tcp_output.c

		/* Slow path, intersegment interval is "high". */

		/* If some rtt estimate is known, use it to bound delayed ack.
		 * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
		 * directly.
		 */
		if (tp->srtt) {
			int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN);

			if (rtt < max_ato)
				max_ato = rtt;
		}

		ato = min(ato, max_ato);
	}

	/* Stay within the limit we were given */
	timeout = jiffies + ato;

	/* Use new timeout only if there wasn't a older one earlier. */
	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
		/* If delack timer was blocked or is about to expire,
		 * send ACK now.
		 */
		if (icsk->icsk_ack.blocked ||
		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
			tcp_send_ack(sk);
			return;
		}

		if (!time_before(timeout, icsk->icsk_ack.timeout))
			timeout = icsk->icsk_ack.timeout;
	}
	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
	icsk->icsk_ack.timeout = timeout;
	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
}

/* This routine sends an ack and also updates the window. */
void tcp_send_ack(struct sock *sk)
{
	struct sk_buff *buff;

	/* If we have been reset, we may not send again. */
	if (sk->sk_state == TCP_CLOSE)
		return;

	/* We are not putting this on the write queue, so
	 * tcp_transmit_skb() will set the ownership to this
	 * sock.
	 */
	buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
	if (buff == NULL) {
		inet_csk_schedule_ack(sk);
		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
					  TCP_DELACK_MAX, TCP_RTO_MAX);
		return;
	}

	/* Reserve space for headers and prepare control bits. */
	skb_reserve(buff, MAX_TCP_HEADER);
	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);

	/* Send it off, this clears delayed acks for us. */
	TCP_SKB_CB(buff)->when = tcp_time_stamp;
	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
}

/* This routine sends a packet with an out of date sequence
 * number. It assumes the other end will try to ack it.
 *
 * Question: what should we make while urgent mode?
 * 4.4BSD forces sending single byte of data. We cannot send
 * out of window data, because we have SND.NXT==SND.MAX...
 *
 * Current solution: to send TWO zero-length segments in urgent mode:
 * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is
 * out-of-date with SND.UNA-1 to probe window.
 */
static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	/* We don't queue it, tcp_transmit_skb() sets ownership. */
	skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
	if (skb == NULL)
		return -1;

	/* Reserve space for headers and set control bits. */
	skb_reserve(skb, MAX_TCP_HEADER);
	/* Use a previous sequence.  This should cause the other
	 * end to send an ack.  Don't queue or clone SKB, just
	 * send it.
	 */
	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
	TCP_SKB_CB(skb)->when = tcp_time_stamp;
	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}

void tcp_send_window_probe(struct sock *sk)
{
	if (sk->sk_state == TCP_ESTABLISHED) {
		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
		tcp_xmit_probe_skb(sk, 0);
	}
}

/* Initiate keepalive or window probe from timer. */
int tcp_write_wakeup(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	if (sk->sk_state == TCP_CLOSE)
		return -1;

	if ((skb = tcp_send_head(sk)) != NULL &&
	    before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
		int err;
		unsigned int mss = tcp_current_mss(sk);
		unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;

		if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
			tp->pushed_seq = TCP_SKB_CB(skb)->end_seq;

		/* We are probing the opening of a window
		 * but the window size is != 0
		 * must have been a result SWS avoidance ( sender )
		 */
		if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq ||
		    skb->len > mss) {
			seg_size = min(seg_size, mss);
			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
			if (tcp_fragment(sk, skb, seg_size, mss))
				return -1;
		} else if (!tcp_skb_pcount(skb))
			tcp_set_skb_tso_segs(sk, skb, mss);

		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
		TCP_SKB_CB(skb)->when = tcp_time_stamp;
		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
		if (!err)
			tcp_event_new_data_sent(sk, skb);
		return err;
	} else {
		if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
			tcp_xmit_probe_skb(sk, 1);
		return tcp_xmit_probe_skb(sk, 0);
	}
}

/* A window probe timeout has occurred.  If window is not closed send
 * a partial packet else a zero probe.
 */
void tcp_send_probe0(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int err;

	err = tcp_write_wakeup(sk);

	if (tp->packets_out || !tcp_send_head(sk)) {
		/* Cancel probe timer, if it is not required. */
		icsk->icsk_probes_out = 0;
		icsk->icsk_backoff = 0;
		return;
	}

	if (err <= 0) {
		if (icsk->icsk_backoff < sysctl_tcp_retries2)
			icsk->icsk_backoff++;
		icsk->icsk_probes_out++;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
					  TCP_RTO_MAX);
	} else {
		/* If packet was not sent due to local congestion,
		 * do not backoff and do not remember icsk_probes_out.
		 * Let local senders to fight for local resources.
		 *
		 * Use accumulated backoff yet.
		 */
		if (!icsk->icsk_probes_out)
			icsk->icsk_probes_out = 1;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  min(icsk->icsk_rto << icsk->icsk_backoff,
					      TCP_RESOURCE_PROBE_INTERVAL),
					  TCP_RTO_MAX);
	}
}