sock.h
63.1 KB
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
/*
* 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 AF_INET socket handler.
*
* Version: @(#)sock.h 1.0.4 05/13/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Florian La Roche <flla@stud.uni-sb.de>
*
* Fixes:
* Alan Cox : Volatiles in skbuff pointers. See
* skbuff comments. May be overdone,
* better to prove they can be removed
* than the reverse.
* Alan Cox : Added a zapped field for tcp to note
* a socket is reset and must stay shut up
* Alan Cox : New fields for options
* Pauline Middelink : identd support
* Alan Cox : Eliminate low level recv/recvfrom
* David S. Miller : New socket lookup architecture.
* Steve Whitehouse: Default routines for sock_ops
* Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made
* protinfo be just a void pointer, as the
* protocol specific parts were moved to
* respective headers and ipv4/v6, etc now
* use private slabcaches for its socks
* Pedro Hortas : New flags field for socket options
*
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _SOCK_H
#define _SOCK_H
#include <linux/hardirq.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/list_nulls.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/bitops.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h> /* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/static_key.h>
#include <linux/aio.h>
#include <linux/sched.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
#include <linux/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>
#include <linux/net_tstamp.h>
struct cgroup;
struct cgroup_subsys;
#ifdef CONFIG_NET
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg);
#else
static inline
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
return 0;
}
static inline
void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
{
}
#endif
/*
* This structure really needs to be cleaned up.
* Most of it is for TCP, and not used by any of
* the other protocols.
*/
/* Define this to get the SOCK_DBG debugging facility. */
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
printk(KERN_DEBUG msg); } while (0)
#else
/* Validate arguments and do nothing */
static inline __printf(2, 3)
void SOCK_DEBUG(const struct sock *sk, const char *msg, ...)
{
}
#endif
/* This is the per-socket lock. The spinlock provides a synchronization
* between user contexts and software interrupt processing, whereas the
* mini-semaphore synchronizes multiple users amongst themselves.
*/
typedef struct {
spinlock_t slock;
int owned;
wait_queue_head_t wq;
/*
* We express the mutex-alike socket_lock semantics
* to the lock validator by explicitly managing
* the slock as a lock variant (in addition to
* the slock itself):
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
} socket_lock_t;
struct sock;
struct proto;
struct net;
typedef __u32 __bitwise __portpair;
typedef __u64 __bitwise __addrpair;
/**
* struct sock_common - minimal network layer representation of sockets
* @skc_daddr: Foreign IPv4 addr
* @skc_rcv_saddr: Bound local IPv4 addr
* @skc_hash: hash value used with various protocol lookup tables
* @skc_u16hashes: two u16 hash values used by UDP lookup tables
* @skc_dport: placeholder for inet_dport/tw_dport
* @skc_num: placeholder for inet_num/tw_num
* @skc_family: network address family
* @skc_state: Connection state
* @skc_reuse: %SO_REUSEADDR setting
* @skc_reuseport: %SO_REUSEPORT setting
* @skc_bound_dev_if: bound device index if != 0
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
* @skc_prot: protocol handlers inside a network family
* @skc_net: reference to the network namespace of this socket
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
* @skc_refcnt: reference count
*
* This is the minimal network layer representation of sockets, the header
* for struct sock and struct inet_timewait_sock.
*/
struct sock_common {
/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
* address on 64bit arches : cf INET_MATCH()
*/
union {
__addrpair skc_addrpair;
struct {
__be32 skc_daddr;
__be32 skc_rcv_saddr;
};
};
union {
unsigned int skc_hash;
__u16 skc_u16hashes[2];
};
/* skc_dport && skc_num must be grouped as well */
union {
__portpair skc_portpair;
struct {
__be16 skc_dport;
__u16 skc_num;
};
};
unsigned short skc_family;
volatile unsigned char skc_state;
unsigned char skc_reuse:4;
unsigned char skc_reuseport:1;
unsigned char skc_ipv6only:1;
int skc_bound_dev_if;
union {
struct hlist_node skc_bind_node;
struct hlist_nulls_node skc_portaddr_node;
};
struct proto *skc_prot;
#ifdef CONFIG_NET_NS
struct net *skc_net;
#endif
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr skc_v6_daddr;
struct in6_addr skc_v6_rcv_saddr;
#endif
/*
* fields between dontcopy_begin/dontcopy_end
* are not copied in sock_copy()
*/
/* private: */
int skc_dontcopy_begin[0];
/* public: */
union {
struct hlist_node skc_node;
struct hlist_nulls_node skc_nulls_node;
};
int skc_tx_queue_mapping;
atomic_t skc_refcnt;
/* private: */
int skc_dontcopy_end[0];
/* public: */
};
struct cg_proto;
/**
* struct sock - network layer representation of sockets
* @__sk_common: shared layout with inet_timewait_sock
* @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
* @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
* @sk_lock: synchronizer
* @sk_rcvbuf: size of receive buffer in bytes
* @sk_wq: sock wait queue and async head
* @sk_rx_dst: receive input route used by early demux
* @sk_dst_cache: destination cache
* @sk_dst_lock: destination cache lock
* @sk_policy: flow policy
* @sk_receive_queue: incoming packets
* @sk_wmem_alloc: transmit queue bytes committed
* @sk_write_queue: Packet sending queue
* @sk_omem_alloc: "o" is "option" or "other"
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
* @sk_napi_id: id of the last napi context to receive data for sk
* @sk_ll_usec: usecs to busypoll when there is no data
* @sk_allocation: allocation mode
* @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
* @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
* @sk_sndbuf: size of send buffer in bytes
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
* @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
* @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
* @sk_error_queue: rarely used
* @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
* IPV6_ADDRFORM for instance)
* @sk_err: last error
* @sk_err_soft: errors that don't cause failure but are the cause of a
* persistent failure not just 'timed out'
* @sk_drops: raw/udp drops counter
* @sk_ack_backlog: current listen backlog
* @sk_max_ack_backlog: listen backlog set in listen()
* @sk_priority: %SO_PRIORITY setting
* @sk_cgrp_prioidx: socket group's priority map index
* @sk_type: socket type (%SOCK_STREAM, etc)
