tcp_output.c

{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int tso_segs, sent_pkts;
	int cwnd_quota;

	/* If we are closed, the bytes will have to remain here.
	 * In time closedown will finish, we empty the write queue and all
	 * will be happy.
	 */
	if (unlikely(sk->sk_state == TCP_CLOSE))
		return 0;

	sent_pkts = 0;
	while ((skb = sk->sk_send_head)) {
		unsigned int limit;

		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
		BUG_ON(!tso_segs);

		cwnd_quota = tcp_cwnd_test(tp, skb);
		if (!cwnd_quota)
			break;

		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
			break;

		if (tso_segs == 1) {
			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
						     (tcp_skb_is_last(sk, skb) ?
						      nonagle : TCP_NAGLE_PUSH))))
				break;
		} else {
			if (tcp_tso_should_defer(sk, tp, skb))
				break;
		}

		limit = mss_now;
		if (tso_segs > 1) {
			limit = tcp_window_allows(tp, skb,
						  mss_now, cwnd_quota);

			if (skb->len < limit) {
				unsigned int trim = skb->len % mss_now;

				if (trim)
					limit = skb->len - trim;
			}
		}

		if (skb->len > limit &&
		    unlikely(tso_fragment(sk, skb, limit, mss_now)))
			break;

		TCP_SKB_CB(skb)->when = tcp_time_stamp;

		if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC)))
			break;

		/* Advance the send_head.  This one is sent out.
		 * This call will increment packets_out.
		 */
		update_send_head(sk, tp, skb);

		tcp_minshall_update(tp, mss_now, skb);
		sent_pkts++;
	}

	if (likely(sent_pkts)) {
		tcp_cwnd_validate(sk, tp);
		return 0;
	}
	return !tp->packets_out && sk->sk_send_head;
}

/* Push out any pending frames which were held back due to
 * TCP_CORK or attempt at coalescing tiny packets.
 * The socket must be locked by the caller.
 */
void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
			       unsigned int cur_mss, int nonagle)
{
	struct sk_buff *skb = sk->sk_send_head;

	if (skb) {
		if (tcp_write_xmit(sk, cur_mss, nonagle))
			tcp_check_probe_timer(sk, tp);
	}
}

/* Send _single_ skb sitting at the send head. This function requires
 * true push pending frames to setup probe timer etc.
 */
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = sk->sk_send_head;
	unsigned int tso_segs, cwnd_quota;

	BUG_ON(!skb || skb->len < mss_now);

	tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
	cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);

	if (likely(cwnd_quota)) {
		unsigned int limit;

		BUG_ON(!tso_segs);

		limit = mss_now;
		if (tso_segs > 1) {
			limit = tcp_window_allows(tp, skb,
						  mss_now, cwnd_quota);

			if (skb->len < limit) {
				unsigned int trim = skb->len % mss_now;

				if (trim)
					limit = skb->len - trim;
			}
		}

		if (skb->len > limit &&
		    unlikely(tso_fragment(sk, skb, limit, mss_now)))
			return;

		/* Send it out now. */
		TCP_SKB_CB(skb)->when = tcp_time_stamp;

		if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
			update_send_head(sk, tp, skb);
			tcp_cwnd_validate(sk, tp);
			return;
		}
	}
}

