summaryrefslogtreecommitdiffstats
path: root/kernel/seccomp.c
blob: 0ed57e8c49d0b71463d59c5b368fb10e79a5efd7 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/kernel/seccomp.c
 *
 * Copyright 2004-2005  Andrea Arcangeli <andrea@cpushare.com>
 *
 * Copyright (C) 2012 Google, Inc.
 * Will Drewry <wad@chromium.org>
 *
 * This defines a simple but solid secure-computing facility.
 *
 * Mode 1 uses a fixed list of allowed system calls.
 * Mode 2 allows user-defined system call filters in the form
 *        of Berkeley Packet Filters/Linux Socket Filters.
 */
#define pr_fmt(fmt) "seccomp: " fmt

#include <linux/refcount.h>
#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/coredump.h>
#include <linux/kmemleak.h>
#include <linux/nospec.h>
#include <linux/prctl.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/seccomp.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/sysctl.h>

#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
#include <asm/syscall.h>
#endif

#ifdef CONFIG_SECCOMP_FILTER
#include <linux/file.h>
#include <linux/filter.h>
#include <linux/pid.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>
#include <linux/anon_inodes.h>
#include <linux/lockdep.h>

/*
 * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the
 * wrong direction flag in the ioctl number. This is the broken one,
 * which the kernel needs to keep supporting until all userspaces stop
 * using the wrong command number.
 */
#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR	SECCOMP_IOR(2, __u64)

enum notify_state {
	SECCOMP_NOTIFY_INIT,
	SECCOMP_NOTIFY_SENT,
	SECCOMP_NOTIFY_REPLIED,
};

struct seccomp_knotif {
	/* The struct pid of the task whose filter triggered the notification */
	struct task_struct *task;

	/* The "cookie" for this request; this is unique for this filter. */
	u64 id;

	/*
	 * The seccomp data. This pointer is valid the entire time this
	 * notification is active, since it comes from __seccomp_filter which
	 * eclipses the entire lifecycle here.
	 */
	const struct seccomp_data *data;

	/*
	 * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a
	 * struct seccomp_knotif is created and starts out in INIT. Once the
	 * handler reads the notification off of an FD, it transitions to SENT.
	 * If a signal is received the state transitions back to INIT and
	 * another message is sent. When the userspace handler replies, state
	 * transitions to REPLIED.
	 */
	enum notify_state state;

	/* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */
	int error;
	long val;
	u32 flags;

	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
	struct completion ready;

	struct list_head list;
};

/**
 * struct notification - container for seccomp userspace notifications. Since
 * most seccomp filters will not have notification listeners attached and this
 * structure is fairly large, we store the notification-specific stuff in a
 * separate structure.
 *
 * @request: A semaphore that users of this notification can wait on for
 *           changes. Actual reads and writes are still controlled with
 *           filter->notify_lock.
 * @next_id: The id of the next request.
 * @notifications: A list of struct seccomp_knotif elements.
 */
struct notification {
	struct semaphore request;
	u64 next_id;
	struct list_head notifications;
};

/**
 * struct seccomp_filter - container for seccomp BPF programs
 *
 * @refs: Reference count to manage the object lifetime.
 *	  A filter's reference count is incremented for each directly
 *	  attached task, once for the dependent filter, and if
 *	  requested for the user notifier. When @refs reaches zero,
 *	  the filter can be freed.
 * @users: A filter's @users count is incremented for each directly
 *         attached task (filter installation, fork(), thread_sync),
 *	   and once for the dependent filter (tracked in filter->prev).
 *	   When it reaches zero it indicates that no direct or indirect
 *	   users of that filter exist. No new tasks can get associated with
 *	   this filter after reaching 0. The @users count is always smaller
 *	   or equal to @refs. Hence, reaching 0 for @users does not mean
 *	   the filter can be freed.
 * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
 * @prev: points to a previously installed, or inherited, filter
 * @prog: the BPF program to evaluate
 * @notif: the struct that holds all notification related information
 * @notify_lock: A lock for all notification-related accesses.
 * @wqh: A wait queue for poll if a notifier is in use.
 *
 * seccomp_filter objects are organized in a tree linked via the @prev
 * pointer.  For any task, it appears to be a singly-linked list starting
 * with current->seccomp.filter, the most recently attached or inherited filter.
 * However, multiple filters may share a @prev node, by way of fork(), which
 * results in a unidirectional tree existing in memory.  This is similar to
 * how namespaces work.
 *
 * seccomp_filter objects should never be modified after being attached
 * to a task_struct (other than @refs).
 */
struct seccomp_filter {
	refcount_t refs;
	refcount_t users;
	bool log;
	struct seccomp_filter *prev;
	struct bpf_prog *prog;
	struct notification *notif;
	struct mutex notify_lock;
	wait_queue_head_t wqh;
};

/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))

/*
 * Endianness is explicitly ignored and left for BPF program authors to manage
 * as per the specific architecture.
 */
static void populate_seccomp_data(struct seccomp_data *sd)
{
	struct task_struct *task = current;
	struct pt_regs *regs = task_pt_regs(task);
	unsigned long args[6];

	sd->nr = syscall_get_nr(task, regs);
	sd->arch = syscall_get_arch(task);
	syscall_get_arguments(task, regs, args);
	sd->args[0] = args[0];
	sd->args[1] = args[1];
	sd->args[2] = args[2];
	sd->args[3] = args[3];
	sd->args[4] = args[4];
	sd->args[5] = args[5];
	sd->instruction_pointer = KSTK_EIP(task);
}

/**
 *	seccomp_check_filter - verify seccomp filter code
 *	@filter: filter to verify
 *	@flen: length of filter
 *
 * Takes a previously checked filter (by bpf_check_classic) and
 * redirects all filter code that loads struct sk_buff data
 * and related data through seccomp_bpf_load.  It also
 * enforces length and alignment checking of those loads.
 *
 * Returns 0 if the rule set is legal or -EINVAL if not.
 */
static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
{
	int pc;
	for (pc = 0; pc < flen; pc++) {
		struct sock_filter *ftest = &filter[pc];
		u16 code = ftest->code;
		u32 k = ftest->k;

