summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/progs/profiler.inc.h
blob: 6957d9f2805eb3009fe972d04e137ab157b05c94 (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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2020 Facebook */
#include <vmlinux.h>
#include <bpf/bpf_core_read.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>

#include "profiler.h"
#include "err.h"
#include "bpf_experimental.h"
#include "bpf_compiler.h"

#ifndef NULL
#define NULL 0
#endif

#define O_WRONLY 00000001
#define O_RDWR 00000002
#define O_DIRECTORY 00200000
#define __O_TMPFILE 020000000
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
#define S_IFMT 00170000
#define S_IFSOCK 0140000
#define S_IFLNK 0120000
#define S_IFREG 0100000
#define S_IFBLK 0060000
#define S_IFDIR 0040000
#define S_IFCHR 0020000
#define S_IFIFO 0010000
#define S_ISUID 0004000
#define S_ISGID 0002000
#define S_ISVTX 0001000
#define S_ISLNK(m) (((m)&S_IFMT) == S_IFLNK)
#define S_ISDIR(m) (((m)&S_IFMT) == S_IFDIR)
#define S_ISCHR(m) (((m)&S_IFMT) == S_IFCHR)
#define S_ISBLK(m) (((m)&S_IFMT) == S_IFBLK)
#define S_ISFIFO(m) (((m)&S_IFMT) == S_IFIFO)
#define S_ISSOCK(m) (((m)&S_IFMT) == S_IFSOCK)

#define KILL_DATA_ARRAY_SIZE 8

struct var_kill_data_arr_t {
	struct var_kill_data_t array[KILL_DATA_ARRAY_SIZE];
};

union any_profiler_data_t {
	struct var_exec_data_t var_exec;
	struct var_kill_data_t var_kill;
	struct var_sysctl_data_t var_sysctl;
	struct var_filemod_data_t var_filemod;
	struct var_fork_data_t var_fork;
	struct var_kill_data_arr_t var_kill_data_arr;
};

volatile struct profiler_config_struct bpf_config = {};

#define FETCH_CGROUPS_FROM_BPF (bpf_config.fetch_cgroups_from_bpf)
#define CGROUP_FS_INODE (bpf_config.cgroup_fs_inode)
#define CGROUP_LOGIN_SESSION_INODE \
	(bpf_config.cgroup_login_session_inode)
#define KILL_SIGNALS (bpf_config.kill_signals_mask)
#define STALE_INFO (bpf_config.stale_info_secs)
#define INODE_FILTER (bpf_config.inode_filter)
#define READ_ENVIRON_FROM_EXEC (bpf_config.read_environ_from_exec)
#define ENABLE_CGROUP_V1_RESOLVER (bpf_config.enable_cgroup_v1_resolver)

struct kernfs_iattrs___52 {
	struct iattr ia_iattr;
};

struct kernfs_node___52 {
	union /* kernfs_node_id */ {
		struct {
			u32 ino;
			u32 generation;
		};
		u64 id;
	} id;
};

struct {
	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
	__uint(max_entries, 1);
	__type(key, u32);
	__type(value, union any_profiler_data_t);
} data_heap SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
	__uint(key_size, sizeof(int));
	__uint(value_size, sizeof(int));
} events SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_HASH);
	__uint(max_entries, KILL_DATA_ARRAY_SIZE);
	__type(key, u32);
	__type(value, struct var_kill_data_arr_t);
} var_tpid_to_data SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
	__uint(max_entries, profiler_bpf_max_function_id);
	__type(key, u32);
	__type(value, struct bpf_func_stats_data);
} bpf_func_stats SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_HASH);
	__type(key, u32);
	__type(value, bool);
	__uint(max_entries, 16);
} allowed_devices SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_HASH);
	__type(key, u64);
	__type(value, bool);
	__uint(max_entries, 1024);
} allowed_file_inodes SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_HASH);
	__type(key, u64);
	__type(value, bool);
	__uint(max_entries, 1024);
} allowed_directory_inodes SEC(".maps");

struct {
	__uint(type, BPF_MAP_TYPE_HASH);
	__type(key, u32);
	__type(value, bool);
	__uint(max_entries, 16);
} disallowed_exec_inodes SEC(".maps");

