summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/cgroup.c
blob: afb414b26d01d7b92b72f727426afc7d4b7ed214 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Functions to manage eBPF programs attached to cgroups
 *
 * Copyright (c) 2016 Daniel Mack
 */

#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
#include <linux/filter.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/string.h>
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
#include <net/bpf_sk_storage.h>

#include "../cgroup/cgroup-internal.h"

DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE);
EXPORT_SYMBOL(cgroup_bpf_enabled_key);

/* __always_inline is necessary to prevent indirect call through run_prog
 * function pointer.
 */
static __always_inline int
bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp,
		      enum cgroup_bpf_attach_type atype,
		      const void *ctx, bpf_prog_run_fn run_prog,
		      int retval, u32 *ret_flags)
{
	const struct bpf_prog_array_item *item;
	const struct bpf_prog *prog;
	const struct bpf_prog_array *array;
	struct bpf_run_ctx *old_run_ctx;
	struct bpf_cg_run_ctx run_ctx;
	u32 func_ret;

	run_ctx.retval = retval;
	migrate_disable();
	rcu_read_lock();
	array = rcu_dereference(cgrp->effective[atype]);
	item = &array->items[0];
	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
	while ((prog = READ_ONCE(item->prog))) {
		run_ctx.prog_item = item;
		func_ret = run_prog(prog, ctx);
		if (ret_flags) {
			*(ret_flags) |= (func_ret >> 1);
			func_ret &= 1;
		}
		if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval))
			run_ctx.retval = -EPERM;
		item++;
	}
	bpf_reset_run_ctx(old_run_ctx);
	rcu_read_unlock();
	migrate_enable();
	return run_ctx.retval;
}

void cgroup_bpf_offline(struct cgroup *cgrp)
{
	cgroup_get(cgrp);
	percpu_ref_kill(&cgrp->bpf.refcnt);
}

static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[])
{
	enum bpf_cgroup_storage_type stype;

	for_each_cgroup_storage_type(stype)
		bpf_cgroup_storage_free(storages[stype]);
}

static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[],
				     struct bpf_cgroup_storage *new_storages[],
				     enum bpf_attach_type type,
				     struct bpf_prog *prog,
				     struct cgroup *cgrp)
{
	enum bpf_cgroup_storage_type stype;
	struct bpf_cgroup_storage_key key;
	struct bpf_map *map;

	key.cgroup_inode_id = cgroup_id(cgrp);
	key.attach_type = type;

	for_each_cgroup_storage_type(stype) {
		map = prog->aux->cgroup_storage[stype];
		if (!map)
			continue;

		storages[stype] = cgroup_storage_lookup((void *)map, &key, false);
		if (storages[stype])
			continue;

		storages[stype] = bpf_cgroup_storage_alloc(prog, stype);
		if (IS_ERR(storages[stype])) {
			bpf_cgroup_storages_free(new_storages);
			return -ENOMEM;
		}

		new_storages[stype] = storages[stype];
	}

	return 0;
}

static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[],
				       struct bpf_cgroup_storage *src[])
{
	enum bpf_cgroup_storage_type stype;

	for_each_cgroup_storage_type(stype)
		dst[stype] = src[stype];
}

static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
				     struct cgroup *cgrp,
				     enum bpf_attach_type attach_type)
{
	enum bpf_cgroup_storage_type stype;

	for_each_cgroup_storage_type(stype)
		bpf_cgroup_storage_link(storages[stype], cgrp, attach_type);
}

/* Called when bpf_cgroup_link is auto-detached from dying cgroup.
 * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It
 * doesn't free link memory, which will eventually be done by bpf_link's
 * release() callback, when its last FD is closed.
 */
static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link)
{
	cgroup_put(link->cgroup);
	link->cgroup = NULL;
}

/**
 * cgroup_bpf_release() - put references of all bpf programs and
 *                        release all cgroup bpf data
 * @work: work structure embedded into the cgroup to modify
 */
static void cgroup_bpf_release(struct work_struct *work)
{
	struct cgroup *p, *cgrp = container_of(work, struct cgroup,
					       bpf.release_work);
	struct bpf_prog_array *old_array;
	struct list_head *storages = &cgrp->bpf.storages;
	struct bpf_cgroup_storage *storage, *stmp;

	unsigned int atype;

	mutex_lock(&cgroup_mutex);

	for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) {
		struct list_head *progs = &cgrp->bpf.progs[atype];
		struct bpf_prog_list *pl, *pltmp;

		list_for_each_entry_safe(pl, pltmp, progs, node) {
			list_del(&pl->node);
			if (pl->prog)
				bpf_prog_put(pl->prog);
			if (pl->link)
				bpf_cgroup_link_auto_detach(pl->link);
			kfree(pl);
			static_branch_dec(&cgroup_bpf_enabled_key[atype]);
		}
		old_array = rcu_dereference_protected(
				cgrp->bpf.effective[atype],
				lockdep_is_held(&cgroup_mutex));
		bpf_prog_array_free(old_array);
	}

	list_for_each_entry_safe(storage, stmp, storages, list_cg) {
		bpf_cgroup_storage_unlink(storage);
		bpf_cgroup_storage_free(storage);
	}

	mutex_unlock(&cgroup_mutex);

	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
		cgroup_bpf_put(p);

	percpu_ref_exit(&cgrp->bpf.refcnt);
	cgroup_put(cgrp);
}

/**
 * cgroup_bpf_release_fn() - callback used to schedule releasing
 *                           of bpf cgroup data
 * @ref: percpu ref counter structure
 */
static void cgroup_bpf_release_fn(struct percpu_ref *ref)
{
	struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt);

	INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release);
	queue_work(system_wq, &cgrp->bpf.release_work);
}

/* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through
 * link or direct prog.
 */
static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl)
{
	if (pl->prog)
		return pl->prog;
	if (pl->link)
		return pl->link->link.prog;
	return NULL;
}

/* count number of elements in the list.
 * it's slow but the list cannot be long
 */
static u32 prog_list_length(struct list_head *head)
{
	struct bpf_prog_list *pl;
	u32 cnt = 0;

	list_for_each_entry(pl, head, node) {
		if (!prog_list_prog(pl))
			continue;
		cnt++;
	}
	return cnt;
}

/* if parent has non-overridable prog attached,
 * disallow attaching new programs to the descendent cgroup.
 * if parent has overridable or multi-prog, allow attaching
 */
static bool hierarchy_allows_attach(struct cgroup *cgrp,
				    enum cgroup_bpf_attach_type atype)
{
	struct cgroup *p;

	p = cgroup_parent(cgrp);
	if (!p)
		return true;
	do {
		u32 flags = p->bpf.flags[atype];
		u32 cnt;

		if (flags & BPF_F_ALLOW_MULTI)
			return true;
		cnt = prog_list_length(&p->bpf.progs[atype]);
		WARN_ON_ONCE(cnt > 1);
		if (cnt == 1)
			return !!(flags & BPF_F_ALLOW_OVERRIDE);
		p = cgroup_parent(p);
	} while (p);
	return true;
}

