tcp_input.c

来自「eCos操作系统源码」· C语言 代码 · 共 2,238 行 · 第 1/5 页

			if (DELAY_ACK(tp) && tlen != 0)
                                callout_reset(tp->tt_delack, tcp_delacktime,  
                                    tcp_timer_delack, tp);  
			else
				tp->t_flags |= TF_ACKNOW;
			/*
			 * Received <SYN,ACK> in SYN_SENT[*] state.
			 * Transitions:
			 *	SYN_SENT  --> ESTABLISHED
			 *	SYN_SENT* --> FIN_WAIT_1
			 */
			tp->t_starttime = ticks;
			if (tp->t_flags & TF_NEEDFIN) {
				tp->t_state = TCPS_FIN_WAIT_1;
				tp->t_flags &= ~TF_NEEDFIN;
				thflags &= ~TH_SYN;
			} else {
				tp->t_state = TCPS_ESTABLISHED;
				callout_reset(tp->tt_keep, tcp_keepidle,
					      tcp_timer_keep, tp);
			}
		} else {
		/*
		 *  Received initial SYN in SYN-SENT[*] state => simul-
		 *  taneous open.  If segment contains CC option and there is
		 *  a cached CC, apply TAO test; if it succeeds, connection is
		 *  half-synchronized.  Otherwise, do 3-way handshake:
		 *        SYN-SENT -> SYN-RECEIVED
		 *        SYN-SENT* -> SYN-RECEIVED*
		 *  If there was no CC option, clear cached CC value.
		 */
			tp->t_flags |= TF_ACKNOW;
			callout_stop(tp->tt_rexmt);
			if (to.to_flag & TOF_CC) {
				if (taop->tao_cc != 0 &&
				    CC_GT(to.to_cc, taop->tao_cc)) {
					/*
					 * update cache and make transition:
					 *        SYN-SENT -> ESTABLISHED*
					 *        SYN-SENT* -> FIN-WAIT-1*
					 */
					taop->tao_cc = to.to_cc;
					tp->t_starttime = ticks;
					if (tp->t_flags & TF_NEEDFIN) {
						tp->t_state = TCPS_FIN_WAIT_1;
						tp->t_flags &= ~TF_NEEDFIN;
					} else {
						tp->t_state = TCPS_ESTABLISHED;
						callout_reset(tp->tt_keep,
							      tcp_keepidle,
							      tcp_timer_keep,
							      tp);
					}
					tp->t_flags |= TF_NEEDSYN;
				} else
					tp->t_state = TCPS_SYN_RECEIVED;
			} else {
				/* CC.NEW or no option => invalidate cache */
				taop->tao_cc = 0;
				tp->t_state = TCPS_SYN_RECEIVED;
			}
		}

trimthenstep6:
		/*
		 * Advance th->th_seq to correspond to first data byte.
		 * If data, trim to stay within window,
		 * dropping FIN if necessary.
		 */
		th->th_seq++;
		if (tlen > tp->rcv_wnd) {
			todrop = tlen - tp->rcv_wnd;
			m_adj(m, -todrop);
			tlen = tp->rcv_wnd;
			thflags &= ~TH_FIN;
			tcpstat.tcps_rcvpackafterwin++;
			tcpstat.tcps_rcvbyteafterwin += todrop;
		}
		tp->snd_wl1 = th->th_seq - 1;
		tp->rcv_up = th->th_seq;
		/*
		 *  Client side of transaction: already sent SYN and data.
		 *  If the remote host used T/TCP to validate the SYN,
		 *  our data will be ACK'd; if so, enter normal data segment
		 *  processing in the middle of step 5, ack processing.
		 *  Otherwise, goto step 6.
		 */
 		if (thflags & TH_ACK)
			goto process_ACK;
		goto step6;
	/*
	 * If the state is LAST_ACK or CLOSING or TIME_WAIT:
	 *	if segment contains a SYN and CC [not CC.NEW] option:
	 *              if state == TIME_WAIT and connection duration > MSL,
	 *                  drop packet and send RST;
	 *
	 *		if SEG.CC > CCrecv then is new SYN, and can implicitly
	 *		    ack the FIN (and data) in retransmission queue.
	 *                  Complete close and delete TCPCB.  Then reprocess
	 *                  segment, hoping to find new TCPCB in LISTEN state;
	 *
	 *		else must be old SYN; drop it.
	 *      else do normal processing.
	 */
	case TCPS_LAST_ACK:
	case TCPS_CLOSING:
	case TCPS_TIME_WAIT:
		if ((thflags & TH_SYN) &&
		    (to.to_flag & TOF_CC) && tp->cc_recv != 0) {
			if (tp->t_state == TCPS_TIME_WAIT &&
					(ticks - tp->t_starttime) > tcp_msl) {
				rstreason = BANDLIM_UNLIMITED;
				goto dropwithreset;
			}
			if (CC_GT(to.to_cc, tp->cc_recv)) {
				tp = tcp_close(tp);
				goto findpcb;
			}
			else
				goto drop;
		}
 		break;  /* continue normal processing */
	}

