summaryrefslogtreecommitdiff
path: root/kernel/trace/bpf_trace.c
blob: 01e6b3a38871e275bb81bc6a401848dc9eb6401e (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
/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016 Facebook
 *
 * 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.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/bpf_perf_event.h>
#include <linux/filter.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include <linux/kprobes.h>
#include <linux/error-injection.h>

#include "trace_probe.h"
#include "trace.h"

u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);

/**
 * trace_call_bpf - invoke BPF program
 * @call: tracepoint event
 * @ctx: opaque context pointer
 *
 * kprobe handlers execute BPF programs via this helper.
 * Can be used from static tracepoints in the future.
 *
 * Return: BPF programs always return an integer which is interpreted by
 * kprobe handler as:
 * 0 - return from kprobe (event is filtered out)
 * 1 - store kprobe event into ring buffer
 * Other values are reserved and currently alias to 1
 */
unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
	unsigned int ret;

	if (in_nmi()) /* not supported yet */
		return 1;

	preempt_disable();

	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
		/*
		 * since some bpf program is already running on this cpu,
		 * don't call into another bpf program (same or different)
		 * and don't send kprobe event into ring-buffer,
		 * so return zero here
		 */
		ret = 0;
		goto out;
	}

	/*
	 * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
	 * to all call sites, we did a bpf_prog_array_valid() there to check
	 * whether call->prog_array is empty or not, which is
	 * a heurisitc to speed up execution.
	 *
	 * If bpf_prog_array_valid() fetched prog_array was
	 * non-NULL, we go into trace_call_bpf() and do the actual
	 * proper rcu_dereference() under RCU lock.
	 * If it turns out that prog_array is NULL then, we bail out.
	 * For the opposite, if the bpf_prog_array_valid() fetched pointer
	 * was NULL, you'll skip the prog_array with the risk of missing
	 * out of events when it was updated in between this and the
	 * rcu_dereference() which is accepted risk.
	 */
	ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);

 out:
	__this_cpu_dec(bpf_prog_active);
	preempt_enable();

	return ret;
}
EXPORT_SYMBOL_GPL(trace_call_bpf);

#ifdef CONFIG_BPF_KPROBE_OVERRIDE
BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
{
	regs_set_return_value(regs, rc);
	override_function_with_return(regs);
	return 0;
}

static const struct bpf_func_proto bpf_override_return_proto = {
	.func		= bpf_override_return,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};
#endif

BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
{
	int ret;

	ret = probe_kernel_read(dst, unsafe_ptr, size);
	if (unlikely(ret < 0))
		memset(dst, 0, size);

	return ret;
}

static const struct bpf_func_proto bpf_probe_read_proto = {
	.func		= bpf_probe_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
	   u32, size)
{
	/*
	 * Ensure we're in user context which is safe for the helper to
	 * run. This helper has no business in a kthread.
	 *
	 * access_ok() should prevent writing to non-user memory, but in
	 * some situations (nommu, temporary switch, etc) access_ok() does
	 * not provide enough validation, hence the check on KERNEL_DS.
	 */

	if (unlikely(in_interrupt() ||
		     current->flags & (PF_KTHREAD | PF_EXITING)))
		return -EPERM;
	if (unlikely(uaccess_kernel()))
		return -EPERM;
	if (!access_ok(VERIFY_WRITE, unsafe_ptr, size))
		return -EPERM;

	return probe_kernel_write(unsafe_ptr, src, size);
}

static const struct bpf_func_proto bpf_probe_write_user_proto = {
	.func		= bpf_probe_write_user,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_ANYTHING,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
{
	pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
			    current->comm, task_pid_nr(current));

	return &bpf_probe_write_user_proto;
}

/*
 * Only limited trace_printk() conversion specifiers allowed:
 * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
 */
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
	   u64, arg2, u64, arg3)
{
	bool str_seen = false;
	int mod[3] = {};
	int fmt_cnt = 0;
	u64 unsafe_addr;
	char buf[64];
	int i;

