tcp_output.c

	mtu = mss +
	      tp->tcp_header_len +
	      icsk->icsk_ext_hdr_len +
	      icsk->icsk_af_ops->net_header_len;

	return mtu;
}

/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1;
	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
			       icsk->icsk_af_ops->net_header_len;
	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
	icsk->icsk_mtup.probe_size = 0;
}

/* This function synchronize snd mss to current pmtu/exthdr set.

   tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
   for TCP options, but includes only bare TCP header.

   tp->rx_opt.mss_clamp is mss negotiated at connection setup.
   It is minimum of user_mss and mss received with SYN.
   It also does not include TCP options.

   inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function.

   tp->mss_cache is current effective sending mss, including
   all tcp options except for SACKs. It is evaluated,
   taking into account current pmtu, but never exceeds
   tp->rx_opt.mss_clamp.

   NOTE1. rfc1122 clearly states that advertised MSS
   DOES NOT include either tcp or ip options.

   NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache
   are READ ONLY outside this function.		--ANK (980731)
 */
unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	int mss_now;

	if (icsk->icsk_mtup.search_high > pmtu)
		icsk->icsk_mtup.search_high = pmtu;

	mss_now = tcp_mtu_to_mss(sk, pmtu);
	mss_now = tcp_bound_to_half_wnd(tp, mss_now);

	/* And store cached results */
	icsk->icsk_pmtu_cookie = pmtu;
	if (icsk->icsk_mtup.enabled)
		mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low));
	tp->mss_cache = mss_now;

	return mss_now;
}

/* Compute the current effective MSS, taking SACKs and IP options,
 * and even PMTU discovery events into account.
 */
unsigned int tcp_current_mss(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);
	u32 mss_now;
	unsigned header_len;
	struct tcp_out_options opts;
	struct tcp_md5sig_key *md5;

	mss_now = tp->mss_cache;

	if (dst) {
		u32 mtu = dst_mtu(dst);
		if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
			mss_now = tcp_sync_mss(sk, mtu);
	}

	header_len = tcp_established_options(sk, NULL, &opts, &md5) +
		     sizeof(struct tcphdr);
	/* The mss_cache is sized based on tp->tcp_header_len, which assumes
	 * some common options. If this is an odd packet (because we have SACK
	 * blocks etc) then our calculated header_len will be different, and
	 * we have to adjust mss_now correspondingly */
	if (header_len != tp->tcp_header_len) {
		int delta = (int) header_len - tp->tcp_header_len;
		mss_now -= delta;
	}

	return mss_now;
}

/* Congestion window validation. (RFC2861) */
static void tcp_cwnd_validate(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->packets_out >= tp->snd_cwnd) {
		/* Network is feed fully. */
		tp->snd_cwnd_used = 0;
		tp->snd_cwnd_stamp = tcp_time_stamp;
	} else {
		/* Network starves. */
		if (tp->packets_out > tp->snd_cwnd_used)
			tp->snd_cwnd_used = tp->packets_out;

		if (sysctl_tcp_slow_start_after_idle &&
		    (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
			tcp_cwnd_application_limited(sk);
	}
}

/* Returns the portion of skb which can be sent right away without
 * introducing MSS oddities to segment boundaries. In rare cases where
 * mss_now != mss_cache, we will request caller to create a small skb
 * per input skb which could be mostly avoided here (if desired).
 *
 * We explicitly want to create a request for splitting write queue tail
 * to a small skb for Nagle purposes while avoiding unnecessary modulos,
 * thus all the complexity (cwnd_len is always MSS multiple which we
 * return whenever allowed by the other factors). Basically we need the
 * modulo only when the receiver window alone is the limiting factor or
 * when we would be allowed to send the split-due-to-Nagle skb fully.
 */
static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb,
					unsigned int mss_now, unsigned int cwnd)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 needed, window, cwnd_len;

	window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
	cwnd_len = mss_now * cwnd;

	if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk)))
		return cwnd_len;

	needed = min(skb->len, window);

	if (cwnd_len <= needed)
		return cwnd_len;

	return needed - needed % mss_now;
}

/* Can at least one segment of SKB be sent right now, according to the
 * congestion window rules?  If so, return how many segments are allowed.
 */
static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp,
					 struct sk_buff *skb)
{
	u32 in_flight, cwnd;

	/* Don't be strict about the congestion window for the final FIN.  */
	if ((TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
	    tcp_skb_pcount(skb) == 1)
		return 1;

	in_flight = tcp_packets_in_flight(tp);
	cwnd = tp->snd_cwnd;
	if (in_flight < cwnd)
		return (cwnd - in_flight);

	return 0;
}

/* Intialize TSO state of a skb.
 * This must be invoked the first time we consider transmitting
 * SKB onto the wire.
 */
static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
			     unsigned int mss_now)
{
	int tso_segs = tcp_skb_pcount(skb);

