tcp_output.c

linux 内核源代码

		return;

	tcp_verify_left_out(tp);

	/* Don't muck with the congestion window here.
	 * Reason is that we do not increase amount of _data_
	 * in network, but units changed and effective
	 * cwnd/ssthresh really reduced now.
	 */
	if (icsk->icsk_ca_state != TCP_CA_Loss) {
		tp->high_seq = tp->snd_nxt;
		tp->snd_ssthresh = tcp_current_ssthresh(sk);
		tp->prior_ssthresh = 0;
		tp->undo_marker = 0;
		tcp_set_ca_state(sk, TCP_CA_Loss);
	}
	tcp_xmit_retransmit_queue(sk);
}

/* 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 = tcp_current_mss(sk, 0);
	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.
	 */
	if (atomic_read(&sk->sk_wmem_alloc) >
	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
		return -EAGAIN;

	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;
	}

	/* 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.
	 */
	if (!before(TCP_SKB_CB(skb)->seq, tp->snd_una+tp->snd_wnd)
	    && TCP_SKB_CB(skb)->seq != tp->snd_una)
		return -EAGAIN;

	if (skb->len > cur_mss) {
		if (tcp_fragment(sk, skb, cur_mss, cur_mss))
			return -ENOMEM; /* We'll try again later. */
	}

	/* Collapse two adjacent packets if worthwhile and we can. */
	if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
	    (skb->len < (cur_mss >> 1)) &&
	    (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
	    (!tcp_skb_is_last(sk, skb)) &&
	    (skb_shinfo(skb)->nr_frags == 0 && skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) &&
	    (tcp_skb_pcount(skb) == 1 && tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) &&
	    (sysctl_tcp_retrans_collapse != 0))
		tcp_retrans_try_collapse(sk, skb, cur_mss);

	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
		return -EHOSTUNREACH; /* Routing failure or similar. */

	/* 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.
	 */
	if (skb->len > 0 &&
	    (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
	    tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
		if (!pskb_trim(skb, 0)) {
			TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
			skb_shinfo(skb)->gso_segs = 1;
			skb_shinfo(skb)->gso_size = 0;
			skb_shinfo(skb)->gso_type = 0;
			skb->ip_summed = CHECKSUM_NONE;
			skb->csum = 0;
		}
	}

	/* 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);

	if (err == 0) {
		/* Update global TCP statistics. */
		TCP_INC_STATS(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++;

		/* 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;
}

/* This gets called after a retransmit timeout, and the initially
 * retransmitted data is acknowledged.  It tries to continue
 * resending the rest of the retransmit queue, until either
 * we've sent it all or the congestion window limit is reached.
 * If doing SACK, the first ACK which comes back for a timeout
 * based retransmit packet might feed us FACK information again.
 * If so, we use it to avoid unnecessarily retransmissions.
 */
void tcp_xmit_retransmit_queue(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int packet_cnt;

	if (tp->retransmit_skb_hint) {
		skb = tp->retransmit_skb_hint;
		packet_cnt = tp->retransmit_cnt_hint;
	}else{
		skb = tcp_write_queue_head(sk);
		packet_cnt = 0;
	}

	/* First pass: retransmit lost packets. */
	if (tp->lost_out) {
		tcp_for_write_queue_from(skb, sk) {
			__u8 sacked = TCP_SKB_CB(skb)->sacked;

			if (skb == tcp_send_head(sk))
				break;
			/* we could do better than to assign each time */
			tp->retransmit_skb_hint = skb;
			tp->retransmit_cnt_hint = packet_cnt;

			/* Assume this retransmit will generate
			 * only one packet for congestion window
			 * calculation purposes.  This works because
			 * tcp_retransmit_skb() will chop up the
			 * packet to be MSS sized and all the
			 * packet counting works out.
			 */
			if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
				return;

			if (sacked & TCPCB_LOST) {
				if (!(sacked&(TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) {
					if (tcp_retransmit_skb(sk, skb)) {
						tp->retransmit_skb_hint = NULL;
						return;
					}
					if (icsk->icsk_ca_state != TCP_CA_Loss)
						NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS);
					else
						NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS);

					if (skb == tcp_write_queue_head(sk))
						inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
									  inet_csk(sk)->icsk_rto,
									  TCP_RTO_MAX);
				}

				packet_cnt += tcp_skb_pcount(skb);
				if (packet_cnt >= tp->lost_out)
					break;
			}
		}
	}

	/* OK, demanded retransmission is finished. */

	/* Forward retransmissions are possible only during Recovery. */
	if (icsk->icsk_ca_state != TCP_CA_Recovery)
		return;

	/* No forward retransmissions in Reno are possible. */
	if (tcp_is_reno(tp))
		return;

	/* Yeah, we have to make difficult choice between forward transmission
	 * and retransmission... Both ways have their merits...
	 *
	 * For now we do not retransmit anything, while we have some new
	 * segments to send. In the other cases, follow rule 3 for
	 * NextSeg() specified in RFC3517.
	 */

	if (tcp_may_send_now(sk))
		return;

	/* If nothing is SACKed, highest_sack in the loop won't be valid */
	if (!tp->sacked_out)
		return;

	if (tp->forward_skb_hint)
		skb = tp->forward_skb_hint;
	else
		skb = tcp_write_queue_head(sk);

	tcp_for_write_queue_from(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		tp->forward_skb_hint = skb;

		if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack))
			break;

		if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
			break;

		if (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS)
			continue;

		/* Ok, retransmit it. */
		if (tcp_retransmit_skb(sk, skb)) {
			tp->forward_skb_hint = NULL;
			break;
		}

		if (skb == tcp_write_queue_head(sk))
			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
						  inet_csk(sk)->icsk_rto,
						  TCP_RTO_MAX);