#ifndef ARRAY_SIZE
#define ARRAY_SIZE(arr) (int)(sizeof(arr) / sizeof(arr[0]))
#endif

static INLINE bool IS_ERR(const void* ptr)
{
	return IS_ERR_VALUE((unsigned long)ptr);
}

static INLINE u32 get_userspace_pid()
{
	return bpf_get_current_pid_tgid() >> 32;
}

static INLINE bool is_init_process(u32 tgid)
{
	return tgid == 1 || tgid == 0;
}

static INLINE unsigned long
probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max)
{
	len = len < max ? len : max;
	if (len > 1) {
		if (bpf_probe_read_kernel(dst, len, src))
			return 0;
	} else if (len == 1) {
		if (bpf_probe_read_kernel(dst, 1, src))
			return 0;
	}
	return len;
}

static INLINE int get_var_spid_index(struct var_kill_data_arr_t* arr_struct,
				     int spid)
{
#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
		if (arr_struct->array[i].meta.pid == spid)
			return i;
	return -1;
}

static INLINE void populate_ancestors(struct task_struct* task,
				      struct ancestors_data_t* ancestors_data)
{
	struct task_struct* parent = task;
	u32 num_ancestors, ppid;

	ancestors_data->num_ancestors = 0;
#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (num_ancestors = 0; num_ancestors < MAX_ANCESTORS; num_ancestors++) {
		parent = BPF_CORE_READ(parent, real_parent);
		if (parent == NULL)
			break;
		ppid = BPF_CORE_READ(parent, tgid);
		if (is_init_process(ppid))
			break;
		ancestors_data->ancestor_pids[num_ancestors] = ppid;
		ancestors_data->ancestor_exec_ids[num_ancestors] =
			BPF_CORE_READ(parent, self_exec_id);
		ancestors_data->ancestor_start_times[num_ancestors] =
			BPF_CORE_READ(parent, start_time);
		ancestors_data->num_ancestors = num_ancestors;
	}
}

static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
					  struct kernfs_node* cgroup_root_node,
					  void* payload,
					  int* root_pos)
{
	void* payload_start = payload;
	size_t filepart_length;

#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
		filepart_length =
			bpf_probe_read_kernel_str(payload, MAX_PATH,
						  BPF_CORE_READ(cgroup_node, name));
		if (!cgroup_node)
			return payload;
		if (cgroup_node == cgroup_root_node)
			*root_pos = payload - payload_start;
		if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
			payload += filepart_length;
		}
		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
	}
	return payload;
}

static ino_t get_inode_from_kernfs(struct kernfs_node* node)
{
	struct kernfs_node___52* node52 = (void*)node;

	if (bpf_core_field_exists(node52->id.ino)) {
		barrier_var(node52);
		return BPF_CORE_READ(node52, id.ino);
	} else {
		barrier_var(node);
		return (u64)BPF_CORE_READ(node, id);
	}
}

extern bool CONFIG_CGROUP_PIDS __kconfig __weak;
enum cgroup_subsys_id___local {
	pids_cgrp_id___local = 123, /* value doesn't matter */
};

static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
					 struct task_struct* task,
					 void* payload)
{
	struct kernfs_node* root_kernfs =
		BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);

#if __has_builtin(__builtin_preserve_enum_value)
	if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
		int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
						  pids_cgrp_id___local);
#ifdef UNROLL
		__pragma_loop_unroll
#endif
		for (int i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys_state* subsys =
				BPF_CORE_READ(task, cgroups, subsys[i]);
			if (subsys != NULL) {
				int subsys_id = BPF_CORE_READ(subsys, ss, id);
				if (subsys_id == cgrp_id) {
					proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn);
					root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn);
					break;
				}
			}
		}
	}
#endif

	cgroup_data->cgroup_root_inode = get_inode_from_kernfs(root_kernfs);
	cgroup_data->cgroup_proc_inode = get_inode_from_kernfs(proc_kernfs);