* @sk_protocol: which protocol this socket belongs in this network family
* @sk_peer_pid: &struct pid for this socket's peer
* @sk_peer_cred: %SO_PEERCRED setting
* @sk_rcvlowat: %SO_RCVLOWAT setting
* @sk_rcvtimeo: %SO_RCVTIMEO setting
* @sk_sndtimeo: %SO_SNDTIMEO setting
* @sk_rxhash: flow hash received from netif layer
* @sk_incoming_cpu: record cpu processing incoming packets
* @sk_txhash: computed flow hash for use on transmit
* @sk_filter: socket filtering instructions
* @sk_protinfo: private area, net family specific, when not using slab
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
* @sk_tsflags: SO_TIMESTAMPING socket options
* @sk_tskey: counter to disambiguate concurrent tstamp requests
* @sk_socket: Identd and reporting IO signals
* @sk_user_data: RPC layer private data
* @sk_frag: cached page frag
* @sk_peek_off: current peek_offset value
* @sk_send_head: front of stuff to transmit
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_classid: this socket's cgroup classid
* @sk_cgrp: this socket's cgroup-specific proto data
* @sk_write_pending: a write to stream socket waits to start
* @sk_state_change: callback to indicate change in the state of the sock
* @sk_data_ready: callback to indicate there is data to be processed
* @sk_write_space: callback to indicate there is bf sending space available
* @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
* @sk_backlog_rcv: callback to process the backlog
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
*/
struct sock {
/*
* Now struct inet_timewait_sock also uses sock_common, so please just
* don't add nothing before this first member (__sk_common) --acme
*/
struct sock_common __sk_common;
#define sk_node __sk_common.skc_node
#define sk_nulls_node __sk_common.skc_nulls_node
#define sk_refcnt __sk_common.skc_refcnt
#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
#define sk_hash __sk_common.skc_hash
#define sk_portpair __sk_common.skc_portpair
#define sk_num __sk_common.skc_num
#define sk_dport __sk_common.skc_dport
#define sk_addrpair __sk_common.skc_addrpair
#define sk_daddr __sk_common.skc_daddr
#define sk_rcv_saddr __sk_common.skc_rcv_saddr
#define sk_family __sk_common.skc_family
#define sk_state __sk_common.skc_state
#define sk_reuse __sk_common.skc_reuse
#define sk_reuseport __sk_common.skc_reuseport
#define sk_ipv6only __sk_common.skc_ipv6only
#define sk_bound_dev_if __sk_common.skc_bound_dev_if
#define sk_bind_node __sk_common.skc_bind_node
#define sk_prot __sk_common.skc_prot
#define sk_net __sk_common.skc_net
#define sk_v6_daddr __sk_common.skc_v6_daddr
#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr
socket_lock_t sk_lock;
struct sk_buff_head sk_receive_queue;
/*
* The backlog queue is special, it is always used with
* the per-socket spinlock held and requires low latency
* access. Therefore we special case it's implementation.
* Note : rmem_alloc is in this structure to fill a hole
* on 64bit arches, not because its logically part of
* backlog.
*/
struct {
atomic_t rmem_alloc;
int len;
struct sk_buff *head;
struct sk_buff *tail;
} sk_backlog;
#define sk_rmem_alloc sk_backlog.rmem_alloc
int sk_forward_alloc;
#ifdef CONFIG_RPS
__u32 sk_rxhash;
#endif
u16 sk_incoming_cpu;
/* 16bit hole
* Warned : sk_incoming_cpu can be set from softirq,
* Do not use this hole without fully understanding possible issues.
*/
__u32 sk_txhash;
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sk_napi_id;
unsigned int sk_ll_usec;
#endif
atomic_t sk_drops;
int sk_rcvbuf;
struct sk_filter __rcu *sk_filter;
struct socket_wq __rcu *sk_wq;
#ifdef CONFIG_XFRM
struct xfrm_policy *sk_policy[2];
#endif
unsigned long sk_flags;
struct dst_entry *sk_rx_dst;
struct dst_entry __rcu *sk_dst_cache;
spinlock_t sk_dst_lock;
atomic_t sk_wmem_alloc;
atomic_t sk_omem_alloc;
int sk_sndbuf;
struct sk_buff_head sk_write_queue;
kmemcheck_bitfield_begin(flags);
unsigned int sk_shutdown : 2,
sk_no_check_tx : 1,
sk_no_check_rx : 1,
sk_userlocks : 4,
sk_protocol : 8,
sk_type : 16;
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
u32 sk_pacing_rate; /* bytes per second */
u32 sk_max_pacing_rate;
netdev_features_t sk_route_caps;
netdev_features_t sk_route_nocaps;
int sk_gso_type;
unsigned int sk_gso_max_size;
u16 sk_gso_max_segs;
int sk_rcvlowat;
unsigned long sk_lingertime;
struct sk_buff_head sk_error_queue;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
int sk_err,
sk_err_soft;
unsigned short sk_ack_backlog;
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
__u32 sk_cgrp_prioidx;
#endif
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
long sk_sndtimeo;
void *sk_protinfo;
struct timer_list sk_timer;
ktime_t sk_stamp;
u16 sk_tsflags;
u32 sk_tskey;
struct socket *sk_socket;
void *sk_user_data;
struct page_frag sk_frag;
struct sk_buff *sk_send_head;
__s32 sk_peek_off;
int sk_write_pending;
#ifdef CONFIG_SECURITY
void *sk_security;
#endif
__u32 sk_mark;
u32 sk_classid;
struct cg_proto *sk_cgrp;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk);
void (*sk_write_space)(struct sock *sk);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk,
struct sk_buff *skb);
void (*sk_destruct)(struct sock *sk);
};
#define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk)))
#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr)
/*
* SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
* or not whether his port will be reused by someone else. SK_FORCE_REUSE
* on a socket means that the socket will reuse everybody else's port
* without looking at the other's sk_reuse value.
*/
#define SK_NO_REUSE 0
#define SK_CAN_REUSE 1
#define SK_FORCE_REUSE 2
static inline int sk_peek_offset(struct sock *sk, int flags)
{
if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))
return sk->sk_peek_off;
else
return 0;
}
static inline void sk_peek_offset_bwd(struct sock *sk, int val)
{
if (sk->sk_peek_off >= 0) {
if (sk->sk_peek_off >= val)
sk->sk_peek_off -= val;
else
sk->sk_peek_off = 0;
}
}
static inline void sk_peek_offset_fwd(struct sock *sk, int val)
{
if (sk->sk_peek_off >= 0)
sk->sk_peek_off += val;
}
/*
* Hashed lists helper routines
*/
static inline struct sock *sk_entry(const struct hlist_node *node)
{
return hlist_entry(node, struct sock, sk_node);
}
static inline struct sock *__sk_head(const struct hlist_head *head)
{
return hlist_entry(head->first, struct sock, sk_node);
}
static inline struct sock *sk_head(const struct hlist_head *head)
{
return hlist_empty(head) ? NULL : __sk_head(head);
}
static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
{
return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
}
static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
{
return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
}
static inline struct sock *sk_next(const struct sock *sk)
{
return sk->sk_node.next ?
hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}
static inline struct sock *sk_nulls_next(const struct sock *sk)
{
return (!is_a_nulls(sk->sk_nulls_node.next)) ?
hlist_nulls_entry(sk->sk_nulls_node.next,
struct sock, sk_nulls_node) :
NULL;
}
static inline bool sk_unhashed(const struct sock *sk)
{
return hlist_unhashed(&sk->sk_node);
}
static inline bool sk_hashed(const struct sock *sk)
{
return !sk_unhashed(sk);
}
static inline void sk_node_init(struct hlist_node *node)
{
node->pprev = NULL;
}
static inline void sk_nulls_node_init(struct hlist_nulls_node *node)
{
node->pprev = NULL;
}
static inline void __sk_del_node(struct sock *sk)
{
__hlist_del(&sk->sk_node);
}
/* NB: equivalent to hlist_del_init_rcu */
static inline bool __sk_del_node_init(struct sock *sk)
{
if (sk_hashed(sk)) {
__sk_del_node(sk);
sk_node_init(&sk->sk_node);
return true;
}
return false;
}
/* Grab socket reference count. This operation is valid only
when sk is ALREADY grabbed f.e. it is found in hash table
or a list and the lookup is made under lock preventing hash table
modifications.
*/
static inline void sock_hold(struct sock *sk)
{
atomic_inc(&sk->sk_refcnt);
}
/* Ungrab socket in the context, which assumes that socket refcnt
cannot hit zero, f.e. it is true in context of any socketcall.
*/
static inline void __sock_put(struct sock *sk)
{
atomic_dec(&sk->sk_refcnt);
}
static inline bool sk_del_node_init(struct sock *sk)
{
bool rc = __sk_del_node_init(sk);
if (rc) {
/* paranoid for a while -acme */
WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
return rc;
}
#define sk_del_node_init_rcu(sk) sk_del_node_init(sk)
static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk)
{
if (sk_hashed(sk)) {
hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
return true;
}
return false;
}
static inline bool sk_nulls_del_node_init_rcu(struct sock *sk)
{
bool rc = __sk_nulls_del_node_init_rcu(sk);
if (rc) {
/* paranoid for a while -acme */
WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
return rc;
}
static inline void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
hlist_add_head(&sk->sk_node, list);
}
static inline void sk_add_node(struct sock *sk, struct hlist_head *list)
{
sock_hold(sk);
__sk_add_node(sk, list);
}
static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
{
sock_hold(sk);
hlist_add_head_rcu(&sk->sk_node, list);
}
static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
}
static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
sock_hold(sk);
__sk_nulls_add_node_rcu(sk, list);
}
static inline void __sk_del_bind_node(struct sock *sk)
{
__hlist_del(&sk->sk_bind_node);
}
static inline void sk_add_bind_node(struct sock *sk,
struct hlist_head *list)
{
hlist_add_head(&sk->sk_bind_node, list);
}
#define sk_for_each(__sk, list) \
hlist_for_each_entry(__sk, list, sk_node)
#define sk_for_each_rcu(__sk, list) \
hlist_for_each_entry_rcu(__sk, list, sk_node)
#define sk_nulls_for_each(__sk, node, list) \
hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
#define sk_nulls_for_each_rcu(__sk, node, list) \
hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
#define sk_for_each_from(__sk) \
hlist_for_each_entry_from(__sk, sk_node)
#define sk_nulls_for_each_from(__sk, node) \
if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
#define sk_for_each_safe(__sk, tmp, list) \
hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
#define sk_for_each_bound(__sk, list) \
hlist_for_each_entry(__sk, list, sk_bind_node)
/**
* sk_nulls_for_each_entry_offset - iterate over a list at a given struct offset
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_node to use as a loop cursor.
* @head: the head for your list.
* @offset: offset of hlist_node within the struct.
*
*/
#define sk_nulls_for_each_entry_offset(tpos, pos, head, offset) \
for (pos = (head)->first; \
(!is_a_nulls(pos)) && \
({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \
pos = pos->next)
static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
/* Careful only use this in a context where these parameters
* can not change and must all be valid, such as recvmsg from
* userspace.
*/
return sk->sk_socket->file->f_cred->user_ns;
}
/* Sock flags */
enum sock_flags {
SOCK_DEAD,
SOCK_DONE,
SOCK_URGINLINE,
SOCK_KEEPOPEN,
SOCK_LINGER,
SOCK_DESTROY,
SOCK_BROADCAST,
SOCK_TIMESTAMP,
SOCK_ZAPPED,
SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
SOCK_DBG, /* %SO_DEBUG setting */
SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
SOCK_MEMALLOC, /* VM depends on this socket for swapping */
SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */
SOCK_FASYNC, /* fasync() active */
SOCK_RXQ_OVFL,
SOCK_ZEROCOPY, /* buffers from userspace */
SOCK_WIFI_STATUS, /* push wifi status to userspace */
SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS.
* Will use last 4 bytes of packet sent from
* user-space instead.
*/
SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
};
static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
{
nsk->sk_flags = osk->sk_flags;
}
static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
__set_bit(flag, &sk->sk_flags);
}
static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
__clear_bit(flag, &sk->sk_flags);
}
static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
{
return test_bit(flag, &sk->sk_flags);
}
#ifdef CONFIG_NET
extern struct static_key memalloc_socks;
static inline int sk_memalloc_socks(void)
{
return static_key_false(&memalloc_socks);
}
#else
static inline int sk_memalloc_socks(void)
{
return 0;
}
#endif
static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
{
return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
}
static inline void sk_acceptq_removed(struct sock *sk)
{
sk->sk_ack_backlog--;
}
static inline void sk_acceptq_added(struct sock *sk)
{
sk->sk_ack_backlog++;
}
static inline bool sk_acceptq_is_full(const struct sock *sk)
{
return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}
/*
* Compute minimal free write space needed to queue new packets.
*/
static inline int sk_stream_min_wspace(const struct sock *sk)
{
return sk->sk_wmem_queued >> 1;
}
static inline int sk_stream_wspace(const struct sock *sk)
{
return sk->sk_sndbuf - sk->sk_wmem_queued;
}
void sk_stream_write_space(struct sock *sk);
/* OOB backlog add */
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
/* dont let skb dst not refcounted, we are going to leave rcu lock */
skb_dst_force(skb);
if (!sk->sk_backlog.tail)
sk->sk_backlog.head = skb;
else
sk->sk_backlog.tail->next = skb;
sk->sk_backlog.tail = skb;
skb->next = NULL;
}
/*
* Take into account size of receive queue and backlog queue
* Do not take into account this skb truesize,
* to allow even a single big packet to come.
