aboutsummaryrefslogtreecommitdiff
path: root/sys/netinet/tcp_stacks/fastpath.c
blob: 551433d36f13870d5e18aea222dd48dd6a8fbb60 (plain) (blame)
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
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
/*-
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
 *	The Regents of the University of California.  All rights reserved.
 * Copyright (c) 2007-2008,2010
 *	Swinburne University of Technology, Melbourne, Australia.
 * Copyright (c) 2009-2010 Lawrence Stewart <lstewart@freebsd.org>
 * Copyright (c) 2010 The FreeBSD Foundation
 * Copyright (c) 2010-2011 Juniper Networks, Inc.
 * Copyright (c) 2015 Netflix Inc.
 * All rights reserved.
 *
 * Portions of this software were developed at the Centre for Advanced Internet
 * Architectures, Swinburne University of Technology, by Lawrence Stewart,
 * James Healy and David Hayes, made possible in part by a grant from the Cisco
 * University Research Program Fund at Community Foundation Silicon Valley.
 *
 * Portions of this software were developed at the Centre for Advanced
 * Internet Architectures, Swinburne University of Technology, Melbourne,
 * Australia by David Hayes under sponsorship from the FreeBSD Foundation.
 *
 * Portions of this software were developed by Robert N. M. Watson under
 * contract to Juniper Networks, Inc.
 *
 * Portions of this software were developed by Randall R. Stewart while
 * working for Netflix Inc.
 *
 * 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.
 * 4. 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	8.12 (Berkeley) 5/24/95
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_tcpdebug.h"

#include <sys/param.h>
#include <sys/lock.h>
#include <sys/module.h>
#include <sys/mutex.h>
#include <sys/kernel.h>
#ifdef TCP_HHOOK
#include <sys/hhook.h>
#endif
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/proc.h>		/* for proc0 declaration */
#include <sys/protosw.h>
#include <sys/sdt.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>

#include <machine/cpu.h>	/* before tcp_seq.h, for tcp_random18() */

#include <vm/uma.h>

#include <net/route.h>
#include <net/vnet.h>

#define TCPSTATES		/* for logging */

#include <netinet/in.h>
#include <netinet/in_kdtrace.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>	/* required for icmp_var.h */
#include <netinet/icmp_var.h>	/* for ICMP_BANDLIM */
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#include <netinet/ip6.h>
#include <netinet/icmp6.h>
#include <netinet6/in6_pcb.h>
#include <netinet6/ip6_var.h>
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet6/tcp6_var.h>
#include <netinet/tcpip.h>
#include <netinet/tcp_syncache.h>
#include <netinet/cc/cc.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif /* TCPDEBUG */
#ifdef TCP_OFFLOAD
#include <netinet/tcp_offload.h>
#endif

#include <machine/in_cksum.h>

#include <security/mac/mac_framework.h>

VNET_DECLARE(int, tcp_autorcvbuf_inc);
#define	V_tcp_autorcvbuf_inc	VNET(tcp_autorcvbuf_inc)
VNET_DECLARE(int, tcp_autorcvbuf_max);
#define	V_tcp_autorcvbuf_max	VNET(tcp_autorcvbuf_max)
VNET_DECLARE(int, tcp_do_rfc3042);
#define	V_tcp_do_rfc3042	VNET(tcp_do_rfc3042)
VNET_DECLARE(int, tcp_do_autorcvbuf);
#define	V_tcp_do_autorcvbuf	VNET(tcp_do_autorcvbuf)
VNET_DECLARE(int, tcp_insecure_rst);
#define	V_tcp_insecure_rst	VNET(tcp_insecure_rst)
VNET_DECLARE(int, tcp_insecure_syn);
#define	V_tcp_insecure_syn	VNET(tcp_insecure_syn)

static void	 tcp_do_segment_fastslow(struct mbuf *, struct tcphdr *,
			struct socket *, struct tcpcb *, int, int, uint8_t,
			int);

static void	 tcp_do_segment_fastack(struct mbuf *, struct tcphdr *,
			struct socket *, struct tcpcb *, int, int, uint8_t,
			int);

/*
 * Indicate whether this ack should be delayed.  We can delay the ack if
 * following conditions are met:
 *	- There is no delayed ack timer in progress.
 *	- Our last ack wasn't a 0-sized window. We never want to delay
 *	  the ack that opens up a 0-sized window.
 *	- LRO wasn't used for this segment. We make sure by checking that the
 *	  segment size is not larger than the MSS.
 */
#define DELAY_ACK(tp, tlen)						\
	((!tcp_timer_active(tp, TT_DELACK) &&				\
	    (tp->t_flags & TF_RXWIN0SENT) == 0) &&			\
	    (tlen <= tp->t_maxseg) &&					\
	    (V_tcp_delack_enabled || (tp->t_flags & TF_NEEDSYN)))

/*
 * So how is this faster than the normal fast ack?
 * It basically allows us to also stay in the fastpath
 * when a window-update ack also arrives. In testing
 * we saw only 25-30% of connections doing fastpath 
 * due to the fact that along with moving forward
 * in sequence the window was also updated.
 */
static void
tcp_do_fastack(struct mbuf *m, struct tcphdr *th, struct socket *so,
	       struct tcpcb *tp, struct tcpopt *to, int drop_hdrlen, int tlen, 
	       int ti_locked, uint32_t tiwin)
{
	int acked;
	uint16_t nsegs;
	int winup_only=0;

	nsegs = max(1, m->m_pkthdr.lro_nsegs);
#ifdef TCPDEBUG
	/*
	 * The size of tcp_saveipgen must be the size of the max ip header,
	 * now IPv6.
	 */
	u_char tcp_saveipgen[IP6_HDR_LEN];
	struct tcphdr tcp_savetcp;
	short ostate = 0;
#endif
        /*
	 * The following if statement will be true if
	 * we are doing the win_up_in_fp <and>
	 * - We have more new data (SEQ_LT(tp->snd_wl1, th->th_seq)) <or>
	 * - No more new data, but we have an ack for new data
	 *   (tp->snd_wl1 == th->th_seq && SEQ_LT(tp->snd_wl2, th->th_ack))
	 * - No more new data, the same ack point but the window grew
	 *   (tp->snd_wl1 == th->th_seq && tp->snd_wl2 == th->th_ack && twin > tp->snd_wnd)
	 */
	if ((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 (tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd) {
			winup_only = 1;
			TCPSTAT_INC(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;
	}
	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record the timestamp.
	 * NOTE that the test is modified according to the latest
	 * proposal of the tcplw@cray.com list (Braden 1993/04/26).
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
		tp->ts_recent_age = tcp_ts_getticks();
		tp->ts_recent = to->to_tsval;
	}
	/*
	 * This is a pure ack for outstanding data.
	 */
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

	TCPSTAT_INC(tcps_predack);

	/*
	 * "bad retransmit" recovery.
	 */
	if (tp->t_rxtshift == 1 &&
	    tp->t_flags & TF_PREVVALID &&
	    (int)(ticks - tp->t_badrxtwin) < 0) {
		cc_cong_signal(tp, th, CC_RTO_ERR);
	}

	/*
	 * Recalculate the transmit timer / rtt.
	 *
	 * Some boxes send broken timestamp replies
	 * during the SYN+ACK phase, ignore
	 * timestamps of 0 or we could calculate a
	 * huge RTT and blow up the retransmit timer.
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    to->to_tsecr) {
		uint32_t t;

		t = tcp_ts_getticks() - to->to_tsecr;
		if (!tp->t_rttlow || tp->t_rttlow > t)
			tp->t_rttlow = t;
		tcp_xmit_timer(tp,
			       TCP_TS_TO_TICKS(t) + 1);
	} else if (tp->t_rtttime &&
		   SEQ_GT(th->th_ack, tp->t_rtseq)) {
		if (!tp->t_rttlow ||
		    tp->t_rttlow > ticks - tp->t_rtttime)
			tp->t_rttlow = ticks - tp->t_rtttime;
		tcp_xmit_timer(tp,
			       ticks - tp->t_rtttime);
	}
	if (winup_only == 0) {
		acked = BYTES_THIS_ACK(tp, th);

#ifdef TCP_HHOOK
		/* Run HHOOK_TCP_ESTABLISHED_IN helper hooks. */
		hhook_run_tcp_est_in(tp, th, to);
#endif

		TCPSTAT_ADD(tcps_rcvackbyte, acked);
		sbdrop(&so->so_snd, acked);
		if (SEQ_GT(tp->snd_una, tp->snd_recover) &&
		    SEQ_LEQ(th->th_ack, tp->snd_recover))
			tp->snd_recover = th->th_ack - 1;
				
		/*
		 * Let the congestion control algorithm update
		 * congestion control related information. This
		 * typically means increasing the congestion
		 * window.
		 */
		cc_ack_received(tp, th, nsegs, CC_ACK);

		tp->snd_una = th->th_ack;
		/*
		 * Pull snd_wl2 up to prevent seq wrap relative
		 * to th_ack.
		 */
		tp->snd_wl2 = th->th_ack;
		tp->t_dupacks = 0;