	if (bpf_core_field_exists(root_kernfs->iattr->ia_mtime)) {
		cgroup_data->cgroup_root_mtime =
			BPF_CORE_READ(root_kernfs, iattr, ia_mtime.tv_nsec);
		cgroup_data->cgroup_proc_mtime =
			BPF_CORE_READ(proc_kernfs, iattr, ia_mtime.tv_nsec);
	} else {
		struct kernfs_iattrs___52* root_iattr =
			(struct kernfs_iattrs___52*)BPF_CORE_READ(root_kernfs, iattr);
		cgroup_data->cgroup_root_mtime =
			BPF_CORE_READ(root_iattr, ia_iattr.ia_mtime.tv_nsec);

		struct kernfs_iattrs___52* proc_iattr =
			(struct kernfs_iattrs___52*)BPF_CORE_READ(proc_kernfs, iattr);
		cgroup_data->cgroup_proc_mtime =
			BPF_CORE_READ(proc_iattr, ia_iattr.ia_mtime.tv_nsec);
	}

	cgroup_data->cgroup_root_length = 0;
	cgroup_data->cgroup_proc_length = 0;
	cgroup_data->cgroup_full_length = 0;

	size_t cgroup_root_length =
		bpf_probe_read_kernel_str(payload, MAX_PATH,
					  BPF_CORE_READ(root_kernfs, name));
	if (bpf_cmp_likely(cgroup_root_length, <=, MAX_PATH)) {
		cgroup_data->cgroup_root_length = cgroup_root_length;
		payload += cgroup_root_length;
	}

	size_t cgroup_proc_length =
		bpf_probe_read_kernel_str(payload, MAX_PATH,
					  BPF_CORE_READ(proc_kernfs, name));
	if (bpf_cmp_likely(cgroup_proc_length, <=, MAX_PATH)) {
		cgroup_data->cgroup_proc_length = cgroup_proc_length;
		payload += cgroup_proc_length;
	}

	if (FETCH_CGROUPS_FROM_BPF) {
		cgroup_data->cgroup_full_path_root_pos = -1;
		void* payload_end_pos = read_full_cgroup_path(proc_kernfs, root_kernfs, payload,
							      &cgroup_data->cgroup_full_path_root_pos);
		cgroup_data->cgroup_full_length = payload_end_pos - payload;
		payload = payload_end_pos;
	}

	return (void*)payload;
}

static INLINE void* populate_var_metadata(struct var_metadata_t* metadata,
					  struct task_struct* task,
					  u32 pid, void* payload)
{
	u64 uid_gid = bpf_get_current_uid_gid();

	metadata->uid = (u32)uid_gid;
	metadata->gid = uid_gid >> 32;
	metadata->pid = pid;
	metadata->exec_id = BPF_CORE_READ(task, self_exec_id);
	metadata->start_time = BPF_CORE_READ(task, start_time);
	metadata->comm_length = 0;

	size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
	if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
		metadata->comm_length = comm_length;
		payload += comm_length;
	}

	return (void*)payload;
}

static INLINE struct var_kill_data_t*
get_var_kill_data(struct pt_regs* ctx, int spid, int tpid, int sig)
{
	int zero = 0;
	struct var_kill_data_t* kill_data = bpf_map_lookup_elem(&data_heap, &zero);

	if (kill_data == NULL)
		return NULL;
	struct task_struct* task = (struct task_struct*)bpf_get_current_task();

	void* payload = populate_var_metadata(&kill_data->meta, task, spid, kill_data->payload);
	payload = populate_cgroup_info(&kill_data->cgroup_data, task, payload);
	size_t payload_length = payload - (void*)kill_data->payload;
	kill_data->payload_length = payload_length;
	populate_ancestors(task, &kill_data->ancestors_info);
	kill_data->meta.type = KILL_EVENT;
	kill_data->kill_target_pid = tpid;
	kill_data->kill_sig = sig;
	kill_data->kill_count = 1;
	kill_data->last_kill_time = bpf_ktime_get_ns();
	return kill_data;
}

static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig)
{
	if ((KILL_SIGNALS & (1ULL << sig)) == 0)
		return 0;

