summaryrefslogtreecommitdiff
path: root/net/core/bpf_sk_storage.c
blob: 6c4d90b24d467e35aec7b227af1ead927d7979e3 (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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook  */
#include <linux/rculist.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
#include <linux/rcupdate_trace.h>

DEFINE_BPF_STORAGE_CACHE(sk_cache);

static struct bpf_local_storage_data *
bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
	struct bpf_local_storage *sk_storage;
	struct bpf_local_storage_map *smap;

	sk_storage =
		rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held());
	if (!sk_storage)
		return NULL;

	smap = (struct bpf_local_storage_map *)map;
	return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}

static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
{
	struct bpf_local_storage_data *sdata;

	sdata = bpf_sk_storage_lookup(sk, map, false);
	if (!sdata)
		return -ENOENT;

	bpf_selem_unlink(SELEM(sdata), false);

	return 0;
}

/* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk)
{
	struct bpf_local_storage *sk_storage;

	rcu_read_lock();
	sk_storage = rcu_dereference(sk->sk_bpf_storage);
	if (!sk_storage) {
		rcu_read_unlock();
		return;
	}

	bpf_local_storage_destroy(sk_storage);
	rcu_read_unlock();
}

static void bpf_sk_storage_map_free(struct bpf_map *map)
{
	bpf_local_storage_map_free(map, &sk_cache, NULL);
}

static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
{
	return bpf_local_storage_map_alloc(attr, &sk_cache, false);
}

static int notsupp_get_next_key(struct bpf_map *map, void *key,
				void *next_key)
{
	return -ENOTSUPP;
}

static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_local_storage_data *sdata;
	struct socket *sock;
	int fd, err;

	fd = *(int *)key;
	sock = sockfd_lookup(fd, &err);
	if (sock) {
		sdata = bpf_sk_storage_lookup(sock->sk, map, true);
		sockfd_put(sock);
		return sdata ? sdata->data : NULL;
	}

	return ERR_PTR(err);
}

static long bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
					  void *value, u64 map_flags)
{
	struct bpf_local_storage_data *sdata;
	struct socket *sock;
	int fd, err;

	fd = *(int *)key;
	sock = sockfd_lookup(fd, &err);
	if (sock) {
		sdata = bpf_local_storage_update(
			sock->sk, (struct bpf_local_storage_map *)map, value,
			map_flags, GFP_ATOMIC);
		sockfd_put(sock);
		return PTR_ERR_OR_ZERO(sdata);
	}

	return err;
}

static long bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
{
	struct socket *sock;
	int fd, err;

	fd = *(int *)key;
	sock = sockfd_lookup(fd, &err);
	if (sock) {
		err = bpf_sk_storage_del(sock->sk, map);
		sockfd_put(sock);
		return err;
	}

	return err;
}

static struct bpf_local_storage_elem *
bpf_sk_storage_clone_elem(struct sock *newsk,
			  struct bpf_local_storage_map *smap,
			  struct bpf_local_storage_elem *selem)
{
	struct bpf_local_storage_elem *copy_selem;

	copy_selem = bpf_selem_alloc(smap, newsk, NULL, true, GFP_ATOMIC);
	if (!copy_selem)
		return NULL;

	if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))
		copy_map_value_locked(&smap->map, SDATA(copy_selem)->data,
				      SDATA(selem)->data, true);
	else
		copy_map_value(&smap->map, SDATA(copy_selem)->data,
			       SDATA(selem)->data);

	return copy_selem;
}

int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
{
	struct bpf_local_storage *new_sk_storage = NULL;
	struct bpf_local_storage *sk_storage;
	struct bpf_local_storage_elem *selem;
	int ret = 0;

	RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);

	rcu_read_lock();
	sk_storage = rcu_dereference(sk->sk_bpf_storage);

	if (!sk_storage || hlist_empty(&sk_storage->list))
		goto out;

	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
		struct bpf_local_storage_elem *copy_selem;
		struct bpf_local_storage_map *smap;
		struct bpf_map *map;

		smap = rcu_dereference(SDATA(selem)->smap);
		if (!(smap->map.map_flags & BPF_F_CLONE))
			continue;