	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
		tcp_set_skb_tso_segs(sk, skb, mss_now);
		tso_segs = tcp_skb_pcount(skb);
	}
	return tso_segs;
}

/* Minshall's variant of the Nagle send check. */
static inline int tcp_minshall_check(const struct tcp_sock *tp)
{
	return after(tp->snd_sml, tp->snd_una) &&
		!after(tp->snd_sml, tp->snd_nxt);
}

/* Return 0, if packet can be sent now without violation Nagle's rules:
 * 1. It is full sized.
 * 2. Or it contains FIN. (already checked by caller)
 * 3. Or TCP_NODELAY was set.
 * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
 *    With Minshall's modification: all sent small packets are ACKed.
 */
static inline int tcp_nagle_check(const struct tcp_sock *tp,
				  const struct sk_buff *skb,
				  unsigned mss_now, int nonagle)
{
	return (skb->len < mss_now &&
		((nonagle & TCP_NAGLE_CORK) ||
		 (!nonagle && tp->packets_out && tcp_minshall_check(tp))));
}

/* Return non-zero if the Nagle test allows this packet to be
 * sent now.
 */
static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
				 unsigned int cur_mss, int nonagle)
{
	/* Nagle rule does not apply to frames, which sit in the middle of the
	 * write_queue (they have no chances to get new data).
	 *
	 * This is implemented in the callers, where they modify the 'nonagle'
	 * argument based upon the location of SKB in the send queue.
	 */
	if (nonagle & TCP_NAGLE_PUSH)
		return 1;

	/* Don't use the nagle rule for urgent data (or for the final FIN).
	 * Nagle can be ignored during F-RTO too (see RFC4138).
	 */
	if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
	    (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
		return 1;

	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
		return 1;

	return 0;
}

/* Does at least the first segment of SKB fit into the send window? */
static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb,
				   unsigned int cur_mss)
{
	u32 end_seq = TCP_SKB_CB(skb)->end_seq;

	if (skb->len > cur_mss)
		end_seq = TCP_SKB_CB(skb)->seq + cur_mss;

	return !after(end_seq, tcp_wnd_end(tp));
}

/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
 * should be put on the wire right now.  If so, it returns the number of
 * packets allowed by the congestion window.
 */
static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
				 unsigned int cur_mss, int nonagle)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int cwnd_quota;

	tcp_init_tso_segs(sk, skb, cur_mss);

	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
		return 0;

	cwnd_quota = tcp_cwnd_test(tp, skb);
	if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
		cwnd_quota = 0;

	return cwnd_quota;
}

/* Test if sending is allowed right now. */
int tcp_may_send_now(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = tcp_send_head(sk);

	return (skb &&
		tcp_snd_test(sk, skb, tcp_current_mss(sk),
			     (tcp_skb_is_last(sk, skb) ?
			      tp->nonagle : TCP_NAGLE_PUSH)));
}

/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
 * which is put after SKB on the list.  It is very much like
 * tcp_fragment() except that it may make several kinds of assumptions
 * in order to speed up the splitting operation.  In particular, we
 * know that all the data is in scatter-gather pages, and that the
 * packet has never been sent out before (and thus is not cloned).
 */
static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
			unsigned int mss_now)
{
	struct sk_buff *buff;
	int nlen = skb->len - len;
	u8 flags;

	/* All of a TSO frame must be composed of paged data.  */
	if (skb->len != skb->data_len)
		return tcp_fragment(sk, skb, len, mss_now);

	buff = sk_stream_alloc_skb(sk, 0, GFP_ATOMIC);
	if (unlikely(buff == NULL))
		return -ENOMEM;

	sk->sk_wmem_queued += buff->truesize;
	sk_mem_charge(sk, buff->truesize);
	buff->truesize += nlen;
	skb->truesize -= nlen;

	/* Correct the sequence numbers. */
	TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;

	/* PSH and FIN should only be set in the second packet. */
	flags = TCP_SKB_CB(skb)->flags;
	TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN | TCPCB_FLAG_PSH);
	TCP_SKB_CB(buff)->flags = flags;

	/* This packet was never sent out yet, so no SACK bits. */
	TCP_SKB_CB(buff)->sacked = 0;

	buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
	skb_split(skb, buff, len);

	/* Fix up tso_factor for both original and new SKB.  */
	tcp_set_skb_tso_segs(sk, skb, mss_now);
	tcp_set_skb_tso_segs(sk, buff, mss_now);

