summaryrefslogtreecommitdiff
path: root/kernel/bpf/syscall.c
blob: fd2411fd69148cff375120316fba0a0e033541f6 (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
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/vmalloc.h>
#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
#include <linux/filter.h>
#include <linux/version.h>
#include <linux/kernel.h>

DEFINE_PER_CPU(int, bpf_prog_active);

int sysctl_unprivileged_bpf_disabled __read_mostly;

static const struct bpf_map_ops * const bpf_map_types[] = {
#define BPF_PROG_TYPE(_id, _ops)
#define BPF_MAP_TYPE(_id, _ops) \
	[_id] = &_ops,
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};

static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
	struct bpf_map *map;

	if (attr->map_type >= ARRAY_SIZE(bpf_map_types) ||
	    !bpf_map_types[attr->map_type])
		return ERR_PTR(-EINVAL);

	map = bpf_map_types[attr->map_type]->map_alloc(attr);
	if (IS_ERR(map))
		return map;
	map->ops = bpf_map_types[attr->map_type];
	map->map_type = attr->map_type;
	return map;
}

void *bpf_map_area_alloc(size_t size)
{
	/* We definitely need __GFP_NORETRY, so OOM killer doesn't
	 * trigger under memory pressure as we really just want to
	 * fail instead.
	 */
	const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
	void *area;

	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
		area = kmalloc(size, GFP_USER | flags);
		if (area != NULL)
			return area;
	}

	return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL);
}

void bpf_map_area_free(void *area)
{
	kvfree(area);
}

int bpf_map_precharge_memlock(u32 pages)
{
	struct user_struct *user = get_current_user();
	unsigned long memlock_limit, cur;

	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
	cur = atomic_long_read(&user->locked_vm);
	free_uid(user);
	if (cur + pages > memlock_limit)
		return -EPERM;
	return 0;
}

static int bpf_map_charge_memlock(struct bpf_map *map)
{
	struct user_struct *user = get_current_user();
	unsigned long memlock_limit;

	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;

	atomic_long_add(map->pages, &user->locked_vm);

	if (atomic_long_read(&user->locked_vm) > memlock_limit) {
		atomic_long_sub(map->pages, &user->locked_vm);
		free_uid(user);
		return -EPERM;
	}
	map->user = user;
	return 0;
}

static void bpf_map_uncharge_memlock(struct bpf_map *map)
{
	struct user_struct *user = map->user;

	atomic_long_sub(map->pages, &user->locked_vm);
	free_uid(user);
}

/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
	struct bpf_map *map = container_of(work, struct bpf_map, work);

	bpf_map_uncharge_memlock(map);
	/* implementation dependent freeing */
	map->ops->map_free(map);
}

static void bpf_map_put_uref(struct bpf_map *map)
{
	if (atomic_dec_and_test(&map->usercnt)) {
		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
			bpf_fd_array_map_clear(map);
	}
}

/* decrement map refcnt and schedule it for freeing via workqueue
 * (unrelying map implementation ops->map_free() might sleep)
 */
void bpf_map_put(struct bpf_map *map)
{
	if (atomic_dec_and_test(&map->refcnt)) {
		INIT_WORK(&map->work, bpf_map_free_deferred);
		schedule_work(&map->work);
	}
}

void bpf_map_put_with_uref(struct bpf_map *map)
{
	bpf_map_put_uref(map);
	bpf_map_put(map);
}

static int bpf_map_release(struct inode *inode, struct file *filp)
{
	struct bpf_map *map = filp->private_data;

	if (map->ops->map_release)
		map->ops->map_release(map, filp);

	bpf_map_put_with_uref(map);
	return 0;
}

#ifdef CONFIG_PROC_FS
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
	const struct bpf_map *map = filp->private_data;
	const struct bpf_array *array;
	u32 owner_prog_type = 0;

	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
		array = container_of(map, struct bpf_array, map);
		owner_prog_type = array->owner_prog_type;
	}

	seq_printf(m,
		   "map_type:\t%u\n"
		   "key_size:\t%u\n"
		   "value_size:\t%u\n"
		   "max_entries:\t%u\n"
		   "map_flags:\t%#x\n"
		   "memlock:\t%llu\n",
		   map->map_type,
		   map->key_size,
		   map->value_size,
		   map->max_entries,
		   map->map_flags,
		   map->pages * 1ULL << PAGE_SHIFT);

	if (owner_prog_type)
		seq_printf(m, "owner_prog_type:\t%u\n",
			   owner_prog_type);
}
#endif

static const struct file_operations bpf_map_fops = {
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= bpf_map_show_fdinfo,
#endif
	.release	= bpf_map_release,
};

int bpf_map_new_fd(struct bpf_map *map)
{
	return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
				O_RDWR | O_CLOEXEC);
}