		/* Note that for lockless listeners adding new element
		 * here can race with cleanup in bpf_local_storage_map_free.
		 * Try to grab map refcnt to make sure that it's still
		 * alive and prevent concurrent removal.
		 */
		map = bpf_map_inc_not_zero(&smap->map);
		if (IS_ERR(map))
			continue;

		copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem);
		if (!copy_selem) {
			ret = -ENOMEM;
			bpf_map_put(map);
			goto out;
		}

		if (new_sk_storage) {
			bpf_selem_link_map(smap, copy_selem);
			bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
		} else {
			ret = bpf_local_storage_alloc(newsk, smap, copy_selem, GFP_ATOMIC);
			if (ret) {
				bpf_selem_free(copy_selem, smap, true);
				atomic_sub(smap->elem_size,
					   &newsk->sk_omem_alloc);
				bpf_map_put(map);
				goto out;
			}

			new_sk_storage =
				rcu_dereference(copy_selem->local_storage);
		}
		bpf_map_put(map);
	}

out:
	rcu_read_unlock();

	/* In case of an error, don't free anything explicitly here, the
	 * caller is responsible to call bpf_sk_storage_free.
	 */

	return ret;
}

/* *gfp_flags* is a hidden argument provided by the verifier */
BPF_CALL_5(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
	   void *, value, u64, flags, gfp_t, gfp_flags)
{
	struct bpf_local_storage_data *sdata;

	WARN_ON_ONCE(!bpf_rcu_lock_held());
	if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
		return (unsigned long)NULL;

	sdata = bpf_sk_storage_lookup(sk, map, true);
	if (sdata)
		return (unsigned long)sdata->data;

	if (flags == BPF_SK_STORAGE_GET_F_CREATE &&
	    /* Cannot add new elem to a going away sk.
	     * Otherwise, the new elem may become a leak
	     * (and also other memory issues during map
	     *  destruction).
	     */
	    refcount_inc_not_zero(&sk->sk_refcnt)) {
		sdata = bpf_local_storage_update(
			sk, (struct bpf_local_storage_map *)map, value,
			BPF_NOEXIST, gfp_flags);
		/* sk must be a fullsock (guaranteed by verifier),
		 * so sock_gen_put() is unnecessary.
		 */
		sock_put(sk);
		return IS_ERR(sdata) ?
			(unsigned long)NULL : (unsigned long)sdata->data;
	}

	return (unsigned long)NULL;
}

BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
{
	WARN_ON_ONCE(!bpf_rcu_lock_held());
	if (!sk || !sk_fullsock(sk))
		return -EINVAL;

	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
		int err;

		err = bpf_sk_storage_del(sk, map);
		sock_put(sk);
		return err;
	}

	return -ENOENT;
}

static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
				 void *owner, u32 size)
{
	struct sock *sk = (struct sock *)owner;
	int optmem_max;

	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
	/* same check as in sock_kmalloc() */
	if (size <= optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
		atomic_add(size, &sk->sk_omem_alloc);
		return 0;
	}

	return -ENOMEM;
}

static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
				    void *owner, u32 size)
{
	struct sock *sk = owner;

	atomic_sub(size, &sk->sk_omem_alloc);
}

static struct bpf_local_storage __rcu **
bpf_sk_storage_ptr(void *owner)
{
	struct sock *sk = owner;

	return &sk->sk_bpf_storage;
}

const struct bpf_map_ops sk_storage_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc_check = bpf_local_storage_map_alloc_check,
	.map_alloc = bpf_sk_storage_map_alloc,
	.map_free = bpf_sk_storage_map_free,
	.map_get_next_key = notsupp_get_next_key,
	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
	.map_update_elem = bpf_fd_sk_storage_update_elem,
	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
	.map_check_btf = bpf_local_storage_map_check_btf,
	.map_btf_id = &bpf_local_storage_map_btf_id[0],
	.map_local_storage_charge = bpf_sk_storage_charge,
	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
	.map_owner_storage_ptr = bpf_sk_storage_ptr,
	.map_mem_usage = bpf_local_storage_map_mem_usage,
};

const struct bpf_func_proto bpf_sk_storage_get_proto = {
	.func		= bpf_sk_storage_get,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
	.arg4_type	= ARG_ANYTHING,
};

const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = {
	.func		= bpf_sk_storage_get,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_CTX, /* context is 'struct sock' */
	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
	.arg4_type	= ARG_ANYTHING,
};

const struct bpf_func_proto bpf_sk_storage_delete_proto = {
	.func		= bpf_sk_storage_delete,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
};

static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
{
	const struct btf *btf_vmlinux;
	const struct btf_type *t;
	const char *tname;
	u32 btf_id;

	if (prog->aux->dst_prog)
		return false;