		/*
		 * 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.
		 */
#ifdef TCPDEBUG
		if (so->so_options & SO_DEBUG)
			tcp_trace(TA_INPUT, ostate, tp,
				  (void *)tcp_saveipgen,
				  &tcp_savetcp, 0);
#endif
		TCP_PROBE3(debug__input, tp, th, m);
		m_freem(m);
		if (tp->snd_una == tp->snd_max)
			tcp_timer_activate(tp, TT_REXMT, 0);
		else if (!tcp_timer_active(tp, TT_PERSIST))
			tcp_timer_activate(tp, TT_REXMT,
					   tp->t_rxtcur);
	} else {
		/* 
		 * Window update only, just free the mbufs and
		 * send out whatever we can.
		 */
		m_freem(m);
	}
	sowwakeup(so);
	if (sbavail(&so->so_snd))
		(void) tcp_output(tp);
	KASSERT(ti_locked == TI_UNLOCKED, ("%s: check_delack ti_locked %d",
					    __func__, ti_locked));
	INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
	INP_WLOCK_ASSERT(tp->t_inpcb);

	if (tp->t_flags & TF_DELACK) {
		tp->t_flags &= ~TF_DELACK;
		tcp_timer_activate(tp, TT_DELACK, tcp_delacktime);
	}
	INP_WUNLOCK(tp->t_inpcb);
}

/*
 * Here nothing is really faster, its just that we
 * have broken out the fast-data path also just like
 * the fast-ack. 
 */
static void
tcp_do_fastnewdata(struct mbuf *m, struct tcphdr *th, struct socket *so,
		   struct tcpcb *tp, struct tcpopt *to, int drop_hdrlen, int tlen, 
		   int ti_locked, uint32_t tiwin)
{
	int newsize = 0;	/* automatic sockbuf scaling */
#ifdef TCPDEBUG
	/*
	 * The size of tcp_saveipgen must be the size of the max ip header,
	 * now IPv6.
	 */
	u_char tcp_saveipgen[IP6_HDR_LEN];
	struct tcphdr tcp_savetcp;
	short ostate = 0;
#endif
	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record the timestamp.
	 * NOTE that the test is modified according to the latest
	 * proposal of the tcplw@cray.com list (Braden 1993/04/26).
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
		tp->ts_recent_age = tcp_ts_getticks();
		tp->ts_recent = to->to_tsval;
	}

	/*
	 * This is a pure, in-sequence data packet with
	 * nothing on the reassembly queue and we have enough
	 * buffer space to take it.
	 */
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

	/* Clean receiver SACK report if present */
	if ((tp->t_flags & TF_SACK_PERMIT) && tp->rcv_numsacks)
		tcp_clean_sackreport(tp);
	TCPSTAT_INC(tcps_preddat);
	tp->rcv_nxt += tlen;
	/*
	 * Pull snd_wl1 up to prevent seq wrap relative to
	 * th_seq.
	 */
	tp->snd_wl1 = th->th_seq;
	/*
	 * Pull rcv_up up to prevent seq wrap relative to
	 * rcv_nxt.
	 */
	tp->rcv_up = tp->rcv_nxt;
	TCPSTAT_ADD(tcps_rcvbyte, tlen);
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_INPUT, ostate, tp,
			  (void *)tcp_saveipgen, &tcp_savetcp, 0);
#endif
	TCP_PROBE3(debug__input, tp, th, m);
	/*
	 * Automatic sizing of receive socket buffer.  Often the send
	 * buffer size is not optimally adjusted to the actual network
	 * conditions at hand (delay bandwidth product).  Setting the
	 * buffer size too small limits throughput on links with high
	 * bandwidth and high delay (eg. trans-continental/oceanic links).
	 *
	 * On the receive side the socket buffer memory is only rarely
	 * used to any significant extent.  This allows us to be much
	 * more aggressive in scaling the receive socket buffer.  For
	 * the case that the buffer space is actually used to a large
	 * extent and we run out of kernel memory we can simply drop
	 * the new segments; TCP on the sender will just retransmit it
	 * later.  Setting the buffer size too big may only consume too
	 * much kernel memory if the application doesn't read() from
	 * the socket or packet loss or reordering makes use of the
	 * reassembly queue.
	 *
	 * The criteria to step up the receive buffer one notch are:
	 *  1. Application has not set receive buffer size with
	 *     SO_RCVBUF. Setting SO_RCVBUF clears SB_AUTOSIZE.
	 *  2. the number of bytes received during the time it takes
	 *     one timestamp to be reflected back to us (the RTT);
	 *  3. received bytes per RTT is within seven eighth of the
	 *     current socket buffer size;
	 *  4. receive buffer size has not hit maximal automatic size;
	 *
	 * This algorithm does one step per RTT at most and only if
	 * we receive a bulk stream w/o packet losses or reorderings.
	 * Shrinking the buffer during idle times is not necessary as
	 * it doesn't consume any memory when idle.
	 *
	 * TODO: Only step up if the application is actually serving
	 * the buffer to better manage the socket buffer resources.
	 */
	if (V_tcp_do_autorcvbuf &&
	    (to->to_flags & TOF_TS) &&
	    to->to_tsecr &&
	    (so->so_rcv.sb_flags & SB_AUTOSIZE)) {
		if (TSTMP_GT(to->to_tsecr, tp->rfbuf_ts) &&
		    to->to_tsecr - tp->rfbuf_ts < hz) {
			if (tp->rfbuf_cnt >
			    (so->so_rcv.sb_hiwat / 8 * 7) &&
			    so->so_rcv.sb_hiwat <
			    V_tcp_autorcvbuf_max) {
				newsize =
					min(so->so_rcv.sb_hiwat +
					    V_tcp_autorcvbuf_inc,
					    V_tcp_autorcvbuf_max);
			}
			/* Start over with next RTT. */
			tp->rfbuf_ts = 0;
			tp->rfbuf_cnt = 0;
		} else
			tp->rfbuf_cnt += tlen;	/* add up */
	}

	/* Add data to socket buffer. */
	SOCKBUF_LOCK(&so->so_rcv);
	if (so->so_rcv.sb_state & SBS_CANTRCVMORE) {
		m_freem(m);
	} else {
		/*
		 * Set new socket buffer size.
		 * Give up when limit is reached.
		 */
		if (newsize)
			if (!sbreserve_locked(&so->so_rcv,
					      newsize, so, NULL))
				so->so_rcv.sb_flags &= ~SB_AUTOSIZE;
		m_adj(m, drop_hdrlen);	/* delayed header drop */
		sbappendstream_locked(&so->so_rcv, m, 0);
	}
	/* NB: sorwakeup_locked() does an implicit unlock. */
	sorwakeup_locked(so);
	if (DELAY_ACK(tp, tlen)) {
		tp->t_flags |= TF_DELACK;
	} else {
		tp->t_flags |= TF_ACKNOW;
		tcp_output(tp);
	}
	KASSERT(ti_locked == TI_UNLOCKED, ("%s: check_delack ti_locked %d",
					    __func__, ti_locked));
	INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
	INP_WLOCK_ASSERT(tp->t_inpcb);

	if (tp->t_flags & TF_DELACK) {
		tp->t_flags &= ~TF_DELACK;
		tcp_timer_activate(tp, TT_DELACK, tcp_delacktime);
	}
	INP_WUNLOCK(tp->t_inpcb);
}

/*
 * The slow-path is the clone of the long long part
 * of tcp_do_segment past all the fast-path stuff. We
 * use it here by two different callers, the fast/slow and
 * the fastack only.
 */
static void
tcp_do_slowpath(struct mbuf *m, struct tcphdr *th, struct socket *so,
		struct tcpcb *tp, struct tcpopt *to, int drop_hdrlen, int tlen, 
		int ti_locked, uint32_t tiwin, int thflags)
{
	int  acked, ourfinisacked, needoutput = 0;
	int rstreason, todrop, win;
	uint16_t nsegs;
	char *s;
	struct in_conninfo *inc;
	struct mbuf *mfree = NULL;

	nsegs = max(1, m->m_pkthdr.lro_nsegs);
#ifdef TCPDEBUG
	/*
	 * The size of tcp_saveipgen must be the size of the max ip header,
	 * now IPv6.
	 */
	u_char tcp_saveipgen[IP6_HDR_LEN];
	struct tcphdr tcp_savetcp;
	short ostate = 0;
#endif
	/*
	 * 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.
	 */
	inc = &tp->t_inpcb->inp_inc;
	win = sbspace(&so->so_rcv);
	if (win < 0)
		win = 0;
	tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt));

	/* Reset receive buffer auto scaling when not in bulk receive mode. */
	tp->rfbuf_ts = 0;
	tp->rfbuf_cnt = 0;

	switch (tp->t_state) {

	/*
	 * If the state is SYN_RECEIVED:
	 *	if seg contains an ACK, but not for our SYN/ACK, send a RST.
	 */
	case TCPS_SYN_RECEIVED:
		if ((thflags & TH_ACK) &&
		    (SEQ_LEQ(th->th_ack, tp->snd_una) ||
		     SEQ_GT(th->th_ack, tp->snd_max))) {
				rstreason = BANDLIM_RST_OPENPORT;
				goto dropwithreset;
		}
		break;

