tcp_input.c

						reord = min(fack_count, reord);
				}

				/* Nothing to do; acked frame is about to be dropped. */
				continue;
			}

			if ((sacked&TCPCB_SACKED_RETRANS) &&
			    after(end_seq, TCP_SKB_CB(skb)->ack_seq) &&
			    (!lost_retrans || after(end_seq, lost_retrans)))
				lost_retrans = end_seq;

			if (!in_sack)
				continue;

			if (!(sacked&TCPCB_SACKED_ACKED)) {
				if (sacked & TCPCB_SACKED_RETRANS) {
					/* If the segment is not tagged as lost,
					 * we do not clear RETRANS, believing
					 * that retransmission is still in flight.
					 */
					if (sacked & TCPCB_LOST) {
						TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
						tp->lost_out -= tcp_skb_pcount(skb);
						tp->retrans_out -= tcp_skb_pcount(skb);
					}
				} else {
					/* New sack for not retransmitted frame,
					 * which was in hole. It is reordering.
					 */
					if (!(sacked & TCPCB_RETRANS) &&
					    fack_count < prior_fackets)
						reord = min(fack_count, reord);

					if (sacked & TCPCB_LOST) {
						TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
						tp->lost_out -= tcp_skb_pcount(skb);
					}
				}

				TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
				flag |= FLAG_DATA_SACKED;
				tp->sacked_out += tcp_skb_pcount(skb);

				if (fack_count > tp->fackets_out)
					tp->fackets_out = fack_count;
			} else {
				if (dup_sack && (sacked&TCPCB_RETRANS))
					reord = min(fack_count, reord);
			}

			/* D-SACK. We can detect redundant retransmission
			 * in S|R and plain R frames and clear it.
			 * undo_retrans is decreased above, L|R frames
			 * are accounted above as well.
			 */
			if (dup_sack &&
			    (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS)) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);
			}
		}
	}

	/* Check for lost retransmit. This superb idea is
	 * borrowed from "ratehalving". Event "C".
	 * Later note: FACK people cheated me again 8),
	 * we have to account for reordering! Ugly,
	 * but should help.
	 */
	if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery) {
		struct sk_buff *skb;

		sk_stream_for_retrans_queue(skb, sk) {
			if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
				break;
			if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
				continue;
			if ((TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) &&
			    after(lost_retrans, TCP_SKB_CB(skb)->ack_seq) &&
			    (IsFack(tp) ||
			     !before(lost_retrans,
				     TCP_SKB_CB(skb)->ack_seq + tp->reordering *
				     tp->mss_cache))) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);

				if (!(TCP_SKB_CB(skb)->sacked&(TCPCB_LOST|TCPCB_SACKED_ACKED))) {
					tp->lost_out += tcp_skb_pcount(skb);
					TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
					flag |= FLAG_DATA_SACKED;
					NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
				}
			}
		}
	}

	tp->left_out = tp->sacked_out + tp->lost_out;

	if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss)
		tcp_update_reordering(sk, ((tp->fackets_out + 1) - reord), 0);

#if FASTRETRANS_DEBUG > 0
	BUG_TRAP((int)tp->sacked_out >= 0);
	BUG_TRAP((int)tp->lost_out >= 0);
	BUG_TRAP((int)tp->retrans_out >= 0);
	BUG_TRAP((int)tcp_packets_in_flight(tp) >= 0);
#endif
	return flag;
}

/* RTO occurred, but do not yet enter loss state. Instead, transmit two new
 * segments to see from the next ACKs whether any data was really missing.
 * If the RTO was spurious, new ACKs should arrive.
 */
void tcp_enter_frto(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	tp->frto_counter = 1;

	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
            tp->snd_una == tp->high_seq ||
            (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
		tp->prior_ssthresh = tcp_current_ssthresh(sk);
		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
		tcp_ca_event(sk, CA_EVENT_FRTO);
	}

