aboutsummaryrefslogtreecommitdiff
path: root/slirp/tcp_input.c
blob: f946db8dc07eaed24fa0f9ffffdd12a88c32ce76 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
/*
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)tcp_input.c	8.5 (Berkeley) 4/10/94
 * tcp_input.c,v 1.10 1994/10/13 18:36:32 wollman Exp
 */

/*
 * Changes and additions relating to SLiRP
 * Copyright (c) 1995 Danny Gasparovski.
 *
 * Please read the file COPYRIGHT for the
 * terms and conditions of the copyright.
 */

#include <slirp.h>
#include "ip_icmp.h"

#define	TCPREXMTTHRESH 3

#define TCP_PAWS_IDLE	(24 * 24 * 60 * 60 * PR_SLOWHZ)

/* for modulo comparisons of timestamps */
#define TSTMP_LT(a,b)	((int)((a)-(b)) < 0)
#define TSTMP_GEQ(a,b)	((int)((a)-(b)) >= 0)

/*
 * Insert segment ti into reassembly queue of tcp with
 * control block tp.  Return TH_FIN if reassembly now includes
 * a segment with FIN.  The macro form does 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).
 */
#ifdef TCP_ACK_HACK
#define TCP_REASS(tp, ti, m, so, flags) {\
       if ((ti)->ti_seq == (tp)->rcv_nxt && \
           tcpfrag_list_empty(tp) && \
           (tp)->t_state == TCPS_ESTABLISHED) {\
               if (ti->ti_flags & TH_PUSH) \
                       tp->t_flags |= TF_ACKNOW; \
               else \
                       tp->t_flags |= TF_DELACK; \
               (tp)->rcv_nxt += (ti)->ti_len; \
               flags = (ti)->ti_flags & TH_FIN; \
               if (so->so_emu) { \
		       if (tcp_emu((so),(m))) sbappend((so), (m)); \
	       } else \
	       	       sbappend((so), (m)); \
	} else {\
               (flags) = tcp_reass((tp), (ti), (m)); \
               tp->t_flags |= TF_ACKNOW; \
       } \
}
#else
#define	TCP_REASS(tp, ti, m, so, flags) { \
	if ((ti)->ti_seq == (tp)->rcv_nxt && \
        tcpfrag_list_empty(tp) && \
	    (tp)->t_state == TCPS_ESTABLISHED) { \
		tp->t_flags |= TF_DELACK; \
		(tp)->rcv_nxt += (ti)->ti_len; \
		flags = (ti)->ti_flags & TH_FIN; \
		if (so->so_emu) { \
			if (tcp_emu((so),(m))) sbappend(so, (m)); \
		} else \
			sbappend((so), (m)); \
	} else { \
		(flags) = tcp_reass((tp), (ti), (m)); \
		tp->t_flags |= TF_ACKNOW; \
	} \
}
#endif
static void tcp_dooptions(struct tcpcb *tp, u_char *cp, int cnt,
                          struct tcpiphdr *ti);
static void tcp_xmit_timer(register struct tcpcb *tp, int rtt);

static int
tcp_reass(register struct tcpcb *tp, register struct tcpiphdr *ti,
          struct mbuf *m)
{
	register struct tcpiphdr *q;
	struct socket *so = tp->t_socket;
	int flags;

	/*
	 * Call with ti==NULL after become established to
	 * force pre-ESTABLISHED data up to user socket.
	 */
        if (ti == NULL)
		goto present;

	/*
	 * Find a segment which begins after this one does.
	 */
	for (q = tcpfrag_list_first(tp); !tcpfrag_list_end(q, tp);
            q = tcpiphdr_next(q))
		if (SEQ_GT(q->ti_seq, ti->ti_seq))
			break;