	/*
	 * bpf_check()->check_func_arg()->check_stack_boundary()
	 * guarantees that fmt points to bpf program stack,
	 * fmt_size bytes of it were initialized and fmt_size > 0
	 */
	if (fmt[--fmt_size] != 0)
		return -EINVAL;

	/* check format string for allowed specifiers */
	for (i = 0; i < fmt_size; i++) {
		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i]))
			return -EINVAL;

		if (fmt[i] != '%')
			continue;

		if (fmt_cnt >= 3)
			return -EINVAL;

		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
		i++;
		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		} else if (fmt[i] == 'p' || fmt[i] == 's') {
			mod[fmt_cnt]++;
			i++;
			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
				return -EINVAL;
			fmt_cnt++;
			if (fmt[i - 1] == 's') {
				if (str_seen)
					/* allow only one '%s' per fmt string */
					return -EINVAL;
				str_seen = true;

				switch (fmt_cnt) {
				case 1:
					unsafe_addr = arg1;
					arg1 = (long) buf;
					break;
				case 2:
					unsafe_addr = arg2;
					arg2 = (long) buf;
					break;
				case 3:
					unsafe_addr = arg3;
					arg3 = (long) buf;
					break;
				}
				buf[0] = 0;
				strncpy_from_unsafe(buf,
						    (void *) (long) unsafe_addr,
						    sizeof(buf));
			}
			continue;
		}

		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		}

		if (fmt[i] != 'i' && fmt[i] != 'd' &&
		    fmt[i] != 'u' && fmt[i] != 'x')
			return -EINVAL;
		fmt_cnt++;
	}

/* Horrid workaround for getting va_list handling working with different
 * argument type combinations generically for 32 and 64 bit archs.
 */
#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
#define __BPF_TP(...)							\
	__trace_printk(0 /* Fake ip */,					\
		       fmt, ##__VA_ARGS__)

#define __BPF_ARG1_TP(...)						\
	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))

#define __BPF_ARG2_TP(...)						\
	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))

#define __BPF_ARG3_TP(...)						\
	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))

	return __BPF_TP_EMIT();
}

static const struct bpf_func_proto bpf_trace_printk_proto = {
	.func		= bpf_trace_printk,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_MEM,
	.arg2_type	= ARG_CONST_SIZE,
};

const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
{
	/*
	 * this program might be calling bpf_trace_printk,
	 * so allocate per-cpu printk buffers
	 */
	trace_printk_init_buffers();

	return &bpf_trace_printk_proto;
}

static __always_inline int
get_map_perf_counter(struct bpf_map *map, u64 flags,
		     u64 *value, u64 *enabled, u64 *running)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	unsigned int cpu = smp_processor_id();
	u64 index = flags & BPF_F_INDEX_MASK;
	struct bpf_event_entry *ee;

	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
		return -EINVAL;
	if (index == BPF_F_CURRENT_CPU)
		index = cpu;
	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	ee = READ_ONCE(array->ptrs[index]);
	if (!ee)
		return -ENOENT;

	return perf_event_read_local(ee->event, value, enabled, running);
}

BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
{
	u64 value = 0;
	int err;

	err = get_map_perf_counter(map, flags, &value, NULL, NULL);
	/*
	 * this api is ugly since we miss [-22..-2] range of valid
	 * counter values, but that's uapi
	 */
	if (err)
		return err;
	return value;
}

static const struct bpf_func_proto bpf_perf_event_read_proto = {
	.func		= bpf_perf_event_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
	   struct bpf_perf_event_value *, buf, u32, size)
{
	int err = -EINVAL;