	/* Link BUFF into the send queue. */
	skb_header_release(buff);
	tcp_insert_write_queue_after(skb, buff, sk);

	return 0;
}

/* Try to defer sending, if possible, in order to minimize the amount
 * of TSO splitting we do.  View it as a kind of TSO Nagle test.
 *
 * This algorithm is from John Heffner.
 */
static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	u32 send_win, cong_win, limit, in_flight;

	if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
		goto send_now;

	if (icsk->icsk_ca_state != TCP_CA_Open)
		goto send_now;

	/* Defer for less than two clock ticks. */
	if (tp->tso_deferred &&
	    (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
		goto send_now;

	in_flight = tcp_packets_in_flight(tp);

	BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight));

	send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;

	/* From in_flight test above, we know that cwnd > in_flight.  */
	cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;

	limit = min(send_win, cong_win);

	/* If a full-sized TSO skb can be sent, do it. */
	if (limit >= sk->sk_gso_max_size)
		goto send_now;

	/* Middle in queue won't get any more data, full sendable already? */
	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
		goto send_now;

	if (sysctl_tcp_tso_win_divisor) {
		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);

		/* If at least some fraction of a window is available,
		 * just use it.
		 */
		chunk /= sysctl_tcp_tso_win_divisor;
		if (limit >= chunk)
			goto send_now;
	} else {
		/* Different approach, try not to defer past a single
		 * ACK.  Receiver should ACK every other full sized
		 * frame, so if we have space for more than 3 frames
		 * then send now.
		 */
		if (limit > tcp_max_burst(tp) * tp->mss_cache)
			goto send_now;
	}

	/* Ok, it looks like it is advisable to defer.  */
	tp->tso_deferred = 1 | (jiffies << 1);

	return 1;

send_now:
	tp->tso_deferred = 0;
	return 0;
}

/* Create a new MTU probe if we are ready.
 * MTU probe is regularly attempting to increase the path MTU by
 * deliberately sending larger packets.  This discovers routing
 * changes resulting in larger path MTUs.
 *
 * Returns 0 if we should wait to probe (no cwnd available),
 *         1 if a probe was sent,
 *         -1 otherwise
 */
static int tcp_mtu_probe(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sk_buff *skb, *nskb, *next;
	int len;
	int probe_size;
	int size_needed;
	int copy;
	int mss_now;

	/* Not currently probing/verifying,
	 * not in recovery,
	 * have enough cwnd, and
	 * not SACKing (the variable headers throw things off) */
	if (!icsk->icsk_mtup.enabled ||
	    icsk->icsk_mtup.probe_size ||
	    inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
	    tp->snd_cwnd < 11 ||
	    tp->rx_opt.num_sacks || tp->rx_opt.dsack)
		return -1;

	/* Very simple search strategy: just double the MSS. */
	mss_now = tcp_current_mss(sk);
	probe_size = 2 * tp->mss_cache;
	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
		/* TODO: set timer for probe_converge_event */
		return -1;
	}

	/* Have enough data in the send queue to probe? */
	if (tp->write_seq - tp->snd_nxt < size_needed)
		return -1;

	if (tp->snd_wnd < size_needed)
		return -1;
	if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp)))
		return 0;

	/* Do we need to wait to drain cwnd? With none in flight, don't stall */
	if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) {
		if (!tcp_packets_in_flight(tp))
			return -1;
		else
			return 0;
	}

	/* We're allowed to probe.  Build it now. */
	if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
		return -1;
	sk->sk_wmem_queued += nskb->truesize;
	sk_mem_charge(sk, nskb->truesize);

	skb = tcp_send_head(sk);

	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
	TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK;
	TCP_SKB_CB(nskb)->sacked = 0;
	nskb->csum = 0;
	nskb->ip_summed = skb->ip_summed;

	tcp_insert_write_queue_before(nskb, skb, sk);

	len = 0;
	tcp_for_write_queue_from_safe(skb, next, sk) {
		copy = min_t(int, skb->len, probe_size - len);
		if (nskb->ip_summed)
			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
		else
			nskb->csum = skb_copy_and_csum_bits(skb, 0,
							    skb_put(nskb, copy),
							    copy, nskb->csum);

		if (skb->len <= copy) {
			/* We've eaten all the data from this skb.
			 * Throw it away. */
			TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags;
			tcp_unlink_write_queue(skb, sk);
			sk_wmem_free_skb(sk, skb);
		} else {
			TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
						   ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
			if (!skb_shinfo(skb)->nr_frags) {
				skb_pull(skb, copy);
				if (skb->ip_summed != CHECKSUM_PARTIAL)
					skb->csum = csum_partial(skb->data,
								 skb->len, 0);
			} else {
				__pskb_trim_head(skb, copy);
				tcp_set_skb_tso_segs(sk, skb, mss_now);
			}
			TCP_SKB_CB(skb)->seq += copy;
		}

		len += copy;

		if (len >= probe_size)
			break;
	}
	tcp_init_tso_segs(sk, nskb, nskb->len);