	/* Have to clear retransmission markers here to keep the bookkeeping
	 * in shape, even though we are not yet in Loss state.
	 * If something was really lost, it is eventually caught up
	 * in tcp_enter_frto_loss.
	 */
	tp->retrans_out = 0;
	tp->undo_marker = tp->snd_una;
	tp->undo_retrans = 0;

	sk_stream_for_retrans_queue(skb, sk) {
		TCP_SKB_CB(skb)->sacked &= ~TCPCB_RETRANS;
	}
	tcp_sync_left_out(tp);

	tcp_set_ca_state(sk, TCP_CA_Open);
	tp->frto_highmark = tp->snd_nxt;
}

/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO,
 * which indicates that we should follow the traditional RTO recovery,
 * i.e. mark everything lost and do go-back-N retransmission.
 */
static void tcp_enter_frto_loss(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int cnt = 0;

	tp->sacked_out = 0;
	tp->lost_out = 0;
	tp->fackets_out = 0;

	sk_stream_for_retrans_queue(skb, sk) {
		cnt += tcp_skb_pcount(skb);
		TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {

			/* Do not mark those segments lost that were
			 * forward transmitted after RTO
			 */
			if (!after(TCP_SKB_CB(skb)->end_seq,
				   tp->frto_highmark)) {
				TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
				tp->lost_out += tcp_skb_pcount(skb);
			}
		} else {
			tp->sacked_out += tcp_skb_pcount(skb);
			tp->fackets_out = cnt;
		}
	}
	tcp_sync_left_out(tp);

	tp->snd_cwnd = tp->frto_counter + tcp_packets_in_flight(tp)+1;
	tp->snd_cwnd_cnt = 0;
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tp->undo_marker = 0;
	tp->frto_counter = 0;

	tp->reordering = min_t(unsigned int, tp->reordering,
					     sysctl_tcp_reordering);
	tcp_set_ca_state(sk, TCP_CA_Loss);
	tp->high_seq = tp->frto_highmark;
	TCP_ECN_queue_cwr(tp);
}

void tcp_clear_retrans(struct tcp_sock *tp)
{
	tp->left_out = 0;
	tp->retrans_out = 0;

	tp->fackets_out = 0;
	tp->sacked_out = 0;
	tp->lost_out = 0;

	tp->undo_marker = 0;
	tp->undo_retrans = 0;
}

/* Enter Loss state. If "how" is not zero, forget all SACK information
 * and reset tags completely, otherwise preserve SACKs. If receiver
 * dropped its ofo queue, we will know this due to reneging detection.
 */
void tcp_enter_loss(struct sock *sk, int how)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int cnt = 0;

	/* Reduce ssthresh if it has not yet been made inside this window. */
	if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
		tp->prior_ssthresh = tcp_current_ssthresh(sk);
		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
		tcp_ca_event(sk, CA_EVENT_LOSS);
	}
	tp->snd_cwnd	   = 1;
	tp->snd_cwnd_cnt   = 0;
	tp->snd_cwnd_stamp = tcp_time_stamp;

	tp->bytes_acked = 0;
	tcp_clear_retrans(tp);

	/* Push undo marker, if it was plain RTO and nothing
	 * was retransmitted. */
	if (!how)
		tp->undo_marker = tp->snd_una;

	sk_stream_for_retrans_queue(skb, sk) {
		cnt += tcp_skb_pcount(skb);
		if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
			tp->undo_marker = 0;
		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
			tp->lost_out += tcp_skb_pcount(skb);
		} else {
			tp->sacked_out += tcp_skb_pcount(skb);
			tp->fackets_out = cnt;
		}
	}
	tcp_sync_left_out(tp);

	tp->reordering = min_t(unsigned int, tp->reordering,
					     sysctl_tcp_reordering);
	tcp_set_ca_state(sk, TCP_CA_Loss);
	tp->high_seq = tp->snd_nxt;
	TCP_ECN_queue_cwr(tp);
}

static int tcp_check_sack_reneging(struct sock *sk)
{
	struct sk_buff *skb;