	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
		goto clear;
	err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
				   &buf->running);
	if (unlikely(err))
		goto clear;
	return 0;
clear:
	memset(buf, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
	.func		= bpf_perf_event_read_value,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg4_type	= ARG_CONST_SIZE,
};

static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);

static __always_inline u64
__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
			u64 flags, struct perf_sample_data *sd)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	unsigned int cpu = smp_processor_id();
	u64 index = flags & BPF_F_INDEX_MASK;
	struct bpf_event_entry *ee;
	struct perf_event *event;

	if (index == BPF_F_CURRENT_CPU)
		index = cpu;
	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	ee = READ_ONCE(array->ptrs[index]);
	if (!ee)
		return -ENOENT;

	event = ee->event;
	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
		return -EINVAL;

	if (unlikely(event->oncpu != cpu))
		return -EOPNOTSUPP;

	perf_event_output(event, sd, regs);
	return 0;
}

BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
	   u64, flags, void *, data, u64, size)
{
	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
	struct perf_raw_record raw = {
		.frag = {
			.size = size,
			.data = data,
		},
	};

	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
		return -EINVAL;

	perf_sample_data_init(sd, 0, 0);
	sd->raw = &raw;

	return __bpf_perf_event_output(regs, map, flags, sd);
}

static const struct bpf_func_proto bpf_perf_event_output_proto = {
	.func		= bpf_perf_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_MEM,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd);

u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
	struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd);
	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
	struct perf_raw_frag frag = {
		.copy		= ctx_copy,
		.size		= ctx_size,
		.data		= ctx,
	};
	struct perf_raw_record raw = {
		.frag = {
			{
				.next	= ctx_size ? &frag : NULL,
			},
			.size	= meta_size,
			.data	= meta,
		},
	};

	perf_fetch_caller_regs(regs);
	perf_sample_data_init(sd, 0, 0);
	sd->raw = &raw;

	return __bpf_perf_event_output(regs, map, flags, sd);
}

BPF_CALL_0(bpf_get_current_task)
{
	return (long) current;
}

static const struct bpf_func_proto bpf_get_current_task_proto = {
	.func		= bpf_get_current_task,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
};

BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct cgroup *cgrp;

	if (unlikely(in_interrupt()))
		return -EINVAL;
	if (unlikely(idx >= array->map.max_entries))
		return -E2BIG;

	cgrp = READ_ONCE(array->ptrs[idx]);
	if (unlikely(!cgrp))
		return -EAGAIN;

	return task_under_cgroup_hierarchy(current, cgrp);
}

static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
	.func           = bpf_current_task_under_cgroup,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_CONST_MAP_PTR,
	.arg2_type      = ARG_ANYTHING,
};

BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
	   const void *, unsafe_ptr)
{
	int ret;

	/*
	 * The strncpy_from_unsafe() call will likely not fill the entire
	 * buffer, but that's okay in this circumstance as we're probing
	 * arbitrary memory anyway similar to bpf_probe_read() and might
	 * as well probe the stack. Thus, memory is explicitly cleared
	 * only in error case, so that improper users ignoring return
	 * code altogether don't copy garbage; otherwise length of string
	 * is returned that can be used for bpf_perf_event_output() et al.
	 */
	ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
	if (unlikely(ret < 0))
		memset(dst, 0, size);

	return ret;
}

static const struct bpf_func_proto bpf_probe_read_str_proto = {
	.func		= bpf_probe_read_str,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg3_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_probe_read:
		return &bpf_probe_read_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	case BPF_FUNC_tail_call:
		return &bpf_tail_call_proto;
	case BPF_FUNC_get_current_pid_tgid:
		return &bpf_get_current_pid_tgid_proto;
	case BPF_FUNC_get_current_task:
		return &bpf_get_current_task_proto;
	case BPF_FUNC_get_current_uid_gid:
		return &bpf_get_current_uid_gid_proto;
	case BPF_FUNC_get_current_comm:
		return &bpf_get_current_comm_proto;
	case BPF_FUNC_trace_printk:
		return bpf_get_trace_printk_proto();
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_get_numa_node_id:
		return &bpf_get_numa_node_id_proto;
	case BPF_FUNC_perf_event_read:
		return &bpf_perf_event_read_proto;
	case BPF_FUNC_probe_write_user:
		return bpf_get_probe_write_proto();
	case BPF_FUNC_current_task_under_cgroup:
		return &bpf_current_task_under_cgroup_proto;
	case BPF_FUNC_get_prandom_u32:
		return &bpf_get_prandom_u32_proto;
	case BPF_FUNC_probe_read_str:
		return &bpf_probe_read_str_proto;
	default:
		return NULL;
	}
}

