tcp_input.c

		if (sacked & TCPCB_RETRANS) {
			if (sacked & TCPCB_SACKED_RETRANS)
				tp->retrans_out -= acked_pcount;
			flag |= FLAG_RETRANS_DATA_ACKED;
		} else {
			ca_seq_rtt = now - scb->when;
			last_ackt = skb->tstamp;
			if (seq_rtt < 0) {
				seq_rtt = ca_seq_rtt;
			}
			if (!(sacked & TCPCB_SACKED_ACKED))
				reord = min(pkts_acked, reord);
			if (!after(scb->end_seq, tp->high_seq))
				flag |= FLAG_ORIG_SACK_ACKED;
		}

		if (sacked & TCPCB_SACKED_ACKED)
			tp->sacked_out -= acked_pcount;
		if (sacked & TCPCB_LOST)
			tp->lost_out -= acked_pcount;

		tp->packets_out -= acked_pcount;
		pkts_acked += acked_pcount;

		/* Initial outgoing SYN's get put onto the write_queue
		 * just like anything else we transmit.  It is not
		 * true data, and if we misinform our callers that
		 * this ACK acks real data, we will erroneously exit
		 * connection startup slow start one packet too
		 * quickly.  This is severely frowned upon behavior.
		 */
		if (!(scb->tcp_flags & TCPHDR_SYN)) {
			flag |= FLAG_DATA_ACKED;
		} else {
			flag |= FLAG_SYN_ACKED;
			tp->retrans_stamp = 0;
		}

		if (!fully_acked)
			break;

		tcp_unlink_write_queue(skb, sk);
		sk_wmem_free_skb(sk, skb);
		if (skb == tp->retransmit_skb_hint)
			tp->retransmit_skb_hint = NULL;
		if (skb == tp->lost_skb_hint)
			tp->lost_skb_hint = NULL;
	}

	if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
		tp->snd_up = tp->snd_una;

	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
		flag |= FLAG_SACK_RENEGING;

	if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) ||
	    (flag & FLAG_ACKED))
		tcp_rearm_rto(sk);

	if (flag & FLAG_ACKED) {
		const struct tcp_congestion_ops *ca_ops
			= inet_csk(sk)->icsk_ca_ops;

		if (unlikely(icsk->icsk_mtup.probe_size &&
			     !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
			tcp_mtup_probe_success(sk);
		}

		if (tcp_is_reno(tp)) {
			tcp_remove_reno_sacks(sk, pkts_acked);
		} else {
			int delta;

			/* Non-retransmitted hole got filled? That's reordering */
			if (reord < prior_fackets)
				tcp_update_reordering(sk, tp->fackets_out - reord, 0);

			delta = tcp_is_fack(tp) ? pkts_acked :
						  prior_sacked - tp->sacked_out;
			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
		}

		tp->fackets_out -= min(pkts_acked, tp->fackets_out);

		if (ca_ops->pkts_acked) {
			s32 rtt_us = -1;

			/* Is the ACK triggering packet unambiguous? */
			if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
				/* High resolution needed and available? */
				if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
				    !ktime_equal(last_ackt,
						 net_invalid_timestamp()))
					rtt_us = ktime_us_delta(ktime_get_real(),
								last_ackt);
				else if (ca_seq_rtt >= 0)
					rtt_us = jiffies_to_usecs(ca_seq_rtt);
			}

			ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
		}
	}

#if FASTRETRANS_DEBUG > 0
	WARN_ON((int)tp->sacked_out < 0);
	WARN_ON((int)tp->lost_out < 0);
	WARN_ON((int)tp->retrans_out < 0);
	if (!tp->packets_out && tcp_is_sack(tp)) {
		icsk = inet_csk(sk);
		if (tp->lost_out) {
			pr_debug("Leak l=%u %d\n",
				 tp->lost_out, icsk->icsk_ca_state);
			tp->lost_out = 0;
		}
		if (tp->sacked_out) {
			pr_debug("Leak s=%u %d\n",
				 tp->sacked_out, icsk->icsk_ca_state);
			tp->sacked_out = 0;
		}
		if (tp->retrans_out) {
			pr_debug("Leak r=%u %d\n",
				 tp->retrans_out, icsk->icsk_ca_state);
			tp->retrans_out = 0;
		}
	}
#endif
	return flag;
}

