tcp_input.c

		tcp_ca_event(sk, CA_EVENT_FAST_ACK);

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

		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;
	tp->rcv_tstamp = tcp_time_stamp;
	prior_packets = tp->packets_out;
	if (!prior_packets)
		goto no_queue;

	prior_in_flight = tcp_packets_in_flight(tp);

	/* See if we can take anything off of the retransmit queue. */
	flag |= tcp_clean_rtx_queue(sk, &seq_rtt);

	/* Guarantee sacktag reordering detection against wrap-arounds */
	if (before(tp->frto_highmark, tp->snd_una))
		tp->frto_highmark = 0;
	if (tp->frto_counter)
		frto_cwnd = tcp_process_frto(sk, flag);

	if (tcp_ack_is_dubious(sk, flag)) {
		/* Advance CWND, if state allows this. */
		if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
		    tcp_may_raise_cwnd(sk, flag))
			tcp_cong_avoid(sk, ack, prior_in_flight, 0);
		tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, flag);
	} else {
		if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
			tcp_cong_avoid(sk, ack, prior_in_flight, 1);
	}

	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag&FLAG_NOT_DUP))
		dst_confirm(sk->sk_dst_cache);

	return 1;

no_queue:
	icsk->icsk_probes_out = 0;

	/* 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);
	return 1;

old_ack:
	if (TCP_SKB_CB(skb)->sacked)
		tcp_sacktag_write_queue(sk, skb, prior_snd_una);

uninteresting_ack:
	SOCK_DEBUG(sk, "Ack %u out of %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(struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab)
{
	unsigned char *ptr;
	struct tcphdr *th = tcp_hdr(skb);
	int length=(th->doff*4)-sizeof(struct tcphdr);

	ptr = (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 = ntohs(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)
						if (sysctl_tcp_window_scaling) {
							__u8 snd_wscale = *(__u8 *) ptr;
							opt_rx->wscale_ok = 1;
							if (snd_wscale > 14) {
								if (net_ratelimit())
									printk(KERN_INFO "tcp_parse_options: Illegal window "
									       "scaling value %d >14 received.\n",
									       snd_wscale);
								snd_wscale = 14;
							}
							opt_rx->snd_wscale = snd_wscale;
						}
					break;
				case TCPOPT_TIMESTAMP:
					if (opsize==TCPOLEN_TIMESTAMP) {
						if ((estab && opt_rx->tstamp_ok) ||
						    (!estab && sysctl_tcp_timestamps)) {
							opt_rx->saw_tstamp = 1;
							opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr));
							opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4)));
						}
					}
					break;
				case TCPOPT_SACK_PERM:
					if (opsize==TCPOLEN_SACK_PERM && th->syn && !estab) {
						if (sysctl_tcp_sack) {
							opt_rx->sack_ok = 1;
							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
				}

				ptr+=opsize-2;
				length-=opsize;
		}
	}
}

/* Fast parse options. This hopes to only see timestamps.
 * If it is wrong it falls back on tcp_parse_options().
 */
static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
				  struct tcp_sock *tp)
{
	if (th->doff == sizeof(struct tcphdr)>>2) {
		tp->rx_opt.saw_tstamp = 0;
		return 0;
	} else if (tp->rx_opt.tstamp_ok &&
		   th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
		__be32 *ptr = (__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;
			tp->rx_opt.rcv_tsecr = ntohl(*ptr);
			return 1;
		}
	}
	tcp_parse_options(skb, &tp->rx_opt, 1);
	return 1;
}

static inline 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 inline 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 ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
		   get_seconds() >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
			tcp_store_ts_recent(tp);
	}
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	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 int tcp_paws_discard(const struct sock *sk, const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	return ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > TCP_PAWS_WINDOW &&
		get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
		!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 int tcp_sequence(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. */
static 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;
	}

	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 sk_buff *skb, struct sock *sk, struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);

	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);
			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.
			 */
			printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
			       __FUNCTION__, 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_stream_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, 1, POLL_HUP);
		else
			sk_wake_async(sk, 1, POLL_IN);
	}
}

static inline int 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 1;
	}
	return 0;
}

static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
		if (before(seq, tp->rcv_nxt))
			NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT);
		else
			NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFOSENT);

		tp->rx_opt.dsack = 1;
		tp->duplicate_sack[0].start_seq = seq;
		tp->duplicate_sack[0].end_seq = end_seq;
		tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + 1, 4 - tp->rx_opt.tstamp_ok);
	}
}

static void tcp_dsack_extend(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	if (!tp->rx_opt.dsack)
		tcp_dsack_set(tp, seq, end_seq);
	else
		tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}

