tcp_input.c

	 * or we break the semantics of SIOCATMARK (and thus sockatmark())
	 *
	 * NOTE. Double Dutch. Rendering to plain English: author of comment
	 * above did something sort of 	send("A", MSG_OOB); send("B", MSG_OOB);
	 * and expect that both A and B disappear from stream. This is _wrong_.
	 * Though this happens in BSD with high probability, this is occasional.
	 * Any application relying on this is buggy. Note also, that fix "works"
	 * only in this artificial test. Insert some normal data between A and B and we will
	 * decline of BSD again. Verdict: it is better to remove to trap
	 * buggy users.
	 */
	if (tp->urg_seq == tp->copied_seq && tp->urg_data &&
	    !sock_flag(sk, SOCK_URGINLINE) && tp->copied_seq != tp->rcv_nxt) {
		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
		tp->copied_seq++;
		if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) {
			__skb_unlink(skb, &sk->sk_receive_queue);
			__kfree_skb(skb);
		}
	}

	tp->urg_data = TCP_URG_NOTYET;
	tp->urg_seq = ptr;

	/* Disable header prediction. */
	tp->pred_flags = 0;
}

/* This is the 'fast' part of urgent handling. */
static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Check if we get a new urgent pointer - normally not. */
	if (th->urg)
		tcp_check_urg(sk, th);

	/* Do we wait for any urgent data? - normally not... */
	if (tp->urg_data == TCP_URG_NOTYET) {
		u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
			  th->syn;

		/* Is the urgent pointer pointing into this packet? */
		if (ptr < skb->len) {
			u8 tmp;
			if (skb_copy_bits(skb, ptr, &tmp, 1))
				BUG();
			tp->urg_data = TCP_URG_VALID | tmp;
			if (!sock_flag(sk, SOCK_DEAD))
				sk->sk_data_ready(sk, 0);
		}
	}
}

static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int chunk = skb->len - hlen;
	int err;

	local_bh_enable();
	if (skb_csum_unnecessary(skb))
		err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
	else
		err = skb_copy_and_csum_datagram_iovec(skb, hlen,
						       tp->ucopy.iov);

	if (!err) {
		tp->ucopy.len -= chunk;
		tp->copied_seq += chunk;
		tcp_rcv_space_adjust(sk);
	}

	local_bh_disable();
	return err;
}

static __sum16 __tcp_checksum_complete_user(struct sock *sk,
					    struct sk_buff *skb)
{
	__sum16 result;

	if (sock_owned_by_user(sk)) {
		local_bh_enable();
		result = __tcp_checksum_complete(skb);
		local_bh_disable();
	} else {
		result = __tcp_checksum_complete(skb);
	}
	return result;
}

static inline int tcp_checksum_complete_user(struct sock *sk,
					     struct sk_buff *skb)
{
	return !skb_csum_unnecessary(skb) &&
	       __tcp_checksum_complete_user(sk, skb);
}

#ifdef CONFIG_NET_DMA
static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
				  int hlen)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int chunk = skb->len - hlen;
	int dma_cookie;
	int copied_early = 0;

	if (tp->ucopy.wakeup)
		return 0;

	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
		tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);

	if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {

		dma_cookie = dma_skb_copy_datagram_iovec(tp->ucopy.dma_chan,
							 skb, hlen,
							 tp->ucopy.iov, chunk,
							 tp->ucopy.pinned_list);

		if (dma_cookie < 0)
			goto out;

		tp->ucopy.dma_cookie = dma_cookie;
		copied_early = 1;

		tp->ucopy.len -= chunk;
		tp->copied_seq += chunk;
		tcp_rcv_space_adjust(sk);

		if ((tp->ucopy.len == 0) ||
		    (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
		    (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
			tp->ucopy.wakeup = 1;
			sk->sk_data_ready(sk, 0);
		}
	} else if (chunk > 0) {
		tp->ucopy.wakeup = 1;
		sk->sk_data_ready(sk, 0);
	}
out:
	return copied_early;
}
#endif /* CONFIG_NET_DMA */

/* Does PAWS and seqno based validation of an incoming segment, flags will
 * play significant role here.
 */
static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
			      struct tcphdr *th, int syn_inerr)
{
	u8 *hash_location;
	struct tcp_sock *tp = tcp_sk(sk);