static void tcp_ack_probe(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	/* Was it a usable window open? */

	if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) {
		icsk->icsk_backoff = 0;
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
		/* Socket must be waked up by subsequent tcp_data_snd_check().
		 * This function is not for random using!
		 */
	} else {
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
					  TCP_RTO_MAX);
	}
}

static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag)
{
	return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
		inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
}

/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
	if (tcp_in_cwnd_reduction(sk))
		return false;

	/* If reordering is high then always grow cwnd whenever data is
	 * delivered regardless of its ordering. Otherwise stay conservative
	 * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/
	 * new SACK or ECE mark may first advance cwnd here and later reduce
	 * cwnd in tcp_fastretrans_alert() based on more states.
	 */
	if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
		return flag & FLAG_FORWARD_PROGRESS;

	return flag & FLAG_DATA_ACKED;
}

/* Check that window update is acceptable.
 * The function assumes that snd_una<=ack<=snd_next.
 */
static inline bool tcp_may_update_window(const struct tcp_sock *tp,
					const u32 ack, const u32 ack_seq,
					const u32 nwin)
{
	return	after(ack, tp->snd_una) ||
		after(ack_seq, tp->snd_wl1) ||
		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
}

/* Update our send window.
 *
 * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
 * and in FreeBSD. NetBSD's one is even worse.) is wrong.
 */
static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 ack,
				 u32 ack_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int flag = 0;
	u32 nwin = ntohs(tcp_hdr(skb)->window);

	if (likely(!tcp_hdr(skb)->syn))
		nwin <<= tp->rx_opt.snd_wscale;

	if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
		flag |= FLAG_WIN_UPDATE;
		tcp_update_wl(tp, ack_seq);

		if (tp->snd_wnd != nwin) {
			tp->snd_wnd = nwin;

			/* Note, it is the only place, where
			 * fast path is recovered for sending TCP.
			 */
			tp->pred_flags = 0;
			tcp_fast_path_check(sk);

			if (nwin > tp->max_window) {
				tp->max_window = nwin;
				tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie);
			}
		}
	}

	tp->snd_una = ack;

	return flag;
}

/* RFC 5961 7 [ACK Throttling] */
static void tcp_send_challenge_ack(struct sock *sk)
{
	/* unprotected vars, we dont care of overwrites */
	static u32 challenge_timestamp;
	static unsigned int challenge_count;
	u32 now = jiffies / HZ;

	if (now != challenge_timestamp) {
		challenge_timestamp = now;
		challenge_count = 0;
	}
	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
		tcp_send_ack(sk);
	}
}

static void tcp_store_ts_recent(struct tcp_sock *tp)
{
	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
	tp->rx_opt.ts_recent_stamp = get_seconds();
}

static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
{
	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
		 * extra check below makes sure this can only happen
		 * for pure ACK frames.  -DaveM
		 *
		 * Not only, also it occurs for expired timestamps.
		 */

		if (tcp_paws_check(&tp->rx_opt, 0))
			tcp_store_ts_recent(tp);
	}
}

/* This routine deals with acks during a TLP episode.
 * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
 */
static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);
	bool is_tlp_dupack = (ack == tp->tlp_high_seq) &&
			     !(flag & (FLAG_SND_UNA_ADVANCED |
				       FLAG_NOT_DUP | FLAG_DATA_SACKED));

