Qian's Blog

#define TCP_RTO_MAX     ((unsigned)(120*HZ))
#define TCP_RTO_MIN     ((unsigned)(HZ/5))
#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))     /* RFC2988bis initial RTO value */
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now
                                                 * used as a fallback RTO for the
                                                 * initial data transmission if no
                                                 * valid RTT sample has been acquired,
                                                 * most likely due to retrans in 3WHS.
                                                 */

/**
 *  retransmits_timed_out() - returns true if this connection has timed out
 *  @sk:       The current socket
 *  @boundary: max number of retransmissions
 *  @timeout:  A custom timeout value.
 *             If set to 0 the default timeout is calculated and used.
 *             Using TCP_RTO_MIN and the number of unsuccessful retransmits.
 *  @syn_set:  true if the SYN Bit was set.
 *
 * The default "timeout" value this function can calculate and use
 * is equivalent to the timeout of a TCP Connection
 * after "boundary" unsuccessful, exponentially backed-off
 * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
 * syn_set flag is set.
 */
static bool retransmits_timed_out(struct sock *sk,
                                  unsigned int boundary,
                                  unsigned int timeout,
                                  bool syn_set)
{
        unsigned int linear_backoff_thresh, start_ts;
        unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; //SYN包则rto_base为 TCP_TIMEOUT_INIT也就是1s，否则为200ms

        if (!inet_csk(sk)->icsk_retransmits)
                return false;

        start_ts = tcp_sk(sk)->retrans_stamp;
        if (unlikely(!start_ts))
                start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));

        if (likely(timeout == 0)) {
                linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); // 指数和线性增长的阈值

                if (boundary <= linear_backoff_thresh)
                        timeout = ((2 << boundary) - 1) * rto_base; // 小于阈值指数增长
                else
                        timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +  //大于阈值线性增长
                                (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
        }
        return (tcp_time_stamp - start_ts) >= timeout; //当前的时间戳减去开始时间
}

/* Called with bottom-half processing disabled.
   Called by tcp_write_timer() */
void tcp_write_timer_handler(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	int event;

  // state 是CLOSE或者未安装定时器则直接go out
	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
	    !icsk->icsk_pending)
		goto out;

	if (time_after(icsk->icsk_timeout, jiffies)) {
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
		goto out;
	}

	event = icsk->icsk_pending;

	switch (event) {
	case ICSK_TIME_EARLY_RETRANS:
		tcp_resume_early_retransmit(sk);
		break;
	case ICSK_TIME_LOSS_PROBE:
		tcp_send_loss_probe(sk);
		break;
	case ICSK_TIME_RETRANS: //正常情况的重传
		icsk->icsk_pending = 0;
		tcp_retransmit_timer(sk);
		break;
	case ICSK_TIME_PROBE0:
		icsk->icsk_pending = 0;
		tcp_probe_timer(sk);
		break;
	}

out:
	sk_mem_reclaim(sk);
}

/**
 *  tcp_retransmit_timer() - The TCP retransmit timeout handler
 *  @sk:  Pointer to the current socket.
 *
 *  This function gets called when the kernel timer for a TCP packet
 *  of this socket expires.
 *
 *  It handles retransmission, timer adjustment and other necesarry measures.
 *
 *  Returns: Nothing (void)
 */
void tcp_retransmit_timer(struct sock *sk)
{
    //...
    // 若开启了TFO，则重传SYN／ACK
	if (tp->fastopen_rsk) { 
		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
			     sk->sk_state != TCP_FIN_WAIT1);
		tcp_fastopen_synack_timer(sk);
		/* Before we receive ACK to our SYN-ACK don't retransmit
		 * anything else (e.g., data or FIN segments).
		 */
		return;
	}
    // 包是否已经全部确认
	if (!tp->packets_out)
		goto out;

    // ... 

	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
		/* Receiver dastardly shrinks window. Our retransmits
		 * become zero probes, but we should not timeout this
		 * connection. If the socket is an orphan, time it out,
		 * we cannot allow such beasts to hang infinitely.
		 */
		struct inet_sock *inet = inet_sk(sk);
		if (sk->sk_family == AF_INET) {
			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
					    &inet->inet_daddr,
					    ntohs(inet->inet_dport),
					    inet->inet_num,
					    tp->snd_una, tp->snd_nxt);
		}

        //...
        // 如果超过了最长时间还未收到对端的确认，则报错，且关闭连接
		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
			tcp_write_err(sk);
			goto out;
		}
		tcp_enter_loss(sk); // 进入拥塞控制的LOSS阶段
		tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1); // 重传发送队列的手包
		__sk_dst_reset(sk);
		goto out_reset_timer;
	}

	if (tcp_write_timeout(sk)) // 重传等待时间超时或者orphan socket消耗资源过多
		goto out;

    // 第一次重传
	if (icsk->icsk_retransmits == 0) {
		int mib_idx;
        //更新MIB数据库
	}

	tcp_enter_loss(sk); // 进入拥塞控制loss状态

    // 重传发送队列首包失败，不退避，直接重设timer
	if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) {
		/* Retransmission failed because of local congestion,
		 * do not backoff.
		 */
		if (!icsk->icsk_retransmits)
			icsk->icsk_retransmits = 1;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL),
					  TCP_RTO_MAX);
		goto out;
	}

	/* Increase the timeout each time we retransmit.  Note that
	 * we do not increase the rtt estimate.  rto is initialized
	 * from rtt, but increases here.  Jacobson (SIGCOMM 88) suggests
	 * that doubling rto each time is the least we can get away with.
	 * In KA9Q, Karn uses this for the first few times, and then
	 * goes to quadratic.  netBSD doubles, but only goes up to *64,
	 * and clamps at 1 to 64 sec afterwards.  Note that 120 sec is
	 * defined in the protocol as the maximum possible RTT.  I guess
	 * we'll have to use something other than TCP to talk to the
	 * University of Mars.
	 *
	 * PAWS allows us longer timeouts and large windows, so once
	 * implemented ftp to mars will work nicely. We will have to fix
	 * the 120 second clamps though!
	 */
    // 指数退避
	icsk->icsk_backoff++;
	icsk->icsk_retransmits++;

out_reset_timer:
	/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
	 * used to reset timer, set to 0. Recalculate 'icsk_rto' as this
	 * might be increased if the stream oscillates between thin and thick,
	 * thus the old value might already be too high compared to the value
	 * set by 'tcp_set_rto' in tcp_input.c which resets the rto without
	 * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating
	 * exponential backoff behaviour to avoid continue hammering
	 * linear-timeout retransmissions into a black hole
	 */
	if (sk->sk_state == TCP_ESTABLISHED &&
	    (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) &&
	    tcp_stream_is_thin(tp) &&
	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
		icsk->icsk_backoff = 0;
		icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
	} else {
		/* Use normal (exponential) backoff */
		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); // double一下超时时间
	}
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
	if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0))
		__sk_dst_reset(sk);

out:;
}