		switch (code) {
		case BPF_LD | BPF_W | BPF_ABS:
			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
			/* 32-bit aligned and not out of bounds. */
			if (k >= sizeof(struct seccomp_data) || k & 3)
				return -EINVAL;
			continue;
		case BPF_LD | BPF_W | BPF_LEN:
			ftest->code = BPF_LD | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		case BPF_LDX | BPF_W | BPF_LEN:
			ftest->code = BPF_LDX | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		/* Explicitly include allowed calls. */
		case BPF_RET | BPF_K:
		case BPF_RET | BPF_A:
		case BPF_ALU | BPF_ADD | BPF_K:
		case BPF_ALU | BPF_ADD | BPF_X:
		case BPF_ALU | BPF_SUB | BPF_K:
		case BPF_ALU | BPF_SUB | BPF_X:
		case BPF_ALU | BPF_MUL | BPF_K:
		case BPF_ALU | BPF_MUL | BPF_X:
		case BPF_ALU | BPF_DIV | BPF_K:
		case BPF_ALU | BPF_DIV | BPF_X:
		case BPF_ALU | BPF_AND | BPF_K:
		case BPF_ALU | BPF_AND | BPF_X:
		case BPF_ALU | BPF_OR | BPF_K:
		case BPF_ALU | BPF_OR | BPF_X:
		case BPF_ALU | BPF_XOR | BPF_K:
		case BPF_ALU | BPF_XOR | BPF_X:
		case BPF_ALU | BPF_LSH | BPF_K:
		case BPF_ALU | BPF_LSH | BPF_X:
		case BPF_ALU | BPF_RSH | BPF_K:
		case BPF_ALU | BPF_RSH | BPF_X:
		case BPF_ALU | BPF_NEG:
		case BPF_LD | BPF_IMM:
		case BPF_LDX | BPF_IMM:
		case BPF_MISC | BPF_TAX:
		case BPF_MISC | BPF_TXA:
		case BPF_LD | BPF_MEM:
		case BPF_LDX | BPF_MEM:
		case BPF_ST:
		case BPF_STX:
		case BPF_JMP | BPF_JA:
		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
			continue;
		default:
			return -EINVAL;
		}
	}
	return 0;
}

/**
 * seccomp_run_filters - evaluates all seccomp filters against @sd
 * @sd: optional seccomp data to be passed to filters
 * @match: stores struct seccomp_filter that resulted in the return value,
 *         unless filter returned SECCOMP_RET_ALLOW, in which case it will
 *         be unchanged.
 *
 * Returns valid seccomp BPF response codes.
 */
#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL)))
static u32 seccomp_run_filters(const struct seccomp_data *sd,
			       struct seccomp_filter **match)
{
	u32 ret = SECCOMP_RET_ALLOW;
	/* Make sure cross-thread synced filter points somewhere sane. */
	struct seccomp_filter *f =
			READ_ONCE(current->seccomp.filter);

	/* Ensure unexpected behavior doesn't result in failing open. */
	if (WARN_ON(f == NULL))
		return SECCOMP_RET_KILL_PROCESS;

	/*
	 * All filters in the list are evaluated and the lowest BPF return
	 * value always takes priority (ignoring the DATA).
	 */
	for (; f; f = f->prev) {
		u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd);

		if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
			ret = cur_ret;
			*match = f;
		}
	}
	return ret;
}
#endif /* CONFIG_SECCOMP_FILTER */

static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
{
	assert_spin_locked(&current->sighand->siglock);

	if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
		return false;

	return true;
}

void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }

static inline void seccomp_assign_mode(struct task_struct *task,
				       unsigned long seccomp_mode,
				       unsigned long flags)
{
	assert_spin_locked(&task->sighand->siglock);

	task->seccomp.mode = seccomp_mode;
	/*
	 * Make sure TIF_SECCOMP cannot be set before the mode (and
	 * filter) is set.
	 */
	smp_mb__before_atomic();
	/* Assume default seccomp processes want spec flaw mitigation. */
	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
		arch_seccomp_spec_mitigate(task);
	set_tsk_thread_flag(task, TIF_SECCOMP);
}

#ifdef CONFIG_SECCOMP_FILTER
/* Returns 1 if the parent is an ancestor of the child. */
static int is_ancestor(struct seccomp_filter *parent,
		       struct seccomp_filter *child)
{
	/* NULL is the root ancestor. */
	if (parent == NULL)
		return 1;
	for (; child; child = child->prev)
		if (child == parent)
			return 1;
	return 0;
}

/**
 * seccomp_can_sync_threads: checks if all threads can be synchronized
 *
 * Expects sighand and cred_guard_mutex locks to be held.
 *
 * Returns 0 on success, -ve on error, or the pid of a thread which was
 * either not in the correct seccomp mode or did not have an ancestral
 * seccomp filter.
 */
static inline pid_t seccomp_can_sync_threads(void)
{
	struct task_struct *thread, *caller;

	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
	assert_spin_locked(&current->sighand->siglock);

	/* Validate all threads being eligible for synchronization. */
	caller = current;
	for_each_thread(caller, thread) {
		pid_t failed;

		/* Skip current, since it is initiating the sync. */
		if (thread == caller)
			continue;

		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
		    (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
		     is_ancestor(thread->seccomp.filter,
				 caller->seccomp.filter)))
			continue;

		/* Return the first thread that cannot be synchronized. */
		failed = task_pid_vnr(thread);
		/* If the pid cannot be resolved, then return -ESRCH */
		if (WARN_ON(failed == 0))
			failed = -ESRCH;
		return failed;
	}

	return 0;
}

static inline void seccomp_filter_free(struct seccomp_filter *filter)
{
	if (filter) {
		bpf_prog_destroy(filter->prog);
		kfree(filter);
	}
}

static void __seccomp_filter_orphan(struct seccomp_filter *orig)
{
	while (orig && refcount_dec_and_test(&orig->users)) {
		if (waitqueue_active(&orig->wqh))
			wake_up_poll(&orig->wqh, EPOLLHUP);
		orig = orig->prev;
	}
}

static void __put_seccomp_filter(struct seccomp_filter *orig)
{
	/* Clean up single-reference branches iteratively. */
	while (orig && refcount_dec_and_test(&orig->refs)) {
		struct seccomp_filter *freeme = orig;
		orig = orig->prev;
		seccomp_filter_free(freeme);
	}
}

static void __seccomp_filter_release(struct seccomp_filter *orig)
{
	/* Notify about any unused filters in the task's former filter tree. */
	__seccomp_filter_orphan(orig);
	/* Finally drop all references to the task's former tree. */
	__put_seccomp_filter(orig);
}

/**
 * seccomp_filter_release - Detach the task from its filter tree,
 *			    drop its reference count, and notify
 *			    about unused filters
 *
 * This function should only be called when the task is exiting as
 * it detaches it from its filter tree. As such, READ_ONCE() and
 * barriers are not needed here, as would normally be needed.
 */
void seccomp_filter_release(struct task_struct *tsk)
{
	struct seccomp_filter *orig = tsk->seccomp.filter;

	/* Detach task from its filter tree. */
	tsk->seccomp.filter = NULL;
	__seccomp_filter_release(orig);
}