	/* Mark the end of TLP episode on receiving TLP dupack or when
	 * ack is after tlp_high_seq.
	 */
	if (is_tlp_dupack) {
		tp->tlp_high_seq = 0;
		return;
	}

	if (after(ack, tp->tlp_high_seq)) {
		tp->tlp_high_seq = 0;
		/* Don't reduce cwnd if DSACK arrives for TLP retrans. */
		if (!(flag & FLAG_DSACKING_ACK)) {
			tcp_init_cwnd_reduction(sk, true);
			tcp_set_ca_state(sk, TCP_CA_CWR);
			tcp_end_cwnd_reduction(sk);
			tcp_set_ca_state(sk, TCP_CA_Open);
			NET_INC_STATS_BH(sock_net(sk),
					 LINUX_MIB_TCPLOSSPROBERECOVERY);
		}
	}
}

/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	u32 prior_snd_una = tp->snd_una;
	u32 ack_seq = TCP_SKB_CB(skb)->seq;
	u32 ack = TCP_SKB_CB(skb)->ack_seq;
	bool is_dupack = false;
	u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
	u32 prior_fackets;
	int prior_packets = tp->packets_out;
	const int prior_unsacked = tp->packets_out - tp->sacked_out;
	int acked = 0; /* Number of packets newly acked */
	s32 sack_rtt = -1;

	/* If the ack is older than previous acks
	 * then we can probably ignore it.
	 */
	if (before(ack, prior_snd_una)) {
		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
		if (before(ack, prior_snd_una - tp->max_window)) {
			tcp_send_challenge_ack(sk);
			return -1;
		}
		goto old_ack;
	}

	/* If the ack includes data we haven't sent yet, discard
	 * this segment (RFC793 Section 3.9).
	 */
	if (after(ack, tp->snd_nxt))
		goto invalid_ack;

	if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
		tcp_rearm_rto(sk);

	if (after(ack, prior_snd_una))
		flag |= FLAG_SND_UNA_ADVANCED;

	prior_fackets = tp->fackets_out;
	prior_in_flight = tcp_packets_in_flight(tp);

	/* ts_recent update must be made after we are sure that the packet
	 * is in window.
	 */
	if (flag & FLAG_UPDATE_TS_RECENT)
		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);

	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
		/* Window is constant, pure forward advance.
		 * No more checks are required.
		 * Note, we use the fact that SND.UNA>=SND.WL2.
		 */
		tcp_update_wl(tp, ack_seq);
		tp->snd_una = ack;
		flag |= FLAG_WIN_UPDATE;

		tcp_ca_event(sk, CA_EVENT_FAST_ACK);

		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
	} else {
		if (ack_seq != TCP_SKB_CB(skb)->end_seq)
			flag |= FLAG_DATA;
		else
			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPUREACKS);

		flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);

		if (TCP_SKB_CB(skb)->sacked)
			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
							&sack_rtt);

		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
			flag |= FLAG_ECE;

		tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
	}

	/* We passed data and got it acked, remove any soft error
	 * log. Something worked...
	 */
	sk->sk_err_soft = 0;
	icsk->icsk_probes_out = 0;
	tp->rcv_tstamp = tcp_time_stamp;
	if (!prior_packets)
		goto no_queue;

	/* See if we can take anything off of the retransmit queue. */
	acked = tp->packets_out;
	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
	acked -= tp->packets_out;

	/* Advance cwnd if state allows */
	if (tcp_may_raise_cwnd(sk, flag))
		tcp_cong_avoid(sk, ack, prior_in_flight);

	if (tcp_ack_is_dubious(sk, flag)) {
		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
		tcp_fastretrans_alert(sk, acked, prior_unsacked,
				      is_dupack, flag);
	}
	if (tp->tlp_high_seq)
		tcp_process_tlp_ack(sk, ack, flag);

	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
		struct dst_entry *dst = __sk_dst_get(sk);
		if (dst)
			dst_confirm(dst);
	}

