summaryrefslogtreecommitdiff
path: root/kernel/bpf/cgroup.c
blob: fcde0f7b25854882c42e76f901406cbf4a1718a9 (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
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
/*
 * Functions to manage eBPF programs attached to cgroups
 *
 * Copyright (c) 2016 Daniel Mack
 *
 * This file is subject to the terms and conditions of version 2 of the GNU
 * General Public License.  See the file COPYING in the main directory of the
 * Linux distribution for more details.
 */

#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
#include <linux/filter.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/string.h>
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>

DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
EXPORT_SYMBOL(cgroup_bpf_enabled_key);

/**
 * cgroup_bpf_put() - put references of all bpf programs
 * @cgrp: the cgroup to modify
 */
void cgroup_bpf_put(struct cgroup *cgrp)
{
	enum bpf_cgroup_storage_type stype;
	unsigned int type;

	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
		struct list_head *progs = &cgrp->bpf.progs[type];
		struct bpf_prog_list *pl, *tmp;

		list_for_each_entry_safe(pl, tmp, progs, node) {
			list_del(&pl->node);
			bpf_prog_put(pl->prog);
			for_each_cgroup_storage_type(stype) {
				bpf_cgroup_storage_unlink(pl->storage[stype]);
				bpf_cgroup_storage_free(pl->storage[stype]);
			}
			kfree(pl);
			static_branch_dec(&cgroup_bpf_enabled_key);
		}
		bpf_prog_array_free(cgrp->bpf.effective[type]);
	}
}

/* count number of elements in the list.
 * it's slow but the list cannot be long
 */
static u32 prog_list_length(struct list_head *head)
{
	struct bpf_prog_list *pl;
	u32 cnt = 0;

	list_for_each_entry(pl, head, node) {
		if (!pl->prog)
			continue;
		cnt++;
	}
	return cnt;
}

/* if parent has non-overridable prog attached,
 * disallow attaching new programs to the descendent cgroup.
 * if parent has overridable or multi-prog, allow attaching
 */
static bool hierarchy_allows_attach(struct cgroup *cgrp,
				    enum bpf_attach_type type,
				    u32 new_flags)
{
	struct cgroup *p;

	p = cgroup_parent(cgrp);
	if (!p)
		return true;
	do {
		u32 flags = p->bpf.flags[type];
		u32 cnt;

		if (flags & BPF_F_ALLOW_MULTI)
			return true;
		cnt = prog_list_length(&p->bpf.progs[type]);
		WARN_ON_ONCE(cnt > 1);
		if (cnt == 1)
			return !!(flags & BPF_F_ALLOW_OVERRIDE);
		p = cgroup_parent(p);
	} while (p);
	return true;
}

/* compute a chain of effective programs for a given cgroup:
 * start from the list of programs in this cgroup and add
 * all parent programs.
 * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
 * to programs in this cgroup
 */
static int compute_effective_progs(struct cgroup *cgrp,
				   enum bpf_attach_type type,
				   struct bpf_prog_array __rcu **array)
{
	enum bpf_cgroup_storage_type stype;
	struct bpf_prog_array *progs;
	struct bpf_prog_list *pl;
	struct cgroup *p = cgrp;
	int cnt = 0;

	/* count number of effective programs by walking parents */
	do {
		if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
			cnt += prog_list_length(&p->bpf.progs[type]);
		p = cgroup_parent(p);
	} while (p);

	progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
	if (!progs)
		return -ENOMEM;

	/* populate the array with effective progs */
	cnt = 0;
	p = cgrp;
	do {
		if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
			continue;

		list_for_each_entry(pl, &p->bpf.progs[type], node) {
			if (!pl->prog)
				continue;

			progs->items[cnt].prog = pl->prog;
			for_each_cgroup_storage_type(stype)
				progs->items[cnt].cgroup_storage[stype] =
					pl->storage[stype];
			cnt++;
		}
	} while ((p = cgroup_parent(p)));

	rcu_assign_pointer(*array, progs);
	return 0;
}

static void activate_effective_progs(struct cgroup *cgrp,
				     enum bpf_attach_type type,
				     struct bpf_prog_array __rcu *array)
{
	struct bpf_prog_array __rcu *old_array;

	old_array = xchg(&cgrp->bpf.effective[type], array);
	/* free prog array after grace period, since __cgroup_bpf_run_*()
	 * might be still walking the array
	 */
	bpf_prog_array_free(old_array);
}