	u32 spid = get_userspace_pid();
	struct var_kill_data_arr_t* arr_struct = bpf_map_lookup_elem(&var_tpid_to_data, &tpid);

	if (arr_struct == NULL) {
		struct var_kill_data_t* kill_data = get_var_kill_data(ctx, spid, tpid, sig);
		int zero = 0;

		if (kill_data == NULL)
			return 0;
		arr_struct = bpf_map_lookup_elem(&data_heap, &zero);
		if (arr_struct == NULL)
			return 0;
		bpf_probe_read_kernel(&arr_struct->array[0],
				      sizeof(arr_struct->array[0]), kill_data);
	} else {
		int index = get_var_spid_index(arr_struct, spid);

		if (index == -1) {
			struct var_kill_data_t* kill_data =
				get_var_kill_data(ctx, spid, tpid, sig);
			if (kill_data == NULL)
				return 0;
#ifdef UNROLL
			__pragma_loop_unroll
#endif
			for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
				if (arr_struct->array[i].meta.pid == 0) {
					bpf_probe_read_kernel(&arr_struct->array[i],
							      sizeof(arr_struct->array[i]),
							      kill_data);
					bpf_map_update_elem(&var_tpid_to_data, &tpid,
							    arr_struct, 0);

					return 0;
				}
			return 0;
		}

		struct var_kill_data_t* kill_data = &arr_struct->array[index];

		u64 delta_sec =
			(bpf_ktime_get_ns() - kill_data->last_kill_time) / 1000000000;

		if (delta_sec < STALE_INFO) {
			kill_data->kill_count++;
			kill_data->last_kill_time = bpf_ktime_get_ns();
			bpf_probe_read_kernel(&arr_struct->array[index],
					      sizeof(arr_struct->array[index]),
					      kill_data);
		} else {
			struct var_kill_data_t* kill_data =
				get_var_kill_data(ctx, spid, tpid, sig);
			if (kill_data == NULL)
				return 0;
			bpf_probe_read_kernel(&arr_struct->array[index],
					      sizeof(arr_struct->array[index]),
					      kill_data);
		}
	}
	bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0);
	return 0;
}

static INLINE void bpf_stats_enter(struct bpf_func_stats_ctx* bpf_stat_ctx,
				   enum bpf_function_id func_id)
{
	int func_id_key = func_id;

	bpf_stat_ctx->start_time_ns = bpf_ktime_get_ns();
	bpf_stat_ctx->bpf_func_stats_data_val =
		bpf_map_lookup_elem(&bpf_func_stats, &func_id_key);
	if (bpf_stat_ctx->bpf_func_stats_data_val)
		bpf_stat_ctx->bpf_func_stats_data_val->num_executions++;
}

static INLINE void bpf_stats_exit(struct bpf_func_stats_ctx* bpf_stat_ctx)
{
	if (bpf_stat_ctx->bpf_func_stats_data_val)
		bpf_stat_ctx->bpf_func_stats_data_val->time_elapsed_ns +=
			bpf_ktime_get_ns() - bpf_stat_ctx->start_time_ns;
}

static INLINE void
bpf_stats_pre_submit_var_perf_event(struct bpf_func_stats_ctx* bpf_stat_ctx,
				    struct var_metadata_t* meta)
{
	if (bpf_stat_ctx->bpf_func_stats_data_val) {
		bpf_stat_ctx->bpf_func_stats_data_val->num_perf_events++;
		meta->bpf_stats_num_perf_events =
			bpf_stat_ctx->bpf_func_stats_data_val->num_perf_events;
	}
	meta->bpf_stats_start_ktime_ns = bpf_stat_ctx->start_time_ns;
	meta->cpu_id = bpf_get_smp_processor_id();
}

static INLINE size_t
read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
{
	size_t length = 0;
	size_t filepart_length;
	struct dentry* parent_dentry;