/* compute a chain of effective programs for a given cgroup:
 * start from the list of programs in this cgroup and add
 * all parent programs.
 * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
 * to programs in this cgroup
 */
static int compute_effective_progs(struct cgroup *cgrp,
				   enum cgroup_bpf_attach_type atype,
				   struct bpf_prog_array **array)
{
	struct bpf_prog_array_item *item;
	struct bpf_prog_array *progs;
	struct bpf_prog_list *pl;
	struct cgroup *p = cgrp;
	int cnt = 0;

	/* count number of effective programs by walking parents */
	do {
		if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
			cnt += prog_list_length(&p->bpf.progs[atype]);
		p = cgroup_parent(p);
	} while (p);

	progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
	if (!progs)
		return -ENOMEM;

	/* populate the array with effective progs */
	cnt = 0;
	p = cgrp;
	do {
		if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
			continue;

		list_for_each_entry(pl, &p->bpf.progs[atype], node) {
			if (!prog_list_prog(pl))
				continue;

			item = &progs->items[cnt];
			item->prog = prog_list_prog(pl);
			bpf_cgroup_storages_assign(item->cgroup_storage,
						   pl->storage);
			cnt++;
		}
	} while ((p = cgroup_parent(p)));

	*array = progs;
	return 0;
}

static void activate_effective_progs(struct cgroup *cgrp,
				     enum cgroup_bpf_attach_type atype,
				     struct bpf_prog_array *old_array)
{
	old_array = rcu_replace_pointer(cgrp->bpf.effective[atype], old_array,
					lockdep_is_held(&cgroup_mutex));
	/* free prog array after grace period, since __cgroup_bpf_run_*()
	 * might be still walking the array
	 */
	bpf_prog_array_free(old_array);
}

/**
 * cgroup_bpf_inherit() - inherit effective programs from parent
 * @cgrp: the cgroup to modify
 */
int cgroup_bpf_inherit(struct cgroup *cgrp)
{
/* has to use marco instead of const int, since compiler thinks
 * that array below is variable length
 */
#define	NR ARRAY_SIZE(cgrp->bpf.effective)
	struct bpf_prog_array *arrays[NR] = {};
	struct cgroup *p;
	int ret, i;

	ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0,
			      GFP_KERNEL);
	if (ret)
		return ret;

	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
		cgroup_bpf_get(p);

	for (i = 0; i < NR; i++)
		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);

	INIT_LIST_HEAD(&cgrp->bpf.storages);

	for (i = 0; i < NR; i++)
		if (compute_effective_progs(cgrp, i, &arrays[i]))
			goto cleanup;

	for (i = 0; i < NR; i++)
		activate_effective_progs(cgrp, i, arrays[i]);

	return 0;
cleanup:
	for (i = 0; i < NR; i++)
		bpf_prog_array_free(arrays[i]);

	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
		cgroup_bpf_put(p);

	percpu_ref_exit(&cgrp->bpf.refcnt);

	return -ENOMEM;
}

static int update_effective_progs(struct cgroup *cgrp,
				  enum cgroup_bpf_attach_type atype)
{
	struct cgroup_subsys_state *css;
	int err;

	/* allocate and recompute effective prog arrays */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		if (percpu_ref_is_zero(&desc->bpf.refcnt))
			continue;

		err = compute_effective_progs(desc, atype, &desc->bpf.inactive);
		if (err)
			goto cleanup;
	}

	/* all allocations were successful. Activate all prog arrays */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		if (percpu_ref_is_zero(&desc->bpf.refcnt)) {
			if (unlikely(desc->bpf.inactive)) {
				bpf_prog_array_free(desc->bpf.inactive);
				desc->bpf.inactive = NULL;
			}
			continue;
		}

		activate_effective_progs(desc, atype, desc->bpf.inactive);
		desc->bpf.inactive = NULL;
	}

	return 0;

cleanup:
	/* oom while computing effective. Free all computed effective arrays
	 * since they were not activated
	 */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		bpf_prog_array_free(desc->bpf.inactive);
		desc->bpf.inactive = NULL;
	}

	return err;
}

#define BPF_CGROUP_MAX_PROGS 64

static struct bpf_prog_list *find_attach_entry(struct list_head *progs,
					       struct bpf_prog *prog,
					       struct bpf_cgroup_link *link,
					       struct bpf_prog *replace_prog,
					       bool allow_multi)
{
	struct bpf_prog_list *pl;

	/* single-attach case */
	if (!allow_multi) {
		if (list_empty(progs))
			return NULL;
		return list_first_entry(progs, typeof(*pl), node);
	}

	list_for_each_entry(pl, progs, node) {
		if (prog && pl->prog == prog && prog != replace_prog)
			/* disallow attaching the same prog twice */
			return ERR_PTR(-EINVAL);
		if (link && pl->link == link)
			/* disallow attaching the same link twice */
			return ERR_PTR(-EINVAL);
	}

	/* direct prog multi-attach w/ replacement case */
	if (replace_prog) {
		list_for_each_entry(pl, progs, node) {
			if (pl->prog == replace_prog)
				/* a match found */
				return pl;
		}
		/* prog to replace not found for cgroup */
		return ERR_PTR(-ENOENT);
	}

	return NULL;
}

/**
 * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and
 *                         propagate the change to descendants
 * @cgrp: The cgroup which descendants to traverse
 * @prog: A program to attach
 * @link: A link to attach
 * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
 * @type: Type of attach operation
 * @flags: Option flags
 *
 * Exactly one of @prog or @link can be non-null.
 * Must be called with cgroup_mutex held.
 */
static int __cgroup_bpf_attach(struct cgroup *cgrp,
			       struct bpf_prog *prog, struct bpf_prog *replace_prog,
			       struct bpf_cgroup_link *link,
			       enum bpf_attach_type type, u32 flags)
{
	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
	struct bpf_prog *old_prog = NULL;
	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
	struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
	enum cgroup_bpf_attach_type atype;
	struct bpf_prog_list *pl;
	struct list_head *progs;
	int err;

	if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) ||
	    ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
		/* invalid combination */
		return -EINVAL;
	if (link && (prog || replace_prog))
		/* only either link or prog/replace_prog can be specified */
		return -EINVAL;
	if (!!replace_prog != !!(flags & BPF_F_REPLACE))
		/* replace_prog implies BPF_F_REPLACE, and vice versa */
		return -EINVAL;

	atype = to_cgroup_bpf_attach_type(type);
	if (atype < 0)
		return -EINVAL;

	progs = &cgrp->bpf.progs[atype];

	if (!hierarchy_allows_attach(cgrp, atype))
		return -EPERM;

	if (!list_empty(progs) && cgrp->bpf.flags[atype] != saved_flags)
		/* Disallow attaching non-overridable on top
		 * of existing overridable in this cgroup.
		 * Disallow attaching multi-prog if overridable or none
		 */
		return -EPERM;