	/*
	 * If there is a preceding segment, it may provide some of
	 * our data already.  If so, drop the data from the incoming
	 * segment.  If it provides all of our data, drop us.
	 */
	if (!tcpfrag_list_end(tcpiphdr_prev(q), tp)) {
		register int i;
		q = tcpiphdr_prev(q);
		/* conversion to int (in i) handles seq wraparound */
		i = q->ti_seq + q->ti_len - ti->ti_seq;
		if (i > 0) {
			if (i >= ti->ti_len) {
				m_free(m);
				/*
				 * Try to present any queued data
				 * at the left window edge to the user.
				 * This is needed after the 3-WHS
				 * completes.
				 */
				goto present;   /* ??? */
			}
			m_adj(m, i);
			ti->ti_len -= i;
			ti->ti_seq += i;
		}
		q = tcpiphdr_next(q);
	}
	ti->ti_mbuf = m;

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	while (!tcpfrag_list_end(q, tp)) {
		register int i = (ti->ti_seq + ti->ti_len) - q->ti_seq;
		if (i <= 0)
			break;
		if (i < q->ti_len) {
			q->ti_seq += i;
			q->ti_len -= i;
			m_adj(q->ti_mbuf, i);
			break;
		}
		q = tcpiphdr_next(q);
		m = tcpiphdr_prev(q)->ti_mbuf;
		remque(tcpiphdr2qlink(tcpiphdr_prev(q)));
		m_free(m);
	}

	/*
	 * Stick new segment in its place.
	 */
	insque(tcpiphdr2qlink(ti), tcpiphdr2qlink(tcpiphdr_prev(q)));

present:
	/*
	 * Present data to user, advancing rcv_nxt through
	 * completed sequence space.
	 */
	if (!TCPS_HAVEESTABLISHED(tp->t_state))
		return (0);
	ti = tcpfrag_list_first(tp);
	if (tcpfrag_list_end(ti, tp) || ti->ti_seq != tp->rcv_nxt)
		return (0);
	if (tp->t_state == TCPS_SYN_RECEIVED && ti->ti_len)
		return (0);
	do {
		tp->rcv_nxt += ti->ti_len;
		flags = ti->ti_flags & TH_FIN;
		remque(tcpiphdr2qlink(ti));
		m = ti->ti_mbuf;
		ti = tcpiphdr_next(ti);
		if (so->so_state & SS_FCANTSENDMORE)
			m_free(m);
		else {
			if (so->so_emu) {
				if (tcp_emu(so,m)) sbappend(so, m);
			} else
				sbappend(so, m);
		}
	} while (ti != (struct tcpiphdr *)tp && ti->ti_seq == tp->rcv_nxt);
	return (flags);
}

/*
 * TCP input routine, follows pages 65-76 of the
 * protocol specification dated September, 1981 very closely.
 */
void
tcp_input(struct mbuf *m, int iphlen, struct socket *inso)
{
  	struct ip save_ip, *ip;
	register struct tcpiphdr *ti;
	caddr_t optp = NULL;
	int optlen = 0;
	int len, tlen, off;
        register struct tcpcb *tp = NULL;
	register int tiflags;
        struct socket *so = NULL;
	int todrop, acked, ourfinisacked, needoutput = 0;
	int iss = 0;
	u_long tiwin;
	int ret;
    struct ex_list *ex_ptr;
    Slirp *slirp;

	DEBUG_CALL("tcp_input");
	DEBUG_ARGS((dfd, " m = %8lx  iphlen = %2d  inso = %lx\n",
		    (long )m, iphlen, (long )inso ));

	/*
	 * If called with m == 0, then we're continuing the connect
	 */
	if (m == NULL) {
		so = inso;
		slirp = so->slirp;

		/* Re-set a few variables */
		tp = sototcpcb(so);
		m = so->so_m;
                so->so_m = NULL;
		ti = so->so_ti;
		tiwin = ti->ti_win;
		tiflags = ti->ti_flags;

		goto cont_conn;
	}
	slirp = m->slirp;