	/*
	 * 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 seg contains an ECE and ECN support is enabled, the stream
	 *	    is ECN capable.
	 *	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 ((thflags & TH_ACK) &&
		    (SEQ_LEQ(th->th_ack, tp->iss) ||
		     SEQ_GT(th->th_ack, tp->snd_max))) {
			rstreason = BANDLIM_UNLIMITED;
			goto dropwithreset;
		}
		if ((thflags & (TH_ACK|TH_RST)) == (TH_ACK|TH_RST)) {
			TCP_PROBE5(connect__refused, NULL, tp, m, tp, th);
			tp = tcp_drop(tp, ECONNREFUSED);
		}
		if (thflags & TH_RST)
			goto drop;
		if (!(thflags & TH_SYN))
			goto drop;

		tp->irs = th->th_seq;
		tcp_rcvseqinit(tp);
		if (thflags & TH_ACK) {
			TCPSTAT_INC(tcps_connects);
			soisconnected(so);
#ifdef MAC
			mac_socketpeer_set_from_mbuf(m, so);
#endif
			/* Do window scaling on this connection? */
			if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
				(TF_RCVD_SCALE|TF_REQ_SCALE)) {
				tp->rcv_scale = tp->request_r_scale;
			}
			tp->rcv_adv += min(tp->rcv_wnd,
			    TCP_MAXWIN << tp->rcv_scale);
			tp->snd_una++;		/* SYN is acked */
			/*
			 * If there's data, delay ACK; if there's also a FIN
			 * ACKNOW will be turned on later.
			 */
			if (DELAY_ACK(tp, tlen) && tlen != 0)
				tcp_timer_activate(tp, TT_DELACK,
				    tcp_delacktime);
			else
				tp->t_flags |= TF_ACKNOW;

			if ((thflags & TH_ECE) && V_tcp_do_ecn) {
				tp->t_flags |= TF_ECN_PERMIT;
				TCPSTAT_INC(tcps_ecn_shs);
			}
			
			/*
			 * 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) {
				tcp_state_change(tp, TCPS_FIN_WAIT_1);
				tp->t_flags &= ~TF_NEEDFIN;
				thflags &= ~TH_SYN;
			} else {
				tcp_state_change(tp, TCPS_ESTABLISHED);
				TCP_PROBE5(connect__established, NULL, tp,
				    m, tp, th);
				cc_conn_init(tp);
				tcp_timer_activate(tp, TT_KEEP,
				    TP_KEEPIDLE(tp));
			}
		} else {
			/*
			 * Received initial SYN in SYN-SENT[*] state =>
			 * simultaneous open.
			 * If it succeeds, connection is * half-synchronized.
			 * Otherwise, do 3-way handshake:
			 *        SYN-SENT -> SYN-RECEIVED
			 *        SYN-SENT* -> SYN-RECEIVED*
			 */
			tp->t_flags |= (TF_ACKNOW | TF_NEEDSYN);
			tcp_timer_activate(tp, TT_REXMT, 0);
			tcp_state_change(tp, TCPS_SYN_RECEIVED);
		}

		KASSERT(ti_locked == TI_RLOCKED, ("%s: trimthenstep6: "
		    "ti_locked %d", __func__, ti_locked));
		INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
		INP_WLOCK_ASSERT(tp->t_inpcb);

		/*
		 * 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_INC(tcps_rcvpackafterwin);
			TCPSTAT_ADD(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:
	 *      do normal processing.
	 *
	 * NB: Leftover from RFC1644 T/TCP.  Cases to be reused later.
	 */
	case TCPS_LAST_ACK:
	case TCPS_CLOSING:
		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 (thflags & TH_RST) {
		/*
		 * RFC5961 Section 3.2
		 *
		 * - RST drops connection only if SEG.SEQ == RCV.NXT.
		 * - If RST is in window, we send challenge ACK.
		 *
		 * Note: to take into account delayed ACKs, we should
		 *   test against last_ack_sent instead of rcv_nxt.
		 * Note 2: we handle special case of closed window, not
		 *   covered by the RFC.
		 */
		if ((SEQ_GEQ(th->th_seq, tp->last_ack_sent) &&
		    SEQ_LT(th->th_seq, tp->last_ack_sent + tp->rcv_wnd)) ||
		    (tp->rcv_wnd == 0 && tp->last_ack_sent == th->th_seq)) {
			INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
			KASSERT(ti_locked == TI_RLOCKED,
			    ("%s: TH_RST ti_locked %d, th %p tp %p",
			    __func__, ti_locked, th, tp));
			KASSERT(tp->t_state != TCPS_SYN_SENT,
			    ("%s: TH_RST for TCPS_SYN_SENT th %p tp %p",
			    __func__, th, tp));

			if (V_tcp_insecure_rst ||
			    tp->last_ack_sent == th->th_seq) {
				TCPSTAT_INC(tcps_drops);
				/* Drop the connection. */
				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:
				case TCPS_CLOSING:
				case TCPS_LAST_ACK:
					so->so_error = ECONNRESET;
				close:
					/* FALLTHROUGH */
				default:
					tp = tcp_close(tp);
				}
			} else {
				TCPSTAT_INC(tcps_badrst);
				/* Send challenge ACK. */
				tcp_respond(tp, mtod(m, void *), th, m,
				    tp->rcv_nxt, tp->snd_nxt, TH_ACK);
				tp->last_ack_sent = tp->rcv_nxt;
				m = NULL;
			}
		}
		goto drop;
	}

	/*
	 * RFC5961 Section 4.2
	 * Send challenge ACK for any SYN in synchronized state.
	 */
	if ((thflags & TH_SYN) && tp->t_state != TCPS_SYN_SENT) {
		KASSERT(ti_locked == TI_RLOCKED,
		    ("tcp_do_segment: TH_SYN ti_locked %d", ti_locked));
		INP_INFO_RLOCK_ASSERT(&V_tcbinfo);

		TCPSTAT_INC(tcps_badsyn);
		if (V_tcp_insecure_syn &&
		    SEQ_GEQ(th->th_seq, tp->last_ack_sent) &&
		    SEQ_LT(th->th_seq, tp->last_ack_sent + tp->rcv_wnd)) {
			tp = tcp_drop(tp, ECONNRESET);
			rstreason = BANDLIM_UNLIMITED;
		} else {
			/* Send challenge ACK. */
			tcp_respond(tp, mtod(m, void *), th, m, tp->rcv_nxt,
			    tp->snd_nxt, TH_ACK);
			tp->last_ack_sent = tp->rcv_nxt;
			m = NULL;
		}
		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_flags & 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 (tcp_ts_getticks() - 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_INC(tcps_rcvduppack);
			TCPSTAT_ADD(tcps_rcvdupbyte, tlen);
			TCPSTAT_INC(tcps_pawsdrop);
			if (tlen)
				goto dropafterack;
			goto drop;
		}
	}

	/*
	 * 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_RST_OPENPORT;
		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_INC(tcps_rcvduppack);
			TCPSTAT_ADD(tcps_rcvdupbyte, todrop);
		} else {
			TCPSTAT_INC(tcps_rcvpartduppack);
			TCPSTAT_ADD(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) {
		KASSERT(ti_locked == TI_RLOCKED, ("%s: SS_NOFDEREF && "
		    "CLOSE_WAIT && tlen ti_locked %d", __func__, ti_locked));
		INP_INFO_RLOCK_ASSERT(&V_tcbinfo);

		if ((s = tcp_log_addrs(inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: %s: Received %d bytes of data "
			    "after socket was closed, "
			    "sending RST and removing tcpcb\n",
			    s, __func__, tcpstates[tp->t_state], tlen);
			free(s, M_TCPLOG);
		}
		tp = tcp_close(tp);
		TCPSTAT_INC(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_INC(tcps_rcvpackafterwin);
		if (todrop >= tlen) {
			TCPSTAT_ADD(tcps_rcvbyteafterwin, tlen);
			/*
			 * 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_INC(tcps_rcvwinprobe);
			} else
				goto dropafterack;
		} else
			TCPSTAT_ADD(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: 
	 * 1) That the test incorporates suggestions from the latest
	 *    proposal of the tcplw@cray.com list (Braden 1993/04/26).
	 * 2) That updating only on newer timestamps interferes with
	 *    our earlier PAWS tests, so this check should be solely
	 *    predicated on the sequence space of this segment.
	 * 3) That we modify the segment boundary check to be 
	 *        Last.ACK.Sent <= SEG.SEQ + SEG.Len  
	 *    instead of RFC1323's
	 *        Last.ACK.Sent < SEG.SEQ + SEG.Len,
	 *    This modified check allows us to overcome RFC1323's
	 *    limitations as described in Stevens TCP/IP Illustrated
	 *    Vol. 2 p.869. In such cases, we can still calculate the
	 *    RTT correctly when RCV.NXT == Last.ACK.Sent.
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    SEQ_LEQ(th->th_seq, tp->last_ack_sent) &&
	    SEQ_LEQ(tp->last_ack_sent, th->th_seq + tlen +
		((thflags & (TH_SYN|TH_FIN)) != 0))) {
		tp->ts_recent_age = tcp_ts_getticks();
		tp->ts_recent = to->to_tsval;
	}

