summaryrefslogtreecommitdiff
path: root/kernel/trace/bpf_trace.c
blob: 92ba69b716dc70c087040ec1948e3afaf15c2ea5 (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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016 Facebook
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/bpf_perf_event.h>
#include <linux/filter.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include <linux/kprobes.h>
#include <linux/syscalls.h>
#include <linux/error-injection.h>

#include <asm/tlb.h>

#include "trace_probe.h"
#include "trace.h"

#define bpf_event_rcu_dereference(p)					\
	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))

#ifdef CONFIG_MODULES
struct bpf_trace_module {
	struct module *module;
	struct list_head list;
};

static LIST_HEAD(bpf_trace_modules);
static DEFINE_MUTEX(bpf_module_mutex);

static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
{
	struct bpf_raw_event_map *btp, *ret = NULL;
	struct bpf_trace_module *btm;
	unsigned int i;

	mutex_lock(&bpf_module_mutex);
	list_for_each_entry(btm, &bpf_trace_modules, list) {
		for (i = 0; i < btm->module->num_bpf_raw_events; ++i) {
			btp = &btm->module->bpf_raw_events[i];
			if (!strcmp(btp->tp->name, name)) {
				if (try_module_get(btm->module))
					ret = btp;
				goto out;
			}
		}
	}
out:
	mutex_unlock(&bpf_module_mutex);
	return ret;
}
#else
static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
{
	return NULL;
}
#endif /* CONFIG_MODULES */

u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);

/**
 * trace_call_bpf - invoke BPF program
 * @call: tracepoint event
 * @ctx: opaque context pointer
 *
 * kprobe handlers execute BPF programs via this helper.
 * Can be used from static tracepoints in the future.
 *
 * Return: BPF programs always return an integer which is interpreted by
 * kprobe handler as:
 * 0 - return from kprobe (event is filtered out)
 * 1 - store kprobe event into ring buffer
 * Other values are reserved and currently alias to 1
 */
unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
	unsigned int ret;

	if (in_nmi()) /* not supported yet */
		return 1;

	cant_sleep();

	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
		/*
		 * since some bpf program is already running on this cpu,
		 * don't call into another bpf program (same or different)
		 * and don't send kprobe event into ring-buffer,
		 * so return zero here
		 */
		ret = 0;
		goto out;
	}

	/*
	 * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
	 * to all call sites, we did a bpf_prog_array_valid() there to check
	 * whether call->prog_array is empty or not, which is
	 * a heurisitc to speed up execution.
	 *
	 * If bpf_prog_array_valid() fetched prog_array was
	 * non-NULL, we go into trace_call_bpf() and do the actual
	 * proper rcu_dereference() under RCU lock.
	 * If it turns out that prog_array is NULL then, we bail out.
	 * For the opposite, if the bpf_prog_array_valid() fetched pointer
	 * was NULL, you'll skip the prog_array with the risk of missing
	 * out of events when it was updated in between this and the
	 * rcu_dereference() which is accepted risk.
	 */
	ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);

 out:
	__this_cpu_dec(bpf_prog_active);

	return ret;
}

#ifdef CONFIG_BPF_KPROBE_OVERRIDE
BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
{
	regs_set_return_value(regs, rc);
	override_function_with_return(regs);
	return 0;
}

static const struct bpf_func_proto bpf_override_return_proto = {
	.func		= bpf_override_return,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};
#endif

BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
	   const void __user *, unsafe_ptr)
{
	int ret = probe_user_read(dst, unsafe_ptr, size);

	if (unlikely(ret < 0))
		memset(dst, 0, size);

	return ret;
}

static const struct bpf_func_proto bpf_probe_read_user_proto = {
	.func		= bpf_probe_read_user,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
	   const void __user *, unsafe_ptr)
{
	int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);

	if (unlikely(ret < 0))
		memset(dst, 0, size);

	return ret;
}

static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
	.func		= bpf_probe_read_user_str,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

static __always_inline int
bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
			     const bool compat)
{
	int ret = security_locked_down(LOCKDOWN_BPF_READ);

	if (unlikely(ret < 0))
		goto out;
	ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
	      probe_kernel_read_strict(dst, unsafe_ptr, size);
	if (unlikely(ret < 0))
out:
		memset(dst, 0, size);
	return ret;
}

BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
	   const void *, unsafe_ptr)
{
	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
}

static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
	.func		= bpf_probe_read_kernel,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
	   const void *, unsafe_ptr)
{
	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
}

static const struct bpf_func_proto bpf_probe_read_compat_proto = {
	.func		= bpf_probe_read_compat,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

static __always_inline int
bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
				 const bool compat)
{
	int ret = security_locked_down(LOCKDOWN_BPF_READ);

	if (unlikely(ret < 0))
		goto out;
	/*
	 * The strncpy_from_unsafe_*() call will likely not fill the entire
	 * buffer, but that's okay in this circumstance as we're probing
	 * arbitrary memory anyway similar to bpf_probe_read_*() and might
	 * as well probe the stack. Thus, memory is explicitly cleared
	 * only in error case, so that improper users ignoring return
	 * code altogether don't copy garbage; otherwise length of string
	 * is returned that can be used for bpf_perf_event_output() et al.
	 */
	ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
	      strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
	if (unlikely(ret < 0))
out:
		memset(dst, 0, size);
	return ret;
}

BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
	   const void *, unsafe_ptr)
{
	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
}

static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
	.func		= bpf_probe_read_kernel_str,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
	   const void *, unsafe_ptr)
{
	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
}

static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
	.func		= bpf_probe_read_compat_str,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
	   u32, size)
{
	/*
	 * Ensure we're in user context which is safe for the helper to
	 * run. This helper has no business in a kthread.
	 *
	 * access_ok() should prevent writing to non-user memory, but in
	 * some situations (nommu, temporary switch, etc) access_ok() does
	 * not provide enough validation, hence the check on KERNEL_DS.
	 *
	 * nmi_uaccess_okay() ensures the probe is not run in an interim
	 * state, when the task or mm are switched. This is specifically
	 * required to prevent the use of temporary mm.
	 */

	if (unlikely(in_interrupt() ||
		     current->flags & (PF_KTHREAD | PF_EXITING)))
		return -EPERM;
	if (unlikely(uaccess_kernel()))
		return -EPERM;
	if (unlikely(!nmi_uaccess_okay()))
		return -EPERM;

	return probe_user_write(unsafe_ptr, src, size);
}

static const struct bpf_func_proto bpf_probe_write_user_proto = {
	.func		= bpf_probe_write_user,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_ANYTHING,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
{
	pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
			    current->comm, task_pid_nr(current));

	return &bpf_probe_write_user_proto;
}

/*
 * Only limited trace_printk() conversion specifiers allowed:
 * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
 */
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
	   u64, arg2, u64, arg3)
{
	int i, mod[3] = {}, fmt_cnt = 0;
	char buf[64], fmt_ptype;
	void *unsafe_ptr = NULL;
	bool str_seen = false;

	/*
	 * bpf_check()->check_func_arg()->check_stack_boundary()
	 * guarantees that fmt points to bpf program stack,
	 * fmt_size bytes of it were initialized and fmt_size > 0
	 */
	if (fmt[--fmt_size] != 0)
		return -EINVAL;

	/* check format string for allowed specifiers */
	for (i = 0; i < fmt_size; i++) {
		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i]))
			return -EINVAL;

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

		if (fmt_cnt >= 3)
			return -EINVAL;

		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
		i++;
		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		} else if (fmt[i] == 'p') {
			mod[fmt_cnt]++;
			if ((fmt[i + 1] == 'k' ||
			     fmt[i + 1] == 'u') &&
			    fmt[i + 2] == 's') {
				fmt_ptype = fmt[i + 1];
				i += 2;
				goto fmt_str;
			}

			/* disallow any further format extensions */
			if (fmt[i + 1] != 0 &&
			    !isspace(fmt[i + 1]) &&
			    !ispunct(fmt[i + 1]))
				return -EINVAL;

			goto fmt_next;
		} else if (fmt[i] == 's') {
			mod[fmt_cnt]++;
			fmt_ptype = fmt[i];
fmt_str:
			if (str_seen)
				/* allow only one '%s' per fmt string */
				return -EINVAL;
			str_seen = true;

			if (fmt[i + 1] != 0 &&
			    !isspace(fmt[i + 1]) &&
			    !ispunct(fmt[i + 1]))
				return -EINVAL;

			switch (fmt_cnt) {
			case 0:
				unsafe_ptr = (void *)(long)arg1;
				arg1 = (long)buf;
				break;
			case 1:
				unsafe_ptr = (void *)(long)arg2;
				arg2 = (long)buf;
				break;
			case 2:
				unsafe_ptr = (void *)(long)arg3;
				arg3 = (long)buf;
				break;
			}

			buf[0] = 0;
			switch (fmt_ptype) {
			case 's':
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
				strncpy_from_unsafe(buf, unsafe_ptr,
						    sizeof(buf));
				break;
#endif
			case 'k':
				strncpy_from_unsafe_strict(buf, unsafe_ptr,
							   sizeof(buf));
				break;
			case 'u':
				strncpy_from_unsafe_user(buf,
					(__force void __user *)unsafe_ptr,
							 sizeof(buf));
				break;
			}
			goto fmt_next;
		}

		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		}

		if (fmt[i] != 'i' && fmt[i] != 'd' &&
		    fmt[i] != 'u' && fmt[i] != 'x')
			return -EINVAL;
fmt_next:
		fmt_cnt++;
	}

/* Horrid workaround for getting va_list handling working with different
 * argument type combinations generically for 32 and 64 bit archs.
 */
#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
#define __BPF_TP(...)							\
	__trace_printk(0 /* Fake ip */,					\
		       fmt, ##__VA_ARGS__)