/* This function returns the amount that we can raise the
 * usable window based on the following constraints
 *  
 * 1. The window can never be shrunk once it is offered (RFC 793)
 * 2. We limit memory per socket
 *
 * RFC 1122:
 * "the suggested [SWS] avoidance algorithm for the receiver is to keep
 *  RECV.NEXT + RCV.WIN fixed until:
 *  RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)"
 *
 * i.e. don't raise the right edge of the window until you can raise
 * it at least MSS bytes.
 *
 * Unfortunately, the recommended algorithm breaks header prediction,
 * since header prediction assumes th->window stays fixed.
 *
 * Strictly speaking, keeping th->window fixed violates the receiver
 * side SWS prevention criteria. The problem is that under this rule
 * a stream of single byte packets will cause the right side of the
 * window to always advance by a single byte.
 * 
 * Of course, if the sender implements sender side SWS prevention
 * then this will not be a problem.
 * 
 * BSD seems to make the following compromise:
 * 
 *	If the free space is less than the 1/4 of the maximum
 *	space available and the free space is less than 1/2 mss,
 *	then set the window to 0.
 *	[ Actually, bsd uses MSS and 1/4 of maximal _window_ ]
 *	Otherwise, just prevent the window from shrinking
 *	and from being larger than the largest representable value.
 *
 * This prevents incremental opening of the window in the regime
 * where TCP is limited by the speed of the reader side taking
 * data out of the TCP receive queue. It does nothing about
 * those cases where the window is constrained on the sender side
 * because the pipeline is full.
 *
 * BSD also seems to "accidentally" limit itself to windows that are a
 * multiple of MSS, at least until the free space gets quite small.
 * This would appear to be a side effect of the mbuf implementation.
 * Combining these two algorithms results in the observed behavior
 * of having a fixed window size at almost all times.
 *
 * Below we obtain similar behavior by forcing the offered window to
 * a multiple of the mss when it is feasible to do so.
 *
 * Note, we don't "adjust" for TIMESTAMP or SACK option bytes.
 * Regular options like TIMESTAMP are taken into account.
 */
u32 __tcp_select_window(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	/* MSS for the peer's data.  Previous versions used mss_clamp
	 * here.  I don't know if the value based on our guesses
	 * of peer's MSS is better for the performance.  It's more correct
	 * but may be worse for the performance because of rcv_mss
	 * fluctuations.  --SAW  1998/11/1
	 */
	int mss = icsk->icsk_ack.rcv_mss;
	int free_space = tcp_space(sk);
	int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
	int window;

	if (mss > full_space)
		mss = full_space; 

	if (free_space < full_space/2) {
		icsk->icsk_ack.quick = 0;

		if (tcp_memory_pressure)
			tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U*tp->advmss);

		if (free_space < mss)
			return 0;
	}

	if (free_space > tp->rcv_ssthresh)
		free_space = tp->rcv_ssthresh;

	/* Don't do rounding if we are using window scaling, since the
	 * scaled window will not line up with the MSS boundary anyway.
	 */
	window = tp->rcv_wnd;
	if (tp->rx_opt.rcv_wscale) {
		window = free_space;

		/* Advertise enough space so that it won't get scaled away.
		 * Import case: prevent zero window announcement if
		 * 1<<rcv_wscale > mss.
		 */
		if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
			window = (((window >> tp->rx_opt.rcv_wscale) + 1)
				  << tp->rx_opt.rcv_wscale);
	} else {
		/* Get the largest window that is a nice multiple of mss.
		 * Window clamp already applied above.
		 * If our current window offering is within 1 mss of the
		 * free space we just keep it. This prevents the divide
		 * and multiply from happening most of the time.
		 * We also don't do any window rounding when the free space
		 * is too small.
		 */
		if (window <= free_space - mss || window > free_space)
			window = (free_space/mss)*mss;
	}

	return window;
}

/* Attempt to collapse two adjacent SKB's during retransmission. */
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *next_skb = skb->next;

	/* The first test we must make is that neither of these two
	 * SKB's are still referenced by someone else.
	 */
	if (!skb_cloned(skb) && !skb_cloned(next_skb)) {
		int skb_size = skb->len, next_skb_size = next_skb->len;
		u16 flags = TCP_SKB_CB(skb)->flags;

		/* Also punt if next skb has been SACK'd. */
		if(TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
			return;

		/* Next skb is out of window. */
		if (after(TCP_SKB_CB(next_skb)->end_seq, tp->snd_una+tp->snd_wnd))
			return;

		/* Punt if not enough space exists in the first SKB for
		 * the data in the second, or the total combined payload
		 * would exceed the MSS.
		 */
		if ((next_skb_size > skb_tailroom(skb)) ||
		    ((skb_size + next_skb_size) > mss_now))
			return;

		BUG_ON(tcp_skb_pcount(skb) != 1 ||
		       tcp_skb_pcount(next_skb) != 1);

		/* changing transmit queue under us so clear hints */
		clear_all_retrans_hints(tp);

		/* Ok.	We will be able to collapse the packet. */
		__skb_unlink(next_skb, &sk->sk_write_queue);

		memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size);

		if (next_skb->ip_summed == CHECKSUM_HW)
			skb->ip_summed = CHECKSUM_HW;

		if (skb->ip_summed != CHECKSUM_HW)
			skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);

		/* Update sequence range on original skb. */
		TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;

		/* Merge over control information. */
		flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
		TCP_SKB_CB(skb)->flags = flags;