	/*
	 * States other than LISTEN or SYN_SENT.
	 * First check the RST flag and sequence number since reset segments
	 * are exempt from the timestamp and connection count tests.  This
	 * fixes a bug introduced by the Stevens, vol. 2, p. 960 bugfix
	 * below which allowed reset segments in half the sequence space
	 * to fall though and be processed (which gives forged reset
	 * segments with a random sequence number a 50 percent chance of
	 * killing a connection).
	 * Then check timestamp, if present.
	 * Then check the connection count, if present.
	 * Then check that at least some bytes of segment are within
	 * receive window.  If segment begins before rcv_nxt,
	 * drop leading data (and SYN); if nothing left, just ack.
	 *
	 *
	 * If the RST bit is set, check the sequence number to see
	 * if this is a valid reset segment.
	 * RFC 793 page 37:
	 *   In all states except SYN-SENT, all reset (RST) segments
	 *   are validated by checking their SEQ-fields.  A reset is
	 *   valid if its sequence number is in the window.
	 * Note: this does not take into account delayed ACKs, so
	 *   we should test against last_ack_sent instead of rcv_nxt.
	 *   The sequence number in the reset segment is normally an
	 *   echo of our outgoing acknowlegement numbers, but some hosts
	 *   send a reset with the sequence number at the rightmost edge
	 *   of our receive window, and we have to handle this case.
	 * If we have multiple segments in flight, the intial reset
	 * segment sequence numbers will be to the left of last_ack_sent,
	 * but they will eventually catch up.
	 * In any case, it never made sense to trim reset segments to
	 * fit the receive window since RFC 1122 says:
	 *   4.2.2.12  RST Segment: RFC-793 Section 3.4
	 *
	 *    A TCP SHOULD allow a received RST segment to include data.
	 *
	 *    DISCUSSION
	 *         It has been suggested that a RST segment could contain
	 *         ASCII text that encoded and explained the cause of the
	 *         RST.  No standard has yet been established for such
	 *         data.
	 *
	 * If the reset segment passes the sequence number test examine
	 * the state:
	 *    SYN_RECEIVED STATE:
	 *	If passive open, return to LISTEN state.
	 *	If active open, inform user that connection was refused.
	 *    ESTABLISHED, FIN_WAIT_1, FIN_WAIT2, CLOSE_WAIT STATES:
	 *	Inform user that connection was reset, and close tcb.
	 *    CLOSING, LAST_ACK STATES:
	 *	Close the tcb.
	 *    TIME_WAIT STATE:
	 *	Drop the segment - see Stevens, vol. 2, p. 964 and
	 *      RFC 1337.
	 */
	if (thflags & TH_RST) {
		if (SEQ_GEQ(th->th_seq, tp->last_ack_sent) &&
		    SEQ_LT(th->th_seq, tp->last_ack_sent + tp->rcv_wnd)) {
			switch (tp->t_state) {

			case TCPS_SYN_RECEIVED:
				so->so_error = ECONNREFUSED;
				goto close;

			case TCPS_ESTABLISHED:
			case TCPS_FIN_WAIT_1:
			case TCPS_FIN_WAIT_2:
			case TCPS_CLOSE_WAIT:
				so->so_error = ECONNRESET;
			close:
				tp->t_state = TCPS_CLOSED;
				tcpstat.tcps_drops++;
				tp = tcp_close(tp);
				break;

			case TCPS_CLOSING:
			case TCPS_LAST_ACK:
				tp = tcp_close(tp);
				break;

			case TCPS_TIME_WAIT:
				break;
			}
		}
		goto drop;
	}

	/*
	 * RFC 1323 PAWS: If we have a timestamp reply on this segment
	 * and it's less than ts_recent, drop it.
	 */
	if ((to.to_flag & TOF_TS) != 0 && tp->ts_recent &&
	    TSTMP_LT(to.to_tsval, tp->ts_recent)) {

		/* Check to see if ts_recent is over 24 days old.  */
		if ((int)(ticks - tp->ts_recent_age) > TCP_PAWS_IDLE) {
			/*
			 * Invalidate ts_recent.  If this segment updates
			 * ts_recent, the age will be reset later and ts_recent
			 * will get a valid value.  If it does not, setting
			 * ts_recent to zero will at least satisfy the
			 * requirement that zero be placed in the timestamp
			 * echo reply when ts_recent isn't valid.  The
			 * age isn't reset until we get a valid ts_recent
			 * because we don't want out-of-order segments to be
			 * dropped when ts_recent is old.
			 */
			tp->ts_recent = 0;
		} else {
			tcpstat.tcps_rcvduppack++;
			tcpstat.tcps_rcvdupbyte += tlen;
			tcpstat.tcps_pawsdrop++;
			goto dropafterack;
		}
	}

	/*
	 * T/TCP mechanism
	 *   If T/TCP was negotiated and the segment doesn't have CC,
	 *   or if its CC is wrong then drop the segment.
	 *   RST segments do not have to comply with this.
	 */
	if ((tp->t_flags & (TF_REQ_CC|TF_RCVD_CC)) == (TF_REQ_CC|TF_RCVD_CC) &&
	    ((to.to_flag & TOF_CC) == 0 || tp->cc_recv != to.to_cc))
 		goto dropafterack;

	/*
	 * In the SYN-RECEIVED state, validate that the packet belongs to
	 * this connection before trimming the data to fit the receive
	 * window.  Check the sequence number versus IRS since we know
	 * the sequence numbers haven't wrapped.  This is a partial fix
	 * for the "LAND" DoS attack.
	 */
	if (tp->t_state == TCPS_SYN_RECEIVED && SEQ_LT(th->th_seq, tp->irs)) {
		rstreason = BANDLIM_UNLIMITED;
		goto dropwithreset;
	}

	todrop = tp->rcv_nxt - th->th_seq;
	if (todrop > 0) {
		if (thflags & TH_SYN) {
			thflags &= ~TH_SYN;
			th->th_seq++;
			if (th->th_urp > 1)
				th->th_urp--;
			else
				thflags &= ~TH_URG;
			todrop--;
		}
		/*
		 * Following if statement from Stevens, vol. 2, p. 960.
		 */
		if (todrop > tlen
		    || (todrop == tlen && (thflags & TH_FIN) == 0)) {
			/*
			 * Any valid FIN must be to the left of the window.
			 * At this point the FIN must be a duplicate or out
			 * of sequence; drop it.
			 */
			thflags &= ~TH_FIN;

			/*
			 * Send an ACK to resynchronize and drop any data.
			 * But keep on processing for RST or ACK.
			 */
			tp->t_flags |= TF_ACKNOW;
			todrop = tlen;
			tcpstat.tcps_rcvduppack++;
			tcpstat.tcps_rcvdupbyte += todrop;
		} else {
			tcpstat.tcps_rcvpartduppack++;
			tcpstat.tcps_rcvpartdupbyte += todrop;
		}
		drop_hdrlen += todrop;	/* drop from the top afterwards */
		th->th_seq += todrop;
		tlen -= todrop;
		if (th->th_urp > todrop)
			th->th_urp -= todrop;
		else {
			thflags &= ~TH_URG;
			th->th_urp = 0;
		}
	}

	/*
	 * If new data are received on a connection after the
	 * user processes are gone, then RST the other end.
	 */
	if ((so->so_state & SS_NOFDREF) &&
	    tp->t_state > TCPS_CLOSE_WAIT && tlen) {
		tp = tcp_close(tp);
		tcpstat.tcps_rcvafterclose++;
		rstreason = BANDLIM_UNLIMITED;
		goto dropwithreset;
	}