#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
		filepart_length =
			bpf_probe_read_kernel_str(payload, MAX_PATH,
						  BPF_CORE_READ(filp_dentry, d_name.name));
		bpf_nop_mov(filepart_length);
		if (bpf_cmp_unlikely(filepart_length, >, MAX_PATH))
			break;
		payload += filepart_length;
		length += filepart_length;

		parent_dentry = BPF_CORE_READ(filp_dentry, d_parent);
		if (filp_dentry == parent_dentry)
			break;
		filp_dentry = parent_dentry;
	}

	return length;
}

static INLINE bool
is_ancestor_in_allowed_inodes(struct dentry* filp_dentry)
{
	struct dentry* parent_dentry;
#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
		u64 dir_ino = BPF_CORE_READ(filp_dentry, d_inode, i_ino);
		bool* allowed_dir = bpf_map_lookup_elem(&allowed_directory_inodes, &dir_ino);

		if (allowed_dir != NULL)
			return true;
		parent_dentry = BPF_CORE_READ(filp_dentry, d_parent);
		if (filp_dentry == parent_dentry)
			break;
		filp_dentry = parent_dentry;
	}
	return false;
}

static INLINE bool is_dentry_allowed_for_filemod(struct dentry* file_dentry,
						 u32* device_id,
						 u64* file_ino)
{
	u32 dev_id = BPF_CORE_READ(file_dentry, d_sb, s_dev);
	*device_id = dev_id;
	bool* allowed_device = bpf_map_lookup_elem(&allowed_devices, &dev_id);

	if (allowed_device == NULL)
		return false;

	u64 ino = BPF_CORE_READ(file_dentry, d_inode, i_ino);
	*file_ino = ino;
	bool* allowed_file = bpf_map_lookup_elem(&allowed_file_inodes, &ino);

	if (allowed_file == NULL)
		if (!is_ancestor_in_allowed_inodes(BPF_CORE_READ(file_dentry, d_parent)))
			return false;
	return true;
}

SEC("kprobe/proc_sys_write")
ssize_t BPF_KPROBE(kprobe__proc_sys_write,
		   struct file* filp, const char* buf,
		   size_t count, loff_t* ppos)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_proc_sys_write);

	u32 pid = get_userspace_pid();
	int zero = 0;
	struct var_sysctl_data_t* sysctl_data =
		bpf_map_lookup_elem(&data_heap, &zero);
	if (!sysctl_data)
		goto out;

	struct task_struct* task = (struct task_struct*)bpf_get_current_task();
	sysctl_data->meta.type = SYSCTL_EVENT;
	void* payload = populate_var_metadata(&sysctl_data->meta, task, pid, sysctl_data->payload);
	payload = populate_cgroup_info(&sysctl_data->cgroup_data, task, payload);

	populate_ancestors(task, &sysctl_data->ancestors_info);

	sysctl_data->sysctl_val_length = 0;
	sysctl_data->sysctl_path_length = 0;

	size_t sysctl_val_length = bpf_probe_read_kernel_str(payload,
							     CTL_MAXNAME, buf);
	if (bpf_cmp_likely(sysctl_val_length, <=, CTL_MAXNAME)) {
		sysctl_data->sysctl_val_length = sysctl_val_length;
		payload += sysctl_val_length;
	}

	size_t sysctl_path_length =
		bpf_probe_read_kernel_str(payload, MAX_PATH,
					  BPF_CORE_READ(filp, f_path.dentry,
							d_name.name));
	if (bpf_cmp_likely(sysctl_path_length, <=, MAX_PATH)) {
		sysctl_data->sysctl_path_length = sysctl_path_length;
		payload += sysctl_path_length;
	}

	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &sysctl_data->meta);
	unsigned long data_len = payload - (void*)sysctl_data;
	data_len = data_len > sizeof(struct var_sysctl_data_t)
		? sizeof(struct var_sysctl_data_t)
		: data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, sysctl_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("tracepoint/syscalls/sys_enter_kill")
int tracepoint__syscalls__sys_enter_kill(struct syscall_trace_enter* ctx)
{
	struct bpf_func_stats_ctx stats_ctx;

	bpf_stats_enter(&stats_ctx, profiler_bpf_sys_enter_kill);
	int pid = ctx->args[0];
	int sig = ctx->args[1];
	int ret = trace_var_sys_kill(ctx, pid, sig);
	bpf_stats_exit(&stats_ctx);
	return ret;
};

