summaryrefslogtreecommitdiff
path: root/kernel/bpf/verifier.c
blob: a086dd3210a8427ffec6e80b008fd3266e6b44b1 (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
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>

/* bpf_check() is a static code analyzer that walks eBPF program
 * instruction by instruction and updates register/stack state.
 * All paths of conditional branches are analyzed until 'bpf_exit' insn.
 *
 * The first pass is depth-first-search to check that the program is a DAG.
 * It rejects the following programs:
 * - larger than BPF_MAXINSNS insns
 * - if loop is present (detected via back-edge)
 * - unreachable insns exist (shouldn't be a forest. program = one function)
 * - out of bounds or malformed jumps
 * The second pass is all possible path descent from the 1st insn.
 * Since it's analyzing all pathes through the program, the length of the
 * analysis is limited to 32k insn, which may be hit even if total number of
 * insn is less then 4K, but there are too many branches that change stack/regs.
 * Number of 'branches to be analyzed' is limited to 1k
 *
 * On entry to each instruction, each register has a type, and the instruction
 * changes the types of the registers depending on instruction semantics.
 * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
 * copied to R1.
 *
 * All registers are 64-bit.
 * R0 - return register
 * R1-R5 argument passing registers
 * R6-R9 callee saved registers
 * R10 - frame pointer read-only
 *
 * At the start of BPF program the register R1 contains a pointer to bpf_context
 * and has type PTR_TO_CTX.
 *
 * Verifier tracks arithmetic operations on pointers in case:
 *    BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
 * 1st insn copies R10 (which has FRAME_PTR) type into R1
 * and 2nd arithmetic instruction is pattern matched to recognize
 * that it wants to construct a pointer to some element within stack.
 * So after 2nd insn, the register R1 has type PTR_TO_STACK
 * (and -20 constant is saved for further stack bounds checking).
 * Meaning that this reg is a pointer to stack plus known immediate constant.
 *
 * Most of the time the registers have UNKNOWN_VALUE type, which
 * means the register has some value, but it's not a valid pointer.
 * (like pointer plus pointer becomes UNKNOWN_VALUE type)
 *
 * When verifier sees load or store instructions the type of base register
 * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer
 * types recognized by check_mem_access() function.
 *
 * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
 * and the range of [ptr, ptr + map's value_size) is accessible.
 *
 * registers used to pass values to function calls are checked against
 * function argument constraints.
 *
 * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
 * It means that the register type passed to this function must be
 * PTR_TO_STACK and it will be used inside the function as
 * 'pointer to map element key'
 *
 * For example the argument constraints for bpf_map_lookup_elem():
 *   .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 *   .arg1_type = ARG_CONST_MAP_PTR,
 *   .arg2_type = ARG_PTR_TO_MAP_KEY,
 *
 * ret_type says that this function returns 'pointer to map elem value or null'
 * function expects 1st argument to be a const pointer to 'struct bpf_map' and
 * 2nd argument should be a pointer to stack, which will be used inside
 * the helper function as a pointer to map element key.
 *
 * On the kernel side the helper function looks like:
 * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 * {
 *    struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 *    void *key = (void *) (unsigned long) r2;
 *    void *value;
 *
 *    here kernel can access 'key' and 'map' pointers safely, knowing that
 *    [key, key + map->key_size) bytes are valid and were initialized on
 *    the stack of eBPF program.
 * }
 *
 * Corresponding eBPF program may look like:
 *    BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),  // after this insn R2 type is FRAME_PTR
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
 *    BPF_LD_MAP_FD(BPF_REG_1, map_fd),      // after this insn R1 type is CONST_PTR_TO_MAP
 *    BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 * here verifier looks at prototype of map_lookup_elem() and sees:
 * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
 * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
 *
 * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
 * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
 * and were initialized prior to this call.
 * If it's ok, then verifier allows this BPF_CALL insn and looks at
 * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
 * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
 * returns ether pointer to map value or NULL.
 *
 * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
 * insn, the register holding that pointer in the true branch changes state to
 * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
 * branch. See check_cond_jmp_op().
 *
 * After the call R0 is set to return type of the function and registers R1-R5
 * are set to NOT_INIT to indicate that they are no longer readable.
 */

/* types of values stored in eBPF registers */
enum bpf_reg_type {
	NOT_INIT = 0,		 /* nothing was written into register */
	UNKNOWN_VALUE,		 /* reg doesn't contain a valid pointer */
	PTR_TO_CTX,		 /* reg points to bpf_context */
	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
	FRAME_PTR,		 /* reg == frame_pointer */
	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
	CONST_IMM,		 /* constant integer value */
};

struct reg_state {
	enum bpf_reg_type type;
	union {
		/* valid when type == CONST_IMM | PTR_TO_STACK */
		int imm;

		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
		 *   PTR_TO_MAP_VALUE_OR_NULL
		 */
		struct bpf_map *map_ptr;
	};
};

enum bpf_stack_slot_type {
	STACK_INVALID,    /* nothing was stored in this stack slot */
	STACK_SPILL,      /* 1st byte of register spilled into stack */
	STACK_SPILL_PART, /* other 7 bytes of register spill */
	STACK_MISC	  /* BPF program wrote some data into this slot */
};

struct bpf_stack_slot {
	enum bpf_stack_slot_type stype;
	struct reg_state reg_st;
};

/* state of the program:
 * type of all registers and stack info
 */
struct verifier_state {
	struct reg_state regs[MAX_BPF_REG];
	struct bpf_stack_slot stack[MAX_BPF_STACK];
};

/* linked list of verifier states used to prune search */
struct verifier_state_list {
	struct verifier_state state;
	struct verifier_state_list *next;
};

/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct verifier_stack_elem {
	/* verifer state is 'st'
	 * before processing instruction 'insn_idx'
	 * and after processing instruction 'prev_insn_idx'
	 */
	struct verifier_state st;
	int insn_idx;
	int prev_insn_idx;
	struct verifier_stack_elem *next;
};