	/* RFC1323: H1. Apply PAWS check first. */
	if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
	    tp->rx_opt.saw_tstamp &&
	    tcp_paws_discard(sk, skb)) {
		if (!th->rst) {
			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
			tcp_send_dupack(sk, skb);
			goto discard;
		}
		/* Reset is accepted even if it did not pass PAWS. */
	}

	/* Step 1: check sequence number */
	if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) {
		/* RFC793, page 37: "In all states except SYN-SENT, all reset
		 * (RST) segments are validated by checking their SEQ-fields."
		 * And page 69: "If an incoming segment is not acceptable,
		 * an acknowledgment should be sent in reply (unless the RST
		 * bit is set, if so drop the segment and return)".
		 */
		if (!th->rst)
			tcp_send_dupack(sk, skb);
		goto discard;
	}

	/* Step 2: check RST bit */
	if (th->rst) {
		tcp_reset(sk);
		goto discard;
	}

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

	/* step 3: check security and precedence [ignored] */

	/* step 4: Check for a SYN in window. */
	if (th->syn && !before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		if (syn_inerr)
			TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONSYN);
		tcp_reset(sk);
		return -1;
	}

	return 1;

discard:
	__kfree_skb(skb);
	return 0;
}

/*
 *	TCP receive function for the ESTABLISHED state.
 *
 *	It is split into a fast path and a slow path. The fast path is
 * 	disabled when:
 *	- A zero window was announced from us - zero window probing
 *        is only handled properly in the slow path.
 *	- Out of order segments arrived.
 *	- Urgent data is expected.
 *	- There is no buffer space left
 *	- Unexpected TCP flags/window values/header lengths are received
 *	  (detected by checking the TCP header against pred_flags)
 *	- Data is sent in both directions. Fast path only supports pure senders
 *	  or pure receivers (this means either the sequence number or the ack
 *	  value must stay constant)
 *	- Unexpected TCP option.
 *
 *	When these conditions are not satisfied it drops into a standard
 *	receive procedure patterned after RFC793 to handle all cases.
 *	The first three cases are guaranteed by proper pred_flags setting,
 *	the rest is checked inline. Fast processing is turned on in
 *	tcp_data_queue when everything is OK.
 */
int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
			struct tcphdr *th, unsigned len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int res;

	/*
	 *	Header prediction.
	 *	The code loosely follows the one in the famous
	 *	"30 instruction TCP receive" Van Jacobson mail.
	 *
	 *	Van's trick is to deposit buffers into socket queue
	 *	on a device interrupt, to call tcp_recv function
	 *	on the receive process context and checksum and copy
	 *	the buffer to user space. smart...
	 *
	 *	Our current scheme is not silly either but we take the
	 *	extra cost of the net_bh soft interrupt processing...
	 *	We do checksum and copy also but from device to kernel.
	 */

	tp->rx_opt.saw_tstamp = 0;

	/*	pred_flags is 0xS?10 << 16 + snd_wnd
	 *	if header_prediction is to be made
	 *	'S' will always be tp->tcp_header_len >> 2
	 *	'?' will be 0 for the fast path, otherwise pred_flags is 0 to
	 *  turn it off	(when there are holes in the receive
	 *	 space for instance)
	 *	PSH flag is ignored.
	 */

	if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
	    TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
	    !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
		int tcp_header_len = tp->tcp_header_len;

		/* Timestamp header prediction: tcp_header_len
		 * is automatically equal to th->doff*4 due to pred_flags
		 * match.
		 */

		/* Check timestamp */
		if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
			/* No? Slow path! */
			if (!tcp_parse_aligned_timestamp(tp, th))
				goto slow_path;

			/* If PAWS failed, check it more carefully in slow path */
			if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
				goto slow_path;

			/* DO NOT update ts_recent here, if checksum fails
			 * and timestamp was corrupted part, it will result
			 * in a hung connection since we will drop all
			 * future packets due to the PAWS test.
			 */
		}

		if (len <= tcp_header_len) {
			/* Bulk data transfer: sender */
			if (len == tcp_header_len) {
				/* Predicted packet is in window by definition.
				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
				 * Hence, check seq<=rcv_wup reduces to:
				 */
				if (tcp_header_len ==
				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
				    tp->rcv_nxt == tp->rcv_wup)
					tcp_store_ts_recent(tp);