	/*
	 * Get IP and TCP header together in first mbuf.
	 * Note: IP leaves IP header in first mbuf.
	 */
	ti = mtod(m, struct tcpiphdr *);
	if (iphlen > sizeof(struct ip )) {
	  ip_stripoptions(m, (struct mbuf *)0);
	  iphlen=sizeof(struct ip );
	}
	/* XXX Check if too short */


	/*
	 * Save a copy of the IP header in case we want restore it
	 * for sending an ICMP error message in response.
	 */
	ip=mtod(m, struct ip *);
	save_ip = *ip;
	save_ip.ip_len+= iphlen;

	/*
	 * Checksum extended TCP header and data.
	 */
	tlen = ((struct ip *)ti)->ip_len;
        tcpiphdr2qlink(ti)->next = tcpiphdr2qlink(ti)->prev = NULL;
        memset(&ti->ti_i.ih_mbuf, 0 , sizeof(struct mbuf_ptr));
	ti->ti_x1 = 0;
	ti->ti_len = htons((uint16_t)tlen);
	len = sizeof(struct ip ) + tlen;
	if(cksum(m, len)) {
	  goto drop;
	}

	/*
	 * Check that TCP offset makes sense,
	 * pull out TCP options and adjust length.		XXX
	 */
	off = ti->ti_off << 2;
	if (off < sizeof (struct tcphdr) || off > tlen) {
	  goto drop;
	}
	tlen -= off;
	ti->ti_len = tlen;
	if (off > sizeof (struct tcphdr)) {
	  optlen = off - sizeof (struct tcphdr);
	  optp = mtod(m, caddr_t) + sizeof (struct tcpiphdr);
	}
	tiflags = ti->ti_flags;

	/*
	 * Convert TCP protocol specific fields to host format.
	 */
	NTOHL(ti->ti_seq);
	NTOHL(ti->ti_ack);
	NTOHS(ti->ti_win);
	NTOHS(ti->ti_urp);

	/*
	 * Drop TCP, IP headers and TCP options.
	 */
	m->m_data += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
	m->m_len  -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);

	/*
	 * Locate pcb for segment.
	 */
findso:
	so = slirp->tcp_last_so;
	if (so->so_fport != ti->ti_dport ||
	    so->so_lport != ti->ti_sport ||
	    so->so_laddr.s_addr != ti->ti_src.s_addr ||
	    so->so_faddr.s_addr != ti->ti_dst.s_addr) {
		so = solookup(&slirp->tcb, ti->ti_src, ti->ti_sport,
			       ti->ti_dst, ti->ti_dport);
		if (so)
			slirp->tcp_last_so = so;
	}

	/*
	 * If the state is CLOSED (i.e., TCB does not exist) then
	 * all data in the incoming segment is discarded.
	 * If the TCB exists but is in CLOSED state, it is embryonic,
	 * but should either do a listen or a connect soon.
	 *
	 * state == CLOSED means we've done socreate() but haven't
	 * attached it to a protocol yet...
	 *
	 * XXX If a TCB does not exist, and the TH_SYN flag is
	 * the only flag set, then create a session, mark it
	 * as if it was LISTENING, and continue...
	 */
        if (so == NULL) {
          if (slirp->restricted) {
            /* Any hostfwds will have an existing socket, so we only get here
             * for non-hostfwd connections. These should be dropped, unless it
             * happens to be a guestfwd.
             */
            for (ex_ptr = slirp->exec_list; ex_ptr; ex_ptr = ex_ptr->ex_next) {
                if (ex_ptr->ex_fport == ti->ti_dport &&
                    ti->ti_dst.s_addr == ex_ptr->ex_addr.s_addr) {
                    break;
                }
            }
            if (!ex_ptr) {
                goto dropwithreset;
            }
          }

	  if ((tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) != TH_SYN)
	    goto dropwithreset;

	  if ((so = socreate(slirp)) == NULL)
	    goto dropwithreset;
	  if (tcp_attach(so) < 0) {
	    free(so); /* Not sofree (if it failed, it's not insqued) */
	    goto dropwithreset;
	  }