#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */

/* single container for all structs
 * one verifier_env per bpf_check() call
 */
struct verifier_env {
	struct bpf_prog *prog;		/* eBPF program being verified */
	struct verifier_stack_elem *head; /* stack of verifier states to be processed */
	int stack_size;			/* number of states to be processed */
	struct verifier_state cur_state; /* current verifier state */
	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
	u32 used_map_cnt;		/* number of used maps */
};

/* verbose verifier prints what it's seeing
 * bpf_check() is called under lock, so no race to access these global vars
 */
static u32 log_level, log_size, log_len;
static char *log_buf;

static DEFINE_MUTEX(bpf_verifier_lock);

/* log_level controls verbosity level of eBPF verifier.
 * verbose() is used to dump the verification trace to the log, so the user
 * can figure out what's wrong with the program
 */
static void verbose(const char *fmt, ...)
{
	va_list args;

	if (log_level == 0 || log_len >= log_size - 1)
		return;

	va_start(args, fmt);
	log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
	va_end(args);
}

/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
	[NOT_INIT]		= "?",
	[UNKNOWN_VALUE]		= "inv",
	[PTR_TO_CTX]		= "ctx",
	[CONST_PTR_TO_MAP]	= "map_ptr",
	[PTR_TO_MAP_VALUE]	= "map_value",
	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
	[FRAME_PTR]		= "fp",
	[PTR_TO_STACK]		= "fp",
	[CONST_IMM]		= "imm",
};

static void print_verifier_state(struct verifier_env *env)
{
	enum bpf_reg_type t;
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
		t = env->cur_state.regs[i].type;
		if (t == NOT_INIT)
			continue;
		verbose(" R%d=%s", i, reg_type_str[t]);
		if (t == CONST_IMM || t == PTR_TO_STACK)
			verbose("%d", env->cur_state.regs[i].imm);
		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
			 t == PTR_TO_MAP_VALUE_OR_NULL)
			verbose("(ks=%d,vs=%d)",
				env->cur_state.regs[i].map_ptr->key_size,
				env->cur_state.regs[i].map_ptr->value_size);
	}
	for (i = 0; i < MAX_BPF_STACK; i++) {
		if (env->cur_state.stack[i].stype == STACK_SPILL)
			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
				reg_type_str[env->cur_state.stack[i].reg_st.type]);
	}
	verbose("\n");
}

static const char *const bpf_class_string[] = {
	[BPF_LD]    = "ld",
	[BPF_LDX]   = "ldx",
	[BPF_ST]    = "st",
	[BPF_STX]   = "stx",
	[BPF_ALU]   = "alu",
	[BPF_JMP]   = "jmp",
	[BPF_RET]   = "BUG",
	[BPF_ALU64] = "alu64",
};

static const char *const bpf_alu_string[] = {
	[BPF_ADD >> 4]  = "+=",
	[BPF_SUB >> 4]  = "-=",
	[BPF_MUL >> 4]  = "*=",
	[BPF_DIV >> 4]  = "/=",
	[BPF_OR  >> 4]  = "|=",
	[BPF_AND >> 4]  = "&=",
	[BPF_LSH >> 4]  = "<<=",
	[BPF_RSH >> 4]  = ">>=",
	[BPF_NEG >> 4]  = "neg",
	[BPF_MOD >> 4]  = "%=",
	[BPF_XOR >> 4]  = "^=",
	[BPF_MOV >> 4]  = "=",
	[BPF_ARSH >> 4] = "s>>=",
	[BPF_END >> 4]  = "endian",
};

static const char *const bpf_ldst_string[] = {
	[BPF_W >> 3]  = "u32",
	[BPF_H >> 3]  = "u16",
	[BPF_B >> 3]  = "u8",
	[BPF_DW >> 3] = "u64",
};

static const char *const bpf_jmp_string[] = {
	[BPF_JA >> 4]   = "jmp",
	[BPF_JEQ >> 4]  = "==",
	[BPF_JGT >> 4]  = ">",
	[BPF_JGE >> 4]  = ">=",
	[BPF_JSET >> 4] = "&",
	[BPF_JNE >> 4]  = "!=",
	[BPF_JSGT >> 4] = "s>",
	[BPF_JSGE >> 4] = "s>=",
	[BPF_CALL >> 4] = "call",
	[BPF_EXIT >> 4] = "exit",
};

static void print_bpf_insn(struct bpf_insn *insn)
{
	u8 class = BPF_CLASS(insn->code);

	if (class == BPF_ALU || class == BPF_ALU64) {
		if (BPF_SRC(insn->code) == BPF_X)
			verbose("(%02x) %sr%d %s %sr%d\n",
				insn->code, class == BPF_ALU ? "(u32) " : "",
				insn->dst_reg,
				bpf_alu_string[BPF_OP(insn->code) >> 4],
				class == BPF_ALU ? "(u32) " : "",
				insn->src_reg);
		else
			verbose("(%02x) %sr%d %s %s%d\n",
				insn->code, class == BPF_ALU ? "(u32) " : "",
				insn->dst_reg,
				bpf_alu_string[BPF_OP(insn->code) >> 4],
				class == BPF_ALU ? "(u32) " : "",
				insn->imm);
	} else if (class == BPF_STX) {
		if (BPF_MODE(insn->code) == BPF_MEM)
			verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->dst_reg,
				insn->off, insn->src_reg);
		else if (BPF_MODE(insn->code) == BPF_XADD)
			verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->dst_reg, insn->off,
				insn->src_reg);
		else
			verbose("BUG_%02x\n", insn->code);
	} else if (class == BPF_ST) {
		if (BPF_MODE(insn->code) != BPF_MEM) {
			verbose("BUG_st_%02x\n", insn->code);
			return;
		}
		verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
			insn->code,
			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
			insn->dst_reg,
			insn->off, insn->imm);
	} else if (class == BPF_LDX) {
		if (BPF_MODE(insn->code) != BPF_MEM) {
			verbose("BUG_ldx_%02x\n", insn->code);
			return;
		}
		verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
			insn->code, insn->dst_reg,
			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
			insn->src_reg, insn->off);
	} else if (class == BPF_LD) {
		if (BPF_MODE(insn->code) == BPF_ABS) {
			verbose("(%02x) r0 = *(%s *)skb[%d]\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->imm);
		} else if (BPF_MODE(insn->code) == BPF_IND) {
			verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
				insn->code,
				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
				insn->src_reg, insn->imm);
		} else if (BPF_MODE(insn->code) == BPF_IMM) {
			verbose("(%02x) r%d = 0x%x\n",
				insn->code, insn->dst_reg, insn->imm);
		} else {
			verbose("BUG_ld_%02x\n", insn->code);
			return;
		}
	} else if (class == BPF_JMP) {
		u8 opcode = BPF_OP(insn->code);

