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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the TCP module.
*
* Version: @(#)tcp.h 1.0.5 05/23/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*/
#ifndef _TCP_H
#define _TCP_H
#define FASTRETRANS_DEBUG 1
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/bug.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
#include <linux/skbuff.h>
#include <linux/kref.h>
#include <linux/ktime.h>
#include <linux/indirect_call_wrapper.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock_reuseport.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <net/inet_ecn.h>
#include <net/dst.h>
#include <net/mptcp.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
#include <linux/bpf-cgroup.h>
#include <linux/siphash.h>
extern struct inet_hashinfo tcp_hashinfo;
DECLARE_PER_CPU(unsigned int, tcp_orphan_count);
int tcp_orphan_count_sum(void);
void tcp_time_wait(struct sock *sk, int state, int timeo);
#define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER)
#define MAX_TCP_OPTION_SPACE 40
#define TCP_MIN_SND_MSS 48
#define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
/*
* Never offer a window over 32767 without using window scaling. Some
* poor stacks do signed 16bit maths!
*/
#define MAX_TCP_WINDOW 32767U
/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS 88U
/* The initial MTU to use for probing */
#define TCP_BASE_MSS 1024
/* probing interval, default to 10 minutes as per RFC4821 */
#define TCP_PROBE_INTERVAL 600
/* Specify interval when tcp mtu probing will stop */
#define TCP_PROBE_THRESHOLD 8
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3
/* Maximal number of ACKs sent quickly to accelerate slow-start. */
#define TCP_MAX_QUICKACKS 16U
/* Maximal number of window scale according to RFC1323 */
#define TCP_MAX_WSCALE 14U
/* urg_data states */
#define TCP_URG_VALID 0x0100
#define TCP_URG_NOTYET 0x0200
#define TCP_URG_READ 0x0400
#define TCP_RETR1 3 /*
* This is how many retries it does before it
* tries to figure out if the gateway is
* down. Minimal RFC value is 3; it corresponds
* to ~3sec-8min depending on RTO.
*/
#define TCP_RETR2 15 /*
* This should take at least
* 90 minutes to time out.
* RFC1122 says that the limit is 100 sec.
* 15 is ~13-30min depending on RTO.
*/
#define TCP_SYN_RETRIES 6 /* This is how many retries are done
* when active opening a connection.
* RFC1122 says the minimum retry MUST
* be at least 180secs. Nevertheless
* this value is corresponding to
* 63secs of retransmission with the
* current initial RTO.
*/
#define TCP_SYNACK_RETRIES 5 /* This is how may retries are done
* when passive opening a connection.
* This is corresponding to 31secs of
* retransmission with the current
* initial RTO.
*/
#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
* state, about 60 seconds */
#define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN
/* BSD style FIN_WAIT2 deadlock breaker.
* It used to be 3min, new value is 60sec,
* to combine FIN-WAIT-2 timeout with
* TIME-WAIT timer.
*/
#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */
#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
#if HZ >= 100
#define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */
#define TCP_ATO_MIN ((unsigned)(HZ/25))
#else
#define TCP_DELACK_MIN 4U
#define TCP_ATO_MIN 4U
#endif
#define TCP_RTO_MAX ((unsigned)(120*HZ))
#define TCP_RTO_MIN ((unsigned)(HZ/5))
#define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */
#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now
* used as a fallback RTO for the
* initial data transmission if no
* valid RTT sample has been acquired,
* most likely due to retrans in 3WHS.
*/
#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
* for local resources.
*/
#define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */
#define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */
#define TCP_KEEPALIVE_INTVL (75*HZ)
#define MAX_TCP_KEEPIDLE 32767
#define MAX_TCP_KEEPINTVL 32767
#define MAX_TCP_KEEPCNT 127
#define MAX_TCP_SYNCNT 127
#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */
#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
#define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated
* after this time. It should be equal
* (or greater than) TCP_TIMEWAIT_LEN
* to provide reliability equal to one
* provided by timewait state.
*/
#define TCP_PAWS_WINDOW 1 /* Replay window for per-host
* timestamps. It must be less than
* minimal timewait lifetime.
*/
/*
* TCP option
*/
#define TCPOPT_NOP 1 /* Padding */
#define TCPOPT_EOL 0 /* End of options */
#define TCPOPT_MSS 2 /* Segment size negotiating */
#define TCPOPT_WINDOW 3 /* Window scaling */
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
#define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */
#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
* experimental options. See draft-ietf-tcpm-experimental-options-00.txt
*/
#define TCPOPT_FASTOPEN_MAGIC 0xF989
#define TCPOPT_SMC_MAGIC 0xE2D4C3D9
/*
* TCP option lengths
*/
#define TCPOLEN_MSS 4
#define TCPOLEN_WINDOW 3
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
#define TCPOLEN_FASTOPEN_BASE 2
#define TCPOLEN_EXP_FASTOPEN_BASE 4
#define TCPOLEN_EXP_SMC_BASE 6
/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED 12
#define TCPOLEN_WSCALE_ALIGNED 4
#define TCPOLEN_SACKPERM_ALIGNED 4
#define TCPOLEN_SACK_BASE 2
#define TCPOLEN_SACK_BASE_ALIGNED 4
#define TCPOLEN_SACK_PERBLOCK 8
#define TCPOLEN_MD5SIG_ALIGNED 20
#define TCPOLEN_MSS_ALIGNED 4
#define TCPOLEN_EXP_SMC_BASE_ALIGNED 8
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
/* TCP thin-stream limits */
#define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */
/* TCP initial congestion window as per rfc6928 */
#define TCP_INIT_CWND 10
/* Bit Flags for sysctl_tcp_fastopen */
#define TFO_CLIENT_ENABLE 1
#define TFO_SERVER_ENABLE 2
#define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */
/* Accept SYN data w/o any cookie option */
#define TFO_SERVER_COOKIE_NOT_REQD 0x200
/* Force enable TFO on all listeners, i.e., not requiring the
* TCP_FASTOPEN socket option.
*/
#define TFO_SERVER_WO_SOCKOPT1 0x400
/* sysctl variables for tcp */
extern int sysctl_tcp_max_orphans;
extern long sysctl_tcp_mem[3];
#define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */
#define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */
#define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */
extern atomic_long_t tcp_memory_allocated;
DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc);
extern struct percpu_counter tcp_sockets_allocated;
extern unsigned long tcp_memory_pressure;
/* optimized version of sk_under_memory_pressure() for TCP sockets */
static inline bool tcp_under_memory_pressure(const struct sock *sk)
{
if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
mem_cgroup_under_socket_pressure(sk->sk_memcg))
return true;
return READ_ONCE(tcp_memory_pressure);
}
/*
* The next routines deal with comparing 32 bit unsigned ints
* and worry about wraparound (automatic with unsigned arithmetic).