#define __BPF_ARG1_TP(...)						\
	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))

#define __BPF_ARG2_TP(...)						\
	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))

#define __BPF_ARG3_TP(...)						\
	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))

	return __BPF_TP_EMIT();
}

static const struct bpf_func_proto bpf_trace_printk_proto = {
	.func		= bpf_trace_printk,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM,
	.arg2_type	= ARG_CONST_SIZE,
};

const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
{
	/*
	 * this program might be calling bpf_trace_printk,
	 * so allocate per-cpu printk buffers
	 */
	trace_printk_init_buffers();

	return &bpf_trace_printk_proto;
}

static __always_inline int
get_map_perf_counter(struct bpf_map *map, u64 flags,
		     u64 *value, u64 *enabled, u64 *running)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	unsigned int cpu = smp_processor_id();
	u64 index = flags & BPF_F_INDEX_MASK;
	struct bpf_event_entry *ee;

	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
		return -EINVAL;
	if (index == BPF_F_CURRENT_CPU)
		index = cpu;
	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	ee = READ_ONCE(array->ptrs[index]);
	if (!ee)
		return -ENOENT;

	return perf_event_read_local(ee->event, value, enabled, running);
}

BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
{
	u64 value = 0;
	int err;

	err = get_map_perf_counter(map, flags, &value, NULL, NULL);
	/*
	 * this api is ugly since we miss [-22..-2] range of valid
	 * counter values, but that's uapi
	 */
	if (err)
		return err;
	return value;
}

static const struct bpf_func_proto bpf_perf_event_read_proto = {
	.func		= bpf_perf_event_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
	   struct bpf_perf_event_value *, buf, u32, size)
{
	int err = -EINVAL;

	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
		goto clear;
	err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
				   &buf->running);
	if (unlikely(err))
		goto clear;
	return 0;
clear:
	memset(buf, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
	.func		= bpf_perf_event_read_value,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg4_type	= ARG_CONST_SIZE,
};

static __always_inline u64
__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
			u64 flags, struct perf_sample_data *sd)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	unsigned int cpu = smp_processor_id();
	u64 index = flags & BPF_F_INDEX_MASK;
	struct bpf_event_entry *ee;
	struct perf_event *event;

	if (index == BPF_F_CURRENT_CPU)
		index = cpu;
	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	ee = READ_ONCE(array->ptrs[index]);
	if (!ee)
		return -ENOENT;

	event = ee->event;
	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
		return -EINVAL;

	if (unlikely(event->oncpu != cpu))
		return -EOPNOTSUPP;

	return perf_event_output(event, sd, regs);
}

/*
 * Support executing tracepoints in normal, irq, and nmi context that each call
 * bpf_perf_event_output
 */
struct bpf_trace_sample_data {
	struct perf_sample_data sds[3];
};

static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds);
static DEFINE_PER_CPU(int, bpf_trace_nest_level);
BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
	   u64, flags, void *, data, u64, size)
{
	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
	struct perf_raw_record raw = {
		.frag = {
			.size = size,
			.data = data,
		},
	};
	struct perf_sample_data *sd;
	int err;

	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
		err = -EBUSY;
		goto out;
	}

	sd = &sds->sds[nest_level - 1];

	if (unlikely(flags & ~(BPF_F_INDEX_MASK))) {
		err = -EINVAL;
		goto out;
	}

	perf_sample_data_init(sd, 0, 0);
	sd->raw = &raw;

	err = __bpf_perf_event_output(regs, map, flags, sd);

out:
	this_cpu_dec(bpf_trace_nest_level);
	return err;
}

static const struct bpf_func_proto bpf_perf_event_output_proto = {
	.func		= bpf_perf_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_MEM,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

static DEFINE_PER_CPU(int, bpf_event_output_nest_level);
struct bpf_nested_pt_regs {
	struct pt_regs regs[3];
};
static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs);
static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);

u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
	int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
	struct perf_raw_frag frag = {
		.copy		= ctx_copy,
		.size		= ctx_size,
		.data		= ctx,
	};
	struct perf_raw_record raw = {
		.frag = {
			{
				.next	= ctx_size ? &frag : NULL,
			},
			.size	= meta_size,
			.data	= meta,
		},
	};
	struct perf_sample_data *sd;
	struct pt_regs *regs;
	u64 ret;

	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
		ret = -EBUSY;
		goto out;
	}
	sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]);
	regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]);

	perf_fetch_caller_regs(regs);
	perf_sample_data_init(sd, 0, 0);
	sd->raw = &raw;

	ret = __bpf_perf_event_output(regs, map, flags, sd);
out:
	this_cpu_dec(bpf_event_output_nest_level);
	return ret;
}