static void tcp_send_dupack(struct sock *sk, 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(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(tp, 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--;
			tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
			for (i=this_sack; i < tp->rx_opt.num_sacks; i++)
				sp[i] = sp[i+1];
			continue;
		}
		this_sack++, swalk++;
	}
}

static inline void tcp_sack_swap(struct tcp_sack_block *sack1, struct tcp_sack_block *sack2)
{
	__u32 tmp;

	tmp = sack1->start_seq;
	sack1->start_seq = sack2->start_seq;
	sack2->start_seq = tmp;

	tmp = sack1->end_seq;
	sack1->end_seq = sack2->end_seq;
	sack2->end_seq = tmp;
}

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--)
				tcp_sack_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 >= 4) {
		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++;
	tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
}

/* 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;
		tp->rx_opt.eff_sacks = tp->rx_opt.dsack;
		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! */
			BUG_TRAP(!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++;
	}
	if (num_sacks != tp->rx_opt.num_sacks) {
		tp->rx_opt.num_sacks = num_sacks;
		tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
	}
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	__u32 dsack_high = tp->rcv_nxt;
	struct sk_buff *skb;

	while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
			break;

		if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
			__u32 dsack = dsack_high;
			if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
				dsack_high = TCP_SKB_CB(skb)->end_seq;
			tcp_dsack_extend(tp, TCP_SKB_CB(skb)->seq, dsack);
		}

		if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
			SOCK_DEBUG(sk, "ofo packet was already received \n");
			__skb_unlink(skb, &tp->out_of_order_queue);
			__kfree_skb(skb);
			continue;
		}
		SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		__skb_unlink(skb, &tp->out_of_order_queue);
		__skb_queue_tail(&sk->sk_receive_queue, skb);
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		if (tcp_hdr(skb)->fin)
			tcp_fin(skb, sk, tcp_hdr(skb));
	}
}

static int tcp_prune_queue(struct sock *sk);

static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = tcp_hdr(skb);
	struct tcp_sock *tp = tcp_sk(sk);
	int eaten = -1;

	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
		goto drop;

	__skb_pull(skb, th->doff*4);

	TCP_ECN_accept_cwr(tp, skb);

	if (tp->rx_opt.dsack) {
		tp->rx_opt.dsack = 0;
		tp->rx_opt.eff_sacks = min_t(unsigned int, tp->rx_opt.num_sacks,
						    4 - tp->rx_opt.tstamp_ok);
	}

	/*  Queue data for delivery to the user.
	 *  Packets in sequence go to the receive queue.
	 *  Out of sequence packets to the out_of_order_queue.
	 */
	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
		if (tcp_receive_window(tp) == 0)
			goto out_of_window;

		/* Ok. In sequence. In window. */
		if (tp->ucopy.task == current &&
		    tp->copied_seq == tp->rcv_nxt && tp->ucopy.len &&
		    sock_owned_by_user(sk) && !tp->urg_data) {
			int chunk = min_t(unsigned int, skb->len,
							tp->ucopy.len);

			__set_current_state(TASK_RUNNING);

			local_bh_enable();
			if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) {
				tp->ucopy.len -= chunk;
				tp->copied_seq += chunk;
				eaten = (chunk == skb->len && !th->fin);
				tcp_rcv_space_adjust(sk);
			}
			local_bh_disable();
		}

		if (eaten <= 0) {
queue_and_out:
			if (eaten < 0 &&
			    (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
			     !sk_stream_rmem_schedule(sk, skb))) {
				if (tcp_prune_queue(sk) < 0 ||
				    !sk_stream_rmem_schedule(sk, skb))
					goto drop;
			}
			sk_stream_set_owner_r(skb, sk);
			__skb_queue_tail(&sk->sk_receive_queue, skb);
		}
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		if (skb->len)
			tcp_event_data_recv(sk, skb);
		if (th->fin)
			tcp_fin(skb, sk, th);

		if (!skb_queue_empty(&tp->out_of_order_queue)) {
			tcp_ofo_queue(sk);

			/* RFC2581. 4.2. SHOULD send immediate ACK, when
			 * gap in queue is filled.
			 */
			if (skb_queue_empty(&tp->out_of_order_queue))
				inet_csk(sk)->icsk_ack.pingpong = 0;
		}

		if (tp->rx_opt.num_sacks)
			tcp_sack_remove(tp);

		tcp_fast_path_check(sk);

		if (eaten > 0)
			__kfree_skb(skb);
		else if (!sock_flag(sk, SOCK_DEAD))
			sk->sk_data_ready(sk, 0);
		return;
	}

	if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
		/* A retransmit, 2nd most common case.  Force an immediate ack. */
		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOST);
		tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);

out_of_window:
		tcp_enter_quickack_mode(sk);
		inet_csk_schedule_ack(sk);
drop:
		__kfree_skb(skb);
		return;
	}

