UDP socket流程（13）——ip_push_pending_frames

作者：[e-mail]

博客：linuxfocus.blog.chinaunix.net

今天开始学习新的函数ip_push_pending_frames，这个函数会被icmp_push_reply，ip_send_reply，raw_sendmsg，和udp_push_pending_frames调用。该函数用于将该socket上的所有pending的IP分片，组成一个IP报文发送出去。

下面是函数的具体的代码。

int ip_push_pending_frames(struct sock *sk)
{
    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 *)inet->cork.dst;
    struct iphdr *iph;
    __be16 df = 0;
    __u8 ttl;
    int err = 0;

     /* 发送队列可能为空 */

    if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
        goto out;
    /* 获得分片链表 */
    tail_skb = &(skb_shinfo(skb)->frag_list);

    /* move skb->data to ip header from ext header */
    /* 调整data指针位置 */
    if (skb->data < skb_network_header(skb))
        __skb_pull(skb, skb_network_offset(skb));

     /* 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 */

    while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
        __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.
     */
    /* 允许本地分片 */
    if (inet->pmtudisc < IP_PMTUDISC_DO)
        skb->local_df = 1;

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

      /* ip option 保存在cork中， 则使用cork中的option */

    if (inet->cork.flags & IPCORK_OPT)
        opt = inet->cork.opt;

      /* 选择合适的TTL值 */

    if (rt->rt_type == RTN_MULTICAST)
        ttl = inet->mc_ttl;
    else
        ttl = ip_select_ttl(inet, &rt->dst);

     /* 得到IP报文头的地址 */ 

    iph = (struct iphdr *)skb->data;
    /* 初始化IP报文头的内容 */
    iph->version = 4;
    iph->ihl = 5;
    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, inet->cork.addr, rt, 0);
    }
    iph->tos = inet->tos;
    iph->frag_off = df;
    ip_select_ident(iph, &rt->dst, sk);
    iph->ttl = ttl;
    iph->protocol = sk->sk_protocol;
    iph->saddr = rt->rt_src;
    iph->daddr = rt->rt_dst;

    skb->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
     */
    inet->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);

    /* Netfilter gets whole the not fragmented skb. */
    /* 发送数据 */
    err = ip_local_out(skb);
    if (err) {
        if (err > 0)
            err = net_xmit_errno(err);
        if (err)
            goto error;
    }

out:
    ip_cork_release(inet);
    return err;

error:
    IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
    goto out;
}

这个函数比较容易看懂——当然不是所有细节都非常清楚了。

第一遍浏览这些API，只要搞懂该API的大致流程和用途。当整个框架建立好以后，再慢慢补充细节。