	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
		return -E2BIG;

	pl = find_attach_entry(progs, prog, link, replace_prog,
			       flags & BPF_F_ALLOW_MULTI);
	if (IS_ERR(pl))
		return PTR_ERR(pl);

	if (bpf_cgroup_storages_alloc(storage, new_storage, type,
				      prog ? : link->link.prog, cgrp))
		return -ENOMEM;

	if (pl) {
		old_prog = pl->prog;
	} else {
		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
		if (!pl) {
			bpf_cgroup_storages_free(new_storage);
			return -ENOMEM;
		}
		list_add_tail(&pl->node, progs);
	}

	pl->prog = prog;
	pl->link = link;
	bpf_cgroup_storages_assign(pl->storage, storage);
	cgrp->bpf.flags[atype] = saved_flags;

	err = update_effective_progs(cgrp, atype);
	if (err)
		goto cleanup;

	if (old_prog)
		bpf_prog_put(old_prog);
	else
		static_branch_inc(&cgroup_bpf_enabled_key[atype]);
	bpf_cgroup_storages_link(new_storage, cgrp, type);
	return 0;

cleanup:
	if (old_prog) {
		pl->prog = old_prog;
		pl->link = NULL;
	}
	bpf_cgroup_storages_free(new_storage);
	if (!old_prog) {
		list_del(&pl->node);
		kfree(pl);
	}
	return err;
}

static int cgroup_bpf_attach(struct cgroup *cgrp,
			     struct bpf_prog *prog, struct bpf_prog *replace_prog,
			     struct bpf_cgroup_link *link,
			     enum bpf_attach_type type,
			     u32 flags)
{
	int ret;

	mutex_lock(&cgroup_mutex);
	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags);
	mutex_unlock(&cgroup_mutex);
	return ret;
}

/* Swap updated BPF program for given link in effective program arrays across
 * all descendant cgroups. This function is guaranteed to succeed.
 */
static void replace_effective_prog(struct cgroup *cgrp,
				   enum cgroup_bpf_attach_type atype,
				   struct bpf_cgroup_link *link)
{
	struct bpf_prog_array_item *item;
	struct cgroup_subsys_state *css;
	struct bpf_prog_array *progs;
	struct bpf_prog_list *pl;
	struct list_head *head;
	struct cgroup *cg;
	int pos;

	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		if (percpu_ref_is_zero(&desc->bpf.refcnt))
			continue;

		/* find position of link in effective progs array */
		for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
			if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
				continue;

			head = &cg->bpf.progs[atype];
			list_for_each_entry(pl, head, node) {
				if (!prog_list_prog(pl))
					continue;
				if (pl->link == link)
					goto found;
				pos++;
			}
		}
found:
		BUG_ON(!cg);
		progs = rcu_dereference_protected(
				desc->bpf.effective[atype],
				lockdep_is_held(&cgroup_mutex));
		item = &progs->items[pos];
		WRITE_ONCE(item->prog, link->link.prog);
	}
}

/**
 * __cgroup_bpf_replace() - Replace link's program and propagate the change
 *                          to descendants
 * @cgrp: The cgroup which descendants to traverse
 * @link: A link for which to replace BPF program
 * @type: Type of attach operation
 *
 * Must be called with cgroup_mutex held.
 */
static int __cgroup_bpf_replace(struct cgroup *cgrp,
				struct bpf_cgroup_link *link,
				struct bpf_prog *new_prog)
{
	enum cgroup_bpf_attach_type atype;
	struct bpf_prog *old_prog;
	struct bpf_prog_list *pl;
	struct list_head *progs;
	bool found = false;

	atype = to_cgroup_bpf_attach_type(link->type);
	if (atype < 0)
		return -EINVAL;

	progs = &cgrp->bpf.progs[atype];

	if (link->link.prog->type != new_prog->type)
		return -EINVAL;

	list_for_each_entry(pl, progs, node) {
		if (pl->link == link) {
			found = true;
			break;
		}
	}
	if (!found)
		return -ENOENT;

	old_prog = xchg(&link->link.prog, new_prog);
	replace_effective_prog(cgrp, atype, link);
	bpf_prog_put(old_prog);
	return 0;
}

static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog,
			      struct bpf_prog *old_prog)
{
	struct bpf_cgroup_link *cg_link;
	int ret;

	cg_link = container_of(link, struct bpf_cgroup_link, link);

	mutex_lock(&cgroup_mutex);
	/* link might have been auto-released by dying cgroup, so fail */
	if (!cg_link->cgroup) {
		ret = -ENOLINK;
		goto out_unlock;
	}
	if (old_prog && link->prog != old_prog) {
		ret = -EPERM;
		goto out_unlock;
	}
	ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog);
out_unlock:
	mutex_unlock(&cgroup_mutex);
	return ret;
}

static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
					       struct bpf_prog *prog,
					       struct bpf_cgroup_link *link,
					       bool allow_multi)
{
	struct bpf_prog_list *pl;

	if (!allow_multi) {
		if (list_empty(progs))
			/* report error when trying to detach and nothing is attached */
			return ERR_PTR(-ENOENT);

		/* to maintain backward compatibility NONE and OVERRIDE cgroups
		 * allow detaching with invalid FD (prog==NULL) in legacy mode
		 */
		return list_first_entry(progs, typeof(*pl), node);
	}

	if (!prog && !link)
		/* to detach MULTI prog the user has to specify valid FD
		 * of the program or link to be detached
		 */
		return ERR_PTR(-EINVAL);

	/* find the prog or link and detach it */
	list_for_each_entry(pl, progs, node) {
		if (pl->prog == prog && pl->link == link)
			return pl;
	}
	return ERR_PTR(-ENOENT);
}

/**
 * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
 *                         propagate the change to descendants
 * @cgrp: The cgroup which descendants to traverse
 * @prog: A program to detach or NULL
 * @link: A link to detach or NULL
 * @type: Type of detach operation
 *
 * At most one of @prog or @link can be non-NULL.
 * Must be called with cgroup_mutex held.
 */
static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
			       struct bpf_cgroup_link *link, enum bpf_attach_type type)
{
	enum cgroup_bpf_attach_type atype;
	struct bpf_prog *old_prog;
	struct bpf_prog_list *pl;
	struct list_head *progs;
	u32 flags;
	int err;

	atype = to_cgroup_bpf_attach_type(type);
	if (atype < 0)
		return -EINVAL;

	progs = &cgrp->bpf.progs[atype];
	flags = cgrp->bpf.flags[atype];

	if (prog && link)
		/* only one of prog or link can be specified */
		return -EINVAL;

	pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI);
	if (IS_ERR(pl))
		return PTR_ERR(pl);

	/* mark it deleted, so it's ignored while recomputing effective */
	old_prog = pl->prog;
	pl->prog = NULL;
	pl->link = NULL;

	err = update_effective_progs(cgrp, atype);
	if (err)
		goto cleanup;

	/* now can actually delete it from this cgroup list */
	list_del(&pl->node);
	kfree(pl);
	if (list_empty(progs))
		/* last program was detached, reset flags to zero */
		cgrp->bpf.flags[atype] = 0;
	if (old_prog)
		bpf_prog_put(old_prog);
	static_branch_dec(&cgroup_bpf_enabled_key[atype]);
	return 0;

cleanup:
	/* restore back prog or link */
	pl->prog = old_prog;
	pl->link = link;
	return err;
}

static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
			     enum bpf_attach_type type)
{
	int ret;

	mutex_lock(&cgroup_mutex);
	ret = __cgroup_bpf_detach(cgrp, prog, NULL, type);
	mutex_unlock(&cgroup_mutex);
	return ret;
}

/* Must be called with cgroup_mutex held to avoid races. */
static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
			      union bpf_attr __user *uattr)
{
	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
	enum bpf_attach_type type = attr->query.attach_type;
	enum cgroup_bpf_attach_type atype;
	struct bpf_prog_array *effective;
	struct list_head *progs;
	struct bpf_prog *prog;
	int cnt, ret = 0, i;
	u32 flags;

	atype = to_cgroup_bpf_attach_type(type);
	if (atype < 0)
		return -EINVAL;

	progs = &cgrp->bpf.progs[atype];
	flags = cgrp->bpf.flags[atype];

	effective = rcu_dereference_protected(cgrp->bpf.effective[atype],
					      lockdep_is_held(&cgroup_mutex));

	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
		cnt = bpf_prog_array_length(effective);
	else
		cnt = prog_list_length(progs);

	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
		return -EFAULT;
	if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
		return -EFAULT;
	if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
		/* return early if user requested only program count + flags */
		return 0;
	if (attr->query.prog_cnt < cnt) {
		cnt = attr->query.prog_cnt;
		ret = -ENOSPC;
	}

	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
		return bpf_prog_array_copy_to_user(effective, prog_ids, cnt);
	} else {
		struct bpf_prog_list *pl;
		u32 id;

		i = 0;
		list_for_each_entry(pl, progs, node) {
			prog = prog_list_prog(pl);
			id = prog->aux->id;
			if (copy_to_user(prog_ids + i, &id, sizeof(id)))
				return -EFAULT;
			if (++i == cnt)
				break;
		}
	}
	return ret;
}

static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
			    union bpf_attr __user *uattr)
{
	int ret;

	mutex_lock(&cgroup_mutex);
	ret = __cgroup_bpf_query(cgrp, attr, uattr);
	mutex_unlock(&cgroup_mutex);
	return ret;
}

int cgroup_bpf_prog_attach(const union bpf_attr *attr,
			   enum bpf_prog_type ptype, struct bpf_prog *prog)
{
	struct bpf_prog *replace_prog = NULL;
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	if ((attr->attach_flags & BPF_F_ALLOW_MULTI) &&
	    (attr->attach_flags & BPF_F_REPLACE)) {
		replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype);
		if (IS_ERR(replace_prog)) {
			cgroup_put(cgrp);
			return PTR_ERR(replace_prog);
		}
	}

	ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL,
				attr->attach_type, attr->attach_flags);

	if (replace_prog)
		bpf_prog_put(replace_prog);
	cgroup_put(cgrp);
	return ret;
}

int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
{
	struct bpf_prog *prog;
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
	if (IS_ERR(prog))
		prog = NULL;

	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type);
	if (prog)
		bpf_prog_put(prog);

	cgroup_put(cgrp);
	return ret;
}

static void bpf_cgroup_link_release(struct bpf_link *link)
{
	struct bpf_cgroup_link *cg_link =
		container_of(link, struct bpf_cgroup_link, link);
	struct cgroup *cg;

	/* link might have been auto-detached by dying cgroup already,
	 * in that case our work is done here
	 */
	if (!cg_link->cgroup)
		return;

	mutex_lock(&cgroup_mutex);

	/* re-check cgroup under lock again */
	if (!cg_link->cgroup) {
		mutex_unlock(&cgroup_mutex);
		return;
	}

	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
				    cg_link->type));

	cg = cg_link->cgroup;
	cg_link->cgroup = NULL;

	mutex_unlock(&cgroup_mutex);

	cgroup_put(cg);
}

static void bpf_cgroup_link_dealloc(struct bpf_link *link)
{
	struct bpf_cgroup_link *cg_link =
		container_of(link, struct bpf_cgroup_link, link);

	kfree(cg_link);
}

static int bpf_cgroup_link_detach(struct bpf_link *link)
{
	bpf_cgroup_link_release(link);

	return 0;
}

static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
					struct seq_file *seq)
{
	struct bpf_cgroup_link *cg_link =
		container_of(link, struct bpf_cgroup_link, link);
	u64 cg_id = 0;

	mutex_lock(&cgroup_mutex);
	if (cg_link->cgroup)
		cg_id = cgroup_id(cg_link->cgroup);
	mutex_unlock(&cgroup_mutex);

	seq_printf(seq,
		   "cgroup_id:\t%llu\n"
		   "attach_type:\t%d\n",
		   cg_id,
		   cg_link->type);
}

static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
					  struct bpf_link_info *info)
{
	struct bpf_cgroup_link *cg_link =
		container_of(link, struct bpf_cgroup_link, link);
	u64 cg_id = 0;

	mutex_lock(&cgroup_mutex);
	if (cg_link->cgroup)
		cg_id = cgroup_id(cg_link->cgroup);
	mutex_unlock(&cgroup_mutex);

	info->cgroup.cgroup_id = cg_id;
	info->cgroup.attach_type = cg_link->type;
	return 0;
}

static const struct bpf_link_ops bpf_cgroup_link_lops = {
	.release = bpf_cgroup_link_release,
	.dealloc = bpf_cgroup_link_dealloc,
	.detach = bpf_cgroup_link_detach,
	.update_prog = cgroup_bpf_replace,
	.show_fdinfo = bpf_cgroup_link_show_fdinfo,
	.fill_link_info = bpf_cgroup_link_fill_link_info,
};

int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
	struct bpf_link_primer link_primer;
	struct bpf_cgroup_link *link;
	struct cgroup *cgrp;
	int err;

	if (attr->link_create.flags)
		return -EINVAL;

	cgrp = cgroup_get_from_fd(attr->link_create.target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	link = kzalloc(sizeof(*link), GFP_USER);
	if (!link) {
		err = -ENOMEM;
		goto out_put_cgroup;
	}
	bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops,
		      prog);
	link->cgroup = cgrp;
	link->type = attr->link_create.attach_type;

	err = bpf_link_prime(&link->link, &link_primer);
	if (err) {
		kfree(link);
		goto out_put_cgroup;
	}

	err = cgroup_bpf_attach(cgrp, NULL, NULL, link,
				link->type, BPF_F_ALLOW_MULTI);
	if (err) {
		bpf_link_cleanup(&link_primer);
		goto out_put_cgroup;
	}

	return bpf_link_settle(&link_primer);

out_put_cgroup:
	cgroup_put(cgrp);
	return err;
}

int cgroup_bpf_prog_query(const union bpf_attr *attr,
			  union bpf_attr __user *uattr)
{
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->query.target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	ret = cgroup_bpf_query(cgrp, attr, uattr);

	cgroup_put(cgrp);
	return ret;
}

/**
 * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
 * @sk: The socket sending or receiving traffic
 * @skb: The skb that is being sent or received
 * @type: The type of program to be executed
 *
 * If no socket is passed, or the socket is not of type INET or INET6,
 * this function does nothing and returns 0.
 *
 * The program type passed in via @type must be suitable for network
 * filtering. No further check is performed to assert that.
 *
 * For egress packets, this function can return:
 *   NET_XMIT_SUCCESS    (0)	- continue with packet output
 *   NET_XMIT_DROP       (1)	- drop packet and notify TCP to call cwr
 *   NET_XMIT_CN         (2)	- continue with packet output and notify TCP
 *				  to call cwr
 *   -err			- drop packet
 *
 * For ingress packets, this function will return -EPERM if any
 * attached program was found and if it returned != 1 during execution.
 * Otherwise 0 is returned.
 */
int __cgroup_bpf_run_filter_skb(struct sock *sk,
				struct sk_buff *skb,
				enum cgroup_bpf_attach_type atype)
{
	unsigned int offset = skb->data - skb_network_header(skb);
	struct sock *save_sk;
	void *saved_data_end;
	struct cgroup *cgrp;
	int ret;

	if (!sk || !sk_fullsock(sk))
		return 0;

	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
		return 0;

	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	save_sk = skb->sk;
	skb->sk = sk;
	__skb_push(skb, offset);

	/* compute pointers for the bpf prog */
	bpf_compute_and_save_data_end(skb, &saved_data_end);

	if (atype == CGROUP_INET_EGRESS) {
		u32 flags = 0;
		bool cn;

		ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb,
					    __bpf_prog_run_save_cb, 0, &flags);

		/* Return values of CGROUP EGRESS BPF programs are:
		 *   0: drop packet
		 *   1: keep packet
		 *   2: drop packet and cn
		 *   3: keep packet and cn
		 *
		 * The returned value is then converted to one of the NET_XMIT
		 * or an error code that is then interpreted as drop packet
		 * (and no cn):
		 *   0: NET_XMIT_SUCCESS  skb should be transmitted
		 *   1: NET_XMIT_DROP     skb should be dropped and cn
		 *   2: NET_XMIT_CN       skb should be transmitted and cn
		 *   3: -err              skb should be dropped
		 */

		cn = flags & BPF_RET_SET_CN;
		if (ret && !IS_ERR_VALUE((long)ret))
			ret = -EFAULT;
		if (!ret)
			ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);
		else
			ret = (cn ? NET_XMIT_DROP : ret);
	} else {
		ret = bpf_prog_run_array_cg(&cgrp->bpf, atype,
					    skb, __bpf_prog_run_save_cb, 0,
					    NULL);
		if (ret && !IS_ERR_VALUE((long)ret))
			ret = -EFAULT;
	}
	bpf_restore_data_end(skb, saved_data_end);
	__skb_pull(skb, offset);
	skb->sk = save_sk;

	return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);

/**
 * __cgroup_bpf_run_filter_sk() - Run a program on a sock
 * @sk: sock structure to manipulate
 * @type: The type of program to be executed
 *
 * socket is passed is expected to be of type INET or INET6.
 *
 * The program type passed in via @type must be suitable for sock
 * filtering. No further check is performed to assert that.
 *
 * This function will return %-EPERM if any if an attached program was found
 * and if it returned != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sk(struct sock *sk,
			       enum cgroup_bpf_attach_type atype)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);

	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0,
				     NULL);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);

/**
 * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and
 *                                       provided by user sockaddr
 * @sk: sock struct that will use sockaddr
 * @uaddr: sockaddr struct provided by user
 * @type: The type of program to be executed
 * @t_ctx: Pointer to attach type specific context
 * @flags: Pointer to u32 which contains higher bits of BPF program
 *         return value (OR'ed together).
 *
 * socket is expected to be of type INET or INET6.
 *
 * This function will return %-EPERM if an attached program is found and
 * returned value != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
				      struct sockaddr *uaddr,
				      enum cgroup_bpf_attach_type atype,
				      void *t_ctx,
				      u32 *flags)
{
	struct bpf_sock_addr_kern ctx = {
		.sk = sk,
		.uaddr = uaddr,
		.t_ctx = t_ctx,
	};
	struct sockaddr_storage unspec;
	struct cgroup *cgrp;

	/* Check socket family since not all sockets represent network
	 * endpoint (e.g. AF_UNIX).
	 */
	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
		return 0;

	if (!ctx.uaddr) {
		memset(&unspec, 0, sizeof(unspec));
		ctx.uaddr = (struct sockaddr *)&unspec;
	}

	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
				     0, flags);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);

/**
 * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
 * @sk: socket to get cgroup from
 * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
 * sk with connection information (IP addresses, etc.) May not contain
 * cgroup info if it is a req sock.
 * @type: The type of program to be executed
 *
 * socket passed is expected to be of type INET or INET6.
 *
 * The program type passed in via @type must be suitable for sock_ops
 * filtering. No further check is performed to assert that.
 *
 * This function will return %-EPERM if any if an attached program was found
 * and if it returned != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
				     struct bpf_sock_ops_kern *sock_ops,
				     enum cgroup_bpf_attach_type atype)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);

	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run,
				     0, NULL);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);

int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
				      short access, enum cgroup_bpf_attach_type atype)
{
	struct cgroup *cgrp;
	struct bpf_cgroup_dev_ctx ctx = {
		.access_type = (access << 16) | dev_type,
		.major = major,
		.minor = minor,
	};
	int ret;

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0,
				    NULL);
	rcu_read_unlock();

	return ret;
}

BPF_CALL_0(bpf_get_retval)
{
	struct bpf_cg_run_ctx *ctx =
		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);

	return ctx->retval;
}

static const struct bpf_func_proto bpf_get_retval_proto = {
	.func		= bpf_get_retval,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_1(bpf_set_retval, int, retval)
{
	struct bpf_cg_run_ctx *ctx =
		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);

	ctx->retval = retval;
	return 0;
}

static const struct bpf_func_proto bpf_set_retval_proto = {
	.func		= bpf_set_retval,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *
cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_get_current_uid_gid:
		return &bpf_get_current_uid_gid_proto;
	case BPF_FUNC_get_local_storage:
		return &bpf_get_local_storage_proto;
	case BPF_FUNC_get_current_cgroup_id:
		return &bpf_get_current_cgroup_id_proto;
	case BPF_FUNC_perf_event_output:
		return &bpf_event_output_data_proto;
	case BPF_FUNC_get_retval:
		return &bpf_get_retval_proto;
	case BPF_FUNC_set_retval:
		return &bpf_set_retval_proto;
	default:
		return bpf_base_func_proto(func_id);
	}
}

static const struct bpf_func_proto *
cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	return cgroup_base_func_proto(func_id, prog);
}

static bool cgroup_dev_is_valid_access(int off, int size,
				       enum bpf_access_type type,
				       const struct bpf_prog *prog,
				       struct bpf_insn_access_aux *info)
{
	const int size_default = sizeof(__u32);

	if (type == BPF_WRITE)
		return false;

	if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
		return false;
	/* The verifier guarantees that size > 0. */
	if (off % size != 0)
		return false;

	switch (off) {
	case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type):
		bpf_ctx_record_field_size(info, size_default);
		if (!bpf_ctx_narrow_access_ok(off, size, size_default))
			return false;
		break;
	default:
		if (size != size_default)
			return false;
	}

	return true;
}

const struct bpf_prog_ops cg_dev_prog_ops = {
};

const struct bpf_verifier_ops cg_dev_verifier_ops = {
	.get_func_proto		= cgroup_dev_func_proto,
	.is_valid_access	= cgroup_dev_is_valid_access,
};

/**
 * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl
 *
 * @head: sysctl table header
 * @table: sysctl table
 * @write: sysctl is being read (= 0) or written (= 1)
 * @buf: pointer to buffer (in and out)
 * @pcount: value-result argument: value is size of buffer pointed to by @buf,
 *	result is size of @new_buf if program set new value, initial value
 *	otherwise
 * @ppos: value-result argument: value is position at which read from or write
 *	to sysctl is happening, result is new position if program overrode it,
 *	initial value otherwise
 * @type: type of program to be executed
 *
 * Program is run when sysctl is being accessed, either read or written, and
 * can allow or deny such access.
 *
 * This function will return %-EPERM if an attached program is found and
 * returned value != 1 during execution. In all other cases 0 is returned.
 */
int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
				   struct ctl_table *table, int write,
				   char **buf, size_t *pcount, loff_t *ppos,
				   enum cgroup_bpf_attach_type atype)
{
	struct bpf_sysctl_kern ctx = {
		.head = head,
		.table = table,
		.write = write,
		.ppos = ppos,
		.cur_val = NULL,
		.cur_len = PAGE_SIZE,
		.new_val = NULL,
		.new_len = 0,
		.new_updated = 0,
	};
	struct cgroup *cgrp;
	loff_t pos = 0;
	int ret;

	ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
	if (!ctx.cur_val ||
	    table->proc_handler(table, 0, ctx.cur_val, &ctx.cur_len, &pos)) {
		/* Let BPF program decide how to proceed. */
		ctx.cur_len = 0;
	}

	if (write && *buf && *pcount) {
		/* BPF program should be able to override new value with a
		 * buffer bigger than provided by user.
		 */
		ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
		ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount);
		if (ctx.new_val) {
			memcpy(ctx.new_val, *buf, ctx.new_len);
		} else {
			/* Let BPF program decide how to proceed. */
			ctx.new_len = 0;
		}
	}

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0,
				    NULL);
	rcu_read_unlock();

	kfree(ctx.cur_val);

	if (ret == 1 && ctx.new_updated) {
		kfree(*buf);
		*buf = ctx.new_val;
		*pcount = ctx.new_len;
	} else {
		kfree(ctx.new_val);
	}

	return ret;
}

#ifdef CONFIG_NET
static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen,
			     struct bpf_sockopt_buf *buf)
{
	if (unlikely(max_optlen < 0))
		return -EINVAL;

	if (unlikely(max_optlen > PAGE_SIZE)) {
		/* We don't expose optvals that are greater than PAGE_SIZE
		 * to the BPF program.
		 */
		max_optlen = PAGE_SIZE;
	}

	if (max_optlen <= sizeof(buf->data)) {
		/* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE
		 * bytes avoid the cost of kzalloc.
		 */
		ctx->optval = buf->data;
		ctx->optval_end = ctx->optval + max_optlen;
		return max_optlen;
	}

	ctx->optval = kzalloc(max_optlen, GFP_USER);
	if (!ctx->optval)
		return -ENOMEM;

	ctx->optval_end = ctx->optval + max_optlen;

	return max_optlen;
}

static void sockopt_free_buf(struct bpf_sockopt_kern *ctx,
			     struct bpf_sockopt_buf *buf)
{
	if (ctx->optval == buf->data)
		return;
	kfree(ctx->optval);
}

static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
				  struct bpf_sockopt_buf *buf)
{
	return ctx->optval != buf->data;
}

int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
				       int *optname, char __user *optval,
				       int *optlen, char **kernel_optval)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	struct bpf_sockopt_buf buf = {};
	struct bpf_sockopt_kern ctx = {
		.sk = sk,
		.level = *level,
		.optname = *optname,
	};
	int ret, max_optlen;

	/* Allocate a bit more than the initial user buffer for
	 * BPF program. The canonical use case is overriding
	 * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic).
	 */
	max_optlen = max_t(int, 16, *optlen);
	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
	if (max_optlen < 0)
		return max_optlen;

	ctx.optlen = *optlen;

	if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
		ret = -EFAULT;
		goto out;
	}

	lock_sock(sk);
	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT,
				    &ctx, bpf_prog_run, 0, NULL);
	release_sock(sk);

	if (ret)
		goto out;

	if (ctx.optlen == -1) {
		/* optlen set to -1, bypass kernel */
		ret = 1;
	} else if (ctx.optlen > max_optlen || ctx.optlen < -1) {
		/* optlen is out of bounds */
		ret = -EFAULT;
	} else {
		/* optlen within bounds, run kernel handler */
		ret = 0;

		/* export any potential modifications */
		*level = ctx.level;
		*optname = ctx.optname;

		/* optlen == 0 from BPF indicates that we should
		 * use original userspace data.
		 */
		if (ctx.optlen != 0) {
			*optlen = ctx.optlen;
			/* We've used bpf_sockopt_kern->buf as an intermediary
			 * storage, but the BPF program indicates that we need
			 * to pass this data to the kernel setsockopt handler.
			 * No way to export on-stack buf, have to allocate a
			 * new buffer.
			 */
			if (!sockopt_buf_allocated(&ctx, &buf)) {
				void *p = kmalloc(ctx.optlen, GFP_USER);

				if (!p) {
					ret = -ENOMEM;
					goto out;
				}
				memcpy(p, ctx.optval, ctx.optlen);
				*kernel_optval = p;
			} else {
				*kernel_optval = ctx.optval;
			}
			/* export and don't free sockopt buf */
			return 0;
		}
	}

out:
	sockopt_free_buf(&ctx, &buf);
	return ret;
}

int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
				       int optname, char __user *optval,
				       int __user *optlen, int max_optlen,
				       int retval)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	struct bpf_sockopt_buf buf = {};
	struct bpf_sockopt_kern ctx = {
		.sk = sk,
		.level = level,
		.optname = optname,
		.current_task = current,
	};
	int ret;

	ctx.optlen = max_optlen;
	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
	if (max_optlen < 0)
		return max_optlen;

	if (!retval) {
		/* If kernel getsockopt finished successfully,
		 * copy whatever was returned to the user back
		 * into our temporary buffer. Set optlen to the
		 * one that kernel returned as well to let
		 * BPF programs inspect the value.
		 */

		if (get_user(ctx.optlen, optlen)) {
			ret = -EFAULT;
			goto out;
		}

		if (ctx.optlen < 0) {
			ret = -EFAULT;
			goto out;
		}

		if (copy_from_user(ctx.optval, optval,
				   min(ctx.optlen, max_optlen)) != 0) {
			ret = -EFAULT;
			goto out;
		}
	}

	lock_sock(sk);
	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
				    &ctx, bpf_prog_run, retval, NULL);
	release_sock(sk);

	if (ret < 0)
		goto out;

	if (ctx.optlen > max_optlen || ctx.optlen < 0) {
		ret = -EFAULT;
		goto out;
	}

	if (ctx.optlen != 0) {
		if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
		    put_user(ctx.optlen, optlen)) {
			ret = -EFAULT;
			goto out;
		}
	}

out:
	sockopt_free_buf(&ctx, &buf);
	return ret;
}

int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
					    int optname, void *optval,
					    int *optlen, int retval)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	struct bpf_sockopt_kern ctx = {
		.sk = sk,
		.level = level,
		.optname = optname,
		.optlen = *optlen,
		.optval = optval,
		.optval_end = optval + *optlen,
		.current_task = current,
	};
	int ret;

	/* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy
	 * user data back into BPF buffer when reval != 0. This is
	 * done as an optimization to avoid extra copy, assuming
	 * kernel won't populate the data in case of an error.
	 * Here we always pass the data and memset() should
	 * be called if that data shouldn't be "exported".
	 */

	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
				    &ctx, bpf_prog_run, retval, NULL);
	if (ret < 0)
		return ret;

	if (ctx.optlen > *optlen)
		return -EFAULT;

	/* BPF programs can shrink the buffer, export the modifications.
	 */
	if (ctx.optlen != 0)
		*optlen = ctx.optlen;

	return ret;
}
#endif

static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
			      size_t *lenp)
{
	ssize_t tmp_ret = 0, ret;

	if (dir->header.parent) {
		tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp);
		if (tmp_ret < 0)
			return tmp_ret;
	}

	ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp);
	if (ret < 0)
		return ret;
	*bufp += ret;
	*lenp -= ret;
	ret += tmp_ret;

	/* Avoid leading slash. */
	if (!ret)
		return ret;

	tmp_ret = strscpy(*bufp, "/", *lenp);
	if (tmp_ret < 0)
		return tmp_ret;
	*bufp += tmp_ret;
	*lenp -= tmp_ret;

	return ret + tmp_ret;
}

BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf,
	   size_t, buf_len, u64, flags)
{
	ssize_t tmp_ret = 0, ret;

	if (!buf)
		return -EINVAL;

	if (!(flags & BPF_F_SYSCTL_BASE_NAME)) {
		if (!ctx->head)
			return -EINVAL;
		tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len);
		if (tmp_ret < 0)
			return tmp_ret;
	}

	ret = strscpy(buf, ctx->table->procname, buf_len);

	return ret < 0 ? ret : tmp_ret + ret;
}

static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
	.func		= bpf_sysctl_get_name,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE,
	.arg4_type	= ARG_ANYTHING,
};

static int copy_sysctl_value(char *dst, size_t dst_len, char *src,
			     size_t src_len)
{
	if (!dst)
		return -EINVAL;

	if (!dst_len)
		return -E2BIG;

	if (!src || !src_len) {
		memset(dst, 0, dst_len);
		return -EINVAL;
	}

	memcpy(dst, src, min(dst_len, src_len));

	if (dst_len > src_len) {
		memset(dst + src_len, '\0', dst_len - src_len);
		return src_len;
	}

	dst[dst_len - 1] = '\0';

	return -E2BIG;
}

BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx,
	   char *, buf, size_t, buf_len)
{
	return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len);
}

static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
	.func		= bpf_sysctl_get_current_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf,
	   size_t, buf_len)
{
	if (!ctx->write) {
		if (buf && buf_len)
			memset(buf, '\0', buf_len);
		return -EINVAL;
	}
	return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len);
}

static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = {
	.func		= bpf_sysctl_get_new_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx,
	   const char *, buf, size_t, buf_len)
{
	if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len)
		return -EINVAL;

	if (buf_len > PAGE_SIZE - 1)
		return -E2BIG;

	memcpy(ctx->new_val, buf, buf_len);
	ctx->new_len = buf_len;
	ctx->new_updated = 1;

	return 0;
}

static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
	.func		= bpf_sysctl_set_new_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
	.arg3_type	= ARG_CONST_SIZE,
};

static const struct bpf_func_proto *
sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_strtol:
		return &bpf_strtol_proto;
	case BPF_FUNC_strtoul:
		return &bpf_strtoul_proto;
	case BPF_FUNC_sysctl_get_name:
		return &bpf_sysctl_get_name_proto;
	case BPF_FUNC_sysctl_get_current_value:
		return &bpf_sysctl_get_current_value_proto;
	case BPF_FUNC_sysctl_get_new_value:
		return &bpf_sysctl_get_new_value_proto;
	case BPF_FUNC_sysctl_set_new_value:
		return &bpf_sysctl_set_new_value_proto;
	case BPF_FUNC_ktime_get_coarse_ns:
		return &bpf_ktime_get_coarse_ns_proto;
	default:
		return cgroup_base_func_proto(func_id, prog);
	}
}

static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
				   const struct bpf_prog *prog,
				   struct bpf_insn_access_aux *info)
{
	const int size_default = sizeof(__u32);

	if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size)
		return false;

	switch (off) {
	case bpf_ctx_range(struct bpf_sysctl, write):
		if (type != BPF_READ)
			return false;
		bpf_ctx_record_field_size(info, size_default);
		return bpf_ctx_narrow_access_ok(off, size, size_default);
	case bpf_ctx_range(struct bpf_sysctl, file_pos):
		if (type == BPF_READ) {
			bpf_ctx_record_field_size(info, size_default);
			return bpf_ctx_narrow_access_ok(off, size, size_default);
		} else {
			return size == size_default;
		}
	default:
		return false;
	}
}

static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
				     const struct bpf_insn *si,
				     struct bpf_insn *insn_buf,
				     struct bpf_prog *prog, u32 *target_size)
{
	struct bpf_insn *insn = insn_buf;
	u32 read_size;

	switch (si->off) {
	case offsetof(struct bpf_sysctl, write):
		*insn++ = BPF_LDX_MEM(
			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
			bpf_target_off(struct bpf_sysctl_kern, write,
				       sizeof_field(struct bpf_sysctl_kern,
						    write),
				       target_size));
		break;
	case offsetof(struct bpf_sysctl, file_pos):
		/* ppos is a pointer so it should be accessed via indirect
		 * loads and stores. Also for stores additional temporary
		 * register is used since neither src_reg nor dst_reg can be
		 * overridden.
		 */
		if (type == BPF_WRITE) {
			int treg = BPF_REG_9;

