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

		/* fall into ... */

	/*
	 * In ESTABLISHED state: drop duplicate ACKs; ACK out of range
	 * ACKs.  If the ack is in the range
	 *	tp->snd_una < th->th_ack <= tp->snd_max
	 * then advance tp->snd_una to th->th_ack and drop
	 * data from the retransmission queue.  If this ACK reflects
	 * more up to date window information we update our window information.
	 */
	case TCPS_ESTABLISHED:
	case TCPS_FIN_WAIT_1:
	case TCPS_FIN_WAIT_2:
	case TCPS_CLOSE_WAIT:
	case TCPS_CLOSING:
	case TCPS_LAST_ACK:
	case TCPS_TIME_WAIT:

		if (SEQ_LEQ(th->th_ack, tp->snd_una)) {
			if (tlen == 0 && tiwin == tp->snd_wnd) {
				tcpstat.tcps_rcvdupack++;
				/*
				 * If we have outstanding data (other than
				 * a window probe), this is a completely
				 * duplicate ack (ie, window info didn't
				 * change), the ack is the biggest we've
				 * seen and we've seen exactly our rexmt
				 * threshhold of them, assume a packet
				 * has been dropped and retransmit it.
				 * Kludge snd_nxt & the congestion
				 * window so we send only this one
				 * packet.
				 *
				 * We know we're losing at the current
				 * window size so do congestion avoidance
				 * (set ssthresh to half the current window
				 * and pull our congestion window back to
				 * the new ssthresh).
				 *
				 * Dup acks mean that packets have left the
				 * network (they're now cached at the receiver)
				 * so bump cwnd by the amount in the receiver
				 * to keep a constant cwnd packets in the
				 * network.
				 */
				if (!callout_active(tp->tt_rexmt) ||
				    th->th_ack != tp->snd_una)
					tp->t_dupacks = 0;
				else if (++tp->t_dupacks == tcprexmtthresh) {
					tcp_seq onxt = tp->snd_nxt;
					u_int win =
					    min(tp->snd_wnd, tp->snd_cwnd) / 2 /
						tp->t_maxseg;
					if (tcp_do_newreno && SEQ_LT(th->th_ack,
					    tp->snd_recover)) {
						/* False retransmit, should not
						 * cut window
						 */
						tp->snd_cwnd += tp->t_maxseg;
						tp->t_dupacks = 0;
						(void) tcp_output(tp);
						goto drop;
					}
					if (win < 2)
						win = 2;
					tp->snd_ssthresh = win * tp->t_maxseg;
					tp->snd_recover = tp->snd_max;
					callout_stop(tp->tt_rexmt);
					tp->t_rtttime = 0;
					tp->snd_nxt = th->th_ack;
					tp->snd_cwnd = tp->t_maxseg;
					(void) tcp_output(tp);
					tp->snd_cwnd = tp->snd_ssthresh +
					       tp->t_maxseg * tp->t_dupacks;
					if (SEQ_GT(onxt, tp->snd_nxt))
						tp->snd_nxt = onxt;
					goto drop;
				} else if (tp->t_dupacks > tcprexmtthresh) {
					tp->snd_cwnd += tp->t_maxseg;
					(void) tcp_output(tp);
					goto drop;
				}
			} else
				tp->t_dupacks = 0;
			break;
		}
		/*
		 * If the congestion window was inflated to account
		 * for the other side's cached packets, retract it.
		 */
		if (tcp_do_newreno == 0) {
                        if (tp->t_dupacks >= tcprexmtthresh &&
                                tp->snd_cwnd > tp->snd_ssthresh)
                                tp->snd_cwnd = tp->snd_ssthresh;
                        tp->t_dupacks = 0;
                } else if (tp->t_dupacks >= tcprexmtthresh &&
		    !tcp_newreno(tp, th)) {
                        /*
                         * Window inflation should have left us with approx.
                         * snd_ssthresh outstanding data.  But in case we
                         * would be inclined to send a burst, better to do
                         * it via the slow start mechanism.
                         */
			if (SEQ_GT(th->th_ack + tp->snd_ssthresh, tp->snd_max))
                                tp->snd_cwnd =
				    tp->snd_max - th->th_ack + tp->t_maxseg;
			else
                        	tp->snd_cwnd = tp->snd_ssthresh;
                        tp->t_dupacks = 0;
                }
		if (SEQ_GT(th->th_ack, tp->snd_max)) {
			tcpstat.tcps_rcvacktoomuch++;
			goto dropafterack;
		}
		/*
		 *  If we reach this point, ACK is not a duplicate,
		 *     i.e., it ACKs something we sent.
		 */
		if (tp->t_flags & TF_NEEDSYN) {
			/*
			 * T/TCP: Connection was half-synchronized, and our
			 * SYN has been ACK'd (so connection is now fully
			 * synchronized).  Go to non-starred state,
			 * increment snd_una for ACK of SYN, and check if
			 * we can do window scaling.
			 */
			tp->t_flags &= ~TF_NEEDSYN;
			tp->snd_una++;
			/* 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;
			}
		}