		NET_INC_STATS_BH(LINUX_MIB_TCPFORWARDRETRANS);
	}
}


/* Send a fin.  The caller locks the socket for us.  This cannot be
 * allowed to fail queueing a FIN frame under any circumstances.
 */
void tcp_send_fin(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = tcp_write_queue_tail(sk);
	int mss_now;

	/* Optimization, tack on the FIN if we have a queue of
	 * unsent frames.  But be careful about outgoing SACKS
	 * and IP options.
	 */
	mss_now = tcp_current_mss(sk, 1);

	if (tcp_send_head(sk) != NULL) {
		TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN;
		TCP_SKB_CB(skb)->end_seq++;
		tp->write_seq++;
	} else {
		/* Socket is locked, keep trying until memory is available. */
		for (;;) {
			skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
			if (skb)
				break;
			yield();
		}

		/* Reserve space for headers and prepare control bits. */
		skb_reserve(skb, MAX_TCP_HEADER);
		skb->csum = 0;
		TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
		TCP_SKB_CB(skb)->sacked = 0;
		skb_shinfo(skb)->gso_segs = 1;
		skb_shinfo(skb)->gso_size = 0;
		skb_shinfo(skb)->gso_type = 0;

		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
		TCP_SKB_CB(skb)->seq = tp->write_seq;
		TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
		tcp_queue_skb(sk, skb);
	}
	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
}

/* We get here when a process closes a file descriptor (either due to
 * an explicit close() or as a byproduct of exit()'ing) and there
 * was unread data in the receive queue.  This behavior is recommended
 * by RFC 2525, section 2.17.  -DaveM
 */
void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
	struct sk_buff *skb;

	/* NOTE: No TCP options attached and we never retransmit this. */
	skb = alloc_skb(MAX_TCP_HEADER, priority);
	if (!skb) {
		NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
		return;
	}

	/* Reserve space for headers and prepare control bits. */
	skb_reserve(skb, MAX_TCP_HEADER);
	skb->csum = 0;
	TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
	TCP_SKB_CB(skb)->sacked = 0;
	skb_shinfo(skb)->gso_segs = 1;
	skb_shinfo(skb)->gso_size = 0;
	skb_shinfo(skb)->gso_type = 0;

	/* Send it off. */
	TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk);
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq;
	TCP_SKB_CB(skb)->when = tcp_time_stamp;
	if (tcp_transmit_skb(sk, skb, 0, priority))
		NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
}

/* WARNING: This routine must only be called when we have already sent
 * a SYN packet that crossed the incoming SYN that caused this routine
 * to get called. If this assumption fails then the initial rcv_wnd
 * and rcv_wscale values will not be correct.
 */
int tcp_send_synack(struct sock *sk)
{
	struct sk_buff* skb;

	skb = tcp_write_queue_head(sk);
	if (skb == NULL || !(TCP_SKB_CB(skb)->flags&TCPCB_FLAG_SYN)) {
		printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n");
		return -EFAULT;
	}
	if (!(TCP_SKB_CB(skb)->flags&TCPCB_FLAG_ACK)) {
		if (skb_cloned(skb)) {
			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
			if (nskb == NULL)
				return -ENOMEM;
			tcp_unlink_write_queue(skb, sk);
			skb_header_release(nskb);
			__tcp_add_write_queue_head(sk, nskb);
			sk_stream_free_skb(sk, skb);
			sk_charge_skb(sk, nskb);
			skb = nskb;
		}

		TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ACK;
		TCP_ECN_send_synack(tcp_sk(sk), skb);
	}
	TCP_SKB_CB(skb)->when = tcp_time_stamp;
	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}

/*
 * Prepare a SYN-ACK.
 */
struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
				 struct request_sock *req)
{
	struct inet_request_sock *ireq = inet_rsk(req);
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcphdr *th;
	int tcp_header_size;
	struct sk_buff *skb;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *md5;
	__u8 *md5_hash_location;
#endif

	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
	if (skb == NULL)
		return NULL;

	/* Reserve space for headers. */
	skb_reserve(skb, MAX_TCP_HEADER);

	skb->dst = dst_clone(dst);

	tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
			   (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
			   (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
			   /* SACK_PERM is in the place of NOP NOP of TS */
			   ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));

#ifdef CONFIG_TCP_MD5SIG
	/* Are we doing MD5 on this segment? If so - make room for it */
	md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
	if (md5)
		tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif
	skb_push(skb, tcp_header_size);
	skb_reset_transport_header(skb);

	th = tcp_hdr(skb);
	memset(th, 0, sizeof(struct tcphdr));
	th->syn = 1;
	th->ack = 1;
	TCP_ECN_make_synack(req, th);
	th->source = inet_sk(sk)->sport;
	th->dest = ireq->rmt_port;
	TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
	TCP_SKB_CB(skb)->sacked = 0;
	skb_shinfo(skb)->gso_segs = 1;
	skb_shinfo(skb)->gso_size = 0;
	skb_shinfo(skb)->gso_type = 0;
	th->seq = htonl(TCP_SKB_CB(skb)->seq);
	th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
	if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
		__u8 rcv_wscale;
		/* Set this up on the first call only */
		req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
		/* tcp_full_space because it is guaranteed to be the first packet */
		tcp_select_initial_window(tcp_full_space(sk),
			dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
			&req->rcv_wnd,
			&req->window_clamp,
			ireq->wscale_ok,
			&rcv_wscale);
		ireq->rcv_wscale = rcv_wscale;
	}

	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
	th->window = htons(min(req->rcv_wnd, 65535U));

	TCP_SKB_CB(skb)->when = tcp_time_stamp;
	tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
			      ireq->sack_ok, ireq->wscale_ok, ireq->