static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto;
	case BPF_FUNC_perf_event_read_value:
		return &bpf_perf_event_read_value_proto;
#ifdef CONFIG_BPF_KPROBE_OVERRIDE
	case BPF_FUNC_override_return:
		return &bpf_override_return_proto;
#endif
	default:
		return tracing_func_proto(func_id);
	}
}

/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
					struct bpf_insn_access_aux *info)
{
	if (off < 0 || off >= sizeof(struct pt_regs))
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;
	/*
	 * Assertion for 32 bit to make sure last 8 byte access
	 * (BPF_DW) to the last 4 byte member is disallowed.
	 */
	if (off + size > sizeof(struct pt_regs))
		return false;

	return true;
}

const struct bpf_verifier_ops kprobe_verifier_ops = {
	.get_func_proto  = kprobe_prog_func_proto,
	.is_valid_access = kprobe_prog_is_valid_access,
};

const struct bpf_prog_ops kprobe_prog_ops = {
};

BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
	   u64, flags, void *, data, u64, size)
{
	struct pt_regs *regs = *(struct pt_regs **)tp_buff;

	/*
	 * r1 points to perf tracepoint buffer where first 8 bytes are hidden
	 * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
	 * from there and call the same bpf_perf_event_output() helper inline.
	 */
	return ____bpf_perf_event_output(regs, map, flags, data, size);
}

static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
	.func		= bpf_perf_event_output_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_MEM,
	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
};

BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map,
	   u64, flags)
{
	struct pt_regs *regs = *(struct pt_regs **)tp_buff;

	/*
	 * Same comment as in bpf_perf_event_output_tp(), only that this time
	 * the other helper's function body cannot be inlined due to being
	 * external, thus we need to call raw helper function.
	 */
	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
			       flags, 0, 0);
}

static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
	.func		= bpf_get_stackid_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_tp;
	default:
		return tracing_func_proto(func_id);
	}
}

static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
				    struct bpf_insn_access_aux *info)
{
	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;

	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
	return true;
}

const struct bpf_verifier_ops tracepoint_verifier_ops = {
	.get_func_proto  = tp_prog_func_proto,
	.is_valid_access = tp_prog_is_valid_access,
};

const struct bpf_prog_ops tracepoint_prog_ops = {
};

BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
	   struct bpf_perf_event_value *, buf, u32, size)
{
	int err = -EINVAL;

	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
		goto clear;
	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
				    &buf->running);
	if (unlikely(err))
		goto clear;
	return 0;
clear:
	memset(buf, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
         .func           = bpf_perf_prog_read_value,
         .gpl_only       = true,
         .ret_type       = RET_INTEGER,
         .arg1_type      = ARG_PTR_TO_CTX,
         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
         .arg3_type      = ARG_CONST_SIZE,
};

static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_tp;
	case BPF_FUNC_perf_prog_read_value:
		return &bpf_perf_prog_read_value_proto;
	default:
		return tracing_func_proto(func_id);
	}
}

static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
				    struct bpf_insn_access_aux *info)
{
	const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data,
					 sample_period);

	if (off < 0 || off >= sizeof(struct bpf_perf_event_data))
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;