	/* Ensure the tracing program is not tracing
	 * any bpf_sk_storage*() function and also
	 * use the bpf_sk_storage_(get|delete) helper.
	 */
	switch (prog->expected_attach_type) {
	case BPF_TRACE_ITER:
	case BPF_TRACE_RAW_TP:
		/* bpf_sk_storage has no trace point */
		return true;
	case BPF_TRACE_FENTRY:
	case BPF_TRACE_FEXIT:
		btf_vmlinux = bpf_get_btf_vmlinux();
		if (IS_ERR_OR_NULL(btf_vmlinux))
			return false;
		btf_id = prog->aux->attach_btf_id;
		t = btf_type_by_id(btf_vmlinux, btf_id);
		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
		return !!strncmp(tname, "bpf_sk_storage",
				 strlen("bpf_sk_storage"));
	default:
		return false;
	}

	return false;
}

/* *gfp_flags* is a hidden argument provided by the verifier */
BPF_CALL_5(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
	   void *, value, u64, flags, gfp_t, gfp_flags)
{
	WARN_ON_ONCE(!bpf_rcu_lock_held());
	if (in_hardirq() || in_nmi())
		return (unsigned long)NULL;

	return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags,
						     gfp_flags);
}

BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
	   struct sock *, sk)
{
	WARN_ON_ONCE(!bpf_rcu_lock_held());
	if (in_hardirq() || in_nmi())
		return -EPERM;

	return ____bpf_sk_storage_delete(map, sk);
}

const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
	.func		= bpf_sk_storage_get_tracing,
	.gpl_only	= false,
	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_BTF_ID_OR_NULL,
	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
	.arg4_type	= ARG_ANYTHING,
	.allowed	= bpf_sk_storage_tracing_allowed,
};

const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
	.func		= bpf_sk_storage_delete_tracing,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_PTR_TO_BTF_ID_OR_NULL,
	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
	.allowed	= bpf_sk_storage_tracing_allowed,
};

struct bpf_sk_storage_diag {
	u32 nr_maps;
	struct bpf_map *maps[];
};

/* The reply will be like:
 * INET_DIAG_BPF_SK_STORAGES (nla_nest)
 *	SK_DIAG_BPF_STORAGE (nla_nest)
 *		SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32)
 *		SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit)
 *	SK_DIAG_BPF_STORAGE (nla_nest)
 *		SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32)
 *		SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit)
 *	....
 */
static int nla_value_size(u32 value_size)
{
	/* SK_DIAG_BPF_STORAGE (nla_nest)
	 *	SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32)
	 *	SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit)
	 */
	return nla_total_size(0) + nla_total_size(sizeof(u32)) +
		nla_total_size_64bit(value_size);
}

void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag)
{
	u32 i;

	if (!diag)
		return;

	for (i = 0; i < diag->nr_maps; i++)
		bpf_map_put(diag->maps[i]);

	kfree(diag);
}
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free);

static bool diag_check_dup(const struct bpf_sk_storage_diag *diag,
			   const struct bpf_map *map)
{
	u32 i;

	for (i = 0; i < diag->nr_maps; i++) {
		if (diag->maps[i] == map)
			return true;
	}

	return false;
}

struct bpf_sk_storage_diag *
bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
{
	struct bpf_sk_storage_diag *diag;
	struct nlattr *nla;
	u32 nr_maps = 0;
	int rem, err;

	/* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as
	 * the map_alloc_check() side also does.
	 */
	if (!bpf_capable())
		return ERR_PTR(-EPERM);

	nla_for_each_nested(nla, nla_stgs, rem) {
		if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) {
			if (nla_len(nla) != sizeof(u32))
				return ERR_PTR(-EINVAL);
			nr_maps++;
		}
	}

	diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL);
	if (!diag)
		return ERR_PTR(-ENOMEM);

	nla_for_each_nested(nla, nla_stgs, rem) {
		struct bpf_map *map;
		int map_fd;

		if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD)
			continue;

		map_fd = nla_get_u32(nla);
		map = bpf_map_get(map_fd);
		if (IS_ERR(map)) {
			err = PTR_ERR(map);
			goto err_free;
		}
		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) {
			bpf_map_put(map);
			err = -EINVAL;
			goto err_free;
		}
		if (diag_check_dup(diag, map)) {
			bpf_map_put(map);
			err = -EEXIST;
			goto err_free;
		}
		diag->maps[diag->nr_maps++] = map;
	}

	return diag;

err_free:
	bpf_sk_storage_diag_free(diag);
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc);

static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
{
	struct nlattr *nla_stg, *nla_value;
	struct bpf_local_storage_map *smap;