		/* All done, get rid of second SKB and account for it so
		 * packet counting does not break.
		 */
		TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked&(TCPCB_EVER_RETRANS|TCPCB_AT_TAIL);
		if (TCP_SKB_CB(next_skb)->sacked&TCPCB_SACKED_RETRANS)
			tp->retrans_out -= tcp_skb_pcount(next_skb);
		if (TCP_SKB_CB(next_skb)->sacked&TCPCB_LOST) {
			tp->lost_out -= tcp_skb_pcount(next_skb);
			tp->left_out -= tcp_skb_pcount(next_skb);
		}
		/* Reno case is special. Sigh... */
		if (!tp->rx_opt.sack_ok && tp->sacked_out) {
			tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
			tp->left_out -= tcp_skb_pcount(next_skb);
		}

		/* Not quite right: it can be > snd.fack, but
		 * it is better to underestimate fackets.
		 */
		tcp_dec_pcount_approx(&tp->fackets_out, next_skb);
		tcp_packets_out_dec(tp, next_skb);
		sk_stream_free_skb(sk, next_skb);
	}
}

/* Do a simple retransmit without using the backoff mechanisms in
 * tcp_timer. This is used for path mtu discovery. 
 * The socket is already locked here.
 */ 
void tcp_simple_retransmit(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int mss = tcp_current_mss(sk, 0);
	int lost = 0;

	sk_stream_for_retrans_queue(skb, sk) {
		if (skb->len > mss && 
		    !(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
			if (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);
			}
			if (!(TCP_SKB_CB(skb)->sacked&TCPCB_LOST)) {
				TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
				tp->lost_out += tcp_skb_pcount(skb);
				lost = 1;
			}
		}
	}

	clear_all_retrans_hints(tp);

	if (!lost)
		return;

	tcp_sync_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);
 	unsigned int cur_mss = tcp_current_mss(sk, 0);
	int err;

	/* 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)) &&
	   (skb->next != sk->sk_send_head) &&
	   (skb->next != (struct sk_buff *)&sk->sk_write_queue) &&
	   (skb_shinfo(skb)->nr_frags == 0 && skb_shinfo(skb->next)->nr_frags == 0) &&
	   (tcp_skb_pcount(skb) == 1 && tcp_skb_pcount(skb->next) == 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)->tso_segs = 1;
			skb_shinfo(skb)->tso_size = 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
		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 = sk->sk_write_queue.next;
		packet_cnt = 0;
	}

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

			/* 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 ==
					    skb_peek(&sk->sk_write_queue))
						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 (!tp->rx_opt.sack_ok)
		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.
	 */

	if (tcp_may_send_now(sk, tp))
		return;

	if (tp->forward_skb_hint) {
		skb = tp->forward_skb_hint;
		packet_cnt = tp->forward_cnt_hint;
	} else{
		skb = sk->sk_write_queue.next;
		packet_cnt = 0;
	}

	sk_stream_for_retrans_queue_from(skb, sk) {
		tp->forward_cnt_hint = packet_cnt;
		tp->forward_skb_hint = skb;

		/* Similar to the retransmit loop above we
		 * can pretend that the retransmitted SKB
		 * we send out here will be composed of one
		 * real MSS sized packet because tcp_retransmit_skb()
		 * will fragment it if necessary.
		 */
		if (++packet_cnt > tp->fackets_out)
			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 == skb_peek(&sk->sk_write_queue))
			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 = skb_peek_tail(&sk->sk_write_queue);
	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 (sk->sk_send_head != 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)->tso_segs = 1;
		skb_shinfo(skb)->tso_size = 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, tp, 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 draft-ietf-tcpimpl-prob-03.txt section 3.10.  -DaveM
 */
void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
	struct tcp_sock *tp = tcp_sk(sk);
	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)->tso_segs = 1;
	skb_shinfo(skb)->tso_size = 0;

	/* Send it off. */
	TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
	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 = skb_peek(&sk->sk_write_queue);
	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;
			__skb_unlink(skb, &sk->sk_write_queue);
			skb_header_release(nskb);
			__skb_queue_head(&sk->sk_write_queue, 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;

	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));
	skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size);

	memset(th, 0, sizeof(struct tcphdr));
	th->syn = 1;
	th->ack = 1;
	if (dst->dev->features&NETIF_F_TSO)
		ireq->ecn_ok = 0;
	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)->tso_segs = 1;
	skb_shinfo(skb)->tso_size = 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(req->rcv_wnd);