	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
		tcp_schedule_loss_probe(sk);
	if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
		tcp_update_pacing_rate(sk);
	return 1;

no_queue:
	/* If data was DSACKed, see if we can undo a cwnd reduction. */
	if (flag & FLAG_DSACKING_ACK)
		tcp_fastretrans_alert(sk, acked, prior_unsacked,
				      is_dupack, flag);
	/* If this ack opens up a zero window, clear backoff.  It was
	 * being used to time the probes, and is probably far higher than
	 * it needs to be for normal retransmission.
	 */
	if (tcp_send_head(sk))
		tcp_ack_probe(sk);

	if (tp->tlp_high_seq)
		tcp_process_tlp_ack(sk, ack, flag);
	return 1;

invalid_ack:
	SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
	return -1;

old_ack:
	/* If data was SACKed, tag it and see if we should send more data.
	 * If data was DSACKed, see if we can undo a cwnd reduction.
	 */
	if (TCP_SKB_CB(skb)->sacked) {
		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
						&sack_rtt);
		tcp_fastretrans_alert(sk, acked, prior_unsacked,
				      is_dupack, flag);
	}

	SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
	return 0;
}

/* Look for tcp options. Normally only called on SYN and SYNACK packets.
 * But, this can also be called on packets in the established flow when
 * the fast version below fails.
 */
void tcp_parse_options(const struct sk_buff *skb,
		       struct tcp_options_received *opt_rx, int estab,
		       struct tcp_fastopen_cookie *foc)
{
	const unsigned char *ptr;
	const struct tcphdr *th = tcp_hdr(skb);
	int length = (th->doff * 4) - sizeof(struct tcphdr);

	ptr = (const unsigned char *)(th + 1);
	opt_rx->saw_tstamp = 0;

	while (length > 0) {
		int opcode = *ptr++;
		int opsize;

		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				return;	/* don't parse partial options */
			switch (opcode) {
			case TCPOPT_MSS:
				if (opsize == TCPOLEN_MSS && th->syn && !estab) {
					u16 in_mss = get_unaligned_be16(ptr);
					if (in_mss) {
						if (opt_rx->user_mss &&
						    opt_rx->user_mss < in_mss)
							in_mss = opt_rx->user_mss;
						opt_rx->mss_clamp = in_mss;
					}
				}
				break;
			case TCPOPT_WINDOW:
				if (opsize == TCPOLEN_WINDOW && th->syn &&
				    !estab && sysctl_tcp_window_scaling) {
					__u8 snd_wscale = *(__u8 *)ptr;
					opt_rx->wscale_ok = 1;
					if (snd_wscale > 14) {
						net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n",
								     __func__,
								     snd_wscale);
						snd_wscale = 14;
					}
					opt_rx->snd_wscale = snd_wscale;
				}
				break;
			case TCPOPT_TIMESTAMP:
				if ((opsize == TCPOLEN_TIMESTAMP) &&
				    ((estab && opt_rx->tstamp_ok) ||
				     (!estab && sysctl_tcp_timestamps))) {
					opt_rx->saw_tstamp = 1;
					opt_rx->rcv_tsval = get_unaligned_be32(ptr);
					opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
				}
				break;
			case TCPOPT_SACK_PERM:
				if (opsize == TCPOLEN_SACK_PERM && th->syn &&
				    !estab && sysctl_tcp_sack) {
					opt_rx->sack_ok = TCP_SACK_SEEN;
					tcp_sack_reset(opt_rx);
				}
				break;

			case TCPOPT_SACK:
				if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
				   !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
				   opt_rx->sack_ok) {
					TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
				}
				break;
#ifdef CONFIG_TCP_MD5SIG
			case TCPOPT_MD5SIG:
				/*
				 * The MD5 Hash has already been
				 * checked (see tcp_v{4,6}_do_rcv()).
				 */
				break;
#endif
			case TCPOPT_EXP:
				/* Fast Open option shares code 254 using a
				 * 16 bits magic number. It's valid only in
				 * SYN or SYN-ACK with an even size.
				 */
				if (opsize < TCPOLEN_EXP_FASTOPEN_BASE ||
				    get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC ||
				    foc == NULL || !th->syn || (opsize & 1))
					break;
				foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
				if (foc->len >= TCP_FASTOPEN_COOKIE_MIN &&
				    foc->len <= TCP_FASTOPEN_COOKIE_MAX)
					memcpy(foc->val, ptr + 2, foc->len);
				else if (foc->len != 0)
					foc->len = -1;
				break;

