tcp_input.c

RTEMS (Real-Time Executive for Multiprocessor Systems) is a free open source real-time operating sys

				so2 = sodropablereq(so);
				if (so2) {
					tcp_drop(sototcpcb(so2), ETIMEDOUT);
					so2 = sonewconn(so, 0);
				}
				if (!so2)
					goto drop;
			}
			so = so2;
			/*
			 * This is ugly, but ....
			 *
			 * Mark socket as temporary until we're
			 * committed to keeping it.  The code at
			 * ``drop'' and ``dropwithreset'' check the
			 * flag dropsocket to see if the temporary
			 * socket created here should be discarded.
			 * We mark the socket as discardable until
			 * we're committed to it below in TCPS_LISTEN.
			 */
			dropsocket++;
			inp = (struct inpcb *)so->so_pcb;
			inp->inp_laddr = ti->ti_dst;
			inp->inp_lport = ti->ti_dport;
			in_pcbrehash(inp);
#if BSD>=43
			inp->inp_options = ip_srcroute();
#endif
			tp = intotcpcb(inp);
			tp->t_state = TCPS_LISTEN;
			tp->t_flags |= tp0->t_flags & (TF_NOPUSH|TF_NOOPT);

			/* Compute proper scaling value from buffer space */
			while (tp->request_r_scale < TCP_MAX_WINSHIFT &&
			   TCP_MAXWIN << tp->request_r_scale < so->so_rcv.sb_hiwat)
				tp->request_r_scale++;
		}
	}

	/*
	 * Segment received on connection.
	 * Reset idle time and keep-alive timer.
	 */
	tp->t_idle = 0;
	if (TCPS_HAVEESTABLISHED(tp->t_state))
		tp->t_timer[TCPT_KEEP] = tcp_keepidle;

	/*
	 * Process options if not in LISTEN state,
	 * else do it below (after getting remote address).
	 */
	if (tp->t_state != TCPS_LISTEN)
		tcp_dooptions(tp, optp, optlen, ti, &to);

	/*
	 * Header prediction: check for the two common cases
	 * of a uni-directional data xfer.  If the packet has
	 * no control flags, is in-sequence, the window didn't
	 * change and we're not retransmitting, it's a
	 * candidate.  If the length is zero and the ack moved
	 * forward, we're the sender side of the xfer.  Just
	 * free the data acked & wake any higher level process
	 * that was blocked waiting for space.  If the length
	 * is non-zero and the ack didn't move, we're the
	 * receiver side.  If we're getting packets in-order
	 * (the reassembly queue is empty), add the data to
	 * the socket buffer and note that we need a delayed ack.
	 * Make sure that the hidden state-flags are also off.
	 * Since we check for TCPS_ESTABLISHED above, it can only
	 * be TH_NEEDSYN.
	 */
	if (tp->t_state == TCPS_ESTABLISHED &&
	    (tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK &&
	    ((tp->t_flags & (TF_NEEDSYN|TF_NEEDFIN)) == 0) &&
	    ((to.to_flag & TOF_TS) == 0 ||
	     TSTMP_GEQ(to.to_tsval, tp->ts_recent)) &&
	    /*
	     * Using the CC option is compulsory if once started:
	     *   the segment is OK if no T/TCP was negotiated or
	     *   if the segment has a CC option equal to CCrecv
	     */
	    ((tp->t_flags & (TF_REQ_CC|TF_RCVD_CC)) != (TF_REQ_CC|TF_RCVD_CC) ||
	     ((to.to_flag & TOF_CC) != 0 && to.to_cc == tp->cc_recv)) &&
	    ti->ti_seq == tp->rcv_nxt &&
	    tiwin && tiwin == tp->snd_wnd &&
	    tp->snd_nxt == tp->snd_max) {

