aboutsummaryrefslogtreecommitdiff
path: root/tools/lib/bpf/bpf.c
blob: 2f3495d80d69bcefa0afed405a4049f0e3b2f8c4 (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
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)

/*
 * common eBPF ELF operations.
 *
 * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
 * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
 * Copyright (C) 2015 Huawei Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License (not later!)
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not,  see <http://www.gnu.org/licenses>
 */

#include <stdlib.h>
#include <string.h>
#include <memory.h>
#include <unistd.h>
#include <asm/unistd.h>
#include <errno.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/kernel.h>
#include <limits.h>
#include <sys/resource.h>
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_internal.h"

/*
 * When building perf, unistd.h is overridden. __NR_bpf is
 * required to be defined explicitly.
 */
#ifndef __NR_bpf
# if defined(__i386__)
#  define __NR_bpf 357
# elif defined(__x86_64__)
#  define __NR_bpf 321
# elif defined(__aarch64__)
#  define __NR_bpf 280
# elif defined(__sparc__)
#  define __NR_bpf 349
# elif defined(__s390__)
#  define __NR_bpf 351
# elif defined(__arc__)
#  define __NR_bpf 280
# elif defined(__mips__) && defined(_ABIO32)
#  define __NR_bpf 4355
# elif defined(__mips__) && defined(_ABIN32)
#  define __NR_bpf 6319
# elif defined(__mips__) && defined(_ABI64)
#  define __NR_bpf 5315
# else
#  error __NR_bpf not defined. libbpf does not support your arch.
# endif
#endif

static inline __u64 ptr_to_u64(const void *ptr)
{
	return (__u64) (unsigned long) ptr;
}

static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
			  unsigned int size)
{
	return syscall(__NR_bpf, cmd, attr, size);
}

static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
			     unsigned int size)
{
	int fd;

	fd = sys_bpf(cmd, attr, size);
	return ensure_good_fd(fd);
}

#define PROG_LOAD_ATTEMPTS 5

static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
{
	int fd;

	do {
		fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size);
	} while (fd < 0 && errno == EAGAIN && --attempts > 0);

	return fd;
}

/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to
 * memcg-based memory accounting for BPF maps and progs. This was done in [0].
 * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in
 * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF.
 *
 *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
 *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
 */
int probe_memcg_account(void)
{
	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
	struct bpf_insn insns[] = {
		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
		BPF_EXIT_INSN(),
	};
	size_t insn_cnt = ARRAY_SIZE(insns);
	union bpf_attr attr;
	int prog_fd;

	/* attempt loading freplace trying to use custom BTF */
	memset(&attr, 0, prog_load_attr_sz);
	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
	attr.insns = ptr_to_u64(insns);
	attr.insn_cnt = insn_cnt;
	attr.license = ptr_to_u64("GPL");

	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
	if (prog_fd >= 0) {
		close(prog_fd);
		return 1;
	}
	return 0;
}

static bool memlock_bumped;
static rlim_t memlock_rlim = RLIM_INFINITY;

int libbpf_set_memlock_rlim(size_t memlock_bytes)
{
	if (memlock_bumped)
		return libbpf_err(-EBUSY);

	memlock_rlim = memlock_bytes;
	return 0;
}

int bump_rlimit_memlock(void)
{
	struct rlimit rlim;

	/* this the default in libbpf 1.0, but for now user has to opt-in explicitly */
	if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK))
		return 0;

	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
		return 0;

	memlock_bumped = true;