*/
static inline bool before(__u32 seq1, __u32 seq2)
{
return (__s32)(seq1-seq2) < 0;
}
#define after(seq2, seq1) before(seq1, seq2)
/* is s2<=s1<=s3 ? */
static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3)
{
return seq3 - seq2 >= seq1 - seq2;
}
static inline bool tcp_out_of_memory(struct sock *sk)
{
if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
return true;
return false;
}
static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
sk_wmem_queued_add(sk, -skb->truesize);
if (!skb_zcopy_pure(skb))
sk_mem_uncharge(sk, skb->truesize);
else
sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb)));
__kfree_skb(skb);
}
void sk_forced_mem_schedule(struct sock *sk, int size);
bool tcp_check_oom(struct sock *sk, int shift);
extern struct proto tcp_prot;
#define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field)
#define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field)
#define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
#define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
void tcp_tasklet_init(void);
int tcp_v4_err(struct sk_buff *skb, u32);
void tcp_shutdown(struct sock *sk, int how);
int tcp_v4_early_demux(struct sk_buff *skb);
int tcp_v4_rcv(struct sk_buff *skb);
void tcp_remove_empty_skb(struct sock *sk);
int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
int flags);
int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
int size_goal);
void tcp_release_cb(struct sock *sk);
void tcp_wfree(struct sk_buff *skb);
void tcp_write_timer_handler(struct sock *sk);
void tcp_delack_timer_handler(struct sock *sk);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
void tcp_rcv_space_adjust(struct sock *sk);
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
void tcp_twsk_destructor(struct sock *sk);
ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
bool force_schedule);
void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
static inline void tcp_dec_quickack_mode(struct sock *sk,
const unsigned int pkts)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ack.quick) {
if (pkts >= icsk->icsk_ack.quick) {
icsk->icsk_ack.quick = 0;
/* Leaving quickack mode we deflate ATO. */
icsk->icsk_ack.ato = TCP_ATO_MIN;
} else
icsk->icsk_ack.quick -= pkts;
}
}
#define TCP_ECN_OK 1
#define TCP_ECN_QUEUE_CWR 2
#define TCP_ECN_DEMAND_CWR 4
#define TCP_ECN_SEEN 8
enum tcp_tw_status {
TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1,
TCP_TW_ACK = 2,
TCP_TW_SYN = 3
};
enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
struct sk_buff *skb,
const struct tcphdr *th);
struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req, bool fastopen,
bool *lost_race);
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb);
void tcp_enter_loss(struct sock *sk);
void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag);
void tcp_clear_retrans(struct tcp_sock *tp);
void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void __tcp_close(struct sock *sk, long timeout);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
__poll_t tcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
bool tcp_bpf_bypass_getsockopt(int level, int optname);
int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
void tcp_set_keepalive(struct sock *sk, int val);
void tcp_syn_ack_timeout(const struct request_sock *req);
int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len);
int tcp_set_rcvlowat(struct sock *sk, int val);
int tcp_set_window_clamp(struct sock *sk, int val);
void tcp_update_recv_tstamps(struct sk_buff *skb,
struct scm_timestamping_internal *tss);
void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
struct scm_timestamping_internal *tss);
void tcp_data_ready(struct sock *sk);
#ifdef CONFIG_MMU
int tcp_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma);
#endif
void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
struct tcp_options_received *opt_rx,
int estab, struct tcp_fastopen_cookie *foc);
const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
/*
* BPF SKB-less helpers
*/
u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
struct tcphdr *th, u32 *cookie);
u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
struct tcphdr *th, u32 *cookie);
u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss);
u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct tcphdr *th);
/*
* TCP v4 functions exported for the inet6 API
*/
void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
void tcp_v4_mtu_reduced(struct sock *sk);
void tcp_req_err(struct sock *sk, u32 seq, bool abort);
void tcp_ld_RTO_revert(struct sock *sk, u32 seq);
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_create_openreq_child(const struct sock *sk,
struct request_sock *req,
struct sk_buff *skb);
void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst);
struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req);
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int tcp_connect(struct sock *sk);
enum tcp_synack_type {
TCP_SYNACK_NORMAL,
TCP_SYNACK_FASTOPEN,
TCP_SYNACK_COOKIE,
};
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb);
int tcp_disconnect(struct sock *sk, int flags);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size);
void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
/* From syncookies.c */
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst, u32 tsoff);
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct sk_buff *skb);
#ifdef CONFIG_SYN_COOKIES
/* Syncookies use a monotonic timer which increments every 60 seconds.
* This counter is used both as a hash input and partially encoded into
* the cookie value. A cookie is only validated further if the delta
* between the current counter value and the encoded one is less than this,
* i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
* the counter advances immediately after a cookie is generated).
*/
#define MAX_SYNCOOKIE_AGE 2
#define TCP_SYNCOOKIE_PERIOD (60 * HZ)
#define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD)
/* syncookies: remember time of last synqueue overflow
* But do not dirty this field too often (once per second is enough)
* It is racy as we do not hold a lock, but race is very minor.
*/
static inline void tcp_synq_overflow(const struct sock *sk)
{
unsigned int last_overflow;
unsigned int now = jiffies;
if (sk->sk_reuseport) {
struct sock_reuseport *reuse;
reuse = rcu_dereference(sk->sk_reuseport_cb);
if (likely(reuse)) {
last_overflow = READ_ONCE(reuse->synq_overflow_ts);
if (!time_between32(now, last_overflow,
last_overflow + HZ))
WRITE_ONCE(reuse->synq_overflow_ts, now);
return;
}
}
last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
if (!time_between32(now, last_overflow, last_overflow + HZ))
WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now);
}
/* syncookies: no recent synqueue overflow on this listening socket? */
static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
{
unsigned int last_overflow;
unsigned int now = jiffies;
if (sk->sk_reuseport) {
struct sock_reuseport *reuse;
reuse = rcu_dereference(sk->sk_reuseport_cb);
if (likely(reuse)) {
last_overflow = READ_ONCE(reuse->synq_overflow_ts);
return !time_between32(now, last_overflow - HZ,
last_overflow +
TCP_SYNCOOKIE_VALID);
}
}
last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
* then we're under synflood. However, we have to use
* 'last_overflow - HZ' as lower bound. That's because a concurrent
* tcp_synq_overflow() could update .ts_recent_stamp after we read
* jiffies but before we store .ts_recent_stamp into last_overflow,
* which could lead to rejecting a valid syncookie.