BPF_CALL_0(bpf_get_current_task)
{
	return (long) current;
}

static const struct bpf_func_proto bpf_get_current_task_proto = {
	.func		= bpf_get_current_task,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct cgroup *cgrp;

	if (unlikely(idx >= array->map.max_entries))
		return -E2BIG;

	cgrp = READ_ONCE(array->ptrs[idx]);
	if (unlikely(!cgrp))
		return -EAGAIN;

	return task_under_cgroup_hierarchy(current, cgrp);
}

static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
	.func           = bpf_current_task_under_cgroup,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_CONST_MAP_PTR,
	.arg2_type      = ARG_ANYTHING,
};

struct send_signal_irq_work {
	struct irq_work irq_work;
	struct task_struct *task;
	u32 sig;
	enum pid_type type;
};

static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);

static void do_bpf_send_signal(struct irq_work *entry)
{
	struct send_signal_irq_work *work;

	work = container_of(entry, struct send_signal_irq_work, irq_work);
	group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
}

static int bpf_send_signal_common(u32 sig, enum pid_type type)
{
	struct send_signal_irq_work *work = NULL;

	/* Similar to bpf_probe_write_user, task needs to be
	 * in a sound condition and kernel memory access be
	 * permitted in order to send signal to the current
	 * task.
	 */
	if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING)))
		return -EPERM;
	if (unlikely(uaccess_kernel()))
		return -EPERM;
	if (unlikely(!nmi_uaccess_okay()))
		return -EPERM;

	if (irqs_disabled()) {
		/* Do an early check on signal validity. Otherwise,
		 * the error is lost in deferred irq_work.
		 */
		if (unlikely(!valid_signal(sig)))
			return -EINVAL;

		work = this_cpu_ptr(&send_signal_work);
		if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY)
			return -EBUSY;

		/* Add the current task, which is the target of sending signal,
		 * to the irq_work. The current task may change when queued
		 * irq works get executed.
		 */
		work->task = current;
		work->sig = sig;
		work->type = type;
		irq_work_queue(&work->irq_work);
		return 0;
	}

	return group_send_sig_info(sig, SEND_SIG_PRIV, current, type);
}

BPF_CALL_1(bpf_send_signal, u32, sig)
{
	return bpf_send_signal_common(sig, PIDTYPE_TGID);
}

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

BPF_CALL_1(bpf_send_signal_thread, u32, sig)
{
	return bpf_send_signal_common(sig, PIDTYPE_PID);
}

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

const struct bpf_func_proto *
bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_map_push_elem:
		return &bpf_map_push_elem_proto;
	case BPF_FUNC_map_pop_elem:
		return &bpf_map_pop_elem_proto;
	case BPF_FUNC_map_peek_elem:
		return &bpf_map_peek_elem_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	case BPF_FUNC_tail_call:
		return &bpf_tail_call_proto;
	case BPF_FUNC_get_current_pid_tgid:
		return &bpf_get_current_pid_tgid_proto;
	case BPF_FUNC_get_current_task:
		return &bpf_get_current_task_proto;
	case BPF_FUNC_get_current_uid_gid:
		return &bpf_get_current_uid_gid_proto;
	case BPF_FUNC_get_current_comm:
		return &bpf_get_current_comm_proto;
	case BPF_FUNC_trace_printk:
		return bpf_get_trace_printk_proto();
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_get_numa_node_id:
		return &bpf_get_numa_node_id_proto;
	case BPF_FUNC_perf_event_read:
		return &bpf_perf_event_read_proto;
	case BPF_FUNC_probe_write_user:
		return bpf_get_probe_write_proto();
	case BPF_FUNC_current_task_under_cgroup:
		return &bpf_current_task_under_cgroup_proto;
	case BPF_FUNC_get_prandom_u32:
		return &bpf_get_prandom_u32_proto;
	case BPF_FUNC_probe_read_user:
		return &bpf_probe_read_user_proto;
	case BPF_FUNC_probe_read_kernel:
		return &bpf_probe_read_kernel_proto;
	case BPF_FUNC_probe_read_user_str:
		return &bpf_probe_read_user_str_proto;
	case BPF_FUNC_probe_read_kernel_str:
		return &bpf_probe_read_kernel_str_proto;
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
	case BPF_FUNC_probe_read:
		return &bpf_probe_read_compat_proto;
	case BPF_FUNC_probe_read_str:
		return &bpf_probe_read_compat_str_proto;
#endif
#ifdef CONFIG_CGROUPS
	case BPF_FUNC_get_current_cgroup_id:
		return &bpf_get_current_cgroup_id_proto;
#endif
	case BPF_FUNC_send_signal:
		return &bpf_send_signal_proto;
	case BPF_FUNC_send_signal_thread:
		return &bpf_send_signal_thread_proto;
	case BPF_FUNC_perf_event_read_value:
		return &bpf_perf_event_read_value_proto;
	case BPF_FUNC_get_ns_current_pid_tgid:
		return &bpf_get_ns_current_pid_tgid_proto;
	default:
		return NULL;
	}
}

static const struct bpf_func_proto *
kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto;
	case BPF_FUNC_get_stack:
		return &bpf_get_stack_proto;
#ifdef CONFIG_BPF_KPROBE_OVERRIDE
	case BPF_FUNC_override_return:
		return &bpf_override_return_proto;
#endif
	default:
		return bpf_tracing_func_proto(func_id, prog);
	}
}