	/* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
	if (memlock_rlim == 0)
		return 0;

	rlim.rlim_cur = rlim.rlim_max = memlock_rlim;
	if (setrlimit(RLIMIT_MEMLOCK, &rlim))
		return -errno;

	return 0;
}

int bpf_map_create(enum bpf_map_type map_type,
		   const char *map_name,
		   __u32 key_size,
		   __u32 value_size,
		   __u32 max_entries,
		   const struct bpf_map_create_opts *opts)
{
	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
	union bpf_attr attr;
	int fd;

	bump_rlimit_memlock();

	memset(&attr, 0, attr_sz);

	if (!OPTS_VALID(opts, bpf_map_create_opts))
		return libbpf_err(-EINVAL);

	attr.map_type = map_type;
	if (map_name)
		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
	attr.key_size = key_size;
	attr.value_size = value_size;
	attr.max_entries = max_entries;

	attr.btf_fd = OPTS_GET(opts, btf_fd, 0);
	attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0);
	attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0);
	attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0);

	attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0);
	attr.map_flags = OPTS_GET(opts, map_flags, 0);
	attr.map_extra = OPTS_GET(opts, map_extra, 0);
	attr.numa_node = OPTS_GET(opts, numa_node, 0);
	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);

	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
	return libbpf_err_errno(fd);
}

static void *
alloc_zero_tailing_info(const void *orecord, __u32 cnt,
			__u32 actual_rec_size, __u32 expected_rec_size)
{
	__u64 info_len = (__u64)actual_rec_size * cnt;
	void *info, *nrecord;
	int i;

	info = malloc(info_len);
	if (!info)
		return NULL;

	/* zero out bytes kernel does not understand */
	nrecord = info;
	for (i = 0; i < cnt; i++) {
		memcpy(nrecord, orecord, expected_rec_size);
		memset(nrecord + expected_rec_size, 0,
		       actual_rec_size - expected_rec_size);
		orecord += actual_rec_size;
		nrecord += actual_rec_size;
	}

	return info;
}

int bpf_prog_load(enum bpf_prog_type prog_type,
		  const char *prog_name, const char *license,
		  const struct bpf_insn *insns, size_t insn_cnt,
		  const struct bpf_prog_load_opts *opts)
{
	void *finfo = NULL, *linfo = NULL;
	const char *func_info, *line_info;
	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
	__u32 func_info_rec_size, line_info_rec_size;
	int fd, attempts;
	union bpf_attr attr;
	char *log_buf;

	bump_rlimit_memlock();

	if (!OPTS_VALID(opts, bpf_prog_load_opts))
		return libbpf_err(-EINVAL);

	attempts = OPTS_GET(opts, attempts, 0);
	if (attempts < 0)
		return libbpf_err(-EINVAL);
	if (attempts == 0)
		attempts = PROG_LOAD_ATTEMPTS;

	memset(&attr, 0, sizeof(attr));

	attr.prog_type = prog_type;
	attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0);

	attr.prog_btf_fd = OPTS_GET(opts, prog_btf_fd, 0);
	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
	attr.kern_version = OPTS_GET(opts, kern_version, 0);

	if (prog_name)
		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
	attr.license = ptr_to_u64(license);

	if (insn_cnt > UINT_MAX)
		return libbpf_err(-E2BIG);

	attr.insns = ptr_to_u64(insns);
	attr.insn_cnt = (__u32)insn_cnt;

	attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
	attach_btf_obj_fd = OPTS_GET(opts, attach_btf_obj_fd, 0);

	if (attach_prog_fd && attach_btf_obj_fd)
		return libbpf_err(-EINVAL);

	attr.attach_btf_id = OPTS_GET(opts, attach_btf_id, 0);
	if (attach_prog_fd)
		attr.attach_prog_fd = attach_prog_fd;
	else
		attr.attach_btf_obj_fd = attach_btf_obj_fd;

	log_buf = OPTS_GET(opts, log_buf, NULL);
	log_size = OPTS_GET(opts, log_size, 0);
	log_level = OPTS_GET(opts, log_level, 0);

	if (!!log_buf != !!log_size)
		return libbpf_err(-EINVAL);
	if (log_level > (4 | 2 | 1))
		return libbpf_err(-EINVAL);
	if (log_level && !log_buf)
		return libbpf_err(-EINVAL);

	func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0);
	func_info = OPTS_GET(opts, func_info, NULL);
	attr.func_info_rec_size = func_info_rec_size;
	attr.func_info = ptr_to_u64(func_info);
	attr.func_info_cnt = OPTS_GET(opts, func_info_cnt, 0);

	line_info_rec_size = OPTS_GET(opts, line_info_rec_size, 0);
	line_info = OPTS_GET(opts, line_info, NULL);
	attr.line_info_rec_size = line_info_rec_size;
	attr.line_info = ptr_to_u64(line_info);
	attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0);

	attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL));

	if (log_level) {
		attr.log_buf = ptr_to_u64(log_buf);
		attr.log_size = log_size;
		attr.log_level = log_level;
	}