		/*
		 * If last ACK falls within this segment's sequence numbers,
		 * record the timestamp.
		 * NOTE that the test is modified according to the latest
		 * proposal of the [e-mail] list (Braden 1993/04/26).
		 */
		if ((to.to_flag & TOF_TS) != 0 &&
		   SEQ_LEQ(ti->ti_seq, tp->last_ack_sent)) {
			tp->ts_recent_age = tcp_now;
			tp->ts_recent = to.to_tsval;
		}

		if (ti->ti_len == 0) {
			if (SEQ_GT(ti->ti_ack, tp->snd_una) &&
			    SEQ_LEQ(ti->ti_ack, tp->snd_max) &&
			    tp->snd_cwnd >= tp->snd_wnd &&
			    tp->t_dupacks < tcprexmtthresh) {
				/*
				 * this is a pure ack for outstanding data.
				 */
				++tcpstat.tcps_predack;
				if ((to.to_flag & TOF_TS) != 0)
					tcp_xmit_timer(tp,
					    tcp_now - to.to_tsecr + 1);
				else if (tp->t_rtt &&
					    SEQ_GT(ti->ti_ack, tp->t_rtseq))
					tcp_xmit_timer(tp, tp->t_rtt);
				acked = ti->ti_ack - tp->snd_una;
				tcpstat.tcps_rcvackpack++;
				tcpstat.tcps_rcvackbyte += acked;
				sbdrop(&so->so_snd, acked);
				tp->snd_una = ti->ti_ack;
				m_freem(m);

				/*
				 * If all outstanding data are acked, stop
				 * retransmit timer, otherwise restart timer
				 * using current (possibly backed-off) value.
				 * If process is waiting for space,
				 * wakeup/selwakeup/signal.  If data
				 * are ready to send, let tcp_output
				 * decide between more output or persist.
				 */
				if (tp->snd_una == tp->snd_max)
					tp->t_timer[TCPT_REXMT] = 0;
				else if (tp->t_timer[TCPT_PERSIST] == 0)
					tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;

				if (so->so_snd.sb_flags & SB_NOTIFY)
					sowwakeup(so);
				if (so->so_snd.sb_cc)
					(void) tcp_output(tp);
				return;
			}
		} else if (ti->ti_ack == tp->snd_una &&
		    tp->seg_next == (struct tcpiphdr *)tp &&
		    ti->ti_len <= sbspace(&so->so_rcv)) {
			/*
			 * this is a pure, in-sequence data packet
			 * with nothing on the reassembly queue and
			 * we have enough buffer space to take it.
			 */
			++tcpstat.tcps_preddat;
			tp->rcv_nxt += ti->ti_len;
			tcpstat.tcps_rcvpack++;
			tcpstat.tcps_rcvbyte += ti->ti_len;
			/*
			 * Add data to socket buffer.
			 */
			sbappend(&so->so_rcv, m);
			sorwakeup(so);
#ifdef TCP_ACK_HACK
			/*
			 * If this is a short packet, then ACK now - with Nagel
			 *	congestion avoidance sender won't send more until
			 *	he gets an ACK.
			 */
			if (tiflags & TH_PUSH) {
				tp->t_flags |= TF_ACKNOW;
				tcp_output(tp);
			} else {
				tp->t_flags |= TF_DELACK;
			}
#else
			tp->t_flags |= TF_DELACK;
#endif
			return;
		}
	}

	/*
	 * Calculate amount of space in receive window,
	 * and then do TCP input processing.
	 * Receive window is amount of space in rcv queue,
	 * but not less than advertised window.
	 */
	{ int win;

	win = sbspace(&so->so_rcv);
	if (win < 0)
		win = 0;
	tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt));
	}

	switch (tp->t_state) {

	/*
	 * If the state is LISTEN then ignore segment if it contains an RST.
	 * If the segment contains an ACK then it is bad and send a RST.
	 * If it does not contain a SYN then it is not interesting; drop it.
	 * If it is from this socket, drop it, it must be forged.
	 * Don't bother responding if the destination was a broadcast.
	 * Otherwise initialize tp->rcv_nxt, and tp->irs, select an initial
	 * tp->iss, and send a segment:
	 *     <SEQ=ISS><ACK=RCV_NXT><CTL=SYN,ACK>
	 * Also initialize tp->snd_nxt to tp->iss+1 and tp->snd_una to tp->iss.
	 * Fill in remote peer address fields if not previously specified.
	 * Enter SYN_RECEIVED state, and process any other fields of this
	 * segment in this state.
	 */
	case TCPS_LISTEN: {
		struct mbuf *am;
		register struct sockaddr_in *sin;

