summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/helpers.c
blob: 5b278a38ae5829018bd80c1d6507ac8b147a2e6a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 */
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf-cgroup.h>
#include <linux/cgroup.h>
#include <linux/rcupdate.h>
#include <linux/random.h>
#include <linux/smp.h>
#include <linux/topology.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/uidgid.h>
#include <linux/filter.h>
#include <linux/ctype.h>
#include <linux/jiffies.h>
#include <linux/pid_namespace.h>
#include <linux/poison.h>
#include <linux/proc_ns.h>
#include <linux/security.h>
#include <linux/btf_ids.h>
#include <linux/bpf_mem_alloc.h>

#include "../../lib/kstrtox.h"

/* If kernel subsystem is allowing eBPF programs to call this function,
 * inside its own verifier_ops->get_func_proto() callback it should return
 * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
 *
 * Different map implementations will rely on rcu in map methods
 * lookup/update/delete, therefore eBPF programs must run under rcu lock
 * if program is allowed to access maps, so check rcu_read_lock_held in
 * all three functions.
 */
BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
{
	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
	return (unsigned long) map->ops->map_lookup_elem(map, key);
}

const struct bpf_func_proto bpf_map_lookup_elem_proto = {
	.func		= bpf_map_lookup_elem,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_KEY,
};

BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
	   void *, value, u64, flags)
{
	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
	return map->ops->map_update_elem(map, key, value, flags);
}

const struct bpf_func_proto bpf_map_update_elem_proto = {
	.func		= bpf_map_update_elem,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_KEY,
	.arg3_type	= ARG_PTR_TO_MAP_VALUE,
	.arg4_type	= ARG_ANYTHING,
};

BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
{
	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
	return map->ops->map_delete_elem(map, key);
}

const struct bpf_func_proto bpf_map_delete_elem_proto = {
	.func		= bpf_map_delete_elem,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_KEY,
};

BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags)
{
	return map->ops->map_push_elem(map, value, flags);
}

const struct bpf_func_proto bpf_map_push_elem_proto = {
	.func		= bpf_map_push_elem,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_VALUE,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
{
	return map->ops->map_pop_elem(map, value);
}

const struct bpf_func_proto bpf_map_pop_elem_proto = {
	.func		= bpf_map_pop_elem,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
};

BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
{
	return map->ops->map_peek_elem(map, value);
}

const struct bpf_func_proto bpf_map_peek_elem_proto = {
	.func		= bpf_map_peek_elem,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
};

BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
{
	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
	return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu);
}

const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = {
	.func		= bpf_map_lookup_percpu_elem,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_MAP_KEY,
	.arg3_type	= ARG_ANYTHING,
};

const struct bpf_func_proto bpf_get_prandom_u32_proto = {
	.func		= bpf_user_rnd_u32,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_get_smp_processor_id)
{
	return smp_processor_id();
}

const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
	.func		= bpf_get_smp_processor_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_get_numa_node_id)
{
	return numa_node_id();
}

const struct bpf_func_proto bpf_get_numa_node_id_proto = {
	.func		= bpf_get_numa_node_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_ktime_get_ns)
{
	/* NMI safe access to clock monotonic */
	return ktime_get_mono_fast_ns();
}

const struct bpf_func_proto bpf_ktime_get_ns_proto = {
	.func		= bpf_ktime_get_ns,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_ktime_get_boot_ns)
{
	/* NMI safe access to clock boottime */
	return ktime_get_boot_fast_ns();
}

const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
	.func		= bpf_ktime_get_boot_ns,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_ktime_get_coarse_ns)
{
	return ktime_get_coarse_ns();
}

const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
	.func		= bpf_ktime_get_coarse_ns,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_ktime_get_tai_ns)
{
	/* NMI safe access to clock tai */
	return ktime_get_tai_fast_ns();
}

const struct bpf_func_proto bpf_ktime_get_tai_ns_proto = {
	.func		= bpf_ktime_get_tai_ns,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_get_current_pid_tgid)
{
	struct task_struct *task = current;

	if (unlikely(!task))
		return -EINVAL;

	return (u64) task->tgid << 32 | task->pid;
}

const struct bpf_func_proto bpf_get_current_pid_tgid_proto = {
	.func		= bpf_get_current_pid_tgid,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_0(bpf_get_current_uid_gid)
{
	struct task_struct *task = current;
	kuid_t uid;
	kgid_t gid;

	if (unlikely(!task))
		return -EINVAL;

	current_uid_gid(&uid, &gid);
	return (u64) from_kgid(&init_user_ns, gid) << 32 |
		     from_kuid(&init_user_ns, uid);
}

const struct bpf_func_proto bpf_get_current_uid_gid_proto = {
	.func		= bpf_get_current_uid_gid,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size)
{
	struct task_struct *task = current;

	if (unlikely(!task))
		goto err_clear;

	/* Verifier guarantees that size > 0 */
	strscpy(buf, task->comm, size);
	return 0;
err_clear:
	memset(buf, 0, size);
	return -EINVAL;
}

const struct bpf_func_proto bpf_get_current_comm_proto = {
	.func		= bpf_get_current_comm,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE,
};

#if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK)

static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
{
	arch_spinlock_t *l = (void *)lock;
	union {
		__u32 val;
		arch_spinlock_t lock;
	} u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED };

	compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
	BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
	BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
	arch_spin_lock(l);
}

static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
{
	arch_spinlock_t *l = (void *)lock;

	arch_spin_unlock(l);
}

#else

static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
{
	atomic_t *l = (void *)lock;

	BUILD_BUG_ON(sizeof(*l) != sizeof(*lock));
	do {
		atomic_cond_read_relaxed(l, !VAL);
	} while (atomic_xchg(l, 1));
}

static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
{
	atomic_t *l = (void *)lock;

	atomic_set_release(l, 0);
}

#endif

static DEFINE_PER_CPU(unsigned long, irqsave_flags);

static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock)
{
	unsigned long flags;

	local_irq_save(flags);
	__bpf_spin_lock(lock);
	__this_cpu_write(irqsave_flags, flags);
}

notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
{
	__bpf_spin_lock_irqsave(lock);
	return 0;
}

const struct bpf_func_proto bpf_spin_lock_proto = {
	.func		= bpf_spin_lock,
	.gpl_only	= false,
	.ret_type	= RET_VOID,
	.arg1_type	= ARG_PTR_TO_SPIN_LOCK,
	.arg1_btf_id    = BPF_PTR_POISON,
};

static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock)
{
	unsigned long flags;

	flags = __this_cpu_read(irqsave_flags);
	__bpf_spin_unlock(lock);
	local_irq_restore(flags);
}

notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
{
	__bpf_spin_unlock_irqrestore(lock);
	return 0;
}

const struct bpf_func_proto bpf_spin_unlock_proto = {
	.func		= bpf_spin_unlock,
	.gpl_only	= false,
	.ret_type	= RET_VOID,
	.arg1_type	= ARG_PTR_TO_SPIN_LOCK,
	.arg1_btf_id    = BPF_PTR_POISON,
};

void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
			   bool lock_src)
{
	struct bpf_spin_lock *lock;

	if (lock_src)
		lock = src + map->record->spin_lock_off;
	else
		lock = dst + map->record->spin_lock_off;
	preempt_disable();
	__bpf_spin_lock_irqsave(lock);
	copy_map_value(map, dst, src);
	__bpf_spin_unlock_irqrestore(lock);
	preempt_enable();
}