		if (opcode == BPF_CALL) {
			verbose("(%02x) call %d\n", insn->code, insn->imm);
		} else if (insn->code == (BPF_JMP | BPF_JA)) {
			verbose("(%02x) goto pc%+d\n",
				insn->code, insn->off);
		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
			verbose("(%02x) exit\n", insn->code);
		} else if (BPF_SRC(insn->code) == BPF_X) {
			verbose("(%02x) if r%d %s r%d goto pc%+d\n",
				insn->code, insn->dst_reg,
				bpf_jmp_string[BPF_OP(insn->code) >> 4],
				insn->src_reg, insn->off);
		} else {
			verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
				insn->code, insn->dst_reg,
				bpf_jmp_string[BPF_OP(insn->code) >> 4],
				insn->imm, insn->off);
		}
	} else {
		verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
	}
}

static int pop_stack(struct verifier_env *env, int *prev_insn_idx)
{
	struct verifier_stack_elem *elem;
	int insn_idx;

	if (env->head == NULL)
		return -1;

	memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
	insn_idx = env->head->insn_idx;
	if (prev_insn_idx)
		*prev_insn_idx = env->head->prev_insn_idx;
	elem = env->head->next;
	kfree(env->head);
	env->head = elem;
	env->stack_size--;
	return insn_idx;
}

static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx,
					 int prev_insn_idx)
{
	struct verifier_stack_elem *elem;

	elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL);
	if (!elem)
		goto err;

	memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
	elem->insn_idx = insn_idx;
	elem->prev_insn_idx = prev_insn_idx;
	elem->next = env->head;
	env->head = elem;
	env->stack_size++;
	if (env->stack_size > 1024) {
		verbose("BPF program is too complex\n");
		goto err;
	}
	return &elem->st;
err:
	/* pop all elements and return */
	while (pop_stack(env, NULL) >= 0);
	return NULL;
}

#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};

static void init_reg_state(struct reg_state *regs)
{
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
		regs[i].type = NOT_INIT;
		regs[i].imm = 0;
		regs[i].map_ptr = NULL;
	}

	/* frame pointer */
	regs[BPF_REG_FP].type = FRAME_PTR;

	/* 1st arg to a function */
	regs[BPF_REG_1].type = PTR_TO_CTX;
}

static void mark_reg_unknown_value(struct reg_state *regs, u32 regno)
{
	BUG_ON(regno >= MAX_BPF_REG);
	regs[regno].type = UNKNOWN_VALUE;
	regs[regno].imm = 0;
	regs[regno].map_ptr = NULL;
}

enum reg_arg_type {
	SRC_OP,		/* register is used as source operand */
	DST_OP,		/* register is used as destination operand */
	DST_OP_NO_MARK	/* same as above, check only, don't mark */
};

static int check_reg_arg(struct reg_state *regs, u32 regno,
			 enum reg_arg_type t)
{
	if (regno >= MAX_BPF_REG) {
		verbose("R%d is invalid\n", regno);
		return -EINVAL;
	}

	if (t == SRC_OP) {
		/* check whether register used as source operand can be read */
		if (regs[regno].type == NOT_INIT) {
			verbose("R%d !read_ok\n", regno);
			return -EACCES;
		}
	} else {
		/* check whether register used as dest operand can be written to */
		if (regno == BPF_REG_FP) {
			verbose("frame pointer is read only\n");
			return -EACCES;
		}
		if (t == DST_OP)
			mark_reg_unknown_value(regs, regno);
	}
	return 0;
}

static int bpf_size_to_bytes(int bpf_size)
{
	if (bpf_size == BPF_W)
		return 4;
	else if (bpf_size == BPF_H)
		return 2;
	else if (bpf_size == BPF_B)
		return 1;
	else if (bpf_size == BPF_DW)
		return 8;
	else
		return -EINVAL;
}

/* check_stack_read/write functions track spill/fill of registers,
 * stack boundary and alignment are checked in check_mem_access()
 */
static int check_stack_write(struct verifier_state *state, int off, int size,
			     int value_regno)
{
	struct bpf_stack_slot *slot;
	int i;

	if (value_regno >= 0 &&
	    (state->regs[value_regno].type == PTR_TO_MAP_VALUE ||
	     state->regs[value_regno].type == PTR_TO_STACK ||
	     state->regs[value_regno].type == PTR_TO_CTX)) {

		/* register containing pointer is being spilled into stack */
		if (size != 8) {
			verbose("invalid size of register spill\n");
			return -EACCES;
		}

		slot = &state->stack[MAX_BPF_STACK + off];
		slot->stype = STACK_SPILL;
		/* save register state */
		slot->reg_st = state->regs[value_regno];
		for (i = 1; i < 8; i++) {
			slot = &state->stack[MAX_BPF_STACK + off + i];
			slot->stype = STACK_SPILL_PART;
			slot->reg_st.type = UNKNOWN_VALUE;
			slot->reg_st.map_ptr = NULL;
		}
	} else {