			}
			ptr += opsize-2;
			length -= opsize;
		}
	}
}
EXPORT_SYMBOL(tcp_parse_options);

static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th)
{
	const __be32 *ptr = (const __be32 *)(th + 1);

	if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
			  | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) {
		tp->rx_opt.saw_tstamp = 1;
		++ptr;
		tp->rx_opt.rcv_tsval = ntohl(*ptr);
		++ptr;
		if (*ptr)
			tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
		else
			tp->rx_opt.rcv_tsecr = 0;
		return true;
	}
	return false;
}

/* Fast parse options. This hopes to only see timestamps.
 * If it is wrong it falls back on tcp_parse_options().
 */
static bool tcp_fast_parse_options(const struct sk_buff *skb,
				   const struct tcphdr *th, struct tcp_sock *tp)
{
	/* In the spirit of fast parsing, compare doff directly to constant
	 * values.  Because equality is used, short doff can be ignored here.
	 */
	if (th->doff == (sizeof(*th) / 4)) {
		tp->rx_opt.saw_tstamp = 0;
		return false;
	} else if (tp->rx_opt.tstamp_ok &&
		   th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
		if (tcp_parse_aligned_timestamp(tp, th))
			return true;
	}

	tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
	if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
		tp->rx_opt.rcv_tsecr -= tp->tsoffset;

	return true;
}

#ifdef CONFIG_TCP_MD5SIG
/*
 * Parse MD5 Signature option
 */
const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
{
	int length = (th->doff << 2) - sizeof(*th);
	const u8 *ptr = (const u8 *)(th + 1);

	/* If the TCP option is too short, we can short cut */
	if (length < TCPOLEN_MD5SIG)
		return NULL;

	while (length > 0) {
		int opcode = *ptr++;
		int opsize;

		switch(opcode) {
		case TCPOPT_EOL:
			return NULL;
		case TCPOPT_NOP:
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2 || opsize > length)
				return NULL;
			if (opcode == TCPOPT_MD5SIG)
				return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
		}
		ptr += opsize - 2;
		length -= opsize;
	}
	return NULL;
}
EXPORT_SYMBOL(tcp_parse_md5sig_option);
#endif

/* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
 *
 * It is not fatal. If this ACK does _not_ change critical state (seqs, window)
 * it can pass through stack. So, the following predicate verifies that
 * this segment is not used for anything but congestion avoidance or
 * fast retransmit. Moreover, we even are able to eliminate most of such
 * second order effects, if we apply some small "replay" window (~RTO)
 * to timestamp space.
 *
 * All these measures still do not guarantee that we reject wrapped ACKs
 * on networks with high bandwidth, when sequence space is recycled fastly,
 * but it guarantees that such events will be very rare and do not affect
 * connection seriously. This doesn't look nice, but alas, PAWS is really
 * buggy extension.
 *
 * [ Later note. Even worse! It is buggy for segments _with_ data. RFC
 * states that events when retransmit arrives after original data are rare.
 * It is a blatant lie. VJ forgot about fast retransmit! 8)8) It is
 * the biggest problem on large power networks even with minor reordering.
 * OK, let's give it small replay window. If peer clock is even 1hz, it is safe
 * up to bandwidth of 18Gigabit/sec. 8) ]
 */

static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct tcphdr *th = tcp_hdr(skb);
	u32 seq = TCP_SKB_CB(skb)->seq;
	u32 ack = TCP_SKB_CB(skb)->ack_seq;

	return (/* 1. Pure ACK with correct sequence number. */
		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&

		/* 2. ... and duplicate ACK. */
		ack == tp->snd_una &&

		/* 3. ... and does not update window. */
		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&

		/* 4. ... and sits in replay window. */
		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
}

static inline bool tcp_paws_discard(const struct sock *sk,
				   const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) &&
	       !tcp_disordered_ack(sk, skb);
}