/* helper macro to check that unused fields 'union bpf_attr' are zero */
#define CHECK_ATTR(CMD) \
	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
		   sizeof(attr->CMD##_LAST_FIELD), 0, \
		   sizeof(*attr) - \
		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
		   sizeof(attr->CMD##_LAST_FIELD)) != NULL

#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
	struct bpf_map *map;
	int err;

	err = CHECK_ATTR(BPF_MAP_CREATE);
	if (err)
		return -EINVAL;

	/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
	map = find_and_alloc_map(attr);
	if (IS_ERR(map))
		return PTR_ERR(map);

	atomic_set(&map->refcnt, 1);
	atomic_set(&map->usercnt, 1);

	err = bpf_map_charge_memlock(map);
	if (err)
		goto free_map_nouncharge;

	err = bpf_map_new_fd(map);
	if (err < 0)
		/* failed to allocate fd */
		goto free_map;

	trace_bpf_map_create(map, err);
	return err;

free_map:
	bpf_map_uncharge_memlock(map);
free_map_nouncharge:
	map->ops->map_free(map);
	return err;
}

/* if error is returned, fd is released.
 * On success caller should complete fd access with matching fdput()
 */
struct bpf_map *__bpf_map_get(struct fd f)
{
	if (!f.file)
		return ERR_PTR(-EBADF);
	if (f.file->f_op != &bpf_map_fops) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	return f.file->private_data;
}

/* prog's and map's refcnt limit */
#define BPF_MAX_REFCNT 32768

struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
{
	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
		atomic_dec(&map->refcnt);
		return ERR_PTR(-EBUSY);
	}
	if (uref)
		atomic_inc(&map->usercnt);
	return map;
}

struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
	struct fd f = fdget(ufd);
	struct bpf_map *map;

	map = __bpf_map_get(f);
	if (IS_ERR(map))
		return map;

	map = bpf_map_inc(map, true);
	fdput(f);

	return map;
}

int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
	return -ENOTSUPP;
}

/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value

static int map_lookup_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_user_ptr(attr->key);
	void __user *uvalue = u64_to_user_ptr(attr->value);
	int ufd = attr->map_fd;
	struct bpf_map *map;
	void *key, *value, *ptr;
	u32 value_size;
	struct fd f;
	int err;

	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
		return -EINVAL;

	f = fdget(ufd);
	map = __bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		value_size = round_up(map->value_size, 8) * num_possible_cpus();
	else
		value_size = map->value_size;

	err = -ENOMEM;
	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
	if (!value)
		goto free_key;

	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
		err = bpf_percpu_hash_copy(map, key, value);
	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
		err = bpf_percpu_array_copy(map, key, value);
	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
		err = bpf_stackmap_copy(map, key, value);
	} else if (map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
		   map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
		err = -ENOTSUPP;
	} else {
		rcu_read_lock();
		ptr = map->ops->map_lookup_elem(map, key);
		if (ptr)
			memcpy(value, ptr, value_size);
		rcu_read_unlock();
		err = ptr ? 0 : -ENOENT;
	}

	if (err)
		goto free_value;

	err = -EFAULT;
	if (copy_to_user(uvalue, value, value_size) != 0)
		goto free_value;

	trace_bpf_map_lookup_elem(map, ufd, key, value);
	err = 0;

free_value:
	kfree(value);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags

static int map_update_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_user_ptr(attr->key);
	void __user *uvalue = u64_to_user_ptr(attr->value);
	int ufd = attr->map_fd;
	struct bpf_map *map;
	void *key, *value;
	u32 value_size;
	struct fd f;
	int err;

	if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
		return -EINVAL;

	f = fdget(ufd);
	map = __bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		value_size = round_up(map->value_size, 8) * num_possible_cpus();
	else
		value_size = map->value_size;

	err = -ENOMEM;
	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
	if (!value)
		goto free_key;

	err = -EFAULT;
	if (copy_from_user(value, uvalue, value_size) != 0)
		goto free_value;

	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
	 * inside bpf map update or delete otherwise deadlocks are possible
	 */
	preempt_disable();
	__this_cpu_inc(bpf_prog_active);
	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
		err = bpf_percpu_hash_update(map, key, value, attr->flags);
	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
		err = bpf_percpu_array_update(map, key, value, attr->flags);
	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY ||
		   map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) {
		rcu_read_lock();
		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
						   attr->flags);
		rcu_read_unlock();
	} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
		rcu_read_lock();
		err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
						  attr->flags);
		rcu_read_unlock();
	} else {
		rcu_read_lock();
		err = map->ops->map_update_elem(map, key, value, attr->flags);
		rcu_read_unlock();
	}
	__this_cpu_dec(bpf_prog_active);
	preempt_enable();

	if (!err)
		trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
	kfree(value);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