	/*
	 * 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 if (tp->t_flags & TF_ACKNOW)
			goto dropafterack;
		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_INC(tcps_connects);
		soisconnected(so);
		/* Do window scaling? */
		if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
			(TF_RCVD_SCALE|TF_REQ_SCALE)) {
			tp->rcv_scale = tp->request_r_scale;
			tp->snd_wnd = tiwin;
		}
		/*
		 * Make transitions:
		 *      SYN-RECEIVED  -> ESTABLISHED
		 *      SYN-RECEIVED* -> FIN-WAIT-1
		 */
		tp->t_starttime = ticks;
		if (tp->t_flags & TF_NEEDFIN) {
			tcp_state_change(tp, TCPS_FIN_WAIT_1);
			tp->t_flags &= ~TF_NEEDFIN;
		} else {
			tcp_state_change(tp, TCPS_ESTABLISHED);
			TCP_PROBE5(accept__established, NULL, tp,
			    m, tp, th);
			cc_conn_init(tp);
			tcp_timer_activate(tp, TT_KEEP, TP_KEEPIDLE(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;
		/* FALLTHROUGH */

	/*
	 * 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:
		if (SEQ_GT(th->th_ack, tp->snd_max)) {
			TCPSTAT_INC(tcps_rcvacktoomuch);
			goto dropafterack;
		}
		if ((tp->t_flags & TF_SACK_PERMIT) &&
		    ((to->to_flags & TOF_SACK) ||
		     !TAILQ_EMPTY(&tp->snd_holes)))
			tcp_sack_doack(tp, to, th->th_ack);
		else
			/*
			 * Reset the value so that previous (valid) value
			 * from the last ack with SACK doesn't get used.
			 */
			tp->sackhint.sacked_bytes = 0;

#ifdef TCP_HHOOK
		/* Run HHOOK_TCP_ESTABLISHED_IN helper hooks. */
		hhook_run_tcp_est_in(tp, th, to);
#endif

		if (SEQ_LEQ(th->th_ack, tp->snd_una)) {
			if (tlen == 0 && tiwin == tp->snd_wnd) {
				/*
				 * If this is the first time we've seen a
				 * FIN from the remote, this is not a
				 * duplicate and it needs to be processed
				 * normally.  This happens during a
				 * simultaneous close.
				 */
				if ((thflags & TH_FIN) &&
				    (TCPS_HAVERCVDFIN(tp->t_state) == 0)) {
					tp->t_dupacks = 0;
					break;
				}
				TCPSTAT_INC(tcps_rcvdupack);
				/*
				 * If we have outstanding data (other than
				 * a window probe), this is a completely
				 * duplicate ack (ie, window info didn't
				 * change and FIN isn't set),
				 * 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.
				 *
				 * When using TCP ECN, notify the peer that
				 * we reduced the cwnd.
				 */
				if (!tcp_timer_active(tp, TT_REXMT) ||
				    th->th_ack != tp->snd_una)
					tp->t_dupacks = 0;
				else if (++tp->t_dupacks > tcprexmtthresh ||
				     IN_FASTRECOVERY(tp->t_flags)) {
					cc_ack_received(tp, th, nsegs,
					    CC_DUPACK);
					if ((tp->t_flags & TF_SACK_PERMIT) &&
					    IN_FASTRECOVERY(tp->t_flags)) {
						int awnd;
						
						/*
						 * Compute the amount of data in flight first.
						 * We can inject new data into the pipe iff 
						 * we have less than 1/2 the original window's
						 * worth of data in flight.
						 */
						if (V_tcp_do_rfc6675_pipe)
							awnd = tcp_compute_pipe(tp);
						else
							awnd = (tp->snd_nxt - tp->snd_fack) +
								tp->sackhint.sack_bytes_rexmit;

						if (awnd < tp->snd_ssthresh) {
							tp->snd_cwnd += tp->t_maxseg;
							/*
							 * RFC5681 Section 3.2 talks about cwnd
							 * inflation on additional dupacks and
							 * deflation on recovering from loss.
							 *
							 * We keep cwnd into check so that
							 * we don't have to 'deflate' it when we
							 * get out of recovery.
							 */
							if (tp->snd_cwnd > tp->snd_ssthresh)
								tp->snd_cwnd = tp->snd_ssthresh;
						}
					} else
						tp->snd_cwnd += tp->t_maxseg;
					(void) tp->t_fb->tfb_tcp_output(tp);
					goto drop;
				} else if (tp->t_dupacks == tcprexmtthresh) {
					tcp_seq onxt = tp->snd_nxt;

					/*
					 * If we're doing sack, check to
					 * see if we're already in sack
					 * recovery. If we're not doing sack,
					 * check to see if we're in newreno
					 * recovery.
					 */
					if (tp->t_flags & TF_SACK_PERMIT) {
						if (IN_FASTRECOVERY(tp->t_flags)) {
							tp->t_dupacks = 0;
							break;
						}
					} else {
						if (SEQ_LEQ(th->th_ack,
						    tp->snd_recover)) {
							tp->t_dupacks = 0;
							break;
						}
					}
					/* Congestion signal before ack. */
					cc_cong_signal(tp, th, CC_NDUPACK);
					cc_ack_received(tp, th, nsegs,
					    CC_DUPACK);
					tcp_timer_activate(tp, TT_REXMT, 0);
					tp->t_rtttime = 0;
					if (tp->t_flags & TF_SACK_PERMIT) {
						TCPSTAT_INC(
						    tcps_sack_recovery_episode);
						tp->sack_newdata = tp->snd_nxt;
						if (CC_ALGO(tp)->cong_signal == NULL)
							tp->snd_cwnd = tp->t_maxseg;
						(void) tp->t_fb->tfb_tcp_output(tp);
						goto drop;
					}
					tp->snd_nxt = th->th_ack;
					if (CC_ALGO(tp)->cong_signal == NULL)
						tp->snd_cwnd = tp->t_maxseg;
					(void) tp->t_fb->tfb_tcp_output(tp);
					KASSERT(tp->snd_limited <= 2,
					    ("%s: tp->snd_limited too big",
					    __func__));
					if (CC_ALGO(tp)->cong_signal == NULL)
						tp->snd_cwnd = tp->snd_ssthresh +
						    tp->t_maxseg *
						    (tp->t_dupacks - tp->snd_limited);
					if (SEQ_GT(onxt, tp->snd_nxt))
						tp->snd_nxt = onxt;
					goto drop;
				} else if (V_tcp_do_rfc3042) {
					/*
					 * Process first and second duplicate
					 * ACKs. Each indicates a segment
					 * leaving the network, creating room
					 * for more. Make sure we can send a
					 * packet on reception of each duplicate
					 * ACK by increasing snd_cwnd by one
					 * segment. Restore the original
					 * snd_cwnd after packet transmission.
					 */
					cc_ack_received(tp, th, nsegs,
					    CC_DUPACK);
					uint32_t oldcwnd = tp->snd_cwnd;
					tcp_seq oldsndmax = tp->snd_max;
					u_int sent;
					int avail;

					KASSERT(tp->t_dupacks == 1 ||
					    tp->t_dupacks == 2,
					    ("%s: dupacks not 1 or 2",
					    __func__));
					if (tp->t_dupacks == 1)
						tp->snd_limited = 0;
					tp->snd_cwnd =
					    (tp->snd_nxt - tp->snd_una) +
					    (tp->t_dupacks - tp->snd_limited) *
					    tp->t_maxseg;
					/*
					 * Only call tcp_output when there
					 * is new data available to be sent.
					 * Otherwise we would send pure ACKs.
					 */
					SOCKBUF_LOCK(&so->so_snd);
					avail = sbavail(&so->so_snd) -
					    (tp->snd_nxt - tp->snd_una);
					SOCKBUF_UNLOCK(&so->so_snd);
					if (avail > 0)
						(void) tp->t_fb->tfb_tcp_output(tp);
					sent = tp->snd_max - oldsndmax;
					if (sent > tp->t_maxseg) {
						KASSERT((tp->t_dupacks == 2 &&
						    tp->snd_limited == 0) ||
						   (sent == tp->t_maxseg + 1 &&
						    tp->t_flags & TF_SENTFIN),
						    ("%s: sent too much",
						    __func__));
						tp->snd_limited = 2;
					} else if (sent > 0)
						++tp->snd_limited;
					tp->snd_cwnd = oldcwnd;
					goto drop;
				}
			} else
				tp->t_dupacks = 0;
			break;
		}

		KASSERT(SEQ_GT(th->th_ack, tp->snd_una),
		    ("%s: th_ack <= snd_una", __func__));

		/*
		 * If the congestion window was inflated to account
		 * for the other side's cached packets, retract it.
		 */
		if (IN_FASTRECOVERY(tp->t_flags)) {
			if (SEQ_LT(th->th_ack, tp->snd_recover)) {
				if (tp->t_flags & TF_SACK_PERMIT)
					tcp_sack_partialack(tp, th);
				else
					tcp_newreno_partial_ack(tp, th);
			} else
				cc_post_recovery(tp, th);
		}
		tp->t_dupacks = 0;
		/*
		 * 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->rcv_scale = tp->request_r_scale;
				/* Send window already scaled. */
			}
		}

process_ACK:
		INP_WLOCK_ASSERT(tp->t_inpcb);

		acked = BYTES_THIS_ACK(tp, th);
		TCPSTAT_INC(tcps_rcvackpack);
		TCPSTAT_ADD(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 && tp->t_flags & TF_PREVVALID &&
		    (int)(ticks - tp->t_badrxtwin) < 0)
			cc_cong_signal(tp, th, CC_RTO_ERR);

		/*
		 * 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.
		 *
		 * Some boxes send broken timestamp replies
		 * during the SYN+ACK phase, ignore
		 * timestamps of 0 or we could calculate a
		 * huge RTT and blow up the retransmit timer.
		 */
		if ((to->to_flags & TOF_TS) != 0 && to->to_tsecr) {
			uint32_t t;

			t = tcp_ts_getticks() - to->to_tsecr;
			if (!tp->t_rttlow || tp->t_rttlow > t)
				tp->t_rttlow = t;
			tcp_xmit_timer(tp, TCP_TS_TO_TICKS(t) + 1);
		} else if (tp->t_rtttime && SEQ_GT(th->th_ack, tp->t_rtseq)) {
			if (!tp->t_rttlow || tp->t_rttlow > ticks - tp->t_rtttime)
				tp->t_rttlow = ticks - tp->t_rtttime;
			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) {
			tcp_timer_activate(tp, TT_REXMT, 0);
			needoutput = 1;
		} else if (!tcp_timer_active(tp, TT_PERSIST))
			tcp_timer_activate(tp, TT_REXMT, tp->t_rxtcur);

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

		/*
		 * Let the congestion control algorithm update congestion
		 * control related information. This typically means increasing
		 * the congestion window.
		 */
		cc_ack_received(tp, th, nsegs, CC_ACK);

		SOCKBUF_LOCK(&so->so_snd);
		if (acked > sbavail(&so->so_snd)) {
			tp->snd_wnd -= sbavail(&so->so_snd);
			mfree = sbcut_locked(&so->so_snd,
			    (int)sbavail(&so->so_snd));
			ourfinisacked = 1;
		} else {
			mfree = sbcut_locked(&so->so_snd, acked);
			tp->snd_wnd -= acked;
			ourfinisacked = 0;
		}
		/* NB: sowwakeup_locked() does an implicit unlock. */
		sowwakeup_locked(so);
		m_freem(mfree);
		/* Detect una wraparound. */
		if (!IN_RECOVERY(tp->t_flags) &&
		    SEQ_GT(tp->snd_una, tp->snd_recover) &&
		    SEQ_LEQ(th->th_ack, tp->snd_recover))
			tp->snd_recover = th->th_ack - 1;
		/* XXXLAS: Can this be moved up into cc_post_recovery? */
		if (IN_RECOVERY(tp->t_flags) &&
		    SEQ_GEQ(th->th_ack, tp->snd_recover)) {
			EXIT_RECOVERY(tp->t_flags);
		}
		tp->snd_una = th->th_ack;
		if (tp->t_flags & TF_SACK_PERMIT) {
			if (SEQ_GT(tp->snd_una, tp->snd_recover))
				tp->snd_recover = tp->snd_una;
		}
		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.
				 *
				 * XXXjl:
				 * we should release the tp also, and use a
				 * compressed state.
				 */
				if (so->so_rcv.sb_state & SBS_CANTRCVMORE) {
					soisdisconnected(so);
					tcp_timer_activate(tp, TT_2MSL,
					    (tcp_fast_finwait2_recycle ?
					    tcp_finwait2_timeout :
					    TP_MAXIDLE(tp)));
				}
				tcp_state_change(tp, 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) {
				INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
				tcp_twstart(tp);
				INP_INFO_RUNLOCK(&V_tcbinfo);
				m_freem(m);
				return;
			}
			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) {
				INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
				tp = tcp_close(tp);
				goto drop;
			}
			break;
		}
	}

step6:
	INP_WLOCK_ASSERT(tp->t_inpcb);

	/*
	 * 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_INC(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.
		 */
		SOCKBUF_LOCK(&so->so_rcv);
		if (th->th_urp + sbavail(&so->so_rcv) > sb_max) {
			th->th_urp = 0;			/* XXX */
			thflags &= ~TH_URG;		/* XXX */
			SOCKBUF_UNLOCK(&so->so_rcv);	/* 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 = sbavail(&so->so_rcv) +
			    (tp->rcv_up - tp->rcv_nxt) - 1;
			if (so->so_oobmark == 0)
				so->so_rcv.sb_state |= SBS_RCVATMARK;
			sohasoutofband(so);
			tp->t_oobflags &= ~(TCPOOB_HAVEDATA | TCPOOB_HADDATA);
		}
		SOCKBUF_UNLOCK(&so->so_rcv);
		/*
		 * 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 <= (uint32_t)tlen &&
		    !(so->so_options & SO_OOBINLINE)) {
			/* hdr drop is delayed */
			tcp_pulloutofband(so, th, m, drop_hdrlen);
		}
	} 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 */
	INP_WLOCK_ASSERT(tp->t_inpcb);

	/*
	 * 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) {
		tcp_seq save_start = th->th_seq;
		m_adj(m, drop_hdrlen);	/* delayed header drop */
		/*
		 * Insert segment which includes th into TCP reassembly queue
		 * with control block tp.  Set thflags to whether reassembly now
		 * includes a segment with FIN.  This handles 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, tlen))
				tp->t_flags |= TF_DELACK;
			else
				tp->t_flags |= TF_ACKNOW;
			tp->rcv_nxt += tlen;
			thflags = th->th_flags & TH_FIN;
			TCPSTAT_INC(tcps_rcvpack);
			TCPSTAT_ADD(tcps_rcvbyte, tlen);
			SOCKBUF_LOCK(&so->so_rcv);
			if (so->so_rcv.sb_state & SBS_CANTRCVMORE)
				m_freem(m);
			else
				sbappendstream_locked(&so->so_rcv, m, 0);
			/* NB: sorwakeup_locked() does an implicit unlock. */
			sorwakeup_locked(so);
		} else {
			/*
			 * XXX: Due to the header drop above "th" is
			 * theoretically invalid by now.  Fortunately
			 * m_adj() doesn't actually frees any mbufs
			 * when trimming from the head.
			 */
			thflags = tcp_reass(tp, th, &tlen, m);
			tp->t_flags |= TF_ACKNOW;
		}
		if (tlen > 0 && (tp->t_flags & TF_SACK_PERMIT))
			tcp_update_sack_list(tp, save_start, save_start + tlen);
#if 0
		/*
		 * Note the amount of data that peer has sent into
		 * our window, in order to estimate the sender's
		 * buffer size.
		 * XXX: Unused.
		 */
		if (SEQ_GT(tp->rcv_adv, tp->rcv_nxt))
			len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt);
		else
			len = so->so_rcv.sb_hiwat;
#endif
	} 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 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:
			tp->t_starttime = ticks;
			/* FALLTHROUGH */
		case TCPS_ESTABLISHED:
			tcp_state_change(tp, 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:
			tcp_state_change(tp, 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:
			INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
			KASSERT(ti_locked == TI_RLOCKED, ("%s: dodata "
			    "TCP_FIN_WAIT_2 ti_locked: %d", __func__,
			    ti_locked));

			tcp_twstart(tp);
			INP_INFO_RUNLOCK(&V_tcbinfo);
			return;
		}
	}
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_INPUT, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif
	TCP_PROBE3(debug__input, tp, th, m);