		/* regular write of data into stack */
		for (i = 0; i < size; i++) {
			slot = &state->stack[MAX_BPF_STACK + off + i];
			slot->stype = STACK_MISC;
			slot->reg_st.type = UNKNOWN_VALUE;
			slot->reg_st.map_ptr = NULL;
		}
	}
	return 0;
}

static int check_stack_read(struct verifier_state *state, int off, int size,
			    int value_regno)
{
	int i;
	struct bpf_stack_slot *slot;

	slot = &state->stack[MAX_BPF_STACK + off];

	if (slot->stype == STACK_SPILL) {
		if (size != 8) {
			verbose("invalid size of register spill\n");
			return -EACCES;
		}
		for (i = 1; i < 8; i++) {
			if (state->stack[MAX_BPF_STACK + off + i].stype !=
			    STACK_SPILL_PART) {
				verbose("corrupted spill memory\n");
				return -EACCES;
			}
		}

		if (value_regno >= 0)
			/* restore register state from stack */
			state->regs[value_regno] = slot->reg_st;
		return 0;
	} else {
		for (i = 0; i < size; i++) {
			if (state->stack[MAX_BPF_STACK + off + i].stype !=
			    STACK_MISC) {
				verbose("invalid read from stack off %d+%d size %d\n",
					off, i, size);
				return -EACCES;
			}
		}
		if (value_regno >= 0)
			/* have read misc data from the stack */
			mark_reg_unknown_value(state->regs, value_regno);
		return 0;
	}
}

/* check read/write into map element returned by bpf_map_lookup_elem() */
static int check_map_access(struct verifier_env *env, u32 regno, int off,
			    int size)
{
	struct bpf_map *map = env->cur_state.regs[regno].map_ptr;

	if (off < 0 || off + size > map->value_size) {
		verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
			map->value_size, off, size);
		return -EACCES;
	}
	return 0;
}

/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
			    enum bpf_access_type t)
{
	if (env->prog->aux->ops->is_valid_access &&
	    env->prog->aux->ops->is_valid_access(off, size, t))
		return 0;

	verbose("invalid bpf_context access off=%d size=%d\n", off, size);
	return -EACCES;
}

/* check whether memory at (regno + off) is accessible for t = (read | write)
 * if t==write, value_regno is a register which value is stored into memory
 * if t==read, value_regno is a register which will receive the value from memory
 * if t==write && value_regno==-1, some unknown value is stored into memory
 * if t==read && value_regno==-1, don't care what we read from memory
 */
static int check_mem_access(struct verifier_env *env, u32 regno, int off,
			    int bpf_size, enum bpf_access_type t,
			    int value_regno)
{
	struct verifier_state *state = &env->cur_state;
	int size, err = 0;

	size = bpf_size_to_bytes(bpf_size);
	if (size < 0)
		return size;

	if (off % size != 0) {
		verbose("misaligned access off %d size %d\n", off, size);
		return -EACCES;
	}

	if (state->regs[regno].type == PTR_TO_MAP_VALUE) {
		err = check_map_access(env, regno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown_value(state->regs, value_regno);

	} else if (state->regs[regno].type == PTR_TO_CTX) {
		err = check_ctx_access(env, off, size, t);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown_value(state->regs, value_regno);

	} else if (state->regs[regno].type == FRAME_PTR) {
		if (off >= 0 || off < -MAX_BPF_STACK) {
			verbose("invalid stack off=%d size=%d\n", off, size);
			return -EACCES;
		}
		if (t == BPF_WRITE)
			err = check_stack_write(state, off, size, value_regno);
		else
			err = check_stack_read(state, off, size, value_regno);
	} else {
		verbose("R%d invalid mem access '%s'\n",
			regno, reg_type_str[state->regs[regno].type]);
		return -EACCES;
	}
	return err;
}

static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
{
	struct reg_state *regs = env->cur_state.regs;
	int err;

	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
	    insn->imm != 0) {
		verbose("BPF_XADD uses reserved fields\n");
		return -EINVAL;
	}

	/* check src1 operand */
	err = check_reg_arg(regs, insn->src_reg, SRC_OP);
	if (err)
		return err;

	/* check src2 operand */
	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	/* check whether atomic_add can read the memory */
	err = check_mem_access(env, insn->dst_reg, insn->off,
			       BPF_SIZE(insn->code), BPF_READ, -1);
	if (err)
		return err;

	/* check whether atomic_add can write into the same memory */
	return check_mem_access(env, insn->dst_reg, insn->off,
				BPF_SIZE(insn->code), BPF_WRITE, -1);
}

/* when register 'regno' is passed into function that will read 'access_size'
 * bytes from that pointer, make sure that it's within stack boundary
 * and all elements of stack are initialized
 */
static int check_stack_boundary(struct verifier_env *env,
				int regno, int access_size)
{
	struct verifier_state *state = &env->cur_state;
	struct reg_state *regs = state->regs;
	int off, i;

	if (regs[regno].type != PTR_TO_STACK)
		return -EACCES;

	off = regs[regno].imm;
	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
	    access_size <= 0) {
		verbose("invalid stack type R%d off=%d access_size=%d\n",
			regno, off, access_size);
		return -EACCES;
	}

	for (i = 0; i < access_size; i++) {
		if (state->stack[MAX_BPF_STACK + off + i].stype != STACK_MISC) {
			verbose("invalid indirect read from stack off %d+%d size %d\n",
				off, i, access_size);
			return -EACCES;
		}
	}
	return 0;
}

static int check_func_arg(struct verifier_env *env, u32 regno,
			  enum bpf_arg_type arg_type, struct bpf_map **mapp)
{
	struct reg_state *reg = env->cur_state.regs + regno;
	enum bpf_reg_type expected_type;
	int err = 0;

	if (arg_type == ARG_ANYTHING)
		return 0;

	if (reg->type == NOT_INIT) {
		verbose("R%d !read_ok\n", regno);
		return -EACCES;
	}

	if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
	    arg_type == ARG_PTR_TO_MAP_VALUE) {
		expected_type = PTR_TO_STACK;
	} else if (arg_type == ARG_CONST_STACK_SIZE) {
		expected_type = CONST_IMM;
	} else if (arg_type == ARG_CONST_MAP_PTR) {
		expected_type = CONST_PTR_TO_MAP;
	} else {
		verbose("unsupported arg_type %d\n", arg_type);
		return -EFAULT;
	}

	if (reg->type != expected_type) {
		verbose("R%d type=%s expected=%s\n", regno,
			reg_type_str[reg->type], reg_type_str[expected_type]);
		return -EACCES;
	}

	if (arg_type == ARG_CONST_MAP_PTR) {
		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
		*mapp = reg->map_ptr;