process_ACK:
		acked = th->th_ack - tp->snd_una;
		tcpstat.tcps_rcvackpack++;
		tcpstat.tcps_rcvackbyte += acked;

		/*
		 * If we just performed our first retransmit, and the ACK
		 * arrives within our recovery window, then it was a mistake
		 * to do the retransmit in the first place.  Recover our
		 * original cwnd and ssthresh, and proceed to transmit where
		 * we left off.
		 */
		if (tp->t_rxtshift == 1 && ticks < tp->t_badrxtwin) {
			tp->snd_cwnd = tp->snd_cwnd_prev;
			tp->snd_ssthresh = tp->snd_ssthresh_prev;
			tp->snd_nxt = tp->snd_max;
			tp->t_badrxtwin = 0;	/* XXX probably not required */ 
		}

		/*
		 * If we have a timestamp reply, update smoothed
		 * round trip time.  If no timestamp is present but
		 * transmit timer is running and timed sequence
		 * number was acked, update smoothed round trip time.
		 * Since we now have an rtt measurement, cancel the
		 * timer backoff (cf., Phil Karn's retransmit alg.).
		 * Recompute the initial retransmit timer.
		 */
		if (to.to_flag & TOF_TS)
			tcp_xmit_timer(tp, ticks - to.to_tsecr + 1);
		else if (tp->t_rtttime && SEQ_GT(th->th_ack, tp->t_rtseq))
			tcp_xmit_timer(tp, ticks - tp->t_rtttime);

		/*
		 * If all outstanding data is acked, stop retransmit
		 * timer and remember to restart (more output or persist).
		 * If there is more data to be acked, restart retransmit
		 * timer, using current (possibly backed-off) value.
		 */
		if (th->th_ack == tp->snd_max) {
			callout_stop(tp->tt_rexmt);
			needoutput = 1;
		} else if (!callout_active(tp->tt_persist))
			callout_reset(tp->tt_rexmt, tp->t_rxtcur,
				      tcp_timer_rexmt, tp);

		/*
		 * If no data (only SYN) was ACK'd,
		 *    skip rest of ACK processing.
		 */
		if (acked == 0)
			goto step6;

		/*
		 * When new data is acked, open the congestion window.
		 * If the window gives us less than ssthresh packets
		 * in flight, open exponentially (maxseg per packet).
		 * Otherwise open linearly: maxseg per window
		 * (maxseg^2 / cwnd per packet).
		 */
		{
		register u_int cw = tp->snd_cwnd;
		register u_int incr = tp->t_maxseg;

		if (cw > tp->snd_ssthresh)
			incr = incr * incr / cw;
		/*
		 * If t_dupacks != 0 here, it indicates that we are still
		 * in NewReno fast recovery mode, so we leave the congestion
		 * window alone.
		 */
		if (tcp_do_newreno == 0 || tp->t_dupacks == 0)
			tp->snd_cwnd = min(cw + incr,TCP_MAXWIN<<tp->snd_scale);
		}
		if (acked > so->so_snd.sb_cc) {
			tp->snd_wnd -= so->so_snd.sb_cc;
			sbdrop(&so->so_snd, (int)so->so_snd.sb_cc);
			ourfinisacked = 1;
		} else {
			sbdrop(&so->so_snd, acked);
			tp->snd_wnd -= acked;
			ourfinisacked = 0;
		}
		sowwakeup(so);
		tp->snd_una = th->th_ack;
		if (SEQ_LT(tp->snd_nxt, tp->snd_una))
			tp->snd_nxt = tp->snd_una;

		switch (tp->t_state) {

		/*
		 * In FIN_WAIT_1 STATE in addition to the processing
		 * for the ESTABLISHED state if our FIN is now acknowledged
		 * then enter FIN_WAIT_2.
		 */
		case TCPS_FIN_WAIT_1:
			if (ourfinisacked) {
				/*
				 * If we can't receive any more
				 * data, then closing user can proceed.
				 * Starting the timer is contrary to the
				 * specification, but if we don't get a FIN
				 * we'll hang forever.
				 */
				if (so->so_state & SS_CANTRCVMORE) {
					soisdisconnected(so);
					callout_reset(tp->tt_2msl, tcp_maxidle,
						      tcp_timer_2msl, tp);
				}
				tp->t_state = TCPS_FIN_WAIT_2;
			}
			break;

	 	/*
		 * In CLOSING STATE in addition to the processing for
		 * the ESTABLISHED state if the ACK acknowledges our FIN
		 * then enter the TIME-WAIT state, otherwise ignore
		 * the segment.
		 */
		case TCPS_CLOSING:
			if (ourfinisacked) {
				tp->t_state = TCPS_TIME_WAIT;
				tcp_canceltimers(tp);
				/* Shorten TIME_WAIT [RFC-1644, p.28] */
				if (tp->cc_recv != 0 &&
				    (ticks - tp->t_starttime) < tcp_msl) {
					callout_reset(tp->tt_2msl,
						      tp->t_rxtcur *
						      TCPTV_TWTRUNC,
						      tcp_timer_2msl, tp);
                                }
				else {
					callout_reset(tp->tt_2msl, 2 * tcp_msl,
						      tcp_timer_2msl, tp);
                                }
				soisdisconnected(so);
			}
			break;

		/*
		 * In LAST_ACK, we may still be waiting for data to drain
		 * and/or to be acked, as well as for the ack of our FIN.
		 * If our FIN is now acknowledged, delete the TCB,
		 * enter the closed state and return.
		 */
		case TCPS_LAST_ACK:
			if (ourfinisacked) {
				tp = tcp_close(tp);
				goto drop;
			}
			break;

		/*
		 * In TIME_WAIT state the only thing that should arrive
		 * is a retransmission of the remote FIN.  Acknowledge
		 * it and restart the finack timer.
		 */
		case TCPS_TIME_WAIT:
			callout_reset(tp->tt_2msl, 2 * tcp_msl,
				      tcp_timer_2msl, tp);
			goto dropafterack;
		}
	}

step6:
	/*
	 * Update window information.
	 * Don't look at window if no ACK: TAC's send garbage on first SYN.
	 */
	if ((thflags & TH_ACK) &&
	    (SEQ_LT(tp->snd_wl1, th->th_seq) ||
	    (tp->snd_wl1 == th->th_seq && (SEQ_LT(tp->snd_wl2, th->th_ack) ||
	     (tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd))))) {
		/* keep track of pure window updates */
		if (tlen == 0 &&
		    tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd)
			tcpstat.tcps_rcvwinupd++;
		tp->snd_wnd = tiwin;
		tp->snd_wl1 = th->th_seq;
		tp->snd_wl2 = th->th_ack;
		if (tp->snd_wnd > tp->max_sndwnd)
			tp->max_sndwnd = tp->snd_wnd;
		needoutput = 1;
	}

