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
7583 lines (7373 loc) · 276 KB
/
bpf.h
File metadata and controls
7583 lines (7373 loc) · 276 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_MEMSX 0x80 /* load with sign extension */
#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
#define BPF_XADD 0xc0 /* exclusive add - legacy name */
/* 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_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */
#define BPF_CALL 0x80 /* function call */
#define BPF_EXIT 0x90 /* function return */
/* atomic op type fields (stored in immediate) */
#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */
#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */
#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */
#define BPF_LOAD_ACQ 0x100 /* load-acquire */
#define BPF_STORE_REL 0x110 /* store-release */
enum bpf_cond_pseudo_jmp {
BPF_MAY_GOTO = 0,
};
/* 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 */
};
/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for
* byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for
* the trailing flexible array member) instead.
*/
struct bpf_lpm_trie_key {
__u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
__u8 data[0]; /* Arbitrary size */
};
/* Header for bpf_lpm_trie_key structs */
struct bpf_lpm_trie_key_hdr {
__u32 prefixlen;
};
/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */
struct bpf_lpm_trie_key_u8 {
union {
struct bpf_lpm_trie_key_hdr hdr;
__u32 prefixlen;
};
__u8 data[]; /* Arbitrary size */
};
struct bpf_cgroup_storage_key {
__u64 cgroup_inode_id; /* cgroup inode id */
__u32 attach_type; /* program attach type (enum bpf_attach_type) */
};
enum bpf_cgroup_iter_order {
BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
};
union bpf_iter_link_info {
struct {
__u32 map_fd;
} map;
struct {
enum bpf_cgroup_iter_order order;
/* At most one of cgroup_fd and cgroup_id can be non-zero. If
* both are zero, the walk starts from the default cgroup v2
* root. For walking v1 hierarchy, one should always explicitly
* specify cgroup_fd.
*/
__u32 cgroup_fd;
__u64 cgroup_id;
} cgroup;
/* Parameters of task iterators. */
struct {
__u32 tid;
__u32 pid;
__u32 pid_fd;
} task;
};
/* BPF syscall commands, see bpf(2) man-page for more details. */
/**
* DOC: eBPF Syscall Preamble
*
* The operation to be performed by the **bpf**\ () system call is determined
* by the *cmd* argument. Each operation takes an accompanying argument,
* provided via *attr*, which is a pointer to a union of type *bpf_attr* (see
* below). The size argument is the size of the union pointed to by *attr*.
*/
/**
* DOC: eBPF Syscall Commands
*
* BPF_MAP_CREATE
* Description
* Create a map and return a file descriptor that refers to the
* map. The close-on-exec file descriptor flag (see **fcntl**\ (2))
* is automatically enabled for the new file descriptor.
*
* Applying **close**\ (2) to the file descriptor returned by
* **BPF_MAP_CREATE** will delete the map (but see NOTES).
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_MAP_LOOKUP_ELEM
* Description
* Look up an element with a given *key* in the map referred to
* by the file descriptor *map_fd*.
*
* The *flags* argument may be specified as one of the
* following:
*
* **BPF_F_LOCK**
* Look up the value of a spin-locked map without
* returning the lock. This must be specified if the
* elements contain a spinlock.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_MAP_UPDATE_ELEM
* Description
* Create or update an element (key/value pair) in a specified map.
*
* The *flags* argument should be specified as one of the
* following:
*
* **BPF_ANY**
* Create a new element or update an existing element.
* **BPF_NOEXIST**
* Create a new element only if it did not exist.
* **BPF_EXIST**
* Update an existing element.
* **BPF_F_LOCK**
* Update a spin_lock-ed map element.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**,
* **E2BIG**, **EEXIST**, or **ENOENT**.
*
* **E2BIG**
* The number of elements in the map reached the
* *max_entries* limit specified at map creation time.
* **EEXIST**
* If *flags* specifies **BPF_NOEXIST** and the element
* with *key* already exists in the map.
* **ENOENT**
* If *flags* specifies **BPF_EXIST** and the element with
* *key* does not exist in the map.