BPF_CALL_0(bpf_jiffies64)
{
	return get_jiffies_64();
}

const struct bpf_func_proto bpf_jiffies64_proto = {
	.func		= bpf_jiffies64,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{
	struct cgroup *cgrp;
	u64 cgrp_id;

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	cgrp_id = cgroup_id(cgrp);
	rcu_read_unlock();

	return cgrp_id;
}

const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
	.func		= bpf_get_current_cgroup_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level)
{
	struct cgroup *cgrp;
	struct cgroup *ancestor;
	u64 cgrp_id;

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	ancestor = cgroup_ancestor(cgrp, ancestor_level);
	cgrp_id = ancestor ? cgroup_id(ancestor) : 0;
	rcu_read_unlock();

	return cgrp_id;
}

const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = {
	.func		= bpf_get_current_ancestor_cgroup_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_ANYTHING,
};
#endif /* CONFIG_CGROUPS */

#define BPF_STRTOX_BASE_MASK 0x1F

static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags,
			  unsigned long long *res, bool *is_negative)
{
	unsigned int base = flags & BPF_STRTOX_BASE_MASK;
	const char *cur_buf = buf;
	size_t cur_len = buf_len;
	unsigned int consumed;
	size_t val_len;
	char str[64];

	if (!buf || !buf_len || !res || !is_negative)
		return -EINVAL;

	if (base != 0 && base != 8 && base != 10 && base != 16)
		return -EINVAL;

	if (flags & ~BPF_STRTOX_BASE_MASK)
		return -EINVAL;

	while (cur_buf < buf + buf_len && isspace(*cur_buf))
		++cur_buf;

	*is_negative = (cur_buf < buf + buf_len && *cur_buf == '-');
	if (*is_negative)
		++cur_buf;

	consumed = cur_buf - buf;
	cur_len -= consumed;
	if (!cur_len)
		return -EINVAL;

	cur_len = min(cur_len, sizeof(str) - 1);
	memcpy(str, cur_buf, cur_len);
	str[cur_len] = '\0';
	cur_buf = str;

	cur_buf = _parse_integer_fixup_radix(cur_buf, &base);
	val_len = _parse_integer(cur_buf, base, res);

	if (val_len & KSTRTOX_OVERFLOW)
		return -ERANGE;

	if (val_len == 0)
		return -EINVAL;

	cur_buf += val_len;
	consumed += cur_buf - str;

	return consumed;
}

static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
			 long long *res)
{
	unsigned long long _res;
	bool is_negative;
	int err;

	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
	if (err < 0)
		return err;
	if (is_negative) {
		if ((long long)-_res > 0)
			return -ERANGE;
		*res = -_res;
	} else {
		if ((long long)_res < 0)
			return -ERANGE;
		*res = _res;
	}
	return err;
}

BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
	   long *, res)
{
	long long _res;
	int err;

	err = __bpf_strtoll(buf, buf_len, flags, &_res);
	if (err < 0)
		return err;
	if (_res != (long)_res)
		return -ERANGE;
	*res = _res;
	return err;
}

const struct bpf_func_proto bpf_strtol_proto = {
	.func		= bpf_strtol,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
	.arg2_type	= ARG_CONST_SIZE,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_LONG,
};

BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
	   unsigned long *, res)
{
	unsigned long long _res;
	bool is_negative;
	int err;

	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
	if (err < 0)
		return err;
	if (is_negative)
		return -EINVAL;
	if (_res != (unsigned long)_res)
		return -ERANGE;
	*res = _res;
	return err;
}

const struct bpf_func_proto bpf_strtoul_proto = {
	.func		= bpf_strtoul,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
	.arg2_type	= ARG_CONST_SIZE,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_LONG,
};

BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
{
	return strncmp(s1, s2, s1_sz);
}

static const struct bpf_func_proto bpf_strncmp_proto = {
	.func		= bpf_strncmp,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM,
	.arg2_type	= ARG_CONST_SIZE,
	.arg3_type	= ARG_PTR_TO_CONST_STR,
};

BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
	   struct bpf_pidns_info *, nsdata, u32, size)
{
	struct task_struct *task = current;
	struct pid_namespace *pidns;
	int err = -EINVAL;

	if (unlikely(size != sizeof(struct bpf_pidns_info)))
		goto clear;

	if (unlikely((u64)(dev_t)dev != dev))
		goto clear;

	if (unlikely(!task))
		goto clear;

	pidns = task_active_pid_ns(task);
	if (unlikely(!pidns)) {
		err = -ENOENT;
		goto clear;
	}

	if (!ns_match(&pidns->ns, (dev_t)dev, ino))
		goto clear;

	nsdata->pid = task_pid_nr_ns(task, pidns);
	nsdata->tgid = task_tgid_nr_ns(task, pidns);
	return 0;
clear:
	memset((void *)nsdata, 0, (size_t) size);
	return err;
}

const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = {
	.func		= bpf_get_ns_current_pid_tgid,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_ANYTHING,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type      = ARG_PTR_TO_UNINIT_MEM,
	.arg4_type      = ARG_CONST_SIZE,
};

static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
	.func		= bpf_get_raw_cpu_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map,
	   u64, flags, void *, data, u64, size)
{
	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
		return -EINVAL;

	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
}

const struct bpf_func_proto bpf_event_output_data_proto =  {
	.func		= bpf_event_output_data,
	.gpl_only       = true,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
	.arg2_type      = ARG_CONST_MAP_PTR,
	.arg3_type      = ARG_ANYTHING,
	.arg4_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
};

BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size,
	   const void __user *, user_ptr)
{
	int ret = copy_from_user(dst, user_ptr, size);

	if (unlikely(ret)) {
		memset(dst, 0, size);
		ret = -EFAULT;
	}

	return ret;
}

const struct bpf_func_proto bpf_copy_from_user_proto = {
	.func		= bpf_copy_from_user,
	.gpl_only	= false,
	.might_sleep	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size,
	   const void __user *, user_ptr, struct task_struct *, tsk, u64, flags)
{
	int ret;

	/* flags is not used yet */
	if (unlikely(flags))
		return -EINVAL;

	if (unlikely(!size))
		return 0;

	ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0);
	if (ret == size)
		return 0;

	memset(dst, 0, size);
	/* Return -EFAULT for partial read */
	return ret < 0 ? ret : -EFAULT;
}

const struct bpf_func_proto bpf_copy_from_user_task_proto = {
	.func		= bpf_copy_from_user_task,
	.gpl_only	= true,
	.might_sleep	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_BTF_ID,
	.arg4_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
	.arg5_type	= ARG_ANYTHING
};

BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
{
	if (cpu >= nr_cpu_ids)
		return (unsigned long)NULL;

	return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu);
}

const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
	.func		= bpf_per_cpu_ptr,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
	.arg2_type	= ARG_ANYTHING,
};

BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
{
	return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr);
}

const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
	.func		= bpf_this_cpu_ptr,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
};

static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
		size_t bufsz)
{
	void __user *user_ptr = (__force void __user *)unsafe_ptr;

	buf[0] = 0;

	switch (fmt_ptype) {
	case 's':
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
		if ((unsigned long)unsafe_ptr < TASK_SIZE)
			return strncpy_from_user_nofault(buf, user_ptr, bufsz);
		fallthrough;
#endif
	case 'k':
		return strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
	case 'u':
		return strncpy_from_user_nofault(buf, user_ptr, bufsz);
	}

	return -EINVAL;
}

/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
 * arguments representation.
 */
#define MAX_BPRINTF_BIN_ARGS	512

/* Support executing three nested bprintf helper calls on a given CPU */
#define MAX_BPRINTF_NEST_LEVEL	3
struct bpf_bprintf_buffers {
	char bin_args[MAX_BPRINTF_BIN_ARGS];
	char buf[MAX_BPRINTF_BUF];
};

static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);

static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
{
	int nest_level;

	preempt_disable();
	nest_level = this_cpu_inc_return(bpf_bprintf_nest_level);
	if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) {
		this_cpu_dec(bpf_bprintf_nest_level);
		preempt_enable();
		return -EBUSY;
	}
	*bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]);

	return 0;
}

void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
{
	if (!data->bin_args && !data->buf)
		return;
	if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
		return;
	this_cpu_dec(bpf_bprintf_nest_level);
	preempt_enable();
}

/*
 * bpf_bprintf_prepare - Generic pass on format strings for bprintf-like helpers
 *
 * Returns a negative value if fmt is an invalid format string or 0 otherwise.
 *
 * This can be used in two ways:
 * - Format string verification only: when data->get_bin_args is false
 * - Arguments preparation: in addition to the above verification, it writes in
 *   data->bin_args a binary representation of arguments usable by bstr_printf
 *   where pointers from BPF have been sanitized.
 *
 * In argument preparation mode, if 0 is returned, safe temporary buffers are
 * allocated and bpf_bprintf_cleanup should be called to free them after use.
 */
int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
			u32 num_args, struct bpf_bprintf_data *data)
{
	bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
	char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end;
	struct bpf_bprintf_buffers *buffers = NULL;
	size_t sizeof_cur_arg, sizeof_cur_ip;
	int err, i, num_spec = 0;
	u64 cur_arg;
	char fmt_ptype, cur_ip[16], ip_spec[] = "%pXX";

	fmt_end = strnchr(fmt, fmt_size, 0);
	if (!fmt_end)
		return -EINVAL;
	fmt_size = fmt_end - fmt;

	if (get_buffers && try_get_buffers(&buffers))
		return -EBUSY;

	if (data->get_bin_args) {
		if (num_args)
			tmp_buf = buffers->bin_args;
		tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS;
		data->bin_args = (u32 *)tmp_buf;
	}

	if (data->get_buf)
		data->buf = buffers->buf;

	for (i = 0; i < fmt_size; i++) {
		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
			err = -EINVAL;
			goto out;
		}

		if (fmt[i] != '%')
			continue;

		if (fmt[i + 1] == '%') {
			i++;
			continue;
		}

		if (num_spec >= num_args) {
			err = -EINVAL;
			goto out;
		}

		/* The string is zero-terminated so if fmt[i] != 0, we can
		 * always access fmt[i + 1], in the worst case it will be a 0
		 */
		i++;

		/* skip optional "[0 +-][num]" width formatting field */
		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
		       fmt[i] == ' ')
			i++;
		if (fmt[i] >= '1' && fmt[i] <= '9') {
			i++;
			while (fmt[i] >= '0' && fmt[i] <= '9')
				i++;
		}

		if (fmt[i] == 'p') {
			sizeof_cur_arg = sizeof(long);

			if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
			    fmt[i + 2] == 's') {
				fmt_ptype = fmt[i + 1];
				i += 2;
				goto fmt_str;
			}

			if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
			    ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
			    fmt[i + 1] == 'x' || fmt[i + 1] == 's' ||
			    fmt[i + 1] == 'S') {
				/* just kernel pointers */
				if (tmp_buf)
					cur_arg = raw_args[num_spec];
				i++;
				goto nocopy_fmt;
			}

			if (fmt[i + 1] == 'B') {
				if (tmp_buf)  {
					err = snprintf(tmp_buf,
						       (tmp_buf_end - tmp_buf),
						       "%pB",
						       (void *)(long)raw_args[num_spec]);
					tmp_buf += (err + 1);
				}

				i++;
				num_spec++;
				continue;
			}

			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
			if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') ||
			    (fmt[i + 2] != '4' && fmt[i + 2] != '6')) {
				err = -EINVAL;
				goto out;
			}

			i += 2;
			if (!tmp_buf)
				goto nocopy_fmt;

			sizeof_cur_ip = (fmt[i] == '4') ? 4 : 16;
			if (tmp_buf_end - tmp_buf < sizeof_cur_ip) {
				err = -ENOSPC;
				goto out;
			}

			unsafe_ptr = (char *)(long)raw_args[num_spec];
			err = copy_from_kernel_nofault(cur_ip, unsafe_ptr,
						       sizeof_cur_ip);
			if (err < 0)
				memset(cur_ip, 0, sizeof_cur_ip);

			/* hack: bstr_printf expects IP addresses to be
			 * pre-formatted as strings, ironically, the easiest way
			 * to do that is to call snprintf.
			 */
			ip_spec[2] = fmt[i - 1];
			ip_spec[3] = fmt[i];
			err = snprintf(tmp_buf, tmp_buf_end - tmp_buf,
				       ip_spec, &cur_ip);

			tmp_buf += err + 1;
			num_spec++;

			continue;
		} else if (fmt[i] == 's') {
			fmt_ptype = fmt[i];
fmt_str:
			if (fmt[i + 1] != 0 &&
			    !isspace(fmt[i + 1]) &&
			    !ispunct(fmt[i + 1])) {
				err = -EINVAL;
				goto out;
			}

			if (!tmp_buf)
				goto nocopy_fmt;

			if (tmp_buf_end == tmp_buf) {
				err = -ENOSPC;
				goto out;
			}

			unsafe_ptr = (char *)(long)raw_args[num_spec];
			err = bpf_trace_copy_string(tmp_buf, unsafe_ptr,
						    fmt_ptype,
						    tmp_buf_end - tmp_buf);
			if (err < 0) {
				tmp_buf[0] = '\0';
				err = 1;
			}

			tmp_buf += err;
			num_spec++;

			continue;
		} else if (fmt[i] == 'c') {
			if (!tmp_buf)
				goto nocopy_fmt;

			if (tmp_buf_end == tmp_buf) {
				err = -ENOSPC;
				goto out;
			}

			*tmp_buf = raw_args[num_spec];
			tmp_buf++;
			num_spec++;

			continue;
		}

		sizeof_cur_arg = sizeof(int);

		if (fmt[i] == 'l') {
			sizeof_cur_arg = sizeof(long);
			i++;
		}
		if (fmt[i] == 'l') {
			sizeof_cur_arg = sizeof(long long);
			i++;
		}

		if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' &&
		    fmt[i] != 'x' && fmt[i] != 'X') {
			err = -EINVAL;
			goto out;
		}

		if (tmp_buf)
			cur_arg = raw_args[num_spec];
nocopy_fmt:
		if (tmp_buf) {
			tmp_buf = PTR_ALIGN(tmp_buf, sizeof(u32));
			if (tmp_buf_end - tmp_buf < sizeof_cur_arg) {
				err = -ENOSPC;
				goto out;
			}

			if (sizeof_cur_arg == 8) {
				*(u32 *)tmp_buf = *(u32 *)&cur_arg;
				*(u32 *)(tmp_buf + 4) = *((u32 *)&cur_arg + 1);
			} else {
				*(u32 *)tmp_buf = (u32)(long)cur_arg;
			}
			tmp_buf += sizeof_cur_arg;
		}
		num_spec++;
	}

	err = 0;
out:
	if (err)
		bpf_bprintf_cleanup(data);
	return err;
}

BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
	   const void *, args, u32, data_len)
{
	struct bpf_bprintf_data data = {
		.get_bin_args	= true,
	};
	int err, num_args;

	if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 ||
	    (data_len && !args))
		return -EINVAL;
	num_args = data_len / 8;

	/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
	 * can safely give an unbounded size.
	 */
	err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data);
	if (err < 0)
		return err;

	err = bstr_printf(str, str_size, fmt, data.bin_args);

	bpf_bprintf_cleanup(&data);

	return err + 1;
}

const struct bpf_func_proto bpf_snprintf_proto = {
	.func		= bpf_snprintf,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_PTR_TO_CONST_STR,
	.arg4_type	= ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

/* BPF map elements can contain 'struct bpf_timer'.
 * Such map owns all of its BPF timers.
 * 'struct bpf_timer' is allocated as part of map element allocation
 * and it's zero initialized.
 * That space is used to keep 'struct bpf_timer_kern'.
 * bpf_timer_init() allocates 'struct bpf_hrtimer', inits hrtimer, and
 * remembers 'struct bpf_map *' pointer it's part of.
 * bpf_timer_set_callback() increments prog refcnt and assign bpf callback_fn.
 * bpf_timer_start() arms the timer.
 * If user space reference to a map goes to zero at this point
 * ops->map_release_uref callback is responsible for cancelling the timers,
 * freeing their memory, and decrementing prog's refcnts.
 * bpf_timer_cancel() cancels the timer and decrements prog's refcnt.
 * Inner maps can contain bpf timers as well. ops->map_release_uref is
 * freeing the timers when inner map is replaced or deleted by user space.
 */
struct bpf_hrtimer {
	struct hrtimer timer;
	struct bpf_map *map;
	struct bpf_prog *prog;
	void __rcu *callback_fn;
	void *value;
};

/* the actual struct hidden inside uapi struct bpf_timer */
struct bpf_timer_kern {
	struct bpf_hrtimer *timer;
	/* bpf_spin_lock is used here instead of spinlock_t to make
	 * sure that it always fits into space reserved by struct bpf_timer
	 * regardless of LOCKDEP and spinlock debug flags.
	 */
	struct bpf_spin_lock lock;
} __attribute__((aligned(8)));

static DEFINE_PER_CPU(struct bpf_hrtimer *, hrtimer_running);

static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
{
	struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer);
	struct bpf_map *map = t->map;
	void *value = t->value;
	bpf_callback_t callback_fn;
	void *key;
	u32 idx;

	BTF_TYPE_EMIT(struct bpf_timer);
	callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held());
	if (!callback_fn)
		goto out;

	/* bpf_timer_cb() runs in hrtimer_run_softirq. It doesn't migrate and
	 * cannot be preempted by another bpf_timer_cb() on the same cpu.
	 * Remember the timer this callback is servicing to prevent
	 * deadlock if callback_fn() calls bpf_timer_cancel() or
	 * bpf_map_delete_elem() on the same timer.
	 */
	this_cpu_write(hrtimer_running, t);
	if (map->map_type == BPF_MAP_TYPE_ARRAY) {
		struct bpf_array *array = container_of(map, struct bpf_array, map);

		/* compute the key */
		idx = ((char *)value - array->value) / array->elem_size;
		key = &idx;
	} else { /* hash or lru */
		key = value - round_up(map->key_size, 8);
	}

	callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0);
	/* The verifier checked that return value is zero. */

	this_cpu_write(hrtimer_running, NULL);
out:
	return HRTIMER_NORESTART;
}

BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map,
	   u64, flags)
{
	clockid_t clockid = flags & (MAX_CLOCKS - 1);
	struct bpf_hrtimer *t;
	int ret = 0;

	BUILD_BUG_ON(MAX_CLOCKS != 16);
	BUILD_BUG_ON(sizeof(struct bpf_timer_kern) > sizeof(struct bpf_timer));
	BUILD_BUG_ON(__alignof__(struct bpf_timer_kern) != __alignof__(struct bpf_timer));

	if (in_nmi())
		return -EOPNOTSUPP;

	if (flags >= MAX_CLOCKS ||
	    /* similar to timerfd except _ALARM variants are not supported */
	    (clockid != CLOCK_MONOTONIC &&
	     clockid != CLOCK_REALTIME &&
	     clockid != CLOCK_BOOTTIME))
		return -EINVAL;
	__bpf_spin_lock_irqsave(&timer->lock);
	t = timer->timer;
	if (t) {
		ret = -EBUSY;
		goto out;
	}
	if (!atomic64_read(&map->usercnt)) {
		/* maps with timers must be either held by user space
		 * or pinned in bpffs.
		 */
		ret = -EPERM;
		goto out;
	}
	/* allocate hrtimer via map_kmalloc to use memcg accounting */
	t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
	if (!t) {
		ret = -ENOMEM;
		goto out;
	}
	t->value = (void *)timer - map->record->timer_off;
	t->map = map;
	t->prog = NULL;
	rcu_assign_pointer(t->callback_fn, NULL);
	hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
	t->timer.function = bpf_timer_cb;
	timer->timer = t;
out:
	__bpf_spin_unlock_irqrestore(&timer->lock);
	return ret;
}

static const struct bpf_func_proto bpf_timer_init_proto = {
	.func		= bpf_timer_init,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_TIMER,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callback_fn,
	   struct bpf_prog_aux *, aux)
{
	struct bpf_prog *prev, *prog = aux->prog;
	struct bpf_hrtimer *t;
	int ret = 0;

	if (in_nmi())
		return -EOPNOTSUPP;
	__bpf_spin_lock_irqsave(&timer->lock);
	t = timer->timer;
	if (!t) {
		ret = -EINVAL;
		goto out;
	}
	if (!atomic64_read(&t->map->usercnt)) {
		/* maps with timers must be either held by user space
		 * or pinned in bpffs. Otherwise timer might still be
		 * running even when bpf prog is detached and user space
		 * is gone, since map_release_uref won't ever be called.
		 */
		ret = -EPERM;
		goto out;
	}
	prev = t->prog;
	if (prev != prog) {
		/* Bump prog refcnt once. Every bpf_timer_set_callback()
		 * can pick different callback_fn-s within the same prog.
		 */
		prog = bpf_prog_inc_not_zero(prog);
		if (IS_ERR(prog)) {
			ret = PTR_ERR(prog);
			goto out;
		}
		if (prev)
			/* Drop prev prog refcnt when swapping with new prog */
			bpf_prog_put(prev);
		t->prog = prog;
	}
	rcu_assign_pointer(t->callback_fn, callback_fn);
out:
	__bpf_spin_unlock_irqrestore(&timer->lock);
	return ret;
}

static const struct bpf_func_proto bpf_timer_set_callback_proto = {
	.func		= bpf_timer_set_callback,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_TIMER,
	.arg2_type	= ARG_PTR_TO_FUNC,
};

BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, flags)
{
	struct bpf_hrtimer *t;
	int ret = 0;

	if (in_nmi())
		return -EOPNOTSUPP;
	if (flags)
		return -EINVAL;
	__bpf_spin_lock_irqsave(&timer->lock);
	t = timer->timer;
	if (!t || !t->prog) {
		ret = -EINVAL;
		goto out;
	}
	hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT);
out:
	__bpf_spin_unlock_irqrestore(&timer->lock);
	return ret;
}

static const struct bpf_func_proto bpf_timer_start_proto = {
	.func		= bpf_timer_start,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_TIMER,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
};

static void drop_prog_refcnt(struct bpf_hrtimer *t)
{
	struct bpf_prog *prog = t->prog;

	if (prog) {
		bpf_prog_put(prog);
		t->prog = NULL;
		rcu_assign_pointer(t->callback_fn, NULL);
	}
}

BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer)
{
	struct bpf_hrtimer *t;
	int ret = 0;

	if (in_nmi())
		return -EOPNOTSUPP;
	__bpf_spin_lock_irqsave(&timer->lock);
	t = timer->timer;
	if (!t) {
		ret = -EINVAL;
		goto out;
	}
	if (this_cpu_read(hrtimer_running) == t) {
		/* If bpf callback_fn is trying to bpf_timer_cancel()
		 * its own timer the hrtimer_cancel() will deadlock
		 * since it waits for callback_fn to finish
		 */
		ret = -EDEADLK;
		goto out;
	}
	drop_prog_refcnt(t);
out:
	__bpf_spin_unlock_irqrestore(&timer->lock);
	/* Cancel the timer and wait for associated callback to finish
	 * if it was running.
	 */
	ret = ret ?: hrtimer_cancel(&t->timer);
	return ret;
}

static const struct bpf_func_proto bpf_timer_cancel_proto = {
	.func		= bpf_timer_cancel,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_TIMER,
};

/* This function is called by map_delete/update_elem for individual element and
 * by ops->map_release_uref when the user space reference to a map reaches zero.
 */
void bpf_timer_cancel_and_free(void *val)
{
	struct bpf_timer_kern *timer = val;
	struct bpf_hrtimer *t;

	/* Performance optimization: read timer->timer without lock first. */
	if (!READ_ONCE(timer->timer))
		return;

	__bpf_spin_lock_irqsave(&timer->lock);
	/* re-read it under lock */
	t = timer->timer;
	if (!t)
		goto out;
	drop_prog_refcnt(t);
	/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
	 * this timer, since it won't be initialized.
	 */
	timer->timer = NULL;
out:
	__bpf_spin_unlock_irqrestore(&timer->lock);
	if (!t)
		return;
	/* Cancel the timer and wait for callback to complete if it was running.
	 * If hrtimer_cancel() can be safely called it's safe to call kfree(t)
	 * right after for both preallocated and non-preallocated maps.
	 * The timer->timer = NULL was already done and no code path can
	 * see address 't' anymore.
	 *
	 * Check that bpf_map_delete/update_elem() wasn't called from timer
	 * callback_fn. In such case don't call hrtimer_cancel() (since it will
	 * deadlock) and don't call hrtimer_try_to_cancel() (since it will just
	 * return -1). Though callback_fn is still running on this cpu it's
	 * safe to do kfree(t) because bpf_timer_cb() read everything it needed
	 * from 't'. The bpf subprog callback_fn won't be able to access 't',
	 * since timer->timer = NULL was already done. The timer will be
	 * effectively cancelled because bpf_timer_cb() will return
	 * HRTIMER_NORESTART.
	 */
	if (this_cpu_read(hrtimer_running) != t)
		hrtimer_cancel(&t->timer);
	kfree(t);
}

BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
{
	unsigned long *kptr = map_value;

	return xchg(kptr, (unsigned long)ptr);
}

/* Unlike other PTR_TO_BTF_ID helpers the btf_id in bpf_kptr_xchg()
 * helper is determined dynamically by the verifier. Use BPF_PTR_POISON to
 * denote type that verifier will determine.
 */
static const struct bpf_func_proto bpf_kptr_xchg_proto = {
	.func         = bpf_kptr_xchg,
	.gpl_only     = false,
	.ret_type     = RET_PTR_TO_BTF_ID_OR_NULL,
	.ret_btf_id   = BPF_PTR_POISON,
	.arg1_type    = ARG_PTR_TO_KPTR,
	.arg2_type    = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE,
	.arg2_btf_id  = BPF_PTR_POISON,
};

/* Since the upper 8 bits of dynptr->size is reserved, the
 * maximum supported size is 2^24 - 1.
 */
#define DYNPTR_MAX_SIZE	((1UL << 24) - 1)
#define DYNPTR_TYPE_SHIFT	28
#define DYNPTR_SIZE_MASK	0xFFFFFF
#define DYNPTR_RDONLY_BIT	BIT(31)

static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr)
{
	return ptr->size & DYNPTR_RDONLY_BIT;
}

static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type)
{
	ptr->size |= type << DYNPTR_TYPE_SHIFT;
}

u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr)
{
	return ptr->size & DYNPTR_SIZE_MASK;
}

int bpf_dynptr_check_size(u32 size)
{
	return size > DYNPTR_MAX_SIZE ? -E2BIG : 0;
}

void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
		     enum bpf_dynptr_type type, u32 offset, u32 size)
{
	ptr->data = data;
	ptr->offset = offset;
	ptr->size = size;
	bpf_dynptr_set_type(ptr, type);
}

void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
{
	memset(ptr, 0, sizeof(*ptr));
}

static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
{
	u32 size = bpf_dynptr_get_size(ptr);

	if (len > size || offset > size - len)
		return -E2BIG;

	return 0;
}

BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr)
{
	int err;

	BTF_TYPE_EMIT(struct bpf_dynptr);

	err = bpf_dynptr_check_size(size);
	if (err)
		goto error;

	/* flags is currently unsupported */
	if (flags) {
		err = -EINVAL;
		goto error;
	}

	bpf_dynptr_init(ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, size);

	return 0;

error:
	bpf_dynptr_set_null(ptr);
	return err;
}

static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
	.func		= bpf_dynptr_from_mem,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
};

BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
	   u32, offset, u64, flags)
{
	int err;

	if (!src->data || flags)
		return -EINVAL;

	err = bpf_dynptr_check_off_len(src, offset, len);
	if (err)
		return err;

	/* Source and destination may possibly overlap, hence use memmove to
	 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
	 * pointing to overlapping PTR_TO_MAP_VALUE regions.
	 */
	memmove(dst, src->data + src->offset + offset, len);

	return 0;
}

static const struct bpf_func_proto bpf_dynptr_read_proto = {
	.func		= bpf_dynptr_read,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_PTR_TO_DYNPTR | MEM_RDONLY,
	.arg4_type	= ARG_ANYTHING,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
	   u32, len, u64, flags)
{
	int err;

	if (!dst->data || flags || bpf_dynptr_is_rdonly(dst))
		return -EINVAL;

	err = bpf_dynptr_check_off_len(dst, offset, len);
	if (err)
		return err;

	/* Source and destination may possibly overlap, hence use memmove to
	 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
	 * pointing to overlapping PTR_TO_MAP_VALUE regions.
	 */
	memmove(dst->data + dst->offset + offset, src, len);

	return 0;
}

static const struct bpf_func_proto bpf_dynptr_write_proto = {
	.func		= bpf_dynptr_write,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_DYNPTR | MEM_RDONLY,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
{
	int err;

	if (!ptr->data)
		return 0;

	err = bpf_dynptr_check_off_len(ptr, offset, len);
	if (err)
		return 0;

	if (bpf_dynptr_is_rdonly(ptr))
		return 0;

	return (unsigned long)(ptr->data + ptr->offset + offset);
}

static const struct bpf_func_proto bpf_dynptr_data_proto = {
	.func		= bpf_dynptr_data,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_DYNPTR_MEM_OR_NULL,
	.arg1_type	= ARG_PTR_TO_DYNPTR | MEM_RDONLY,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_CONST_ALLOC_SIZE_OR_ZERO,
};

const struct bpf_func_proto bpf_get_current_task_proto __weak;
const struct bpf_func_proto bpf_get_current_task_btf_proto __weak;
const struct bpf_func_proto bpf_probe_read_user_proto __weak;
const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
const struct bpf_func_proto bpf_probe_read_kernel_proto __weak;
const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
const struct bpf_func_proto bpf_task_pt_regs_proto __weak;

const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_map_push_elem:
		return &bpf_map_push_elem_proto;
	case BPF_FUNC_map_pop_elem:
		return &bpf_map_pop_elem_proto;
	case BPF_FUNC_map_peek_elem:
		return &bpf_map_peek_elem_proto;
	case BPF_FUNC_map_lookup_percpu_elem:
		return &bpf_map_lookup_percpu_elem_proto;
	case BPF_FUNC_get_prandom_u32:
		return &bpf_get_prandom_u32_proto;
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_raw_smp_processor_id_proto;
	case BPF_FUNC_get_numa_node_id:
		return &bpf_get_numa_node_id_proto;
	case BPF_FUNC_tail_call:
		return &bpf_tail_call_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	case BPF_FUNC_ktime_get_boot_ns:
		return &bpf_ktime_get_boot_ns_proto;
	case BPF_FUNC_ktime_get_tai_ns:
		return &bpf_ktime_get_tai_ns_proto;
	case BPF_FUNC_ringbuf_output:
		return &bpf_ringbuf_output_proto;
	case BPF_FUNC_ringbuf_reserve:
		return &bpf_ringbuf_reserve_proto;
	case BPF_FUNC_ringbuf_submit:
		return &bpf_ringbuf_submit_proto;
	case BPF_FUNC_ringbuf_discard:
		return &bpf_ringbuf_discard_proto;
	case BPF_FUNC_ringbuf_query:
		return &bpf_ringbuf_query_proto;
	case BPF_FUNC_strncmp:
		return &bpf_strncmp_proto;
	case BPF_FUNC_strtol:
		return &bpf_strtol_proto;
	case BPF_FUNC_strtoul:
		return &bpf_strtoul_proto;
	default:
		break;
	}

	if (!bpf_capable())
		return NULL;

	switch (func_id) {
	case BPF_FUNC_spin_lock:
		return &bpf_spin_lock_proto;
	case BPF_FUNC_spin_unlock:
		return &bpf_spin_unlock_proto;
	case BPF_FUNC_jiffies64:
		return &bpf_jiffies64_proto;
	case BPF_FUNC_per_cpu_ptr:
		return &bpf_per_cpu_ptr_proto;
	case BPF_FUNC_this_cpu_ptr:
		return &bpf_this_cpu_ptr_proto;
	case BPF_FUNC_timer_init:
		return &bpf_timer_init_proto;
	case BPF_FUNC_timer_set_callback:
		return &bpf_timer_set_callback_proto;
	case BPF_FUNC_timer_start:
		return &bpf_timer_start_proto;
	case BPF_FUNC_timer_cancel:
		return &bpf_timer_cancel_proto;
	case BPF_FUNC_kptr_xchg:
		return &bpf_kptr_xchg_proto;
	case BPF_FUNC_for_each_map_elem:
		return &bpf_for_each_map_elem_proto;
	case BPF_FUNC_loop:
		return &bpf_loop_proto;
	case BPF_FUNC_user_ringbuf_drain:
		return &bpf_user_ringbuf_drain_proto;
	case BPF_FUNC_ringbuf_reserve_dynptr:
		return &bpf_ringbuf_reserve_dynptr_proto;
	case BPF_FUNC_ringbuf_submit_dynptr:
		return &bpf_ringbuf_submit_dynptr_proto;
	case BPF_FUNC_ringbuf_discard_dynptr:
		return &bpf_ringbuf_discard_dynptr_proto;
	case BPF_FUNC_dynptr_from_mem:
		return &bpf_dynptr_from_mem_proto;
	case BPF_FUNC_dynptr_read:
		return &bpf_dynptr_read_proto;
	case BPF_FUNC_dynptr_write:
		return &bpf_dynptr_write_proto;
	case BPF_FUNC_dynptr_data:
		return &bpf_dynptr_data_proto;
#ifdef CONFIG_CGROUPS
	case BPF_FUNC_cgrp_storage_get:
		return &bpf_cgrp_storage_get_proto;
	case BPF_FUNC_cgrp_storage_delete:
		return &bpf_cgrp_storage_delete_proto;
#endif
	default:
		break;
	}

	if (!perfmon_capable())
		return NULL;

	switch (func_id) {
	case BPF_FUNC_trace_printk:
		return bpf_get_trace_printk_proto();
	case BPF_FUNC_get_current_task:
		return &bpf_get_current_task_proto;
	case BPF_FUNC_get_current_task_btf:
		return &bpf_get_current_task_btf_proto;
	case BPF_FUNC_probe_read_user:
		return &bpf_probe_read_user_proto;
	case BPF_FUNC_probe_read_kernel:
		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
		       NULL : &bpf_probe_read_kernel_proto;
	case BPF_FUNC_probe_read_user_str:
		return &bpf_probe_read_user_str_proto;
	case BPF_FUNC_probe_read_kernel_str:
		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
		       NULL : &bpf_probe_read_kernel_str_proto;
	case BPF_FUNC_snprintf_btf:
		return &bpf_snprintf_btf_proto;
	case BPF_FUNC_snprintf:
		return &bpf_snprintf_proto;
	case BPF_FUNC_task_pt_regs:
		return &bpf_task_pt_regs_proto;
	case BPF_FUNC_trace_vprintk:
		return bpf_get_trace_vprintk_proto();
	default:
		return NULL;
	}
}

void bpf_list_head_free(const struct btf_field *field, void *list_head,
			struct bpf_spin_lock *spin_lock)
{
	struct list_head *head = list_head, *orig_head = list_head;