	/* If ACK arrived pointing to a remembered SACK,
	 * it means that our remembered SACKs do not reflect
	 * real state of receiver i.e.
	 * receiver _host_ is heavily congested (or buggy).
	 * Do processing similar to RTO timeout.
	 */
	if ((skb = skb_peek(&sk->sk_write_queue)) != NULL &&
	    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
		struct inet_connection_sock *icsk = inet_csk(sk);
		NET_INC_STATS_BH(LINUX_MIB_TCPSACKRENEGING);

		tcp_enter_loss(sk, 1);
		icsk->icsk_retransmits++;
		tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue));
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  icsk->icsk_rto, TCP_RTO_MAX);
		return 1;
	}
	return 0;
}

static inline int tcp_fackets_out(struct tcp_sock *tp)
{
	return IsReno(tp) ? tp->sacked_out+1 : tp->fackets_out;
}

static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
{
	return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
}

static inline int tcp_head_timedout(struct sock *sk, struct tcp_sock *tp)
{
	return tp->packets_out &&
	       tcp_skb_timedout(sk, skb_peek(&sk->sk_write_queue));
}

/* Linux NewReno/SACK/FACK/ECN state machine.
 * --------------------------------------
 *
 * "Open"	Normal state, no dubious events, fast path.
 * "Disorder"   In all the respects it is "Open",
 *		but requires a bit more attention. It is entered when
 *		we see some SACKs or dupacks. It is split of "Open"
 *		mainly to move some processing from fast path to slow one.
 * "CWR"	CWND was reduced due to some Congestion Notification event.
 *		It can be ECN, ICMP source quench, local device congestion.
 * "Recovery"	CWND was reduced, we are fast-retransmitting.
 * "Loss"	CWND was reduced due to RTO timeout or SACK reneging.
 *
 * tcp_fastretrans_alert() is entered:
 * - each incoming ACK, if state is not "Open"
 * - when arrived ACK is unusual, namely:
 *	* SACK
 *	* Duplicate ACK.
 *	* ECN ECE.
 *
 * Counting packets in flight is pretty simple.
 *
 *	in_flight = packets_out - left_out + retrans_out
 *
 *	packets_out is SND.NXT-SND.UNA counted in packets.
 *
 *	retrans_out is number of retransmitted segments.
 *
 *	left_out is number of segments left network, but not ACKed yet.
 *
 *		left_out = sacked_out + lost_out
 *
 *     sacked_out: Packets, which arrived to receiver out of order
 *		   and hence not ACKed. With SACKs this number is simply
 *		   amount of SACKed data. Even without SACKs
 *		   it is easy to give pretty reliable estimate of this number,
 *		   counting duplicate ACKs.
 *
 *       lost_out: Packets lost by network. TCP has no explicit
 *		   "loss notification" feedback from network (for now).
 *		   It means that this number can be only _guessed_.
 *		   Actually, it is the heuristics to predict lossage that
 *		   distinguishes different algorithms.
 *
 *	F.e. after RTO, when all the queue is considered as lost,
 *	lost_out = packets_out and in_flight = retrans_out.
 *
 *		Essentially, we have now two algorithms counting
 *		lost packets.
 *
 *		FACK: It is the simplest heuristics. As soon as we decided
 *		that something is lost, we decide that _all_ not SACKed
 *		packets until the most forward SACK are lost. I.e.
 *		lost_out = fackets_out - sacked_out and left_out = fackets_out.
 *		It is absolutely correct estimate, if network does not reorder
 *		packets. And it loses any connection to reality when reordering
 *		takes place. We use FACK by default until reordering
 *		is suspected on the path to this destination.
 *
 *		NewReno: when Recovery is entered, we assume that one segment
 *		is lost (classic Reno). While we are in Recovery and
 *		a partial ACK arrives, we assume that one more packet
 *		is lost (NewReno). This heuristics are the same in NewReno
 *		and SACK.
 *
 *  Imagine, that's all! Forget about all this shamanism about CWND inflation
 *  deflation etc. CWND is real congestion window, never inflated, changes
 *  only according to classic VJ rules.
 *
 * Really tricky (and requiring careful tuning) part of algorithm
 * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue().
 * The first determines the moment _when_ we should reduce CWND and,
 * hence, slow down forward transmission. In fact, it determines the moment
 * when we decide that hole is caused by loss, rather than by a reorder.
 *
 * tcp_xmit_retransmit_queue() decides, _what_ we should retransmit to fill
 * holes, caused by lost packets.
 *
 * And the most logically complicated part of algorithm is undo
 * heuristics. We detect false retransmits due to both too early
 * fast retransmit (reordering) and underestimated RTO, analyzing
 * timestamps and D-SACKs. When we detect that some segments were
 * retransmitted by mistake and CWND reduction was wrong, we undo
 * window reduction and abort recovery phase. This logic is hidden
 * inside several functions named tcp_try_undo_<something>.
 */