	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
		/* bpf_map_xxx(..., map_ptr, ..., key) call:
		 * check that [key, key + map->key_size) are within
		 * stack limits and initialized
		 */
		if (!*mapp) {
			/* in function declaration map_ptr must come before
			 * map_key, so that it's verified and known before
			 * we have to check map_key here. Otherwise it means
			 * that kernel subsystem misconfigured verifier
			 */
			verbose("invalid map_ptr to access map->key\n");
			return -EACCES;
		}
		err = check_stack_boundary(env, regno, (*mapp)->key_size);

	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
		/* bpf_map_xxx(..., map_ptr, ..., value) call:
		 * check [value, value + map->value_size) validity
		 */
		if (!*mapp) {
			/* kernel subsystem misconfigured verifier */
			verbose("invalid map_ptr to access map->value\n");
			return -EACCES;
		}
		err = check_stack_boundary(env, regno, (*mapp)->value_size);

	} else if (arg_type == ARG_CONST_STACK_SIZE) {
		/* bpf_xxx(..., buf, len) call will access 'len' bytes
		 * from stack pointer 'buf'. Check it
		 * note: regno == len, regno - 1 == buf
		 */
		if (regno == 0) {
			/* kernel subsystem misconfigured verifier */
			verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
			return -EACCES;
		}
		err = check_stack_boundary(env, regno - 1, reg->imm);
	}

	return err;
}

static int check_call(struct verifier_env *env, int func_id)
{
	struct verifier_state *state = &env->cur_state;
	const struct bpf_func_proto *fn = NULL;
	struct reg_state *regs = state->regs;
	struct bpf_map *map = NULL;
	struct reg_state *reg;
	int i, err;

	/* find function prototype */
	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
		verbose("invalid func %d\n", func_id);
		return -EINVAL;
	}

	if (env->prog->aux->ops->get_func_proto)
		fn = env->prog->aux->ops->get_func_proto(func_id);

	if (!fn) {
		verbose("unknown func %d\n", func_id);
		return -EINVAL;
	}

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
	if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) {
		verbose("cannot call GPL only function from proprietary program\n");
		return -EINVAL;
	}

	/* check args */
	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &map);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &map);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &map);
	if (err)
		return err;

	/* reset caller saved regs */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		reg = regs + caller_saved[i];
		reg->type = NOT_INIT;
		reg->imm = 0;
	}

	/* update return register */
	if (fn->ret_type == RET_INTEGER) {
		regs[BPF_REG_0].type = UNKNOWN_VALUE;
	} else if (fn->ret_type == RET_VOID) {
		regs[BPF_REG_0].type = NOT_INIT;
	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
		/* remember map_ptr, so that check_map_access()
		 * can check 'value_size' boundary of memory access
		 * to map element returned from bpf_map_lookup_elem()
		 */
		if (map == NULL) {
			verbose("kernel subsystem misconfigured verifier\n");
			return -EINVAL;
		}
		regs[BPF_REG_0].map_ptr = map;
	} else {
		verbose("unknown return type %d of func %d\n",
			fn->ret_type, func_id);
		return -EINVAL;
	}
	return 0;
}

/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
{
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode == BPF_END || opcode == BPF_NEG) {
		if (opcode == BPF_NEG) {
			if (BPF_SRC(insn->code) != 0 ||
			    insn->src_reg != BPF_REG_0 ||
			    insn->off != 0 || insn->imm != 0) {
				verbose("BPF_NEG uses reserved fields\n");
				return -EINVAL;
			}
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
				verbose("BPF_END uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src operand */
		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
		if (err)
			return err;

	} else if (opcode == BPF_MOV) {

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose("BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}

			/* check src operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose("BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
		if (err)
			return err;

		if (BPF_SRC(insn->code) == BPF_X) {
			if (BPF_CLASS(insn->code) == BPF_ALU64) {
				/* case: R1 = R2
				 * copy register state to dest reg
				 */
				regs[insn->dst_reg] = regs[insn->src_reg];
			} else {
				regs[insn->dst_reg].type = UNKNOWN_VALUE;
				regs[insn->dst_reg].map_ptr = NULL;
			}
		} else {
			/* case: R = imm
			 * remember the value we stored into this reg
			 */
			regs[insn->dst_reg].type = CONST_IMM;
			regs[insn->dst_reg].imm = insn->imm;
		}

	} else if (opcode > BPF_END) {
		verbose("invalid BPF_ALU opcode %x\n", opcode);
		return -EINVAL;

	} else {	/* all other ALU ops: and, sub, xor, add, ... */

		bool stack_relative = false;

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose("BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
			/* check src1 operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose("BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src2 operand */
		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
		    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
			verbose("div by zero\n");
			return -EINVAL;
		}

		/* pattern match 'bpf_add Rx, imm' instruction */
		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
		    regs[insn->dst_reg].type == FRAME_PTR &&
		    BPF_SRC(insn->code) == BPF_K)
			stack_relative = true;