*/
return !time_between32(now, last_overflow - HZ,
last_overflow + TCP_SYNCOOKIE_VALID);
}
static inline u32 tcp_cookie_time(void)
{
u64 val = get_jiffies_64();
do_div(val, TCP_SYNCOOKIE_PERIOD);
return val;
}
u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
u16 *mssp);
__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
u64 cookie_init_timestamp(struct request_sock *req, u64 now);
bool cookie_timestamp_decode(const struct net *net,
struct tcp_options_received *opt);
bool cookie_ecn_ok(const struct tcp_options_received *opt,
const struct net *net, const struct dst_entry *dst);
/* From net/ipv6/syncookies.c */
int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
u32 cookie);
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
const struct tcphdr *th, u16 *mssp);
__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
#endif
/* tcp_output.c */
void tcp_skb_entail(struct sock *sk, struct sk_buff *skb);
void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb);
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle);
int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
void tcp_retransmit_timer(struct sock *sk);
void tcp_xmit_retransmit_queue(struct sock *);
void tcp_simple_retransmit(struct sock *);
void tcp_enter_recovery(struct sock *sk, bool ece_ack);
int tcp_trim_head(struct sock *, struct sk_buff *, u32);
enum tcp_queue {
TCP_FRAG_IN_WRITE_QUEUE,
TCP_FRAG_IN_RTX_QUEUE,
};
int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
struct sk_buff *skb, u32 len,
unsigned int mss_now, gfp_t gfp);
void tcp_send_probe0(struct sock *);
void tcp_send_partial(struct sock *);
int tcp_write_wakeup(struct sock *, int mib);
void tcp_send_fin(struct sock *sk);
void tcp_send_active_reset(struct sock *sk, gfp_t priority);
int tcp_send_synack(struct sock *);
void tcp_push_one(struct sock *, unsigned int mss_now);
void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
void tcp_send_ack(struct sock *sk);
void tcp_send_delayed_ack(struct sock *sk);
void tcp_send_loss_probe(struct sock *sk);
bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto);
void tcp_skb_collapse_tstamp(struct sk_buff *skb,
const struct sk_buff *next_skb);
/* tcp_input.c */
void tcp_rearm_rto(struct sock *sk);
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
void tcp_reset(struct sock *sk, struct sk_buff *skb);
void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
void tcp_fin(struct sock *sk);
void tcp_check_space(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
static inline void tcp_clear_xmit_timers(struct sock *sk)
{
if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1)
__sock_put(sk);
if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1)
__sock_put(sk);
inet_csk_clear_xmit_timers(sk);
}
unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
unsigned int tcp_current_mss(struct sock *sk);
u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when);
/* Bound MSS / TSO packet size with the half of the window */
static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
{
int cutoff;
/* When peer uses tiny windows, there is no use in packetizing
* to sub-MSS pieces for the sake of SWS or making sure there
* are enough packets in the pipe for fast recovery.
*
* On the other hand, for extremely large MSS devices, handling
* smaller than MSS windows in this way does make sense.
*/
if (tp->max_window > TCP_MSS_DEFAULT)
cutoff = (tp->max_window >> 1);
else
cutoff = tp->max_window;
if (cutoff && pktsize > cutoff)
return max_t(int, cutoff, 68U - tp->tcp_header_len);
else
return pktsize;
}
/* tcp.c */
void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
void tcp_initialize_rcv_mss(struct sock *sk);
int tcp_mtu_to_mss(struct sock *sk, int pmtu);
int tcp_mss_to_mtu(struct sock *sk, int mss);
void tcp_mtup_init(struct sock *sk);
static inline void tcp_bound_rto(const struct sock *sk)
{
if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}
static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
{
return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
}
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
/* mptcp hooks are only on the slow path */
if (sk_is_mptcp((struct sock *)tp))
return;
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
}
static inline void tcp_fast_path_on(struct tcp_sock *tp)
{
__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
}
static inline void tcp_fast_path_check(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (RB_EMPTY_ROOT(&tp->out_of_order_queue) &&
tp->rcv_wnd &&
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
!tp->urg_data)
tcp_fast_path_on(tp);
}
/* Compute the actual rto_min value */
static inline u32 tcp_rto_min(struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
u32 rto_min = inet_csk(sk)->icsk_rto_min;
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
return rto_min;
}
static inline u32 tcp_rto_min_us(struct sock *sk)
{
return jiffies_to_usecs(tcp_rto_min(sk));
}
static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
{
return dst_metric_locked(dst, RTAX_CC_ALGO);
}
/* Minimum RTT in usec. ~0 means not available. */
static inline u32 tcp_min_rtt(const struct tcp_sock *tp)
{
return minmax_get(&tp->rtt_min);
}
/* Compute the actual receive window we are currently advertising.
* Rcv_nxt can be after the window if our peer push more data
* than the offered window.
*/
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
{
s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;
if (win < 0)
win = 0;
return (u32) win;
}
/* Choose a new window, without checks for shrinking, and without
* scaling applied to the result. The caller does these things
* if necessary. This is a "raw" window selection.
*/
u32 __tcp_select_window(struct sock *sk);
void tcp_send_window_probe(struct sock *sk);
/* TCP uses 32bit jiffies to save some space.
* Note that this is different from tcp_time_stamp, which
* historically has been the same until linux-4.13.
*/
#define tcp_jiffies32 ((u32)jiffies)
/*
* Deliver a 32bit value for TCP timestamp option (RFC 7323)
* It is no longer tied to jiffies, but to 1 ms clock.
* Note: double check if you want to use tcp_jiffies32 instead of this.
*/
#define TCP_TS_HZ 1000
static inline u64 tcp_clock_ns(void)
{
return ktime_get_ns();
}
static inline u64 tcp_clock_us(void)
{
return div_u64(tcp_clock_ns(), NSEC_PER_USEC);
}
/* This should only be used in contexts where tp->tcp_mstamp is up to date */
static inline u32 tcp_time_stamp(const struct tcp_sock *tp)
{
return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ);
}
/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */
static inline u32 tcp_ns_to_ts(u64 ns)
{
return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ);
}
/* Could use tcp_clock_us() / 1000, but this version uses a single divide */
static inline u32 tcp_time_stamp_raw(void)
{
return tcp_ns_to_ts(tcp_clock_ns());
}
void tcp_mstamp_refresh(struct tcp_sock *tp);
static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0)
{
return max_t(s64, t1 - t0, 0);
}
static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
{
return tcp_ns_to_ts(skb->skb_mstamp_ns);
}
/* provide the departure time in us unit */
static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb)
{
return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC);
}
#define tcp_flag_byte(th) (((u_int8_t *)th)[13])
#define TCPHDR_FIN 0x01
#define TCPHDR_SYN 0x02
#define TCPHDR_RST 0x04
#define TCPHDR_PSH 0x08
#define TCPHDR_ACK 0x10
#define TCPHDR_URG 0x20
#define TCPHDR_ECE 0x40
#define TCPHDR_CWR 0x80
#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
/* This is what the send packet queuing engine uses to pass
* TCP per-packet control information to the transmission code.
* We also store the host-order sequence numbers in here too.
* This is 44 bytes if IPV6 is enabled.
* If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.