	  sbreserve(&so->so_snd, TCP_SNDSPACE);
	  sbreserve(&so->so_rcv, TCP_RCVSPACE);

	  so->so_laddr = ti->ti_src;
	  so->so_lport = ti->ti_sport;
	  so->so_faddr = ti->ti_dst;
	  so->so_fport = ti->ti_dport;

	  if ((so->so_iptos = tcp_tos(so)) == 0)
	    so->so_iptos = ((struct ip *)ti)->ip_tos;

	  tp = sototcpcb(so);
	  tp->t_state = TCPS_LISTEN;
	}

        /*
         * If this is a still-connecting socket, this probably
         * a retransmit of the SYN.  Whether it's a retransmit SYN
	 * or something else, we nuke it.
         */
        if (so->so_state & SS_ISFCONNECTING)
                goto drop;

	tp = sototcpcb(so);

	/* XXX Should never fail */
        if (tp == NULL)
		goto dropwithreset;
	if (tp->t_state == TCPS_CLOSED)
		goto drop;

	tiwin = ti->ti_win;

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

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

	/*
	 * 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.
	 *
	 * XXX Some of these tests are not needed
	 * eg: the tiwin == tp->snd_wnd prevents many more
	 * predictions.. with no *real* advantage..
	 */
	if (tp->t_state == TCPS_ESTABLISHED &&
	    (tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK &&
	    ti->ti_seq == tp->rcv_nxt &&
	    tiwin && tiwin == tp->snd_wnd &&
	    tp->snd_nxt == tp->snd_max) {
		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) {
				/*
				 * this is a pure ack for outstanding data.
				 */
				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;
				sbdrop(&so->so_snd, acked);
				tp->snd_una = ti->ti_ack;
				m_free(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;

				/*
				 * This is called because sowwakeup might have
				 * put data into so_snd.  Since we don't so sowwakeup,
				 * we don't need this.. XXX???
				 */
				if (so->so_snd.sb_cc)
					(void) tcp_output(tp);

				return;
			}
		} else if (ti->ti_ack == tp->snd_una &&
		    tcpfrag_list_empty(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.
			 */
			tp->rcv_nxt += ti->ti_len;
			/*
			 * Add data to socket buffer.
			 */
			if (so->so_emu) {
				if (tcp_emu(so,m)) sbappend(so, m);
			} else
				sbappend(so, m);

			/*
			 * If this is a short packet, then ACK now - with Nagel
			 *	congestion avoidance sender won't send more until
			 *	he gets an ACK.
			 *
			 * It is better to not delay acks at all to maximize
			 * TCP throughput.  See RFC 2581.
			 */
			tp->t_flags |= TF_ACKNOW;
			tcp_output(tp);
			return;
		}
	} /* header prediction */
	/*
	 * 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 = max(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.
	 * 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: {

	  if (tiflags & TH_RST)
	    goto drop;
	  if (tiflags & TH_ACK)
	    goto dropwithreset;
	  if ((tiflags & TH_SYN) == 0)
	    goto drop;

	  /*
	   * This has way too many gotos...
	   * But a bit of spaghetti code never hurt anybody :)
	   */

	  /*
	   * If this is destined for the control address, then flag to
	   * tcp_ctl once connected, otherwise connect
	   */
	  if ((so->so_faddr.s_addr & slirp->vnetwork_mask.s_addr) ==
	      slirp->vnetwork_addr.s_addr) {
	    if (so->so_faddr.s_addr != slirp->vhost_addr.s_addr &&
		so->so_faddr.s_addr != slirp->vnameserver_addr.s_addr) {
		/* May be an add exec */
		for (ex_ptr = slirp->exec_list; ex_ptr;
		     ex_ptr = ex_ptr->ex_next) {
		  if(ex_ptr->ex_fport == so->so_fport &&
		     so->so_faddr.s_addr == ex_ptr->ex_addr.s_addr) {
		    so->so_state |= SS_CTL;
		    break;
		  }
		}
		if (so->so_state & SS_CTL) {
		    goto cont_input;
		}
	    }
	    /* CTL_ALIAS: Do nothing, tcp_fconnect will be called on it */
	  }