/* This function decides, when we should leave Disordered state
 * and enter Recovery phase, reducing congestion window.
 *
 * Main question: may we further continue forward transmission
 * with the same cwnd?
 */
static int tcp_time_to_recover(struct sock *sk, struct tcp_sock *tp)
{
	__u32 packets_out;

	/* Trick#1: The loss is proven. */
	if (tp->lost_out)
		return 1;

	/* Not-A-Trick#2 : Classic rule... */
	if (tcp_fackets_out(tp) > tp->reordering)
		return 1;

	/* Trick#3 : when we use RFC2988 timer restart, fast
	 * retransmit can be triggered by timeout of queue head.
	 */
	if (tcp_head_timedout(sk, tp))
		return 1;

	/* Trick#4: It is still not OK... But will it be useful to delay
	 * recovery more?
	 */
	packets_out = tp->packets_out;
	if (packets_out <= tp->reordering &&
	    tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
	    !tcp_may_send_now(sk, tp)) {
		/* We have nothing to send. This connection is limited
		 * either by receiver window or by application.
		 */
		return 1;
	}

	return 0;
}

/* If we receive more dupacks than we expected counting segments
 * in assumption of absent reordering, interpret this as reordering.
 * The only another reason could be bug in receiver TCP.
 */
static void tcp_check_reno_reordering(struct sock *sk, const int addend)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 holes;

	holes = max(tp->lost_out, 1U);
	holes = min(holes, tp->packets_out);

	if ((tp->sacked_out + holes) > tp->packets_out) {
		tp->sacked_out = tp->packets_out - holes;
		tcp_update_reordering(sk, tp->packets_out + addend, 0);
	}
}

/* Emulate SACKs for SACKless connection: account for a new dupack. */

static void tcp_add_reno_sack(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	tp->sacked_out++;
	tcp_check_reno_reordering(sk, 0);
	tcp_sync_left_out(tp);
}

/* Account for ACK, ACKing some data in Reno Recovery phase. */

static void tcp_remove_reno_sacks(struct sock *sk, struct tcp_sock *tp, int acked)
{
	if (acked > 0) {
		/* One ACK acked hole. The rest eat duplicate ACKs. */
		if (acked-1 >= tp->sacked_out)
			tp->sacked_out = 0;
		else
			tp->sacked_out -= acked-1;
	}
	tcp_check_reno_reordering(sk, acked);
	tcp_sync_left_out(tp);
}

static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
{
	tp->sacked_out = 0;
	tp->left_out = tp->lost_out;
}

/* Mark head of queue up as lost. */
static void tcp_mark_head_lost(struct sock *sk, struct tcp_sock *tp,
			       int packets, u32 high_seq)
{
	struct sk_buff *skb;
	int cnt = packets;

	BUG_TRAP(cnt <= tp->packets_out);

	sk_stream_for_retrans_queue(skb, sk) {
		cnt -= tcp_skb_pcount(skb);
		if (cnt < 0 || after(TCP_SKB_CB(skb)->end_seq, high_seq))
			break;
		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
			tp->lost_out += tcp_skb_pcount(skb);
		}
	}
	tcp_sync_left_out(tp);
}