	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
	if (fd >= 0)
		return fd;

	/* After bpf_prog_load, the kernel may modify certain attributes
	 * to give user space a hint how to deal with loading failure.
	 * Check to see whether we can make some changes and load again.
	 */
	while (errno == E2BIG && (!finfo || !linfo)) {
		if (!finfo && attr.func_info_cnt &&
		    attr.func_info_rec_size < func_info_rec_size) {
			/* try with corrected func info records */
			finfo = alloc_zero_tailing_info(func_info,
							attr.func_info_cnt,
							func_info_rec_size,
							attr.func_info_rec_size);
			if (!finfo) {
				errno = E2BIG;
				goto done;
			}

			attr.func_info = ptr_to_u64(finfo);
			attr.func_info_rec_size = func_info_rec_size;
		} else if (!linfo && attr.line_info_cnt &&
			   attr.line_info_rec_size < line_info_rec_size) {
			linfo = alloc_zero_tailing_info(line_info,
							attr.line_info_cnt,
							line_info_rec_size,
							attr.line_info_rec_size);
			if (!linfo) {
				errno = E2BIG;
				goto done;
			}

			attr.line_info = ptr_to_u64(linfo);
			attr.line_info_rec_size = line_info_rec_size;
		} else {
			break;
		}

		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
		if (fd >= 0)
			goto done;
	}

	if (log_level == 0 && log_buf) {
		/* log_level == 0 with non-NULL log_buf requires retrying on error
		 * with log_level == 1 and log_buf/log_buf_size set, to get details of
		 * failure
		 */
		attr.log_buf = ptr_to_u64(log_buf);
		attr.log_size = log_size;
		attr.log_level = 1;

		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
	}
done:
	/* free() doesn't affect errno, so we don't need to restore it */
	free(finfo);
	free(linfo);
	return libbpf_err_errno(fd);
}

int bpf_map_update_elem(int fd, const void *key, const void *value,
			__u64 flags)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);
	attr.flags = flags;

	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_lookup_elem(int fd, const void *key, void *value)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);

	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);
	attr.flags = flags;

	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);

	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.value = ptr_to_u64(value);
	attr.flags = flags;

	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_delete_elem(int fd, const void *key)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);

	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.flags = flags;

	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_get_next_key(int fd, const void *key, void *next_key)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;
	attr.key = ptr_to_u64(key);
	attr.next_key = ptr_to_u64(next_key);

	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_map_freeze(int fd)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.map_fd = fd;

	ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
				void *out_batch, void *keys, void *values,
				__u32 *count,
				const struct bpf_map_batch_opts *opts)
{
	union bpf_attr attr;
	int ret;

	if (!OPTS_VALID(opts, bpf_map_batch_opts))
		return libbpf_err(-EINVAL);

	memset(&attr, 0, sizeof(attr));
	attr.batch.map_fd = fd;
	attr.batch.in_batch = ptr_to_u64(in_batch);
	attr.batch.out_batch = ptr_to_u64(out_batch);
	attr.batch.keys = ptr_to_u64(keys);
	attr.batch.values = ptr_to_u64(values);
	attr.batch.count = *count;
	attr.batch.elem_flags  = OPTS_GET(opts, elem_flags, 0);
	attr.batch.flags = OPTS_GET(opts, flags, 0);

	ret = sys_bpf(cmd, &attr, sizeof(attr));
	*count = attr.batch.count;

	return libbpf_err_errno(ret);
}

int bpf_map_delete_batch(int fd, const void *keys, __u32 *count,
			 const struct bpf_map_batch_opts *opts)
{
	return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
				    NULL, (void *)keys, NULL, count, opts);
}