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

	KASSERT(ti_locked == TI_UNLOCKED, ("%s: check_delack ti_locked %d",
	    __func__, ti_locked));
	INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
	INP_WLOCK_ASSERT(tp->t_inpcb);

	if (tp->t_flags & TF_DELACK) {
		tp->t_flags &= ~TF_DELACK;
		tcp_timer_activate(tp, TT_DELACK, tcp_delacktime);
	}
	INP_WUNLOCK(tp->t_inpcb);
	return;

dropafterack:
	/*
	 * Generate an ACK dropping incoming segment if it occupies
	 * sequence space, where the ACK reflects our state.
	 *
	 * We can now skip the test for the RST flag since all
	 * paths to this code happen after packets containing
	 * RST have been dropped.
	 *
	 * In the SYN-RECEIVED state, don't send an ACK unless the
	 * segment we received passes the SYN-RECEIVED ACK test.
	 * If it fails send a RST.  This breaks the loop in the
	 * "LAND" DoS attack, and also prevents an ACK storm
	 * between two listening ports that have been sent forged
	 * SYN segments, each with the source address of the other.
	 */
	if (tp->t_state == TCPS_SYN_RECEIVED && (thflags & TH_ACK) &&
	    (SEQ_GT(tp->snd_una, th->th_ack) ||
	     SEQ_GT(th->th_ack, tp->snd_max)) ) {
		rstreason = BANDLIM_RST_OPENPORT;
		goto dropwithreset;
	}
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_DROP, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif
	TCP_PROBE3(debug__drop, tp, th, m);
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

	tp->t_flags |= TF_ACKNOW;
	(void) tp->t_fb->tfb_tcp_output(tp);
	INP_WUNLOCK(tp->t_inpcb);
	m_freem(m);
	return;

dropwithreset:
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

	if (tp != NULL) {
		tcp_dropwithreset(m, th, tp, tlen, rstreason);
		INP_WUNLOCK(tp->t_inpcb);
	} else
		tcp_dropwithreset(m, th, NULL, tlen, rstreason);
	return;

drop:
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
		ti_locked = TI_UNLOCKED;
	}
#ifdef INVARIANTS
	else
		INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
#endif

	/*
	 * Drop space held by incoming segment and return.
	 */
#ifdef TCPDEBUG
	if (tp == NULL || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_DROP, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif
	TCP_PROBE3(debug__drop, tp, th, m);
	if (tp != NULL)
		INP_WUNLOCK(tp->t_inpcb);
	m_freem(m);
}


/*
 * Do fast slow is a combination of the original
 * tcp_dosegment and a split fastpath, one function
 * for the fast-ack which also includes allowing fastpath
 * for window advanced in sequence acks. And also a
 * sub-function that handles the insequence data.
 */
void
tcp_do_segment_fastslow(struct mbuf *m, struct tcphdr *th, struct socket *so,
			struct tcpcb *tp, int drop_hdrlen, int tlen, uint8_t iptos,
			int ti_locked)
{
	int thflags;
	uint32_t tiwin;
	char *s;
	uint16_t nsegs;
	int can_enter;
	struct in_conninfo *inc;
	struct tcpopt to;

	thflags = th->th_flags;
	tp->sackhint.last_sack_ack = 0;
	inc = &tp->t_inpcb->inp_inc;
	nsegs = max(1, m->m_pkthdr.lro_nsegs);
	/*
	 * If this is either a state-changing packet or current state isn't
	 * established, we require a write lock on tcbinfo.  Otherwise, we
	 * allow the tcbinfo to be in either alocked or unlocked, as the
	 * caller may have unnecessarily acquired a write lock due to a race.
	 */
	if ((thflags & (TH_SYN | TH_FIN | TH_RST)) != 0 ||
	    tp->t_state != TCPS_ESTABLISHED) {
		KASSERT(ti_locked == TI_RLOCKED, ("%s ti_locked %d for "
						  "SYN/FIN/RST/!EST", __func__, ti_locked));
		INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
	} else {
#ifdef INVARIANTS
		if (ti_locked == TI_RLOCKED) {
			INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
		} else {
			KASSERT(ti_locked == TI_UNLOCKED, ("%s: EST "
							   "ti_locked: %d", __func__, ti_locked));
			INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
		}
#endif
	}
	INP_WLOCK_ASSERT(tp->t_inpcb);
	KASSERT(tp->t_state > TCPS_LISTEN, ("%s: TCPS_LISTEN",
					    __func__));
	KASSERT(tp->t_state != TCPS_TIME_WAIT, ("%s: TCPS_TIME_WAIT",
						__func__));

	/*
	 * Segment received on connection.
	 * Reset idle time and keep-alive timer.
	 * XXX: This should be done after segment
	 * validation to ignore broken/spoofed segs.
	 */
	tp->t_rcvtime = ticks;

	/*
	 * Unscale the window into a 32-bit value.
	 * For the SYN_SENT state the scale is zero.
	 */
	tiwin = th->th_win << tp->snd_scale;

	/*
	 * TCP ECN processing.
	 */
	if (tp->t_flags & TF_ECN_PERMIT) {
		if (thflags & TH_CWR)
			tp->t_flags &= ~TF_ECN_SND_ECE;
		switch (iptos & IPTOS_ECN_MASK) {
		case IPTOS_ECN_CE:
			tp->t_flags |= TF_ECN_SND_ECE;
			TCPSTAT_INC(tcps_ecn_ce);
			break;
		case IPTOS_ECN_ECT0:
			TCPSTAT_INC(tcps_ecn_ect0);
			break;
		case IPTOS_ECN_ECT1:
			TCPSTAT_INC(tcps_ecn_ect1);
			break;
		}
		/* Congestion experienced. */
		if (thflags & TH_ECE) {
			cc_cong_signal(tp, th, CC_ECN);
		}
	}

	/*
	 * Parse options on any incoming segment.
	 */
	tcp_dooptions(&to, (u_char *)(th + 1),
		      (th->th_off << 2) - sizeof(struct tcphdr),
		      (thflags & TH_SYN) ? TO_SYN : 0);

	/*
	 * If echoed timestamp is later than the current time,
	 * fall back to non RFC1323 RTT calculation.  Normalize
	 * timestamp if syncookies were used when this connection
	 * was established.
	 */
	if ((to.to_flags & TOF_TS) && (to.to_tsecr != 0)) {
		to.to_tsecr -= tp->ts_offset;
		if (TSTMP_GT(to.to_tsecr, tcp_ts_getticks()))
			to.to_tsecr = 0;
	}
	/*
	 * If timestamps were negotiated during SYN/ACK they should
	 * appear on every segment during this session and vice versa.
	 */
	if ((tp->t_flags & TF_RCVD_TSTMP) && !(to.to_flags & TOF_TS)) {
		if ((s = tcp_log_addrs(inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: Timestamp missing, "
			    "no action\n", s, __func__);
			free(s, M_TCPLOG);
		}
	}
	if (!(tp->t_flags & TF_RCVD_TSTMP) && (to.to_flags & TOF_TS)) {
		if ((s = tcp_log_addrs(inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: Timestamp not expected, "
			    "no action\n", s, __func__);
			free(s, M_TCPLOG);
		}
	}

	/*
	 * Process options only when we get SYN/ACK back. The SYN case
	 * for incoming connections is handled in tcp_syncache.
	 * According to RFC1323 the window field in a SYN (i.e., a <SYN>
	 * or <SYN,ACK>) segment itself is never scaled.
	 * XXX this is traditional behavior, may need to be cleaned up.
	 */
	if (tp->t_state == TCPS_SYN_SENT && (thflags & TH_SYN)) {
		if ((to.to_flags & TOF_SCALE) &&
		    (tp->t_flags & TF_REQ_SCALE)) {
			tp->t_flags |= TF_RCVD_SCALE;
			tp->snd_scale = to.to_wscale;
		}
		/*
		 * Initial send window.  It will be updated with
		 * the next incoming segment to the scaled value.
		 */
		tp->snd_wnd = th->th_win;
		if (to.to_flags & TOF_TS) {
			tp->t_flags |= TF_RCVD_TSTMP;
			tp->ts_recent = to.to_tsval;
			tp->ts_recent_age = tcp_ts_getticks();
		}
		if (to.to_flags & TOF_MSS)
			tcp_mss(tp, to.to_mss);
		if ((tp->t_flags & TF_SACK_PERMIT) &&
		    (to.to_flags & TOF_SACKPERM) == 0)
			tp->t_flags &= ~TF_SACK_PERMIT;
	}
	can_enter = 0;
	if (__predict_true((tlen == 0))) {
		/*
		 * The ack moved forward and we have a window (non-zero)
		 * <or>
		 * The ack did not move forward, but the window increased.
		 */
		if (__predict_true((SEQ_GT(th->th_ack, tp->snd_una) && tiwin) ||
				   ((th->th_ack == tp->snd_una) && tiwin && (tiwin > tp->snd_wnd)))) {
			can_enter = 1;
		}
	} else {
		/* 
		 * Data incoming, use the old entry criteria
		 * for fast-path with data.
		 */
		if ((tiwin && tiwin == tp->snd_wnd)) {
			can_enter = 1;
		}
	}
	/*
	 * 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.
	 * Make sure that the hidden state-flags are also off.
	 * Since we check for TCPS_ESTABLISHED first, it can only
	 * be TH_NEEDSYN.
	 */
	if (__predict_true(tp->t_state == TCPS_ESTABLISHED &&
	    th->th_seq == tp->rcv_nxt &&
	    (thflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK &&
	    tp->snd_nxt == tp->snd_max &&
	    can_enter &&
	    ((tp->t_flags & (TF_NEEDSYN|TF_NEEDFIN)) == 0) &&
	    LIST_EMPTY(&tp->t_segq) &&
	    ((to.to_flags & TOF_TS) == 0 ||
	     TSTMP_GEQ(to.to_tsval, tp->ts_recent)))) {
		if (__predict_true((tlen == 0) &&
		    (SEQ_LEQ(th->th_ack, tp->snd_max) &&
		     !IN_RECOVERY(tp->t_flags) &&
		     (to.to_flags & TOF_SACK) == 0 &&
		     TAILQ_EMPTY(&tp->snd_holes)))) {
			/* We are done */
			tcp_do_fastack(m, th, so, tp, &to, drop_hdrlen, tlen, 
				       ti_locked, tiwin);
			return;
		} else if ((tlen) &&
			   (th->th_ack == tp->snd_una &&
			    tlen <= sbspace(&so->so_rcv))) {
			tcp_do_fastnewdata(m, th, so, tp, &to, drop_hdrlen, tlen, 
					   ti_locked, tiwin);
			/* We are done */
			return;
		}
	}
	tcp_do_slowpath(m, th, so, tp, &to, drop_hdrlen, tlen,
			ti_locked, tiwin, thflags);
}