/* Account newly detected lost packet(s) */

static void tcp_update_scoreboard(struct sock *sk, struct tcp_sock *tp)
{
	if (IsFack(tp)) {
		int lost = tp->fackets_out - tp->reordering;
		if (lost <= 0)
			lost = 1;
		tcp_mark_head_lost(sk, tp, lost, tp->high_seq);
	} else {
		tcp_mark_head_lost(sk, tp, 1, tp->high_seq);
	}

	/* New heuristics: it is possible only after we switched
	 * to restart timer each time when something is ACKed.
	 * Hence, we can detect timed out packets during fast
	 * retransmit without falling to slow start.
	 */
	if (tcp_head_timedout(sk, tp)) {
		struct sk_buff *skb;

		sk_stream_for_retrans_queue(skb, sk) {
			if (tcp_skb_timedout(sk, skb) &&
			    !(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
				TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
				tp->lost_out += tcp_skb_pcount(skb);
			}
		}
		tcp_sync_left_out(tp);
	}
}

/* CWND moderation, preventing bursts due to too big ACKs
 * in dubious situations.
 */
static inline void tcp_moderate_cwnd(struct tcp_sock *tp)
{
	tp->snd_cwnd = min(tp->snd_cwnd,
			   tcp_packets_in_flight(tp)+tcp_max_burst(tp));
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

/* Decrease cwnd each second ack. */
static void tcp_cwnd_down(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int decr = tp->snd_cwnd_cnt + 1;

	tp->snd_cwnd_cnt = decr&1;
	decr >>= 1;

	if (decr && tp->snd_cwnd > icsk->icsk_ca_ops->min_cwnd(sk))
		tp->snd_cwnd -= decr;

	tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

/* Nothing was retransmitted or returned timestamp is less
 * than timestamp of the first retransmission.
 */
static inline int tcp_packet_delayed(struct tcp_sock *tp)
{
	return !tp->retrans_stamp ||
		(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
		 (__s32)(tp->rx_opt.rcv_tsecr - tp->retrans_stamp) < 0);
}

/* Undo procedures. */

#if FASTRETRANS_DEBUG > 1
static void DBGUNDO(struct sock *sk, struct tcp_sock *tp, const char *msg)
{
	struct inet_sock *inet = inet_sk(sk);
	printk(KERN_DEBUG "Undo %s %u.%u.%u.%u/%u c%u l%u ss%u/%u p%u\n",
	       msg,
	       NIPQUAD(inet->daddr), ntohs(inet->dport),
	       tp->snd_cwnd, tp->left_out,
	       tp->snd_ssthresh, tp->prior_ssthresh,
	       tp->packets_out);
}
#else
#define DBGUNDO(x...) do { } while (0)
#endif

static void tcp_undo_cwr(struct sock *sk, const int undo)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->prior_ssthresh) {
		const struct inet_connection_sock *icsk = inet_csk(sk);

		if (icsk->icsk_ca_ops->undo_cwnd)
			tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk);
		else
			tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh<<1);

		if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
			tp->snd_ssthresh = tp->prior_ssthresh;
			TCP_ECN_withdraw_cwr(tp);
		}
	} else {
		tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
	}
	tcp_moderate_cwnd(tp);
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

static inline int tcp_may_undo(struct tcp_sock *tp)
{
	return tp->undo_marker &&
		(!tp->undo_retrans || tcp_packet_delayed(tp));
}

/* People celebrate: "We love our President!" */
static int tcp_try_undo_recovery(struct sock *sk, struct tcp_sock *tp)
{
	if (tcp_may_undo(tp)) {
		/* Happy end! We did not retransmit anything
		 * or our original transmission succeeded.
		 */
		DBGUNDO(sk, tp, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
		tcp_undo_cwr(sk, 1);
		if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
			NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
		else
			NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO);
		tp->undo_marker = 0;
	}
	if (tp->snd_una == tp->high_seq && IsReno(tp)) {
		/* Hold old state until something *above* high_seq
		 * is ACKed. For Reno it is MUST to prevent false
		 * fast retransmits (RFC2582). SACK TCP is safe. */
		tcp_moderate_cwnd(tp);
		return 1;
	}
	tcp_set_ca_state(sk, TCP_CA_Open);
	return 0;
}

