forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathbpf.h
More file actions
3764 lines (3638 loc) · 140 KB
/
bpf.h
File metadata and controls
3764 lines (3638 loc) · 140 KB
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
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* 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.
*/
#ifndef _UAPI__LINUX_BPF_H__
#define _UAPI__LINUX_BPF_H__
#include <linux/types.h>
#include <linux/bpf_common.h>
/* Extended instruction set based on top of classic BPF */
/* instruction classes */
#define BPF_JMP32 0x06 /* jmp mode in word width */
#define BPF_ALU64 0x07 /* alu mode in double word width */
/* ld/ldx fields */
#define BPF_DW 0x18 /* double word (64-bit) */
#define BPF_XADD 0xc0 /* exclusive add */
/* alu/jmp fields */
#define BPF_MOV 0xb0 /* mov reg to reg */
#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
/* change endianness of a register */
#define BPF_END 0xd0 /* flags for endianness conversion: */
#define BPF_TO_LE 0x00 /* convert to little-endian */
#define BPF_TO_BE 0x08 /* convert to big-endian */
#define BPF_FROM_LE BPF_TO_LE
#define BPF_FROM_BE BPF_TO_BE
/* jmp encodings */
#define BPF_JNE 0x50 /* jump != */
#define BPF_JLT 0xa0 /* LT is unsigned, '<' */
#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */
#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
#define BPF_CALL 0x80 /* function call */
#define BPF_EXIT 0x90 /* function return */
/* Register numbers */
enum {
BPF_REG_0 = 0,
BPF_REG_1,
BPF_REG_2,
BPF_REG_3,
BPF_REG_4,
BPF_REG_5,
BPF_REG_6,
BPF_REG_7,
BPF_REG_8,
BPF_REG_9,
BPF_REG_10,
__MAX_BPF_REG,
};
/* BPF has 10 general purpose 64-bit registers and stack frame. */
#define MAX_BPF_REG __MAX_BPF_REG
struct bpf_insn {
__u8 code; /* opcode */
__u8 dst_reg:4; /* dest register */
__u8 src_reg:4; /* source register */
__s16 off; /* signed offset */
__s32 imm; /* signed immediate constant */
};
/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
struct bpf_lpm_trie_key {
__u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
__u8 data[0]; /* Arbitrary size */
};
struct bpf_cgroup_storage_key {
__u64 cgroup_inode_id; /* cgroup inode id */
__u32 attach_type; /* program attach type */
};
/* BPF syscall commands, see bpf(2) man-page for details. */
enum bpf_cmd {
BPF_MAP_CREATE,
BPF_MAP_LOOKUP_ELEM,
BPF_MAP_UPDATE_ELEM,
BPF_MAP_DELETE_ELEM,
BPF_MAP_GET_NEXT_KEY,
BPF_PROG_LOAD,
BPF_OBJ_PIN,
BPF_OBJ_GET,
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
BPF_PROG_GET_NEXT_ID,
BPF_MAP_GET_NEXT_ID,
BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
BPF_MAP_FREEZE,
BPF_BTF_GET_NEXT_ID,
BPF_MAP_LOOKUP_BATCH,
BPF_MAP_LOOKUP_AND_DELETE_BATCH,
BPF_MAP_UPDATE_BATCH,
BPF_MAP_DELETE_BATCH,
};
enum bpf_map_type {
BPF_MAP_TYPE_UNSPEC,
BPF_MAP_TYPE_HASH,
BPF_MAP_TYPE_ARRAY,
BPF_MAP_TYPE_PROG_ARRAY,
BPF_MAP_TYPE_PERF_EVENT_ARRAY,
BPF_MAP_TYPE_PERCPU_HASH,
BPF_MAP_TYPE_PERCPU_ARRAY,
BPF_MAP_TYPE_STACK_TRACE,
BPF_MAP_TYPE_CGROUP_ARRAY,
BPF_MAP_TYPE_LRU_HASH,
BPF_MAP_TYPE_LRU_PERCPU_HASH,
BPF_MAP_TYPE_LPM_TRIE,
BPF_MAP_TYPE_ARRAY_OF_MAPS,
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
BPF_MAP_TYPE_CPUMAP,
BPF_MAP_TYPE_XSKMAP,
BPF_MAP_TYPE_SOCKHASH,
BPF_MAP_TYPE_CGROUP_STORAGE,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
BPF_MAP_TYPE_QUEUE,
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
};
/* Note that tracing related programs such as
* BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
* are not subject to a stable API since kernel internal data
* structures can change from release to release and may
* therefore break existing tracing BPF programs. Tracing BPF
* programs correspond to /a/ specific kernel which is to be
* analyzed, and not /a/ specific kernel /and/ all future ones.