	/*
	 * If segment ends after window, drop trailing data
	 * (and PUSH and FIN); if nothing left, just ACK.
	 */
	todrop = (th->th_seq+tlen) - (tp->rcv_nxt+tp->rcv_wnd);
	if (todrop > 0) {
		tcpstat.tcps_rcvpackafterwin++;
		if (todrop >= tlen) {
			tcpstat.tcps_rcvbyteafterwin += tlen;
			/*
			 * If a new connection request is received
			 * while in TIME_WAIT, drop the old connection
			 * and start over if the sequence numbers
			 * are above the previous ones.
			 */
			if (thflags & TH_SYN &&
			    tp->t_state == TCPS_TIME_WAIT &&
			    SEQ_GT(th->th_seq, tp->rcv_nxt)) {
				iss = tcp_new_isn(tp);
				tp = tcp_close(tp);
				goto findpcb;
			}
			/*
			 * If window is closed can only take segments at
			 * window edge, and have to drop data and PUSH from
			 * incoming segments.  Continue processing, but
			 * remember to ack.  Otherwise, drop segment
			 * and ack.
			 */
			if (tp->rcv_wnd == 0 && th->th_seq == tp->rcv_nxt) {
				tp->t_flags |= TF_ACKNOW;
				tcpstat.tcps_rcvwinprobe++;
			} else
				goto dropafterack;
		} else
			tcpstat.tcps_rcvbyteafterwin += todrop;
		m_adj(m, -todrop);
		tlen -= todrop;
		thflags &= ~(TH_PUSH|TH_FIN);
	}

	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record its 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(th->th_seq, tp->last_ack_sent)) {
		tp->ts_recent_age = ticks;
		tp->ts_recent = to.to_tsval;
	}

	/*
	 * If a SYN is in the window, then this is an
	 * error and we send an RST and drop the connection.
	 */
	if (thflags & TH_SYN) {
		tp = tcp_drop(tp, ECONNRESET);
		rstreason = BANDLIM_UNLIMITED;
		goto dropwithreset;
	}

	/*
	 * If the ACK bit is off:  if in SYN-RECEIVED state or SENDSYN
	 * flag is on (half-synchronized state), then queue data for
	 * later processing; else drop segment and return.
	 */
	if ((thflags & TH_ACK) == 0) {
		if (tp->t_state == TCPS_SYN_RECEIVED ||
		    (tp->t_flags & TF_NEEDSYN))
			goto step6;
		else
			goto drop;
	}

	/*
	 * Ack processing.
	 */
	switch (tp->t_state) {

	/*
	 * In SYN_RECEIVED state, the ack ACKs our SYN, so enter
	 * ESTABLISHED state and continue processing.
	 * The ACK was checked above.
	 */
	case TCPS_SYN_RECEIVED:

		tcpstat.tcps_connects++;
		soisconnected(so);
		/* Do window scaling? */
		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;
		}
		/*
		 * Upon successful completion of 3-way handshake,
		 * update cache.CC if it was undefined, pass any queued
		 * data to the user, and advance state appropriately.
		 */
		if ((taop = tcp_gettaocache(inp)) != NULL &&
		    taop->tao_cc == 0)
			taop->tao_cc = tp->cc_recv;

		/*
		 * Make transitions:
		 *      SYN-RECEIVED  -> ESTABLISHED
		 *      SYN-RECEIVED* -> FIN-WAIT-1
		 */
		tp->t_starttime = ticks;
		if (tp->t_flags & TF_NEEDFIN) {
			tp->t_state = TCPS_FIN_WAIT_1;
			tp->t_flags &= ~TF_NEEDFIN;
		} else {
			tp->t_state = TCPS_ESTABLISHED;
			callout_reset(tp->tt_keep, tcp_keepidle, 
				      tcp_timer_keep, tp);
		}
		/*
		 * If segment contains data or ACK, will call tcp_reass()
		 * later; if not, do so now to pass queued data to user.
		 */
		if (tlen == 0 && (thflags & TH_FIN) == 0)
			(void) tcp_reass(tp, (struct tcphdr *)0, 0,
			    (struct mbuf *)0);
		tp->snd_wl1 = th->th_seq - 1;