*/
struct tcp_skb_cb {
__u32 seq; /* Starting sequence number */
__u32 end_seq; /* SEQ + FIN + SYN + datalen */
union {
/* Note : tcp_tw_isn is used in input path only
* (isn chosen by tcp_timewait_state_process())
*
* tcp_gso_segs/size are used in write queue only,
* cf tcp_skb_pcount()/tcp_skb_mss()
*/
__u32 tcp_tw_isn;
struct {
u16 tcp_gso_segs;
u16 tcp_gso_size;
};
};
__u8 tcp_flags; /* TCP header flags. (tcp[13]) */
__u8 sacked; /* State flags for SACK. */
#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */
#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */
#define TCPCB_LOST 0x04 /* SKB is lost */
#define TCPCB_TAGBITS 0x07 /* All tag bits */
#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */
#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */
#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
TCPCB_REPAIRED)
__u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
__u8 txstamp_ack:1, /* Record TX timestamp for ack? */
eor:1, /* Is skb MSG_EOR marked? */
has_rxtstamp:1, /* SKB has a RX timestamp */
unused:5;
__u32 ack_seq; /* Sequence number ACK'd */
union {
struct {
#define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1)
/* There is space for up to 24 bytes */
__u32 is_app_limited:1, /* cwnd not fully used? */
delivered_ce:20,
unused:11;
/* pkts S/ACKed so far upon tx of skb, incl retrans: */
__u32 delivered;
/* start of send pipeline phase */
u64 first_tx_mstamp;
/* when we reached the "delivered" count */
u64 delivered_mstamp;
} tx; /* only used for outgoing skbs */
union {
struct inet_skb_parm h4;
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header; /* For incoming skbs */
};
};
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
extern const struct inet_connection_sock_af_ops ipv4_specific;
#if IS_ENABLED(CONFIG_IPV6)
/* This is the variant of inet6_iif() that must be used by TCP,
* as TCP moves IP6CB into a different location in skb->cb[]
*/
static inline int tcp_v6_iif(const struct sk_buff *skb)
{
return TCP_SKB_CB(skb)->header.h6.iif;
}
static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
{
bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
}
/* TCP_SKB_CB reference means this can not be used from early demux */
static inline int tcp_v6_sdif(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags))
return TCP_SKB_CB(skb)->header.h6.iif;
#endif
return 0;
}
extern const struct inet_connection_sock_af_ops ipv6_specific;
INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb));
INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb));
INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb));
#endif
/* TCP_SKB_CB reference means this can not be used from early demux */
static inline int tcp_v4_sdif(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
return TCP_SKB_CB(skb)->header.h4.iif;
#endif
return 0;
}
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
static inline int tcp_skb_pcount(const struct sk_buff *skb)
{
return TCP_SKB_CB(skb)->tcp_gso_segs;
}
static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs)
{
TCP_SKB_CB(skb)->tcp_gso_segs = segs;
}
static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs)
{
TCP_SKB_CB(skb)->tcp_gso_segs += segs;
}
/* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
return TCP_SKB_CB(skb)->tcp_gso_size;
}
static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
{
return likely(!TCP_SKB_CB(skb)->eor);
}
static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
const struct sk_buff *from)
{
return likely(tcp_skb_can_collapse_to(to) &&
mptcp_skb_can_collapse(to, from) &&
skb_pure_zcopy_same(to, from));
}
/* Events passed to congestion control interface */
enum tcp_ca_event {
CA_EVENT_TX_START, /* first transmit when no packets in flight */
CA_EVENT_CWND_RESTART, /* congestion window restart */
CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
};
/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
enum tcp_ca_ack_event_flags {
CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */
CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */
CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */
};
/*
* Interface for adding new TCP congestion control handlers
*/
#define TCP_CA_NAME_MAX 16
#define TCP_CA_MAX 128
#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
#define TCP_CA_UNSPEC 0
/* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
#define TCP_CONG_NON_RESTRICTED 0x1
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN 0x2
#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
union tcp_cc_info;
struct ack_sample {
u32 pkts_acked;
s32 rtt_us;
u32 in_flight;
};
/* A rate sample measures the number of (original/retransmitted) data
* packets delivered "delivered" over an interval of time "interval_us".
* The tcp_rate.c code fills in the rate sample, and congestion
* control modules that define a cong_control function to run at the end
* of ACK processing can optionally chose to consult this sample when
* setting cwnd and pacing rate.
* A sample is invalid if "delivered" or "interval_us" is negative.
*/
struct rate_sample {
u64 prior_mstamp; /* starting timestamp for interval */
u32 prior_delivered; /* tp->delivered at "prior_mstamp" */
u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */
s32 delivered; /* number of packets delivered over interval */
s32 delivered_ce; /* number of packets delivered w/ CE marks*/
long interval_us; /* time for tp->delivered to incr "delivered" */
u32 snd_interval_us; /* snd interval for delivered packets */
u32 rcv_interval_us; /* rcv interval for delivered packets */
long rtt_us; /* RTT of last (S)ACKed packet (or -1) */
int losses; /* number of packets marked lost upon ACK */
u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
u32 prior_in_flight; /* in flight before this ACK */
u32 last_end_seq; /* end_seq of most recently ACKed packet */
bool is_app_limited; /* is sample from packet with bubble in pipe? */
bool is_retrans; /* is sample from retransmission? */
bool is_ack_delayed; /* is this (likely) a delayed ACK? */
};
struct tcp_congestion_ops {
/* fast path fields are put first to fill one cache line */
/* return slow start threshold (required) */
u32 (*ssthresh)(struct sock *sk);
/* do new cwnd calculation (required) */
void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked);
/* call before changing ca_state (optional) */
void (*set_state)(struct sock *sk, u8 new_state);
/* call when cwnd event occurs (optional) */
void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
/* call when ack arrives (optional) */
void (*in_ack_event)(struct sock *sk, u32 flags);
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
/* override sysctl_tcp_min_tso_segs */
u32 (*min_tso_segs)(struct sock *sk);
/* call when packets are delivered to update cwnd and pacing rate,
* after all the ca_state processing. (optional)
*/
void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
/* new value of cwnd after loss (required) */
u32 (*undo_cwnd)(struct sock *sk);
/* returns the multiplier used in tcp_sndbuf_expand (optional) */
u32 (*sndbuf_expand)(struct sock *sk);
/* control/slow paths put last */
/* get info for inet_diag (optional) */
size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info);
char name[TCP_CA_NAME_MAX];
struct module *owner;
struct list_head list;
u32 key;
u32 flags;
/* initialize private data (optional) */
void (*init)(struct sock *sk);
/* cleanup private data (optional) */
void (*release)(struct sock *sk);
} ____cacheline_aligned_in_smp;
int tcp_register_congestion_control(struct tcp_congestion_ops *type);
void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
void tcp_assign_congestion_control(struct sock *sk);
void tcp_init_congestion_control(struct sock *sk);
void tcp_cleanup_congestion_control(struct sock *sk);
int tcp_set_default_congestion_control(struct net *net, const char *name);
void tcp_get_default_congestion_control(struct net *net, char *name);
void tcp_get_available_congestion_control(char *buf, size_t len);
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
bool cap_net_admin);
u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
u32 tcp_reno_ssthresh(struct sock *sk);
u32 tcp_reno_undo_cwnd(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
struct tcp_congestion_ops *tcp_ca_find(const char *name);
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
char *tcp_ca_get_name_by_key(u32 key, char *buffer);
#else
static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer)
{
return NULL;
}
#endif
static inline bool tcp_ca_needs_ecn(const struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
}
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->cwnd_event)
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
/* From tcp_cong.c */
void tcp_set_ca_state(struct sock *sk, const u8 ca_state);
/* From tcp_rate.c */
void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs);
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
bool is_sack_reneg, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);
static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
{
return t1 > t2 || (t1 == t2 && after(seq1, seq2));
}
/* These functions determine how the current flow behaves in respect of SACK
* handling. SACK is negotiated with the peer, and therefore it can vary
* between different flows.