/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
					const struct bpf_prog *prog,
					struct bpf_insn_access_aux *info)
{
	if (off < 0 || off >= sizeof(struct pt_regs))
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;
	/*
	 * Assertion for 32 bit to make sure last 8 byte access
	 * (BPF_DW) to the last 4 byte member is disallowed.
	 */
	if (off + size > sizeof(struct pt_regs))
		return false;

	return true;
}

const struct bpf_verifier_ops kprobe_verifier_ops = {
	.get_func_proto  = kprobe_prog_func_proto,
	.is_valid_access = kprobe_prog_is_valid_access,
};

const struct bpf_prog_ops kprobe_prog_ops = {
};

BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
	   u64, flags, void *, data, u64, size)
{
	struct pt_regs *regs = *(struct pt_regs **)tp_buff;

	/*
	 * r1 points to perf tracepoint buffer where first 8 bytes are hidden
	 * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
	 * from there and call the same bpf_perf_event_output() helper inline.
	 */
	return ____bpf_perf_event_output(regs, map, flags, data, size);
}

static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
	.func		= bpf_perf_event_output_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_MEM,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map,
	   u64, flags)
{
	struct pt_regs *regs = *(struct pt_regs **)tp_buff;

	/*
	 * Same comment as in bpf_perf_event_output_tp(), only that this time
	 * the other helper's function body cannot be inlined due to being
	 * external, thus we need to call raw helper function.
	 */
	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
			       flags, 0, 0);
}

static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
	.func		= bpf_get_stackid_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size,
	   u64, flags)
{
	struct pt_regs *regs = *(struct pt_regs **)tp_buff;

	return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
			     (unsigned long) size, flags, 0);
}

static const struct bpf_func_proto bpf_get_stack_proto_tp = {
	.func		= bpf_get_stack_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg4_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *
tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_tp;
	case BPF_FUNC_get_stack:
		return &bpf_get_stack_proto_tp;
	default:
		return bpf_tracing_func_proto(func_id, prog);
	}
}

static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
				    const struct bpf_prog *prog,
				    struct bpf_insn_access_aux *info)
{
	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;

	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
	return true;
}

const struct bpf_verifier_ops tracepoint_verifier_ops = {
	.get_func_proto  = tp_prog_func_proto,
	.is_valid_access = tp_prog_is_valid_access,
};

const struct bpf_prog_ops tracepoint_prog_ops = {
};

BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
	   struct bpf_perf_event_value *, buf, u32, size)
{
	int err = -EINVAL;

	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
		goto clear;
	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
				    &buf->running);
	if (unlikely(err))
		goto clear;
	return 0;
clear:
	memset(buf, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
         .func           = bpf_perf_prog_read_value,
         .gpl_only       = true,
         .ret_type       = RET_INTEGER,
         .arg1_type      = ARG_PTR_TO_CTX,
         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
         .arg3_type      = ARG_CONST_SIZE,
};

BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
	   void *, buf, u32, size, u64, flags)
{
#ifndef CONFIG_X86
	return -ENOENT;
#else
	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
	struct perf_branch_stack *br_stack = ctx->data->br_stack;
	u32 to_copy;

	if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
		return -EINVAL;

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

	if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
		return br_stack->nr * br_entry_size;

	if (!buf || (size % br_entry_size != 0))
		return -EINVAL;

	to_copy = min_t(u32, br_stack->nr * br_entry_size, size);
	memcpy(buf, br_stack->entries, to_copy);

	return to_copy;
#endif
}

static const struct bpf_func_proto bpf_read_branch_records_proto = {
	.func           = bpf_read_branch_records,
	.gpl_only       = true,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
	.arg4_type      = ARG_ANYTHING,
};

static const struct bpf_func_proto *
pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_tp;
	case BPF_FUNC_get_stack:
		return &bpf_get_stack_proto_tp;
	case BPF_FUNC_perf_prog_read_value:
		return &bpf_perf_prog_read_value_proto;
	case BPF_FUNC_read_branch_records:
		return &bpf_read_branch_records_proto;
	default:
		return bpf_tracing_func_proto(func_id, prog);
	}
}

/*
 * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
 * to avoid potential recursive reuse issue when/if tracepoints are added
 * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack.
 *
 * Since raw tracepoints run despite bpf_prog_active, support concurrent usage
 * in normal, irq, and nmi context.
 */
struct bpf_raw_tp_regs {
	struct pt_regs regs[3];
};
static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs);
static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level);
static struct pt_regs *get_bpf_raw_tp_regs(void)
{
	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);