	/* Out of window. F.e. zero window probe. */
	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
		goto out_of_window;

	tcp_enter_quickack_mode(sk);

	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		/* Partial packet, seq < rcv_next < end_seq */
		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, tp->rcv_nxt);

		/* If window is closed, drop tail of packet. But after
		 * remembering D-SACK for its head made in previous line.
		 */
		if (!tcp_receive_window(tp))
			goto out_of_window;
		goto queue_and_out;
	}

	TCP_ECN_check_ce(tp, skb);

	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
	    !sk_stream_rmem_schedule(sk, skb)) {
		if (tcp_prune_queue(sk) < 0 ||
		    !sk_stream_rmem_schedule(sk, skb))
			goto drop;
	}

	/* Disable header prediction. */
	tp->pred_flags = 0;
	inet_csk_schedule_ack(sk);

	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
		   tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);

	sk_stream_set_owner_r(skb, sk);

	if (!skb_peek(&tp->out_of_order_queue)) {
		/* Initial out of order segment, build 1 SACK. */
		if (tcp_is_sack(tp)) {
			tp->rx_opt.num_sacks = 1;
			tp->rx_opt.dsack     = 0;
			tp->rx_opt.eff_sacks = 1;
			tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
			tp->selective_acks[0].end_seq =
						TCP_SKB_CB(skb)->end_seq;
		}
		__skb_queue_head(&tp->out_of_order_queue,skb);
	} else {
		struct sk_buff *skb1 = tp->out_of_order_queue.prev;
		u32 seq = TCP_SKB_CB(skb)->seq;
		u32 end_seq = TCP_SKB_CB(skb)->end_seq;

		if (seq == TCP_SKB_CB(skb1)->end_seq) {
			__skb_append(skb1, skb, &tp->out_of_order_queue);

			if (!tp->rx_opt.num_sacks ||
			    tp->selective_acks[0].end_seq != seq)
				goto add_sack;

			/* Common case: data arrive in order after hole. */
			tp->selective_acks[0].end_seq = end_seq;
			return;
		}

		/* Find place to insert this segment. */
		do {
			if (!after(TCP_SKB_CB(skb1)->seq, seq))
				break;
		} while ((skb1 = skb1->prev) !=
			 (struct sk_buff*)&tp->out_of_order_queue);

		/* Do skb overlap to previous one? */
		if (skb1 != (struct sk_buff*)&tp->out_of_order_queue &&
		    before(seq, TCP_SKB_CB(skb1)->end_seq)) {
			if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
				/* All the bits are present. Drop. */
				__kfree_skb(skb);
				tcp_dsack_set(tp, seq, end_seq);
				goto add_sack;
			}
			if (after(seq, TCP_SKB_CB(skb1)->seq)) {
				/* Partial overlap. */
				tcp_dsack_set(tp, seq, TCP_SKB_CB(skb1)->end_seq);
			} else {
				skb1 = skb1->prev;
			}
		}
		__skb_insert(skb, skb1, skb1->next, &tp->out_of_order_queue);

		/* And clean segments covered by new one as whole. */
		while ((skb1 = skb->next) !=
		       (struct sk_buff*)&tp->out_of_order_queue &&
		       after(end_seq, TCP_SKB_CB(skb1)->seq)) {
		       if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
			       tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, end_seq);
			       break;
		       }
		       __skb_unlink(skb1, &tp->out_of_order_queue);
		       tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq);
		       __kfree_skb(skb1);
		}

add_sack:
		if (tcp_is_sack(tp))
			tcp_sack_new_ofo_skb(sk, seq, end_seq);
	}
}

/* Collapse contiguous sequence of skbs head..tail with
 * sequence numbers start..end.
 * Segments with FIN/SYN are not collapsed (only because this
 * simplifies code)
 */
static void
tcp_collapse(struct sock *sk, struct sk_buff_head *list,
	     struct sk_buff *head, struct sk_buff *tail,
	     u32 start, u32 end)
{
	struct sk_buff *skb;

	/* First, check that queue is collapsible and find
	 * the point where collapsing can be useful. */
	for (skb = head; skb != tail; ) {
		/* No new bits? It is possible on ofo queue. */
		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
			struct sk_buff *next = skb->next;
			__skb_unlink(skb, list);
			__kfree_skb(skb);
			NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
			skb = next;
			continue;
		}