/**
 * cgroup_bpf_inherit() - inherit effective programs from parent
 * @cgrp: the cgroup to modify
 */
int cgroup_bpf_inherit(struct cgroup *cgrp)
{
/* has to use marco instead of const int, since compiler thinks
 * that array below is variable length
 */
#define	NR ARRAY_SIZE(cgrp->bpf.effective)
	struct bpf_prog_array __rcu *arrays[NR] = {};
	int i;

	for (i = 0; i < NR; i++)
		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);

	for (i = 0; i < NR; i++)
		if (compute_effective_progs(cgrp, i, &arrays[i]))
			goto cleanup;

	for (i = 0; i < NR; i++)
		activate_effective_progs(cgrp, i, arrays[i]);

	return 0;
cleanup:
	for (i = 0; i < NR; i++)
		bpf_prog_array_free(arrays[i]);
	return -ENOMEM;
}

static int update_effective_progs(struct cgroup *cgrp,
				  enum bpf_attach_type type)
{
	struct cgroup_subsys_state *css;
	int err;

	/* allocate and recompute effective prog arrays */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
		if (err)
			goto cleanup;
	}

	/* all allocations were successful. Activate all prog arrays */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		activate_effective_progs(desc, type, desc->bpf.inactive);
		desc->bpf.inactive = NULL;
	}

	return 0;

cleanup:
	/* oom while computing effective. Free all computed effective arrays
	 * since they were not activated
	 */
	css_for_each_descendant_pre(css, &cgrp->self) {
		struct cgroup *desc = container_of(css, struct cgroup, self);

		bpf_prog_array_free(desc->bpf.inactive);
		desc->bpf.inactive = NULL;
	}

	return err;
}

#define BPF_CGROUP_MAX_PROGS 64

/**
 * __cgroup_bpf_attach() - Attach the program to a cgroup, and
 *                         propagate the change to descendants
 * @cgrp: The cgroup which descendants to traverse
 * @prog: A program to attach
 * @type: Type of attach operation
 * @flags: Option flags
 *
 * Must be called with cgroup_mutex held.
 */
int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
			enum bpf_attach_type type, u32 flags)
{
	struct list_head *progs = &cgrp->bpf.progs[type];
	struct bpf_prog *old_prog = NULL;
	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
		*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
	enum bpf_cgroup_storage_type stype;
	struct bpf_prog_list *pl;
	bool pl_was_allocated;
	int err;

	if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
		/* invalid combination */
		return -EINVAL;

	if (!hierarchy_allows_attach(cgrp, type, flags))
		return -EPERM;

	if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
		/* Disallow attaching non-overridable on top
		 * of existing overridable in this cgroup.
		 * Disallow attaching multi-prog if overridable or none
		 */
		return -EPERM;

	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
		return -E2BIG;

	for_each_cgroup_storage_type(stype) {
		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
		if (IS_ERR(storage[stype])) {
			storage[stype] = NULL;
			for_each_cgroup_storage_type(stype)
				bpf_cgroup_storage_free(storage[stype]);
			return -ENOMEM;
		}
	}

	if (flags & BPF_F_ALLOW_MULTI) {
		list_for_each_entry(pl, progs, node) {
			if (pl->prog == prog) {
				/* disallow attaching the same prog twice */
				for_each_cgroup_storage_type(stype)
					bpf_cgroup_storage_free(storage[stype]);
				return -EINVAL;
			}
		}