*/
static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit)
{
unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
return qsize > limit;
}
/* The per-socket spinlock must be held here. */
static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb,
unsigned int limit)
{
if (sk_rcvqueues_full(sk, limit))
return -ENOBUFS;
__sk_add_backlog(sk, skb);
sk->sk_backlog.len += skb->truesize;
return 0;
}
int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
if (sk_memalloc_socks() && skb_pfmemalloc(skb))
return __sk_backlog_rcv(sk, skb);
return sk->sk_backlog_rcv(sk, skb);
}
static inline void sk_incoming_cpu_update(struct sock *sk)
{
sk->sk_incoming_cpu = raw_smp_processor_id();
}
static inline void sock_rps_record_flow_hash(__u32 hash)
{
#ifdef CONFIG_RPS
struct rps_sock_flow_table *sock_flow_table;
rcu_read_lock();
sock_flow_table = rcu_dereference(rps_sock_flow_table);
rps_record_sock_flow(sock_flow_table, hash);
rcu_read_unlock();
#endif
}
static inline void sock_rps_reset_flow_hash(__u32 hash)
{
#ifdef CONFIG_RPS
struct rps_sock_flow_table *sock_flow_table;
rcu_read_lock();
sock_flow_table = rcu_dereference(rps_sock_flow_table);
rps_reset_sock_flow(sock_flow_table, hash);
rcu_read_unlock();
#endif
}
static inline void sock_rps_record_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
sock_rps_record_flow_hash(sk->sk_rxhash);
#endif
}
static inline void sock_rps_reset_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
sock_rps_reset_flow_hash(sk->sk_rxhash);
#endif
}
static inline void sock_rps_save_rxhash(struct sock *sk,
const struct sk_buff *skb)
{
#ifdef CONFIG_RPS
if (unlikely(sk->sk_rxhash != skb->hash)) {
sock_rps_reset_flow(sk);
sk->sk_rxhash = skb->hash;
}
#endif
}
static inline void sock_rps_reset_rxhash(struct sock *sk)
{
#ifdef CONFIG_RPS
sock_rps_reset_flow(sk);
sk->sk_rxhash = 0;
#endif
}
#define sk_wait_event(__sk, __timeo, __condition) \
({ int __rc; \
release_sock(__sk); \
__rc = __condition; \
if (!__rc) { \
*(__timeo) = schedule_timeout(*(__timeo)); \
} \
sched_annotate_sleep(); \
lock_sock(__sk); \
__rc = __condition; \
__rc; \
})
int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
void sk_stream_wait_close(struct sock *sk, long timeo_p);
int sk_stream_error(struct sock *sk, int flags, int err);
void sk_stream_kill_queues(struct sock *sk);
void sk_set_memalloc(struct sock *sk);
void sk_clear_memalloc(struct sock *sk);
int sk_wait_data(struct sock *sk, long *timeo);
struct request_sock_ops;
struct timewait_sock_ops;
struct inet_hashinfo;
struct raw_hashinfo;
struct module;
/*
* caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
* un-modified. Special care is taken when initializing object to zero.
*/
static inline void sk_prot_clear_nulls(struct sock *sk, int size)
{
if (offsetof(struct sock, sk_node.next) != 0)
memset(sk, 0, offsetof(struct sock, sk_node.next));
memset(&sk->sk_node.pprev, 0,
size - offsetof(struct sock, sk_node.pprev));
}
/* Networking protocol blocks we attach to sockets.
* socket layer -> transport layer interface
* transport -> network interface is defined by struct inet_proto
*/
struct proto {
void (*close)(struct sock *sk,
long timeout);
int (*connect)(struct sock *sk,
struct sockaddr *uaddr,
int addr_len);
int (*disconnect)(struct sock *sk, int flags);
struct sock * (*accept)(struct sock *sk, int flags, int *err);
int (*ioctl)(struct sock *sk, int cmd,
unsigned long arg);
int (*init)(struct sock *sk);
void (*destroy)(struct sock *sk);
void (*shutdown)(struct sock *sk, int how);
int (*setsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *option);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct sock *sk,
int level,
int optname, char __user *optval,
unsigned int optlen);
int (*compat_getsockopt)(struct sock *sk,
int level,
int optname, char __user *optval,
int __user *option);
int (*compat_ioctl)(struct sock *sk,
unsigned int cmd, unsigned long arg);
#endif
int (*sendmsg)(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len);
int (*recvmsg)(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg,
size_t len, int noblock, int flags,
int *addr_len);
int (*sendpage)(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
int (*bind)(struct sock *sk,
struct sockaddr *uaddr, int addr_len);
int (*backlog_rcv) (struct sock *sk,
struct sk_buff *skb);
void (*release_cb)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
void (*hash)(struct sock *sk);
void (*unhash)(struct sock *sk);
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
void (*clear_sk)(struct sock *sk, int size);
/* Keeping track of sockets in use */
#ifdef CONFIG_PROC_FS
unsigned int inuse_idx;
#endif
bool (*stream_memory_free)(const struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
atomic_long_t *memory_allocated; /* Current allocated memory. */
struct percpu_counter *sockets_allocated; /* Current number of sockets. */
/*
* Pressure flag: try to collapse.
* Technical note: it is used by multiple contexts non atomically.
* All the __sk_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
int *memory_pressure;
long *sysctl_mem;
int *sysctl_wmem;
int *sysctl_rmem;
int max_header;
bool no_autobind;
struct kmem_cache *slab;
unsigned int obj_size;
int slab_flags;
struct percpu_counter *orphan_count;
struct request_sock_ops *rsk_prot;
struct timewait_sock_ops *twsk_prot;
union {
struct inet_hashinfo *hashinfo;
struct udp_table *udp_table;
struct raw_hashinfo *raw_hash;
} h;
struct module *owner;
char name[32];
struct list_head node;
#ifdef SOCK_REFCNT_DEBUG
atomic_t socks;
#endif
#ifdef CONFIG_MEMCG_KMEM
/*
* cgroup specific init/deinit functions. Called once for all
* protocols that implement it, from cgroups populate function.
* This function has to setup any files the protocol want to
* appear in the kmem cgroup filesystem.