		if (tiflags & TH_RST)
			goto drop;
		if (tiflags & TH_ACK)
			goto dropwithreset;
		if ((tiflags & TH_SYN) == 0)
			goto drop;
		if ((ti->ti_dport == ti->ti_sport) &&
		    (ti->ti_dst.s_addr == ti->ti_src.s_addr))
			goto drop;
		/*
		 * RFC1122 4.2.3.10, p. 104: discard bcast/mcast SYN
		 * in_broadcast() should never return true on a received
		 * packet with M_BCAST not set.
		 */
		if (m->m_flags & (M_BCAST|M_MCAST) ||
		    IN_MULTICAST(ntohl(ti->ti_dst.s_addr)))
			goto drop;
		am = m_get(M_DONTWAIT, MT_SONAME);	/* XXX */
		if (am == NULL)
			goto drop;
		am->m_len = sizeof (struct sockaddr_in);
		sin = mtod(am, struct sockaddr_in *);
		sin->sin_family = AF_INET;
		sin->sin_len = sizeof(*sin);
		sin->sin_addr = ti->ti_src;
		sin->sin_port = ti->ti_sport;
		bzero((caddr_t)sin->sin_zero, sizeof(sin->sin_zero));
		laddr = inp->inp_laddr;
		if (inp->inp_laddr.s_addr == INADDR_ANY)
			inp->inp_laddr = ti->ti_dst;
		if (in_pcbconnect(inp, am)) {
			inp->inp_laddr = laddr;
			(void) m_free(am);
			goto drop;
		}
		(void) m_free(am);
		tp->t_template = tcp_template(tp);
		if (tp->t_template == 0) {
			tp = tcp_drop(tp, ENOBUFS);
			dropsocket = 0;		/* socket is already gone */
			goto drop;
		}
		if ((taop = tcp_gettaocache(inp)) == NULL) {
			taop = &tao_noncached;
			bzero(taop, sizeof(*taop));
		}
		tcp_dooptions(tp, optp, optlen, ti, &to);
		if (iss)
			tp->iss = iss;
		else
			tp->iss = tcp_iss;
		tcp_iss += TCP_ISSINCR/4;
		tp->irs = ti->ti_seq;
		tcp_sendseqinit(tp);
		tcp_rcvseqinit(tp);
		/*
		 * Initialization of the tcpcb for transaction;
		 *   set SND.WND = SEG.WND,
		 *   initialize CCsend and CCrecv.
		 */
		tp->snd_wnd = tiwin;	/* initial send-window */
		tp->cc_send = CC_INC(tcp_ccgen);
		tp->cc_recv = to.to_cc;
		/*
		 * Perform TAO test on incoming CC (SEG.CC) option, if any.
		 * - compare SEG.CC against cached CC from the same host,
		 *	if any.
		 * - if SEG.CC > chached value, SYN must be new and is accepted
		 *	immediately: save new CC in the cache, mark the socket
		 *	connected, enter ESTABLISHED state, turn on flag to
		 *	send a SYN in the next segment.
		 *	A virtual advertised window is set in rcv_adv to
		 *	initialize SWS prevention.  Then enter normal segment
		 *	processing: drop SYN, process data and FIN.
		 * - otherwise do a normal 3-way handshake.
		 */
		if ((to.to_flag & TOF_CC) != 0) {
		    if (taop->tao_cc != 0 && CC_GT(to.to_cc, taop->tao_cc)) {
			taop->tao_cc = to.to_cc;
			tp->t_state = TCPS_ESTABLISHED;

			/*
			 * If there is a FIN, or if there is data and the
			 * connection is local, then delay SYN,ACK(SYN) in
			 * the hope of piggy-backing it on a response
			 * segment.  Otherwise must send ACK now in case
			 * the other side is slow starting.
			 */
			if ((tiflags & TH_FIN) || (ti->ti_len != 0 &&
			    in_localaddr(inp->inp_faddr)))
				tp->t_flags |= (TF_DELACK | TF_NEEDSYN);
			else
				tp->t_flags |= (TF_ACKNOW | TF_NEEDSYN);