	  if (so->so_emu & EMU_NOCONNECT) {
	    so->so_emu &= ~EMU_NOCONNECT;
	    goto cont_input;
	  }

	  if((tcp_fconnect(so) == -1) && (errno != EINPROGRESS) && (errno != EWOULDBLOCK)) {
	    u_char code=ICMP_UNREACH_NET;
	    DEBUG_MISC((dfd, " tcp fconnect errno = %d-%s\n",
			errno,strerror(errno)));
	    if(errno == ECONNREFUSED) {
	      /* ACK the SYN, send RST to refuse the connection */
	      tcp_respond(tp, ti, m, ti->ti_seq+1, (tcp_seq)0,
			  TH_RST|TH_ACK);
	    } else {
	      if(errno == EHOSTUNREACH) code=ICMP_UNREACH_HOST;
	      HTONL(ti->ti_seq);             /* restore tcp header */
	      HTONL(ti->ti_ack);
	      HTONS(ti->ti_win);
	      HTONS(ti->ti_urp);
	      m->m_data -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
	      m->m_len  += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
	      *ip=save_ip;
	      icmp_error(m, ICMP_UNREACH,code, 0,strerror(errno));
	    }
            tcp_close(tp);
	    m_free(m);
	  } else {
	    /*
	     * Haven't connected yet, save the current mbuf
	     * and ti, and return
	     * XXX Some OS's don't tell us whether the connect()
	     * succeeded or not.  So we must time it out.
	     */
	    so->so_m = m;
	    so->so_ti = ti;
	    tp->t_timer[TCPT_KEEP] = TCPTV_KEEP_INIT;
	    tp->t_state = TCPS_SYN_RECEIVED;
	    tcp_template(tp);
	  }
	  return;

	cont_conn:
	  /* m==NULL
	   * Check if the connect succeeded
	   */
	  if (so->so_state & SS_NOFDREF) {
	    tp = tcp_close(tp);
	    goto dropwithreset;
	  }
	cont_input:
	  tcp_template(tp);

	  if (optp)
	    tcp_dooptions(tp, (u_char *)optp, optlen, ti);

	  if (iss)
	    tp->iss = iss;
	  else
	    tp->iss = slirp->tcp_iss;
	  slirp->tcp_iss += TCP_ISSINCR/2;
	  tp->irs = ti->ti_seq;
	  tcp_sendseqinit(tp);
	  tcp_rcvseqinit(tp);
	  tp->t_flags |= TF_ACKNOW;
	  tp->t_state = TCPS_SYN_RECEIVED;
	  tp->t_timer[TCPT_KEEP] = TCPTV_KEEP_INIT;
	  goto trimthenstep6;
	} /* case TCPS_LISTEN */

	/*
	 * 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 ((tiflags & TH_ACK) &&
		    (SEQ_LEQ(ti->ti_ack, tp->iss) ||
		     SEQ_GT(ti->ti_ack, tp->snd_max)))
			goto dropwithreset;

		if (tiflags & TH_RST) {
                        if (tiflags & TH_ACK) {
                                tcp_drop(tp, 0); /* XXX Check t_softerror! */
                        }
			goto drop;
		}

		if ((tiflags & TH_SYN) == 0)
			goto drop;
		if (tiflags & TH_ACK) {
			tp->snd_una = ti->ti_ack;
			if (SEQ_LT(tp->snd_nxt, tp->snd_una))
				tp->snd_nxt = tp->snd_una;
		}

		tp->t_timer[TCPT_REXMT] = 0;
		tp->irs = ti->ti_seq;
		tcp_rcvseqinit(tp);
		tp->t_flags |= TF_ACKNOW;
		if (tiflags & TH_ACK && SEQ_GT(tp->snd_una, tp->iss)) {
			soisfconnected(so);
			tp->t_state = TCPS_ESTABLISHED;