*/
int (*init_cgroup)(struct mem_cgroup *memcg,
struct cgroup_subsys *ss);
void (*destroy_cgroup)(struct mem_cgroup *memcg);
struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
};
/*
* Bits in struct cg_proto.flags
*/
enum cg_proto_flags {
/* Currently active and new sockets should be assigned to cgroups */
MEMCG_SOCK_ACTIVE,
/* It was ever activated; we must disarm static keys on destruction */
MEMCG_SOCK_ACTIVATED,
};
struct cg_proto {
struct page_counter memory_allocated; /* Current allocated memory. */
struct percpu_counter sockets_allocated; /* Current number of sockets. */
int memory_pressure;
long sysctl_mem[3];
unsigned long flags;
/*
* memcg field is used to find which memcg we belong directly
* Each memcg struct can hold more than one cg_proto, so container_of
* won't really cut.
*
* The elegant solution would be having an inverse function to
* proto_cgroup in struct proto, but that means polluting the structure
* for everybody, instead of just for memcg users.
*/
struct mem_cgroup *memcg;
};
int proto_register(struct proto *prot, int alloc_slab);
void proto_unregister(struct proto *prot);
static inline bool memcg_proto_active(struct cg_proto *cg_proto)
{
return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
}
static inline bool memcg_proto_activated(struct cg_proto *cg_proto)
{
return test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags);
}
#ifdef SOCK_REFCNT_DEBUG
static inline void sk_refcnt_debug_inc(struct sock *sk)
{
atomic_inc(&sk->sk_prot->socks);
}
static inline void sk_refcnt_debug_dec(struct sock *sk)
{
atomic_dec(&sk->sk_prot->socks);
printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}
static inline void sk_refcnt_debug_release(const struct sock *sk)
{
if (atomic_read(&sk->sk_refcnt) != 1)
printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
#define sk_refcnt_debug_dec(sk) do { } while (0)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET)
extern struct static_key memcg_socket_limit_enabled;
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
struct cg_proto *cg_proto)
{
return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
}
#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled)
#else
#define mem_cgroup_sockets_enabled 0
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
struct cg_proto *cg_proto)
{
return NULL;
}
#endif
static inline bool sk_stream_memory_free(const struct sock *sk)
{
if (sk->sk_wmem_queued >= sk->sk_sndbuf)
return false;
return sk->sk_prot->stream_memory_free ?
sk->sk_prot->stream_memory_free(sk) : true;
}
static inline bool sk_stream_is_writeable(const struct sock *sk)
{
return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
sk_stream_memory_free(sk);
}
static inline bool sk_has_memory_pressure(const struct sock *sk)
{
return sk->sk_prot->memory_pressure != NULL;
}
static inline bool sk_under_memory_pressure(const struct sock *sk)
{
if (!sk->sk_prot->memory_pressure)
return false;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
return !!sk->sk_cgrp->memory_pressure;
return !!*sk->sk_prot->memory_pressure;
}
static inline void sk_leave_memory_pressure(struct sock *sk)
{
int *memory_pressure = sk->sk_prot->memory_pressure;
if (!memory_pressure)
return;
if (*memory_pressure)
*memory_pressure = 0;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
struct cg_proto *cg_proto = sk->sk_cgrp;
struct proto *prot = sk->sk_prot;
for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
cg_proto->memory_pressure = 0;
}
}
static inline void sk_enter_memory_pressure(struct sock *sk)
{
if (!sk->sk_prot->enter_memory_pressure)
return;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
struct cg_proto *cg_proto = sk->sk_cgrp;
struct proto *prot = sk->sk_prot;
for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
cg_proto->memory_pressure = 1;
}
sk->sk_prot->enter_memory_pressure(sk);
}
static inline long sk_prot_mem_limits(const struct sock *sk, int index)
{
long *prot = sk->sk_prot->sysctl_mem;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
prot = sk->sk_cgrp->sysctl_mem;
return prot[index];
}
static inline void memcg_memory_allocated_add(struct cg_proto *prot,
unsigned long amt,
int *parent_status)
{
page_counter_charge(&prot->memory_allocated, amt);
if (page_counter_read(&prot->memory_allocated) >
prot->memory_allocated.limit)
*parent_status = OVER_LIMIT;
}
static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
unsigned long amt)
{
page_counter_uncharge(&prot->memory_allocated, amt);
}
static inline long
sk_memory_allocated(const struct sock *sk)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
return page_counter_read(&sk->sk_cgrp->memory_allocated);
return atomic_long_read(prot->memory_allocated);
}
static inline long
sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
/* update the root cgroup regardless */
atomic_long_add_return(amt, prot->memory_allocated);
return page_counter_read(&sk->sk_cgrp->memory_allocated);
}
return atomic_long_add_return(amt, prot->memory_allocated);
}
static inline void
sk_memory_allocated_sub(struct sock *sk, int amt)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
memcg_memory_allocated_sub(sk->sk_cgrp, amt);
atomic_long_sub(amt, prot->memory_allocated);
}
static inline void sk_sockets_allocated_dec(struct sock *sk)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
struct cg_proto *cg_proto = sk->sk_cgrp;
for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
percpu_counter_dec(&cg_proto->sockets_allocated);
}
percpu_counter_dec(prot->sockets_allocated);
}
static inline void sk_sockets_allocated_inc(struct sock *sk)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
struct cg_proto *cg_proto = sk->sk_cgrp;
for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
percpu_counter_inc(&cg_proto->sockets_allocated);
}
percpu_counter_inc(prot->sockets_allocated);
}
static inline int
sk_sockets_allocated_read_positive(struct sock *sk)
{
struct proto *prot = sk->sk_prot;
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated);
return percpu_counter_read_positive(prot->sockets_allocated);
}
static inline int
proto_sockets_allocated_sum_positive(struct proto *prot)
{
return percpu_counter_sum_positive(prot->sockets_allocated);
}
static inline long
proto_memory_allocated(struct proto *prot)
{
return atomic_long_read(prot->memory_allocated);
}
static inline bool
proto_memory_pressure(struct proto *prot)
{
if (!prot->memory_pressure)
return false;
return !!*prot->memory_pressure;
}
#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
int sock_prot_inuse_get(struct net *net, struct proto *proto);
#else
static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
int inc)
{
}
#endif
/* With per-bucket locks this operation is not-atomic, so that
* this version is not worse.