/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
static void tcp_try_undo_dsack(struct sock *sk, struct tcp_sock *tp)
{
	if (tp->undo_marker && !tp->undo_retrans) {
		DBGUNDO(sk, tp, "D-SACK");
		tcp_undo_cwr(sk, 1);
		tp->undo_marker = 0;
		NET_INC_STATS_BH(LINUX_MIB_TCPDSACKUNDO);
	}
}

/* Undo during fast recovery after partial ACK. */

static int tcp_try_undo_partial(struct sock *sk, struct tcp_sock *tp,
				int acked)
{
	/* Partial ACK arrived. Force Hoe's retransmit. */
	int failed = IsReno(tp) || tp->fackets_out>tp->reordering;

	if (tcp_may_undo(tp)) {
		/* Plain luck! Hole if filled with delayed
		 * packet, rather than with a retransmit.
		 */
		if (tp->retrans_out == 0)
			tp->retrans_stamp = 0;

		tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);

		DBGUNDO(sk, tp, "Hoe");
		tcp_undo_cwr(sk, 0);
		NET_INC_STATS_BH(LINUX_MIB_TCPPARTIALUNDO);

		/* So... Do not make Hoe's retransmit yet.
		 * If the first packet was delayed, the rest
		 * ones are most probably delayed as well.
		 */
		failed = 0;
	}
	return failed;
}

/* Undo during loss recovery after partial ACK. */
static int tcp_try_undo_loss(struct sock *sk, struct tcp_sock *tp)
{
	if (tcp_may_undo(tp)) {
		struct sk_buff *skb;
		sk_stream_for_retrans_queue(skb, sk) {
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
		}
		DBGUNDO(sk, tp, "partial loss");
		tp->lost_out = 0;
		tp->left_out = tp->sacked_out;
		tcp_undo_cwr(sk, 1);
		NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
		inet_csk(sk)->icsk_retransmits = 0;
		tp->undo_marker = 0;
		if (!IsReno(tp))
			tcp_set_ca_state(sk, TCP_CA_Open);
		return 1;
	}
	return 0;
}

static inline void tcp_complete_cwr(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}

static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag)
{
	tp->left_out = tp->sacked_out;

	if (tp->retrans_out == 0)
		tp->retrans_stamp = 0;

	if (flag&FLAG_ECE)
		tcp_enter_cwr(sk);

	if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
		int state = TCP_CA_Open;

		if (tp->left_out || tp->retrans_out || tp->undo_marker)
			state = TCP_CA_Disorder;

		if (inet_csk(sk)->icsk_ca_state != state) {
			tcp_set_ca_state(sk, state);
			tp->high_seq = tp->snd_nxt;
		}
		tcp_moderate_cwnd(tp);
	} else {
		tcp_cwnd_down(sk);
	}
}

/* Process an event, which can update packets-in-flight not trivially.
 * Main goal of this function is to calculate new estimate for left_out,
 * taking into account both packets sitting in receiver's buffer and
 * packets lost by network.
 *
 * Besides that it does CWND reduction, when packet loss is detected
 * and changes state of machine.
 *
 * It does _not_ decide what to send, it is made in function
 * tcp_xmit_retransmit_queue().
 */
static void
tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
		      int prior_packets, int flag)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));

	/* Some technical things:
	 * 1. Reno does not count dupacks (sacked_out) automatically. */
	if (!tp->packets_out)
		tp->sacked_out = 0;
        /* 2. SACK counts snd_fack in packets inaccurately. */
	if (tp->sacked_out == 0)
		tp->fackets_out = 0;

