summaryrefslogtreecommitdiff
path: root/include/linux/filter.h
blob: 448dcc448f1fe59cb14de60969f71f8ba6c35278 (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Linux Socket Filter Data Structures
 */
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__

#include <stdarg.h>

#include <linux/atomic.h>
#include <linux/refcount.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <linux/linkage.h>
#include <linux/printk.h>
#include <linux/workqueue.h>
#include <linux/sched.h>
#include <linux/capability.h>
#include <linux/cryptohash.h>
#include <linux/set_memory.h>
#include <linux/kallsyms.h>
#include <linux/if_vlan.h>

#include <net/sch_generic.h>

#include <uapi/linux/filter.h>
#include <uapi/linux/bpf.h>

struct sk_buff;
struct sock;
struct seccomp_data;
struct bpf_prog_aux;
struct xdp_rxq_info;
struct xdp_buff;
struct sock_reuseport;

/* ArgX, context and stack frame pointer register positions. Note,
 * Arg1, Arg2, Arg3, etc are used as argument mappings of function
 * calls in BPF_CALL instruction.
 */
#define BPF_REG_ARG1	BPF_REG_1
#define BPF_REG_ARG2	BPF_REG_2
#define BPF_REG_ARG3	BPF_REG_3
#define BPF_REG_ARG4	BPF_REG_4
#define BPF_REG_ARG5	BPF_REG_5
#define BPF_REG_CTX	BPF_REG_6
#define BPF_REG_FP	BPF_REG_10

/* Additional register mappings for converted user programs. */
#define BPF_REG_A	BPF_REG_0
#define BPF_REG_X	BPF_REG_7
#define BPF_REG_TMP	BPF_REG_2	/* scratch reg */
#define BPF_REG_D	BPF_REG_8	/* data, callee-saved */
#define BPF_REG_H	BPF_REG_9	/* hlen, callee-saved */

/* Kernel hidden auxiliary/helper register for hardening step.
 * Only used by eBPF JITs. It's nothing more than a temporary
 * register that JITs use internally, only that here it's part
 * of eBPF instructions that have been rewritten for blinding
 * constants. See JIT pre-step in bpf_jit_blind_constants().
 */
#define BPF_REG_AX		MAX_BPF_REG
#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)

/* unused opcode to mark special call to bpf_tail_call() helper */
#define BPF_TAIL_CALL	0xf0

/* unused opcode to mark call to interpreter with arguments */
#define BPF_CALL_ARGS	0xe0

/* As per nm, we expose JITed images as text (code) section for
 * kallsyms. That way, tools like perf can find it to match
 * addresses.
 */
#define BPF_SYM_ELF_TYPE	't'

/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK	512

/* Helper macros for filter block array initializers. */

/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */

#define BPF_ALU64_REG(OP, DST, SRC)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

#define BPF_ALU32_REG(OP, DST, SRC)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */

#define BPF_ALU64_IMM(OP, DST, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_ALU32_IMM(OP, DST, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */

#define BPF_ENDIAN(TYPE, DST, LEN)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_END | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = LEN })

/* Short form of mov, dst_reg = src_reg */

#define BPF_MOV64_REG(DST, SRC)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

#define BPF_MOV32_REG(DST, SRC)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

/* Short form of mov, dst_reg = imm32 */

#define BPF_MOV64_IMM(DST, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_MOV32_IMM(DST, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
#define BPF_LD_IMM64(DST, IMM)					\
	BPF_LD_IMM64_RAW(DST, 0, IMM)

#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = (__u32) (IMM) }),			\
	((struct bpf_insn) {					\
		.code  = 0, /* zero is reserved opcode */	\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = ((__u64) (IMM)) >> 32 })

/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
#define BPF_LD_MAP_FD(DST, MAP_FD)				\
	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)

/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */

#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)			\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM)			\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */

#define BPF_LD_ABS(SIZE, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS,	\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */

#define BPF_LD_IND(SIZE, SRC, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_IND,	\
		.dst_reg = 0,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

/* Memory load, dst_reg = *(uint *) (src_reg + off16) */

#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Memory store, *(uint *) (dst_reg + off16) = src_reg */

#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */

#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Memory store, *(uint *) (dst_reg + off16) = imm32 */

#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */

#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */

#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Unconditional jumps, goto pc + off16 */