int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
			 void *values, __u32 *count,
			 const struct bpf_map_batch_opts *opts)
{
	return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch,
				    out_batch, keys, values, count, opts);
}

int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
				    void *keys, void *values, __u32 *count,
				    const struct bpf_map_batch_opts *opts)
{
	return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH,
				    fd, in_batch, out_batch, keys, values,
				    count, opts);
}

int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count,
			 const struct bpf_map_batch_opts *opts)
{
	return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
				    (void *)keys, (void *)values, count, opts);
}

int bpf_obj_pin(int fd, const char *pathname)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.pathname = ptr_to_u64((void *)pathname);
	attr.bpf_fd = fd;

	ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_obj_get(const char *pathname)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.pathname = ptr_to_u64((void *)pathname);

	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
		    unsigned int flags)
{
	DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts,
		.flags = flags,
	);

	return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
}

int bpf_prog_attach_opts(int prog_fd, int target_fd,
			  enum bpf_attach_type type,
			  const struct bpf_prog_attach_opts *opts)
{
	union bpf_attr attr;
	int ret;

	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
		return libbpf_err(-EINVAL);

	memset(&attr, 0, sizeof(attr));
	attr.target_fd	   = target_fd;
	attr.attach_bpf_fd = prog_fd;
	attr.attach_type   = type;
	attr.attach_flags  = OPTS_GET(opts, flags, 0);
	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);

	ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

__attribute__((alias("bpf_prog_attach_opts")))
int bpf_prog_attach_xattr(int prog_fd, int target_fd,
			  enum bpf_attach_type type,
			  const struct bpf_prog_attach_opts *opts);

int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.target_fd	 = target_fd;
	attr.attach_type = type;

	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.target_fd	 = target_fd;
	attr.attach_bpf_fd = prog_fd;
	attr.attach_type = type;

	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_link_create(int prog_fd, int target_fd,
		    enum bpf_attach_type attach_type,
		    const struct bpf_link_create_opts *opts)
{
	__u32 target_btf_id, iter_info_len;
	union bpf_attr attr;
	int fd, err;

	if (!OPTS_VALID(opts, bpf_link_create_opts))
		return libbpf_err(-EINVAL);

	iter_info_len = OPTS_GET(opts, iter_info_len, 0);
	target_btf_id = OPTS_GET(opts, target_btf_id, 0);

	/* validate we don't have unexpected combinations of non-zero fields */
	if (iter_info_len || target_btf_id) {
		if (iter_info_len && target_btf_id)
			return libbpf_err(-EINVAL);
		if (!OPTS_ZEROED(opts, target_btf_id))
			return libbpf_err(-EINVAL);
	}

	memset(&attr, 0, sizeof(attr));
	attr.link_create.prog_fd = prog_fd;
	attr.link_create.target_fd = target_fd;
	attr.link_create.attach_type = attach_type;
	attr.link_create.flags = OPTS_GET(opts, flags, 0);

	if (target_btf_id) {
		attr.link_create.target_btf_id = target_btf_id;
		goto proceed;
	}

	switch (attach_type) {
	case BPF_TRACE_ITER:
		attr.link_create.iter_info = ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
		attr.link_create.iter_info_len = iter_info_len;
		break;
	case BPF_PERF_EVENT:
		attr.link_create.perf_event.bpf_cookie = OPTS_GET(opts, perf_event.bpf_cookie, 0);
		if (!OPTS_ZEROED(opts, perf_event))
			return libbpf_err(-EINVAL);
		break;
	case BPF_TRACE_KPROBE_MULTI:
		attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0);
		attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0);
		attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0));
		attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0));
		attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0));
		if (!OPTS_ZEROED(opts, kprobe_multi))
			return libbpf_err(-EINVAL);
		break;
	case BPF_TRACE_FENTRY:
	case BPF_TRACE_FEXIT:
	case BPF_MODIFY_RETURN:
	case BPF_LSM_MAC:
		attr.link_create.tracing.cookie = OPTS_GET(opts, tracing.cookie, 0);
		if (!OPTS_ZEROED(opts, tracing))
			return libbpf_err(-EINVAL);
		break;
	default:
		if (!OPTS_ZEROED(opts, flags))
			return libbpf_err(-EINVAL);
		break;
	}
proceed:
	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
	if (fd >= 0)
		return fd;
	/* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry
	 * and other similar programs
	 */
	err = -errno;
	if (err != -EINVAL)
		return libbpf_err(err);