SEC("raw_tracepoint/sched_process_exit")
int raw_tracepoint__sched_process_exit(void* ctx)
{
	int zero = 0;
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_exit);

	u32 tpid = get_userspace_pid();

	struct var_kill_data_arr_t* arr_struct = bpf_map_lookup_elem(&var_tpid_to_data, &tpid);
	struct var_kill_data_t* kill_data = bpf_map_lookup_elem(&data_heap, &zero);

	if (arr_struct == NULL || kill_data == NULL)
		goto out;

	struct task_struct* task = (struct task_struct*)bpf_get_current_task();
	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);

#ifdef UNROLL
	__pragma_loop_unroll
#endif
	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];

		if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) {
			bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data),
					      past_kill_data);
			void* payload = kill_data->payload;
			size_t offset = kill_data->payload_length;
			if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN)
				return 0;
			payload += offset;

			kill_data->kill_target_name_length = 0;
			kill_data->kill_target_cgroup_proc_length = 0;

			size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
			if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
				kill_data->kill_target_name_length = comm_length;
				payload += comm_length;
			}

			size_t cgroup_proc_length =
				bpf_probe_read_kernel_str(payload,
							  KILL_TARGET_LEN,
							  BPF_CORE_READ(proc_kernfs, name));
			if (bpf_cmp_likely(cgroup_proc_length, <=, KILL_TARGET_LEN)) {
				kill_data->kill_target_cgroup_proc_length = cgroup_proc_length;
				payload += cgroup_proc_length;
			}

			bpf_stats_pre_submit_var_perf_event(&stats_ctx, &kill_data->meta);
			unsigned long data_len = (void*)payload - (void*)kill_data;
			data_len = data_len > sizeof(struct var_kill_data_t)
				? sizeof(struct var_kill_data_t)
				: data_len;
			bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, kill_data, data_len);
		}
	}
	bpf_map_delete_elem(&var_tpid_to_data, &tpid);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("raw_tracepoint/sched_process_exec")
int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_exec);

	struct linux_binprm* bprm = (struct linux_binprm*)ctx->args[2];
	u64 inode = BPF_CORE_READ(bprm, file, f_inode, i_ino);

	bool* should_filter_binprm = bpf_map_lookup_elem(&disallowed_exec_inodes, &inode);
	if (should_filter_binprm != NULL)
		goto out;

	int zero = 0;
	struct var_exec_data_t* proc_exec_data = bpf_map_lookup_elem(&data_heap, &zero);
	if (!proc_exec_data)
		goto out;

	if (INODE_FILTER && inode != INODE_FILTER)
		return 0;

	u32 pid = get_userspace_pid();
	struct task_struct* task = (struct task_struct*)bpf_get_current_task();

	proc_exec_data->meta.type = EXEC_EVENT;
	proc_exec_data->bin_path_length = 0;
	proc_exec_data->cmdline_length = 0;
	proc_exec_data->environment_length = 0;
	void* payload = populate_var_metadata(&proc_exec_data->meta, task, pid,
					      proc_exec_data->payload);
	payload = populate_cgroup_info(&proc_exec_data->cgroup_data, task, payload);

	struct task_struct* parent_task = BPF_CORE_READ(task, real_parent);
	proc_exec_data->parent_pid = BPF_CORE_READ(parent_task, tgid);
	proc_exec_data->parent_uid = BPF_CORE_READ(parent_task, real_cred, uid.val);
	proc_exec_data->parent_exec_id = BPF_CORE_READ(parent_task, self_exec_id);
	proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time);

	const char* filename = BPF_CORE_READ(bprm, filename);
	size_t bin_path_length =
		bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename);
	if (bpf_cmp_likely(bin_path_length, <=, MAX_FILENAME_LEN)) {
		proc_exec_data->bin_path_length = bin_path_length;
		payload += bin_path_length;
	}