*
* BPF_MAP_DELETE_ELEM
* Description
* Look up and delete an element by key in a specified map.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_MAP_GET_NEXT_KEY
* Description
* Look up an element by key in a specified map and return the key
* of the next element. Can be used to iterate over all elements
* in the map.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* The following cases can be used to iterate over all elements of
* the map:
*
* * If *key* is not found, the operation returns zero and sets
* the *next_key* pointer to the key of the first element.
* * If *key* is found, the operation returns zero and sets the
* *next_key* pointer to the key of the next element.
* * If *key* is the last element, returns -1 and *errno* is set
* to **ENOENT**.
*
* May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or
* **EINVAL** on error.
*
* BPF_PROG_LOAD
* Description
* Verify and load an eBPF program, returning a new file
* descriptor associated with the program.
*
* Applying **close**\ (2) to the file descriptor returned by
* **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES).
*
* The close-on-exec file descriptor flag (see **fcntl**\ (2)) is
* automatically enabled for the new file descriptor.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_OBJ_PIN
* Description
* Pin an eBPF program or map referred by the specified *bpf_fd*
* to the provided *pathname* on the filesystem.
*
* The *pathname* argument must not contain a dot (".").
*
* On success, *pathname* retains a reference to the eBPF object,
* preventing deallocation of the object when the original
* *bpf_fd* is closed. This allow the eBPF object to live beyond
* **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent
* process.
*
* Applying **unlink**\ (2) or similar calls to the *pathname*
* unpins the object from the filesystem, removing the reference.
* If no other file descriptors or filesystem nodes refer to the
* same object, it will be deallocated (see NOTES).
*
* The filesystem type for the parent directory of *pathname* must
* be **BPF_FS_MAGIC**.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_OBJ_GET
* Description
* Open a file descriptor for the eBPF object pinned to the
* specified *pathname*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_PROG_ATTACH
* Description
* Attach an eBPF program to a *target_fd* at the specified
* *attach_type* hook.
*
* The *attach_type* specifies the eBPF attachment point to
* attach the program to, and must be one of *bpf_attach_type*
* (see below).
*
* The *attach_bpf_fd* must be a valid file descriptor for a
* loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap
* or sock_ops type corresponding to the specified *attach_type*.
*
* The *target_fd* must be a valid file descriptor for a kernel
* object which depends on the attach type of *attach_bpf_fd*:
*
* **BPF_PROG_TYPE_CGROUP_DEVICE**,
* **BPF_PROG_TYPE_CGROUP_SKB**,
* **BPF_PROG_TYPE_CGROUP_SOCK**,
* **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
* **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
* **BPF_PROG_TYPE_CGROUP_SYSCTL**,
* **BPF_PROG_TYPE_SOCK_OPS**
*
* Control Group v2 hierarchy with the eBPF controller
* enabled. Requires the kernel to be compiled with
* **CONFIG_CGROUP_BPF**.
*
* **BPF_PROG_TYPE_FLOW_DISSECTOR**
*
* Network namespace (eg /proc/self/ns/net).
*
* **BPF_PROG_TYPE_LIRC_MODE2**
*
* LIRC device path (eg /dev/lircN). Requires the kernel
* to be compiled with **CONFIG_BPF_LIRC_MODE2**.
*
* **BPF_PROG_TYPE_SK_SKB**,
* **BPF_PROG_TYPE_SK_MSG**
*
* eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**).
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_PROG_DETACH
* Description
* Detach the eBPF program associated with the *target_fd* at the
* hook specified by *attach_type*. The program must have been
* previously attached using **BPF_PROG_ATTACH**.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_PROG_TEST_RUN
* Description
* Run the eBPF program associated with the *prog_fd* a *repeat*
* number of times against a provided program context *ctx_in* and
* data *data_in*, and return the modified program context
* *ctx_out*, *data_out* (for example, packet data), result of the
* execution *retval*, and *duration* of the test run.
*
* The sizes of the buffers provided as input and output
* parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
* be provided in the corresponding variables *ctx_size_in*,
* *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
* of these parameters are not provided (ie set to NULL), the
* corresponding size field must be zero.