	/* if user used features not supported by
	 * BPF_RAW_TRACEPOINT_OPEN command, then just give up immediately
	 */
	if (attr.link_create.target_fd || attr.link_create.target_btf_id)
		return libbpf_err(err);
	if (!OPTS_ZEROED(opts, sz))
		return libbpf_err(err);

	/* otherwise, for few select kinds of programs that can be
	 * attached using BPF_RAW_TRACEPOINT_OPEN command, try that as
	 * a fallback for older kernels
	 */
	switch (attach_type) {
	case BPF_TRACE_RAW_TP:
	case BPF_LSM_MAC:
	case BPF_TRACE_FENTRY:
	case BPF_TRACE_FEXIT:
	case BPF_MODIFY_RETURN:
		return bpf_raw_tracepoint_open(NULL, prog_fd);
	default:
		return libbpf_err(err);
	}
}

int bpf_link_detach(int link_fd)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.link_detach.link_fd = link_fd;

	ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_link_update(int link_fd, int new_prog_fd,
		    const struct bpf_link_update_opts *opts)
{
	union bpf_attr attr;
	int ret;

	if (!OPTS_VALID(opts, bpf_link_update_opts))
		return libbpf_err(-EINVAL);

	memset(&attr, 0, sizeof(attr));
	attr.link_update.link_fd = link_fd;
	attr.link_update.new_prog_fd = new_prog_fd;
	attr.link_update.flags = OPTS_GET(opts, flags, 0);
	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);

	ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}

int bpf_iter_create(int link_fd)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.iter_create.link_fd = link_fd;

	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
{
	union bpf_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	attr.query.target_fd	= target_fd;
	attr.query.attach_type	= type;
	attr.query.query_flags	= query_flags;
	attr.query.prog_cnt	= *prog_cnt;
	attr.query.prog_ids	= ptr_to_u64(prog_ids);

	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));

	if (attach_flags)
		*attach_flags = attr.query.attach_flags;
	*prog_cnt = attr.query.prog_cnt;

	return libbpf_err_errno(ret);
}

int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
{
	union bpf_attr attr;
	int ret;

	if (!OPTS_VALID(opts, bpf_test_run_opts))
		return libbpf_err(-EINVAL);

	memset(&attr, 0, sizeof(attr));
	attr.test.prog_fd = prog_fd;
	attr.test.batch_size = OPTS_GET(opts, batch_size, 0);
	attr.test.cpu = OPTS_GET(opts, cpu, 0);
	attr.test.flags = OPTS_GET(opts, flags, 0);
	attr.test.repeat = OPTS_GET(opts, repeat, 0);
	attr.test.duration = OPTS_GET(opts, duration, 0);
	attr.test.ctx_size_in = OPTS_GET(opts, ctx_size_in, 0);
	attr.test.ctx_size_out = OPTS_GET(opts, ctx_size_out, 0);
	attr.test.data_size_in = OPTS_GET(opts, data_size_in, 0);
	attr.test.data_size_out = OPTS_GET(opts, data_size_out, 0);
	attr.test.ctx_in = ptr_to_u64(OPTS_GET(opts, ctx_in, NULL));
	attr.test.ctx_out = ptr_to_u64(OPTS_GET(opts, ctx_out, NULL));
	attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL));
	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));

	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));