	void* arg_start = (void*)BPF_CORE_READ(task, mm, arg_start);
	void* arg_end = (void*)BPF_CORE_READ(task, mm, arg_end);
	unsigned int cmdline_length = probe_read_lim(payload, arg_start,
						     arg_end - arg_start, MAX_ARGS_LEN);

	if (bpf_cmp_likely(cmdline_length, <=, MAX_ARGS_LEN)) {
		proc_exec_data->cmdline_length = cmdline_length;
		payload += cmdline_length;
	}

	if (READ_ENVIRON_FROM_EXEC) {
		void* env_start = (void*)BPF_CORE_READ(task, mm, env_start);
		void* env_end = (void*)BPF_CORE_READ(task, mm, env_end);
		unsigned long env_len = probe_read_lim(payload, env_start,
						       env_end - env_start, MAX_ENVIRON_LEN);
		if (cmdline_length <= MAX_ENVIRON_LEN) {
			proc_exec_data->environment_length = env_len;
			payload += env_len;
		}
	}

	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &proc_exec_data->meta);
	unsigned long data_len = payload - (void*)proc_exec_data;
	data_len = data_len > sizeof(struct var_exec_data_t)
		? sizeof(struct var_exec_data_t)
		: data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, proc_exec_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("kretprobe/do_filp_open")
int kprobe_ret__do_filp_open(struct pt_regs* ctx)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_do_filp_open_ret);

	struct file* filp = (struct file*)PT_REGS_RC_CORE(ctx);

	if (filp == NULL || IS_ERR(filp))
		goto out;
	unsigned int flags = BPF_CORE_READ(filp, f_flags);
	if ((flags & (O_RDWR | O_WRONLY)) == 0)
		goto out;
	if ((flags & O_TMPFILE) > 0)
		goto out;
	struct inode* file_inode = BPF_CORE_READ(filp, f_inode);
	umode_t mode = BPF_CORE_READ(file_inode, i_mode);
	if (S_ISDIR(mode) || S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) ||
	    S_ISSOCK(mode))
		goto out;

	struct dentry* filp_dentry = BPF_CORE_READ(filp, f_path.dentry);
	u32 device_id = 0;
	u64 file_ino = 0;
	if (!is_dentry_allowed_for_filemod(filp_dentry, &device_id, &file_ino))
		goto out;

	int zero = 0;
	struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero);
	if (!filemod_data)
		goto out;

	u32 pid = get_userspace_pid();
	struct task_struct* task = (struct task_struct*)bpf_get_current_task();

	filemod_data->meta.type = FILEMOD_EVENT;
	filemod_data->fmod_type = FMOD_OPEN;
	filemod_data->dst_flags = flags;
	filemod_data->src_inode = 0;
	filemod_data->dst_inode = file_ino;
	filemod_data->src_device_id = 0;
	filemod_data->dst_device_id = device_id;
	filemod_data->src_filepath_length = 0;
	filemod_data->dst_filepath_length = 0;

	void* payload = populate_var_metadata(&filemod_data->meta, task, pid,
					      filemod_data->payload);
	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);

	size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload);
	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
		payload += len;
		filemod_data->dst_filepath_length = len;
	}
	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta);
	unsigned long data_len = payload - (void*)filemod_data;
	data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("kprobe/vfs_link")
int BPF_KPROBE(kprobe__vfs_link,
	       struct dentry* old_dentry, struct mnt_idmap *idmap,
	       struct inode* dir, struct dentry* new_dentry,
	       struct inode** delegated_inode)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_link);

	u32 src_device_id = 0;
	u64 src_file_ino = 0;
	u32 dst_device_id = 0;
	u64 dst_file_ino = 0;
	if (!is_dentry_allowed_for_filemod(old_dentry, &src_device_id, &src_file_ino) &&
	    !is_dentry_allowed_for_filemod(new_dentry, &dst_device_id, &dst_file_ino))
		goto out;

	int zero = 0;
	struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero);
	if (!filemod_data)
		goto out;

	u32 pid = get_userspace_pid();
	struct task_struct* task = (struct task_struct*)bpf_get_current_task();