/* Check segment sequence number for validity.
 *
 * Segment controls are considered valid, if the segment
 * fits to the window after truncation to the window. Acceptability
 * of data (and SYN, FIN, of course) is checked separately.
 * See tcp_data_queue(), for example.
 *
 * Also, controls (RST is main one) are accepted using RCV.WUP instead
 * of RCV.NXT. Peer still did not advance his SND.UNA when we
 * delayed ACK, so that hisSND.UNA<=ourRCV.WUP.
 * (borrowed from freebsd)
 */

static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	return	!before(end_seq, tp->rcv_wup) &&
		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
}

/* When we get a reset we do this. */
void tcp_reset(struct sock *sk)
{
	/* We want the right error as BSD sees it (and indeed as we do). */
	switch (sk->sk_state) {
	case TCP_SYN_SENT:
		sk->sk_err = ECONNREFUSED;
		break;
	case TCP_CLOSE_WAIT:
		sk->sk_err = EPIPE;
		break;
	case TCP_CLOSE:
		return;
	default:
		sk->sk_err = ECONNRESET;
	}
	/* This barrier is coupled with smp_rmb() in tcp_poll() */
	smp_wmb();

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_error_report(sk);

	tcp_done(sk);
}

/*
 * 	Process the FIN bit. This now behaves as it is supposed to work
 *	and the FIN takes effect when it is validly part of sequence
 *	space. Not before when we get holes.
 *
 *	If we are ESTABLISHED, a received fin moves us to CLOSE-WAIT
 *	(and thence onto LAST-ACK and finally, CLOSE, we never enter
 *	TIME-WAIT)
 *
 *	If we are in FINWAIT-1, a received FIN indicates simultaneous
 *	close and we go into CLOSING (and later onto TIME-WAIT)
 *
 *	If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
 */
static void tcp_fin(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct dst_entry *dst;

	inet_csk_schedule_ack(sk);

	sk->sk_shutdown |= RCV_SHUTDOWN;
	sock_set_flag(sk, SOCK_DONE);

	switch (sk->sk_state) {
	case TCP_SYN_RECV:
	case TCP_ESTABLISHED:
		/* Move to CLOSE_WAIT */
		tcp_set_state(sk, TCP_CLOSE_WAIT);
		dst = __sk_dst_get(sk);
		if (!dst || !dst_metric(dst, RTAX_QUICKACK))
			inet_csk(sk)->icsk_ack.pingpong = 1;
		break;

	case TCP_CLOSE_WAIT:
	case TCP_CLOSING:
		/* Received a retransmission of the FIN, do
		 * nothing.
		 */
		break;
	case TCP_LAST_ACK:
		/* RFC793: Remain in the LAST-ACK state. */
		break;

	case TCP_FIN_WAIT1:
		/* This case occurs when a simultaneous close
		 * happens, we must ack the received FIN and
		 * enter the CLOSING state.
		 */
		tcp_send_ack(sk);
		tcp_set_state(sk, TCP_CLOSING);
		break;
	case TCP_FIN_WAIT2:
		/* Received a FIN -- send ACK and enter TIME_WAIT. */
		tcp_send_ack(sk);
		tcp_time_wait(sk, TCP_TIME_WAIT, 0);
		break;
	default:
		/* Only TCP_LISTEN and TCP_CLOSE are left, in these
		 * cases we should never reach this piece of code.
		 */
		pr_err("%s: Impossible, sk->sk_state=%d\n",
		       __func__, sk->sk_state);
		break;
	}

	/* It _is_ possible, that we have something out-of-order _after_ FIN.
	 * Probably, we should reset in this case. For now drop them.
	 */
	__skb_queue_purge(&tp->out_of_order_queue);
	if (tcp_is_sack(tp))
		tcp_sack_reset(&tp->rx_opt);
	sk_mem_reclaim(sk);

	if (!sock_flag(sk, SOCK_DEAD)) {
		sk->sk_state_change(sk);