*
* Some program types have particular requirements:
*
* **BPF_PROG_TYPE_SK_LOOKUP**
* *data_in* and *data_out* must be NULL.
*
* **BPF_PROG_TYPE_RAW_TRACEPOINT**,
* **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
*
* *ctx_out*, *data_in* and *data_out* must be NULL.
* *repeat* must be zero.
*
* BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* **ENOSPC**
* Either *data_size_out* or *ctx_size_out* is too small.
* **ENOTSUPP**
* This command is not supported by the program type of
* the program referred to by *prog_fd*.
*
* BPF_PROG_GET_NEXT_ID
* Description
* Fetch the next eBPF program currently loaded into the kernel.
*
* Looks for the eBPF program with an id greater than *start_id*
* and updates *next_id* on success. If no other eBPF programs
* remain with ids higher than *start_id*, returns -1 and sets
* *errno* to **ENOENT**.
*
* Return
* Returns zero on success. On error, or when no id remains, -1
* is returned and *errno* is set appropriately.
*
* BPF_MAP_GET_NEXT_ID
* Description
* Fetch the next eBPF map currently loaded into the kernel.
*
* Looks for the eBPF map with an id greater than *start_id*
* and updates *next_id* on success. If no other eBPF maps
* remain with ids higher than *start_id*, returns -1 and sets
* *errno* to **ENOENT**.
*
* Return
* Returns zero on success. On error, or when no id remains, -1
* is returned and *errno* is set appropriately.
*
* BPF_PROG_GET_FD_BY_ID
* Description
* Open a file descriptor for the eBPF program corresponding to
* *prog_id*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_MAP_GET_FD_BY_ID
* Description
* Open a file descriptor for the eBPF map corresponding to
* *map_id*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_OBJ_GET_INFO_BY_FD
* Description
* Obtain information about the eBPF object corresponding to
* *bpf_fd*.
*
* Populates up to *info_len* bytes of *info*, which will be in
* one of the following formats depending on the eBPF object type
* of *bpf_fd*:
*
* * **struct bpf_prog_info**
* * **struct bpf_map_info**
* * **struct bpf_btf_info**
* * **struct bpf_link_info**
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_PROG_QUERY
* Description
* Obtain information about eBPF programs associated with the
* specified *attach_type* hook.
*
* The *target_fd* must be a valid file descriptor for a kernel
* object which depends on the attach type of *attach_bpf_fd*:
*
* **BPF_PROG_TYPE_CGROUP_DEVICE**,
* **BPF_PROG_TYPE_CGROUP_SKB**,
* **BPF_PROG_TYPE_CGROUP_SOCK**,
* **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
* **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
* **BPF_PROG_TYPE_CGROUP_SYSCTL**,
* **BPF_PROG_TYPE_SOCK_OPS**
*
* Control Group v2 hierarchy with the eBPF controller
* enabled. Requires the kernel to be compiled with
* **CONFIG_CGROUP_BPF**.
*
* **BPF_PROG_TYPE_FLOW_DISSECTOR**
*
* Network namespace (eg /proc/self/ns/net).
*
* **BPF_PROG_TYPE_LIRC_MODE2**
*
* LIRC device path (eg /dev/lircN). Requires the kernel
* to be compiled with **CONFIG_BPF_LIRC_MODE2**.
*
* **BPF_PROG_QUERY** always fetches the number of programs
* attached and the *attach_flags* which were used to attach those
* programs. Additionally, if *prog_ids* is nonzero and the number
* of attached programs is less than *prog_cnt*, populates
* *prog_ids* with the eBPF program ids of the programs attached
* at *target_fd*.
*
* The following flags may alter the result:
*
* **BPF_F_QUERY_EFFECTIVE**
* Only return information regarding programs which are
* currently effective at the specified *target_fd*.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_RAW_TRACEPOINT_OPEN
* Description
* Attach an eBPF program to a tracepoint *name* to access kernel
* internal arguments of the tracepoint in their raw form.
*
* The *prog_fd* must be a valid file descriptor associated with
* a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**.