*
* tcp_is_sack - SACK enabled
* tcp_is_reno - No SACK
*/
static inline int tcp_is_sack(const struct tcp_sock *tp)
{
return likely(tp->rx_opt.sack_ok);
}
static inline bool tcp_is_reno(const struct tcp_sock *tp)
{
return !tcp_is_sack(tp);
}
static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
return tp->sacked_out + tp->lost_out;
}
/* This determines how many packets are "in the network" to the best
* of our knowledge. In many cases it is conservative, but where
* detailed information is available from the receiver (via SACK
* blocks etc.) we can make more aggressive calculations.
*
* Use this for decisions involving congestion control, use just
* tp->packets_out to determine if the send queue is empty or not.
*
* Read this equation as:
*
* "Packets sent once on transmission queue" MINUS
* "Packets left network, but not honestly ACKed yet" PLUS
* "Packets fast retransmitted"
*/
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
{
return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
}
#define TCP_INFINITE_SSTHRESH 0x7fffffff
static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp)
{
return tp->snd_cwnd;
}
static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val)
{
WARN_ON_ONCE((int)val <= 0);
tp->snd_cwnd = val;
}
static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
{
return tcp_snd_cwnd(tp) < tp->snd_ssthresh;
}
static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
{
return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
}
static inline bool tcp_in_cwnd_reduction(const struct sock *sk)
{
return (TCPF_CA_CWR | TCPF_CA_Recovery) &
(1 << inet_csk(sk)->icsk_ca_state);
}
/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
* The exception is cwnd reduction phase, when cwnd is decreasing towards
* ssthresh.
*/
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
if (tcp_in_cwnd_reduction(sk))
return tp->snd_ssthresh;
else
return max(tp->snd_ssthresh,
((tcp_snd_cwnd(tp) >> 1) +
(tcp_snd_cwnd(tp) >> 2)));
}
/* Use define here intentionally to get WARN_ON location shown at the caller */
#define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out)
void tcp_enter_cwr(struct sock *sk);
__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);
/* The maximum number of MSS of available cwnd for which TSO defers
* sending if not using sysctl_tcp_tso_win_divisor.
*/
static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp)
{
return 3;
}
/* Returns end sequence number of the receiver's advertised window */
static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
{
return tp->snd_una + tp->snd_wnd;
}
/* We follow the spirit of RFC2861 to validate cwnd but implement a more
* flexible approach. The RFC suggests cwnd should not be raised unless
* it was fully used previously. And that's exactly what we do in
* congestion avoidance mode. But in slow start we allow cwnd to grow
* as long as the application has used half the cwnd.
* Example :
* cwnd is 10 (IW10), but application sends 9 frames.
* We allow cwnd to reach 18 when all frames are ACKed.
* This check is safe because it's as aggressive as slow start which already
* risks 100% overshoot. The advantage is that we discourage application to
* either send more filler packets or data to artificially blow up the cwnd
* usage, and allow application-limited process to probe bw more aggressively.
*/
static inline bool tcp_is_cwnd_limited(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
/* If in slow start, ensure cwnd grows to twice what was ACKed. */
if (tcp_in_slow_start(tp))
return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out;
return tp->is_cwnd_limited;
}
/* BBR congestion control needs pacing.
* Same remark for SO_MAX_PACING_RATE.
* sch_fq packet scheduler is efficiently handling pacing,
* but is not always installed/used.
* Return true if TCP stack should pace packets itself.
*/
static inline bool tcp_needs_internal_pacing(const struct sock *sk)
{
return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
}
/* Estimates in how many jiffies next packet for this flow can be sent.
* Scheduling a retransmit timer too early would be silly.
*/
static inline unsigned long tcp_pacing_delay(const struct sock *sk)
{
s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache;
return delay > 0 ? nsecs_to_jiffies(delay) : 0;
}
static inline void tcp_reset_xmit_timer(struct sock *sk,
const int what,
unsigned long when,
const unsigned long max_when)
{
inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk),
max_when);
}
/* Something is really bad, we could not queue an additional packet,
* because qdisc is full or receiver sent a 0 window, or we are paced.
* We do not want to add fuel to the fire, or abort too early,
* so make sure the timer we arm now is at least 200ms in the future,
* regardless of current icsk_rto value (as it could be ~2ms)
*/
static inline unsigned long tcp_probe0_base(const struct sock *sk)
{
return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN);
}
/* Variant of inet_csk_rto_backoff() used for zero window probes */
static inline unsigned long tcp_probe0_when(const struct sock *sk,
unsigned long max_when)
{
u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1,
inet_csk(sk)->icsk_backoff);
u64 when = (u64)tcp_probe0_base(sk) << backoff;
return (unsigned long)min_t(u64, when, max_when);
}
static inline void tcp_check_probe_timer(struct sock *sk)
{
if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
tcp_probe0_base(sk), TCP_RTO_MAX);
}
static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
/*
* Calculate(/check) TCP checksum
*/
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
__be32 daddr, __wsum base)
{
return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base);
}
static inline bool tcp_checksum_complete(struct sk_buff *skb)
{
return !skb_csum_unnecessary(skb) &&
__skb_checksum_complete(skb);
}
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
enum skb_drop_reason *reason);
int tcp_filter(struct sock *sk, struct sk_buff *skb);
void tcp_set_state(struct sock *sk, int state);
void tcp_done(struct sock *sk);
int tcp_abort(struct sock *sk, int err);
static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
rx_opt->dsack = 0;
rx_opt->num_sacks = 0;
}
void tcp_cwnd_restart(struct sock *sk, s32 delta);
static inline void tcp_slow_start_after_idle_check(struct sock *sk)
{
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
s32 delta;
if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out ||
ca_ops->cong_control)
return;
delta = tcp_jiffies32 - tp->lsndtime;
if (delta > inet_csk(sk)->icsk_rto)
tcp_cwnd_restart(sk, delta);
}
/* Determine a window scaling and initial window to offer. */
void tcp_select_initial_window(const struct sock *sk, int __space,
__u32 mss, __u32 *rcv_wnd,
__u32 *window_clamp, int wscale_ok,
__u8 *rcv_wscale, __u32 init_rcv_wnd);
static inline int tcp_win_from_space(const struct sock *sk, int space)
{
int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
return tcp_adv_win_scale <= 0 ?
(space>>(-tcp_adv_win_scale)) :
space - (space>>tcp_adv_win_scale);
}
/* Note: caller must be prepared to deal with negative returns */
static inline int tcp_space(const struct sock *sk)
{
return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
READ_ONCE(sk->sk_backlog.len) -
atomic_read(&sk->sk_rmem_alloc));
}
static inline int tcp_full_space(const struct sock *sk)
{
return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
}
static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
{
int unused_mem = sk_unused_reserved_mem(sk);
struct tcp_sock *tp = tcp_sk(sk);
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
if (unused_mem)
tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
tcp_win_from_space(sk, unused_mem));
}
void tcp_cleanup_rbuf(struct sock *sk, int copied);
/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
* If 87.5 % (7/8) of the space has been consumed, we want to override
* SO_RCVLOWAT constraint, since we are receiving skbs with too small
* len/truesize ratio.