	/* It cannot exceed max nlattr's payload */
	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE);

	nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
	if (!nla_stg)
		return -EMSGSIZE;

	smap = rcu_dereference(sdata->smap);
	if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id))
		goto errout;

	nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE,
				      smap->map.value_size,
				      SK_DIAG_BPF_STORAGE_PAD);
	if (!nla_value)
		goto errout;

	if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))
		copy_map_value_locked(&smap->map, nla_data(nla_value),
				      sdata->data, true);
	else
		copy_map_value(&smap->map, nla_data(nla_value), sdata->data);

	nla_nest_end(skb, nla_stg);
	return 0;

errout:
	nla_nest_cancel(skb, nla_stg);
	return -EMSGSIZE;
}

static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb,
				       int stg_array_type,
				       unsigned int *res_diag_size)
{
	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
	unsigned int diag_size = nla_total_size(0);
	struct bpf_local_storage *sk_storage;
	struct bpf_local_storage_elem *selem;
	struct bpf_local_storage_map *smap;
	struct nlattr *nla_stgs;
	unsigned int saved_len;
	int err = 0;

	rcu_read_lock();

	sk_storage = rcu_dereference(sk->sk_bpf_storage);
	if (!sk_storage || hlist_empty(&sk_storage->list)) {
		rcu_read_unlock();
		return 0;
	}

	nla_stgs = nla_nest_start(skb, stg_array_type);
	if (!nla_stgs)
		/* Continue to learn diag_size */
		err = -EMSGSIZE;

	saved_len = skb->len;
	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
		smap = rcu_dereference(SDATA(selem)->smap);
		diag_size += nla_value_size(smap->map.value_size);

		if (nla_stgs && diag_get(SDATA(selem), skb))
			/* Continue to learn diag_size */
			err = -EMSGSIZE;
	}

	rcu_read_unlock();

	if (nla_stgs) {
		if (saved_len == skb->len)
			nla_nest_cancel(skb, nla_stgs);
		else
			nla_nest_end(skb, nla_stgs);
	}

	if (diag_size == nla_total_size(0)) {
		*res_diag_size = 0;
		return 0;
	}

	*res_diag_size = diag_size;
	return err;
}

int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
			    struct sock *sk, struct sk_buff *skb,
			    int stg_array_type,
			    unsigned int *res_diag_size)
{
	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
	unsigned int diag_size = nla_total_size(0);
	struct bpf_local_storage *sk_storage;
	struct bpf_local_storage_data *sdata;
	struct nlattr *nla_stgs;
	unsigned int saved_len;
	int err = 0;
	u32 i;

	*res_diag_size = 0;

	/* No map has been specified.  Dump all. */
	if (!diag->nr_maps)
		return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type,
						   res_diag_size);

	rcu_read_lock();
	sk_storage = rcu_dereference(sk->sk_bpf_storage);
	if (!sk_storage || hlist_empty(&sk_storage->list)) {
		rcu_read_unlock();
		return 0;
	}

	nla_stgs = nla_nest_start(skb, stg_array_type);
	if (!nla_stgs)
		/* Continue to learn diag_size */
		err = -EMSGSIZE;

	saved_len = skb->len;
	for (i = 0; i < diag->nr_maps; i++) {
		sdata = bpf_local_storage_lookup(sk_storage,
				(struct bpf_local_storage_map *)diag->maps[i],
				false);

		if (!sdata)
			continue;

		diag_size += nla_value_size(diag->maps[i]->value_size);

		if (nla_stgs && diag_get(sdata, skb))
			/* Continue to learn diag_size */
			err = -EMSGSIZE;
	}
	rcu_read_unlock();