	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
	OPTS_SET(opts, duration, attr.test.duration);
	OPTS_SET(opts, retval, attr.test.retval);

	return libbpf_err_errno(ret);
}

static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
{
	union bpf_attr attr;
	int err;

	memset(&attr, 0, sizeof(attr));
	attr.start_id = start_id;

	err = sys_bpf(cmd, &attr, sizeof(attr));
	if (!err)
		*next_id = attr.next_id;

	return libbpf_err_errno(err);
}

int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
{
	return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID);
}

int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
{
	return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID);
}

int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id)
{
	return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID);
}

int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
{
	return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID);
}

int bpf_prog_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.prog_id = id;

	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_map_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.map_id = id;

	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_btf_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.btf_id = id;

	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_link_get_fd_by_id(__u32 id)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.link_id = id;

	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
{
	union bpf_attr attr;
	int err;

	memset(&attr, 0, sizeof(attr));
	attr.info.bpf_fd = bpf_fd;
	attr.info.info_len = *info_len;
	attr.info.info = ptr_to_u64(info);

	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));

	if (!err)
		*info_len = attr.info.info_len;

	return libbpf_err_errno(err);
}

int bpf_raw_tracepoint_open(const char *name, int prog_fd)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.raw_tracepoint.name = ptr_to_u64(name);
	attr.raw_tracepoint.prog_fd = prog_fd;

	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts)
{
	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level);
	union bpf_attr attr;
	char *log_buf;
	size_t log_size;
	__u32 log_level;
	int fd;

	bump_rlimit_memlock();

	memset(&attr, 0, attr_sz);

	if (!OPTS_VALID(opts, bpf_btf_load_opts))
		return libbpf_err(-EINVAL);

	log_buf = OPTS_GET(opts, log_buf, NULL);
	log_size = OPTS_GET(opts, log_size, 0);
	log_level = OPTS_GET(opts, log_level, 0);

	if (log_size > UINT_MAX)
		return libbpf_err(-EINVAL);
	if (log_size && !log_buf)
		return libbpf_err(-EINVAL);

	attr.btf = ptr_to_u64(btf_data);
	attr.btf_size = btf_size;
	/* log_level == 0 and log_buf != NULL means "try loading without
	 * log_buf, but retry with log_buf and log_level=1 on error", which is
	 * consistent across low-level and high-level BTF and program loading
	 * APIs within libbpf and provides a sensible behavior in practice
	 */
	if (log_level) {
		attr.btf_log_buf = ptr_to_u64(log_buf);
		attr.btf_log_size = (__u32)log_size;
		attr.btf_log_level = log_level;
	}

	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
	if (fd < 0 && log_buf && log_level == 0) {
		attr.btf_log_buf = ptr_to_u64(log_buf);
		attr.btf_log_size = (__u32)log_size;
		attr.btf_log_level = 1;
		fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
	}
	return libbpf_err_errno(fd);
}

int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
		      __u64 *probe_addr)
{
	union bpf_attr attr = {};
	int err;

	attr.task_fd_query.pid = pid;
	attr.task_fd_query.fd = fd;
	attr.task_fd_query.flags = flags;
	attr.task_fd_query.buf = ptr_to_u64(buf);
	attr.task_fd_query.buf_len = *buf_len;

	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));

	*buf_len = attr.task_fd_query.buf_len;
	*prog_id = attr.task_fd_query.prog_id;
	*fd_type = attr.task_fd_query.fd_type;
	*probe_offset = attr.task_fd_query.probe_offset;
	*probe_addr = attr.task_fd_query.probe_addr;

	return libbpf_err_errno(err);
}

int bpf_enable_stats(enum bpf_stats_type type)
{
	union bpf_attr attr;
	int fd;

	memset(&attr, 0, sizeof(attr));
	attr.enable_stats.type = type;

	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
	return libbpf_err_errno(fd);
}

int bpf_prog_bind_map(int prog_fd, int map_fd,
		      const struct bpf_prog_bind_opts *opts)
{
	union bpf_attr attr;
	int ret;

	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
		return libbpf_err(-EINVAL);

	memset(&attr, 0, sizeof(attr));
	attr.prog_bind_map.prog_fd = prog_fd;
	attr.prog_bind_map.map_fd = map_fd;
	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);

	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
	return libbpf_err_errno(ret);
}