		/* check dest operand */
		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
		if (err)
			return err;

		if (stack_relative) {
			regs[insn->dst_reg].type = PTR_TO_STACK;
			regs[insn->dst_reg].imm = insn->imm;
		}
	}

	return 0;
}

static int check_cond_jmp_op(struct verifier_env *env,
			     struct bpf_insn *insn, int *insn_idx)
{
	struct reg_state *regs = env->cur_state.regs;
	struct verifier_state *other_branch;
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode > BPF_EXIT) {
		verbose("invalid BPF_JMP opcode %x\n", opcode);
		return -EINVAL;
	}

	if (BPF_SRC(insn->code) == BPF_X) {
		if (insn->imm != 0) {
			verbose("BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}

		/* check src1 operand */
		err = check_reg_arg(regs, insn->src_reg, SRC_OP);
		if (err)
			return err;
	} else {
		if (insn->src_reg != BPF_REG_0) {
			verbose("BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}
	}

	/* check src2 operand */
	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	/* detect if R == 0 where R was initialized to zero earlier */
	if (BPF_SRC(insn->code) == BPF_K &&
	    (opcode == BPF_JEQ || opcode == BPF_JNE) &&
	    regs[insn->dst_reg].type == CONST_IMM &&
	    regs[insn->dst_reg].imm == insn->imm) {
		if (opcode == BPF_JEQ) {
			/* if (imm == imm) goto pc+off;
			 * only follow the goto, ignore fall-through
			 */
			*insn_idx += insn->off;
			return 0;
		} else {
			/* if (imm != imm) goto pc+off;
			 * only follow fall-through branch, since
			 * that's where the program will go
			 */
			return 0;
		}
	}

	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
	if (!other_branch)
		return -EFAULT;

	/* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */
	if (BPF_SRC(insn->code) == BPF_K &&
	    insn->imm == 0 && (opcode == BPF_JEQ ||
			       opcode == BPF_JNE) &&
	    regs[insn->dst_reg].type == PTR_TO_MAP_VALUE_OR_NULL) {
		if (opcode == BPF_JEQ) {
			/* next fallthrough insn can access memory via
			 * this register
			 */
			regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
			/* branch targer cannot access it, since reg == 0 */
			other_branch->regs[insn->dst_reg].type = CONST_IMM;
			other_branch->regs[insn->dst_reg].imm = 0;
		} else {
			other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
			regs[insn->dst_reg].type = CONST_IMM;
			regs[insn->dst_reg].imm = 0;
		}
	} else if (BPF_SRC(insn->code) == BPF_K &&
		   (opcode == BPF_JEQ || opcode == BPF_JNE)) {

		if (opcode == BPF_JEQ) {
			/* detect if (R == imm) goto
			 * and in the target state recognize that R = imm
			 */
			other_branch->regs[insn->dst_reg].type = CONST_IMM;
			other_branch->regs[insn->dst_reg].imm = insn->imm;
		} else {
			/* detect if (R != imm) goto
			 * and in the fall-through state recognize that R = imm
			 */
			regs[insn->dst_reg].type = CONST_IMM;
			regs[insn->dst_reg].imm = insn->imm;
		}
	}
	if (log_level)
		print_verifier_state(env);
	return 0;
}

/* return the map pointer stored inside BPF_LD_IMM64 instruction */
static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
{
	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;

	return (struct bpf_map *) (unsigned long) imm64;
}

/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
{
	struct reg_state *regs = env->cur_state.regs;
	int err;

	if (BPF_SIZE(insn->code) != BPF_DW) {
		verbose("invalid BPF_LD_IMM insn\n");
		return -EINVAL;
	}
	if (insn->off != 0) {
		verbose("BPF_LD_IMM64 uses reserved fields\n");
		return -EINVAL;
	}

	err = check_reg_arg(regs, insn->dst_reg, DST_OP);
	if (err)
		return err;

	if (insn->src_reg == 0)
		/* generic move 64-bit immediate into a register */
		return 0;

	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);

	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
	return 0;
}

/* non-recursive DFS pseudo code
 * 1  procedure DFS-iterative(G,v):
 * 2      label v as discovered
 * 3      let S be a stack
 * 4      S.push(v)
 * 5      while S is not empty
 * 6            t <- S.pop()
 * 7            if t is what we're looking for:
 * 8                return t
 * 9            for all edges e in G.adjacentEdges(t) do
 * 10               if edge e is already labelled
 * 11                   continue with the next edge
 * 12               w <- G.adjacentVertex(t,e)
 * 13               if vertex w is not discovered and not explored
 * 14                   label e as tree-edge
 * 15                   label w as discovered
 * 16                   S.push(w)
 * 17                   continue at 5
 * 18               else if vertex w is discovered
 * 19                   label e as back-edge
 * 20               else
 * 21                   // vertex w is explored
 * 22                   label e as forward- or cross-edge
 * 23           label t as explored
 * 24           S.pop()
 *
 * convention:
 * 0x10 - discovered
 * 0x11 - discovered and fall-through edge labelled
 * 0x12 - discovered and fall-through and branch edges labelled
 * 0x20 - explored
 */

enum {
	DISCOVERED = 0x10,
	EXPLORED = 0x20,
	FALLTHROUGH = 1,
	BRANCH = 2,
};

static int *insn_stack;	/* stack of insns to process */
static int cur_stack;	/* current stack index */
static int *insn_state;

/* t, w, e - match pseudo-code above:
 * t - index of current instruction
 * w - next instruction
 * e - edge
 */
static int push_insn(int t, int w, int e, struct verifier_env *env)
{
	if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
		return 0;

	if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
		return 0;

	if (w < 0 || w >= env->prog->len) {
		verbose("jump out of range from insn %d to %d\n", t, w);
		return -EINVAL;
	}

	if (insn_state[w] == 0) {
		/* tree-edge */
		insn_state[t] = DISCOVERED | e;
		insn_state[w] = DISCOVERED;
		if (cur_stack >= env->prog->len)
			return -E2BIG;
		insn_stack[cur_stack++] = w;
		return 1;
	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
		verbose("back-edge from insn %d to %d\n", t, w);
		return -EINVAL;
	} else if (insn_state[w] == EXPLORED) {
		/* forward- or cross-edge */
		insn_state[t] = DISCOVERED | e;
	} else {
		verbose("insn state internal bug\n");
		return -EFAULT;
	}
	return 0;
}