        /* Now state machine starts.
	 * A. ECE, hence prohibit cwnd undoing, the reduction is required. */
	if (flag&FLAG_ECE)
		tp->prior_ssthresh = 0;

	/* B. In all the states check for reneging SACKs. */
	if (tp->sacked_out && tcp_check_sack_reneging(sk))
		return;

	/* C. Process data loss notification, provided it is valid. */
	if ((flag&FLAG_DATA_LOST) &&
	    before(tp->snd_una, tp->high_seq) &&
	    icsk->icsk_ca_state != TCP_CA_Open &&
	    tp->fackets_out > tp->reordering) {
		tcp_mark_head_lost(sk, tp, tp->fackets_out-tp->reordering, tp->high_seq);
		NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
	}

	/* D. Synchronize left_out to current state. */
	tcp_sync_left_out(tp);

	/* E. Check state exit conditions. State can be terminated
	 *    when high_seq is ACKed. */
	if (icsk->icsk_ca_state == TCP_CA_Open) {
		if (!sysctl_tcp_frto)
			BUG_TRAP(tp->retrans_out == 0);
		tp->retrans_stamp = 0;
	} else if (!before(tp->snd_una, tp->high_seq)) {
		switch (icsk->icsk_ca_state) {
		case TCP_CA_Loss:
			icsk->icsk_retransmits = 0;
			if (tcp_try_undo_recovery(sk, tp))
				return;
			break;

		case TCP_CA_CWR:
			/* CWR is to be held something *above* high_seq
			 * is ACKed for CWR bit to reach receiver. */
			if (tp->snd_una != tp->high_seq) {
				tcp_complete_cwr(sk);
				tcp_set_ca_state(sk, TCP_CA_Open);
			}
			break;

		case TCP_CA_Disorder:
			tcp_try_undo_dsack(sk, tp);
			if (!tp->undo_marker ||
			    /* For SACK case do not Open to allow to undo
			     * catching for all duplicate ACKs. */
			    IsReno(tp) || tp->snd_una != tp->high_seq) {
				tp->undo_marker = 0;
				tcp_set_ca_state(sk, TCP_CA_Open);
			}
			break;

		case TCP_CA_Recovery:
			if (IsReno(tp))
				tcp_reset_reno_sack(tp);
			if (tcp_try_undo_recovery(sk, tp))
				return;
			tcp_complete_cwr(sk);
			break;
		}
	}

	/* F. Process state. */
	switch (icsk->icsk_ca_state) {
	case TCP_CA_Recovery:
		if (prior_snd_una == tp->snd_una) {
			if (IsReno(tp) && is_dupack)
				tcp_add_reno_sack(sk);
		} else {
			int acked = prior_packets - tp->packets_out;
			if (IsReno(tp))
				tcp_remove_reno_sacks(sk, tp, acked);
			is_dupack = tcp_try_undo_partial(sk, tp, acked);
		}
		break;
	case TCP_CA_Loss:
		if (flag&FLAG_DATA_ACKED)
			icsk->icsk_retransmits = 0;
		if (!tcp_try_undo_loss(sk, tp)) {
			tcp_moderate_cwnd(tp);
			tcp_xmit_retransmit_queue(sk);
			return;
		}
		if (icsk->icsk_ca_state != TCP_CA_Open)
			return;
		/* Loss is undone; fall through to processing in Open state. */
	default:
		if (IsReno(tp)) {
			if (tp->snd_una != prior_snd_una)
				tcp_reset_reno_sack(tp);
			if (is_dupack)
				tcp_add_reno_sack(sk);
		}

		if (icsk->icsk_ca_state == TCP_CA_Disorder)
			tcp_try_undo_dsack(sk, tp);

		if (!tcp_time_to_recover(sk, tp)) {
			tcp_try_to_open(sk, tp, flag);
			return;
		}

