tcp_input.c

ReactOS是一些高手根据Windows XP的内核编写出的类XP。内核实现机理和API函数调用几乎相同。甚至可以兼容XP的程序。喜欢研究系统内核的人可以看一看。

					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;
		}
		/*
		 * 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;
		}
		/*
		 *  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 = 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 (to.to_flag & TOF_TS)
			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);

		/*
		 * 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;

		/*
		 * 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;
		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;
		}
		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_CANTRCVMORE) {
					soisdisconnected(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);
				/* Shorten TIME_WAIT [RFC-1644, p.28] */
				if (tp->cc_recv != 0 &&
				    tp->t_duration < TCPTV_MSL)
					tp->t_timer[TCPT_2MSL] =
					    tp->t_rxtcur * TCPTV_TWTRUNC;
				else
					tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
				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:
			tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
			goto dropafterack;
		}
	}

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;
	}

	/*
	 * Process segments with URG.
	 */
	if ((tiflags & TH_URG) && ti->ti_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 (ti->ti_urp + so->so_rcv.sb_cc > sb_max) {
			ti->ti_urp = 0;			/* XXX */
			tiflags &= ~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(ti->ti_seq+ti->ti_urp, tp->rcv_up)) {
			tp->rcv_up = ti->ti_seq + ti->ti_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 (ti->ti_urp <= (u_long)ti->ti_len
#ifdef SO_OOBINLINE
		     && (so->so_options & SO_OOBINLINE) == 0
#endif
		     )
			tcp_pulloutofband(so, ti, m);
	} 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 ((ti->ti_len || (tiflags&TH_FIN)) &&
	    TCPS_HAVERCVDFIN(tp->t_state) == 0) {
		TCP_REASS(tp, ti, m, so, tiflags);
		/*
		 * 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);
		tiflags &= ~TH_FIN;
	}

	/*
	 * If FIN is received ACK the FIN and let the user know
	 * that the connection is closing.
	 */
	if (tiflags & 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 when SYN is sent.
			 *  Otherwise, since we received a FIN then no
			 *  more input can be expected, send ACK now.
			 */
			if (tp->t_flags & TF_NEEDSYN)
				tp->t_flags |= TF_DELACK;
			else
				tp->t_flags |= TF_ACKNOW;
			tp->rcv_nxt++;
		}
		switch (tp->t_state) {

	 	/*
		 * In SYN_RECEIVED and ESTABLISHED STATES
		 * enter the CLOSE_WAIT state.
		 */
		case TCPS_SYN_RECEIVED:
		case TCPS_ESTABLISHED:
			tp->t_state = TCPS_CLOSE_WAIT;
			break;

	 	/*
		 * If still in FIN_WAIT_1 STATE FIN has not been acked so
		 * enter the CLOSING state.
		 */
		case TCPS_FIN_WAIT_1:
			tp->t_state = TCPS_CLOSING;
			break;

	 	/*
		 * In FIN_WAIT_2 state enter the TIME_WAIT state,
		 * starting the time-wait timer, turning off the other
		 * standard timers.
		 */
		case TCPS_FIN_WAIT_2:
			tp->t_state = TCPS_TIME_WAIT;
			tcp_canceltimers(tp);
			/* Shorten TIME_WAIT [RFC-1644, p.28] */
			if (tp->cc_recv != 0 &&
			    tp->t_duration < TCPTV_MSL) {
				tp->t_timer[TCPT_2MSL] =
				    tp->t_rxtcur * TCPTV_TWTRUNC;
				/* For transaction client, force ACK now. */
				tp->t_flags |= TF_ACKNOW;
			}
			else
				tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
			soisdisconnected(so);
			break;

		/*
		 * In TIME_WAIT state restart the 2 MSL time_wait timer.
		 */
		case TCPS_TIME_WAIT:
			tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
			break;
		}
	}
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_INPUT, ostate, tp, &tcp_saveti, 0);
#endif

	/*
	 * Return any desired output.
	 */
	if (needoutput || (tp->t_flags & TF_ACKNOW))
		(void) tcp_output(tp);
	return;

dropafterack:
	/*
	 * Generate an ACK dropping incoming segment if it occupies
	 * sequence space, where the ACK reflects our state.
	 */
	if (tiflags & TH_RST)
		goto drop;
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_DROP, ostate, tp, &tcp_saveti, 0);
#endif
	m_freem(m);
	tp->t_flags |= TF_ACKNOW;
	(void) tcp_output(tp);
	return;

dropwithreset:
	/*
	 * Generate a RST, dropping incoming segment.
	 * Make ACK acceptable to originator of segment.
	 * Don't bother to respond if destination was broadcast/multicast.
	 */
	if ((tiflags & TH_RST) || m->m_flags & (M_BCAST|M_MCAST) ||
	    IN_MULTICAST(ntohl(ti->ti_dst.s_addr)))
		goto drop;
#ifdef TCPDEBUG
	if (tp == 0 || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_DROP, ostate, tp, &tcp_saveti, 0);
#endif
	if (tiflags & TH_ACK)
		tcp_respond(tp, ti, m, (tcp_seq)0, ti->ti_ack, TH_RST);
	else {
		if (tiflags & TH_SYN)
			ti->ti_len++;
		tcp_respond(tp, ti, m, ti->ti_seq+ti->ti_len, (tcp_seq)0,
		    TH_RST|TH_ACK);
	}
	/* destroy temporarily created socket */
	if (dropsocket)
		(void) soabort(so);
	return;

drop:
	/*
	 * Drop space held by incoming segment and return.
	 */
#ifdef TCPDEBUG
	if (tp == 0 || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_DROP, ostate, tp, &tcp_saveti, 0);
#endif
	m_freem(m);
	/* destroy temporarily created socket */
	if (dropsocket)
		(void) soabort(so);
	return;
#ifndef TUBA_INCLUDE
}

void