	/* We're ready to send.  If this fails, the probe will
	 * be resegmented into mss-sized pieces by tcp_write_xmit(). */
	TCP_SKB_CB(nskb)->when = tcp_time_stamp;
	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
		/* Decrement cwnd here because we are sending
		 * effectively two packets. */
		tp->snd_cwnd--;
		tcp_event_new_data_sent(sk, nskb);

		icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
		tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
		tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq;

		return 1;
	}

	return -1;
}

/* This routine writes packets to the network.  It advances the
 * send_head.  This happens as incoming acks open up the remote
 * window for us.
 *
 * LARGESEND note: !tcp_urg_mode is overkill, only frames between
 * snd_up-64k-mss .. snd_up cannot be large. However, taking into
 * account rare use of URG, this is not a big flaw.
 *
 * Returns 1, if no segments are in flight and we have queued segments, but
 * cannot send anything now because of SWS or another problem.
 */
static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
			  int push_one, gfp_t gfp)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int tso_segs, sent_pkts;
	int cwnd_quota;
	int result;

	sent_pkts = 0;

	if (!push_one) {
		/* Do MTU probing. */
		result = tcp_mtu_probe(sk);
		if (!result) {
			return 0;
		} else if (result > 0) {
			sent_pkts = 1;
		}
	}

	while ((skb = tcp_send_head(sk))) {
		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 (!push_one && tcp_tso_should_defer(sk, skb))
				break;
		}

		limit = mss_now;
		if (tso_segs > 1 && !tcp_urg_mode(tp))
			limit = tcp_mss_split_point(sk, skb, mss_now,
						    cwnd_quota);

		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)))
			break;

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

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

		if (push_one)
			break;
	}

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

/* 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, unsigned int cur_mss,
			       int nonagle)
{
	struct sk_buff *skb = tcp_send_head(sk);

	if (!skb)
		return;

	/* 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;

	if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC))
		tcp_check_probe_timer(sk);
}

/* 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 sk_buff *skb = tcp_send_head(sk);

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

	tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation);
}

/* 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 >> 1)) {
		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;
		else if (mss == full_space &&
			 free_space > window + (full_space >> 1))
			window = free_space;
	}

	return window;
}

/* Collapses two adjacent SKB's during retransmission. */
static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
	int skb_size, next_skb_size;

	skb_size = skb->len;
	next_skb_size = next_skb->len;

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

	tcp_highest_sack_combine(sk, next_skb, skb);

	tcp_unlink_write_queue(next_skb, sk);

	skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size),
				  next_skb_size);

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

	if (skb->ip_summed != CHECKSUM_PARTIAL)
		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. This moves PSH/FIN etc. over */
	TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(next_skb)->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;

	/* changed transmit queue under us so clear hints */
	tcp_clear_retrans_hints_partial(tp);
	if (next_skb == tp->retransmit_skb_hint)
		tp->retransmit_skb_hint = skb;

	tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));

	sk_wmem_free_skb(sk, next_skb);
}

/* Check if coalescing SKBs is legal. */
static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
{
	if (tcp_skb_pcount(skb) > 1)
		return 0;
	/* TODO: SACK collapsing could be used to remove this condition */
	if (skb_shinfo(skb)->nr_frags != 0)
		return 0;
	if (skb_cloned(skb))
		return 0;
	if (skb == tcp_send_head(sk))
		return 0;
	/* Some heurestics for collapsing over SACK'd could be invented */
	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
		return 0;

	return 1;
}

/* Collapse packets in the retransmit queue to make to create
 * less packets on the wire. This is only done on retransmission.
 */
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
				     int space)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = to, *tmp;
	int first = 1;

	if (!sysctl_tcp_retrans_collapse)
		return;
	if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)
		return;

	tcp_for_write_queue_from_safe(skb, tmp, sk) {
		if (!tcp_can_collapse(sk, skb))
			break;

		space -= skb->len;

		if (first) {
			first = 0;
			continue;
		}

		if (space < 0)
			break;
		/* Punt if not enough space exists in the first SKB for
		 * the data in the second
		 */
		if (skb->len > skb_tailroom(to))
			break;

		if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))
			break;

		tcp_collapse_retrans(sk, to);
	}
}

/* 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.
	 */
	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 (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.
	 */
	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) {
		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.
	 */
	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)) {
			/* 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);

	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++;

		/* 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;
}

/* Check if we forward retransmits are possible in the current
 * window/congestion state.
 */
static int tcp_can_forward_retransmit(struct sock *sk)