/**
 * seccomp_sync_threads: sets all threads to use current's filter
 *
 * Expects sighand and cred_guard_mutex locks to be held, and for
 * seccomp_can_sync_threads() to have returned success already
 * without dropping the locks.
 *
 */
static inline void seccomp_sync_threads(unsigned long flags)
{
	struct task_struct *thread, *caller;

	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
	assert_spin_locked(&current->sighand->siglock);

	/* Synchronize all threads. */
	caller = current;
	for_each_thread(caller, thread) {
		/* Skip current, since it needs no changes. */
		if (thread == caller)
			continue;

		/* Get a task reference for the new leaf node. */
		get_seccomp_filter(caller);

		/*
		 * Drop the task reference to the shared ancestor since
		 * current's path will hold a reference.  (This also
		 * allows a put before the assignment.)
		 */
		__seccomp_filter_release(thread->seccomp.filter);

		/* Make our new filter tree visible. */
		smp_store_release(&thread->seccomp.filter,
				  caller->seccomp.filter);
		atomic_set(&thread->seccomp.filter_count,
			   atomic_read(&thread->seccomp.filter_count));

		/*
		 * Don't let an unprivileged task work around
		 * the no_new_privs restriction by creating
		 * a thread that sets it up, enters seccomp,
		 * then dies.
		 */
		if (task_no_new_privs(caller))
			task_set_no_new_privs(thread);

		/*
		 * Opt the other thread into seccomp if needed.
		 * As threads are considered to be trust-realm
		 * equivalent (see ptrace_may_access), it is safe to
		 * allow one thread to transition the other.
		 */
		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
					    flags);
	}
}

/**
 * seccomp_prepare_filter: Prepares a seccomp filter for use.
 * @fprog: BPF program to install
 *
 * Returns filter on success or an ERR_PTR on failure.
 */
static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
	struct seccomp_filter *sfilter;
	int ret;
	const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE);

	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
		return ERR_PTR(-EINVAL);

	BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));

	/*
	 * Installing a seccomp filter requires that the task has
	 * CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
	 * This avoids scenarios where unprivileged tasks can affect the
	 * behavior of privileged children.
	 */
	if (!task_no_new_privs(current) &&
	    security_capable(current_cred(), current_user_ns(),
				     CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0)
		return ERR_PTR(-EACCES);

	/* Allocate a new seccomp_filter */
	sfilter = kzalloc(sizeof(*sfilter), GFP_KERNEL | __GFP_NOWARN);
	if (!sfilter)
		return ERR_PTR(-ENOMEM);

	mutex_init(&sfilter->notify_lock);
	ret = bpf_prog_create_from_user(&sfilter->prog, fprog,
					seccomp_check_filter, save_orig);
	if (ret < 0) {
		kfree(sfilter);
		return ERR_PTR(ret);
	}

	refcount_set(&sfilter->refs, 1);
	refcount_set(&sfilter->users, 1);
	init_waitqueue_head(&sfilter->wqh);

	return sfilter;
}

/**
 * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog
 * @user_filter: pointer to the user data containing a sock_fprog.
 *
 * Returns 0 on success and non-zero otherwise.
 */
static struct seccomp_filter *
seccomp_prepare_user_filter(const char __user *user_filter)
{
	struct sock_fprog fprog;
	struct seccomp_filter *filter = ERR_PTR(-EFAULT);

#ifdef CONFIG_COMPAT
	if (in_compat_syscall()) {
		struct compat_sock_fprog fprog32;
		if (copy_from_user(&fprog32, user_filter, sizeof(fprog32)))
			goto out;
		fprog.len = fprog32.len;
		fprog.filter = compat_ptr(fprog32.filter);
	} else /* falls through to the if below. */
#endif
	if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
		goto out;
	filter = seccomp_prepare_filter(&fprog);
out:
	return filter;
}

/**
 * seccomp_attach_filter: validate and attach filter
 * @flags:  flags to change filter behavior
 * @filter: seccomp filter to add to the current process
 *
 * Caller must be holding current->sighand->siglock lock.
 *
 * Returns 0 on success, -ve on error, or
 *   - in TSYNC mode: the pid of a thread which was either not in the correct
 *     seccomp mode or did not have an ancestral seccomp filter
 *   - in NEW_LISTENER mode: the fd of the new listener
 */
static long seccomp_attach_filter(unsigned int flags,
				  struct seccomp_filter *filter)
{
	unsigned long total_insns;
	struct seccomp_filter *walker;

	assert_spin_locked(&current->sighand->siglock);

	/* Validate resulting filter length. */
	total_insns = filter->prog->len;
	for (walker = current->seccomp.filter; walker; walker = walker->prev)
		total_insns += walker->prog->len + 4;  /* 4 instr penalty */
	if (total_insns > MAX_INSNS_PER_PATH)
		return -ENOMEM;

	/* If thread sync has been requested, check that it is possible. */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
		int ret;

		ret = seccomp_can_sync_threads();
		if (ret) {
			if (flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
				return -ESRCH;
			else
				return ret;
		}
	}

	/* Set log flag, if present. */
	if (flags & SECCOMP_FILTER_FLAG_LOG)
		filter->log = true;

	/*
	 * If there is an existing filter, make it the prev and don't drop its
	 * task reference.
	 */
	filter->prev = current->seccomp.filter;
	current->seccomp.filter = filter;
	atomic_inc(&current->seccomp.filter_count);

	/* Now that the new filter is in place, synchronize to all threads. */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
		seccomp_sync_threads(flags);

	return 0;
}

static void __get_seccomp_filter(struct seccomp_filter *filter)
{
	refcount_inc(&filter->refs);
}

/* get_seccomp_filter - increments the reference count of the filter on @tsk */
void get_seccomp_filter(struct task_struct *tsk)
{
	struct seccomp_filter *orig = tsk->seccomp.filter;
	if (!orig)
		return;
	__get_seccomp_filter(orig);
	refcount_inc(&orig->users);
}

static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason)
{
	clear_siginfo(info);
	info->si_signo = SIGSYS;
	info->si_code = SYS_SECCOMP;
	info->si_call_addr = (void __user *)KSTK_EIP(current);
	info->si_errno = reason;
	info->si_arch = syscall_get_arch(current);
	info->si_syscall = syscall;
}

/**
 * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
 * @syscall: syscall number to send to userland
 * @reason: filter-supplied reason code to send to userland (via si_errno)
 *
 * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
 */
static void seccomp_send_sigsys(int syscall, int reason)
{
	struct kernel_siginfo info;
	seccomp_init_siginfo(&info, syscall, reason);
	force_sig_info(&info);
}
#endif	/* CONFIG_SECCOMP_FILTER */