	switch (off) {
	case bpf_ctx_range(struct bpf_perf_event_data, sample_period):
		bpf_ctx_record_field_size(info, size_sp);
		if (!bpf_ctx_narrow_access_ok(off, size, size_sp))
			return false;
		break;
	default:
		if (size != sizeof(long))
			return false;
	}

	return true;
}

static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
				      const struct bpf_insn *si,
				      struct bpf_insn *insn_buf,
				      struct bpf_prog *prog, u32 *target_size)
{
	struct bpf_insn *insn = insn_buf;

	switch (si->off) {
	case offsetof(struct bpf_perf_event_data, sample_period):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
						       data), si->dst_reg, si->src_reg,
				      offsetof(struct bpf_perf_event_data_kern, data));
		*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
				      bpf_target_off(struct perf_sample_data, period, 8,
						     target_size));
		break;
	default:
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
						       regs), si->dst_reg, si->src_reg,
				      offsetof(struct bpf_perf_event_data_kern, regs));
		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg,
				      si->off);
		break;
	}

	return insn - insn_buf;
}

const struct bpf_verifier_ops perf_event_verifier_ops = {
	.get_func_proto		= pe_prog_func_proto,
	.is_valid_access	= pe_prog_is_valid_access,
	.convert_ctx_access	= pe_prog_convert_ctx_access,
};

const struct bpf_prog_ops perf_event_prog_ops = {
};

static DEFINE_MUTEX(bpf_event_mutex);

#define BPF_TRACE_MAX_PROGS 64

int perf_event_attach_bpf_prog(struct perf_event *event,
			       struct bpf_prog *prog)
{
	struct bpf_prog_array __rcu *old_array;
	struct bpf_prog_array *new_array;
	int ret = -EEXIST;

	/*
	 * Kprobe override only works if they are on the function entry,
	 * and only if they are on the opt-in list.
	 */
	if (prog->kprobe_override &&
	    (!trace_kprobe_on_func_entry(event->tp_event) ||
	     !trace_kprobe_error_injectable(event->tp_event)))
		return -EINVAL;

	mutex_lock(&bpf_event_mutex);

	if (event->prog)
		goto unlock;

	old_array = event->tp_event->prog_array;
	if (old_array &&
	    bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) {
		ret = -E2BIG;
		goto unlock;
	}

	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
	if (ret < 0)
		goto unlock;

	/* set the new array to event->tp_event and set event->prog */
	event->prog = prog;
	rcu_assign_pointer(event->tp_event->prog_array, new_array);
	bpf_prog_array_free(old_array);

unlock:
	mutex_unlock(&bpf_event_mutex);
	return ret;
}

void perf_event_detach_bpf_prog(struct perf_event *event)
{
	struct bpf_prog_array __rcu *old_array;
	struct bpf_prog_array *new_array;
	int ret;

	mutex_lock(&bpf_event_mutex);

	if (!event->prog)
		goto unlock;

	old_array = event->tp_event->prog_array;
	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
	if (ret < 0) {
		bpf_prog_array_delete_safe(old_array, event->prog);
	} else {
		rcu_assign_pointer(event->tp_event->prog_array, new_array);
		bpf_prog_array_free(old_array);
	}

	bpf_prog_put(event->prog);
	event->prog = NULL;

unlock:
	mutex_unlock(&bpf_event_mutex);
}

int perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
	struct perf_event_query_bpf __user *uquery = info;
	struct perf_event_query_bpf query = {};
	int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (event->attr.type != PERF_TYPE_TRACEPOINT)
		return -EINVAL;
	if (copy_from_user(&query, uquery, sizeof(query)))
		return -EFAULT;
	if (query.ids_len > BPF_TRACE_MAX_PROGS)
		return -E2BIG;

	mutex_lock(&bpf_event_mutex);
	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
				       uquery->ids,
				       query.ids_len,
				       &uquery->prog_cnt);
	mutex_unlock(&bpf_event_mutex);

	return ret;
}