#define BPF_MAP_DELETE_ELEM_LAST_FIELD key

static int map_delete_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_user_ptr(attr->key);
	int ufd = attr->map_fd;
	struct bpf_map *map;
	struct fd f;
	void *key;
	int err;

	if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
		return -EINVAL;

	f = fdget(ufd);
	map = __bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	preempt_disable();
	__this_cpu_inc(bpf_prog_active);
	rcu_read_lock();
	err = map->ops->map_delete_elem(map, key);
	rcu_read_unlock();
	__this_cpu_dec(bpf_prog_active);
	preempt_enable();

	if (!err)
		trace_bpf_map_delete_elem(map, ufd, key);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key

static int map_get_next_key(union bpf_attr *attr)
{
	void __user *ukey = u64_to_user_ptr(attr->key);
	void __user *unext_key = u64_to_user_ptr(attr->next_key);
	int ufd = attr->map_fd;
	struct bpf_map *map;
	void *key, *next_key;
	struct fd f;
	int err;

	if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
		return -EINVAL;

	f = fdget(ufd);
	map = __bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	if (ukey) {
		err = -ENOMEM;
		key = kmalloc(map->key_size, GFP_USER);
		if (!key)
			goto err_put;

		err = -EFAULT;
		if (copy_from_user(key, ukey, map->key_size) != 0)
			goto free_key;
	} else {
		key = NULL;
	}

	err = -ENOMEM;
	next_key = kmalloc(map->key_size, GFP_USER);
	if (!next_key)
		goto free_key;

	rcu_read_lock();
	err = map->ops->map_get_next_key(map, key, next_key);
	rcu_read_unlock();
	if (err)
		goto free_next_key;

	err = -EFAULT;
	if (copy_to_user(unext_key, next_key, map->key_size) != 0)
		goto free_next_key;

	trace_bpf_map_next_key(map, ufd, key, next_key);
	err = 0;

free_next_key:
	kfree(next_key);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

static const struct bpf_verifier_ops * const bpf_prog_types[] = {
#define BPF_PROG_TYPE(_id, _ops) \
	[_id] = &_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};

static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
		return -EINVAL;

	prog->aux->ops = bpf_prog_types[type];
	prog->type = type;
	return 0;
}

/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
	int i;

	for (i = 0; i < aux->used_map_cnt; i++)
		bpf_map_put(aux->used_maps[i]);

	kfree(aux->used_maps);
}

int __bpf_prog_charge(struct user_struct *user, u32 pages)
{
	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
	unsigned long user_bufs;

	if (user) {
		user_bufs = atomic_long_add_return(pages, &user->locked_vm);
		if (user_bufs > memlock_limit) {
			atomic_long_sub(pages, &user->locked_vm);
			return -EPERM;
		}
	}

	return 0;
}

void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
{
	if (user)
		atomic_long_sub(pages, &user->locked_vm);
}

static int bpf_prog_charge_memlock(struct bpf_prog *prog)
{
	struct user_struct *user = get_current_user();
	int ret;

	ret = __bpf_prog_charge(user, prog->pages);
	if (ret) {
		free_uid(user);
		return ret;
	}

	prog->aux->user = user;
	return 0;
}

static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
{
	struct user_struct *user = prog->aux->user;

	__bpf_prog_uncharge(user, prog->pages);
	free_uid(user);
}

static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);

	free_used_maps(aux);
	bpf_prog_uncharge_memlock(aux->prog);
	bpf_prog_free(aux->prog);
}

void bpf_prog_put(struct bpf_prog *prog)
{
	if (atomic_dec_and_test(&prog->aux->refcnt)) {
		trace_bpf_prog_put_rcu(prog);
		bpf_prog_kallsyms_del(prog);
		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
	}
}
EXPORT_SYMBOL_GPL(bpf_prog_put);

static int bpf_prog_release(struct inode *inode, struct file *filp)
{
	struct bpf_prog *prog = filp->private_data;

	bpf_prog_put(prog);
	return 0;
}

#ifdef CONFIG_PROC_FS
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
	const struct bpf_prog *prog = filp->private_data;
	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };

	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
	seq_printf(m,
		   "prog_type:\t%u\n"
		   "prog_jited:\t%u\n"
		   "prog_tag:\t%s\n"
		   "memlock:\t%llu\n",
		   prog->type,
		   prog->jited,
		   prog_tag,
		   prog->pages * 1ULL << PAGE_SHIFT);
}
#endif

static const struct file_operations bpf_prog_fops = {
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= bpf_prog_show_fdinfo,
#endif
	.release	= bpf_prog_release,
};

int bpf_prog_new_fd(struct bpf_prog *prog)
{
	return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
				O_RDWR | O_CLOEXEC);
}

static struct bpf_prog *____bpf_prog_get(struct fd f)
{
	if (!f.file)
		return ERR_PTR(-EBADF);
	if (f.file->f_op != &bpf_prog_fops) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	return f.file->private_data;
}

struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
{
	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
		atomic_sub(i, &prog->aux->refcnt);
		return ERR_PTR(-EBUSY);
	}
	return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_add);

void bpf_prog_sub(struct bpf_prog *prog, int i)
{
	/* Only to be used for undoing previous bpf_prog_add() in some
	 * error path. We still know that another entity in our call
	 * path holds a reference to the program, thus atomic_sub() can
	 * be safely used in such cases!
	 */
	WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
}
EXPORT_SYMBOL_GPL(bpf_prog_sub);

struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
{
	return bpf_prog_add(prog, 1);
}
EXPORT_SYMBOL_GPL(bpf_prog_inc);

static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
{
	struct fd f = fdget(ufd);
	struct bpf_prog *prog;

	prog = ____bpf_prog_get(f);
	if (IS_ERR(prog))
		return prog;
	if (type && prog->type != *type) {
		prog = ERR_PTR(-EINVAL);
		goto out;
	}

	prog = bpf_prog_inc(prog);
out:
	fdput(f);
	return prog;
}

struct bpf_prog *bpf_prog_get(u32 ufd)
{
	return __bpf_prog_get(ufd, NULL);
}

struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
{
	struct bpf_prog *prog = __bpf_prog_get(ufd, &type);

	if (!IS_ERR(prog))
		trace_bpf_prog_get_type(prog);
	return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type);

/* last field in 'union bpf_attr' used by this command */
#define	BPF_PROG_LOAD_LAST_FIELD kern_version

static int bpf_prog_load(union bpf_attr *attr)
{
	enum bpf_prog_type type = attr->prog_type;
	struct bpf_prog *prog;
	int err;
	char license[128];
	bool is_gpl;

	if (CHECK_ATTR(BPF_PROG_LOAD))
		return -EINVAL;

	/* copy eBPF program license from user space */
	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
			      sizeof(license) - 1) < 0)
		return -EFAULT;
	license[sizeof(license) - 1] = 0;

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
	is_gpl = license_is_gpl_compatible(license);

	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
		return -E2BIG;

	if (type == BPF_PROG_TYPE_KPROBE &&
	    attr->kern_version != LINUX_VERSION_CODE)
		return -EINVAL;

	if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	/* plain bpf_prog allocation */
	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
	if (!prog)
		return -ENOMEM;

	err = bpf_prog_charge_memlock(prog);
	if (err)
		goto free_prog_nouncharge;

	prog->len = attr->insn_cnt;

	err = -EFAULT;
	if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
			   bpf_prog_insn_size(prog)) != 0)
		goto free_prog;

	prog->orig_prog = NULL;
	prog->jited = 0;

	atomic_set(&prog->aux->refcnt, 1);
	prog->gpl_compatible = is_gpl ? 1 : 0;

	/* find program type: socket_filter vs tracing_filter */
	err = find_prog_type(type, prog);
	if (err < 0)
		goto free_prog;

	/* run eBPF verifier */
	err = bpf_check(&prog, attr);
	if (err < 0)
		goto free_used_maps;

	/* eBPF program is ready to be JITed */
	prog = bpf_prog_select_runtime(prog, &err);
	if (err < 0)
		goto free_used_maps;

	err = bpf_prog_new_fd(prog);
	if (err < 0)
		/* failed to allocate fd */
		goto free_used_maps;

	bpf_prog_kallsyms_add(prog);
	trace_bpf_prog_load(prog, err);
	return err;

free_used_maps:
	free_used_maps(prog->aux);
free_prog:
	bpf_prog_uncharge_memlock(prog);
free_prog_nouncharge:
	bpf_prog_free(prog);
	return err;
}

#define BPF_OBJ_LAST_FIELD bpf_fd

static int bpf_obj_pin(const union bpf_attr *attr)
{
	if (CHECK_ATTR(BPF_OBJ))
		return -EINVAL;

	return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
}

static int bpf_obj_get(const union bpf_attr *attr)
{
	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
		return -EINVAL;

	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
}

#ifdef CONFIG_CGROUP_BPF

#define BPF_PROG_ATTACH_LAST_FIELD attach_flags

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

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	if (CHECK_ATTR(BPF_PROG_ATTACH))
		return -EINVAL;

	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
		return -EINVAL;

	switch (attr->attach_type) {
	case BPF_CGROUP_INET_INGRESS:
	case BPF_CGROUP_INET_EGRESS:
		ptype = BPF_PROG_TYPE_CGROUP_SKB;
		break;
	case BPF_CGROUP_INET_SOCK_CREATE:
		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
		break;
	default:
		return -EINVAL;
	}

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

	cgrp = cgroup_get_from_fd(attr->target_fd);
	if (IS_ERR(cgrp)) {
		bpf_prog_put(prog);
		return PTR_ERR(cgrp);
	}

	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
	if (ret)
		bpf_prog_put(prog);
	cgroup_put(cgrp);

	return ret;
}

#define BPF_PROG_DETACH_LAST_FIELD attach_type

static int bpf_prog_detach(const union bpf_attr *attr)
{
	struct cgroup *cgrp;
	int ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	if (CHECK_ATTR(BPF_PROG_DETACH))
		return -EINVAL;

	switch (attr->attach_type) {
	case BPF_CGROUP_INET_INGRESS:
	case BPF_CGROUP_INET_EGRESS:
	case BPF_CGROUP_INET_SOCK_CREATE:
		cgrp = cgroup_get_from_fd(attr->target_fd);
		if (IS_ERR(cgrp))
			return PTR_ERR(cgrp);

		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
		cgroup_put(cgrp);
		break;

	default:
		return -EINVAL;
	}

	return ret;
}
#endif /* CONFIG_CGROUP_BPF */

#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration

static int bpf_prog_test_run(const union bpf_attr *attr,
			     union bpf_attr __user *uattr)
{
	struct bpf_prog *prog;
	int ret = -ENOTSUPP;

	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
		return -EINVAL;

	prog = bpf_prog_get(attr->test.prog_fd);
	if (IS_ERR(prog))
		return PTR_ERR(prog);

	if (prog->aux->ops->test_run)
		ret = prog->aux->ops->test_run(prog, attr, uattr);

	bpf_prog_put(prog);
	return ret;
}

SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
	union bpf_attr attr = {};
	int err;

	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
		return -EPERM;

	if (!access_ok(VERIFY_READ, uattr, 1))
		return -EFAULT;

	if (size > PAGE_SIZE)	/* silly large */
		return -E2BIG;

	/* If we're handed a bigger struct than we know of,
	 * ensure all the unknown bits are 0 - i.e. new
	 * user-space does not rely on any kernel feature
	 * extensions we dont know about yet.
	 */
	if (size > sizeof(attr)) {
		unsigned char __user *addr;
		unsigned char __user *end;
		unsigned char val;

		addr = (void __user *)uattr + sizeof(attr);
		end  = (void __user *)uattr + size;

		for (; addr < end; addr++) {
			err = get_user(val, addr);
			if (err)
				return err;
			if (val)
				return -E2BIG;
		}
		size = sizeof(attr);
	}

	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
	if (copy_from_user(&attr, uattr, size) != 0)
		return -EFAULT;

	switch (cmd) {
	case BPF_MAP_CREATE:
		err = map_create(&attr);
		break;
	case BPF_MAP_LOOKUP_ELEM:
		err = map_lookup_elem(&attr);
		break;
	case BPF_MAP_UPDATE_ELEM:
		err = map_update_elem(&attr);
		break;
	case BPF_MAP_DELETE_ELEM:
		err = map_delete_elem(&attr);
		break;
	case BPF_MAP_GET_NEXT_KEY:
		err = map_get_next_key(&attr);
		break;
	case BPF_PROG_LOAD:
		err = bpf_prog_load(&attr);
		break;
	case BPF_OBJ_PIN:
		err = bpf_obj_pin(&attr);
		break;
	case BPF_OBJ_GET:
		err = bpf_obj_get(&attr);
		break;
#ifdef CONFIG_CGROUP_BPF
	case BPF_PROG_ATTACH:
		err = bpf_prog_attach(&attr);
		break;
	case BPF_PROG_DETACH:
		err = bpf_prog_detach(&attr);
		break;
#endif
	case BPF_PROG_TEST_RUN:
		err = bpf_prog_test_run(&attr, uattr);
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err;
}