	filemod_data->meta.type = FILEMOD_EVENT;
	filemod_data->fmod_type = FMOD_LINK;
	filemod_data->dst_flags = 0;
	filemod_data->src_inode = src_file_ino;
	filemod_data->dst_inode = dst_file_ino;
	filemod_data->src_device_id = src_device_id;
	filemod_data->dst_device_id = dst_device_id;
	filemod_data->src_filepath_length = 0;
	filemod_data->dst_filepath_length = 0;

	void* payload = populate_var_metadata(&filemod_data->meta, task, pid,
					      filemod_data->payload);
	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);

	size_t len = read_absolute_file_path_from_dentry(old_dentry, payload);
	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
		payload += len;
		filemod_data->src_filepath_length = len;
	}

	len = read_absolute_file_path_from_dentry(new_dentry, payload);
	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
		payload += len;
		filemod_data->dst_filepath_length = len;
	}

	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta);
	unsigned long data_len = payload - (void*)filemod_data;
	data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("kprobe/vfs_symlink")
int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry,
	       const char* oldname)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_symlink);

	u32 dst_device_id = 0;
	u64 dst_file_ino = 0;
	if (!is_dentry_allowed_for_filemod(dentry, &dst_device_id, &dst_file_ino))
		goto out;

	int zero = 0;
	struct var_filemod_data_t* filemod_data = bpf_map_lookup_elem(&data_heap, &zero);
	if (!filemod_data)
		goto out;

	u32 pid = get_userspace_pid();
	struct task_struct* task = (struct task_struct*)bpf_get_current_task();

	filemod_data->meta.type = FILEMOD_EVENT;
	filemod_data->fmod_type = FMOD_SYMLINK;
	filemod_data->dst_flags = 0;
	filemod_data->src_inode = 0;
	filemod_data->dst_inode = dst_file_ino;
	filemod_data->src_device_id = 0;
	filemod_data->dst_device_id = dst_device_id;
	filemod_data->src_filepath_length = 0;
	filemod_data->dst_filepath_length = 0;

	void* payload = populate_var_metadata(&filemod_data->meta, task, pid,
					      filemod_data->payload);
	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);

	size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH,
					       oldname);
	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
		payload += len;
		filemod_data->src_filepath_length = len;
	}
	len = read_absolute_file_path_from_dentry(dentry, payload);
	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
		payload += len;
		filemod_data->dst_filepath_length = len;
	}
	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &filemod_data->meta);
	unsigned long data_len = payload - (void*)filemod_data;
	data_len = data_len > sizeof(*filemod_data) ? sizeof(*filemod_data) : data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, filemod_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}

SEC("raw_tracepoint/sched_process_fork")
int raw_tracepoint__sched_process_fork(struct bpf_raw_tracepoint_args* ctx)
{
	struct bpf_func_stats_ctx stats_ctx;
	bpf_stats_enter(&stats_ctx, profiler_bpf_sched_process_fork);

	int zero = 0;
	struct var_fork_data_t* fork_data = bpf_map_lookup_elem(&data_heap, &zero);
	if (!fork_data)
		goto out;

	struct task_struct* parent = (struct task_struct*)ctx->args[0];
	struct task_struct* child = (struct task_struct*)ctx->args[1];
	fork_data->meta.type = FORK_EVENT;

	void* payload = populate_var_metadata(&fork_data->meta, child,
					      BPF_CORE_READ(child, pid), fork_data->payload);
	fork_data->parent_pid = BPF_CORE_READ(parent, pid);
	fork_data->parent_exec_id = BPF_CORE_READ(parent, self_exec_id);
	fork_data->parent_start_time = BPF_CORE_READ(parent, start_time);
	bpf_stats_pre_submit_var_perf_event(&stats_ctx, &fork_data->meta);

	unsigned long data_len = payload - (void*)fork_data;
	data_len = data_len > sizeof(*fork_data) ? sizeof(*fork_data) : data_len;
	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, fork_data, data_len);
out:
	bpf_stats_exit(&stats_ctx);
	return 0;
}
char _license[] SEC("license") = "GPL";