*/
enum bpf_prog_type {
BPF_PROG_TYPE_UNSPEC,
BPF_PROG_TYPE_SOCKET_FILTER,
BPF_PROG_TYPE_KPROBE,
BPF_PROG_TYPE_SCHED_CLS,
BPF_PROG_TYPE_SCHED_ACT,
BPF_PROG_TYPE_TRACEPOINT,
BPF_PROG_TYPE_XDP,
BPF_PROG_TYPE_PERF_EVENT,
BPF_PROG_TYPE_CGROUP_SKB,
BPF_PROG_TYPE_CGROUP_SOCK,
BPF_PROG_TYPE_LWT_IN,
BPF_PROG_TYPE_LWT_OUT,
BPF_PROG_TYPE_LWT_XMIT,
BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
BPF_PROG_TYPE_RAW_TRACEPOINT,
BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_PROG_TYPE_LWT_SEG6LOCAL,
BPF_PROG_TYPE_LIRC_MODE2,
BPF_PROG_TYPE_SK_REUSEPORT,
BPF_PROG_TYPE_FLOW_DISSECTOR,
BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_PROG_TYPE_TRACING,
BPF_PROG_TYPE_STRUCT_OPS,
BPF_PROG_TYPE_EXT,
};
enum bpf_attach_type {
BPF_CGROUP_INET_INGRESS,
BPF_CGROUP_INET_EGRESS,
BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_SOCK_OPS,
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
BPF_CGROUP_DEVICE,
BPF_SK_MSG_VERDICT,
BPF_CGROUP_INET4_BIND,
BPF_CGROUP_INET6_BIND,
BPF_CGROUP_INET4_CONNECT,
BPF_CGROUP_INET6_CONNECT,
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_UDP4_SENDMSG,
BPF_CGROUP_UDP6_SENDMSG,
BPF_LIRC_MODE2,
BPF_FLOW_DISSECTOR,
BPF_CGROUP_SYSCTL,
BPF_CGROUP_UDP4_RECVMSG,
BPF_CGROUP_UDP6_RECVMSG,
BPF_CGROUP_GETSOCKOPT,
BPF_CGROUP_SETSOCKOPT,
BPF_TRACE_RAW_TP,
BPF_TRACE_FENTRY,
BPF_TRACE_FEXIT,
__MAX_BPF_ATTACH_TYPE
};
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
*
* NONE(default): No further bpf programs allowed in the subtree.
*
* BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
* the program in this cgroup yields to sub-cgroup program.
*
* BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
* that cgroup program gets run in addition to the program in this cgroup.
*
* Only one program is allowed to be attached to a cgroup with
* NONE or BPF_F_ALLOW_OVERRIDE flag.
* Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
* release old program and attach the new one. Attach flags has to match.
*
* Multiple programs are allowed to be attached to a cgroup with
* BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
* (those that were attached first, run first)
* The programs of sub-cgroup are executed first, then programs of
* this cgroup and then programs of parent cgroup.
* When children program makes decision (like picking TCP CA or sock bind)
* parent program has a chance to override it.
*
* With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
* programs for a cgroup. Though it's possible to replace an old program at
* any position by also specifying BPF_F_REPLACE flag and position itself in
* replace_bpf_fd attribute. Old program at this position will be released.
*
* A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
* A cgroup with NONE doesn't allow any programs in sub-cgroups.
* Ex1:
* cgrp1 (MULTI progs A, B) ->
* cgrp2 (OVERRIDE prog C) ->
* cgrp3 (MULTI prog D) ->
* cgrp4 (OVERRIDE prog E) ->
* cgrp5 (NONE prog F)
* the event in cgrp5 triggers execution of F,D,A,B in that order.
* if prog F is detached, the execution is E,D,A,B
* if prog F and D are detached, the execution is E,A,B
* if prog F, E and D are detached, the execution is C,A,B
*
* All eligible programs are executed regardless of return code from
* earlier programs.