/* For use with seccomp_actions_logged */
#define SECCOMP_LOG_KILL_PROCESS	(1 << 0)
#define SECCOMP_LOG_KILL_THREAD		(1 << 1)
#define SECCOMP_LOG_TRAP		(1 << 2)
#define SECCOMP_LOG_ERRNO		(1 << 3)
#define SECCOMP_LOG_TRACE		(1 << 4)
#define SECCOMP_LOG_LOG			(1 << 5)
#define SECCOMP_LOG_ALLOW		(1 << 6)
#define SECCOMP_LOG_USER_NOTIF		(1 << 7)

static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS |
				    SECCOMP_LOG_KILL_THREAD  |
				    SECCOMP_LOG_TRAP  |
				    SECCOMP_LOG_ERRNO |
				    SECCOMP_LOG_USER_NOTIF |
				    SECCOMP_LOG_TRACE |
				    SECCOMP_LOG_LOG;

static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
			       bool requested)
{
	bool log = false;

	switch (action) {
	case SECCOMP_RET_ALLOW:
		break;
	case SECCOMP_RET_TRAP:
		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP;
		break;
	case SECCOMP_RET_ERRNO:
		log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO;
		break;
	case SECCOMP_RET_TRACE:
		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE;
		break;
	case SECCOMP_RET_USER_NOTIF:
		log = requested && seccomp_actions_logged & SECCOMP_LOG_USER_NOTIF;
		break;
	case SECCOMP_RET_LOG:
		log = seccomp_actions_logged & SECCOMP_LOG_LOG;
		break;
	case SECCOMP_RET_KILL_THREAD:
		log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD;
		break;
	case SECCOMP_RET_KILL_PROCESS:
	default:
		log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS;
	}

	/*
	 * Emit an audit message when the action is RET_KILL_*, RET_LOG, or the
	 * FILTER_FLAG_LOG bit was set. The admin has the ability to silence
	 * any action from being logged by removing the action name from the
	 * seccomp_actions_logged sysctl.
	 */
	if (!log)
		return;

	audit_seccomp(syscall, signr, action);
}

/*
 * Secure computing mode 1 allows only read/write/exit/sigreturn.
 * To be fully secure this must be combined with rlimit
 * to limit the stack allocations too.
 */
static const int mode1_syscalls[] = {
	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
	0, /* null terminated */
};

static void __secure_computing_strict(int this_syscall)
{
	const int *syscall_whitelist = mode1_syscalls;
#ifdef CONFIG_COMPAT
	if (in_compat_syscall())
		syscall_whitelist = get_compat_mode1_syscalls();
#endif
	do {
		if (*syscall_whitelist == this_syscall)
			return;
	} while (*++syscall_whitelist);

#ifdef SECCOMP_DEBUG
	dump_stack();
#endif
	seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true);
	do_exit(SIGKILL);
}

#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER
void secure_computing_strict(int this_syscall)
{
	int mode = current->seccomp.mode;

	if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
		return;

	if (mode == SECCOMP_MODE_DISABLED)
		return;
	else if (mode == SECCOMP_MODE_STRICT)
		__secure_computing_strict(this_syscall);
	else
		BUG();
}
#else

#ifdef CONFIG_SECCOMP_FILTER
static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
{
	/*
	 * Note: overflow is ok here, the id just needs to be unique per
	 * filter.
	 */
	lockdep_assert_held(&filter->notify_lock);
	return filter->notif->next_id++;
}

static int seccomp_do_user_notification(int this_syscall,
					struct seccomp_filter *match,
					const struct seccomp_data *sd)
{
	int err;
	u32 flags = 0;
	long ret = 0;
	struct seccomp_knotif n = {};

	mutex_lock(&match->notify_lock);
	err = -ENOSYS;
	if (!match->notif)
		goto out;

	n.task = current;
	n.state = SECCOMP_NOTIFY_INIT;
	n.data = sd;
	n.id = seccomp_next_notify_id(match);
	init_completion(&n.ready);
	list_add(&n.list, &match->notif->notifications);

	up(&match->notif->request);
	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
	mutex_unlock(&match->notify_lock);

	/*
	 * This is where we wait for a reply from userspace.
	 */
	err = wait_for_completion_interruptible(&n.ready);
	mutex_lock(&match->notify_lock);
	if (err == 0) {
		ret = n.val;
		err = n.error;
		flags = n.flags;
	}

	/*
	 * Note that it's possible the listener died in between the time when
	 * we were notified of a respons (or a signal) and when we were able to
	 * re-acquire the lock, so only delete from the list if the
	 * notification actually exists.
	 *
	 * Also note that this test is only valid because there's no way to
	 * *reattach* to a notifier right now. If one is added, we'll need to
	 * keep track of the notif itself and make sure they match here.
	 */
	if (match->notif)
		list_del(&n.list);
out:
	mutex_unlock(&match->notify_lock);

	/* Userspace requests to continue the syscall. */
	if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE)
		return 0;

	syscall_set_return_value(current, task_pt_regs(current),
				 err, ret);
	return -1;
}

static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
			    const bool recheck_after_trace)
{
	u32 filter_ret, action;
	struct seccomp_filter *match = NULL;
	int data;
	struct seccomp_data sd_local;

	/*
	 * Make sure that any changes to mode from another thread have
	 * been seen after TIF_SECCOMP was seen.
	 */
	rmb();

	if (!sd) {
		populate_seccomp_data(&sd_local);
		sd = &sd_local;
	}

	filter_ret = seccomp_run_filters(sd, &match);
	data = filter_ret & SECCOMP_RET_DATA;
	action = filter_ret & SECCOMP_RET_ACTION_FULL;

	switch (action) {
	case SECCOMP_RET_ERRNO:
		/* Set low-order bits as an errno, capped at MAX_ERRNO. */
		if (data > MAX_ERRNO)
			data = MAX_ERRNO;
		syscall_set_return_value(current, task_pt_regs(current),
					 -data, 0);
		goto skip;

	case SECCOMP_RET_TRAP:
		/* Show the handler the original registers. */
		syscall_rollback(current, task_pt_regs(current));
		/* Let the filter pass back 16 bits of data. */
		seccomp_send_sigsys(this_syscall, data);
		goto skip;

	case SECCOMP_RET_TRACE:
		/* We've been put in this state by the ptracer already. */
		if (recheck_after_trace)
			return 0;

		/* ENOSYS these calls if there is no tracer attached. */
		if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
			syscall_set_return_value(current,
						 task_pt_regs(current),
						 -ENOSYS, 0);
			goto skip;
		}