/* non-recursive depth-first-search to detect loops in BPF program
 * loop == back-edge in directed graph
 */
static int check_cfg(struct verifier_env *env)
{
	struct bpf_insn *insns = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int ret = 0;
	int i, t;

	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_state)
		return -ENOMEM;

	insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_stack) {
		kfree(insn_state);
		return -ENOMEM;
	}

	insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
	insn_stack[0] = 0; /* 0 is the first instruction */
	cur_stack = 1;

peek_stack:
	if (cur_stack == 0)
		goto check_state;
	t = insn_stack[cur_stack - 1];

	if (BPF_CLASS(insns[t].code) == BPF_JMP) {
		u8 opcode = BPF_OP(insns[t].code);

		if (opcode == BPF_EXIT) {
			goto mark_explored;
		} else if (opcode == BPF_CALL) {
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
		} else if (opcode == BPF_JA) {
			if (BPF_SRC(insns[t].code) != BPF_K) {
				ret = -EINVAL;
				goto err_free;
			}
			/* unconditional jump with single edge */
			ret = push_insn(t, t + insns[t].off + 1,
					FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
		} else {
			/* conditional jump with two edges */
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;

			ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
		}
	} else {
		/* all other non-branch instructions with single
		 * fall-through edge
		 */
		ret = push_insn(t, t + 1, FALLTHROUGH, env);
		if (ret == 1)
			goto peek_stack;
		else if (ret < 0)
			goto err_free;
	}

mark_explored:
	insn_state[t] = EXPLORED;
	if (cur_stack-- <= 0) {
		verbose("pop stack internal bug\n");
		ret = -EFAULT;
		goto err_free;
	}
	goto peek_stack;

check_state:
	for (i = 0; i < insn_cnt; i++) {
		if (insn_state[i] != EXPLORED) {
			verbose("unreachable insn %d\n", i);
			ret = -EINVAL;
			goto err_free;
		}
	}
	ret = 0; /* cfg looks good */

err_free:
	kfree(insn_state);
	kfree(insn_stack);
	return ret;
}

static int do_check(struct verifier_env *env)
{
	struct verifier_state *state = &env->cur_state;
	struct bpf_insn *insns = env->prog->insnsi;
	struct reg_state *regs = state->regs;
	int insn_cnt = env->prog->len;
	int insn_idx, prev_insn_idx = 0;
	int insn_processed = 0;
	bool do_print_state = false;

	init_reg_state(regs);
	insn_idx = 0;
	for (;;) {
		struct bpf_insn *insn;
		u8 class;
		int err;

		if (insn_idx >= insn_cnt) {
			verbose("invalid insn idx %d insn_cnt %d\n",
				insn_idx, insn_cnt);
			return -EFAULT;
		}

		insn = &insns[insn_idx];
		class = BPF_CLASS(insn->code);

		if (++insn_processed > 32768) {
			verbose("BPF program is too large. Proccessed %d insn\n",
				insn_processed);
			return -E2BIG;
		}

		if (log_level && do_print_state) {
			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
			print_verifier_state(env);
			do_print_state = false;
		}

		if (log_level) {
			verbose("%d: ", insn_idx);
			print_bpf_insn(insn);
		}

		if (class == BPF_ALU || class == BPF_ALU64) {
			err = check_alu_op(regs, insn);
			if (err)
				return err;

		} else if (class == BPF_LDX) {
			if (BPF_MODE(insn->code) != BPF_MEM ||
			    insn->imm != 0) {
				verbose("BPF_LDX uses reserved fields\n");
				return -EINVAL;
			}
			/* check src operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;

			err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK);
			if (err)
				return err;

			/* check that memory (src_reg + off) is readable,
			 * the state of dst_reg will be updated by this func
			 */
			err = check_mem_access(env, insn->src_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_READ,
					       insn->dst_reg);
			if (err)
				return err;

		} else if (class == BPF_STX) {
			if (BPF_MODE(insn->code) == BPF_XADD) {
				err = check_xadd(env, insn);
				if (err)
					return err;
				insn_idx++;
				continue;
			}

			if (BPF_MODE(insn->code) != BPF_MEM ||
			    insn->imm != 0) {
				verbose("BPF_STX uses reserved fields\n");
				return -EINVAL;
			}
			/* check src1 operand */
			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
			if (err)
				return err;
			/* check src2 operand */
			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
			if (err)
				return err;

			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, insn->dst_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_WRITE,
					       insn->src_reg);
			if (err)
				return err;

		} else if (class == BPF_ST) {
			if (BPF_MODE(insn->code) != BPF_MEM ||
			    insn->src_reg != BPF_REG_0) {
				verbose("BPF_ST uses reserved fields\n");
				return -EINVAL;
			}
			/* check src operand */
			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
			if (err)
				return err;

			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, insn->dst_reg, insn->off,
					       BPF_SIZE(insn->code), BPF_WRITE,
					       -1);
			if (err)
				return err;

		} else if (class == BPF_JMP) {
			u8 opcode = BPF_OP(insn->code);

			if (opcode == BPF_CALL) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->off != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_CALL uses reserved fields\n");
					return -EINVAL;
				}

				err = check_call(env, insn->imm);
				if (err)
					return err;

			} else if (opcode == BPF_JA) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_JA uses reserved fields\n");
					return -EINVAL;
				}

				insn_idx += insn->off + 1;
				continue;

			} else if (opcode == BPF_EXIT) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose("BPF_EXIT uses reserved fields\n");
					return -EINVAL;
				}