#define BPF_JMP_A(OFF)						\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_JA,			\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Relative call */

#define BPF_CALL_REL(TGT)					\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_CALL,			\
		.dst_reg = 0,					\
		.src_reg = BPF_PSEUDO_CALL,			\
		.off   = 0,					\
		.imm   = TGT })

/* Function call */

#define BPF_CAST_CALL(x)					\
		((u64 (*)(u64, u64, u64, u64, u64))(x))

#define BPF_EMIT_CALL(FUNC)					\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_CALL,			\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = ((FUNC) - __bpf_call_base) })

/* Raw code statement block */

#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
	((struct bpf_insn) {					\
		.code  = CODE,					\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Program exit */

#define BPF_EXIT_INSN()						\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_EXIT,			\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = 0 })

/* Internal classic blocks for direct assignment */

#define __BPF_STMT(CODE, K)					\
	((struct sock_filter) BPF_STMT(CODE, K))

#define __BPF_JUMP(CODE, K, JT, JF)				\
	((struct sock_filter) BPF_JUMP(CODE, K, JT, JF))

#define bytes_to_bpf_size(bytes)				\
({								\
	int bpf_size = -EINVAL;					\
								\
	if (bytes == sizeof(u8))				\
		bpf_size = BPF_B;				\
	else if (bytes == sizeof(u16))				\
		bpf_size = BPF_H;				\
	else if (bytes == sizeof(u32))				\
		bpf_size = BPF_W;				\
	else if (bytes == sizeof(u64))				\
		bpf_size = BPF_DW;				\
								\
	bpf_size;						\
})

#define bpf_size_to_bytes(bpf_size)				\
({								\
	int bytes = -EINVAL;					\
								\
	if (bpf_size == BPF_B)					\
		bytes = sizeof(u8);				\
	else if (bpf_size == BPF_H)				\
		bytes = sizeof(u16);				\
	else if (bpf_size == BPF_W)				\
		bytes = sizeof(u32);				\
	else if (bpf_size == BPF_DW)				\
		bytes = sizeof(u64);				\
								\
	bytes;							\
})

#define BPF_SIZEOF(type)					\
	({							\
		const int __size = bytes_to_bpf_size(sizeof(type)); \
		BUILD_BUG_ON(__size < 0);			\
		__size;						\
	})

#define BPF_FIELD_SIZEOF(type, field)				\
	({							\
		const int __size = bytes_to_bpf_size(FIELD_SIZEOF(type, field)); \
		BUILD_BUG_ON(__size < 0);			\
		__size;						\
	})

#define BPF_LDST_BYTES(insn)					\
	({							\
		const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \
		WARN_ON(__size < 0);				\
		__size;						\
	})

#define __BPF_MAP_0(m, v, ...) v
#define __BPF_MAP_1(m, v, t, a, ...) m(t, a)
#define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__)
#define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__)
#define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__)
#define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__)

#define __BPF_REG_0(...) __BPF_PAD(5)
#define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4)
#define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3)
#define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2)
#define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1)
#define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__)

#define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__)
#define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__)

#define __BPF_CAST(t, a)						       \
	(__force t)							       \
	(__force							       \
	 typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long),      \
				      (unsigned long)0, (t)0))) a
#define __BPF_V void
#define __BPF_N

#define __BPF_DECL_ARGS(t, a) t   a
#define __BPF_DECL_REGS(t, a) u64 a

#define __BPF_PAD(n)							       \
	__BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2,       \
		  u64, __ur_3, u64, __ur_4, u64, __ur_5)

#define BPF_CALL_x(x, name, ...)					       \
	static __always_inline						       \
	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__));   \
	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__));	       \
	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__))	       \
	{								       \
		return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\
	}								       \
	static __always_inline						       \
	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))

#define BPF_CALL_0(name, ...)	BPF_CALL_x(0, name, __VA_ARGS__)
#define BPF_CALL_1(name, ...)	BPF_CALL_x(1, name, __VA_ARGS__)
#define BPF_CALL_2(name, ...)	BPF_CALL_x(2, name, __VA_ARGS__)
#define BPF_CALL_3(name, ...)	BPF_CALL_x(3, name, __VA_ARGS__)
#define BPF_CALL_4(name, ...)	BPF_CALL_x(4, name, __VA_ARGS__)
#define BPF_CALL_5(name, ...)	BPF_CALL_x(5, name, __VA_ARGS__)

#define bpf_ctx_range(TYPE, MEMBER)						\
	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
#define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2)				\
	offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1

#define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE)				\
	({									\
		BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE));		\
		*(PTR_SIZE) = (SIZE);						\
		offsetof(TYPE, MEMBER);						\
	})

#ifdef CONFIG_COMPAT
/* A struct sock_filter is architecture independent. */
struct compat_sock_fprog {
	u16		len;
	compat_uptr_t	filter;	/* struct sock_filter * */
};
#endif

struct sock_fprog_kern {
	u16			len;
	struct sock_filter	*filter;
};

struct bpf_binary_header {
	u32 pages;
	/* Some arches need word alignment for their instructions */
	u8 image[] __aligned(4);
};

struct bpf_prog {
	u16			pages;		/* Number of allocated pages */
	u16			jited:1,	/* Is our filter JIT'ed? */
				jit_requested:1,/* archs need to JIT the prog */
				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
				gpl_compatible:1, /* Is filter GPL compatible? */
				cb_access:1,	/* Is control block accessed? */
				dst_needed:1,	/* Do we need dst entry? */
				blinded:1,	/* Was blinded */
				is_func:1,	/* program is a bpf function */
				kprobe_override:1, /* Do we override a kprobe? */
				has_callchain_buf:1; /* callchain buffer allocated? */
	enum bpf_prog_type	type;		/* Type of BPF program */
	enum bpf_attach_type	expected_attach_type; /* For some prog types */
	u32			len;		/* Number of filter blocks */
	u32			jited_len;	/* Size of jited insns in bytes */
	u8			tag[BPF_TAG_SIZE];
	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
	unsigned int		(*bpf_func)(const void *ctx,
					    const struct bpf_insn *insn);
	/* Instructions for interpreter */
	union {
		struct sock_filter	insns[0];
		struct bpf_insn		insnsi[0];
	};
};

struct sk_filter {
	refcount_t	refcnt;
	struct rcu_head	rcu;
	struct bpf_prog	*prog;
};

#define BPF_PROG_RUN(filter, ctx)  (*(filter)->bpf_func)(ctx, (filter)->insnsi)

#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN

struct bpf_skb_data_end {
	struct qdisc_skb_cb qdisc_cb;
	void *data_meta;
	void *data_end;
};

struct bpf_redirect_info {
	u32 ifindex;
	u32 flags;
	struct bpf_map *map;
	struct bpf_map *map_to_flush;
	u32 kern_flags;
};

DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);

/* flags for bpf_redirect_info kern_flags */
#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */

/* Compute the linear packet data range [data, data_end) which
 * will be accessed by various program types (cls_bpf, act_bpf,
 * lwt, ...). Subsystems allowing direct data access must (!)
 * ensure that cb[] area can be written to when BPF program is
 * invoked (otherwise cb[] save/restore is necessary).
 */
static inline void bpf_compute_data_pointers(struct sk_buff *skb)
{
	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;

	BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
	cb->data_meta = skb->data - skb_metadata_len(skb);
	cb->data_end  = skb->data + skb_headlen(skb);
}

/* Similar to bpf_compute_data_pointers(), except that save orginal
 * data in cb->data and cb->meta_data for restore.
 */
static inline void bpf_compute_and_save_data_end(
	struct sk_buff *skb, void **saved_data_end)
{
	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;

	*saved_data_end = cb->data_end;
	cb->data_end  = skb->data + skb_headlen(skb);
}

/* Restore data saved by bpf_compute_data_pointers(). */
static inline void bpf_restore_data_end(
	struct sk_buff *skb, void *saved_data_end)
{
	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;

	cb->data_end = saved_data_end;
}

static inline u8 *bpf_skb_cb(struct sk_buff *skb)
{
	/* eBPF programs may read/write skb->cb[] area to transfer meta
	 * data between tail calls. Since this also needs to work with
	 * tc, that scratch memory is mapped to qdisc_skb_cb's data area.
	 *
	 * In some socket filter cases, the cb unfortunately needs to be
	 * saved/restored so that protocol specific skb->cb[] data won't
	 * be lost. In any case, due to unpriviledged eBPF programs
	 * attached to sockets, we need to clear the bpf_skb_cb() area
	 * to not leak previous contents to user space.
	 */
	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN);
	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) !=
		     FIELD_SIZEOF(struct qdisc_skb_cb, data));