		/* Allow the BPF to provide the event message */
		ptrace_event(PTRACE_EVENT_SECCOMP, data);
		/*
		 * The delivery of a fatal signal during event
		 * notification may silently skip tracer notification,
		 * which could leave us with a potentially unmodified
		 * syscall that the tracer would have liked to have
		 * changed. Since the process is about to die, we just
		 * force the syscall to be skipped and let the signal
		 * kill the process and correctly handle any tracer exit
		 * notifications.
		 */
		if (fatal_signal_pending(current))
			goto skip;
		/* Check if the tracer forced the syscall to be skipped. */
		this_syscall = syscall_get_nr(current, task_pt_regs(current));
		if (this_syscall < 0)
			goto skip;

		/*
		 * Recheck the syscall, since it may have changed. This
		 * intentionally uses a NULL struct seccomp_data to force
		 * a reload of all registers. This does not goto skip since
		 * a skip would have already been reported.
		 */
		if (__seccomp_filter(this_syscall, NULL, true))
			return -1;

		return 0;

	case SECCOMP_RET_USER_NOTIF:
		if (seccomp_do_user_notification(this_syscall, match, sd))
			goto skip;

		return 0;

	case SECCOMP_RET_LOG:
		seccomp_log(this_syscall, 0, action, true);
		return 0;

	case SECCOMP_RET_ALLOW:
		/*
		 * Note that the "match" filter will always be NULL for
		 * this action since SECCOMP_RET_ALLOW is the starting
		 * state in seccomp_run_filters().
		 */
		return 0;

	case SECCOMP_RET_KILL_THREAD:
	case SECCOMP_RET_KILL_PROCESS:
	default:
		seccomp_log(this_syscall, SIGSYS, action, true);
		/* Dump core only if this is the last remaining thread. */
		if (action == SECCOMP_RET_KILL_PROCESS ||
		    get_nr_threads(current) == 1) {
			kernel_siginfo_t info;

			/* Show the original registers in the dump. */
			syscall_rollback(current, task_pt_regs(current));
			/* Trigger a manual coredump since do_exit skips it. */
			seccomp_init_siginfo(&info, this_syscall, data);
			do_coredump(&info);
		}
		if (action == SECCOMP_RET_KILL_PROCESS)
			do_group_exit(SIGSYS);
		else
			do_exit(SIGSYS);
	}

	unreachable();

skip:
	seccomp_log(this_syscall, 0, action, match ? match->log : false);
	return -1;
}
#else
static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
			    const bool recheck_after_trace)
{
	BUG();
}
#endif

int __secure_computing(const struct seccomp_data *sd)
{
	int mode = current->seccomp.mode;
	int this_syscall;

	if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
		return 0;

	this_syscall = sd ? sd->nr :
		syscall_get_nr(current, task_pt_regs(current));

	switch (mode) {
	case SECCOMP_MODE_STRICT:
		__secure_computing_strict(this_syscall);  /* may call do_exit */
		return 0;
	case SECCOMP_MODE_FILTER:
		return __seccomp_filter(this_syscall, sd, false);
	default:
		BUG();
	}
}
#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */

long prctl_get_seccomp(void)
{
	return current->seccomp.mode;
}

/**
 * seccomp_set_mode_strict: internal function for setting strict seccomp
 *
 * Once current->seccomp.mode is non-zero, it may not be changed.
 *
 * Returns 0 on success or -EINVAL on failure.
 */
static long seccomp_set_mode_strict(void)
{
	const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
	long ret = -EINVAL;

	spin_lock_irq(&current->sighand->siglock);

	if (!seccomp_may_assign_mode(seccomp_mode))
		goto out;

#ifdef TIF_NOTSC
	disable_TSC();
#endif
	seccomp_assign_mode(current, seccomp_mode, 0);
	ret = 0;

out:
	spin_unlock_irq(&current->sighand->siglock);

	return ret;
}

#ifdef CONFIG_SECCOMP_FILTER
static int seccomp_notify_release(struct inode *inode, struct file *file)
{
	struct seccomp_filter *filter = file->private_data;
	struct seccomp_knotif *knotif;

	if (!filter)
		return 0;

	mutex_lock(&filter->notify_lock);

	/*
	 * If this file is being closed because e.g. the task who owned it
	 * died, let's wake everyone up who was waiting on us.
	 */
	list_for_each_entry(knotif, &filter->notif->notifications, list) {
		if (knotif->state == SECCOMP_NOTIFY_REPLIED)
			continue;

		knotif->state = SECCOMP_NOTIFY_REPLIED;
		knotif->error = -ENOSYS;
		knotif->val = 0;

		complete(&knotif->ready);
	}

	kfree(filter->notif);
	filter->notif = NULL;
	mutex_unlock(&filter->notify_lock);
	__put_seccomp_filter(filter);
	return 0;
}

/* must be called with notif_lock held */
static inline struct seccomp_knotif *
find_notification(struct seccomp_filter *filter, u64 id)
{
	struct seccomp_knotif *cur;

	lockdep_assert_held(&filter->notify_lock);

	list_for_each_entry(cur, &filter->notif->notifications, list) {
		if (cur->id == id)
			return cur;
	}

	return NULL;
}


static long seccomp_notify_recv(struct seccomp_filter *filter,
				void __user *buf)
{
	struct seccomp_knotif *knotif = NULL, *cur;
	struct seccomp_notif unotif;
	ssize_t ret;

	/* Verify that we're not given garbage to keep struct extensible. */
	ret = check_zeroed_user(buf, sizeof(unotif));
	if (ret < 0)
		return ret;
	if (!ret)
		return -EINVAL;

	memset(&unotif, 0, sizeof(unotif));

	ret = down_interruptible(&filter->notif->request);
	if (ret < 0)
		return ret;

	mutex_lock(&filter->notify_lock);
	list_for_each_entry(cur, &filter->notif->notifications, list) {
		if (cur->state == SECCOMP_NOTIFY_INIT) {
			knotif = cur;
			break;
		}
	}

	/*
	 * If we didn't find a notification, it could be that the task was
	 * interrupted by a fatal signal between the time we were woken and
	 * when we were able to acquire the rw lock.
	 */
	if (!knotif) {
		ret = -ENOENT;
		goto out;
	}

	unotif.id = knotif->id;
	unotif.pid = task_pid_vnr(knotif->task);
	unotif.data = *(knotif->data);

	knotif->state = SECCOMP_NOTIFY_SENT;
	wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM);
	ret = 0;
out:
	mutex_unlock(&filter->notify_lock);

	if (ret == 0 && copy_to_user(buf, &unotif, sizeof(unotif))) {
		ret = -EFAULT;