	/*
	 * Process segments with URG.
	 */
	if ((thflags & TH_URG) && th->th_urp &&
	    TCPS_HAVERCVDFIN(tp->t_state) == 0) {
		/*
		 * This is a kludge, but if we receive and accept
		 * random urgent pointers, we'll crash in
		 * soreceive.  It's hard to imagine someone
		 * actually wanting to send this much urgent data.
		 */
		if (th->th_urp + so->so_rcv.sb_cc > sb_max) {
			th->th_urp = 0;			/* XXX */
			thflags &= ~TH_URG;		/* XXX */
			goto dodata;			/* XXX */
		}
		/*
		 * If this segment advances the known urgent pointer,
		 * then mark the data stream.  This should not happen
		 * in CLOSE_WAIT, CLOSING, LAST_ACK or TIME_WAIT STATES since
		 * a FIN has been received from the remote side.
		 * In these states we ignore the URG.
		 *
		 * According to RFC961 (Assigned Protocols),
		 * the urgent pointer points to the last octet
		 * of urgent data.  We continue, however,
		 * to consider it to indicate the first octet
		 * of data past the urgent section as the original
		 * spec states (in one of two places).
		 */
		if (SEQ_GT(th->th_seq+th->th_urp, tp->rcv_up)) {
			tp->rcv_up = th->th_seq + th->th_urp;
			so->so_oobmark = so->so_rcv.sb_cc +
			    (tp->rcv_up - tp->rcv_nxt) - 1;
			if (so->so_oobmark == 0)
				so->so_state |= SS_RCVATMARK;
			sohasoutofband(so);
			tp->t_oobflags &= ~(TCPOOB_HAVEDATA | TCPOOB_HADDATA);
		}
		/*
		 * Remove out of band data so doesn't get presented to user.
		 * This can happen independent of advancing the URG pointer,
		 * but if two URG's are pending at once, some out-of-band
		 * data may creep in... ick.
		 */
		if (th->th_urp <= (u_long)tlen
#ifdef SO_OOBINLINE
		     && (so->so_options & SO_OOBINLINE) == 0
#endif
		     )
			tcp_pulloutofband(so, th, m,
				drop_hdrlen);	/* hdr drop is delayed */
	} else
		/*
		 * If no out of band data is expected,
		 * pull receive urgent pointer along
		 * with the receive window.
		 */
		if (SEQ_GT(tp->rcv_nxt, tp->rcv_up))
			tp->rcv_up = tp->rcv_nxt;
dodata:							/* XXX */

	/*
	 * Process the segment text, merging it into the TCP sequencing queue,
	 * and arranging for acknowledgment of receipt if necessary.
	 * This process logically involves adjusting tp->rcv_wnd as data
	 * is presented to the user (this happens in tcp_usrreq.c,
	 * case PRU_RCVD).  If a FIN has already been received on this
	 * connection then we just ignore the text.
	 */
	if ((tlen || (thflags&TH_FIN)) &&
	    TCPS_HAVERCVDFIN(tp->t_state) == 0) {
		m_adj(m, drop_hdrlen);	/* delayed header drop */
		/*
		 * Insert segment which inludes th into reassembly queue of tcp with
		 * control block tp.  Return TH_FIN if reassembly now includes
		 * a segment with FIN.  This handle the common case inline (segment
		 * is the next to be received on an established connection, and the
		 * queue is empty), avoiding linkage into and removal from the queue
		 * and repetition of various conversions.
		 * Set DELACK for segments received in order, but ack immediately
		 * when segments are out of order (so fast retransmit can work).
		 */
		if (th->th_seq == tp->rcv_nxt &&
		    LIST_EMPTY(&tp->t_segq) &&
		    TCPS_HAVEESTABLISHED(tp->t_state)) {
			if (DELAY_ACK(tp))
				callout_reset(tp->tt_delack, tcp_delacktime,
				    tcp_timer_delack, tp);
			else
				tp->t_flags |= TF_ACKNOW;
			tp->rcv_nxt += tlen;
			thflags = th->th_flags & TH_FIN;
			tcpstat.tcps_rcvpack++;
			tcpstat.tcps_rcvbyte += tlen;
			ND6_HINT(tp);
			sbappend(&so->so_rcv, m);
			sorwakeup(so);
		} else {
			thflags = tcp_reass(tp, th, &tlen, m);
			tp->t_flags |= TF_ACKNOW;
		}

		/*
		 * Note the amount of data that peer has sent into
		 * our window, in order to estimate the sender's
		 * buffer size.
		 */
		len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt);
	} else {
		m_freem(m);
		thflags &= ~TH_FIN;
	}

	/*
	 * If FIN is received ACK the FIN and let the user know
	 * that the connection is closing.
	 */
	if (thflags & TH_FIN) {
		if (TCPS_HAVERCVDFIN(tp->t_state) == 0) {
			socantrcvmore(so);
			/*
			 *  If connection is half-synchronized
			 *  (ie NEEDSYN flag on) then delay ACK,
			 *  so it may be piggybacked whe