	return qdisc_skb_cb(skb)->data;
}

static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
				       struct sk_buff *skb)
{
	u8 *cb_data = bpf_skb_cb(skb);
	u8 cb_saved[BPF_SKB_CB_LEN];
	u32 res;

	if (unlikely(prog->cb_access)) {
		memcpy(cb_saved, cb_data, sizeof(cb_saved));
		memset(cb_data, 0, sizeof(cb_saved));
	}

	res = BPF_PROG_RUN(prog, skb);

	if (unlikely(prog->cb_access))
		memcpy(cb_data, cb_saved, sizeof(cb_saved));

	return res;
}

static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
					struct sk_buff *skb)
{
	u8 *cb_data = bpf_skb_cb(skb);

	if (unlikely(prog->cb_access))
		memset(cb_data, 0, BPF_SKB_CB_LEN);

	return BPF_PROG_RUN(prog, skb);
}

static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
					    struct xdp_buff *xdp)
{
	/* Caller needs to hold rcu_read_lock() (!), otherwise program
	 * can be released while still running, or map elements could be
	 * freed early while still having concurrent users. XDP fastpath
	 * already takes rcu_read_lock() when fetching the program, so
	 * it's not necessary here anymore.
	 */
	return BPF_PROG_RUN(prog, xdp);
}

static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
{
	return prog->len * sizeof(struct bpf_insn);
}

static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog)
{
	return round_up(bpf_prog_insn_size(prog) +
			sizeof(__be64) + 1, SHA_MESSAGE_BYTES);
}

static inline unsigned int bpf_prog_size(unsigned int proglen)
{
	return max(sizeof(struct bpf_prog),
		   offsetof(struct bpf_prog, insns[proglen]));
}

static inline bool bpf_prog_was_classic(const struct bpf_prog *prog)
{
	/* When classic BPF programs have been loaded and the arch
	 * does not have a classic BPF JIT (anymore), they have been
	 * converted via bpf_migrate_filter() to eBPF and thus always
	 * have an unspec program type.
	 */
	return prog->type == BPF_PROG_TYPE_UNSPEC;
}

static inline u32 bpf_ctx_off_adjust_machine(u32 size)
{
	const u32 size_machine = sizeof(unsigned long);

	if (size > size_machine && size % size_machine == 0)
		size = size_machine;

	return size;
}

static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access,
					   u32 size_default)
{
	size_default = bpf_ctx_off_adjust_machine(size_default);
	size_access  = bpf_ctx_off_adjust_machine(size_access);

#ifdef __LITTLE_ENDIAN
	return (off & (size_default - 1)) == 0;
#else
	return (off & (size_default - 1)) + size_access == size_default;
#endif
}

static inline bool
bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
{
	return bpf_ctx_narrow_align_ok(off, size, size_default) &&
	       size <= size_default && (size & (size - 1)) == 0;
}

#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))

static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
	fp->undo_set_mem = 1;
	set_memory_ro((unsigned long)fp, fp->pages);
}

static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
	if (fp->undo_set_mem)
		set_memory_rw((unsigned long)fp, fp->pages);
}

static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
{
	set_memory_ro((unsigned long)hdr, hdr->pages);
}

static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
{
	set_memory_rw((unsigned long)hdr, hdr->pages);
}

static inline struct bpf_binary_header *
bpf_jit_binary_hdr(const struct bpf_prog *fp)
{
	unsigned long real_start = (unsigned long)fp->bpf_func;
	unsigned long addr = real_start & PAGE_MASK;

	return (void *)addr;
}

int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
{
	return sk_filter_trim_cap(sk, skb, 1);
}

struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
void bpf_prog_free(struct bpf_prog *fp);

bool bpf_opcode_in_insntable(u8 code);

struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
				  gfp_t gfp_extra_flags);
void __bpf_prog_free(struct bpf_prog *fp);

static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
{
	bpf_prog_unlock_ro(fp);
	__bpf_prog_free(fp);
}

typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter,
				       unsigned int flen);

int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
			      bpf_aux_classic_check_t trans, bool save_orig);
void bpf_prog_destroy(struct bpf_prog *fp);

int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_attach_bpf(u32 ufd, struct sock *sk);
int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
void sk_reuseport_prog_free(struct bpf_prog *prog);
int sk_detach_filter(struct sock *sk);
int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
		  unsigned int len);

bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);

u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
#define __bpf_call_base_args \
	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
	 __bpf_call_base)