		/*
		 * Userspace screwed up. To make sure that we keep this
		 * notification alive, let's reset it back to INIT. It
		 * may have died when we released the lock, so we need to make
		 * sure it's still around.
		 */
		mutex_lock(&filter->notify_lock);
		knotif = find_notification(filter, unotif.id);
		if (knotif) {
			knotif->state = SECCOMP_NOTIFY_INIT;
			up(&filter->notif->request);
		}
		mutex_unlock(&filter->notify_lock);
	}

	return ret;
}

static long seccomp_notify_send(struct seccomp_filter *filter,
				void __user *buf)
{
	struct seccomp_notif_resp resp = {};
	struct seccomp_knotif *knotif;
	long ret;

	if (copy_from_user(&resp, buf, sizeof(resp)))
		return -EFAULT;

	if (resp.flags & ~SECCOMP_USER_NOTIF_FLAG_CONTINUE)
		return -EINVAL;

	if ((resp.flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) &&
	    (resp.error || resp.val))
		return -EINVAL;

	ret = mutex_lock_interruptible(&filter->notify_lock);
	if (ret < 0)
		return ret;

	knotif = find_notification(filter, resp.id);
	if (!knotif) {
		ret = -ENOENT;
		goto out;
	}

	/* Allow exactly one reply. */
	if (knotif->state != SECCOMP_NOTIFY_SENT) {
		ret = -EINPROGRESS;
		goto out;
	}

	ret = 0;
	knotif->state = SECCOMP_NOTIFY_REPLIED;
	knotif->error = resp.error;
	knotif->val = resp.val;
	knotif->flags = resp.flags;
	complete(&knotif->ready);
out:
	mutex_unlock(&filter->notify_lock);
	return ret;
}

static long seccomp_notify_id_valid(struct seccomp_filter *filter,
				    void __user *buf)
{
	struct seccomp_knotif *knotif;
	u64 id;
	long ret;

	if (copy_from_user(&id, buf, sizeof(id)))
		return -EFAULT;

	ret = mutex_lock_interruptible(&filter->notify_lock);
	if (ret < 0)
		return ret;

	knotif = find_notification(filter, id);
	if (knotif && knotif->state == SECCOMP_NOTIFY_SENT)
		ret = 0;
	else
		ret = -ENOENT;

	mutex_unlock(&filter->notify_lock);
	return ret;
}

static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
				 unsigned long arg)
{
	struct seccomp_filter *filter = file->private_data;
	void __user *buf = (void __user *)arg;

	switch (cmd) {
	case SECCOMP_IOCTL_NOTIF_RECV:
		return seccomp_notify_recv(filter, buf);
	case SECCOMP_IOCTL_NOTIF_SEND:
		return seccomp_notify_send(filter, buf);
	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
	case SECCOMP_IOCTL_NOTIF_ID_VALID:
		return seccomp_notify_id_valid(filter, buf);
	default:
		return -EINVAL;
	}
}

static __poll_t seccomp_notify_poll(struct file *file,
				    struct poll_table_struct *poll_tab)
{
	struct seccomp_filter *filter = file->private_data;
	__poll_t ret = 0;
	struct seccomp_knotif *cur;

	poll_wait(file, &filter->wqh, poll_tab);

	if (mutex_lock_interruptible(&filter->notify_lock) < 0)
		return EPOLLERR;

	list_for_each_entry(cur, &filter->notif->notifications, list) {
		if (cur->state == SECCOMP_NOTIFY_INIT)
			ret |= EPOLLIN | EPOLLRDNORM;
		if (cur->state == SECCOMP_NOTIFY_SENT)
			ret |= EPOLLOUT | EPOLLWRNORM;
		if ((ret & EPOLLIN) && (ret & EPOLLOUT))
			break;
	}

	mutex_unlock(&filter->notify_lock);

	if (refcount_read(&filter->users) == 0)
		ret |= EPOLLHUP;

	return ret;
}

static const struct file_operations seccomp_notify_ops = {
	.poll = seccomp_notify_poll,
	.release = seccomp_notify_release,
	.unlocked_ioctl = seccomp_notify_ioctl,
	.compat_ioctl = seccomp_notify_ioctl,
};

static struct file *init_listener(struct seccomp_filter *filter)
{
	struct file *ret = ERR_PTR(-EBUSY);
	struct seccomp_filter *cur;

	for (cur = current->seccomp.filter; cur; cur = cur->prev) {
		if (cur->notif)
			goto out;
	}

	ret = ERR_PTR(-ENOMEM);
	filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL);
	if (!filter->notif)
		goto out;

	sema_init(&filter->notif->request, 0);
	filter->notif->next_id = get_random_u64();
	INIT_LIST_HEAD(&filter->notif->notifications);

	ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops,
				 filter, O_RDWR);
	if (IS_ERR(ret))
		goto out_notif;

	/* The file has a reference to it now */
	__get_seccomp_filter(filter);

out_notif:
	if (IS_ERR(ret))
		kfree(filter->notif);
out:
	return ret;
}

/**
 * seccomp_set_mode_filter: internal function for setting seccomp filter
 * @flags:  flags to change filter behavior
 * @filter: struct sock_fprog containing filter
 *
 * This function may be called repeatedly to install additional filters.
 * Every filter successfully installed will be evaluated (in reverse order)
 * for each system call the task makes.
 *
 * Once current->seccomp.mode is non-zero, it may not be changed.
 *
 * Returns 0 on success or -EINVAL on failure.
 */
static long seccomp_set_mode_filter(unsigned int flags,
				    const char __user *filter)
{
	const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
	struct seccomp_filter *prepared = NULL;
	long ret = -EINVAL;
	int listener = -1;
	struct file *listener_f = NULL;

	/* Validate flags. */
	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
		return -EINVAL;

	/*
	 * In the successful case, NEW_LISTENER returns the new listener fd.
	 * But in the failure case, TSYNC returns the thread that died. If you
	 * combine these two flags, there's no way to tell whether something
	 * succeeded or failed. So, let's disallow this combination if the user
	 * has not explicitly requested no errors from TSYNC.
	 */
	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) &&
	    ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0))
		return -EINVAL;

	/* Prepare the new filter before holding any locks. */
	prepared = seccomp_prepare_user_filter(filter);
	if (IS_ERR(prepared))
		return PTR_ERR(prepared);

	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
		listener = get_unused_fd_flags(O_CLOEXEC);
		if (listener < 0) {
			ret = listener;
			goto out_free;
		}

		listener_f = init_listener(prepared);
		if (IS_ERR(listener_f)) {
			put_unused_fd(listener);
			ret = PTR_ERR(listener_f);
			goto out_free;
		}
	}