	TCP_SKB_CB(skb)->when = tcp_time_stamp;
	tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
			      ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
			      TCP_SKB_CB(skb)->when,
			      req->ts_recent);

	skb->csum = 0;
	th->doff = (tcp_header_size >> 2);
	TCP_INC_STATS(TCP_MIB_OUTSEGS);
	return skb;
}

/* 
 * Do all connect socket setups that can be done AF independent.
 */ 
static inline void tcp_connect_init(struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_get(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	__u8 rcv_wscale;

	/* We'll fix this up when we get a response from the other end.
	 * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
	 */
	tp->tcp_header_len = sizeof(struct tcphdr) +
		(sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);

	/* If user gave his TCP_MAXSEG, record it to clamp */
	if (tp->rx_opt.user_mss)
		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
	tp->max_window = 0;
	tcp_sync_mss(sk, dst_mtu(dst));

	if (!tp->window_clamp)
		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
	tp->advmss = dst_metric(dst, RTAX_ADVMSS);
	tcp_initialize_rcv_mss(sk);

	tcp_select_initial_window(tcp_full_space(sk),
				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
				  &tp->rcv_wnd,
				  &tp->window_clamp,
				  sysctl_tcp_window_scaling,
				  &rcv_wscale);

	tp->rx_opt.rcv_wscale = rcv_wscale;
	tp->rcv_ssthresh = tp->rcv_wnd;

	sk->sk_err = 0;
	sock_reset_flag(sk, SOCK_DONE);
	tp->snd_wnd = 0;
	tcp_init_wl(tp, tp->write_seq, 0);
	tp->snd_una = tp->write_seq;
	tp->snd_sml = tp->write_seq;
	tp->rcv_nxt = 0;
	tp->rcv_wup = 0;
	tp->copied_seq = 0;

	inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
	inet_csk(sk)->icsk_retransmits = 0;
	tcp_clear_retrans(tp);
}

/*
 * Build a SYN and send it off.
 */ 
int tcp_connect(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *buff;

	tcp_connect_init(sk);

	buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
	if (unlikely(buff == NULL))
		return -ENOBUFS;

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

	TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
	TCP_ECN_send_syn(sk, tp, buff);
	TCP_SKB_CB(buff)->sacked = 0;
	skb_shinfo(buff)->tso_segs = 1;
	skb_shinfo(buff)->tso_size = 0;
	buff->csum = 0;
	TCP_SKB_CB(buff)->seq = tp->write_seq++;
	TCP_SKB_CB(buff)->end_seq = tp->write_seq;
	tp->snd_nxt = tp->write_seq;
	tp->pushed_seq = tp->write_seq;

	/* Send it off. */
	TCP_SKB_CB(buff)->when = tcp_time_stamp;
	tp->retrans_stamp = TCP_SKB_CB(buff)->when;
	skb_header_release(buff);
	__skb_queue_tail(&sk->sk_write_queue, buff);
	sk_charge_skb(sk, buff);
	tp->packets_out += tcp_skb_pcount(buff);
	tcp_transmit_skb(sk, buff, 1, GFP_KERNEL);
	TCP_INC_STATS(TCP_MIB_ACTIVEOPENS);

	/* Timer for repeating the SYN until an answer. */
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
				  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
	return 0;
}

/* Send out a delayed ack, the caller does the policy checking
 * to see if we should even be here.  See tcp_input.c:tcp_ack_snd_check()
 * for details.
 */
void tcp_send_delayed_ack(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	int ato = icsk->icsk_ack.ato;
	unsigned long timeout;

	if (ato > TCP_DELACK_MIN) {
		const struct tcp_sock *tp = tcp_sk(sk);
		int max_ato = HZ/2;

		if (icsk->icsk_ack.pingpong || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED))
			max_ato = TCP_DELACK_MAX;

		/* 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)
{
	/* If we have been reset, we may not send again. */
	if (sk->sk_state != TCP_CLOSE) {
		struct tcp_sock *tp = tcp_sk(sk);
		struct sk_buff *buff;

		/* 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, 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);
		buff->csum = 0;
		TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
		TCP_SKB_CB(buff)->sacked = 0;
		skb_shinfo(buff)->tso_segs = 1;
		skb_shinfo(buff)->tso_size = 0;

		/* Send it off, this clears delayed acks for us. */
		TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp);
		TCP_SKB_CB(buff)->when = tcp_time_stamp;
		tcp_transmit_skb(sk, buff, 0, 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, GFP_ATOMIC);
	if (skb == NULL) 
		return -1;