*/
static inline void __sk_prot_rehash(struct sock *sk)
{
sk->sk_prot->unhash(sk);
sk->sk_prot->hash(sk);
}
void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
/* About 10 seconds */
#define SOCK_DESTROY_TIME (10*HZ)
/* Sockets 0-1023 can't be bound to unless you are superuser */
#define PROT_SOCK 1024
#define SHUTDOWN_MASK 3
#define RCV_SHUTDOWN 1
#define SEND_SHUTDOWN 2
#define SOCK_SNDBUF_LOCK 1
#define SOCK_RCVBUF_LOCK 2
#define SOCK_BINDADDR_LOCK 4
#define SOCK_BINDPORT_LOCK 8
/* sock_iocb: used to kick off async processing of socket ios */
struct sock_iocb {
struct list_head list;
int flags;
int size;
struct socket *sock;
struct sock *sk;
struct scm_cookie *scm;
struct msghdr *msg, async_msg;
struct kiocb *kiocb;
};
static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
{
return (struct sock_iocb *)iocb->private;
}
static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
{
return si->kiocb;
}
struct socket_alloc {
struct socket socket;
struct inode vfs_inode;
};
static inline struct socket *SOCKET_I(struct inode *inode)
{
return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
}
static inline struct inode *SOCK_INODE(struct socket *socket)
{
return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
}
/*
* Functions for memory accounting
*/
int __sk_mem_schedule(struct sock *sk, int size, int kind);
void __sk_mem_reclaim(struct sock *sk);
#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND 0
#define SK_MEM_RECV 1
static inline int sk_mem_pages(int amt)
{
return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
}
static inline bool sk_has_account(struct sock *sk)
{
/* return true if protocol supports memory accounting */
return !!sk->sk_prot->memory_allocated;
}
static inline bool sk_wmem_schedule(struct sock *sk, int size)
{
if (!sk_has_account(sk))
return true;
return size <= sk->sk_forward_alloc ||
__sk_mem_schedule(sk, size, SK_MEM_SEND);
}
static inline bool
sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
{
if (!sk_has_account(sk))
return true;
return size<= sk->sk_forward_alloc ||
__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
skb_pfmemalloc(skb);
}
static inline void sk_mem_reclaim(struct sock *sk)
{
if (!sk_has_account(sk))
return;
if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
__sk_mem_reclaim(sk);
}
static inline void sk_mem_reclaim_partial(struct sock *sk)
{
if (!sk_has_account(sk))
return;
if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
__sk_mem_reclaim(sk);
}
static inline void sk_mem_charge(struct sock *sk, int size)
{
if (!sk_has_account(sk))
return;
sk->sk_forward_alloc -= size;
}
static inline void sk_mem_uncharge(struct sock *sk, int size)
{
if (!sk_has_account(sk))
return;
sk->sk_forward_alloc += size;
}
static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
sk->sk_wmem_queued -= skb->truesize;
sk_mem_uncharge(sk, skb->truesize);
__kfree_skb(skb);
}
/* Used by processes to "lock" a socket state, so that
* interrupts and bottom half handlers won't change it
* from under us. It essentially blocks any incoming
* packets, so that we won't get any new data or any
* packets that change the state of the socket.
*
* While locked, BH processing will add new packets to
* the backlog queue. This queue is processed by the
* owner of the socket lock right before it is released.
*
* Since ~2.3.5 it is also exclusive sleep lock serializing
* accesses from user process context.
*/
#define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
static inline void sock_release_ownership(struct sock *sk)
{
sk->sk_lock.owned = 0;
}
/*
* Macro so as to not evaluate some arguments when
* lockdep is not enabled.
*
* Mark both the sk_lock and the sk_lock.slock as a
* per-address-family lock class.
*/
#define sock_lock_init_class_and_name(sk, sname, skey, name, key) \
do { \
sk->sk_lock.owned = 0; \
init_waitqueue_head(&sk->sk_lock.wq); \
spin_lock_init(&(sk)->sk_lock.slock); \
debug_check_no_locks_freed((void *)&(sk)->sk_lock, \
sizeof((sk)->sk_lock)); \
lockdep_set_class_and_name(&(sk)->sk_lock.slock, \
(skey), (sname)); \
lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
} while (0)
void lock_sock_nested(struct sock *sk, int subclass);
static inline void lock_sock(struct sock *sk)
{
lock_sock_nested(sk, 0);
}
void release_sock(struct sock *sk);
/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock))
#define bh_lock_sock_nested(__sk) \
spin_lock_nested(&((__sk)->sk_lock.slock), \
SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
bool lock_sock_fast(struct sock *sk);
/**
* unlock_sock_fast - complement of lock_sock_fast
* @sk: socket
* @slow: slow mode
*
* fast unlock socket for user context.
* If slow mode is on, we call regular release_sock()
*/
static inline void unlock_sock_fast(struct sock *sk, bool slow)
{
if (slow)
release_sock(sk);
else
spin_unlock_bh(&sk->sk_lock.slock);
}
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot);
void sk_free(struct sock *sk);
void sk_release_kernel(struct sock *sk);
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority);
void sock_wfree(struct sk_buff *skb);
void skb_orphan_partial(struct sk_buff *skb);
void sock_rfree(struct sk_buff *skb);
void sock_efree(struct sk_buff *skb);
#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb);
#else
#define sock_edemux(skb) sock_efree(skb)
#endif
int sock_setsockopt(struct socket *sock, int level, int op,
char __user *optval, unsigned int optlen);
int sock_getsockopt(struct socket *sock, int level, int op,
char __user *optval, int __user *optlen);
struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
int noblock, int *errcode);
struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
unsigned long data_len, int noblock,
int *errcode, int max_page_order);
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
void sock_kfree_s(struct sock *sk, void *mem, int size);
void sock_kzfree_s(struct sock *sk, void *mem, int size);
void sk_send_sigurg(struct sock *sk);
/*
* Functions to fill in entries in struct proto_ops when a protocol
* does not implement a particular function.
*/
int sock_no_bind(struct socket *, struct sockaddr *, int);
int sock_no_connect(struct socket *, struct sockaddr *, int, int);
int sock_no_socketpair(struct socket *, struct socket *);
int sock_no_accept(struct socket *, struct socket *, int);
int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
unsigned int sock_no_poll(struct file *, struct socket *,
struct poll_table_struct *);
int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
int sock_no_listen(struct socket *, int);
int sock_no_shutdown(struct socket *, int);
int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t);
int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
int);
int sock_no_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma);
ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags);
/*
* Functions to fill in entries in struct proto_ops when a protocol
* uses the inet style.
*/
int sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen);
int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags);
int sock_common_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen);
int compat_sock_common_getsockopt(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
int compat_sock_common_setsockopt(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
void sk_common_release(struct sock *sk);
/*
* Default socket callbacks and setup code
*/
/* Initialise core socket variables */
void sock_init_data(struct socket *sock, struct sock *sk);
/*
* Socket reference counting postulates.