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
void bpf_jit_compile(struct bpf_prog *prog);
bool bpf_helper_changes_pkt_data(void *func);

static inline bool bpf_dump_raw_ok(void)
{
	/* Reconstruction of call-sites is dependent on kallsyms,
	 * thus make dump the same restriction.
	 */
	return kallsyms_show_value() == 1;
}

struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
				       const struct bpf_insn *patch, u32 len);

void bpf_clear_redirect_map(struct bpf_map *map);

static inline bool xdp_return_frame_no_direct(void)
{
	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);

	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
}

static inline void xdp_set_return_frame_no_direct(void)
{
	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);

	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
}

static inline void xdp_clear_return_frame_no_direct(void)
{
	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);

	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
}

static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
				 unsigned int pktlen)
{
	unsigned int len;

	if (unlikely(!(fwd->flags & IFF_UP)))
		return -ENETDOWN;

	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
	if (pktlen > len)
		return -EMSGSIZE;

	return 0;
}

/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
 * same cpu context. Further for best results no more than a single map
 * for the do_redirect/do_flush pair should be used. This limitation is
 * because we only track one map and force a flush when the map changes.
 * This does not appear to be a real limitation for existing software.
 */
int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
			    struct xdp_buff *xdp, struct bpf_prog *prog);
int xdp_do_redirect(struct net_device *dev,
		    struct xdp_buff *xdp,
		    struct bpf_prog *prog);
void xdp_do_flush_map(void);

void bpf_warn_invalid_xdp_action(u32 act);

#ifdef CONFIG_INET
struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
				  struct bpf_prog *prog, struct sk_buff *skb,
				  u32 hash);
#else
static inline struct sock *
bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
		     struct bpf_prog *prog, struct sk_buff *skb,
		     u32 hash)
{
	return NULL;
}
#endif

#ifdef CONFIG_BPF_JIT
extern int bpf_jit_enable;
extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
extern int bpf_jit_limit;

typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);

struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
		     unsigned int alignment,
		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
void bpf_jit_binary_free(struct bpf_binary_header *hdr);

void bpf_jit_free(struct bpf_prog *fp);

int bpf_jit_get_func_addr(const struct bpf_prog *prog,
			  const struct bpf_insn *insn, bool extra_pass,
			  u64 *func_addr, bool *func_addr_fixed);

struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);

static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
				u32 pass, void *image)
{
	pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen,
	       proglen, pass, image, current->comm, task_pid_nr(current));

	if (image)
		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
			       16, 1, image, proglen, false);
}

static inline bool bpf_jit_is_ebpf(void)
{
# ifdef CONFIG_HAVE_EBPF_JIT
	return true;
# else
	return false;
# endif
}

static inline bool ebpf_jit_enabled(void)
{
	return bpf_jit_enable && bpf_jit_is_ebpf();
}

static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
{
	return fp->jited && bpf_jit_is_ebpf();
}

static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
{
	/* These are the prerequisites, should someone ever have the
	 * idea to call blinding outside of them, we make sure to
	 * bail out.
	 */
	if (!bpf_jit_is_ebpf())
		return false;
	if (!prog->jit_requested)
		return false;
	if (!bpf_jit_harden)
		return false;
	if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN))
		return false;

	return true;
}

static inline bool bpf_jit_kallsyms_enabled(void)
{
	/* There are a couple of corner cases where kallsyms should
	 * not be enabled f.e. on hardening.
	 */
	if (bpf_jit_harden)
		return false;
	if (!bpf_jit_kallsyms)
		return false;
	if (bpf_jit_kallsyms == 1)
		return true;

	return false;
}

const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
				 unsigned long *off, char *sym);
bool is_bpf_text_address(unsigned long addr);
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
		    char *sym);

static inline const char *
bpf_address_lookup(unsigned long addr, unsigned long *size,
		   unsigned long *off, char **modname, char *sym)
{
	const char *ret = __bpf_address_lookup(addr, size, off, sym);

	if (ret && modname)
		*modname = NULL;
	return ret;
}

void bpf_prog_kallsyms_add(struct bpf_prog *fp);
void bpf_prog_kallsyms_del(struct bpf_prog *fp);