	BUILD_BUG_ON(sizeof(struct list_head) > sizeof(struct bpf_list_head));
	BUILD_BUG_ON(__alignof__(struct list_head) > __alignof__(struct bpf_list_head));

	/* Do the actual list draining outside the lock to not hold the lock for
	 * too long, and also prevent deadlocks if tracing programs end up
	 * executing on entry/exit of functions called inside the critical
	 * section, and end up doing map ops that call bpf_list_head_free for
	 * the same map value again.
	 */
	__bpf_spin_lock_irqsave(spin_lock);
	if (!head->next || list_empty(head))
		goto unlock;
	head = head->next;
unlock:
	INIT_LIST_HEAD(orig_head);
	__bpf_spin_unlock_irqrestore(spin_lock);

	while (head != orig_head) {
		void *obj = head;

		obj -= field->graph_root.node_offset;
		head = head->next;
		/* The contained type can also have resources, including a
		 * bpf_list_head which needs to be freed.
		 */
		bpf_obj_free_fields(field->graph_root.value_rec, obj);
		/* bpf_mem_free requires migrate_disable(), since we can be
		 * called from map free path as well apart from BPF program (as
		 * part of map ops doing bpf_obj_free_fields).
		 */
		migrate_disable();
		bpf_mem_free(&bpf_global_ma, obj);
		migrate_enable();
	}
}

/* Like rbtree_postorder_for_each_entry_safe, but 'pos' and 'n' are
 * 'rb_node *', so field name of rb_node within containing struct is not
 * needed.
 *
 * Since bpf_rb_tree's node type has a corresponding struct btf_field with
 * graph_root.node_offset, it's not necessary to know field name
 * or type of node struct
 */
#define bpf_rbtree_postorder_for_each_entry_safe(pos, n, root) \
	for (pos = rb_first_postorder(root); \
	    pos && ({ n = rb_next_postorder(pos); 1; }); \
	    pos = n)

void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
		      struct bpf_spin_lock *spin_lock)
{
	struct rb_root_cached orig_root, *root = rb_root;
	struct rb_node *pos, *n;
	void *obj;

	BUILD_BUG_ON(sizeof(struct rb_root_cached) > sizeof(struct bpf_rb_root));
	BUILD_BUG_ON(__alignof__(struct rb_root_cached) > __alignof__(struct bpf_rb_root));

	__bpf_spin_lock_irqsave(spin_lock);
	orig_root = *root;
	*root = RB_ROOT_CACHED;
	__bpf_spin_unlock_irqrestore(spin_lock);

	bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) {
		obj = pos;
		obj -= field->graph_root.node_offset;

		bpf_obj_free_fields(field->graph_root.value_rec, obj);

		migrate_disable();
		bpf_mem_free(&bpf_global_ma, obj);
		migrate_enable();
	}
}

__diag_push();
__diag_ignore_all("-Wmissing-prototypes",
		  "Global functions as their definitions will be in vmlinux BTF");

__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
{
	struct btf_struct_meta *meta = meta__ign;
	u64 size = local_type_id__k;
	void *p;

	p = bpf_mem_alloc(&bpf_global_ma, size);
	if (!p)
		return NULL;
	if (meta)
		bpf_obj_init(meta->field_offs, p);
	return p;
}

__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
{
	struct btf_struct_meta *meta = meta__ign;
	void *p = p__alloc;

	if (meta)
		bpf_obj_free_fields(meta->record, p);
	bpf_mem_free(&bpf_global_ma, p);
}

static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, bool tail)
{
	struct list_head *n = (void *)node, *h = (void *)head;

	if (unlikely(!h->next))
		INIT_LIST_HEAD(h);
	if (unlikely(!n->next))
		INIT_LIST_HEAD(n);
	tail ? list_add_tail(n, h) : list_add(n, h);
}

__bpf_kfunc void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node)
{
	return __bpf_list_add(node, head, false);
}

__bpf_kfunc void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node)
{
	return __bpf_list_add(node, head, true);
}

static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail)
{
	struct list_head *n, *h = (void *)head;

	if (unlikely(!h->next))
		INIT_LIST_HEAD(h);
	if (list_empty(h))
		return NULL;
	n = tail ? h->prev : h->next;
	list_del_init(n);
	return (struct bpf_list_node *)n;
}

__bpf_kfunc struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head)
{
	return __bpf_list_del(head, false);
}

__bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
{
	return __bpf_list_del(head, true);
}

__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
						  struct bpf_rb_node *node)
{
	struct rb_root_cached *r = (struct rb_root_cached *)root;
	struct rb_node *n = (struct rb_node *)node;

	rb_erase_cached(n, r);
	RB_CLEAR_NODE(n);
	return (struct bpf_rb_node *)n;
}

/* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF
 * program
 */
static void __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
			     void *less)
{
	struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node;
	bpf_callback_t cb = (bpf_callback_t)less;
	struct rb_node *parent = NULL;
	bool leftmost = true;

	while (*link) {
		parent = *link;
		if (cb((uintptr_t)node, (uintptr_t)parent, 0, 0, 0)) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = false;
		}
	}

	rb_link_node((struct rb_node *)node, parent, link);
	rb_insert_color_cached((struct rb_node *)node,
			       (struct rb_root_cached *)root, leftmost);
}

__bpf_kfunc void bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
				bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b))
{
	__bpf_rbtree_add(root, node, (void *)less);
}

__bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
{
	struct rb_root_cached *r = (struct rb_root_cached *)root;

	return (struct bpf_rb_node *)rb_first_cached(r);
}

/**
 * bpf_task_acquire - Acquire a reference to a task. A task acquired by this
 * kfunc which is not stored in a map as a kptr, must be released by calling
 * bpf_task_release().
 * @p: The task on which a reference is being acquired.
 */
__bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p)
{
	return get_task_struct(p);
}