				/* eBPF calling convetion is such that R0 is used
				 * to return the value from eBPF program.
				 * Make sure that it's readable at this time
				 * of bpf_exit, which means that program wrote
				 * something into it earlier
				 */
				err = check_reg_arg(regs, BPF_REG_0, SRC_OP);
				if (err)
					return err;

				insn_idx = pop_stack(env, &prev_insn_idx);
				if (insn_idx < 0) {
					break;
				} else {
					do_print_state = true;
					continue;
				}
			} else {
				err = check_cond_jmp_op(env, insn, &insn_idx);
				if (err)
					return err;
			}
		} else if (class == BPF_LD) {
			u8 mode = BPF_MODE(insn->code);

			if (mode == BPF_ABS || mode == BPF_IND) {
				verbose("LD_ABS is not supported yet\n");
				return -EINVAL;
			} else if (mode == BPF_IMM) {
				err = check_ld_imm(env, insn);
				if (err)
					return err;

				insn_idx++;
			} else {
				verbose("invalid BPF_LD mode\n");
				return -EINVAL;
			}
		} else {
			verbose("unknown insn class %d\n", class);
			return -EINVAL;
		}

		insn_idx++;
	}

	return 0;
}

/* look for pseudo eBPF instructions that access map FDs and
 * replace them with actual map pointers
 */
static int replace_map_fd_with_map_ptr(struct verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i, j;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
			struct bpf_map *map;
			struct fd f;

			if (i == insn_cnt - 1 || insn[1].code != 0 ||
			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
			    insn[1].off != 0) {
				verbose("invalid bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			if (insn->src_reg == 0)
				/* valid generic load 64-bit imm */
				goto next_insn;

			if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
				verbose("unrecognized bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			f = fdget(insn->imm);

			map = bpf_map_get(f);
			if (IS_ERR(map)) {
				verbose("fd %d is not pointing to valid bpf_map\n",
					insn->imm);
				fdput(f);
				return PTR_ERR(map);
			}

			/* store map pointer inside BPF_LD_IMM64 instruction */
			insn[0].imm = (u32) (unsigned long) map;
			insn[1].imm = ((u64) (unsigned long) map) >> 32;

			/* check whether we recorded this map already */
			for (j = 0; j < env->used_map_cnt; j++)
				if (env->used_maps[j] == map) {
					fdput(f);
					goto next_insn;
				}

			if (env->used_map_cnt >= MAX_USED_MAPS) {
				fdput(f);
				return -E2BIG;
			}

			/* remember this map */
			env->used_maps[env->used_map_cnt++] = map;

			/* hold the map. If the program is rejected by verifier,
			 * the map will be released by release_maps() or it
			 * will be used by the valid program until it's unloaded
			 * and all maps are released in free_bpf_prog_info()
			 */
			atomic_inc(&map->refcnt);

			fdput(f);
next_insn:
			insn++;
			i++;
		}
	}

	/* now all pseudo BPF_LD_IMM64 instructions load valid
	 * 'struct bpf_map *' into a register instead of user map_fd.
	 * These pointers will be used later by verifier to validate map access.
	 */
	return 0;
}

/* drop refcnt of maps used by the rejected program */
static void release_maps(struct verifier_env *env)
{
	int i;

	for (i = 0; i < env->used_map_cnt; i++)
		bpf_map_put(env->used_maps[i]);
}

/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
static void convert_pseudo_ld_imm64(struct verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++, insn++)
		if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
			insn->src_reg = 0;
}

int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
{
	char __user *log_ubuf = NULL;
	struct verifier_env *env;
	int ret = -EINVAL;

	if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
		return -E2BIG;

	/* 'struct verifier_env' can be global, but since it's not small,
	 * allocate/free it every time bpf_check() is called
	 */
	env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL);
	if (!env)
		return -ENOMEM;

	env->prog = prog;

	/* grab the mutex to protect few globals used by verifier */
	mutex_lock(&bpf_verifier_lock);

	if (attr->log_level || attr->log_buf || attr->log_size) {
		/* user requested verbose verifier output
		 * and supplied buffer to store the verification trace
		 */
		log_level = attr->log_level;
		log_ubuf = (char __user *) (unsigned long) attr->log_buf;
		log_size = attr->log_size;
		log_len = 0;

		ret = -EINVAL;
		/* log_* values have to be sane */
		if (log_size < 128 || log_size > UINT_MAX >> 8 ||
		    log_level == 0 || log_ubuf == NULL)
			goto free_env;

		ret = -ENOMEM;
		log_buf = vmalloc(log_size);
		if (!log_buf)
			goto free_env;
	} else {
		log_level = 0;
	}

	ret = replace_map_fd_with_map_ptr(env);
	if (ret < 0)
		goto skip_full_check;

	ret = check_cfg(env);
	if (ret < 0)
		goto skip_full_check;

	ret = do_check(env);

skip_full_check:
	while (pop_stack(env, NULL) >= 0);

	if (log_level && log_len >= log_size - 1) {
		BUG_ON(log_len >= log_size);
		/* verifier log exceeded user supplied buffer */
		ret = -ENOSPC;
		/* fall through to return what was recorded */
	}

	/* copy verifier log back to user space including trailing zero */
	if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
		ret = -EFAULT;
		goto free_log_buf;
	}

	if (ret == 0 && env->used_map_cnt) {
		/* if program passed verifier, update used_maps in bpf_prog_info */
		prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
						     sizeof(env->used_maps[0]),
						     GFP_KERNEL);

		if (!prog->aux->used_maps) {
			ret = -ENOMEM;
			goto free_log_buf;
		}

		memcpy(prog->aux->used_maps, env->used_maps,
		       sizeof(env->used_maps[0]) * env->used_map_cnt);
		prog->aux->used_map_cnt = env->used_map_cnt;

		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
		 * bpf_ld_imm64 instructions
		 */
		convert_pseudo_ld_imm64(env);
	}

free_log_buf:
	if (log_level)
		vfree(log_buf);
free_env:
	if (!prog->aux->used_maps)
		/* if we didn't copy map pointers into bpf_prog_info, release
		 * them now. Otherwise free_bpf_prog_info() will release them.
		 */
		release_maps(env);
	kfree(env);
	mutex_unlock(&bpf_verifier_lock);
	return ret;
}