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
#define BPF_F_ALLOW_MULTI (1U << 1)
#define BPF_F_REPLACE (1U << 2)
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will perform strict alignment checking as if the kernel
* has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
* and NET_IP_ALIGN defined to 2.
*/
#define BPF_F_STRICT_ALIGNMENT (1U << 0)
/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
* verifier will allow any alignment whatsoever. On platforms
* with strict alignment requirements for loads ands stores (such
* as sparc and mips) the verifier validates that all loads and
* stores provably follow this requirement. This flag turns that
* checking and enforcement off.
*
* It is mostly used for testing when we want to validate the
* context and memory access aspects of the verifier, but because
* of an unaligned access the alignment check would trigger before
* the one we are interested in.
*/
#define BPF_F_ANY_ALIGNMENT (1U << 1)
/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
* Verifier does sub-register def/use analysis and identifies instructions whose
* def only matters for low 32-bit, high 32-bit is never referenced later
* through implicit zero extension. Therefore verifier notifies JIT back-ends
* that it is safe to ignore clearing high 32-bit for these instructions. This
* saves some back-ends a lot of code-gen. However such optimization is not
* necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
* hence hasn't used verifier's analysis result. But, we really want to have a
* way to be able to verify the correctness of the described optimization on
* x86_64 on which testsuites are frequently exercised.
*
* So, this flag is introduced. Once it is set, verifier will randomize high
* 32-bit for those instructions who has been identified as safe to ignore them.
* Then, if verifier is not doing correct analysis, such randomization will
* regress tests to expose bugs.
*/
#define BPF_F_TEST_RND_HI32 (1U << 2)
/* The verifier internal test flag. Behavior is undefined */
#define BPF_F_TEST_STATE_FREQ (1U << 3)
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* two extensions:
*
* insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
* insn[0].imm: map fd map fd
* insn[1].imm: 0 offset into value
* insn[0].off: 0 0
* insn[1].off: 0 0
* ldimm64 rewrite: address of map address of map[0]+offset
* verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
*/
#define BPF_PSEUDO_MAP_FD 1
#define BPF_PSEUDO_MAP_VALUE 2
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
*/
#define BPF_PSEUDO_CALL 1
/* flags for BPF_MAP_UPDATE_ELEM command */
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */
/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0)
/* Instead of having one common LRU list in the
* BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
* which can scale and perform better.
* Note, the LRU nodes (including free nodes) cannot be moved
* across different LRU lists.
*/
#define BPF_F_NO_COMMON_LRU (1U << 1)
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE (1U << 2)
#define BPF_OBJ_NAME_LEN 16U
/* Flags for accessing BPF object from syscall side. */
#define BPF_F_RDONLY (1U << 3)
#define BPF_F_WRONLY (1U << 4)
/* Flag for stack_map, store build_id+offset instead of pointer */
#define BPF_F_STACK_BUILD_ID (1U << 5)
/* Zero-initialize hash function seed. This should only be used for testing. */
#define BPF_F_ZERO_SEED (1U << 6)
/* Flags for accessing BPF object from program side. */
#define BPF_F_RDONLY_PROG (1U << 7)
#define BPF_F_WRONLY_PROG (1U << 8)
/* Clone map from listener for newly accepted socket */
#define BPF_F_CLONE (1U << 9)
/* Enable memory-mapping BPF map */
#define BPF_F_MMAPABLE (1U << 10)
/* Flags for BPF_PROG_QUERY. */
/* Query effective (directly attached + inherited from ancestor cgroups)
* programs that will be executed for events within a cgroup.
* attach_flags with this flag are returned only for directly attached programs.
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
enum bpf_stack_build_id_status {
/* user space need an empty entry to identify end of a trace */
BPF_STACK_BUILD_ID_EMPTY = 0,
/* with valid build_id and offset */
BPF_STACK_BUILD_ID_VALID = 1,
/* couldn't get build_id, fallback to ip */
BPF_STACK_BUILD_ID_IP = 2,
};
#define BPF_BUILD_ID_SIZE 20
struct bpf_stack_build_id {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
__u64 offset;
__u64 ip;
};
};
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
__u32 key_size; /* size of key in bytes */
__u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */
__u32 map_flags; /* BPF_MAP_CREATE related
* flags defined above.
*/
__u32 inner_map_fd; /* fd pointing to the inner map */
__u32 numa_node; /* numa node (effective only if
* BPF_F_NUMA_NODE is set).