				/* We know that such packets are checksummed
				 * on entry.
				 */
				tcp_ack(sk, skb, 0);
				__kfree_skb(skb);
				tcp_data_snd_check(sk);
				return 0;
			} else { /* Header too small */
				TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
				goto discard;
			}
		} else {
			int eaten = 0;
			int copied_early = 0;

			if (tp->copied_seq == tp->rcv_nxt &&
			    len - tcp_header_len <= tp->ucopy.len) {
#ifdef CONFIG_NET_DMA
				if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
					copied_early = 1;
					eaten = 1;
				}
#endif
				if (tp->ucopy.task == current &&
				    sock_owned_by_user(sk) && !copied_early) {
					__set_current_state(TASK_RUNNING);

					if (!tcp_copy_to_iovec(sk, skb, tcp_header_len))
						eaten = 1;
				}
				if (eaten) {
					/* Predicted packet is in window by definition.
					 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
					 * Hence, check seq<=rcv_wup reduces to:
					 */
					if (tcp_header_len ==
					    (sizeof(struct tcphdr) +
					     TCPOLEN_TSTAMP_ALIGNED) &&
					    tp->rcv_nxt == tp->rcv_wup)
						tcp_store_ts_recent(tp);

					tcp_rcv_rtt_measure_ts(sk, skb);

					__skb_pull(skb, tcp_header_len);
					tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
					NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
				}
				if (copied_early)
					tcp_cleanup_rbuf(sk, skb->len);
			}
			if (!eaten) {
				if (tcp_checksum_complete_user(sk, skb))
					goto csum_error;

				/* Predicted packet is in window by definition.
				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
				 * Hence, check seq<=rcv_wup reduces to:
				 */
				if (tcp_header_len ==
				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
				    tp->rcv_nxt == tp->rcv_wup)
					tcp_store_ts_recent(tp);

				tcp_rcv_rtt_measure_ts(sk, skb);

				if ((int)skb->truesize > sk->sk_forward_alloc)
					goto step5;

				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);

				/* Bulk data transfer: receiver */
				__skb_pull(skb, tcp_header_len);
				__skb_queue_tail(&sk->sk_receive_queue, skb);
				skb_set_owner_r(skb, sk);
				tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
			}

			tcp_event_data_recv(sk, skb);

			if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
				/* Well, only one small jumplet in fast path... */
				tcp_ack(sk, skb, FLAG_DATA);
				tcp_data_snd_check(sk);
				if (!inet_csk_ack_scheduled(sk))
					goto no_ack;
			}

			if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
				__tcp_ack_snd_check(sk, 0);
no_ack:
#ifdef CONFIG_NET_DMA
			if (copied_early)
				__skb_queue_tail(&sk->sk_async_wait_queue, skb);
			else
#endif
			if (eaten)
				__kfree_skb(skb);
			else
				sk->sk_data_ready(sk, 0);
			return 0;
		}
	}

slow_path:
	if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb))
		goto csum_error;

	/*
	 *	Standard slow path.
	 */

	res = tcp_validate_incoming(sk, skb, th, 1);
	if (res <= 0)
		return -res;

step5:
	if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
		goto discard;

	tcp_rcv_rtt_measure_ts(sk, skb);

	/* Process urgent data. */
	tcp_urg(sk, skb, th);

	/* step 7: process the segment text */
	tcp_data_queue(sk, skb);

	tcp_data_snd_check(sk);
	tcp_ack_snd_check(sk);
	return 0;

csum_error:
	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);

discard:
	__kfree_skb(skb);
	return 0;
}
EXPORT_SYMBOL(tcp_rcv_established);

static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
					 struct tcphdr *th, unsigned len)
{
	u8 *hash_location;
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_cookie_values *cvp = tp->cookie_values;
	int saved_clamp = tp->rx_opt.mss_clamp;

	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);

	if (th->ack) {
		/* rfc793:
		 * "If the state is SYN-SENT then
		 *    first check the ACK bit
		 *      If the ACK bit is set
		 *	  If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send
		 *        a reset (unless the RST bit is set, if so drop
		 *        the segment and return)"
		 *
		 *  We do not send data with SYN, so that RFC-correct
		 *  test reduces to:
		 */
		if (TCP_SKB_CB(skb)->ack_seq != tp->snd_nxt)
			goto reset_and_undo;

		if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
		    !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp,
			     tcp_time_stamp)) {
			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED);
			goto reset_and_undo;
		}