	/*
	 * Make sure we cannot change seccomp or nnp state via TSYNC
	 * while another thread is in the middle of calling exec.
	 */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
	    mutex_lock_killable(&current->signal->cred_guard_mutex))
		goto out_put_fd;

	spin_lock_irq(&current->sighand->siglock);

	if (!seccomp_may_assign_mode(seccomp_mode))
		goto out;

	ret = seccomp_attach_filter(flags, prepared);
	if (ret)
		goto out;
	/* Do not free the successfully attached filter. */
	prepared = NULL;

	seccomp_assign_mode(current, seccomp_mode, flags);
out:
	spin_unlock_irq(&current->sighand->siglock);
	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
		mutex_unlock(&current->signal->cred_guard_mutex);
out_put_fd:
	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
		if (ret) {
			listener_f->private_data = NULL;
			fput(listener_f);
			put_unused_fd(listener);
		} else {
			fd_install(listener, listener_f);
			ret = listener;
		}
	}
out_free:
	seccomp_filter_free(prepared);
	return ret;
}
#else
static inline long seccomp_set_mode_filter(unsigned int flags,
					   const char __user *filter)
{
	return -EINVAL;
}
#endif

static long seccomp_get_action_avail(const char __user *uaction)
{
	u32 action;

	if (copy_from_user(&action, uaction, sizeof(action)))
		return -EFAULT;

	switch (action) {
	case SECCOMP_RET_KILL_PROCESS:
	case SECCOMP_RET_KILL_THREAD:
	case SECCOMP_RET_TRAP:
	case SECCOMP_RET_ERRNO:
	case SECCOMP_RET_USER_NOTIF:
	case SECCOMP_RET_TRACE:
	case SECCOMP_RET_LOG:
	case SECCOMP_RET_ALLOW:
		break;
	default:
		return -EOPNOTSUPP;
	}

	return 0;
}

static long seccomp_get_notif_sizes(void __user *usizes)
{
	struct seccomp_notif_sizes sizes = {
		.seccomp_notif = sizeof(struct seccomp_notif),
		.seccomp_notif_resp = sizeof(struct seccomp_notif_resp),
		.seccomp_data = sizeof(struct seccomp_data),
	};

	if (copy_to_user(usizes, &sizes, sizeof(sizes)))
		return -EFAULT;

	return 0;
}

/* Common entry point for both prctl and syscall. */
static long do_seccomp(unsigned int op, unsigned int flags,
		       void __user *uargs)
{
	switch (op) {
	case SECCOMP_SET_MODE_STRICT:
		if (flags != 0 || uargs != NULL)
			return -EINVAL;
		return seccomp_set_mode_strict();
	case SECCOMP_SET_MODE_FILTER:
		return seccomp_set_mode_filter(flags, uargs);
	case SECCOMP_GET_ACTION_AVAIL:
		if (flags != 0)
			return -EINVAL;

		return seccomp_get_action_avail(uargs);
	case SECCOMP_GET_NOTIF_SIZES:
		if (flags != 0)
			return -EINVAL;

		return seccomp_get_notif_sizes(uargs);
	default:
		return -EINVAL;
	}
}

SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
			 void __user *, uargs)
{
	return do_seccomp(op, flags, uargs);
}

/**
 * prctl_set_seccomp: configures current->seccomp.mode
 * @seccomp_mode: requested mode to use
 * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
 *
 * Returns 0 on success or -EINVAL on failure.
 */
long prctl_set_seccomp(unsigned long seccomp_mode, void __user *filter)
{
	unsigned int op;
	void __user *uargs;

	switch (seccomp_mode) {
	case SECCOMP_MODE_STRICT:
		op = SECCOMP_SET_MODE_STRICT;
		/*
		 * Setting strict mode through prctl always ignored filter,
		 * so make sure it is always NULL here to pass the internal
		 * check in do_seccomp().
		 */
		uargs = NULL;
		break;
	case SECCOMP_MODE_FILTER:
		op = SECCOMP_SET_MODE_FILTER;
		uargs = filter;
		break;
	default:
		return -EINVAL;
	}

	/* prctl interface doesn't have flags, so they are always zero. */
	return do_seccomp(op, 0, uargs);
}

#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
static struct seccomp_filter *get_nth_filter(struct task_struct *task,
					     unsigned long filter_off)
{
	struct seccomp_filter *orig, *filter;
	unsigned long count;

	/*
	 * Note: this is only correct because the caller should be the (ptrace)
	 * tracer of the task, otherwise lock_task_sighand is needed.
	 */
	spin_lock_irq(&task->sighand->siglock);

	if (task->seccomp.mode != SECCOMP_MODE_FILTER) {
		spin_unlock_irq(&task->sighand->siglock);
		return ERR_PTR(-EINVAL);
	}

	orig = task->seccomp.filter;
	__get_seccomp_filter(orig);
	spin_unlock_irq(&task->sighand->siglock);

	count = 0;
	for (filter = orig; filter; filter = filter->prev)
		count++;

	if (filter_off >= count) {
		filter = ERR_PTR(-ENOENT);
		goto out;
	}

	count -= filter_off;
	for (filter = orig; filter && count > 1; filter = filter->prev)
		count--;

	if (WARN_ON(count != 1 || !filter)) {
		filter = ERR_PTR(-ENOENT);
		goto out;
	}

	__get_seccomp_filter(filter);

out:
	__put_seccomp_filter(orig);
	return filter;
}

long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
			void __user *data)
{
	struct seccomp_filter *filter;
	struct sock_fprog_kern *fprog;
	long ret;

	if (!capable(CAP_SYS_ADMIN) ||
	    current->seccomp.mode != SECCOMP_MODE_DISABLED) {
		return -EACCES;
	}

	filter = get_nth_filter(task, filter_off);
	if (IS_ERR(filter))
		return PTR_ERR(filter);

	fprog = filter->prog->orig_prog;
	if (!fprog) {
		/* This must be a new non-cBPF filter, since we save
		 * every cBPF filter's orig_prog above when
		 * CONFIG_CHECKPOINT_RESTORE is enabled.
		 */
		ret = -EMEDIUMTYPE;
		goto out;
	}

	ret = fprog->len;
	if (!data)
		goto out;

	if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
		ret = -EFAULT;

out:
	__put_seccomp_filter(filter);
	return ret;
}

long seccomp_get_metadata(struct task_struct *task,
			  unsigned long size, void __user *data)
{
	long ret;
	struct seccomp_filter *filter;
	struct seccomp_metadata kmd = {};

	if (!capable(CAP_SYS_ADMIN) ||
	    current->seccomp.mode != SECCOMP_MODE_DISABLED) {
		return -EACCES;
	}

	size = min_t(unsigned long, size, sizeof(kmd));

	if (size < sizeof(kmd.filter_off))
		return -EINVAL;

	if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off)))
		return -EFAULT;

	filter = get_nth_filter(task, kmd.filter_off);
	if (IS_ERR(filter))
		return PTR_ERR(filter);

	if (filter->log)
		kmd.flags |= SECCOMP_FILTER_FLAG_LOG;

	ret = size;
	if (copy_to_user(data, &kmd, size))
		ret = -EFAULT;