*/
char map_name[BPF_OBJ_NAME_LEN];
__u32 map_ifindex; /* ifindex of netdev to create on */
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_type_id; /* BTF type_id of the key */
__u32 btf_value_type_id; /* BTF type_id of the value */
__u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
* struct stored as the
* map value
*/
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
__u32 map_fd;
__aligned_u64 key;
union {
__aligned_u64 value;
__aligned_u64 next_key;
};
__u64 flags;
};
struct { /* struct used by BPF_MAP_*_BATCH commands */
__aligned_u64 in_batch; /* start batch,
* NULL to start from beginning
*/
__aligned_u64 out_batch; /* output: next start batch */
__aligned_u64 keys;
__aligned_u64 values;
__u32 count; /* input/output:
* input: # of key/value
* elements
* output: # of filled elements
*/
__u32 map_fd;
__u64 elem_flags;
__u64 flags;
} batch;
struct { /* anonymous struct used by BPF_PROG_LOAD command */
__u32 prog_type; /* one of enum bpf_prog_type */
__u32 insn_cnt;
__aligned_u64 insns;
__aligned_u64 license;
__u32 log_level; /* verbosity level of verifier */
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* not used */
__u32 prog_flags;
char prog_name[BPF_OBJ_NAME_LEN];
__u32 prog_ifindex; /* ifindex of netdev to prep for */
/* For some prog types expected attach type must be known at
* load time to verify attach type specific parts of prog
* (context accesses, allowed helpers, etc).
*/
__u32 expected_attach_type;
__u32 prog_btf_fd; /* fd pointing to BTF type data */
__u32 func_info_rec_size; /* userspace bpf_func_info size */
__aligned_u64 func_info; /* func info */
__u32 func_info_cnt; /* number of bpf_func_info records */
__u32 line_info_rec_size; /* userspace bpf_line_info size */
__aligned_u64 line_info; /* line info */
__u32 line_info_cnt; /* number of bpf_line_info records */
__u32 attach_btf_id; /* in-kernel BTF type id to attach to */
__u32 attach_prog_fd; /* 0 to attach to vmlinux */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
__u32 file_flags;
};
struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
__u32 target_fd; /* container object to attach to */
__u32 attach_bpf_fd; /* eBPF program to attach */
__u32 attach_type;
__u32 attach_flags;
__u32 replace_bpf_fd; /* previously attached eBPF
* program to replace if
* BPF_F_REPLACE is used
*/
};
struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
__u32 prog_fd;
__u32 retval;
__u32 data_size_in; /* input: len of data_in */
__u32 data_size_out; /* input/output: len of data_out
* returns ENOSPC if data_out
* is too small.
*/
__aligned_u64 data_in;
__aligned_u64 data_out;
__u32 repeat;
__u32 duration;
__u32 ctx_size_in; /* input: len of ctx_in */
__u32 ctx_size_out; /* input/output: len of ctx_out
* returns ENOSPC if ctx_out
* is too small.
*/
__aligned_u64 ctx_in;
__aligned_u64 ctx_out;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
union {
__u32 start_id;
__u32 prog_id;
__u32 map_id;
__u32 btf_id;
};
__u32 next_id;
__u32 open_flags;
};
struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
__u32 bpf_fd;
__u32 info_len;
__aligned_u64 info;
} info;
struct { /* anonymous struct used by BPF_PROG_QUERY command */
__u32 target_fd; /* container object to query */
__u32 attach_type;
__u32 query_flags;
__u32 attach_flags;
__aligned_u64 prog_ids;
__u32 prog_cnt;
} query;
struct {
__u64 name;
__u32 prog_fd;
} raw_tracepoint;
struct { /* anonymous struct for BPF_BTF_LOAD */
__aligned_u64 btf;
__aligned_u64 btf_log_buf;
__u32 btf_size;
__u32 btf_log_size;
__u32 btf_log_level;
};
struct {
__u32 pid; /* input: pid */
__u32 fd; /* input: fd */
__u32 flags; /* input: flags */
__u32 buf_len; /* input/output: buf len */
__aligned_u64 buf; /* input/output:
* tp_name for tracepoint
* symbol for kprobe
* filename for uprobe
*/
__u32 prog_id; /* output: prod_id */
__u32 fd_type; /* output: BPF_FD_TYPE_* */
__u64 probe_offset; /* output: probe_offset */
__u64 probe_addr; /* output: probe_addr */
} task_fd_query;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
* developers about the multiple available eBPF helper functions. It can be
* parsed and used to produce a manual page. The workflow is the following,
* and requires the rst2man utility:
*
* $ ./scripts/bpf_helpers_doc.py \
* --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
* $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
* $ man /tmp/bpf-helpers.7
*
* Note that in order to produce this external documentation, some RST
* formatting is used in the descriptions to get "bold" and "italics" in
* manual pages. Also note that the few trailing white spaces are
* intentional, removing them would break paragraphs for rst2man.