		/* The first skb to collapse is:
		 * - not SYN/FIN and
		 * - bloated or contains data before "start" or
		 *   overlaps to the next one.
		 */
		if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
		    (tcp_win_from_space(skb->truesize) > skb->len ||
		     before(TCP_SKB_CB(skb)->seq, start) ||
		     (skb->next != tail &&
		      TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb->next)->seq)))
			break;

		/* Decided to skip this, advance start seq. */
		start = TCP_SKB_CB(skb)->end_seq;
		skb = skb->next;
	}
	if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
		return;

	while (before(start, end)) {
		struct sk_buff *nskb;
		int header = skb_headroom(skb);
		int copy = SKB_MAX_ORDER(header, 0);

		/* Too big header? This can happen with IPv6. */
		if (copy < 0)
			return;
		if (end-start < copy)
			copy = end-start;
		nskb = alloc_skb(copy+header, GFP_ATOMIC);
		if (!nskb)
			return;

		skb_set_mac_header(nskb, skb_mac_header(skb) - skb->head);
		skb_set_network_header(nskb, (skb_network_header(skb) -
					      skb->head));
		skb_set_transport_header(nskb, (skb_transport_header(skb) -
						skb->head));
		skb_reserve(nskb, header);
		memcpy(nskb->head, skb->head, header);
		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
		__skb_insert(nskb, skb->prev, skb, list);
		sk_stream_set_owner_r(nskb, sk);

		/* Copy data, releasing collapsed skbs. */
		while (copy > 0) {
			int offset = start - TCP_SKB_CB(skb)->seq;
			int size = TCP_SKB_CB(skb)->end_seq - start;

			BUG_ON(offset < 0);
			if (size > 0) {
				size = min(copy, size);
				if (skb_copy_bits(skb, offset, skb_put(nskb, size), size))
					BUG();
				TCP_SKB_CB(nskb)->end_seq += size;
				copy -= size;
				start += size;
			}
			if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
				struct sk_buff *next = skb->next;
				__skb_unlink(skb, list);
				__kfree_skb(skb);
				NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
				skb = next;
				if (skb == tail ||
				    tcp_hdr(skb)->syn ||
				    tcp_hdr(skb)->fin)
					return;
			}
		}
	}
}

/* Collapse ofo queue. Algorithm: select contiguous sequence of skbs
 * and tcp_collapse() them until all the queue is collapsed.
 */
static void tcp_collapse_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = skb_peek(&tp->out_of_order_queue);
	struct sk_buff *head;
	u32 start, end;

	if (skb == NULL)
		return;

	start = TCP_SKB_CB(skb)->seq;
	end = TCP_SKB_CB(skb)->end_seq;
	head = skb;

	for (;;) {
		skb = skb->next;

		/* Segment is terminated when we see gap or when
		 * we are at the end of all the queue. */
		if (skb == (struct sk_buff *)&tp->out_of_order_queue ||
		    after(TCP_SKB_CB(skb)->seq, end) ||
		    before(TCP_SKB_CB(skb)->end_seq, start)) {
			tcp_collapse(sk, &tp->out_of_order_queue,
				     head, skb, start, end);
			head = skb;
			if (skb == (struct sk_buff *)&tp->out_of_order_queue)
				break;
			/* Start new segment */
			start = TCP_SKB_CB(skb)->seq;
			end = TCP_SKB_CB(skb)->end_seq;
		} else {
			if (before(TCP_SKB_CB(skb)->seq, start))
				start = TCP_SKB_CB(skb)->seq;
			if (after(TCP_SKB_CB(skb)->end_seq, end))
				end = TCP_SKB_CB(skb)->end_seq;
		}
	}
}

/* Reduce allocated memory if we can, trying to get
 * the socket within its memory limits again.
 *
 * Return less than zero if we should start dropping frames
 * until the socket owning process reads some of the data
 * to stabilize the situation.
 */
static int tcp_prune_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq);

	NET_INC_STATS_BH(LINUX_MIB_PRUNECALLED);

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		tcp_clamp_window(sk);
	else if (tcp_memory_pressure)
		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);

	tcp_collapse_ofo_queue(sk);
	tcp_collapse(sk, &sk->sk_receive_queue,
		     sk->sk_receive_queue.next,
		     (struct sk_buff*)&sk->sk_receive_queue,
		     tp->copied_seq, tp->rcv_nxt);
	sk_stream_mem_reclaim(sk);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;