	__put_seccomp_filter(filter);
	return ret;
}
#endif

#ifdef CONFIG_SYSCTL

/* Human readable action names for friendly sysctl interaction */
#define SECCOMP_RET_KILL_PROCESS_NAME	"kill_process"
#define SECCOMP_RET_KILL_THREAD_NAME	"kill_thread"
#define SECCOMP_RET_TRAP_NAME		"trap"
#define SECCOMP_RET_ERRNO_NAME		"errno"
#define SECCOMP_RET_USER_NOTIF_NAME	"user_notif"
#define SECCOMP_RET_TRACE_NAME		"trace"
#define SECCOMP_RET_LOG_NAME		"log"
#define SECCOMP_RET_ALLOW_NAME		"allow"

static const char seccomp_actions_avail[] =
				SECCOMP_RET_KILL_PROCESS_NAME	" "
				SECCOMP_RET_KILL_THREAD_NAME	" "
				SECCOMP_RET_TRAP_NAME		" "
				SECCOMP_RET_ERRNO_NAME		" "
				SECCOMP_RET_USER_NOTIF_NAME     " "
				SECCOMP_RET_TRACE_NAME		" "
				SECCOMP_RET_LOG_NAME		" "
				SECCOMP_RET_ALLOW_NAME;

struct seccomp_log_name {
	u32		log;
	const char	*name;
};

static const struct seccomp_log_name seccomp_log_names[] = {
	{ SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME },
	{ SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME },
	{ SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME },
	{ SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME },
	{ SECCOMP_LOG_USER_NOTIF, SECCOMP_RET_USER_NOTIF_NAME },
	{ SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME },
	{ SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME },
	{ SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME },
	{ }
};

static bool seccomp_names_from_actions_logged(char *names, size_t size,
					      u32 actions_logged,
					      const char *sep)
{
	const struct seccomp_log_name *cur;
	bool append_sep = false;

	for (cur = seccomp_log_names; cur->name && size; cur++) {
		ssize_t ret;

		if (!(actions_logged & cur->log))
			continue;

		if (append_sep) {
			ret = strscpy(names, sep, size);
			if (ret < 0)
				return false;

			names += ret;
			size -= ret;
		} else
			append_sep = true;

		ret = strscpy(names, cur->name, size);
		if (ret < 0)
			return false;

		names += ret;
		size -= ret;
	}

	return true;
}

static bool seccomp_action_logged_from_name(u32 *action_logged,
					    const char *name)
{
	const struct seccomp_log_name *cur;

	for (cur = seccomp_log_names; cur->name; cur++) {
		if (!strcmp(cur->name, name)) {
			*action_logged = cur->log;
			return true;
		}
	}

	return false;
}

static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names)
{
	char *name;

	*actions_logged = 0;
	while ((name = strsep(&names, " ")) && *name) {
		u32 action_logged = 0;

		if (!seccomp_action_logged_from_name(&action_logged, name))
			return false;

		*actions_logged |= action_logged;
	}

	return true;
}

static int read_actions_logged(struct ctl_table *ro_table, void __user *buffer,
			       size_t *lenp, loff_t *ppos)
{
	char names[sizeof(seccomp_actions_avail)];
	struct ctl_table table;

	memset(names, 0, sizeof(names));

	if (!seccomp_names_from_actions_logged(names, sizeof(names),
					       seccomp_actions_logged, " "))
		return -EINVAL;

	table = *ro_table;
	table.data = names;
	table.maxlen = sizeof(names);
	return proc_dostring(&table, 0, buffer, lenp, ppos);
}

static int write_actions_logged(struct ctl_table *ro_table, void __user *buffer,
				size_t *lenp, loff_t *ppos, u32 *actions_logged)
{
	char names[sizeof(seccomp_actions_avail)];
	struct ctl_table table;
	int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	memset(names, 0, sizeof(names));

	table = *ro_table;
	table.data = names;
	table.maxlen = sizeof(names);
	ret = proc_dostring(&table, 1, buffer, lenp, ppos);
	if (ret)
		return ret;

	if (!seccomp_actions_logged_from_names(actions_logged, table.data))
		return -EINVAL;

	if (*actions_logged & SECCOMP_LOG_ALLOW)
		return -EINVAL;

	seccomp_actions_logged = *actions_logged;
	return 0;
}

static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged,
				 int ret)
{
	char names[sizeof(seccomp_actions_avail)];
	char old_names[sizeof(seccomp_actions_avail)];
	const char *new = names;
	const char *old = old_names;

	if (!audit_enabled)
		return;

	memset(names, 0, sizeof(names));
	memset(old_names, 0, sizeof(old_names));

	if (ret)
		new = "?";
	else if (!actions_logged)
		new = "(none)";
	else if (!seccomp_names_from_actions_logged(names, sizeof(names),
						    actions_logged, ","))
		new = "?";

	if (!old_actions_logged)
		old = "(none)";
	else if (!seccomp_names_from_actions_logged(old_names,
						    sizeof(old_names),
						    old_actions_logged, ","))
		old = "?";

	return audit_seccomp_actions_logged(new, old, !ret);
}

static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
					  void *buffer, size_t *lenp,
					  loff_t *ppos)
{
	int ret;

	if (write) {
		u32 actions_logged = 0;
		u32 old_actions_logged = seccomp_actions_logged;

		ret = write_actions_logged(ro_table, buffer, lenp, ppos,
					   &actions_logged);
		audit_actions_logged(actions_logged, old_actions_logged, ret);
	} else
		ret = read_actions_logged(ro_table, buffer, lenp, ppos);

	return ret;
}

static struct ctl_path seccomp_sysctl_path[] = {
	{ .procname = "kernel", },
	{ .procname = "seccomp", },
	{ }
};

static struct ctl_table seccomp_sysctl_table[] = {
	{
		.procname	= "actions_avail",
		.data		= (void *) &seccomp_actions_avail,
		.maxlen		= sizeof(seccomp_actions_avail),
		.mode		= 0444,
		.proc_handler	= proc_dostring,
	},
	{
		.procname	= "actions_logged",
		.mode		= 0644,
		.proc_handler	= seccomp_actions_logged_handler,
	},
	{ }
};

static int __init seccomp_sysctl_init(void)
{
	struct ctl_table_header *hdr;

	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
	if (!hdr)
		pr_warn("sysctl registration failed\n");
	else
		kmemleak_not_leak(hdr);

	return 0;
}

device_initcall(seccomp_sysctl_init)

#endif /* CONFIG_SYSCTL */