#else /* CONFIG_BPF_JIT */

static inline bool ebpf_jit_enabled(void)
{
	return false;
}

static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
{
	return false;
}

static inline void bpf_jit_free(struct bpf_prog *fp)
{
	bpf_prog_unlock_free(fp);
}

static inline bool bpf_jit_kallsyms_enabled(void)
{
	return false;
}

static inline const char *
__bpf_address_lookup(unsigned long addr, unsigned long *size,
		     unsigned long *off, char *sym)
{
	return NULL;
}

static inline bool is_bpf_text_address(unsigned long addr)
{
	return false;
}

static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value,
				  char *type, char *sym)
{
	return -ERANGE;
}

static inline const char *
bpf_address_lookup(unsigned long addr, unsigned long *size,
		   unsigned long *off, char **modname, char *sym)
{
	return NULL;
}

static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
}

static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
{
}
#endif /* CONFIG_BPF_JIT */

void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);

#define BPF_ANC		BIT(15)

static inline bool bpf_needs_clear_a(const struct sock_filter *first)
{
	switch (first->code) {
	case BPF_RET | BPF_K:
	case BPF_LD | BPF_W | BPF_LEN:
		return false;

	case BPF_LD | BPF_W | BPF_ABS:
	case BPF_LD | BPF_H | BPF_ABS:
	case BPF_LD | BPF_B | BPF_ABS:
		if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X)
			return true;
		return false;

	default:
		return true;
	}
}

static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
{
	BUG_ON(ftest->code & BPF_ANC);

	switch (ftest->code) {
	case BPF_LD | BPF_W | BPF_ABS:
	case BPF_LD | BPF_H | BPF_ABS:
	case BPF_LD | BPF_B | BPF_ABS:
#define BPF_ANCILLARY(CODE)	case SKF_AD_OFF + SKF_AD_##CODE:	\
				return BPF_ANC | SKF_AD_##CODE
		switch (ftest->k) {
		BPF_ANCILLARY(PROTOCOL);
		BPF_ANCILLARY(PKTTYPE);
		BPF_ANCILLARY(IFINDEX);
		BPF_ANCILLARY(NLATTR);
		BPF_ANCILLARY(NLATTR_NEST);
		BPF_ANCILLARY(MARK);
		BPF_ANCILLARY(QUEUE);
		BPF_ANCILLARY(HATYPE);
		BPF_ANCILLARY(RXHASH);
		BPF_ANCILLARY(CPU);
		BPF_ANCILLARY(ALU_XOR_X);
		BPF_ANCILLARY(VLAN_TAG);
		BPF_ANCILLARY(VLAN_TAG_PRESENT);
		BPF_ANCILLARY(PAY_OFFSET);
		BPF_ANCILLARY(RANDOM);
		BPF_ANCILLARY(VLAN_TPID);
		}
		/* Fallthrough. */
	default:
		return ftest->code;
	}
}

void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb,
					   int k, unsigned int size);

static inline void *bpf_load_pointer(const struct sk_buff *skb, int k,
				     unsigned int size, void *buffer)
{
	if (k >= 0)
		return skb_header_pointer(skb, k, size, buffer);

	return bpf_internal_load_pointer_neg_helper(skb, k, size);
}

static inline int bpf_tell_extensions(void)
{
	return SKF_AD_MAX;
}

struct bpf_sock_addr_kern {
	struct sock *sk;
	struct sockaddr *uaddr;
	/* Temporary "register" to make indirect stores to nested structures
	 * defined above. We need three registers to make such a store, but
	 * only two (src and dst) are available at convert_ctx_access time
	 */
	u64 tmp_reg;
	void *t_ctx;	/* Attach type specific context. */
};

struct bpf_sock_ops_kern {
	struct	sock *sk;
	u32	op;
	union {
		u32 args[4];
		u32 reply;
		u32 replylong[4];
	};
	u32	is_fullsock;
	u64	temp;			/* temp and everything after is not
					 * initialized to 0 before calling
					 * the BPF program. New fields that
					 * should be initialized to 0 should
					 * be inserted before temp.
					 * temp is scratch storage used by
					 * sock_ops_convert_ctx_access
					 * as temporary storage of a register.
					 */
};

#endif /* __LINUX_FILTER_H__ */