	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
		this_cpu_dec(bpf_raw_tp_nest_level);
		return ERR_PTR(-EBUSY);
	}

	return &tp_regs->regs[nest_level - 1];
}

static void put_bpf_raw_tp_regs(void)
{
	this_cpu_dec(bpf_raw_tp_nest_level);
}

BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
{
	struct pt_regs *regs = get_bpf_raw_tp_regs();
	int ret;

	if (IS_ERR(regs))
		return PTR_ERR(regs);

	perf_fetch_caller_regs(regs);
	ret = ____bpf_perf_event_output(regs, map, flags, data, size);

	put_bpf_raw_tp_regs();
	return ret;
}

static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
	.func		= bpf_perf_event_output_raw_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_MEM,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

extern const struct bpf_func_proto bpf_skb_output_proto;
extern const struct bpf_func_proto bpf_xdp_output_proto;

BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
	   struct bpf_map *, map, u64, flags)
{
	struct pt_regs *regs = get_bpf_raw_tp_regs();
	int ret;

	if (IS_ERR(regs))
		return PTR_ERR(regs);

	perf_fetch_caller_regs(regs);
	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
	ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map,
			      flags, 0, 0);
	put_bpf_raw_tp_regs();
	return ret;
}

static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
	.func		= bpf_get_stackid_raw_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
	   void *, buf, u32, size, u64, flags)
{
	struct pt_regs *regs = get_bpf_raw_tp_regs();
	int ret;

	if (IS_ERR(regs))
		return PTR_ERR(regs);

	perf_fetch_caller_regs(regs);
	ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf,
			    (unsigned long) size, flags, 0);
	put_bpf_raw_tp_regs();
	return ret;
}

static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
	.func		= bpf_get_stack_raw_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg4_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *
raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_raw_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_raw_tp;
	case BPF_FUNC_get_stack:
		return &bpf_get_stack_proto_raw_tp;
	default:
		return bpf_tracing_func_proto(func_id, prog);
	}
}

static const struct bpf_func_proto *
tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
#ifdef CONFIG_NET
	case BPF_FUNC_skb_output:
		return &bpf_skb_output_proto;
	case BPF_FUNC_xdp_output:
		return &bpf_xdp_output_proto;
#endif
	default:
		return raw_tp_prog_func_proto(func_id, prog);
	}
}

static bool raw_tp_prog_is_valid_access(int off, int size,
					enum bpf_access_type type,
					const struct bpf_prog *prog,
					struct bpf_insn_access_aux *info)
{
	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;
	return true;
}

static bool tracing_prog_is_valid_access(int off, int size,
					 enum bpf_access_type type,
					 const struct bpf_prog *prog,
					 struct bpf_insn_access_aux *info)
{
	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;
	return btf_ctx_access(off, size, type, prog, info);
}

int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog,
				     const union bpf_attr *kattr,
				     union bpf_attr __user *uattr)
{
	return -ENOTSUPP;
}

const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
	.get_func_proto  = raw_tp_prog_func_proto,
	.is_valid_access = raw_tp_prog_is_valid_access,
};

const struct bpf_prog_ops raw_tracepoint_prog_ops = {
};

const struct bpf_verifier_ops tracing_verifier_ops = {
	.get_func_proto  = tracing_prog_func_proto,
	.is_valid_access = tracing_prog_is_valid_access,
};

const struct bpf_prog_ops tracing_prog_ops = {
	.test_run = bpf_prog_test_run_tracing,
};

static bool raw_tp_writable_prog_is_valid_access(int off, int size,
						 enum bpf_access_type type,
						 const struct bpf_prog *prog,
						 struct bpf_insn_access_aux *info)
{
	if (off == 0) {
		if (size != sizeof(u64) || type != BPF_READ)
			return false;
		info->reg_type = PTR_TO_TP_BUFFER;
	}
	return raw_tp_prog_is_valid_access(off, size, type, prog, info);
}

const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = {
	.get_func_proto  = raw_tp_prog_func_proto,
	.is_valid_access = raw_tp_writable_prog_is_valid_access,
};

const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = {
};

static bool pe_prog_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_u64 = sizeof(u64);

	if (off < 0 || off >= sizeof(struct bpf_perf_event_data))
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0) {
		if (sizeof(unsigned long) != 4)
			return false;
		if (size != 8)
			return false;
		if (off % size != 4)
			return false;
	}

	switch (off) {
	case bpf_ctx_range(struct bpf_perf_event_data, sample_period):
		bpf_ctx_record_field_size(info, size_u64);
		if (!bpf_ctx_narrow_access_ok(off, size, size_u64))
			return false;
		break;
	case bpf_ctx_range(struct bpf_perf_event_data, addr):
		bpf_ctx_record_field_size(info, size_u64);
		if (!bpf_ctx_narrow_access_ok(off, size, size_u64))
			return false;
		break;
	default:
		if (size != sizeof(long))
			return false;
	}