*/
static inline bool tcp_rmem_pressure(const struct sock *sk)
{
int rcvbuf, threshold;
if (tcp_under_memory_pressure(sk))
return true;
rcvbuf = READ_ONCE(sk->sk_rcvbuf);
threshold = rcvbuf - (rcvbuf >> 3);
return atomic_read(&sk->sk_rmem_alloc) > threshold;
}
static inline bool tcp_epollin_ready(const struct sock *sk, int target)
{
const struct tcp_sock *tp = tcp_sk(sk);
int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
if (avail <= 0)
return false;
return (avail >= target) || tcp_rmem_pressure(sk) ||
(tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss);
}
extern void tcp_openreq_init_rwin(struct request_sock *req,
const struct sock *sk_listener,
const struct dst_entry *dst);
void tcp_enter_memory_pressure(struct sock *sk);
void tcp_leave_memory_pressure(struct sock *sk);
static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl;
}
static inline int keepalive_time_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time;
}
static inline int keepalive_probes(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes;
}
static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
{
const struct inet_connection_sock *icsk = &tp->inet_conn;
return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime,
tcp_jiffies32 - tp->rcv_tstamp);
}
static inline int tcp_fin_time(const struct sock *sk)
{
int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
fin_timeout = (rto << 2) - (rto >> 1);
return fin_timeout;
}
static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt,
int paws_win)
{
if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
return true;
if (unlikely(!time_before32(ktime_get_seconds(),
rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)))
return true;
/*
* Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
* then following tcp messages have valid values. Ignore 0 value,
* or else 'negative' tsval might forbid us to accept their packets.
*/
if (!rx_opt->ts_recent)
return true;
return false;
}
static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
int rst)
{
if (tcp_paws_check(rx_opt, 0))
return false;
/* RST segments are not recommended to carry timestamp,
and, if they do, it is recommended to ignore PAWS because
"their cleanup function should take precedence over timestamps."
Certainly, it is mistake. It is necessary to understand the reasons
of this constraint to relax it: if peer reboots, clock may go
out-of-sync and half-open connections will not be reset.
Actually, the problem would be not existing if all
the implementations followed draft about maintaining clock
via reboots. Linux-2.2 DOES NOT!
However, we can relax time bounds for RST segments to MSL.
*/
if (rst && !time_before32(ktime_get_seconds(),
rx_opt->ts_recent_stamp + TCP_PAWS_MSL))
return false;
return true;
}
bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
int mib_idx, u32 *last_oow_ack_time);
static inline void tcp_mib_init(struct net *net)
{
/* See RFC 2012 */
TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1);
TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1);
}
/* from STCP */
static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
{
tp->lost_skb_hint = NULL;
}
static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
{
tcp_clear_retrans_hints_partial(tp);
tp->retransmit_skb_hint = NULL;
}
union tcp_md5_addr {
struct in_addr a4;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr a6;
#endif
};
/* - key database */
struct tcp_md5sig_key {
struct hlist_node node;
u8 keylen;
u8 family; /* AF_INET or AF_INET6 */
u8 prefixlen;
u8 flags;
union tcp_md5_addr addr;
int l3index; /* set if key added with L3 scope */
u8 key[TCP_MD5SIG_MAXKEYLEN];
struct rcu_head rcu;
};
/* - sock block */
struct tcp_md5sig_info {
struct hlist_head head;
struct rcu_head rcu;
};
/* - pseudo header */
struct tcp4_pseudohdr {
__be32 saddr;
__be32 daddr;
__u8 pad;
__u8 protocol;
__be16 len;
};
struct tcp6_pseudohdr {
struct in6_addr saddr;
struct in6_addr daddr;
__be32 len;
__be32 protocol; /* including padding */
};
union tcp_md5sum_block {
struct tcp4_pseudohdr ip4;
#if IS_ENABLED(CONFIG_IPV6)
struct tcp6_pseudohdr ip6;
#endif
};
/* - pool: digest algorithm, hash description and scratch buffer */
struct tcp_md5sig_pool {
struct ahash_request *md5_req;
void *scratch;
};
/* - functions */
int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
const struct sock *sk, const struct sk_buff *skb);
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
int family, u8 prefixlen, int l3index, u8 flags,
const u8 *newkey, u8 newkeylen, gfp_t gfp);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
int family, u8 prefixlen, int l3index, u8 flags);
struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
const struct sock *addr_sk);
#ifdef CONFIG_TCP_MD5SIG
#include <linux/jump_label.h>
extern struct static_key_false tcp_md5_needed;
struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
const union tcp_md5_addr *addr,
int family);
static inline struct tcp_md5sig_key *
tcp_md5_do_lookup(const struct sock *sk, int l3index,
const union tcp_md5_addr *addr, int family)
{
if (!static_branch_unlikely(&tcp_md5_needed))
return NULL;
return __tcp_md5_do_lookup(sk, l3index, addr, family);
}
enum skb_drop_reason
tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
const void *saddr, const void *daddr,
int family, int dif, int sdif);
#define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key)
#else
static inline struct tcp_md5sig_key *
tcp_md5_do_lookup(const struct sock *sk, int l3index,
const union tcp_md5_addr *addr, int family)
{
return NULL;
}
static inline enum skb_drop_reason
tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
const void *saddr, const void *daddr,
int family, int dif, int sdif)
{
return SKB_NOT_DROPPED_YET;
}
#define tcp_twsk_md5_key(twsk) NULL
#endif
bool tcp_alloc_md5sig_pool(void);
struct tcp_md5sig_pool *tcp_get_md5sig_pool(void);
static inline void tcp_put_md5sig_pool(void)
{
local_bh_enable();
}
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *,
unsigned int header_len);
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
const struct tcp_md5sig_key *key);
/* From tcp_fastopen.c */
void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie);
void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
struct tcp_fastopen_cookie *cookie, bool syn_lost,
u16 try_exp);
struct tcp_fastopen_request {
/* Fast Open cookie. Size 0 means a cookie request */
struct tcp_fastopen_cookie cookie;
struct msghdr *data; /* data in MSG_FASTOPEN */
size_t size;
int copied; /* queued in tcp_connect() */
struct ubuf_info *uarg;
};
void tcp_free_fastopen_req(struct tcp_sock *tp);
void tcp_fastopen_destroy_cipher(struct sock *sk);
void tcp_fastopen_ctx_destroy(struct net *net);
int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
void *primary_key, void *backup_key);
int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
u64 *key);
void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
const struct dst_entry *dst);
void tcp_fastopen_init_key_once(struct net *net);
bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie);
bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
#define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t)
#define TCP_FASTOPEN_KEY_MAX 2
#define TCP_FASTOPEN_KEY_BUF_LENGTH \
(TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX)
/* Fastopen key context */
struct tcp_fastopen_context {
siphash_key_t key[TCP_FASTOPEN_KEY_MAX];
int num;
struct rcu_head rcu;
};
void tcp_fastopen_active_disable(struct sock *sk);
bool tcp_fastopen_active_should_disable(struct sock *sk);
void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired);
/* Caller needs to wrap with rcu_read_(un)lock() */
static inline
struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk)
{
struct tcp_fastopen_context *ctx;
ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
if (!ctx)
ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
return ctx;
}
static inline
bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc,
const struct tcp_fastopen_cookie *orig)
{
if (orig->len == TCP_FASTOPEN_COOKIE_SIZE &&
orig->len == foc->len &&
!memcmp(orig->val, foc->val, foc->len))
return true;
return false;
}
static inline
int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx)
{
return ctx->num;
}
/* Latencies incurred by various limits for a sender. They are
* chronograph-like stats that are mutually exclusive.