*
* No ABI guarantees are made about the content of tracepoint
* arguments exposed to the corresponding eBPF program.
*
* Applying **close**\ (2) to the file descriptor returned by
* **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES).
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_BTF_LOAD
* Description
* Verify and load BPF Type Format (BTF) metadata into the kernel,
* returning a new file descriptor associated with the metadata.
* BTF is described in more detail at
* https://www.kernel.org/doc/html/latest/bpf/btf.html.
*
* The *btf* parameter must point to valid memory providing
* *btf_size* bytes of BTF binary metadata.
*
* The returned file descriptor can be passed to other **bpf**\ ()
* subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to
* associate the BTF with those objects.
*
* Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional
* parameters to specify a *btf_log_buf*, *btf_log_size* and
* *btf_log_level* which allow the kernel to return freeform log
* output regarding the BTF verification process.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_BTF_GET_FD_BY_ID
* Description
* Open a file descriptor for the BPF Type Format (BTF)
* corresponding to *btf_id*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_TASK_FD_QUERY
* Description
* Obtain information about eBPF programs associated with the
* target process identified by *pid* and *fd*.
*
* If the *pid* and *fd* are associated with a tracepoint, kprobe
* or uprobe perf event, then the *prog_id* and *fd_type* will
* be populated with the eBPF program id and file descriptor type
* of type **bpf_task_fd_type**. If associated with a kprobe or
* uprobe, the *probe_offset* and *probe_addr* will also be
* populated. Optionally, if *buf* is provided, then up to
* *buf_len* bytes of *buf* will be populated with the name of
* the tracepoint, kprobe or uprobe.
*
* The resulting *prog_id* may be introspected in deeper detail
* using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_MAP_LOOKUP_AND_DELETE_ELEM
* Description
* Look up an element with the given *key* in the map referred to
* by the file descriptor *fd*, and if found, delete the element.
*
* For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
* types, the *flags* argument needs to be set to 0, but for other
* map types, it may be specified as:
*
* **BPF_F_LOCK**
* Look up and delete the value of a spin-locked map
* without returning the lock. This must be specified if
* the elements contain a spinlock.
*
* The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
* implement this command as a "pop" operation, deleting the top
* element rather than one corresponding to *key*.
* The *key* and *key_len* parameters should be zeroed when
* issuing this operation for these map types.
*
* This command is only valid for the following map types:
* * **BPF_MAP_TYPE_QUEUE**
* * **BPF_MAP_TYPE_STACK**
* * **BPF_MAP_TYPE_HASH**
* * **BPF_MAP_TYPE_PERCPU_HASH**
* * **BPF_MAP_TYPE_LRU_HASH**
* * **BPF_MAP_TYPE_LRU_PERCPU_HASH**
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_MAP_FREEZE
* Description
* Freeze the permissions of the specified map.
*
* Write permissions may be frozen by passing zero *flags*.
* Upon success, no future syscall invocations may alter the
* map state of *map_fd*. Write operations from eBPF programs
* are still possible for a frozen map.
*
* Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_BTF_GET_NEXT_ID
* Description
* Fetch the next BPF Type Format (BTF) object currently loaded
* into the kernel.
*
* Looks for the BTF object with an id greater than *start_id*
* and updates *next_id* on success. If no other BTF objects
* remain with ids higher than *start_id*, returns -1 and sets
* *errno* to **ENOENT**.
*
* Return
* Returns zero on success. On error, or when no id remains, -1
* is returned and *errno* is set appropriately.
*
* BPF_MAP_LOOKUP_BATCH
* Description
* Iterate and fetch multiple elements in a map.
*
* Two opaque values are used to manage batch operations,
* *in_batch* and *out_batch*. Initially, *in_batch* must be set
* to NULL to begin the batched operation. After each subsequent
* **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
* *out_batch* as the *in_batch* for the next operation to
* continue iteration from the current point. Both *in_batch* and
* *out_batch* must point to memory large enough to hold a key,
* except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH,
* LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters
* must be at least 4 bytes wide regardless of key size.