		/* Now ACK is acceptable.
		 *
		 * "If the RST bit is set
		 *    If the ACK was acceptable then signal the user "error:
		 *    connection reset", drop the segment, enter CLOSED state,
		 *    delete TCB, and return."
		 */

		if (th->rst) {
			tcp_reset(sk);
			goto discard;
		}

		/* rfc793:
		 *   "fifth, if neither of the SYN or RST bits is set then
		 *    drop the segment and return."
		 *
		 *    See note below!
		 *                                        --ANK(990513)
		 */
		if (!th->syn)
			goto discard_and_undo;

		/* rfc793:
		 *   "If the SYN bit is on ...
		 *    are acceptable then ...
		 *    (our SYN has been ACKed), change the connection
		 *    state to ESTABLISHED..."
		 */

		TCP_ECN_rcv_synack(tp, th);

		tp->snd_wl1 = TCP_SKB_CB(skb)->seq;
		tcp_ack(sk, skb, FLAG_SLOWPATH);

		/* Ok.. it's good. Set up sequence numbers and
		 * move to established.
		 */
		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;

		/* RFC1323: The window in SYN & SYN/ACK segments is
		 * never scaled.
		 */
		tp->snd_wnd = ntohs(th->window);
		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);

		if (!tp->rx_opt.wscale_ok) {
			tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0;
			tp->window_clamp = min(tp->window_clamp, 65535U);
		}

		if (tp->rx_opt.saw_tstamp) {
			tp->rx_opt.tstamp_ok	   = 1;
			tp->tcp_header_len =
				sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
			tp->advmss	    -= TCPOLEN_TSTAMP_ALIGNED;
			tcp_store_ts_recent(tp);
		} else {
			tp->tcp_header_len = sizeof(struct tcphdr);
		}

		if (tcp_is_sack(tp) && sysctl_tcp_fack)
			tcp_enable_fack(tp);

		tcp_mtup_init(sk);
		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
		tcp_initialize_rcv_mss(sk);

		/* Remember, tcp_poll() does not lock socket!
		 * Change state from SYN-SENT only after copied_seq
		 * is initialized. */
		tp->copied_seq = tp->rcv_nxt;

		if (cvp != NULL &&
		    cvp->cookie_pair_size > 0 &&
		    tp->rx_opt.cookie_plus > 0) {
			int cookie_size = tp->rx_opt.cookie_plus
					- TCPOLEN_COOKIE_BASE;
			int cookie_pair_size = cookie_size
					     + cvp->cookie_desired;

			/* A cookie extension option was sent and returned.
			 * Note that each incoming SYNACK replaces the
			 * Responder cookie.  The initial exchange is most
			 * fragile, as protection against spoofing relies
			 * entirely upon the sequence and timestamp (above).
			 * This replacement strategy allows the correct pair to
			 * pass through, while any others will be filtered via
			 * Responder verification later.
			 */
			if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
				memcpy(&cvp->cookie_pair[cvp->cookie_desired],
				       hash_location, cookie_size);
				cvp->cookie_pair_size = cookie_pair_size;
			}
		}

		smp_mb();
		tcp_set_state(sk, TCP_ESTABLISHED);

		security_inet_conn_established(sk, skb);

		/* Make sure socket is routed, for correct metrics.  */
		icsk->icsk_af_ops->rebuild_header(sk);

		tcp_init_metrics(sk);

		tcp_init_congestion_control(sk);

		/* Prevent spurious tcp_cwnd_restart() on first data
		 * packet.
		 */
		tp->lsndtime = tcp_time_stamp;

		tcp_init_buffer_space(sk);

		if (sock_flag(sk, SOCK_KEEPOPEN))
			inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));

		if (!tp->rx_opt.snd_wscale)
			__tcp_fast_path_on(tp, tp->snd_wnd);
		else
			tp->pred_flags = 0;

		if (!sock_flag(sk, SOCK_DEAD)) {
			sk->sk_state_change(sk);
			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
		}

		if (sk->sk_write_pending ||
		    icsk->icsk_accept_queue.rskq_defer_accept ||
		    icsk->icsk_ack.pingpong) {
			/* Save one ACK. Data will be ready after
			 * several ticks, if write_pending is set.
			 *
			 * It may be deleted, but with this feature tcpdumps
			 * look so _wonderfully_ clever, that I was not able
			 * to stand against the temptation 8)     --ANK
			 */
			inet_csk_schedule_ack(sk);
			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
			icsk->icsk_ack.ato	 = TCP_ATO_MIN;
			tcp_incr_quickack(sk);
			tcp_enter_quickack_mode(sk);
			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
						  TCP_DELACK_MAX, TCP_RTO_MAX);

discard:
			__kfree_skb(skb);
			return 0;
		} else {
			tcp_send_ack(sk);
		}
		return -1;
	}