		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
		if (!pl) {
			for_each_cgroup_storage_type(stype)
				bpf_cgroup_storage_free(storage[stype]);
			return -ENOMEM;
		}

		pl_was_allocated = true;
		pl->prog = prog;
		for_each_cgroup_storage_type(stype)
			pl->storage[stype] = storage[stype];
		list_add_tail(&pl->node, progs);
	} else {
		if (list_empty(progs)) {
			pl = kmalloc(sizeof(*pl), GFP_KERNEL);
			if (!pl) {
				for_each_cgroup_storage_type(stype)
					bpf_cgroup_storage_free(storage[stype]);
				return -ENOMEM;
			}
			pl_was_allocated = true;
			list_add_tail(&pl->node, progs);
		} else {
			pl = list_first_entry(progs, typeof(*pl), node);
			old_prog = pl->prog;
			for_each_cgroup_storage_type(stype) {
				old_storage[stype] = pl->storage[stype];
				bpf_cgroup_storage_unlink(old_storage[stype]);
			}
			pl_was_allocated = false;
		}
		pl->prog = prog;
		for_each_cgroup_storage_type(stype)
			pl->storage[stype] = storage[stype];
	}

	cgrp->bpf.flags[type] = flags;

	err = update_effective_progs(cgrp, type);
	if (err)
		goto cleanup;

	static_branch_inc(&cgroup_bpf_enabled_key);
	for_each_cgroup_storage_type(stype) {
		if (!old_storage[stype])
			continue;
		bpf_cgroup_storage_free(old_storage[stype]);
	}
	if (old_prog) {
		bpf_prog_put(old_prog);
		static_branch_dec(&cgroup_bpf_enabled_key);
	}
	for_each_cgroup_storage_type(stype)
		bpf_cgroup_storage_link(storage[stype], cgrp, type);
	return 0;

cleanup:
	/* and cleanup the prog list */
	pl->prog = old_prog;
	for_each_cgroup_storage_type(stype) {
		bpf_cgroup_storage_free(pl->storage[stype]);
		pl->storage[stype] = old_storage[stype];
		bpf_cgroup_storage_link(old_storage[stype], cgrp, type);
	}
	if (pl_was_allocated) {
		list_del(&pl->node);
		kfree(pl);
	}
	return err;
}

/**
 * __cgroup_bpf_detach() - Detach the program from a cgroup, and
 *                         propagate the change to descendants
 * @cgrp: The cgroup which descendants to traverse
 * @prog: A program to detach or NULL
 * @type: Type of detach operation
 *
 * Must be called with cgroup_mutex held.
 */
int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
			enum bpf_attach_type type)
{
	struct list_head *progs = &cgrp->bpf.progs[type];
	enum bpf_cgroup_storage_type stype;
	u32 flags = cgrp->bpf.flags[type];
	struct bpf_prog *old_prog = NULL;
	struct bpf_prog_list *pl;
	int err;

	if (flags & BPF_F_ALLOW_MULTI) {
		if (!prog)
			/* to detach MULTI prog the user has to specify valid FD
			 * of the program to be detached
			 */
			return -EINVAL;
	} else {
		if (list_empty(progs))
			/* report error when trying to detach and nothing is attached */
			return -ENOENT;
	}

	if (flags & BPF_F_ALLOW_MULTI) {
		/* find the prog and detach it */
		list_for_each_entry(pl, progs, node) {
			if (pl->prog != prog)
				continue;
			old_prog = prog;
			/* mark it deleted, so it's ignored while
			 * recomputing effective
			 */
			pl->prog = NULL;
			break;
		}
		if (!old_prog)
			return -ENOENT;
	} else {
		/* to maintain backward compatibility NONE and OVERRIDE cgroups
		 * allow detaching with invalid FD (prog==NULL)
		 */
		pl = list_first_entry(progs, typeof(*pl), node);
		old_prog = pl->prog;
		pl->prog = NULL;
	}

	err = update_effective_progs(cgrp, type);
	if (err)
		goto cleanup;

	/* now can actually delete it from this cgroup list */
	list_del(&pl->node);
	for_each_cgroup_storage_type(stype) {
		bpf_cgroup_storage_unlink(pl->storage[stype]);
		bpf_cgroup_storage_free(pl->storage[stype]);
	}
	kfree(pl);
	if (list_empty(progs))
		/* last program was detached, reset flags to zero */
		cgrp->bpf.flags[type] = 0;

	bpf_prog_put(old_prog);
	static_branch_dec(&cgroup_bpf_enabled_key);
	return 0;

cleanup:
	/* and restore back old_prog */
	pl->prog = old_prog;
	return err;
}

/* Must be called with cgroup_mutex held to avoid races. */
int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
		       union bpf_attr __user *uattr)
{
	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
	enum bpf_attach_type type = attr->query.attach_type;
	struct list_head *progs = &cgrp->bpf.progs[type];
	u32 flags = cgrp->bpf.flags[type];
	int cnt, ret = 0, i;

	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
		cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
	else
		cnt = prog_list_length(progs);

	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
		return -EFAULT;
	if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
		return -EFAULT;
	if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
		/* return early if user requested only program count + flags */
		return 0;
	if (attr->query.prog_cnt < cnt) {
		cnt = attr->query.prog_cnt;
		ret = -ENOSPC;
	}

	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
		return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
						   prog_ids, cnt);
	} else {
		struct bpf_prog_list *pl;
		u32 id;

		i = 0;
		list_for_each_entry(pl, progs, node) {
			id = pl->prog->aux->id;
			if (copy_to_user(prog_ids + i, &id, sizeof(id)))
				return -EFAULT;
			if (++i == cnt)
				break;
		}
	}
	return ret;
}

int cgroup_bpf_prog_attach(const union bpf_attr *attr,
			   enum bpf_prog_type ptype, struct bpf_prog *prog)
{
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
				attr->attach_flags);
	cgroup_put(cgrp);
	return ret;
}

int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
{
	struct bpf_prog *prog;
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
	if (IS_ERR(prog))
		prog = NULL;

	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
	if (prog)
		bpf_prog_put(prog);

	cgroup_put(cgrp);
	return ret;
}

int cgroup_bpf_prog_query(const union bpf_attr *attr,
			  union bpf_attr __user *uattr)
{
	struct cgroup *cgrp;
	int ret;

	cgrp = cgroup_get_from_fd(attr->query.target_fd);
	if (IS_ERR(cgrp))
		return PTR_ERR(cgrp);

	ret = cgroup_bpf_query(cgrp, attr, uattr);

	cgroup_put(cgrp);
	return ret;
}

/**
 * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
 * @sk: The socket sending or receiving traffic
 * @skb: The skb that is being sent or received
 * @type: The type of program to be exectuted
 *
 * If no socket is passed, or the socket is not of type INET or INET6,
 * this function does nothing and returns 0.
 *
 * The program type passed in via @type must be suitable for network
 * filtering. No further check is performed to assert that.
 *
 * This function will return %-EPERM if any if an attached program was found
 * and if it returned != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_skb(struct sock *sk,
				struct sk_buff *skb,
				enum bpf_attach_type type)
{
	unsigned int offset = skb->data - skb_network_header(skb);
	struct sock *save_sk;
	void *saved_data_end;
	struct cgroup *cgrp;
	int ret;

	if (!sk || !sk_fullsock(sk))
		return 0;

	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
		return 0;

	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	save_sk = skb->sk;
	skb->sk = sk;
	__skb_push(skb, offset);

	/* compute pointers for the bpf prog */
	bpf_compute_and_save_data_end(skb, &saved_data_end);

	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
				 __bpf_prog_run_save_cb);
	bpf_restore_data_end(skb, saved_data_end);
	__skb_pull(skb, offset);
	skb->sk = save_sk;
	return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);

/**
 * __cgroup_bpf_run_filter_sk() - Run a program on a sock
 * @sk: sock structure to manipulate
 * @type: The type of program to be exectuted
 *
 * socket is passed is expected to be of type INET or INET6.
 *
 * The program type passed in via @type must be suitable for sock
 * filtering. No further check is performed to assert that.
 *
 * This function will return %-EPERM if any if an attached program was found
 * and if it returned != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sk(struct sock *sk,
			       enum bpf_attach_type type)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	int ret;

	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN);
	return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);

/**
 * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and
 *                                       provided by user sockaddr
 * @sk: sock struct that will use sockaddr
 * @uaddr: sockaddr struct provided by user
 * @type: The type of program to be exectuted
 * @t_ctx: Pointer to attach type specific context
 *
 * socket is expected to be of type INET or INET6.
 *
 * This function will return %-EPERM if an attached program is found and
 * returned value != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
				      struct sockaddr *uaddr,
				      enum bpf_attach_type type,
				      void *t_ctx)
{
	struct bpf_sock_addr_kern ctx = {
		.sk = sk,
		.uaddr = uaddr,
		.t_ctx = t_ctx,
	};
	struct sockaddr_storage unspec;
	struct cgroup *cgrp;
	int ret;

	/* Check socket family since not all sockets represent network
	 * endpoint (e.g. AF_UNIX).
	 */
	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
		return 0;

	if (!ctx.uaddr) {
		memset(&unspec, 0, sizeof(unspec));
		ctx.uaddr = (struct sockaddr *)&unspec;
	}

	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);

	return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);

/**
 * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
 * @sk: socket to get cgroup from
 * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
 * sk with connection information (IP addresses, etc.) May not contain
 * cgroup info if it is a req sock.
 * @type: The type of program to be exectuted
 *
 * socket passed is expected to be of type INET or INET6.
 *
 * The program type passed in via @type must be suitable for sock_ops
 * filtering. No further check is performed to assert that.
 *
 * This function will return %-EPERM if any if an attached program was found
 * and if it returned != 1 during execution. In all other cases, 0 is returned.
 */
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
				     struct bpf_sock_ops_kern *sock_ops,
				     enum bpf_attach_type type)
{
	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
	int ret;

	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops,
				 BPF_PROG_RUN);
	return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);

int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
				      short access, enum bpf_attach_type type)
{
	struct cgroup *cgrp;
	struct bpf_cgroup_dev_ctx ctx = {
		.access_type = (access << 16) | dev_type,
		.major = major,
		.minor = minor,
	};
	int allow = 1;

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx,
				   BPF_PROG_RUN);
	rcu_read_unlock();

	return !allow;
}
EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);

static const struct bpf_func_proto *
cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	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_map_push_elem:
		return &bpf_map_push_elem_proto;
	case BPF_FUNC_map_pop_elem:
		return &bpf_map_pop_elem_proto;
	case BPF_FUNC_map_peek_elem:
		return &bpf_map_peek_elem_proto;
	case BPF_FUNC_get_current_uid_gid:
		return &bpf_get_current_uid_gid_proto;
	case BPF_FUNC_get_local_storage:
		return &bpf_get_local_storage_proto;
	case BPF_FUNC_get_current_cgroup_id:
		return &bpf_get_current_cgroup_id_proto;
	case BPF_FUNC_trace_printk:
		if (capable(CAP_SYS_ADMIN))
			return bpf_get_trace_printk_proto();
		/* fall through */
	default:
		return NULL;
	}
}

static const struct bpf_func_proto *
cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	return cgroup_base_func_proto(func_id, prog);
}

static bool cgroup_dev_is_valid_access(int off, int size,
				       enum bpf_access_type type,
				       const struct bpf_prog *prog,
				       struct bpf_insn_access_aux *info)
{
	const int size_default = sizeof(__u32);

	if (type == BPF_WRITE)
		return false;

	if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
		return false;
	/* The verifier guarantees that size > 0. */
	if (off % size != 0)
		return false;

	switch (off) {
	case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type):
		bpf_ctx_record_field_size(info, size_default);
		if (!bpf_ctx_narrow_access_ok(off, size, size_default))
			return false;
		break;
	default:
		if (size != size_default)
			return false;
	}

	return true;
}

const struct bpf_prog_ops cg_dev_prog_ops = {
};

const struct bpf_verifier_ops cg_dev_verifier_ops = {
	.get_func_proto		= cgroup_dev_func_proto,
	.is_valid_access	= cgroup_dev_is_valid_access,
};

/**
 * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl
 *
 * @head: sysctl table header
 * @table: sysctl table
 * @write: sysctl is being read (= 0) or written (= 1)
 * @buf: pointer to buffer passed by user space
 * @pcount: value-result argument: value is size of buffer pointed to by @buf,
 *	result is size of @new_buf if program set new value, initial value
 *	otherwise
 * @ppos: value-result argument: value is position at which read from or write
 *	to sysctl is happening, result is new position if program overrode it,
 *	initial value otherwise
 * @new_buf: pointer to pointer to new buffer that will be allocated if program
 *	overrides new value provided by user space on sysctl write
 *	NOTE: it's caller responsibility to free *new_buf if it was set
 * @type: type of program to be executed
 *
 * Program is run when sysctl is being accessed, either read or written, and
 * can allow or deny such access.
 *
 * This function will return %-EPERM if an attached program is found and
 * returned value != 1 during execution. In all other cases 0 is returned.
 */
int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
				   struct ctl_table *table, int write,
				   void __user *buf, size_t *pcount,
				   loff_t *ppos, void **new_buf,
				   enum bpf_attach_type type)
{
	struct bpf_sysctl_kern ctx = {
		.head = head,
		.table = table,
		.write = write,
		.ppos = ppos,
		.cur_val = NULL,
		.cur_len = PAGE_SIZE,
		.new_val = NULL,
		.new_len = 0,
		.new_updated = 0,
	};
	struct cgroup *cgrp;
	int ret;

	ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
	if (ctx.cur_val) {
		mm_segment_t old_fs;
		loff_t pos = 0;

		old_fs = get_fs();
		set_fs(KERNEL_DS);
		if (table->proc_handler(table, 0, (void __user *)ctx.cur_val,
					&ctx.cur_len, &pos)) {
			/* Let BPF program decide how to proceed. */
			ctx.cur_len = 0;
		}
		set_fs(old_fs);
	} else {
		/* Let BPF program decide how to proceed. */
		ctx.cur_len = 0;
	}

	if (write && buf && *pcount) {
		/* BPF program should be able to override new value with a
		 * buffer bigger than provided by user.
		 */
		ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
		ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount);
		if (!ctx.new_val ||
		    copy_from_user(ctx.new_val, buf, ctx.new_len))
			/* Let BPF program decide how to proceed. */
			ctx.new_len = 0;
	}

	rcu_read_lock();
	cgrp = task_dfl_cgroup(current);
	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
	rcu_read_unlock();

	kfree(ctx.cur_val);

	if (ret == 1 && ctx.new_updated) {
		*new_buf = ctx.new_val;
		*pcount = ctx.new_len;
	} else {
		kfree(ctx.new_val);
	}

	return ret == 1 ? 0 : -EPERM;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);

static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
			      size_t *lenp)
{
	ssize_t tmp_ret = 0, ret;

	if (dir->header.parent) {
		tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp);
		if (tmp_ret < 0)
			return tmp_ret;
	}

	ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp);
	if (ret < 0)
		return ret;
	*bufp += ret;
	*lenp -= ret;
	ret += tmp_ret;

	/* Avoid leading slash. */
	if (!ret)
		return ret;

	tmp_ret = strscpy(*bufp, "/", *lenp);
	if (tmp_ret < 0)
		return tmp_ret;
	*bufp += tmp_ret;
	*lenp -= tmp_ret;

	return ret + tmp_ret;
}

BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf,
	   size_t, buf_len, u64, flags)
{
	ssize_t tmp_ret = 0, ret;

	if (!buf)
		return -EINVAL;

	if (!(flags & BPF_F_SYSCTL_BASE_NAME)) {
		if (!ctx->head)
			return -EINVAL;
		tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len);
		if (tmp_ret < 0)
			return tmp_ret;
	}

	ret = strscpy(buf, ctx->table->procname, buf_len);

	return ret < 0 ? ret : tmp_ret + ret;
}

static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
	.func		= bpf_sysctl_get_name,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE,
	.arg4_type	= ARG_ANYTHING,
};

static int copy_sysctl_value(char *dst, size_t dst_len, char *src,
			     size_t src_len)
{
	if (!dst)
		return -EINVAL;

	if (!dst_len)
		return -E2BIG;

	if (!src || !src_len) {
		memset(dst, 0, dst_len);
		return -EINVAL;
	}

	memcpy(dst, src, min(dst_len, src_len));

	if (dst_len > src_len) {
		memset(dst + src_len, '\0', dst_len - src_len);
		return src_len;
	}

	dst[dst_len - 1] = '\0';

	return -E2BIG;
}

BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx,
	   char *, buf, size_t, buf_len)
{
	return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len);
}