		/* Otherwise enter Recovery state */

		if (IsReno(tp))
			NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY);
		else
			NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY);

		tp->high_seq = tp->snd_nxt;
		tp->prior_ssthresh = 0;
		tp->undo_marker = tp->snd_una;
		tp->undo_retrans = tp->retrans_out;

		if (icsk->icsk_ca_state < TCP_CA_CWR) {
			if (!(flag&FLAG_ECE))
				tp->prior_ssthresh = tcp_current_ssthresh(sk);
			tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
			TCP_ECN_queue_cwr(tp);
		}

		tp->bytes_acked = 0;
		tp->snd_cwnd_cnt = 0;
		tcp_set_ca_state(sk, TCP_CA_Recovery);
	}

	if (is_dupack || tcp_head_timedout(sk, tp))
		tcp_update_scoreboard(sk, tp);
	tcp_cwnd_down(sk);
	tcp_xmit_retransmit_queue(sk);
}

/* Read draft-ietf-tcplw-high-performance before mucking
 * with this code. (Superceeds RFC1323)
 */
static void tcp_ack_saw_tstamp(struct sock *sk, int flag)
{
	/* RTTM Rule: A TSecr value received in a segment is used to
	 * update the averaged RTT measurement only if the segment
	 * acknowledges some new data, i.e., only if it advances the
	 * left edge of the send window.
	 *
	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
	 * 1998/04/10 Andrey V. Savochkin <saw@msu.ru>
	 *
	 * Changed: reset backoff as soon as we see the first valid sample.
	 * If we do not, we get strongly overstimated rto. With timestamps
	 * samples are accepted even from very old segments: f.e., when rtt=1
	 * increases to 8, we retransmit 5 times and after 8 seconds delayed
	 * answer arrives rto becomes 120 seconds! If at least one of segments
	 * in window is lost... Voila.	 			--ANK (010210)
	 */
	struct tcp_sock *tp = tcp_sk(sk);
	const __u32 seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
	tcp_rtt_estimator(sk, seq_rtt);
	tcp_set_rto(sk);
	inet_csk(sk)->icsk_backoff = 0;
	tcp_bound_rto(sk);
}

static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag)
{
	/* We don't have a timestamp. Can only use
	 * packets that are not retransmitted to determine
	 * rtt estimates. Also, we must not reset the
	 * backoff for rto until we get a non-retransmitted
	 * packet. This allows us to deal with a situation
	 * where the network delay has increased suddenly.
	 * I.e. Karn's algorithm. (SIGCOMM '87, p5.)
	 */

	if (flag & FLAG_RETRANS_DATA_ACKED)
		return;

	tcp_rtt_estimator(sk, seq_rtt);
	tcp_set_rto(sk);
	inet_csk(sk)->icsk_backoff = 0;
	tcp_bound_rto(sk);
}

static inline void tcp_ack_update_rtt(struct sock *sk, const int flag,
				      const s32 seq_rtt)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	/* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */
	if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
		tcp_ack_saw_tstamp(sk, flag);
	else if (seq_rtt >= 0)
		tcp_ack_no_tstamp(sk, seq_rtt, flag);
}

static inline void tcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt,
				  u32 in_flight, int good)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	icsk->icsk_ca_ops->cong_avoid(sk, ack, rtt, in_flight, good);
	tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}

/* Restart timer after forward progress on connection.
 * RFC2988 recommends to restart timer to now+rto.
 */

static inline void tcp_ack_packets_out(struct sock *sk, struct tcp_sock *tp)
{
	if (!tp->packets_out) {
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
	} else {
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
	}
}

static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
			 __u32 now, __s32 *seq_rtt)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_skb_cb *scb = TCP_SKB_CB(skb); 
	__u32 seq = tp->snd_una;
	__u32 packets_acked;
	int acked = 0;

	/* If we get here, the whole TSO packet has not been
	 * acked.
	 */
	BUG_ON(!after(scb->end_seq, seq));

	packets_acked = tcp_skb_pcount(skb);
	if (tcp_trim_head(sk, skb, seq - scb->seq))
		return 0;
	packets_acked -= tcp_skb_pcount(skb);

	if (packets_acked) {