*/
enum tcp_chrono {
TCP_CHRONO_UNSPEC,
TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */
TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */
TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */
__TCP_CHRONO_MAX,
};
void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type);
void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type);
/* This helper is needed, because skb->tcp_tsorted_anchor uses
* the same memory storage than skb->destructor/_skb_refdst
*/
static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb)
{
skb->destructor = NULL;
skb->_skb_refdst = 0UL;
}
#define tcp_skb_tsorted_save(skb) { \
unsigned long _save = skb->_skb_refdst; \
skb->_skb_refdst = 0UL;
#define tcp_skb_tsorted_restore(skb) \
skb->_skb_refdst = _save; \
}
void tcp_write_queue_purge(struct sock *sk);
static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
{
return skb_rb_first(&sk->tcp_rtx_queue);
}
static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
{
return skb_rb_last(&sk->tcp_rtx_queue);
}
static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
{
return skb_peek_tail(&sk->sk_write_queue);
}
#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
static inline struct sk_buff *tcp_send_head(const struct sock *sk)
{
return skb_peek(&sk->sk_write_queue);
}
static inline bool tcp_skb_is_last(const struct sock *sk,
const struct sk_buff *skb)
{
return skb_queue_is_last(&sk->sk_write_queue, skb);
}
/**
* tcp_write_queue_empty - test if any payload (or FIN) is available in write queue
* @sk: socket
*
* Since the write queue can have a temporary empty skb in it,
* we must not use "return skb_queue_empty(&sk->sk_write_queue)"
*/
static inline bool tcp_write_queue_empty(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
return tp->write_seq == tp->snd_nxt;
}
static inline bool tcp_rtx_queue_empty(const struct sock *sk)
{
return RB_EMPTY_ROOT(&sk->tcp_rtx_queue);
}
static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
{
return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
}
static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
{
__skb_queue_tail(&sk->sk_write_queue, skb);
/* Queue it, remembering where we must start sending. */
if (sk->sk_write_queue.next == skb)
tcp_chrono_start(sk, TCP_CHRONO_BUSY);
}
/* Insert new before skb on the write queue of sk. */
static inline void tcp_insert_write_queue_before(struct sk_buff *new,
struct sk_buff *skb,
struct sock *sk)
{
__skb_queue_before(&sk->sk_write_queue, skb, new);
}
static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
{
tcp_skb_tsorted_anchor_cleanup(skb);
__skb_unlink(skb, &sk->sk_write_queue);
}
void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb);
static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk)
{
tcp_skb_tsorted_anchor_cleanup(skb);
rb_erase(&skb->rbnode, &sk->tcp_rtx_queue);
}
static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk)
{
list_del(&skb->tcp_tsorted_anchor);
tcp_rtx_queue_unlink(skb, sk);
tcp_wmem_free_skb(sk, skb);
}
static inline void tcp_push_pending_frames(struct sock *sk)
{
if (tcp_send_head(sk)) {
struct tcp_sock *tp = tcp_sk(sk);
__tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
}
}
/* Start sequence of the skb just after the highest skb with SACKed
* bit, valid only if sacked_out > 0 or when the caller has ensured
* validity by itself.
*/
static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
{
if (!tp->sacked_out)
return tp->snd_una;
if (tp->highest_sack == NULL)
return tp->snd_nxt;
return TCP_SKB_CB(tp->highest_sack)->seq;
}
static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
{
tcp_sk(sk)->highest_sack = skb_rb_next(skb);
}
static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
{
return tcp_sk(sk)->highest_sack;
}
static inline void tcp_highest_sack_reset(struct sock *sk)
{
tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk);
}
/* Called when old skb is about to be deleted and replaced by new skb */
static inline void tcp_highest_sack_replace(struct sock *sk,
struct sk_buff *old,
struct sk_buff *new)
{
if (old == tcp_highest_sack(sk))
tcp_sk(sk)->highest_sack = new;
}
/* This helper checks if socket has IP_TRANSPARENT set */
static inline bool inet_sk_transparent(const struct sock *sk)
{
switch (sk->sk_state) {
case TCP_TIME_WAIT:
return inet_twsk(sk)->tw_transparent;
case TCP_NEW_SYN_RECV:
return inet_rsk(inet_reqsk(sk))->no_srccheck;
}
return inet_sk(sk)->transparent;
}
/* Determines whether this is a thin stream (which may suffer from
* increased latency). Used to trigger latency-reducing mechanisms.
*/
static inline bool tcp_stream_is_thin(struct tcp_sock *tp)
{
return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp);
}
/* /proc */
enum tcp_seq_states {
TCP_SEQ_STATE_LISTENING,
TCP_SEQ_STATE_ESTABLISHED,
};
void *tcp_seq_start(struct seq_file *seq, loff_t *pos);
void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void tcp_seq_stop(struct seq_file *seq, void *v);
struct tcp_seq_afinfo {
sa_family_t family;
};
struct tcp_iter_state {
struct seq_net_private p;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
int bucket, offset, sbucket, num;
loff_t last_pos;
};
extern struct request_sock_ops tcp_request_sock_ops;
extern struct request_sock_ops tcp6_request_sock_ops;
void tcp_v4_destroy_sock(struct sock *sk);
struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
netdev_features_t features);
struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb));
int tcp_gro_complete(struct sk_buff *skb);
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
}
bool tcp_stream_memory_free(const struct sock *sk, int wake);
#ifdef CONFIG_PROC_FS
int tcp4_proc_init(void);
void tcp4_proc_exit(void);
#endif
int tcp_rtx_synack(const struct sock *sk, struct request_sock *req);
int tcp_conn_request(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct sk_buff *skb);
/* TCP af-specific functions */
struct tcp_sock_af_ops {
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk,
const struct sock *addr_sk);
int (*calc_md5_hash)(char *location,
const struct tcp_md5sig_key *md5,
const struct sock *sk,
const struct sk_buff *skb);
int (*md5_parse)(struct sock *sk,
int optname,
sockptr_t optval,
int optlen);
#endif
};
struct tcp_request_sock_ops {
u16 mss_clamp;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk,
const struct sock *addr_sk);
int (*calc_md5_hash) (char *location,
const struct tcp_md5sig_key *md5,
const struct sock *sk,
const struct sk_buff *skb);
#endif
#ifdef CONFIG_SYN_COOKIES
__u32 (*cookie_init_seq)(const struct sk_buff *skb,
__u16 *mss);
#endif
struct dst_entry *(*route_req)(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req);
u32 (*init_seq)(const struct sk_buff *skb);
u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb);
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb);
};
extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
#if IS_ENABLED(CONFIG_IPV6)
extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops;
#endif
#ifdef CONFIG_SYN_COOKIES
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
const struct sock *sk, struct sk_buff *skb,
__u16 *mss)
{
tcp_synq_overflow(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
return ops->cookie_init_seq(skb, mss);
}
#else
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
const struct sock *sk, struct sk_buff *skb,
__u16 *mss)
{
return 0;
}
#endif
int tcpv4_offload_init(void);
void tcp_v4_init(void);
void tcp_init(void);
/* tcp_recovery.c */
void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb);
void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced);
extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb,
u32 reo_wnd);
extern bool tcp_rack_mark_lost(struct sock *sk);
extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
u64 xmit_time);
extern void tcp_rack_reo_timeout(struct sock *sk);
extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs);
/* At how many usecs into the future should the RTO fire? */
static inline s64 tcp_rto_delta_us(const struct sock *sk)
{
const struct sk_buff *skb = tcp_rtx_queue_head(sk);
u32 rto = inet_csk(sk)->icsk_rto;
u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);
return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
}
/*
* Save and compile IPv4 options, return a pointer to it
*/
static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net,
struct sk_buff *skb)
{
const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
struct ip_options_rcu *dopt = NULL;
if (opt->optlen) {
int opt_size = sizeof(*dopt) + opt->optlen;
dopt = kmalloc(opt_size, GFP_ATOMIC);
if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) {
kfree(dopt);
dopt = NULL;
}
}
return dopt;
}
/* locally generated TCP pure ACKs have skb->truesize == 2
* (check tcp_send_ack() in net/ipv4/tcp_output.c )
* This is much faster than dissecting the packet to find out.