*
* The *keys* and *values* are output parameters which must point
* to memory large enough to hold *count* items based on the key
* and value size of the map *map_fd*. The *keys* buffer must be
* of *key_size* * *count*. The *values* buffer must be of
* *value_size* * *count*.
*
* The *elem_flags* argument may be specified as one of the
* following:
*
* **BPF_F_LOCK**
* Look up the value of a spin-locked map without
* returning the lock. This must be specified if the
* elements contain a spinlock.
*
* On success, *count* elements from the map are copied into the
* user buffer, with the keys copied into *keys* and the values
* copied into the corresponding indices in *values*.
*
* If an error is returned and *errno* is not **EFAULT**, *count*
* is set to the number of successfully processed elements.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* May set *errno* to **ENOSPC** to indicate that *keys* or
* *values* is too small to dump an entire bucket during
* iteration of a hash-based map type.
*
* BPF_MAP_LOOKUP_AND_DELETE_BATCH
* Description
* Iterate and delete all elements in a map.
*
* This operation has the same behavior as
* **BPF_MAP_LOOKUP_BATCH** with two exceptions:
*
* * Every element that is successfully returned is also deleted
* from the map. This is at least *count* elements. Note that
* *count* is both an input and an output parameter.
* * Upon returning with *errno* set to **EFAULT**, up to
* *count* elements may be deleted without returning the keys
* and values of the deleted elements.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_MAP_UPDATE_BATCH
* Description
* Update multiple elements in a map by *key*.
*
* The *keys* and *values* are input parameters which must point
* to memory large enough to hold *count* items based on the key
* and value size of the map *map_fd*. The *keys* buffer must be
* of *key_size* * *count*. The *values* buffer must be of
* *value_size* * *count*.
*
* Each element specified in *keys* is sequentially updated to the
* value in the corresponding index in *values*. The *in_batch*
* and *out_batch* parameters are ignored and should be zeroed.
*
* The *elem_flags* argument should be specified as one of the
* following:
*
* **BPF_ANY**
* Create new elements or update a existing elements.
* **BPF_NOEXIST**
* Create new elements only if they do not exist.
* **BPF_EXIST**
* Update existing elements.
* **BPF_F_LOCK**
* Update spin_lock-ed map elements. This must be
* specified if the map value contains a spinlock.
*
* On success, *count* elements from the map are updated.
*
* If an error is returned and *errno* is not **EFAULT**, *count*
* is set to the number of successfully processed elements.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or
* **E2BIG**. **E2BIG** indicates that the number of elements in
* the map reached the *max_entries* limit specified at map
* creation time.
*
* May set *errno* to one of the following error codes under
* specific circumstances:
*
* **EEXIST**
* If *flags* specifies **BPF_NOEXIST** and the element
* with *key* already exists in the map.
* **ENOENT**
* If *flags* specifies **BPF_EXIST** and the element with
* *key* does not exist in the map.
*
* BPF_MAP_DELETE_BATCH
* Description
* Delete multiple elements in a map by *key*.
*
* The *keys* parameter is an input parameter which must point
* to memory large enough to hold *count* items based on the key
* size of the map *map_fd*, that is, *key_size* * *count*.
*
* Each element specified in *keys* is sequentially deleted. The
* *in_batch*, *out_batch*, and *values* parameters are ignored
* and should be zeroed.
*
* The *elem_flags* argument may be specified as one of the
* following:
*
* **BPF_F_LOCK**
* Look up the value of a spin-locked map without
* returning the lock. This must be specified if the
* elements contain a spinlock.
*
* On success, *count* elements from the map are updated.
*
* If an error is returned and *errno* is not **EFAULT**, *count*
* is set to the number of successfully processed elements. If
* *errno* is **EFAULT**, up to *count* elements may be been
* deleted.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_LINK_CREATE
* Description
* Attach an eBPF program to a *target_fd* at the specified
* *attach_type* hook and return a file descriptor handle for
* managing the link.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_LINK_UPDATE
* Description
* Update the eBPF program in the specified *link_fd* to
* *new_prog_fd*.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_LINK_GET_FD_BY_ID
* Description
* Open a file descriptor for the eBPF Link corresponding to
* *link_id*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_LINK_GET_NEXT_ID
* Description
* Fetch the next eBPF link currently loaded into the kernel.