*
* * Each user of socket SHOULD hold a reference count.
* * Each access point to socket (an hash table bucket, reference from a list,
* running timer, skb in flight MUST hold a reference count.
* * When reference count hits 0, it means it will never increase back.
* * When reference count hits 0, it means that no references from
* outside exist to this socket and current process on current CPU
* is last user and may/should destroy this socket.
* * sk_free is called from any context: process, BH, IRQ. When
* it is called, socket has no references from outside -> sk_free
* may release descendant resources allocated by the socket, but
* to the time when it is called, socket is NOT referenced by any
* hash tables, lists etc.
* * Packets, delivered from outside (from network or from another process)
* and enqueued on receive/error queues SHOULD NOT grab reference count,
* when they sit in queue. Otherwise, packets will leak to hole, when
* socket is looked up by one cpu and unhasing is made by another CPU.
* It is true for udp/raw, netlink (leak to receive and error queues), tcp
* (leak to backlog). Packet socket does all the processing inside
* BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
* use separate SMP lock, so that they are prone too.
*/
/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
if (atomic_dec_and_test(&sk->sk_refcnt))
sk_free(sk);
}
/* Generic version of sock_put(), dealing with all sockets
* (TCP_TIMEWAIT, ESTABLISHED...)
*/
void sock_gen_put(struct sock *sk);
int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
{
sk->sk_tx_queue_mapping = tx_queue;
}
static inline void sk_tx_queue_clear(struct sock *sk)
{
sk->sk_tx_queue_mapping = -1;
}
static inline int sk_tx_queue_get(const struct sock *sk)
{
return sk ? sk->sk_tx_queue_mapping : -1;
}
static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
sk_tx_queue_clear(sk);
sk->sk_socket = sock;
}
static inline wait_queue_head_t *sk_sleep(struct sock *sk)
{
BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
return &rcu_dereference_raw(sk->sk_wq)->wait;
}
/* Detach socket from process context.
* Announce socket dead, detach it from wait queue and inode.
* Note that parent inode held reference count on this struct sock,
* we do not release it in this function, because protocol
* probably wants some additional cleanups or even continuing
* to work with this socket (TCP).
*/
static inline void sock_orphan(struct sock *sk)
{
write_lock_bh(&sk->sk_callback_lock);
sock_set_flag(sk, SOCK_DEAD);
sk_set_socket(sk, NULL);
sk->sk_wq = NULL;
write_unlock_bh(&sk->sk_callback_lock);
}
static inline void sock_graft(struct sock *sk, struct socket *parent)
{
write_lock_bh(&sk->sk_callback_lock);
sk->sk_wq = parent->wq;
parent->sk = sk;
sk_set_socket(sk, parent);
security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) ||
lockdep_is_held(&sk->sk_lock.slock));
}
static inline struct dst_entry *
sk_dst_get(struct sock *sk)
{
struct dst_entry *dst;
rcu_read_lock();
dst = rcu_dereference(sk->sk_dst_cache);
if (dst && !atomic_inc_not_zero(&dst->__refcnt))
dst = NULL;
rcu_read_unlock();
return dst;
}
static inline void dst_negative_advice(struct sock *sk)
{
struct dst_entry *ndst, *dst = __sk_dst_get(sk);
if (dst && dst->ops->negative_advice) {
ndst = dst->ops->negative_advice(dst);
if (ndst != dst) {
rcu_assign_pointer(sk->sk_dst_cache, ndst);
sk_tx_queue_clear(sk);
}
}
}
static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
struct dst_entry *old_dst;
sk_tx_queue_clear(sk);
/*
* This can be called while sk is owned by the caller only,
* with no state that can be checked in a rcu_dereference_check() cond
*/
old_dst = rcu_dereference_raw(sk->sk_dst_cache);
rcu_assign_pointer(sk->sk_dst_cache, dst);
dst_release(old_dst);
}
static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
struct dst_entry *old_dst;
sk_tx_queue_clear(sk);
old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
dst_release(old_dst);
}
static inline void
__sk_dst_reset(struct sock *sk)
{
__sk_dst_set(sk, NULL);
}
static inline void
sk_dst_reset(struct sock *sk)
{
sk_dst_set(sk, NULL);
}
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
static inline bool sk_can_gso(const struct sock *sk)
{
return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}
void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
{
sk->sk_route_nocaps |= flags;
sk->sk_route_caps &= ~flags;
}
static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
char __user *from, char *to,
int copy, int offset)
{
if (skb->ip_summed == CHECKSUM_NONE) {
int err = 0;
__wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
if (err)
return err;
skb->csum = csum_block_add(skb->csum, csum, offset);
} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
if (!access_ok(VERIFY_READ, from, copy) ||
__copy_from_user_nocache(to, from, copy))
return -EFAULT;
} else if (copy_from_user(to, from, copy))
return -EFAULT;
return 0;
}
static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
char __user *from, int copy)
{
int err, offset = skb->len;
err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
copy, offset);
if (err)
__skb_trim(skb, offset);
return err;
}
static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
struct sk_buff *skb,
struct page *page,
int off, int copy)
{
int err;
err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
copy, skb->len);
if (err)
return err;
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
sk->sk_wmem_queued += copy;
sk_mem_charge(sk, copy);
return 0;
}
/**
* sk_wmem_alloc_get - returns write allocations
* @sk: socket
*
* Returns sk_wmem_alloc minus initial offset of one
*/
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
return atomic_read(&sk->sk_wmem_alloc) - 1;
}
/**
* sk_rmem_alloc_get - returns read allocations
* @sk: socket
*
* Returns sk_rmem_alloc
*/
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
return atomic_read(&sk->sk_rmem_alloc);
}
/**
* sk_has_allocations - check if allocations are outstanding
* @sk: socket
*
* Returns true if socket has write or read allocations
*/
static inline bool sk_has_allocations(const struct sock *sk)
{
return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}
/**
* wq_has_sleeper - check if there are any waiting processes
* @wq: struct socket_wq
*
* Returns true if socket_wq has waiting processes
*
* The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
* barrier call. They were added due to the race found within the tcp code.
*
* Consider following tcp code paths:
*
* CPU1 CPU2
*
* sys_select receive packet
* ... ...
* __add_wait_queue update tp->rcv_nxt
* ... ...
* tp->rcv_nxt check sock_def_readable
* ... {
* schedule rcu_read_lock();
* wq = rcu_dereference(sk->sk_wq);
* if (wq && waitqueue_active(&wq->wait))
* wake_up_interruptible(&wq->wait)
* ...