/*
 * This subfunction is used to try to highly optimize the
 * fast path. We again allow window updates that are
 * in sequence to remain in the fast-path. We also add
 * in the __predict's to attempt to help the compiler.
 * Note that if we return a 0, then we can *not* process
 * it and the caller should push the packet into the 
 * slow-path.
 */
static int
tcp_fastack(struct mbuf *m, struct tcphdr *th, struct socket *so,
	       struct tcpcb *tp, struct tcpopt *to, int drop_hdrlen, int tlen, 
	       int ti_locked, uint32_t tiwin)
{
	int acked;
	uint16_t nsegs;
	int winup_only=0;

	nsegs = max(1, m->m_pkthdr.lro_nsegs);
#ifdef TCPDEBUG
	/*
	 * The size of tcp_saveipgen must be the size of the max ip header,
	 * now IPv6.
	 */
	u_char tcp_saveipgen[IP6_HDR_LEN];
	struct tcphdr tcp_savetcp;
	short ostate = 0;
#endif


	if (__predict_false(SEQ_LEQ(th->th_ack, tp->snd_una))) {
		/* Old ack, behind (or duplicate to) the last one rcv'd */
		return (0);
	}
	if (__predict_false(th->th_ack == tp->snd_una) && 
	    __predict_false(tiwin <= tp->snd_wnd)) {
		/* duplicate ack <or> a shrinking dup ack with shrinking window */
		return (0);
	}
	if (__predict_false(tiwin == 0)) {
		/* zero window */
		return (0);
	}
	if (__predict_false(SEQ_GT(th->th_ack, tp->snd_max))) {
		/* Above what we have sent? */
		return (0);
	}
	if (__predict_false(tp->snd_nxt != tp->snd_max)) {
		/* We are retransmitting */
		return (0);
	}
	if (__predict_false(tp->t_flags & (TF_NEEDSYN|TF_NEEDFIN))) {
		/* We need a SYN or a FIN, unlikely.. */
		return (0);
	}
	if((to->to_flags & TOF_TS) && __predict_false(TSTMP_LT(to->to_tsval, tp->ts_recent))) {
		/* Timestamp is behind .. old ack with seq wrap? */
		return (0);
	}
	if (__predict_false(IN_RECOVERY(tp->t_flags))) {
		/* Still recovering */
		return (0);
	}
	if (__predict_false(to->to_flags & TOF_SACK)) {
		/* Sack included in the ack..  */
		return (0);
	}
	if (!TAILQ_EMPTY(&tp->snd_holes)) {
		/* We have sack holes on our scoreboard */
		return (0);
	}
	/* Ok if we reach here, we can process a fast-ack */

	/* Did the window get updated? */
	if (tiwin != tp->snd_wnd) {
		/* keep track of pure window updates */
		if (tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd) {
			winup_only = 1;
			TCPSTAT_INC(tcps_rcvwinupd);
		}
		tp->snd_wnd = tiwin;
		tp->snd_wl1 = th->th_seq;
		if (tp->snd_wnd > tp->max_sndwnd)
			tp->max_sndwnd = tp->snd_wnd;
	}
	/*
	 * Pull snd_wl2 up to prevent seq wrap relative
	 * to th_ack.
	 */
	tp->snd_wl2 = th->th_ack;
	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record the timestamp.
	 * NOTE that the test is modified according to the latest
	 * proposal of the tcplw@cray.com list (Braden 1993/04/26).
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
		tp->ts_recent_age = tcp_ts_getticks();
		tp->ts_recent = to->to_tsval;
	}
	/*
	 * This is a pure ack for outstanding data.
	 */
	if (ti_locked == TI_RLOCKED) {
		INP_INFO_RUNLOCK(&V_tcbinfo);
	}
	ti_locked = TI_UNLOCKED;

	TCPSTAT_INC(tcps_predack);

	/*
	 * "bad retransmit" recovery.
	 */
	if (tp->t_rxtshift == 1 &&
	    tp->t_flags & TF_PREVVALID &&
	    (int)(ticks - tp->t_badrxtwin) < 0) {
		cc_cong_signal(tp, th, CC_RTO_ERR);
	}

	/*
	 * Recalculate the transmit timer / rtt.
	 *
	 * Some boxes send broken timestamp replies
	 * during the SYN+ACK phase, ignore
	 * timestamps of 0 or we could calculate a
	 * huge RTT and blow up the retransmit timer.
	 */
	if ((to->to_flags & TOF_TS) != 0 &&
	    to->to_tsecr) {
		uint32_t t;

		t = tcp_ts_getticks() - to->to_tsecr;
		if (!tp->t_rttlow || tp->t_rttlow > t)
			tp->t_rttlow = t;
		tcp_xmit_timer(tp,
			       TCP_TS_TO_TICKS(t) + 1);
	} else if (tp->t_rtttime &&
		   SEQ_GT(th->th_ack, tp->t_rtseq)) {
		if (!tp->t_rttlow ||
		    tp->t_rttlow > ticks - tp->t_rtttime)
			tp->t_rttlow = ticks - tp->t_rtttime;
		tcp_xmit_timer(tp,
			       ticks - tp->t_rtttime);
	}
	if (winup_only == 0) {
		acked = BYTES_THIS_ACK(tp, th);

#ifdef TCP_HHOOK
		/* Run HHOOK_TCP_ESTABLISHED_IN helper hooks. */
		hhook_run_tcp_est_in(tp, th, to);
#endif

		TCPSTAT_ADD(tcps_rcvackbyte, acked);
		sbdrop(&so->so_snd, acked);
		if (SEQ_GT(tp->snd_una, tp->snd_recover) &&
		    SEQ_LEQ(th->th_ack, tp->snd_recover))
			tp->snd_recover = th->th_ack - 1;
				
		/*
		 * Let the congestion control algorithm update
		 * congestion control related information. This
		 * typically means increasing the congestion
		 * window.
		 */
		cc_ack_received(tp, th, nsegs, CC_ACK);

		tp->snd_una = th->th_ack;
		tp->t_dupacks = 0;

		/*
		 * 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.
		 */
#ifdef TCPDEBUG
		if (so->so_options & SO_DEBUG)
			tcp_trace(TA_INPUT, ostate, tp,
				  (void *)tcp_saveipgen,
				  &tcp_savetcp, 0);
#endif
		TCP_PROBE3(debug__input, tp, th, m);
		m_freem(m);
		if (tp->snd_una == tp->snd_max)
			tcp_timer_activate(tp, TT_REXMT, 0);
		else if (!tcp_timer_active(tp, TT_PERSIST))
			tcp_timer_activate(tp, TT_REXMT,
					   tp->t_rxtcur);
		/* Wake up the socket if we have room to write more */
		sowwakeup(so);
	} else {
		/* 
		 * Window update only, just free the mbufs and
		 * send out whatever we can.
		 */
		m_freem(m);
	}
	if (sbavail(&so->so_snd))
		(void) tcp_output(tp);
	KASSERT(ti_locked == TI_UNLOCKED, ("%s: check_delack ti_locked %d",
					    __func__, ti_locked));
	INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
	INP_WLOCK_ASSERT(tp->t_inpcb);

	if (tp->t_flags & TF_DELACK) {
		tp->t_flags &= ~TF_DELACK;
		tcp_timer_activate(tp, TT_DELACK, tcp_delacktime);
	}
	INP_WUNLOCK(tp->t_inpcb);
	return (1);
}