*
* Looks for the eBPF link with an id greater than *start_id*
* and updates *next_id* on success. If no other eBPF links
* remain with ids higher than *start_id*, returns -1 and sets
* *errno* to **ENOENT**.
*
* Return
* Returns zero on success. On error, or when no id remains, -1
* is returned and *errno* is set appropriately.
*
* BPF_ENABLE_STATS
* Description
* Enable eBPF runtime statistics gathering.
*
* Runtime statistics gathering for the eBPF runtime is disabled
* by default to minimize the corresponding performance overhead.
* This command enables statistics globally.
*
* Multiple programs may independently enable statistics.
* After gathering the desired statistics, eBPF runtime statistics
* may be disabled again by calling **close**\ (2) for the file
* descriptor returned by this function. Statistics will only be
* disabled system-wide when all outstanding file descriptors
* returned by prior calls for this subcommand are closed.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_ITER_CREATE
* Description
* Create an iterator on top of the specified *link_fd* (as
* previously created using **BPF_LINK_CREATE**) and return a
* file descriptor that can be used to trigger the iteration.
*
* If the resulting file descriptor is pinned to the filesystem
* using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls
* for that path will trigger the iterator to read kernel state
* using the eBPF program attached to *link_fd*.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* BPF_LINK_DETACH
* Description
* Forcefully detach the specified *link_fd* from its
* corresponding attachment point.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_PROG_BIND_MAP
* Description
* Bind a map to the lifetime of an eBPF program.
*
* The map identified by *map_fd* is bound to the program
* identified by *prog_fd* and only released when *prog_fd* is
* released. This may be used in cases where metadata should be
* associated with a program which otherwise does not contain any
* references to the map (for example, embedded in the eBPF
* program instructions).
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_TOKEN_CREATE
* Description
* Create BPF token with embedded information about what
* BPF-related functionality it allows:
* - a set of allowed bpf() syscall commands;
* - a set of allowed BPF map types to be created with
* BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
* - a set of allowed BPF program types and BPF program attach
* types to be loaded with BPF_PROG_LOAD command, if
* BPF_PROG_LOAD itself is allowed.
*
* BPF token is created (derived) from an instance of BPF FS,
* assuming it has necessary delegation mount options specified.
* This BPF token can be passed as an extra parameter to various
* bpf() syscall commands to grant BPF subsystem functionality to
* unprivileged processes.
*
* When created, BPF token is "associated" with the owning
* user namespace of BPF FS instance (super block) that it was
* derived from, and subsequent BPF operations performed with
* BPF token would be performing capabilities checks (i.e.,
* CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
* that user namespace. Without BPF token, such capabilities
* have to be granted in init user namespace, making bpf()
* syscall incompatible with user namespace, for the most part.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* NOTES
* eBPF objects (maps and programs) can be shared between processes.
*
* * After **fork**\ (2), the child inherits file descriptors
* referring to the same eBPF objects.
* * File descriptors referring to eBPF objects can be transferred over
* **unix**\ (7) domain sockets.
* * File descriptors referring to eBPF objects can be duplicated in the
* usual way, using **dup**\ (2) and similar calls.
* * File descriptors referring to eBPF objects can be pinned to the
* filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2).
*
* An eBPF object is deallocated only after all file descriptors referring
* to the object have been closed and no references remain pinned to the
* filesystem or attached (for example, bound to a program or device).
*/
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_RUN = 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,
BPF_LINK_CREATE,
BPF_LINK_UPDATE,
BPF_LINK_GET_FD_BY_ID,
BPF_LINK_GET_NEXT_ID,
BPF_ENABLE_STATS,
BPF_ITER_CREATE,
BPF_LINK_DETACH,
BPF_PROG_BIND_MAP,
BPF_TOKEN_CREATE,
__MAX_BPF_CMD,
};
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_DEPRECATED,
/* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
* to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
* both cgroup-attached and other progs and supports all functionality
* provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
* BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
*/
BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
* attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
* local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
* functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE