tcp_input.c

 * --------------------
 * Reordering metric is maximal distance, which a packet can be displaced
 * in packet stream. With SACKs we can estimate it:
 *
 * 1. SACK fills old hole and the corresponding segment was not
 *    ever retransmitted -> reordering. Alas, we cannot use it
 *    when segment was retransmitted.
 * 2. The last flaw is solved with D-SACK. D-SACK arrives
 *    for retransmitted and already SACKed segment -> reordering..
 * Both of these heuristics are not used in Loss state, when we cannot
 * account for retransmits accurately.
 */
static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
			   struct tcp_sack_block_wire *sp, int num_sacks,
			   u32 prior_snd_una)
{
	u32 start_seq_0 = ntohl(get_unaligned(&sp[0].start_seq));
	u32 end_seq_0 = ntohl(get_unaligned(&sp[0].end_seq));
	int dup_sack = 0;

	if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
		dup_sack = 1;
		tp->rx_opt.sack_ok |= 4;
		NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
	} else if (num_sacks > 1) {
		u32 end_seq_1 = ntohl(get_unaligned(&sp[1].end_seq));
		u32 start_seq_1 = ntohl(get_unaligned(&sp[1].start_seq));

		if (!after(end_seq_0, end_seq_1) &&
		    !before(start_seq_0, start_seq_1)) {
			dup_sack = 1;
			tp->rx_opt.sack_ok |= 4;
			NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
		}
	}

	/* D-SACK for already forgotten data... Do dumb counting. */
	if (dup_sack &&
	    !after(end_seq_0, prior_snd_una) &&
	    after(end_seq_0, tp->undo_marker))
		tp->undo_retrans--;

	return dup_sack;
}

static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned char *ptr = (skb_transport_header(ack_skb) +
			      TCP_SKB_CB(ack_skb)->sacked);
	struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
	struct sk_buff *cached_skb;
	int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
	int reord = tp->packets_out;
	int prior_fackets;
	u32 lost_retrans = 0;
	int flag = 0;
	int found_dup_sack = 0;
	int cached_fack_count;
	int i;
	int first_sack_index;

	if (!tp->sacked_out) {
		tp->fackets_out = 0;
		tp->highest_sack = tp->snd_una;
	}
	prior_fackets = tp->fackets_out;

	found_dup_sack = tcp_check_dsack(tp, ack_skb, sp,
					 num_sacks, prior_snd_una);
	if (found_dup_sack)
		flag |= FLAG_DSACKING_ACK;

	/* Eliminate too old ACKs, but take into
	 * account more or less fresh ones, they can
	 * contain valid SACK info.
	 */
	if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
		return 0;

	/* SACK fastpath:
	 * if the only SACK change is the increase of the end_seq of
	 * the first block then only apply that SACK block
	 * and use retrans queue hinting otherwise slowpath */
	flag = 1;
	for (i = 0; i < num_sacks; i++) {
		__be32 start_seq = sp[i].start_seq;
		__be32 end_seq = sp[i].end_seq;

		if (i == 0) {
			if (tp->recv_sack_cache[i].start_seq != start_seq)
				flag = 0;
		} else {
			if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
			    (tp->recv_sack_cache[i].end_seq != end_seq))
				flag = 0;
		}
		tp->recv_sack_cache[i].start_seq = start_seq;
		tp->recv_sack_cache[i].end_seq = end_seq;
	}
	/* Clear the rest of the cache sack blocks so they won't match mistakenly. */
	for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) {
		tp->recv_sack_cache[i].start_seq = 0;
		tp->recv_sack_cache[i].end_seq = 0;
	}

	first_sack_index = 0;
	if (flag)
		num_sacks = 1;
	else {
		int j;
		tp->fastpath_skb_hint = NULL;

		/* order SACK blocks to allow in order walk of the retrans queue */
		for (i = num_sacks-1; i > 0; i--) {
			for (j = 0; j < i; j++){
				if (after(ntohl(sp[j].start_seq),
					  ntohl(sp[j+1].start_seq))){
					struct tcp_sack_block_wire tmp;

					tmp = sp[j];
					sp[j] = sp[j+1];
					sp[j+1] = tmp;

					/* Track where the first SACK block goes to */
					if (j == first_sack_index)
						first_sack_index = j+1;
				}

			}
		}
	}

	/* clear flag as used for different purpose in following code */
	flag = 0;

	/* Use SACK fastpath hint if valid */
	cached_skb = tp->fastpath_skb_hint;
	cached_fack_count = tp->fastpath_cnt_hint;
	if (!cached_skb) {
		cached_skb = tcp_write_queue_head(sk);
		cached_fack_count = 0;
	}

	for (i=0; i<num_sacks; i++, sp++) {
		struct sk_buff *skb;
		__u32 start_seq = ntohl(sp->start_seq);
		__u32 end_seq = ntohl(sp->end_seq);
		int fack_count;
		int dup_sack = (found_dup_sack && (i == first_sack_index));

		skb = cached_skb;
		fack_count = cached_fack_count;

		/* Event "B" in the comment above. */
		if (after(end_seq, tp->high_seq))
			flag |= FLAG_DATA_LOST;

		tcp_for_write_queue_from(skb, sk) {
			int in_sack, pcount;
			u8 sacked;

			if (skb == tcp_send_head(sk))
				break;

			cached_skb = skb;
			cached_fack_count = fack_count;
			if (i == first_sack_index) {
				tp->fastpath_skb_hint = skb;
				tp->fastpath_cnt_hint = fack_count;
			}

			/* The retransmission queue is always in order, so
			 * we can short-circuit the walk early.
			 */
			if (!before(TCP_SKB_CB(skb)->seq, end_seq))
				break;

			in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
				!before(end_seq, TCP_SKB_CB(skb)->end_seq);

			pcount = tcp_skb_pcount(skb);

			if (pcount > 1 && !in_sack &&
			    after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
				unsigned int pkt_len;

				in_sack = !after(start_seq,
						 TCP_SKB_CB(skb)->seq);

				if (!in_sack)
					pkt_len = (start_seq -
						   TCP_SKB_CB(skb)->seq);
				else
					pkt_len = (end_seq -
						   TCP_SKB_CB(skb)->seq);
				if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
					break;
				pcount = tcp_skb_pcount(skb);
			}

			fack_count += pcount;

			sacked = TCP_SKB_CB(skb)->sacked;

			/* Account D-SACK for retransmitted packet. */
			if ((dup_sack && in_sack) &&
			    (sacked & TCPCB_RETRANS) &&
			    after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
				tp->undo_retrans--;

			/* The frame is ACKed. */
			if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) {
				if (sacked&TCPCB_RETRANS) {
					if ((dup_sack && in_sack) &&
					    (sacked&TCPCB_SACKED_ACKED))
						reord = min(fack_count, reord);
				} else {
					/* If it was in a hole, we detected reordering. */
					if (fack_count < prior_fackets &&
					    !(sacked&TCPCB_SACKED_ACKED))
						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);

						/* clear lost hint */
						tp->retransmit_skb_hint = NULL;
					}
				} 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);

						/* clear lost hint */
						tp->retransmit_skb_hint = NULL;
					}
					/* SACK enhanced F-RTO detection.
					 * Set flag if and only if non-rexmitted
					 * segments below frto_highmark are
					 * SACKed (RFC4138; Appendix B).
					 * Clearing correct due to in-order walk
					 */
					if (after(end_seq, tp->frto_highmark)) {
						flag &= ~FLAG_ONLY_ORIG_SACKED;
					} else {
						if (!(sacked & TCPCB_RETRANS))
							flag |= FLAG_ONLY_ORIG_SACKED;
					}
				}

				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;

				if (after(TCP_SKB_CB(skb)->seq,
				    tp->highest_sack))
					tp->highest_sack = TCP_SKB_CB(skb)->seq;
			} 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);
				tp->retransmit_skb_hint = NULL;
			}
		}
	}

	/* 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;

		tcp_for_write_queue(skb, sk) {
			if (skb == tcp_send_head(sk))
				break;
			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);

				/* clear lost hint */
				tp->retransmit_skb_hint = NULL;

				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);
				}
			}
		}
	}

	if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss &&
	    (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
		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;
}

/* F-RTO can only be used if TCP has never retransmitted anything other than
 * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
 */
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_verify_left_out(tp);
}

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

static void tcp_remove_reno_sacks(struct sock *sk, int acked)
{
	struct tcp_sock *tp = tcp_sk(sk);

	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_verify_left_out(tp);
}

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

int tcp_use_frto(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	if (!sysctl_tcp_frto)
		return 0;

	if (IsSackFrto())
		return 1;

	/* Avoid expensive walking of rexmit queue if possible */
	if (tp->retrans_out > 1)
		return 0;

	skb = tcp_write_queue_head(sk);
	skb = tcp_write_queue_next(sk, skb);	/* Skips head */
	tcp_for_write_queue_from(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
			return 0;
		/* Short-circuit when first non-SACKed skb has been checked */
		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED))
			break;
	}
	return 1;
}

/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO
 * recovery a bit and use heuristics in tcp_process_frto() to detect if
 * the RTO was spurious. Only clear SACKED_RETRANS of the head here to
 * keep retrans_out counting accurate (with SACK F-RTO, other than head
 * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS
 * bits are handled if the Loss state is really to be entered (in
 * tcp_enter_frto_loss).
 *
 * Do like tcp_enter_loss() would; when RTO expires the second time it
 * does:
 *  "Reduce ssthresh if it has not yet been made inside this window."
 */
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;

	if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) ||
	    tp->snd_una == tp->high_seq ||
	    ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) &&
	     !icsk->icsk_retransmits)) {
		tp->prior_ssthresh = tcp_current_ssthresh(sk);
		/* Our state is too optimistic in ssthresh() call because cwnd
		 * is not reduced until tcp_enter_frto_loss() when previous FRTO
		 * recovery has not yet completed. Pattern would be this: RTO,
		 * Cumulative ACK, RTO (2xRTO for the same segment does not end
		 * up here twice).
		 * RFC4138 should be more specific on what to do, even though
		 * RTO is quite unlikely to occur after the first Cumulative ACK
		 * due to back-off and complexity of triggering events ...
		 */
		if (tp->frto_counter) {
			u32 stored_cwnd;
			stored_cwnd = tp->snd_cwnd;
			tp->snd_cwnd = 2;
			tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
			tp->snd_cwnd = stored_cwnd;
		} else {
			tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
		}
		/* ... in theory, cong.control module could do "any tricks" in
		 * ssthresh(), which means that ca_state, lost bits and lost_out
		 * counter would have to be faked before the call occurs. We
		 * consider that too expensive, unlikely and hacky, so modules
		 * using these in ssthresh() must deal these incompatibility
		 * issues if they receives CA_EVENT_FRTO and frto_counter != 0
		 */
		tcp_ca_event(sk, CA_EVENT_FRTO);
	}

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

	skb = tcp_write_queue_head(sk);
	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
		TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
		tp->retrans_out -= tcp_skb_pcount(skb);
	}
	tcp_verify_left_out(tp);

	/* Earlier loss recovery underway (see RFC4138; Appendix B).
	 * The last condition is necessary at least in tp->frto_counter case.
	 */
	if (IsSackFrto() && (tp->frto_counter ||
	    ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
	    after(tp->high_seq, tp->snd_una)) {
		tp->frto_highmark = tp->high_seq;
	} else {
		tp->frto_highmark = tp->snd_nxt;
	}
	tcp_set_ca_state(sk, TCP_CA_Disorder);
	tp->high_seq = tp->snd_nxt;
	tp->frto_counter = 1;
}

/* 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, int allowed_segments, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	tp->lost_out = 0;
	tp->retrans_out = 0;
	if (IsReno(tp))
		tcp_reset_reno_sack(tp);

	tcp_for_write_queue(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		/*
		 * Count the retransmission made on RTO correctly (only when
		 * waiting for the first ACK and did not get it)...
		 */
		if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
			/* For some reason this R-bit might get cleared? */
			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
				tp->retrans_out += tcp_skb_pcount(skb);
			/* ...enter this if branch just for the first segment */
			flag |= FLAG_DATA_ACKED;
		} else {
			TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
		}

		/* Don't lost mark skbs that were fwd transmitted after RTO */
		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) &&
		    !after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) {
			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
			tp->lost_out += tcp_skb_pcount(skb);
		}
	}
	tcp_verify_left_out(tp);

	tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
	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);

	clear_all_retrans_hints(tp);
}

void tcp_clear_retrans(struct tcp_sock *tp)
{
	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;

	tcp_for_write_queue(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		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_verify_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);
	/* Abort FRTO algorithm if one is in progress */
	tp->frto_counter = 0;

	clear_all_retrans_hints(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 = tcp_write_queue_head(sk)) != 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, tcp_write_queue_head(sk));
		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 = tcp_sk(sk);

	return tp->packets_out &&
	       tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}

/* 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 = tcp_sk(sk);
	__u32 packets_out;

	/* Do not perform any recovery during FRTO algorithm */
	if (tp->frto_counter)
		return 0;

	/* 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))
		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)) {
		/* We have nothing to send. This connection is limited
		 * either by receiver window or by application.
		 */
		return 1;
	}

	return 0;
}

/* RFC: This is from the original, I doubt that this is necessary at all:
 * clear xmit_retrans hint if seq of this skb is beyond hint. How could we
 * retransmitted past LOST markings in the first place? I'm not fully sure
 * about undo and end of connection cases, which can cause R without L?
 */
static void tcp_verify_retransmit_hint(struct tcp_sock *tp,
				       struct sk_buff *skb)
{
	if ((tp->retransmit_skb_hint != NULL) &&
	    before(TCP_SKB_CB(skb)->seq,
	    TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
		tp->retransmit_skb_hint = NULL;
}

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

	BUG_TRAP(packets <= tp->packets_out);
	if (tp->lost_skb_hint) {
		skb = tp->lost_skb_hint;
		cnt = tp->lost_cnt_hint;
	} else {
		skb = tcp_write_queue_head(sk);
		cnt = 0;
	}

	tcp_for_write_queue_from(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		/* TODO: do this better */
		/* this is not the most efficient way to do this... */
		tp->lost_skb_hint = skb;
		tp->lost_cnt_hint = cnt;
		cnt += tcp_skb_pcount(skb);
		if (cnt > packets || 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_verify_retransmit_hint(tp, skb);
		}
	}
	tcp_verify_left_out(tp);
}

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

static void tcp_update_scoreboard(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (IsFack(tp)) {
		int lost = tp->fackets_out - tp->reordering;
		if (lost <= 0)
			lost = 1;
		tcp_mark_head_lost(sk, lost, tp->high_seq);
	} else {
		tcp_mark_head_lost(sk, 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 (!IsReno(tp) && tcp_head_timedout(sk)) {
		struct sk_buff *skb;

		skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
			: tcp_write_queue_head(sk);

		tcp_for_write_queue_from(skb, sk) {
			if (skb == tcp_send_head(sk))
				break;
			if (!tcp_skb_timedout(sk, skb))
				break;

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

		tp->scoreboard_skb_hint = skb;

		tcp_verify_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;
}

/* Lower bound on congestion window is slow start threshold
 * unless congestion avoidance choice decides to overide it.
 */
static inline u32 tcp_cwnd_min(const struct sock *sk)
{
	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;

	return ca_ops->min_cwnd ? ca_ops->min_cwnd(sk) : tcp_sk(sk)->snd_ssthresh;
}

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

	if ((flag&(FLAG_ANY_PROGRESS|FLAG_DSACKING_ACK)) ||
	    (IsReno(tp) && !(flag&FLAG_NOT_DUP))) {
		tp->snd_cwnd_cnt = decr&1;
		decr >>= 1;

		if (decr && tp->snd_cwnd > tcp_cwnd_min(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, const char *msg)
{
	struct tcp_sock *tp = tcp_sk(sk);
	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, tcp_left_out(tp),
	       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;