tcp_input.c

qemu虚拟机代码

			 * At this point the FIN must be a duplicate or out
			 * of sequence; drop it.
			 */
			tiflags &= ~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 = ti->ti_len;
			tcpstat.tcps_rcvduppack++;
			tcpstat.tcps_rcvdupbyte += todrop;
		} else {
			tcpstat.tcps_rcvpartduppack++;
			tcpstat.tcps_rcvpartdupbyte += todrop;
		}
		m_adj(m, todrop);
		ti->ti_seq += todrop;
		ti->ti_len -= todrop;
		if (ti->ti_urp > todrop)
			ti->ti_urp -= todrop;
		else {
			tiflags &= ~TH_URG;
			ti->ti_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 && ti->ti_len) {
		tp = tcp_close(tp);
		tcpstat.tcps_rcvafterclose++;
		goto dropwithreset;
	}

	/*
	 * If segment ends after window, drop trailing data
	 * (and PUSH and FIN); if nothing left, just ACK.
	 */
	todrop = (ti->ti_seq+ti->ti_len) - (tp->rcv_nxt+tp->rcv_wnd);
	if (todrop > 0) {
		tcpstat.tcps_rcvpackafterwin++;
		if (todrop >= ti->ti_len) {
			tcpstat.tcps_rcvbyteafterwin += ti->ti_len;
			/*
			 * 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 (tiflags & TH_SYN &&
			    tp->t_state == TCPS_TIME_WAIT &&
			    SEQ_GT(ti->ti_seq, tp->rcv_nxt)) {
				iss = tp->rcv_nxt + TCP_ISSINCR;
				tp = tcp_close(tp);
				goto findso;
			}
			/*
			 * 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 && ti->ti_seq == tp->rcv_nxt) {
				tp->t_flags |= TF_ACKNOW;
				tcpstat.tcps_rcvwinprobe++;
			} else
				goto dropafterack;
		} else
			tcpstat.tcps_rcvbyteafterwin += todrop;
		m_adj(m, -todrop);
		ti->ti_len -= todrop;
		tiflags &= ~(TH_PUSH|TH_FIN);
	}

	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record its timestamp.
	 */
/*	if (ts_present && SEQ_LEQ(ti->ti_seq, tp->last_ack_sent) &&
 *	    SEQ_LT(tp->last_ack_sent, ti->ti_seq + ti->ti_len +
 *		   ((tiflags & (TH_SYN|TH_FIN)) != 0))) {
 *		tp->ts_recent_age = tcp_now;
 *		tp->ts_recent = ts_val;
 *	}
 */

	/*
	 * If the RST bit is set 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, TIME_WAIT STATES
	 *	Close the tcb.
	 */
	if (tiflags&TH_RST) 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);
		goto drop;

	case TCPS_CLOSING:
	case TCPS_LAST_ACK:
	case TCPS_TIME_WAIT:
		tp = tcp_close(tp);
		goto drop;
	}

	/*
	 * If a SYN is in the window, then this is an
	 * error and we send an RST and drop the connection.
	 */
	if (tiflags & TH_SYN) {
		tp = tcp_drop(tp,0);
		goto dropwithreset;
	}

	/*
	 * If the ACK bit is off we drop the segment and return.
	 */
	if ((tiflags & TH_ACK) == 0) goto drop;

	/*
	 * Ack processing.
	 */
	switch (tp->t_state) {
	/*
	 * In SYN_RECEIVED state if the ack ACKs our SYN then enter
	 * ESTABLISHED state and continue processing, otherwise
	 * send an RST.  una<=ack<=max
	 */
	case TCPS_SYN_RECEIVED:

		if (SEQ_GT(tp->snd_una, ti->ti_ack) ||
		    SEQ_GT(ti->ti_ack, tp->snd_max))
			goto dropwithreset;
		tcpstat.tcps_connects++;
		tp->t_state = TCPS_ESTABLISHED;
		/* 
		 * The sent SYN is ack'ed with our sequence number +1 
		 * The first data byte already in the buffer will get 
		 * lost if no correction is made.  This is only needed for
		 * SS_CTL since the buffer is empty otherwise.
		 * tp->snd_una++; or:     
		 */
		tp->snd_una=ti->ti_ack;
		if (so->so_state & SS_CTL) {
		  /* So tcp_ctl reports the right state */
		  ret = tcp_ctl(so);
		  if (ret == 1) {
		    soisfconnected(so);
		    so->so_state &= ~SS_CTL;   /* success XXX */
		  } else if (ret == 2) {
		    so->so_state = SS_NOFDREF; /* CTL_CMD */
		  } else {
		    needoutput = 1;
		    tp->t_state = TCPS_FIN_WAIT_1;
		  }
		} else {
		  soisfconnected(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;
 *		}
 */
		(void) tcp_reass(tp, (struct tcpiphdr *)0, (struct mbuf *)0);
		tp->snd_wl1 = ti->ti_seq - 1;
		/* Avoid ack processing; snd_una==ti_ack  =>  dup ack */
		goto synrx_to_est;
		/* fall into ... */

	/*
	 * In ESTABLISHED state: drop duplicate ACKs; ACK out of range
	 * ACKs.  If the ack is in the range
	 *	tp->snd_una < ti->ti_ack <= tp->snd_max
	 * then advance tp->snd_una to ti->ti_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(ti->ti_ack, tp->snd_una)) {
			if (ti->ti_len == 0 && tiwin == tp->snd_wnd) {
			  tcpstat.tcps_rcvdupack++;
			  DEBUG_MISC((dfd," dup ack  m = %lx  so = %lx \n",
				      (long )m, (long )so));
				/*
				 * 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
				 * threshold 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 (tp->t_timer[TCPT_REXMT] == 0 ||
				    ti->ti_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 (win < 2)
						win = 2;
					tp->snd_ssthresh = win * tp->t_maxseg;
					tp->t_timer[TCPT_REXMT] = 0;
					tp->t_rtt = 0;
					tp->snd_nxt = ti->ti_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;
		}
	synrx_to_est:
		/*
		 * If the congestion window was inflated to account
		 * for the other side's cached packets, retract it.
		 */
		if (tp->t_dupacks > tcprexmtthresh &&
		    tp->snd_cwnd > tp->snd_ssthresh)
			tp->snd_cwnd = tp->snd_ssthresh;
		tp->t_dupacks = 0;
		if (SEQ_GT(ti->ti_ack, tp->snd_max)) {
			tcpstat.tcps_rcvacktoomuch++;
			goto dropafterack;
		}
		acked = ti->ti_ack - tp->snd_una;
		tcpstat.tcps_rcvackpack++;
		tcpstat.tcps_rcvackbyte += acked;

		/*
		 * 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 (ts_present)
 *			tcp_xmit_timer(tp, tcp_now-ts_ecr+1);
 *		else
 */		     
		     if (tp->t_rtt && SEQ_GT(ti->ti_ack, tp->t_rtseq))
			tcp_xmit_timer(tp,tp->t_rtt);

		/*
		 * 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 (ti->ti_ack == tp->snd_max) {
			tp->t_timer[TCPT_REXMT] = 0;
			needoutput = 1;
		} else if (tp->t_timer[TCPT_PERSIST] == 0)
			tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
		/*
		 * 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;
		  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;
		}
		/*
		 * XXX sowwakup is called when data is acked and there's room for
		 * for more data... it should read() the socket 
		 */
/*		if (so->so_snd.sb_flags & SB_NOTIFY)
 *			sowwakeup(so);
 */
		tp->snd_una = ti->ti_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_FCANTRCVMORE) {
					soisfdisconnected(so);
					tp->t_timer[TCPT_2MSL] = tcp_maxidle;
				}
				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);
				tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
				soisfdisconnected(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:
			tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
			goto dropafterack;
		}
	} /* switch(tp->t_state) */

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

	/*