			(void) tcp_reass(tp, (struct tcpiphdr *)0,
				(struct mbuf *)0);
			/*
			 * if we didn't have to retransmit the SYN,
			 * use its rtt as our initial srtt & rtt var.
			 */
			if (tp->t_rtt)
				tcp_xmit_timer(tp, tp->t_rtt);
		} else
			tp->t_state = TCPS_SYN_RECEIVED;

trimthenstep6:
		/*
		 * Advance ti->ti_seq to correspond to first data byte.
		 * If data, trim to stay within window,
		 * dropping FIN if necessary.
		 */
		ti->ti_seq++;
		if (ti->ti_len > tp->rcv_wnd) {
			todrop = ti->ti_len - tp->rcv_wnd;
			m_adj(m, -todrop);
			ti->ti_len = tp->rcv_wnd;
			tiflags &= ~TH_FIN;
		}
		tp->snd_wl1 = ti->ti_seq - 1;
		tp->rcv_up = ti->ti_seq;
		goto step6;
	} /* switch tp->t_state */
	/*
	 * States other than LISTEN or SYN_SENT.
	 * 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.
	 */
	todrop = tp->rcv_nxt - ti->ti_seq;
	if (todrop > 0) {
		if (tiflags & TH_SYN) {
			tiflags &= ~TH_SYN;
			ti->ti_seq++;
			if (ti->ti_urp > 1)
				ti->ti_urp--;
			else
				tiflags &= ~TH_URG;
			todrop--;
		}
		/*
		 * Following if statement from Stevens, vol. 2, p. 960.
		 */
		if (todrop > ti->ti_len
		    || (todrop == ti->ti_len && (tiflags & 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.
			 */
			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;
		}
		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);
		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) {
		if (todrop >= 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;
			} else {
				goto dropafterack;
			}
		}
		m_adj(m, -todrop);
		ti->ti_len -= todrop;
		tiflags &= ~(TH_PUSH|TH_FIN);
	}

	/*
	 * 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:
	case TCPS_ESTABLISHED:
	case TCPS_FIN_WAIT_1:
	case TCPS_FIN_WAIT_2:
	case TCPS_CLOSE_WAIT:
		tp->t_state = TCPS_CLOSED;
                tcp_close(tp);
		goto drop;

	case TCPS_CLOSING:
	case TCPS_LAST_ACK:
	case TCPS_TIME_WAIT:
                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;
		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_PERSISTENT_MASK;
		    so->so_state |= SS_NOFDREF; /* CTL_CMD */
		  } else {
		    needoutput = 1;
		    tp->t_state = TCPS_FIN_WAIT_1;
		  }
		} else {
		  soisfconnected(so);
		}

		(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) {
			  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)) {
			goto dropafterack;
		}
		acked = ti->ti_ack - tp->snd_una;

		/*
		 * If 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 (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;
		}
		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) {
					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;
			}
			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) {
                                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))))) {
		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 > so->so_rcv.sb_datalen) {
			ti->ti_urp = 0;
			tiflags &= ~TH_URG;
			goto dodata;
		}
		/*
		 * 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_urgc =  so->so_rcv.sb_cc +
				(tp->rcv_up - tp->rcv_nxt); /* -1; */
			tp->rcv_up = ti->ti_seq + ti->ti_urp;

		}
	} 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:

	/*
	 * If this is a small packet, then ACK now - with Nagel
	 *      congestion avoidance sender won't send more until
	 *      he gets an ACK.
	 */
	if (ti->ti_len && (unsigned)ti->ti_len <= 5 &&
	    ((struct tcpiphdr_2 *)ti)->first_char == (char)27) {
		tp->t_flags |= TF_ACKNOW;
	}