*
* Start of BPF helper function descriptions:
*
* void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
* Description
* Perform a lookup in *map* for an entry associated to *key*.
* Return
* Map value associated to *key*, or **NULL** if no entry was
* found.
*
* int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
* Description
* Add or update the value of the entry associated to *key* in
* *map* with *value*. *flags* is one of:
*
* **BPF_NOEXIST**
* The entry for *key* must not exist in the map.
* **BPF_EXIST**
* The entry for *key* must already exist in the map.
* **BPF_ANY**
* No condition on the existence of the entry for *key*.
*
* Flag value **BPF_NOEXIST** cannot be used for maps of types
* **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all
* elements always exist), the helper would return an error.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_map_delete_elem(struct bpf_map *map, const void *key)
* Description
* Delete entry with *key* from *map*.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
* kernel space address *unsafe_ptr* and store the data in *dst*.
*
* Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
* instead.
* Return
* 0 on success, or a negative error in case of failure.
*
* u64 bpf_ktime_get_ns(void)
* Description
* Return the time elapsed since system boot, in nanoseconds.
* Return
* Current *ktime*.
*
* int bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
* Description
* This helper is a "printk()-like" facility for debugging. It
* prints a message defined by format *fmt* (of size *fmt_size*)
* to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if
* available. It can take up to three additional **u64**
* arguments (as an eBPF helpers, the total number of arguments is
* limited to five).
*
* Each time the helper is called, it appends a line to the trace.
* Lines are discarded while *\/sys/kernel/debug/tracing/trace* is
* open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this.
* The format of the trace is customizable, and the exact output
* one will get depends on the options set in
* *\/sys/kernel/debug/tracing/trace_options* (see also the
* *README* file under the same directory). However, it usually
* defaults to something like:
*
* ::
*
* telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg>
*
* In the above:
*
* * ``telnet`` is the name of the current task.
* * ``470`` is the PID of the current task.
* * ``001`` is the CPU number on which the task is
* running.
* * In ``.N..``, each character refers to a set of
* options (whether irqs are enabled, scheduling
* options, whether hard/softirqs are running, level of
* preempt_disabled respectively). **N** means that
* **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED**
* are set.
* * ``419421.045894`` is a timestamp.
* * ``0x00000001`` is a fake value used by BPF for the
* instruction pointer register.
* * ``<formatted msg>`` is the message formatted with
* *fmt*.
*
* The conversion specifiers supported by *fmt* are similar, but
* more limited than for printk(). They are **%d**, **%i**,
* **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**,
* **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size
* of field, padding with zeroes, etc.) is available, and the
* helper will return **-EINVAL** (but print nothing) if it
* encounters an unknown specifier.
*
* Also, note that **bpf_trace_printk**\ () is slow, and should
* only be used for debugging purposes. For this reason, a notice
* bloc (spanning several lines) is printed to kernel logs and
* states that the helper should not be used "for production use"
* the first time this helper is used (or more precisely, when
* **trace_printk**\ () buffers are allocated). For passing values
* to user space, perf events should be preferred.
* Return
* The number of bytes written to the buffer, or a negative error
* in case of failure.
*
* u32 bpf_get_prandom_u32(void)
* Description
* Get a pseudo-random number.
*
* From a security point of view, this helper uses its own
* pseudo-random internal state, and cannot be used to infer the
* seed of other random functions in the kernel. However, it is
* essential to note that the generator used by the helper is not
* cryptographically secure.
* Return
* A random 32-bit unsigned value.
*
* u32 bpf_get_smp_processor_id(void)
* Description
* Get the SMP (symmetric multiprocessing) processor id. Note that
* all programs run with preemption disabled, which means that the
* SMP processor id is stable during all the execution of the
* program.
* Return
* The SMP id of the processor running the program.