		/* Do not send POLL_HUP for half duplex close. */
		if (sk->sk_shutdown == SHUTDOWN_MASK ||
		    sk->sk_state == TCP_CLOSE)
			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
		else
			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
	}
}

static inline bool tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
				  u32 end_seq)
{
	if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) {
		if (before(seq, sp->start_seq))
			sp->start_seq = seq;
		if (after(end_seq, sp->end_seq))
			sp->end_seq = end_seq;
		return true;
	}
	return false;
}

static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
		int mib_idx;

		if (before(seq, tp->rcv_nxt))
			mib_idx = LINUX_MIB_TCPDSACKOLDSENT;
		else
			mib_idx = LINUX_MIB_TCPDSACKOFOSENT;

		NET_INC_STATS_BH(sock_net(sk), mib_idx);

		tp->rx_opt.dsack = 1;
		tp->duplicate_sack[0].start_seq = seq;
		tp->duplicate_sack[0].end_seq = end_seq;
	}
}

static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!tp->rx_opt.dsack)
		tcp_dsack_set(sk, seq, end_seq);
	else
		tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}

static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
		tcp_enter_quickack_mode(sk);

		if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
			u32 end_seq = TCP_SKB_CB(skb)->end_seq;

			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
				end_seq = tp->rcv_nxt;
			tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq);
		}
	}

	tcp_send_ack(sk);
}

/* These routines update the SACK block as out-of-order packets arrive or
 * in-order packets close up the sequence space.
 */
static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
{
	int this_sack;
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	struct tcp_sack_block *swalk = sp + 1;

	/* See if the recent change to the first SACK eats into
	 * or hits the sequence space of other SACK blocks, if so coalesce.
	 */
	for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;) {
		if (tcp_sack_extend(sp, swalk->start_seq, swalk->end_seq)) {
			int i;

			/* Zap SWALK, by moving every further SACK up by one slot.
			 * Decrease num_sacks.
			 */
			tp->rx_opt.num_sacks--;
			for (i = this_sack; i < tp->rx_opt.num_sacks; i++)
				sp[i] = sp[i + 1];
			continue;
		}
		this_sack++, swalk++;
	}
}

static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int cur_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	if (!cur_sacks)
		goto new_sack;

	for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) {
		if (tcp_sack_extend(sp, seq, end_seq)) {
			/* Rotate this_sack to the first one. */
			for (; this_sack > 0; this_sack--, sp--)
				swap(*sp, *(sp - 1));
			if (cur_sacks > 1)
				tcp_sack_maybe_coalesce(tp);
			return;
		}
	}

	/* Could not find an adjacent existing SACK, build a new one,
	 * put it at the front, and shift everyone else down.  We
	 * always know there is at least one SACK present already here.
	 *
	 * If the sack array is full, forget about the last one.
	 */
	if (this_sack >= TCP_NUM_SACKS) {
		this_sack--;
		tp->rx_opt.num_sacks--;
		sp--;
	}
	for (; this_sack > 0; this_sack--, sp--)
		*sp = *(sp - 1);

new_sack:
	/* Build the new head SACK, and we're done. */
	sp->start_seq = seq;
	sp->end_seq = end_seq;
	tp->rx_opt.num_sacks++;
}

/* RCV.NXT advances, some SACKs should be eaten. */

static void tcp_sack_remove(struct tcp_sock *tp)
{
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int num_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
	if (skb_queue_empty(&tp->out_of_order_queue)) {
		tp->rx_opt.num_sacks = 0;
		return;
	}

	for (this_sack = 0; this_sack < num_sacks;) {
		/* Check if the start of the sack is covered by RCV.NXT. */
		if (!before(tp->rcv_nxt, sp->start_seq)) {
			int i;

			/* RCV.NXT must cover all the block! */
			WARN_ON(before(tp->rcv_nxt, sp->end_seq));

			/* Zap this SACK, by moving forward any other SACKS. */
			for (i=this_sack+1; i < num_sacks; i++)
				tp->selective_acks[i-1] = tp->selective_acks[i];
			num_sacks--;
			continue;
		}
		this_sack++;
		sp++;
	}
	tp->rx_opt.num_sacks = num_sacks;
}

/* This one checks to see if we can put data from the
 * out_of_order queue into the receive_queue.
 */
static void tcp_ofo_queue(struct sock *sk)