* }
*
* The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
* in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1
* could then endup calling schedule and sleep forever if there are no more
* data on the socket.
*
*/
static inline bool wq_has_sleeper(struct socket_wq *wq)
{
/* We need to be sure we are in sync with the
* add_wait_queue modifications to the wait queue.
*
* This memory barrier is paired in the sock_poll_wait.
*/
smp_mb();
return wq && waitqueue_active(&wq->wait);
}
/**
* sock_poll_wait - place memory barrier behind the poll_wait call.
* @filp: file
* @wait_address: socket wait queue
* @p: poll_table
*
* See the comments in the wq_has_sleeper function.
*/
static inline void sock_poll_wait(struct file *filp,
wait_queue_head_t *wait_address, poll_table *p)
{
if (!poll_does_not_wait(p) && wait_address) {
poll_wait(filp, wait_address, p);
/* We need to be sure we are in sync with the
* socket flags modification.
*
* This memory barrier is paired in the wq_has_sleeper.
*/
smp_mb();
}
}
static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
{
if (sk->sk_txhash) {
skb->l4_hash = 1;
skb->hash = sk->sk_txhash;
}
}
/*
* Queue a received datagram if it will fit. Stream and sequenced
* protocols can't normally use this as they need to fit buffers in
* and play with them.
*
* Inlined as it's very short and called for pretty much every
* packet ever received.
*/
static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
skb_orphan(skb);
skb->sk = sk;
skb->destructor = sock_wfree;
skb_set_hash_from_sk(skb, sk);
/*
* We used to take a refcount on sk, but following operation
* is enough to guarantee sk_free() wont free this sock until
* all in-flight packets are completed
*/
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}
static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
skb_orphan(skb);
skb->sk = sk;
skb->destructor = sock_rfree;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
void sk_reset_timer(struct sock *sk, struct timer_list *timer,
unsigned long expires);
void sk_stop_timer(struct sock *sk, struct timer_list *timer);
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
/*
* Recover an error report and clear atomically
*/
static inline int sock_error(struct sock *sk)
{
int err;
if (likely(!sk->sk_err))
return 0;
err = xchg(&sk->sk_err, 0);
return -err;
}
static inline unsigned long sock_wspace(struct sock *sk)
{
int amt = 0;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
if (amt < 0)
amt = 0;
}
return amt;
}
static inline void sk_wake_async(struct sock *sk, int how, int band)
{
if (sock_flag(sk, SOCK_FASYNC))
sock_wake_async(sk->sk_socket, how, band);
}
/* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
* need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak.
* Note: for send buffers, TCP works better if we can build two skbs at
* minimum.
*/
#define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff)))
#define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2)
#define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE
static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF);
}
}
struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);
/**
* sk_page_frag - return an appropriate page_frag
* @sk: socket
*
* If socket allocation mode allows current thread to sleep, it means its
* safe to use the per task page_frag instead of the per socket one.
*/
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
if (sk->sk_allocation & __GFP_WAIT)
return ¤t->task_frag;
return &sk->sk_frag;
}
bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
/*
* Default write policy as shown to user space via poll/select/SIGIO
*/
static inline bool sock_writeable(const struct sock *sk)
{
return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
}
static inline gfp_t gfp_any(void)
{
return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}
static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
{
return noblock ? 0 : sk->sk_rcvtimeo;
}
static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
{
return noblock ? 0 : sk->sk_sndtimeo;
}
static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
}
/* Alas, with timeout socket operations are not restartable.
* Compare this to poll().
*/
static inline int sock_intr_errno(long timeo)
{
return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}
void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb);
void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb);
static inline void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
ktime_t kt = skb->tstamp;
struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
/*
* generate control messages if
* - receive time stamping in software requested
* - software time stamp available and wanted
* - hardware time stamps available and wanted
*/
if (sock_flag(sk, SOCK_RCVTSTAMP) ||
(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
(kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
(hwtstamps->hwtstamp.tv64 &&
(sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
__sock_recv_timestamp(msg, sk, skb);
else
sk->sk_stamp = kt;
if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
__sock_recv_wifi_status(msg, sk, skb);
}
void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb);
static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
(1UL << SOCK_RCVTSTAMP))
#define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \
SOF_TIMESTAMPING_RAW_HARDWARE)
if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
__sock_recv_ts_and_drops(msg, sk, skb);
else
sk->sk_stamp = skb->tstamp;
}
void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
/**
* sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
* @sk: socket sending this packet
* @tx_flags: completed with instructions for time stamping
*
* Note : callers should take care of initial *tx_flags value (usually 0)
*/
static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
{
if (unlikely(sk->sk_tsflags))
__sock_tx_timestamp(sk, tx_flags);
if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
*tx_flags |= SKBTX_WIFI_STATUS;
}
/**
* sk_eat_skb - Release a skb if it is no longer needed
* @sk: socket to eat this skb from
* @skb: socket buffer to eat
*
* This routine must be called with interrupts disabled or with the socket
* locked so that the sk_buff queue operation is ok.
*/
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
{
__skb_unlink(skb, &sk->sk_receive_queue);
__kfree_skb(skb);
}
static inline
struct net *sock_net(const struct sock *sk)
{
return read_pnet(&sk->sk_net);
}
static inline
void sock_net_set(struct sock *sk, struct net *net)
{
write_pnet(&sk->sk_net, net);
}
/*
* Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
* They should not hold a reference to a namespace in order to allow
* to stop it.
* Sockets after sk_change_net should be released using sk_release_kernel
*/
static inline void sk_change_net(struct sock *sk, struct net *net)
{
struct net *current_net = sock_net(sk);
if (!net_eq(current_net, net)) {
put_net(current_net);
sock_net_set(sk, hold_net(net));
}
}
static inline struct sock *skb_steal_sock(struct sk_buff *skb)
{
if (skb->sk) {
struct sock *sk = skb->sk;
skb->destructor = NULL;
skb->sk = NULL;
return sk;
}
return NULL;
}
void sock_enable_timestamp(struct sock *sk, int flag);
int sock_get_timestamp(struct sock *, struct timeval __user *);
int sock_get_timestampns(struct sock *, struct timespec __user *);
int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
int type);
bool sk_ns_capable(const struct sock *sk,
struct user_namespace *user_ns, int cap);
bool sk_capable(const struct sock *sk, int cap);
bool sk_net_capable(const struct sock *sk, int cap);
extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;
extern int sysctl_optmem_max;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
#endif /* _SOCK_H */