	return true;
}

static u32 pe_prog_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_perf_event_data, sample_period):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
						       data), si->dst_reg, si->src_reg,
				      offsetof(struct bpf_perf_event_data_kern, data));
		*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
				      bpf_target_off(struct perf_sample_data, period, 8,
						     target_size));
		break;
	case offsetof(struct bpf_perf_event_data, addr):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
						       data), si->dst_reg, si->src_reg,
				      offsetof(struct bpf_perf_event_data_kern, data));
		*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
				      bpf_target_off(struct perf_sample_data, addr, 8,
						     target_size));
		break;
	default:
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
						       regs), si->dst_reg, si->src_reg,
				      offsetof(struct bpf_perf_event_data_kern, regs));
		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg,
				      si->off);
		break;
	}

	return insn - insn_buf;
}

const struct bpf_verifier_ops perf_event_verifier_ops = {
	.get_func_proto		= pe_prog_func_proto,
	.is_valid_access	= pe_prog_is_valid_access,
	.convert_ctx_access	= pe_prog_convert_ctx_access,
};

const struct bpf_prog_ops perf_event_prog_ops = {
};

static DEFINE_MUTEX(bpf_event_mutex);

#define BPF_TRACE_MAX_PROGS 64

int perf_event_attach_bpf_prog(struct perf_event *event,
			       struct bpf_prog *prog)
{
	struct bpf_prog_array *old_array;
	struct bpf_prog_array *new_array;
	int ret = -EEXIST;

	/*
	 * Kprobe override only works if they are on the function entry,
	 * and only if they are on the opt-in list.
	 */
	if (prog->kprobe_override &&
	    (!trace_kprobe_on_func_entry(event->tp_event) ||
	     !trace_kprobe_error_injectable(event->tp_event)))
		return -EINVAL;

	mutex_lock(&bpf_event_mutex);

	if (event->prog)
		goto unlock;

	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
	if (old_array &&
	    bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) {
		ret = -E2BIG;
		goto unlock;
	}

	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
	if (ret < 0)
		goto unlock;

	/* set the new array to event->tp_event and set event->prog */
	event->prog = prog;
	rcu_assign_pointer(event->tp_event->prog_array, new_array);
	bpf_prog_array_free(old_array);

unlock:
	mutex_unlock(&bpf_event_mutex);
	return ret;
}

void perf_event_detach_bpf_prog(struct perf_event *event)
{
	struct bpf_prog_array *old_array;
	struct bpf_prog_array *new_array;
	int ret;

	mutex_lock(&bpf_event_mutex);

	if (!event->prog)
		goto unlock;

	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
	if (ret == -ENOENT)
		goto unlock;
	if (ret < 0) {
		bpf_prog_array_delete_safe(old_array, event->prog);
	} else {
		rcu_assign_pointer(event->tp_event->prog_array, new_array);
		bpf_prog_array_free(old_array);
	}

	bpf_prog_put(event->prog);
	event->prog = NULL;

unlock:
	mutex_unlock(&bpf_event_mutex);
}

int perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
	struct perf_event_query_bpf __user *uquery = info;
	struct perf_event_query_bpf query = {};
	struct bpf_prog_array *progs;
	u32 *ids, prog_cnt, ids_len;
	int ret;

	if (!perfmon_capable())
		return -EPERM;
	if (event->attr.type != PERF_TYPE_TRACEPOINT)
		return -EINVAL;
	if (copy_from_user(&query, uquery, sizeof(query)))
		return -EFAULT;

	ids_len = query.ids_len;
	if (ids_len > BPF_TRACE_MAX_PROGS)
		return -E2BIG;
	ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
	if (!ids)
		return -ENOMEM;
	/*
	 * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
	 * is required when user only wants to check for uquery->prog_cnt.
	 * There is no need to check for it since the case is handled
	 * gracefully in bpf_prog_array_copy_info.
	 */

	mutex_lock(&bpf_event_mutex);
	progs = bpf_event_rcu_dereference(event->tp_event->prog_array);
	ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt);
	mutex_unlock(&bpf_event_mutex);

	if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
	    copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
		ret = -EFAULT;

	kfree(ids);
	return ret;
}

extern struct bpf_raw_event_map __start__bpf_raw_tp[];
extern struct bpf_raw_event_map __stop__bpf_raw_tp[];

struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
{
	struct bpf_raw_event_map *btp = __start__bpf_raw_tp;

	for (; btp < __stop__bpf_raw_tp; btp++) {
		if (!strcmp(btp->tp->name, name))
			return btp;
	}

	return bpf_get_raw_tracepoint_module(name);
}

void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
{
	struct module *mod = __module_address((unsigned long)btp);

	if (mod)
		module_put(mod);
}

static __always_inline
void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
{
	cant_sleep();
	rcu_read_lock();
	(void) BPF_PROG_RUN(prog, args);
	rcu_read_unlock();
}

#define UNPACK(...)			__VA_ARGS__
#define REPEAT_1(FN, DL, X, ...)	FN(X)
#define REPEAT_2(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__)
#define REPEAT_3(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__)
#define REPEAT_4(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__)
#define REPEAT_5(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__)
#define REPEAT_6(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__)
#define REPEAT_7(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__)
#define REPEAT_8(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__)
#define REPEAT_9(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__)
#define REPEAT_10(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__)
#define REPEAT_11(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__)
#define REPEAT_12(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__)
#define REPEAT(X, FN, DL, ...)		REPEAT_##X(FN, DL, __VA_ARGS__)