	/* No ACK in the segment */

	if (th->rst) {
		/* rfc793:
		 * "If the RST bit is set
		 *
		 *      Otherwise (no ACK) drop the segment and return."
		 */

		goto discard_and_undo;
	}

	/* PAWS check. */
	if (tp->rx_opt.ts_recent_stamp && tp->rx_opt.saw_tstamp &&
	    tcp_paws_reject(&tp->rx_opt, 0))
		goto discard_and_undo;

	if (th->syn) {
		/* We see SYN without ACK. It is attempt of
		 * simultaneous connect with crossed SYNs.
		 * Particularly, it can be connect to self.
		 */
		tcp_set_state(sk, TCP_SYN_RECV);

		if (tp->rx_opt.saw_tstamp) {
			tp->rx_opt.tstamp_ok = 1;
			tcp_store_ts_recent(tp);
			tp->tcp_header_len =
				sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
		} else {
			tp->tcp_header_len = sizeof(struct tcphdr);
		}

		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;

		/* RFC1323: The window in SYN & SYN/ACK segments is
		 * never scaled.
		 */
		tp->snd_wnd    = ntohs(th->window);
		tp->snd_wl1    = TCP_SKB_CB(skb)->seq;
		tp->max_window = tp->snd_wnd;

		TCP_ECN_rcv_syn(tp, th);

		tcp_mtup_init(sk);
		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
		tcp_initialize_rcv_mss(sk);

		tcp_send_synack(sk);
#if 0
		/* Note, we could accept data and URG from this segment.
		 * There are no obstacles to make this.
		 *
		 * However, if we ignore data in ACKless segments sometimes,
		 * we have no reasons to accept it sometimes.
		 * Also, seems the code doing it in step6 of tcp_rcv_state_process
		 * is not flawless. So, discard packet for sanity.
		 * Uncomment this return to process the data.
		 */
		return -1;
#else
		goto discard;
#endif
	}
	/* "fifth, if neither of the SYN or RST bits is set then
	 * drop the segment and return."
	 */

discard_and_undo:
	tcp_clear_options(&tp->rx_opt);
	tp->rx_opt.mss_clamp = saved_clamp;
	goto discard;

reset_and_undo:
	tcp_clear_options(&tp->rx_opt);
	tp->rx_opt.mss_clamp = saved_clamp;
	return 1;
}

/*
 *	This function implements the receiving procedure of RFC 793 for
 *	all states except ESTABLISHED and TIME_WAIT.
 *	It's called from both tcp_v4_rcv and tcp_v6_rcv and should be
 *	address independent.
 */

int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
			  struct tcphdr *th, unsigned len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	int queued = 0;
	int res;

	tp->rx_opt.saw_tstamp = 0;

	switch (sk->sk_state) {
	case TCP_CLOSE:
		goto discard;

	case TCP_LISTEN:
		if (th->ack)
			return 1;

		if (th->rst)
			goto discard;

		if (th->syn) {
			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
				return 1;

			/* Now we have several options: In theory there is
			 * nothing else in the frame. KA9Q has an option to
			 * send data with the syn, BSD accepts data with the
			 * syn up to the [to be] advertised window and
			 * Solaris 2.1 gives you a protocol error. For now
			 * we just ignore it, that fits the spec precisely
			 * and avoids incompatibilities. It would be nice in
			 * future to drop through and process the data.
			 *
			 * Now that TTCP is starting to be used we ought to
			 * queue this data.
			 * But, this leaves one open to an easy denial of
			 * service attack, and SYN cookies can't defend
			 * against this problem. So, we drop the data
			 * in the interest of security over speed unless
			 * it's still in use.
			 */
			kfree_skb(skb);
			return 0;
		}
		goto discard;

	case TCP_SYN_SENT:
		queued = tcp_rcv_synsent_state_process(sk, skb, th, len);
		if (queued >= 0)
			return queued;

		/* Do step6 onward by hand. */
		tcp_urg(sk, skb, th);
		__kfree_skb(skb);
		tcp_data_snd_check(sk);
		return 0;
	}

	res = tcp_validate_incoming(sk, skb, th, 0);
	if (res <= 0)
		return -res;

