linux TCP数据包重传过程----小结
于TCP/IP协议栈的TCP协议的重传功能是由在linux内核源码(net/ipv4/tcp_output.c)中的函数tcp_retransmit_skb()实现的
代码如下：
/* This retransmits one SKB. Policy decisions and retransmit queue
* state updates are done by the caller. Returns non-zero if an
* error occurred which prevented the send.
*/
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned int cur_mss;
int err;
/* Inconslusive MTU probe */
if (icsk->icsk_mtup.probe_size) {
icsk->icsk_mtup.probe_size = 0;
}
/* Do not sent more than we queued. 1/4 is reserved for possible
* copying overhead: fragmentation, tunneling, mangling etc.
*/
//说明在发送缓存区中消耗了许多内存去做其他的工作(比如分片等，只有1/4的缓存才是保留给这些工作的)，暂时不能重传
if (atomic_read(&sk->sk_wmem_alloc) >
min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
return -EAGAIN;
//检测重传的段，接收方是否已经收到其部分或者全部，如果收到则说明有bug ，否者就调整TCP段的负荷，即删除SKB缓存区
//前面部分已经接收到的数据
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
BUG();
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
//根据目的地址等条件获取路由，如果获取路由失败就不能发送
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
cur_mss = tcp_current_mss(sk);
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
* our retransmit serves as a zero window probe.
*/
//如果接收方已经减小了窗口，并且带重传的SKB已经不在新的窗口内，则不能重传该SKB，
//有一种情况例外，就是接收方的接受窗口减少为0，在这种情况下会发送0窗口探测段
if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
TCP_SKB_CB(skb)->seq != tp->snd_una)
return -EAGAIN;
if (skb->len > cur_mss) {//如果当前的SKB长度大于MSS，则要进行分段处理
if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
} else {
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
}
tcp_retrans_try_collapse(sk, skb, cur_mss);
/* Some Solaris stacks overoptimize and ignore the FIN on a
* retransmit when old data is attached. So strip it off
* since it is cheap to do so and saves bytes on the network.
*/
//有以下Solaris系统的协议栈有时候会忽略重传SKB上带有的FIN标志的payload，将payload全部剥离掉，节省网络流量
if (skb->len > 0 &&
(TCP_SKB_CB(skb)->flags & TCPHDR_FIN) &&
tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
/* Reuse, even though it does some unnecessary work */
tcp_init_nondata_skb(skb, TCP_SKB_CB(skb)->end_seq - 1,
TCP_SKB_CB(skb)->flags);
skb->ip_summed = CHECKSUM_NONE;
}
}
/* Make a copy, if the first transmission SKB clone we made
* is still in somebody's hands, else make a clone.
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);//发送SKB
if (err == 0) {
/* Update global TCP statistics. */
TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
tp->total_retrans++;
#if FASTRETRANS_DEBUG > 0
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
if (net_ratelimit())
printk(KERN_DEBUG "retrans_out leaked.\n");
}
#endif
if (!tp->retrans_out)
tp->lost_retrans_low = tp->snd_nxt;
TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
tp->retrans_out += tcp_skb_pcount(skb);
/* Save stamp of the first retransmit. */
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
tp->undo_retrans += tcp_skb_pcount(skb);
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
*/
TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
}
return err;
}
我们知道，TCP的发送是有一个SKB 队列如图，这样维持一个发送队列，如果收到发送了SKB的ACK，就将对应的SKB从队列中删除掉，在函数
tcp_retransmit_skb中我们可以看到，接受方游有可能只是收到了部分SKB的数据，那么就将收到的SKB的数据删除掉，这样可以节省缓存空间
这里注意的到函数tcp_retransmit_skb()最终的是调用函数tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);将SKB发送出去，而构造TCP的头部信息在函
数tcp_transmit_skb()中，下面是函数tcp_transmit_skb()构造TCP头部的片段 所以也就是说在发送队列中的SKB是没有头部的，这也是方便了选择重传等功能
/* Build TCP header and checksum it. */ th = tcp_hdr(skb); th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->flags);