/*
 * This tcp-do-segment concentrates on making the fastest
 * ack processing path. It does not have a fast-path for
 * data (it possibly could which would then eliminate the
 * need for fast-slow above). For a content distributor having
 * large outgoing elephants and very very little coming in
 * having no fastpath for data does not really help (since you
 * don't get much data in). The most important thing is 
 * processing ack's quickly and getting the rest of the data
 * output to the peer as quickly as possible. This routine
 * seems to be about an overall 3% faster then the old
 * tcp_do_segment and keeps us in the fast-path for packets
 * much more (by allowing window updates to also stay in the fastpath).
 */
void
tcp_do_segment_fastack(struct mbuf *m, struct tcphdr *th, struct socket *so,
		       struct tcpcb *tp, int drop_hdrlen, int tlen, uint8_t iptos,
		       int ti_locked)
{
	int thflags;
	uint32_t tiwin;
	char *s;
	struct in_conninfo *inc;
	struct tcpopt to;

	thflags = th->th_flags;
	tp->sackhint.last_sack_ack = 0;
	inc = &tp->t_inpcb->inp_inc;
	/*
	 * If this is either a state-changing packet or current state isn't
	 * established, we require a write lock on tcbinfo.  Otherwise, we
	 * allow the tcbinfo to be in either alocked or unlocked, as the
	 * caller may have unnecessarily acquired a write lock due to a race.
	 */
	if ((thflags & (TH_SYN | TH_FIN | TH_RST)) != 0 ||
	    tp->t_state != TCPS_ESTABLISHED) {
		KASSERT(ti_locked == TI_RLOCKED, ("%s ti_locked %d for "
						  "SYN/FIN/RST/!EST", __func__, ti_locked));
		INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
	} else {
#ifdef INVARIANTS
		if (ti_locked == TI_RLOCKED) {
			INP_INFO_RLOCK_ASSERT(&V_tcbinfo);
		} else {
			KASSERT(ti_locked == TI_UNLOCKED, ("%s: EST "
							   "ti_locked: %d", __func__, ti_locked));
			INP_INFO_UNLOCK_ASSERT(&V_tcbinfo);
		}
#endif
	}
	INP_WLOCK_ASSERT(tp->t_inpcb);
	KASSERT(tp->t_state > TCPS_LISTEN, ("%s: TCPS_LISTEN",
					    __func__));
	KASSERT(tp->t_state != TCPS_TIME_WAIT, ("%s: TCPS_TIME_WAIT",
						__func__));

	/*
	 * Segment received on connection.
	 * Reset idle time and keep-alive timer.
	 * XXX: This should be done after segment
	 * validation to ignore broken/spoofed segs.
	 */
	tp->t_rcvtime = ticks;

	/*
	 * Unscale the window into a 32-bit value.
	 * For the SYN_SENT state the scale is zero.
	 */
	tiwin = th->th_win << tp->snd_scale;

	/*
	 * TCP ECN processing.
	 */
	if (tp->t_flags & TF_ECN_PERMIT) {
		if (thflags & TH_CWR)
			tp->t_flags &= ~TF_ECN_SND_ECE;
		switch (iptos & IPTOS_ECN_MASK) {
		case IPTOS_ECN_CE:
			tp->t_flags |= TF_ECN_SND_ECE;
			TCPSTAT_INC(tcps_ecn_ce);
			break;
		case IPTOS_ECN_ECT0:
			TCPSTAT_INC(tcps_ecn_ect0);
			break;
		case IPTOS_ECN_ECT1:
			TCPSTAT_INC(tcps_ecn_ect1);
			break;
		}
		/* Congestion experienced. */
		if (thflags & TH_ECE) {
			cc_cong_signal(tp, th, CC_ECN);
		}
	}

	/*
	 * Parse options on any incoming segment.
	 */
	tcp_dooptions(&to, (u_char *)(th + 1),
		      (th->th_off << 2) - sizeof(struct tcphdr),
		      (thflags & TH_SYN) ? TO_SYN : 0);

	/*
	 * If echoed timestamp is later than the current time,
	 * fall back to non RFC1323 RTT calculation.  Normalize
	 * timestamp if syncookies were used when this connection
	 * was established.
	 */
	if ((to.to_flags & TOF_TS) && (to.to_tsecr != 0)) {
		to.to_tsecr -= tp->ts_offset;
		if (TSTMP_GT(to.to_tsecr, tcp_ts_getticks()))
			to.to_tsecr = 0;
	}
	/*
	 * If timestamps were negotiated during SYN/ACK they should
	 * appear on every segment during this session and vice versa.
	 */
	if ((tp->t_flags & TF_RCVD_TSTMP) && !(to.to_flags & TOF_TS)) {
		if ((s = tcp_log_addrs(inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: Timestamp missing, "
			    "no action\n", s, __func__);
			free(s, M_TCPLOG);
		}
	}
	if (!(tp->t_flags & TF_RCVD_TSTMP) && (to.to_flags & TOF_TS)) {
		if ((s = tcp_log_addrs(inc, th, NULL, NULL))) {
			log(LOG_DEBUG, "%s; %s: Timestamp not expected, "
			    "no action\n", s, __func__);
			free(s, M_TCPLOG);
		}
	}

	/*
	 * Process options only when we get SYN/ACK back. The SYN case
	 * for incoming connections is handled in tcp_syncache.
	 * According to RFC1323 the window field in a SYN (i.e., a <SYN>
	 * or <SYN,ACK>) segment itself is never scaled.
	 * XXX this is traditional behavior, may need to be cleaned up.
	 */
	if (tp->t_state == TCPS_SYN_SENT && (thflags & TH_SYN)) {
		if ((to.to_flags & TOF_SCALE) &&
		    (tp->t_flags & TF_REQ_SCALE)) {
			tp->t_flags |= TF_RCVD_SCALE;
			tp->snd_scale = to.to_wscale;
		}
		/*
		 * Initial send window.  It will be updated with
		 * the next incoming segment to the scaled value.
		 */
		tp->snd_wnd = th->th_win;
		if (to.to_flags & TOF_TS) {
			tp->t_flags |= TF_RCVD_TSTMP;
			tp->ts_recent = to.to_tsval;
			tp->ts_recent_age = tcp_ts_getticks();
		}
		if (to.to_flags & TOF_MSS)
			tcp_mss(tp, to.to_mss);
		if ((tp->t_flags & TF_SACK_PERMIT) &&
		    (to.to_flags & TOF_SACKPERM) == 0)
			tp->t_flags &= ~TF_SACK_PERMIT;
	}
	/*
	 * 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.
	 * Make sure that the hidden state-flags are also off.
	 * Since we check for TCPS_ESTABLISHED first, it can only
	 * be TH_NEEDSYN.
	 */
	if (__predict_true(tp->t_state == TCPS_ESTABLISHED) &&
	    __predict_true(((to.to_flags & TOF_SACK) == 0)) &&
	    __predict_true(tlen == 0) &&
	    __predict_true((thflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK) &&
	    __predict_true(LIST_EMPTY(&tp->t_segq)) &&
	    __predict_true(th->th_seq == tp->rcv_nxt)) {
		    if (tcp_fastack(m, th, so, tp, &to, drop_hdrlen, tlen, 
				    ti_locked, tiwin)) {
			    return;
		    }
	} 
	tcp_do_slowpath(m, th, so, tp, &to, drop_hdrlen, tlen,
			ti_locked, tiwin, thflags);
}

struct tcp_function_block __tcp_fastslow = {
	.tfb_tcp_block_name = "fastslow",
	.tfb_tcp_output = tcp_output,
	.tfb_tcp_do_segment = tcp_do_segment_fastslow,
	.tfb_tcp_ctloutput = tcp_default_ctloutput,
};

struct tcp_function_block __tcp_fastack = {
	.tfb_tcp_block_name = "fastack",
	.tfb_tcp_output = tcp_output,
	.tfb_tcp_do_segment = tcp_do_segment_fastack,
	.tfb_tcp_ctloutput = tcp_default_ctloutput
};

static int
tcp_addfastpaths(module_t mod, int type, void *data)
{
	int err=0;

	switch (type) {
	case MOD_LOAD:
		err = register_tcp_functions(&__tcp_fastack, M_WAITOK);
		if (err) {
			printf("Failed to register fastack module -- err:%d\n", err);
			return(err);
		}
		err = register_tcp_functions(&__tcp_fastslow, M_WAITOK); 
		if (err) {
			printf("Failed to register fastslow module -- err:%d\n", err);
			deregister_tcp_functions(&__tcp_fastack);
			return(err);
		}
		break;
	case MOD_QUIESCE:
		if ((__tcp_fastslow.tfb_refcnt) ||( __tcp_fastack.tfb_refcnt)) {
			return(EBUSY);
		}
		break;
	case MOD_UNLOAD:
		err = deregister_tcp_functions(&__tcp_fastack);
		if (err == EBUSY)
			break;
		err = deregister_tcp_functions(&__tcp_fastslow);
		if (err == EBUSY)
			break;
		err = 0;
		break;
	default:
		return (EOPNOTSUPP);
	}
	return (err);
}

static moduledata_t new_tcp_fastpaths = {
	.name = "tcp_fastpaths",
	.evhand = tcp_addfastpaths,
	.priv = 0
};

MODULE_VERSION(kern_tcpfastpaths, 1);
DECLARE_MODULE(kern_tcpfastpaths, new_tcp_fastpaths, SI_SUB_PROTO_DOMAIN, SI_ORDER_ANY);