	/* step 5: check the ACK field */
	if (th->ack) {
		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;

		switch (sk->sk_state) {
		case TCP_SYN_RECV:
			if (acceptable) {
				tp->copied_seq = tp->rcv_nxt;
				smp_mb();
				tcp_set_state(sk, TCP_ESTABLISHED);
				sk->sk_state_change(sk);

				/* Note, that this wakeup is only for marginal
				 * crossed SYN case. Passively open sockets
				 * are not waked up, because sk->sk_sleep ==
				 * NULL and sk->sk_socket == NULL.
				 */
				if (sk->sk_socket)
					sk_wake_async(sk,
						      SOCK_WAKE_IO, POLL_OUT);

				tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
				tp->snd_wnd = ntohs(th->window) <<
					      tp->rx_opt.snd_wscale;
				tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);

				/* tcp_ack considers this ACK as duplicate
				 * and does not calculate rtt.
				 * Force it here.
				 */
				tcp_ack_update_rtt(sk, 0, 0);

				if (tp->rx_opt.tstamp_ok)
					tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;

				/* Make sure socket is routed, for
				 * correct metrics.
				 */
				icsk->icsk_af_ops->rebuild_header(sk);

				tcp_init_metrics(sk);

				tcp_init_congestion_control(sk);

				/* Prevent spurious tcp_cwnd_restart() on
				 * first data packet.
				 */
				tp->lsndtime = tcp_time_stamp;

				tcp_mtup_init(sk);
				tcp_initialize_rcv_mss(sk);
				tcp_init_buffer_space(sk);
				tcp_fast_path_on(tp);
			} else {
				return 1;
			}
			break;

		case TCP_FIN_WAIT1:
			if (tp->snd_una == tp->write_seq) {
				tcp_set_state(sk, TCP_FIN_WAIT2);
				sk->sk_shutdown |= SEND_SHUTDOWN;
				dst_confirm(__sk_dst_get(sk));

				if (!sock_flag(sk, SOCK_DEAD))
					/* Wake up lingering close() */
					sk->sk_state_change(sk);
				else {
					int tmo;

					if (tp->linger2 < 0 ||
					    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
					     after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
						tcp_done(sk);
						NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
						return 1;
					}

					tmo = tcp_fin_time(sk);
					if (tmo > TCP_TIMEWAIT_LEN) {
						inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
					} else if (th->fin || sock_owned_by_user(sk)) {
						/* Bad case. We could lose such FIN otherwise.
						 * It is not a big problem, but it looks confusing
						 * and not so rare event. We still can lose it now,
						 * if it spins in bh_lock_sock(), but it is really
						 * marginal case.
						 */
						inet_csk_reset_keepalive_timer(sk, tmo);
					} else {
						tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
						goto discard;
					}
				}
			}
			break;

		case TCP_CLOSING:
			if (tp->snd_una == tp->write_seq) {
				tcp_time_wait(sk, TCP_TIME_WAIT, 0);
				goto discard;
			}
			break;

		case TCP_LAST_ACK:
			if (tp->snd_una == tp->write_seq) {
				tcp_update_metrics(sk);
				tcp_done(sk);
				goto discard;
			}
			break;
		}
	} else
		goto discard;

	/* step 6: check the URG bit */
	tcp_urg(sk, skb, th);

	/* step 7: process the segment text */
	switch (sk->sk_state) {
	case TCP_CLOSE_WAIT:
	case TCP_CLOSING:
	case TCP_LAST_ACK:
		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
			break;
	case TCP_FIN_WAIT1:
	case TCP_FIN_WAIT2:
		/* RFC 793 says to queue data in these states,
		 * RFC 1122 says we MUST send a reset.
		 * BSD 4.4 also does reset.
		 */
		if (sk->sk_shutdown & RCV_SHUTDOWN) {
			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
				tcp_reset(sk);
				return 1;
			}
		}
		/* Fall through */
	case TCP_ESTABLISHED:
		tcp_data_queue(sk, skb);
		queued = 1;
		break;
	}

	/* tcp_data could move socket to TIME-WAIT */
	if (sk->sk_state != TCP_CLOSE) {
		tcp_data_snd_check(sk);
		tcp_ack_snd_check(sk);
	}

	if (!queued) {
discard:
		__kfree_skb(skb);
	}
	return 0;
}
EXPORT_SYMBOL(tcp_rcv_state_process);