	/*
	 * 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);
	} else {
		m_free(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) {
			/*
			 * If we receive a FIN we can't send more data,
			 * set it SS_FDRAIN
                         * Shutdown the socket if there is no rx data in the
			 * buffer.
			 * soread() is called on completion of shutdown() and
			 * will got to TCPS_LAST_ACK, and use tcp_output()
			 * to send the FIN.
			 */
			sofwdrain(so);

			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:
		  if(so->so_emu == EMU_CTL)        /* no shutdown on socket */
		    tp->t_state = TCPS_LAST_ACK;
		  else
		    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);
			tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
			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;
		}
	}

	/*
	 * 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;
	m_free(m);
	tp->t_flags |= TF_ACKNOW;
	(void) tcp_output(tp);
	return;

dropwithreset:
	/* reuses m if m!=NULL, m_free() unnecessary */
	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);
	}

	return;

drop:
	/*
	 * Drop space held by incoming segment and return.
	 */
	m_free(m);
}

static void
tcp_dooptions(struct tcpcb *tp, u_char *cp, int cnt, struct tcpiphdr *ti)
{
	uint16_t mss;
	int opt, optlen;

	DEBUG_CALL("tcp_dooptions");
	DEBUG_ARGS((dfd, " tp = %lx  cnt=%i\n", (long)tp, cnt));

	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[0];
		if (opt == TCPOPT_EOL)
			break;
		if (opt == TCPOPT_NOP)
			optlen = 1;
		else {
			optlen = cp[1];
			if (optlen <= 0)
				break;
		}
		switch (opt) {

		default:
			continue;

		case TCPOPT_MAXSEG:
			if (optlen != TCPOLEN_MAXSEG)
				continue;
			if (!(ti->ti_flags & TH_SYN))
				continue;
			memcpy((char *) &mss, (char *) cp + 2, sizeof(mss));
			NTOHS(mss);
			(void) tcp_mss(tp, mss);	/* sets t_maxseg */
			break;
		}
	}
}


/*
 * Pull out of band byte out of a segment so
 * it doesn't appear in the user's data queue.
 * It is still reflected in the segment length for
 * sequencing purposes.
 */

#ifdef notdef

void
tcp_pulloutofband(so, ti, m)
	struct socket *so;
	struct tcpiphdr *ti;
	register struct mbuf *m;
{
	int cnt = ti->ti_urp - 1;

	while (cnt >= 0) {
		if (m->m_len > cnt) {
			char *cp = mtod(m, caddr_t) + cnt;
			struct tcpcb *tp = sototcpcb(so);

			tp->t_iobc = *cp;
			tp->t_oobflags |= TCPOOB_HAVEDATA;
			memcpy(sp, cp+1, (unsigned)(m->m_len - cnt - 1));
			m->m_len--;
			return;
		}
		cnt -= m->m_len;
		m = m->m_next; /* XXX WRONG! Fix it! */
		if (m == 0)
			break;
	}
	panic("tcp_pulloutofband");
}

#endif /* notdef */

/*
 * Collect new round-trip time estimate
 * and update averages and current timeout.
 */

static void
tcp_xmit_timer(register struct tcpcb *tp, int rtt)
{
	register short delta;

	DEBUG_CALL("tcp_xmit_timer");
	DEBUG_ARG("tp = %lx", (long)tp);
	DEBUG_ARG("rtt = %d", rtt);