			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			*insn++ = BPF_STX_MEM(
				BPF_DW, si->dst_reg, treg,
				offsetof(struct bpf_sysctl_kern, tmp_reg));
			*insn++ = BPF_LDX_MEM(
				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
				treg, si->dst_reg,
				offsetof(struct bpf_sysctl_kern, ppos));
			*insn++ = BPF_STX_MEM(
				BPF_SIZEOF(u32), treg, si->src_reg,
				bpf_ctx_narrow_access_offset(
					0, sizeof(u32), sizeof(loff_t)));
			*insn++ = BPF_LDX_MEM(
				BPF_DW, treg, si->dst_reg,
				offsetof(struct bpf_sysctl_kern, tmp_reg));
		} else {
			*insn++ = BPF_LDX_MEM(
				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
				si->dst_reg, si->src_reg,
				offsetof(struct bpf_sysctl_kern, ppos));
			read_size = bpf_size_to_bytes(BPF_SIZE(si->code));
			*insn++ = BPF_LDX_MEM(
				BPF_SIZE(si->code), si->dst_reg, si->dst_reg,
				bpf_ctx_narrow_access_offset(
					0, read_size, sizeof(loff_t)));
		}
		*target_size = sizeof(u32);
		break;
	}

	return insn - insn_buf;
}

const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
	.get_func_proto		= sysctl_func_proto,
	.is_valid_access	= sysctl_is_valid_access,
	.convert_ctx_access	= sysctl_convert_ctx_access,
};

const struct bpf_prog_ops cg_sysctl_prog_ops = {
};

#ifdef CONFIG_NET
BPF_CALL_1(bpf_get_netns_cookie_sockopt, struct bpf_sockopt_kern *, ctx)
{
	const struct net *net = ctx ? sock_net(ctx->sk) : &init_net;

	return net->net_cookie;
}

static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = {
	.func		= bpf_get_netns_cookie_sockopt,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
};
#endif

static const struct bpf_func_proto *
cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
#ifdef CONFIG_NET
	case BPF_FUNC_get_netns_cookie:
		return &bpf_get_netns_cookie_sockopt_proto;
	case BPF_FUNC_sk_storage_get:
		return &bpf_sk_storage_get_proto;
	case BPF_FUNC_sk_storage_delete:
		return &bpf_sk_storage_delete_proto;
	case BPF_FUNC_setsockopt:
		if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT)
			return &bpf_sk_setsockopt_proto;
		return NULL;
	case BPF_FUNC_getsockopt:
		if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT)
			return &bpf_sk_getsockopt_proto;
		return NULL;
#endif
#ifdef CONFIG_INET
	case BPF_FUNC_tcp_sock:
		return &bpf_tcp_sock_proto;
#endif
	default:
		return cgroup_base_func_proto(func_id, prog);
	}
}

static bool cg_sockopt_is_valid_access(int off, int size,
				       enum bpf_access_type type,
				       const struct bpf_prog *prog,
				       struct bpf_insn_access_aux *info)
{
	const int size_default = sizeof(__u32);

	if (off < 0 || off >= sizeof(struct bpf_sockopt))
		return false;

	if (off % size != 0)
		return false;

	if (type == BPF_WRITE) {
		switch (off) {
		case offsetof(struct bpf_sockopt, retval):
			if (size != size_default)
				return false;
			return prog->expected_attach_type ==
				BPF_CGROUP_GETSOCKOPT;
		case offsetof(struct bpf_sockopt, optname):
			fallthrough;
		case offsetof(struct bpf_sockopt, level):
			if (size != size_default)
				return false;
			return prog->expected_attach_type ==
				BPF_CGROUP_SETSOCKOPT;
		case offsetof(struct bpf_sockopt, optlen):
			return size == size_default;
		default:
			return false;
		}
	}

	switch (off) {
	case offsetof(struct bpf_sockopt, sk):
		if (size != sizeof(__u64))
			return false;
		info->reg_type = PTR_TO_SOCKET;
		break;
	case offsetof(struct bpf_sockopt, optval):
		if (size != sizeof(__u64))
			return false;
		info->reg_type = PTR_TO_PACKET;
		break;
	case offsetof(struct bpf_sockopt, optval_end):
		if (size != sizeof(__u64))
			return false;
		info->reg_type = PTR_TO_PACKET_END;
		break;
	case offsetof(struct bpf_sockopt, retval):
		if (size != size_default)
			return false;
		return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT;
	default:
		if (size != size_default)
			return false;
		break;
	}
	return true;
}

#define CG_SOCKOPT_ACCESS_FIELD(T, F)					\
	T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F),			\
	  si->dst_reg, si->src_reg,					\
	  offsetof(struct bpf_sockopt_kern, F))

static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
					 const struct bpf_insn *si,
					 struct bpf_insn *insn_buf,
					 struct bpf_prog *prog,
					 u32 *target_size)
{
	struct bpf_insn *insn = insn_buf;

	switch (si->off) {
	case offsetof(struct bpf_sockopt, sk):
		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk);
		break;
	case offsetof(struct bpf_sockopt, level):
		if (type == BPF_WRITE)
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level);
		else
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level);
		break;
	case offsetof(struct bpf_sockopt, optname):
		if (type == BPF_WRITE)
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname);
		else
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname);
		break;
	case offsetof(struct bpf_sockopt, optlen):
		if (type == BPF_WRITE)
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen);
		else
			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
		break;
	case offsetof(struct bpf_sockopt, retval):
		BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0);

		if (type == BPF_WRITE) {
			int treg = BPF_REG_9;

			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			*insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg,
					      offsetof(struct bpf_sockopt_kern, tmp_reg));
			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
					      treg, si->dst_reg,
					      offsetof(struct bpf_sockopt_kern, current_task));
			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
					      treg, treg,
					      offsetof(struct task_struct, bpf_ctx));
			*insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
					      treg, si->src_reg,
					      offsetof(struct bpf_cg_run_ctx, retval));
			*insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg,
					      offsetof(struct bpf_sockopt_kern, tmp_reg));
		} else {
			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
					      si->dst_reg, si->src_reg,
					      offsetof(struct bpf_sockopt_kern, current_task));
			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
					      si->dst_reg, si->dst_reg,
					      offsetof(struct task_struct, bpf_ctx));
			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
					      si->dst_reg, si->dst_reg,
					      offsetof(struct bpf_cg_run_ctx, retval));
		}
		break;
	case offsetof(struct bpf_sockopt, optval):
		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
		break;
	case offsetof(struct bpf_sockopt, optval_end):
		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end);
		break;
	}

	return insn - insn_buf;
}

static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf,
				   bool direct_write,
				   const struct bpf_prog *prog)
{
	/* Nothing to do for sockopt argument. The data is kzalloc'ated.
	 */
	return 0;
}

const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
	.get_func_proto		= cg_sockopt_func_proto,
	.is_valid_access	= cg_sockopt_is_valid_access,
	.convert_ctx_access	= cg_sockopt_convert_ctx_access,
	.gen_prologue		= cg_sockopt_get_prologue,
};

const struct bpf_prog_ops cg_sockopt_prog_ops = {
};