*
* int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
* Description
* Store *len* bytes from address *from* into the packet
* associated to *skb*, at *offset*. *flags* are a combination of
* **BPF_F_RECOMPUTE_CSUM** (automatically recompute the
* checksum for the packet after storing the bytes) and
* **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
* **->swhash** and *skb*\ **->l4hash** to 0).
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
* Description
* Recompute the layer 3 (e.g. IP) checksum for the packet
* associated to *skb*. Computation is incremental, so the helper
* must know the former value of the header field that was
* modified (*from*), the new value of this field (*to*), and the
* number of bytes (2 or 4) for this field, stored in *size*.
* Alternatively, it is possible to store the difference between
* the previous and the new values of the header field in *to*, by
* setting *from* and *size* to 0. For both methods, *offset*
* indicates the location of the IP checksum within the packet.
*
* This helper works in combination with **bpf_csum_diff**\ (),
* which does not update the checksum in-place, but offers more
* flexibility and can handle sizes larger than 2 or 4 for the
* checksum to update.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
* Description
* Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
* packet associated to *skb*. Computation is incremental, so the
* helper must know the former value of the header field that was
* modified (*from*), the new value of this field (*to*), and the
* number of bytes (2 or 4) for this field, stored on the lowest
* four bits of *flags*. Alternatively, it is possible to store
* the difference between the previous and the new values of the
* header field in *to*, by setting *from* and the four lowest
* bits of *flags* to 0. For both methods, *offset* indicates the
* location of the IP checksum within the packet. In addition to
* the size of the field, *flags* can be added (bitwise OR) actual
* flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
* untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
* for updates resulting in a null checksum the value is set to
* **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
* the checksum is to be computed against a pseudo-header.
*
* This helper works in combination with **bpf_csum_diff**\ (),
* which does not update the checksum in-place, but offers more
* flexibility and can handle sizes larger than 2 or 4 for the
* checksum to update.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
* Description
* This special helper is used to trigger a "tail call", or in
* other words, to jump into another eBPF program. The same stack
* frame is used (but values on stack and in registers for the
* caller are not accessible to the callee). This mechanism allows
* for program chaining, either for raising the maximum number of
* available eBPF instructions, or to execute given programs in
* conditional blocks. For security reasons, there is an upper
* limit to the number of successive tail calls that can be
* performed.
*
* Upon call of this helper, the program attempts to jump into a
* program referenced at index *index* in *prog_array_map*, a
* special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
* *ctx*, a pointer to the context.
*
* If the call succeeds, the kernel immediately runs the first
* instruction of the new program. This is not a function call,
* and it never returns to the previous program. If the call
* fails, then the helper has no effect, and the caller continues
* to run its subsequent instructions. A call can fail if the
* destination program for the jump does not exist (i.e. *index*
* is superior to the number of entries in *prog_array_map*), or
* if the maximum number of tail calls has been reached for this
* chain of programs. This limit is defined in the kernel by the
* macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
* which is currently set to 32.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
* Description
* Clone and redirect the packet associated to *skb* to another
* net device of index *ifindex*. Both ingress and egress
* interfaces can be used for redirection. The **BPF_F_INGRESS**
* value in *flags* is used to make the distinction (ingress path
* is selected if the flag is present, egress path otherwise).
* This is the only flag supported for now.
*
* In comparison with **bpf_redirect**\ () helper,
* **bpf_clone_redirect**\ () has the associated cost of
* duplicating the packet buffer, but this can be executed out of
* the eBPF program. Conversely, **bpf_redirect**\ () is more
* efficient, but it is handled through an action code where the
* redirection happens only after the eBPF program has returned.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* u64 bpf_get_current_pid_tgid(void)
* Return
* A 64-bit integer containing the current tgid and pid, and
* created as such:
* *current_task*\ **->tgid << 32 \|**
* *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
* Return
* A 64-bit integer containing the current GID and UID, and
* created as such: *current_gid* **<< 32 \|** *current_uid*.
*
* int bpf_get_current_comm(void *buf, u32 size_of_buf)
* Description
* Copy the **comm** attribute of the current task into *buf* of
* *size_of_buf*. The **comm** attribute contains the name of
* the executable (excluding the path) for the current task. The
* *size_of_buf* must be strictly positive. On success, the
* helper makes sure that the *buf* is NUL-terminated. On failure,
* it is filled with zeroes.
* Return
* 0 on success, or a negative error in case of failure.