			/*
			 * Limit the `virtual advertised window' to TCP_MAXWIN
			 * here.  Even if we requested window scaling, it will
			 * become effective only later when our SYN is acked.
			 */
			tp->rcv_adv += min(tp->rcv_wnd, TCP_MAXWIN);
			tcpstat.tcps_connects++;
			soisconnected(so);
			tp->t_timer[TCPT_KEEP] = tcp_keepinit;
			dropsocket = 0;		/* committed to socket */
			tcpstat.tcps_accepts++;
			goto trimthenstep6;
		    }
		/* else do standard 3-way handshake */
		} else {
		    /*
		     * No CC option, but maybe CC.NEW:
		     *   invalidate cached value.
		     */
		     taop->tao_cc = 0;
		}
		/*
		 * TAO test failed or there was no CC option,
		 *    do a standard 3-way handshake.
		 */
		tp->t_flags |= TF_ACKNOW;
		tp->t_state = TCPS_SYN_RECEIVED;
		tp->t_timer[TCPT_KEEP] = tcp_keepinit;
		dropsocket = 0;		/* committed to socket */
		tcpstat.tcps_accepts++;
		goto trimthenstep6;
		}

	/*
	 * If the state is SYN_RECEIVED:
	 *	if seg contains SYN/ACK, send a RST.
	 *	if seg contains an ACK, but not for our SYN/ACK, send a RST.
	 */
	case TCPS_SYN_RECEIVED:
		if (tiflags & TH_ACK) {
			if (tiflags & TH_SYN) {
				tcpstat.tcps_badsyn++;
				goto dropwithreset;
			}
			if (SEQ_LEQ(ti->ti_ack, tp->snd_una) ||
			    SEQ_GT(ti->ti_ack, tp->snd_max))
				goto dropwithreset;
		}
		break;

	/*
	 * If the state is SYN_SENT:
	 *	if seg contains an ACK, but not for our SYN, drop the input.
	 *	if seg contains a RST, then drop the connection.
	 *	if seg does not contain SYN, then drop it.
	 * Otherwise this is an acceptable SYN segment
	 *	initialize tp->rcv_nxt and tp->irs
	 *	if seg contains ack then advance tp->snd_una
	 *	if SYN has been acked change to ESTABLISHED else SYN_RCVD state
	 *	arrange for segment to be acked (eventually)
	 *	continue processing rest of data/controls, beginning with URG
	 */
	case TCPS_SYN_SENT:
		if ((taop = tcp_gettaocache(inp)) == NULL) {
			taop = &tao_noncached;
			bzero(taop, sizeof(*taop));
		}

		if ((tiflags & TH_ACK) &&
		    (SEQ_LEQ(ti->ti_ack, tp->iss) ||
		     SEQ_GT(ti->ti_ack, tp->snd_max))) {
			/*
			 * If we have a cached CCsent for the remote host,
			 * hence we haven't just crashed and restarted,
			 * do not send a RST.  This may be a retransmission
			 * from the other side after our earlier ACK was lost.
			 * Our new SYN, when it arrives, will serve as the
			 * needed ACK.
			 */
			if (taop->tao_ccsent != 0)
				goto drop;
			else
				goto dropwithreset;
		}
		if (tiflags & TH_RST) {
			if (tiflags & TH_ACK)
				tp = tcp_drop(tp, ECONNREFUSED);
			goto drop;
		}
		if ((tiflags & TH_SYN) == 0)
			goto drop;
		tp->snd_wnd = ti->ti_win;	/* initial send window */
		tp->cc_recv = to.to_cc;		/* foreign CC */

		tp->irs = ti->ti_seq;
		tcp_rcvseqinit(tp);
		if (tiflags & TH_ACK) {
			/*
			 * Our SYN was acked.  If segment contains CC.ECHO
			 * option, check it to make sure this segment really
			 * matches our SYN.  If not, just drop it as old
			 * duplicate, but send an RST if we're still playing
			 * by the old rules.  If no CC.ECHO option, make sure
			 * we don't get fooled into using T/TCP.
			 */
			if (to.to_flag & TOF_CCECHO) {
				if (tp->cc_send != to.to_ccecho) {
					if (taop->tao_ccsent != 0)
						goto drop;
					else
						goto dropwithreset;
				}
			} else
				tp->t_flags &= ~TF_RCVD_CC;
			tcpstat.tcps_connects++;
			soisconnected(so);
			/* Do window scaling on this connection? */
			if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
				(TF_RCVD_SCALE|TF_REQ_SCALE)) {
				tp->snd_scale = tp->requested_s_scale;
				tp->rcv_scale = tp->request_r_scale;
			}
			/* Segment is acceptable, update cache if undefined. */
			if (taop->tao_ccsent == 0)
				taop->tao_ccsent = to.to_ccecho;

			tp->rcv_adv += tp->rcv_wnd;
			tp->snd_una++;		/* SYN is acked */
			/*