* (Think of GRE encapsulations, IPv4, IPv6, ...)
*/
static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb)
{
return skb->truesize == 2;
}
static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
{
skb->truesize = 2;
}
static inline int tcp_inq(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int answ;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
answ = 0;
} else if (sock_flag(sk, SOCK_URGINLINE) ||
!tp->urg_data ||
before(tp->urg_seq, tp->copied_seq) ||
!before(tp->urg_seq, tp->rcv_nxt)) {
answ = tp->rcv_nxt - tp->copied_seq;
/* Subtract 1, if FIN was received */
if (answ && sock_flag(sk, SOCK_DONE))
answ--;
} else {
answ = tp->urg_seq - tp->copied_seq;
}
return answ;
}
int tcp_peek_len(struct socket *sock);
static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
{
u16 segs_in;
segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
/* We update these fields while other threads might
* read them from tcp_get_info()
*/
WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in);
if (skb->len > tcp_hdrlen(skb))
WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in);
}
/*
* TCP listen path runs lockless.
* We forced "struct sock" to be const qualified to make sure
* we don't modify one of its field by mistake.
* Here, we increment sk_drops which is an atomic_t, so we can safely
* make sock writable again.
*/
static inline void tcp_listendrop(const struct sock *sk)
{
atomic_inc(&((struct sock *)sk)->sk_drops);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
}
enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
/*
* Interface for adding Upper Level Protocols over TCP
*/
#define TCP_ULP_NAME_MAX 16
#define TCP_ULP_MAX 128
#define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX)
struct tcp_ulp_ops {
struct list_head list;
/* initialize ulp */
int (*init)(struct sock *sk);
/* update ulp */
void (*update)(struct sock *sk, struct proto *p,
void (*write_space)(struct sock *sk));
/* cleanup ulp */
void (*release)(struct sock *sk);
/* diagnostic */
int (*get_info)(const struct sock *sk, struct sk_buff *skb);
size_t (*get_info_size)(const struct sock *sk);
/* clone ulp */
void (*clone)(const struct request_sock *req, struct sock *newsk,
const gfp_t priority);
char name[TCP_ULP_NAME_MAX];
struct module *owner;
};
int tcp_register_ulp(struct tcp_ulp_ops *type);
void tcp_unregister_ulp(struct tcp_ulp_ops *type);
int tcp_set_ulp(struct sock *sk, const char *name);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
void tcp_update_ulp(struct sock *sk, struct proto *p,
void (*write_space)(struct sock *sk));
#define MODULE_ALIAS_TCP_ULP(name) \
__MODULE_INFO(alias, alias_userspace, name); \
__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
#ifdef CONFIG_NET_SOCK_MSG
struct sk_msg;
struct sk_psock;
#ifdef CONFIG_BPF_SYSCALL
struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
#endif /* CONFIG_BPF_SYSCALL */
int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
int flags);
#endif /* CONFIG_NET_SOCK_MSG */
#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG)
static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
{
}
#endif
#ifdef CONFIG_CGROUP_BPF
static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
struct sk_buff *skb,
unsigned int end_offset)
{
skops->skb = skb;
skops->skb_data_end = skb->data + end_offset;
}
#else
static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
struct sk_buff *skb,
unsigned int end_offset)
{
}
#endif
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
* program does not support the chosen operation or there is no BPF
* program loaded).
*/
#ifdef CONFIG_BPF
static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
struct bpf_sock_ops_kern sock_ops;
int ret;
memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
if (sk_fullsock(sk)) {
sock_ops.is_fullsock = 1;
sock_owned_by_me(sk);
}
sock_ops.sk = sk;
sock_ops.op = op;
if (nargs > 0)
memcpy(sock_ops.args, args, nargs * sizeof(*args));
ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
if (ret == 0)
ret = sock_ops.reply;
else
ret = -1;
return ret;
}
static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
{
u32 args[2] = {arg1, arg2};
return tcp_call_bpf(sk, op, 2, args);
}
static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
u32 arg3)
{
u32 args[3] = {arg1, arg2, arg3};
return tcp_call_bpf(sk, op, 3, args);
}
#else
static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
return -EPERM;
}
static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
{
return -EPERM;
}
static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
u32 arg3)
{
return -EPERM;
}
#endif
static inline u32 tcp_timeout_init(struct sock *sk)
{
int timeout;
timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL);
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
return min_t(int, timeout, TCP_RTO_MAX);
}
static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
{
int rwnd;
rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL);
if (rwnd < 0)
rwnd = 0;
return rwnd;
}
static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
{
return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
}
static inline void tcp_bpf_rtt(struct sock *sk)
{
if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG))
tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
}
#if IS_ENABLED(CONFIG_SMC)
extern struct static_key_false tcp_have_smc;
#endif
#if IS_ENABLED(CONFIG_TLS_DEVICE)
void clean_acked_data_enable(struct inet_connection_sock *icsk,
void (*cad)(struct sock *sk, u32 ack_seq));
void clean_acked_data_disable(struct inet_connection_sock *icsk);
void clean_acked_data_flush(void);
#endif
DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled);
static inline void tcp_add_tx_delay(struct sk_buff *skb,
const struct tcp_sock *tp)
{
if (static_branch_unlikely(&tcp_tx_delay_enabled))
skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC;
}
/* Compute Earliest Departure Time for some control packets
* like ACK or RST for TIME_WAIT or non ESTABLISHED sockets.
*/
static inline u64 tcp_transmit_time(const struct sock *sk)
{
if (static_branch_unlikely(&tcp_tx_delay_enabled)) {
u32 delay = (sk->sk_state == TCP_TIME_WAIT) ?
tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay;
return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC;
}
return 0;
}
#endif /* _TCP_H */
|