ttl(inet, &rt->dst);

    iph = ip_hdr(skb);/* 得到IP报文头的地址 */ 
    iph->version = 4;
    iph->ihl = 5;
    iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
    iph->frag_off = df;
    iph->ttl = ttl;
    iph->protocol = sk->sk_protocol;
    ip_copy_addrs(iph, fl4);
    ip_select_ident(net, skb, sk);

    if (opt) { /* 
        填充IP option
        看到这里，可以发现opt只可能从cork中获得
         */
        iph->ihl += opt->optlen>>2;
        ip_options_build(skb, opt, cork->addr, rt, 0);
    }

    skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
    skb->mark = sk->sk_mark;
    /*
     * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
     * on dst refcount
     */
    cork->dst = NULL;
    skb_dst_set(skb, &rt->dst);

    if (iph->protocol == IPPROTO_ICMP)
        icmp_out_count(net, ((struct icmphdr *)
            skb_transport_header(skb))->type);

    ip_cork_release(cork);
out:
    return skb;
}