/**
 * bpf_task_acquire_not_zero - Acquire a reference to a rcu task object. A task
 * acquired by this kfunc which is not stored in a map as a kptr, must be
 * released by calling bpf_task_release().
 * @p: The task on which a reference is being acquired.
 */
__bpf_kfunc struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p)
{
	/* For the time being this function returns NULL, as it's not currently
	 * possible to safely acquire a reference to a task with RCU protection
	 * using get_task_struct() and put_task_struct(). This is due to the
	 * slightly odd mechanics of p->rcu_users, and how task RCU protection
	 * works.
	 *
	 * A struct task_struct is refcounted by two different refcount_t
	 * fields:
	 *
	 * 1. p->usage:     The "true" refcount field which tracks a task's
	 *		    lifetime. The task is freed as soon as this
	 *		    refcount drops to 0.
	 *
	 * 2. p->rcu_users: An "RCU users" refcount field which is statically
	 *		    initialized to 2, and is co-located in a union with
	 *		    a struct rcu_head field (p->rcu). p->rcu_users
	 *		    essentially encapsulates a single p->usage
	 *		    refcount, and when p->rcu_users goes to 0, an RCU
	 *		    callback is scheduled on the struct rcu_head which
	 *		    decrements the p->usage refcount.
	 *
	 * There are two important implications to this task refcounting logic
	 * described above. The first is that
	 * refcount_inc_not_zero(&p->rcu_users) cannot be used anywhere, as
	 * after the refcount goes to 0, the RCU callback being scheduled will
	 * cause the memory backing the refcount to again be nonzero due to the
	 * fields sharing a union. The other is that we can't rely on RCU to
	 * guarantee that a task is valid in a BPF program. This is because a
	 * task could have already transitioned to being in the TASK_DEAD
	 * state, had its rcu_users refcount go to 0, and its rcu callback
	 * invoked in which it drops its single p->usage reference. At this
	 * point the task will be freed as soon as the last p->usage reference
	 * goes to 0, without waiting for another RCU gp to elapse. The only
	 * way that a BPF program can guarantee that a task is valid is in this
	 * scenario is to hold a p->usage refcount itself.
	 *
	 * Until we're able to resolve this issue, either by pulling
	 * p->rcu_users and p->rcu out of the union, or by getting rid of
	 * p->usage and just using p->rcu_users for refcounting, we'll just
	 * return NULL here.
	 */
	return NULL;
}

/**
 * bpf_task_kptr_get - Acquire a reference on a struct task_struct kptr. A task
 * kptr acquired by this kfunc which is not subsequently stored in a map, must
 * be released by calling bpf_task_release().
 * @pp: A pointer to a task kptr on which a reference is being acquired.
 */
__bpf_kfunc struct task_struct *bpf_task_kptr_get(struct task_struct **pp)
{
	/* We must return NULL here until we have clarity on how to properly
	 * leverage RCU for ensuring a task's lifetime. See the comment above
	 * in bpf_task_acquire_not_zero() for more details.
	 */
	return NULL;
}

/**
 * bpf_task_release - Release the reference acquired on a task.
 * @p: The task on which a reference is being released.
 */
__bpf_kfunc void bpf_task_release(struct task_struct *p)
{
	if (!p)
		return;

	put_task_struct(p);
}

#ifdef CONFIG_CGROUPS
/**
 * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by
 * this kfunc which is not stored in a map as a kptr, must be released by
 * calling bpf_cgroup_release().
 * @cgrp: The cgroup on which a reference is being acquired.
 */
__bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp)
{
	cgroup_get(cgrp);
	return cgrp;
}

/**
 * bpf_cgroup_kptr_get - Acquire a reference on a struct cgroup kptr. A cgroup
 * kptr acquired by this kfunc which is not subsequently stored in a map, must
 * be released by calling bpf_cgroup_release().
 * @cgrpp: A pointer to a cgroup kptr on which a reference is being acquired.
 */
__bpf_kfunc struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp)
{
	struct cgroup *cgrp;

	rcu_read_lock();
	/* Another context could remove the cgroup from the map and release it
	 * at any time, including after we've done the lookup above. This is
	 * safe because we're in an RCU read region, so the cgroup is
	 * guaranteed to remain valid until at least the rcu_read_unlock()
	 * below.
	 */
	cgrp = READ_ONCE(*cgrpp);

	if (cgrp && !cgroup_tryget(cgrp))
		/* If the cgroup had been removed from the map and freed as
		 * described above, cgroup_tryget() will return false. The
		 * cgroup will be freed at some point after the current RCU gp
		 * has ended, so just return NULL to the user.
		 */
		cgrp = NULL;
	rcu_read_unlock();

	return cgrp;
}

/**
 * bpf_cgroup_release - Release the reference acquired on a cgroup.
 * If this kfunc is invoked in an RCU read region, the cgroup is guaranteed to
 * not be freed until the current grace period has ended, even if its refcount
 * drops to 0.
 * @cgrp: The cgroup on which a reference is being released.
 */
__bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp)
{
	if (!cgrp)
		return;

	cgroup_put(cgrp);
}

/**
 * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor
 * array. A cgroup returned by this kfunc which is not subsequently stored in a
 * map, must be released by calling bpf_cgroup_release().
 * @cgrp: The cgroup for which we're performing a lookup.
 * @level: The level of ancestor to look up.
 */
__bpf_kfunc struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level)
{
	struct cgroup *ancestor;

	if (level > cgrp->level || level < 0)
		return NULL;

	ancestor = cgrp->ancestors[level];
	cgroup_get(ancestor);
	return ancestor;
}
#endif /* CONFIG_CGROUPS */

/**
 * bpf_task_from_pid - Find a struct task_struct from its pid by looking it up
 * in the root pid namespace idr. If a task is returned, it must either be
 * stored in a map, or released with bpf_task_release().
 * @pid: The pid of the task being looked up.
 */
__bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
{
	struct task_struct *p;

	rcu_read_lock();
	p = find_task_by_pid_ns(pid, &init_pid_ns);
	if (p)
		bpf_task_acquire(p);
	rcu_read_unlock();

	return p;
}

__bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj)
{
	return obj;
}

__bpf_kfunc void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k)
{
	return obj__ign;
}

__bpf_kfunc void bpf_rcu_read_lock(void)
{
	rcu_read_lock();
}

__bpf_kfunc void bpf_rcu_read_unlock(void)
{
	rcu_read_unlock();
}

__diag_pop();

BTF_SET8_START(generic_btf_ids)
#ifdef CONFIG_KEXEC_CORE
BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
#endif
BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_list_push_front)
BTF_ID_FLAGS(func, bpf_list_push_back)
BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE)
BTF_ID_FLAGS(func, bpf_rbtree_add)
BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL)

#ifdef CONFIG_CGROUPS
BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_cgroup_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
BTF_SET8_END(generic_btf_ids)

static const struct btf_kfunc_id_set generic_kfunc_set = {
	.owner = THIS_MODULE,
	.set   = &generic_btf_ids,
};


BTF_ID_LIST(generic_dtor_ids)
BTF_ID(struct, task_struct)
BTF_ID(func, bpf_task_release)
#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
BTF_ID(func, bpf_cgroup_release)
#endif

BTF_SET8_START(common_btf_ids)
BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx)
BTF_ID_FLAGS(func, bpf_rdonly_cast)
BTF_ID_FLAGS(func, bpf_rcu_read_lock)
BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
BTF_SET8_END(common_btf_ids)

static const struct btf_kfunc_id_set common_kfunc_set = {
	.owner = THIS_MODULE,
	.set   = &common_btf_ids,
};

static int __init kfunc_init(void)
{
	int ret;
	const struct btf_id_dtor_kfunc generic_dtors[] = {
		{
			.btf_id       = generic_dtor_ids[0],
			.kfunc_btf_id = generic_dtor_ids[1]
		},
#ifdef CONFIG_CGROUPS
		{
			.btf_id       = generic_dtor_ids[2],
			.kfunc_btf_id = generic_dtor_ids[3]
		},
#endif
	};

	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set);
	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set);
	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set);
	ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors,
						  ARRAY_SIZE(generic_dtors),
						  THIS_MODULE);
	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set);
}

late_initcall(kfunc_init);