	if (tp->t_srtt != 0) {
		/*
		 * srtt is stored as fixed point with 3 bits after the
		 * binary point (i.e., scaled by 8).  The following magic
		 * is equivalent to the smoothing algorithm in rfc793 with
		 * an alpha of .875 (srtt = rtt/8 + srtt*7/8 in fixed
		 * point).  Adjust rtt to origin 0.
		 */
		delta = rtt - 1 - (tp->t_srtt >> TCP_RTT_SHIFT);
		if ((tp->t_srtt += delta) <= 0)
			tp->t_srtt = 1;
		/*
		 * We accumulate a smoothed rtt variance (actually, a
		 * smoothed mean difference), then set the retransmit
		 * timer to smoothed rtt + 4 times the smoothed variance.
		 * rttvar is stored as fixed point with 2 bits after the
		 * binary point (scaled by 4).  The following is
		 * equivalent to rfc793 smoothing with an alpha of .75
		 * (rttvar = rttvar*3/4 + |delta| / 4).  This replaces
		 * rfc793's wired-in beta.
		 */
		if (delta < 0)
			delta = -delta;
		delta -= (tp->t_rttvar >> TCP_RTTVAR_SHIFT);
		if ((tp->t_rttvar += delta) <= 0)
			tp->t_rttvar = 1;
	} else {
		/*
		 * No rtt measurement yet - use the unsmoothed rtt.
		 * Set the variance to half the rtt (so our first
		 * retransmit happens at 3*rtt).
		 */
		tp->t_srtt = rtt << TCP_RTT_SHIFT;
		tp->t_rttvar = rtt << (TCP_RTTVAR_SHIFT - 1);
	}
	tp->t_rtt = 0;
	tp->t_rxtshift = 0;

	/*
	 * the retransmit should happen at rtt + 4 * rttvar.
	 * Because of the way we do the smoothing, srtt and rttvar
	 * will each average +1/2 tick of bias.  When we compute
	 * the retransmit timer, we want 1/2 tick of rounding and
	 * 1 extra tick because of +-1/2 tick uncertainty in the
	 * firing of the timer.  The bias will give us exactly the
	 * 1.5 tick we need.  But, because the bias is
	 * statistical, we have to test that we don't drop below
	 * the minimum feasible timer (which is 2 ticks).
	 */
	TCPT_RANGESET(tp->t_rxtcur, TCP_REXMTVAL(tp),
	    (short)tp->t_rttmin, TCPTV_REXMTMAX); /* XXX */

	/*
	 * We received an ack for a packet that wasn't retransmitted;
	 * it is probably safe to discard any error indications we've
	 * received recently.  This isn't quite right, but close enough
	 * for now (a route might have failed after we sent a segment,
	 * and the return path might not be symmetrical).
	 */
	tp->t_softerror = 0;
}

/*
 * Determine a reasonable value for maxseg size.
 * If the route is known, check route for mtu.
 * If none, use an mss that can be handled on the outgoing
 * interface without forcing IP to fragment; if bigger than
 * an mbuf cluster (MCLBYTES), round down to nearest multiple of MCLBYTES
 * to utilize large mbufs.  If no route is found, route has no mtu,
 * or the destination isn't local, use a default, hopefully conservative
 * size (usually 512 or the default IP max size, but no more than the mtu
 * of the interface), as we can't discover anything about intervening
 * gateways or networks.  We also initialize the congestion/slow start
 * window to be a single segment if the destination isn't local.
 * While looking at the routing entry, we also initialize other path-dependent
 * parameters from pre-set or cached values in the routing entry.
 */

int
tcp_mss(struct tcpcb *tp, u_int offer)
{
	struct socket *so = tp->t_socket;
	int mss;

	DEBUG_CALL("tcp_mss");
	DEBUG_ARG("tp = %lx", (long)tp);
	DEBUG_ARG("offer = %d", offer);

	mss = min(IF_MTU, IF_MRU) - sizeof(struct tcpiphdr);
	if (offer)
		mss = min(mss, offer);
	mss = max(mss, 32);
	if (mss < tp->t_maxseg || offer != 0)
	   tp->t_maxseg = mss;

	tp->snd_cwnd = mss;

	sbreserve(&so->so_snd, TCP_SNDSPACE + ((TCP_SNDSPACE % mss) ?
                                               (mss - (TCP_SNDSPACE % mss)) :
                                               0));
	sbreserve(&so->so_rcv, TCP_RCVSPACE + ((TCP_RCVSPACE % mss) ?
                                               (mss - (TCP_RCVSPACE % mss)) :
                                               0));

	DEBUG_MISC((dfd, " returning mss = %d\n", mss));

	return mss;
}