static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
	.func		= bpf_sysctl_get_current_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf,
	   size_t, buf_len)
{
	if (!ctx->write) {
		if (buf && buf_len)
			memset(buf, '\0', buf_len);
		return -EINVAL;
	}
	return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len);
}

static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = {
	.func		= bpf_sysctl_get_new_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx,
	   const char *, buf, size_t, buf_len)
{
	if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len)
		return -EINVAL;

	if (buf_len > PAGE_SIZE - 1)
		return -E2BIG;

	memcpy(ctx->new_val, buf, buf_len);
	ctx->new_len = buf_len;
	ctx->new_updated = 1;

	return 0;
}

static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
	.func		= bpf_sysctl_set_new_value,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_MEM,
	.arg3_type	= ARG_CONST_SIZE,
};

static const struct bpf_func_proto *
sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_strtol:
		return &bpf_strtol_proto;
	case BPF_FUNC_strtoul:
		return &bpf_strtoul_proto;
	case BPF_FUNC_sysctl_get_name:
		return &bpf_sysctl_get_name_proto;
	case BPF_FUNC_sysctl_get_current_value:
		return &bpf_sysctl_get_current_value_proto;
	case BPF_FUNC_sysctl_get_new_value:
		return &bpf_sysctl_get_new_value_proto;
	case BPF_FUNC_sysctl_set_new_value:
		return &bpf_sysctl_set_new_value_proto;
	default:
		return cgroup_base_func_proto(func_id, prog);
	}
}

static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
				   const struct bpf_prog *prog,
				   struct bpf_insn_access_aux *info)
{
	const int size_default = sizeof(__u32);

	if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size)
		return false;

	switch (off) {
	case offsetof(struct bpf_sysctl, write):
		if (type != BPF_READ)
			return false;
		bpf_ctx_record_field_size(info, size_default);
		return bpf_ctx_narrow_access_ok(off, size, size_default);
	case offsetof(struct bpf_sysctl, file_pos):
		if (type == BPF_READ) {
			bpf_ctx_record_field_size(info, size_default);
			return bpf_ctx_narrow_access_ok(off, size, size_default);
		} else {
			return size == size_default;
		}
	default:
		return false;
	}
}

static u32 sysctl_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_sysctl, write):
		*insn++ = BPF_LDX_MEM(
			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
			bpf_target_off(struct bpf_sysctl_kern, write,
				       FIELD_SIZEOF(struct bpf_sysctl_kern,
						    write),
				       target_size));
		break;
	case offsetof(struct bpf_sysctl, file_pos):
		/* ppos is a pointer so it should be accessed via indirect
		 * loads and stores. Also for stores additional temporary
		 * register is used since neither src_reg nor dst_reg can be
		 * overridden.
		 */
		if (type == BPF_WRITE) {
			int treg = BPF_REG_9;

			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			if (si->src_reg == treg || si->dst_reg == treg)
				--treg;
			*insn++ = BPF_STX_MEM(
				BPF_DW, si->dst_reg, treg,
				offsetof(struct bpf_sysctl_kern, tmp_reg));
			*insn++ = BPF_LDX_MEM(
				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
				treg, si->dst_reg,
				offsetof(struct bpf_sysctl_kern, ppos));
			*insn++ = BPF_STX_MEM(
				BPF_SIZEOF(u32), treg, si->src_reg, 0);
			*insn++ = BPF_LDX_MEM(
				BPF_DW, treg, si->dst_reg,
				offsetof(struct bpf_sysctl_kern, tmp_reg));
		} else {
			*insn++ = BPF_LDX_MEM(
				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
				si->dst_reg, si->src_reg,
				offsetof(struct bpf_sysctl_kern, ppos));
			*insn++ = BPF_LDX_MEM(
				BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0);
		}
		*target_size = sizeof(u32);
		break;
	}

	return insn - insn_buf;
}

const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
	.get_func_proto		= sysctl_func_proto,
	.is_valid_access	= sysctl_is_valid_access,
	.convert_ctx_access	= sysctl_convert_ctx_access,
};

const struct bpf_prog_ops cg_sysctl_prog_ops = {
};