*
* u32 bpf_get_cgroup_classid(struct sk_buff *skb)
* Description
* Retrieve the classid for the current task, i.e. for the net_cls
* cgroup to which *skb* belongs.
*
* This helper can be used on TC egress path, but not on ingress.
*
* The net_cls cgroup provides an interface to tag network packets
* based on a user-provided identifier for all traffic coming from
* the tasks belonging to the related cgroup. See also the related
* kernel documentation, available from the Linux sources in file
* *Documentation/admin-guide/cgroup-v1/net_cls.rst*.
*
* The Linux kernel has two versions for cgroups: there are
* cgroups v1 and cgroups v2. Both are available to users, who can
* use a mixture of them, but note that the net_cls cgroup is for
* cgroup v1 only. This makes it incompatible with BPF programs
* run on cgroups, which is a cgroup-v2-only feature (a socket can
* only hold data for one version of cgroups at a time).
*
* This helper is only available is the kernel was compiled with
* the **CONFIG_CGROUP_NET_CLASSID** configuration option set to
* "**y**" or to "**m**".
* Return
* The classid, or 0 for the default unconfigured classid.
*
* int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
* Description
* Push a *vlan_tci* (VLAN tag control information) of protocol
* *vlan_proto* to the packet associated to *skb*, then update
* the checksum. Note that if *vlan_proto* is different from
* **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
* be **ETH_P_8021Q**.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_skb_vlan_pop(struct sk_buff *skb)
* Description
* Pop a VLAN header from the packet associated to *skb*.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
* Description
* Get tunnel metadata. This helper takes a pointer *key* to an
* empty **struct bpf_tunnel_key** of **size**, that will be
* filled with tunnel metadata for the packet associated to *skb*.
* The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
* indicates that the tunnel is based on IPv6 protocol instead of
* IPv4.
*
* The **struct bpf_tunnel_key** is an object that generalizes the
* principal parameters used by various tunneling protocols into a
* single struct. This way, it can be used to easily make a
* decision based on the contents of the encapsulation header,
* "summarized" in this struct. In particular, it holds the IP
* address of the remote end (IPv4 or IPv6, depending on the case)
* in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
* this struct exposes the *key*\ **->tunnel_id**, which is
* generally mapped to a VNI (Virtual Network Identifier), making
* it programmable together with the **bpf_skb_set_tunnel_key**\
* () helper.
*
* Let's imagine that the following code is part of a program
* attached to the TC ingress interface, on one end of a GRE
* tunnel, and is supposed to filter out all messages coming from
* remote ends with IPv4 address other than 10.0.0.1:
*
* ::
*
* int ret;
* struct bpf_tunnel_key key = {};
*
* ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
* if (ret < 0)
* return TC_ACT_SHOT; // drop packet
*
* if (key.remote_ipv4 != 0x0a000001)
* return TC_ACT_SHOT; // drop packet
*
* return TC_ACT_OK; // accept packet
*
* This interface can also be used with all encapsulation devices
* that can operate in "collect metadata" mode: instead of having
* one network device per specific configuration, the "collect
* metadata" mode only requires a single device where the
* configuration can be extracted from this helper.
*
* This can be used together with various tunnels such as VXLan,
* Geneve, GRE or IP in IP (IPIP).
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
* Description
* Populate tunnel metadata for packet associated to *skb.* The
* tunnel metadata is set to the contents of *key*, of *size*. The
* *flags* can be set to a combination of the following values:
*
* **BPF_F_TUNINFO_IPV6**
* Indicate that the tunnel is based on IPv6 protocol
* instead of IPv4.
* **BPF_F_ZERO_CSUM_TX**
* For IPv4 packets, add a flag to tunnel metadata
* indicating that checksum computation should be skipped
* and checksum set to zeroes.
* **BPF_F_DONT_FRAGMENT**
* Add a flag to tunnel metadata indicating that the
* packet should not be fragmented.
* **BPF_F_SEQ_NUMBER**
* Add a flag to tunnel metadata indicating that a
* sequence number should be added to tunnel header before
* sending the packet. This flag was added for GRE
* encapsulation, but might be used with other protocols
* as well in the future.
*
* Here is a typical usage on the transmit path:
*
* ::
*
* struct bpf_tunnel_key key;
* populate key ...
* bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
* bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
*
* See also the description of the **bpf_skb_get_tunnel_key**\ ()