#define SARG(X)		u64 arg##X
#define COPY(X)		args[X] = arg##X

#define __DL_COM	(,)
#define __DL_SEM	(;)

#define __SEQ_0_11	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11

#define BPF_TRACE_DEFN_x(x)						\
	void bpf_trace_run##x(struct bpf_prog *prog,			\
			      REPEAT(x, SARG, __DL_COM, __SEQ_0_11))	\
	{								\
		u64 args[x];						\
		REPEAT(x, COPY, __DL_SEM, __SEQ_0_11);			\
		__bpf_trace_run(prog, args);				\
	}								\
	EXPORT_SYMBOL_GPL(bpf_trace_run##x)
BPF_TRACE_DEFN_x(1);
BPF_TRACE_DEFN_x(2);
BPF_TRACE_DEFN_x(3);
BPF_TRACE_DEFN_x(4);
BPF_TRACE_DEFN_x(5);
BPF_TRACE_DEFN_x(6);
BPF_TRACE_DEFN_x(7);
BPF_TRACE_DEFN_x(8);
BPF_TRACE_DEFN_x(9);
BPF_TRACE_DEFN_x(10);
BPF_TRACE_DEFN_x(11);
BPF_TRACE_DEFN_x(12);

static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
{
	struct tracepoint *tp = btp->tp;

	/*
	 * check that program doesn't access arguments beyond what's
	 * available in this tracepoint
	 */
	if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64))
		return -EINVAL;

	if (prog->aux->max_tp_access > btp->writable_size)
		return -EINVAL;

	return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
}

int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
{
	return __bpf_probe_register(btp, prog);
}

int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
{
	return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
}

int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
			    u32 *fd_type, const char **buf,
			    u64 *probe_offset, u64 *probe_addr)
{
	bool is_tracepoint, is_syscall_tp;
	struct bpf_prog *prog;
	int flags, err = 0;

	prog = event->prog;
	if (!prog)
		return -ENOENT;

	/* not supporting BPF_PROG_TYPE_PERF_EVENT yet */
	if (prog->type == BPF_PROG_TYPE_PERF_EVENT)
		return -EOPNOTSUPP;

	*prog_id = prog->aux->id;
	flags = event->tp_event->flags;
	is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT;
	is_syscall_tp = is_syscall_trace_event(event->tp_event);

	if (is_tracepoint || is_syscall_tp) {
		*buf = is_tracepoint ? event->tp_event->tp->name
				     : event->tp_event->name;
		*fd_type = BPF_FD_TYPE_TRACEPOINT;
		*probe_offset = 0x0;
		*probe_addr = 0x0;
	} else {
		/* kprobe/uprobe */
		err = -EOPNOTSUPP;
#ifdef CONFIG_KPROBE_EVENTS
		if (flags & TRACE_EVENT_FL_KPROBE)
			err = bpf_get_kprobe_info(event, fd_type, buf,
						  probe_offset, probe_addr,
						  event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
#ifdef CONFIG_UPROBE_EVENTS
		if (flags & TRACE_EVENT_FL_UPROBE)
			err = bpf_get_uprobe_info(event, fd_type, buf,
						  probe_offset,
						  event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
	}

	return err;
}

static int __init send_signal_irq_work_init(void)
{
	int cpu;
	struct send_signal_irq_work *work;

	for_each_possible_cpu(cpu) {
		work = per_cpu_ptr(&send_signal_work, cpu);
		init_irq_work(&work->irq_work, do_bpf_send_signal);
	}
	return 0;
}

subsys_initcall(send_signal_irq_work_init);

#ifdef CONFIG_MODULES
static int bpf_event_notify(struct notifier_block *nb, unsigned long op,
			    void *module)
{
	struct bpf_trace_module *btm, *tmp;
	struct module *mod = module;

	if (mod->num_bpf_raw_events == 0 ||
	    (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
		return 0;

	mutex_lock(&bpf_module_mutex);

	switch (op) {
	case MODULE_STATE_COMING:
		btm = kzalloc(sizeof(*btm), GFP_KERNEL);
		if (btm) {
			btm->module = module;
			list_add(&btm->list, &bpf_trace_modules);
		}
		break;
	case MODULE_STATE_GOING:
		list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) {
			if (btm->module == module) {
				list_del(&btm->list);
				kfree(btm);
				break;
			}
		}
		break;
	}

	mutex_unlock(&bpf_module_mutex);

	return 0;
}

static struct notifier_block bpf_module_nb = {
	.notifier_call = bpf_event_notify,
};

static int __init bpf_event_init(void)
{
	register_module_notifier(&bpf_module_nb);
	return 0;
}

fs_initcall(bpf_event_init);
#endif /* CONFIG_MODULES */