	if (nla_stgs) {
		if (saved_len == skb->len)
			nla_nest_cancel(skb, nla_stgs);
		else
			nla_nest_end(skb, nla_stgs);
	}

	if (diag_size == nla_total_size(0)) {
		*res_diag_size = 0;
		return 0;
	}

	*res_diag_size = diag_size;
	return err;
}
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put);

struct bpf_iter_seq_sk_storage_map_info {
	struct bpf_map *map;
	unsigned int bucket_id;
	unsigned skip_elems;
};

static struct bpf_local_storage_elem *
bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
				 struct bpf_local_storage_elem *prev_selem)
	__acquires(RCU) __releases(RCU)
{
	struct bpf_local_storage *sk_storage;
	struct bpf_local_storage_elem *selem;
	u32 skip_elems = info->skip_elems;
	struct bpf_local_storage_map *smap;
	u32 bucket_id = info->bucket_id;
	u32 i, count, n_buckets;
	struct bpf_local_storage_map_bucket *b;

	smap = (struct bpf_local_storage_map *)info->map;
	n_buckets = 1U << smap->bucket_log;
	if (bucket_id >= n_buckets)
		return NULL;

	/* try to find next selem in the same bucket */
	selem = prev_selem;
	count = 0;
	while (selem) {
		selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)),
					 struct bpf_local_storage_elem, map_node);
		if (!selem) {
			/* not found, unlock and go to the next bucket */
			b = &smap->buckets[bucket_id++];
			rcu_read_unlock();
			skip_elems = 0;
			break;
		}
		sk_storage = rcu_dereference(selem->local_storage);
		if (sk_storage) {
			info->skip_elems = skip_elems + count;
			return selem;
		}
		count++;
	}

	for (i = bucket_id; i < (1U << smap->bucket_log); i++) {
		b = &smap->buckets[i];
		rcu_read_lock();
		count = 0;
		hlist_for_each_entry_rcu(selem, &b->list, map_node) {
			sk_storage = rcu_dereference(selem->local_storage);
			if (sk_storage && count >= skip_elems) {
				info->bucket_id = i;
				info->skip_elems = count;
				return selem;
			}
			count++;
		}
		rcu_read_unlock();
		skip_elems = 0;
	}

	info->bucket_id = i;
	info->skip_elems = 0;
	return NULL;
}

static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bpf_local_storage_elem *selem;

	selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
	if (!selem)
		return NULL;

	if (*pos == 0)
		++*pos;
	return selem;
}

static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v,
					 loff_t *pos)
{
	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;

	++*pos;
	++info->skip_elems;
	return bpf_sk_storage_map_seq_find_next(seq->private, v);
}

struct bpf_iter__bpf_sk_storage_map {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct bpf_map *, map);
	__bpf_md_ptr(struct sock *, sk);
	__bpf_md_ptr(void *, value);
};

DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
		     struct bpf_map *map, struct sock *sk,
		     void *value)

static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
					 struct bpf_local_storage_elem *selem)
{
	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
	struct bpf_iter__bpf_sk_storage_map ctx = {};
	struct bpf_local_storage *sk_storage;
	struct bpf_iter_meta meta;
	struct bpf_prog *prog;
	int ret = 0;

	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, selem == NULL);
	if (prog) {
		ctx.meta = &meta;
		ctx.map = info->map;
		if (selem) {
			sk_storage = rcu_dereference(selem->local_storage);
			ctx.sk = sk_storage->owner;
			ctx.value = SDATA(selem)->data;
		}
		ret = bpf_iter_run_prog(prog, &ctx);
	}

	return ret;
}

static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
{
	return __bpf_sk_storage_map_seq_show(seq, v);
}

static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
	__releases(RCU)
{
	if (!v)
		(void)__bpf_sk_storage_map_seq_show(seq, v);
	else
		rcu_read_unlock();
}

static int bpf_iter_init_sk_storage_map(void *priv_data,
					struct bpf_iter_aux_info *aux)
{
	struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;

	bpf_map_inc_with_uref(aux->map);
	seq_info->map = aux->map;
	return 0;
}

static void bpf_iter_fini_sk_storage_map(void *priv_data)
{
	struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;

	bpf_map_put_with_uref(seq_info->map);
}

static int bpf_iter_attach_map(struct bpf_prog *prog,
			       union bpf_iter_link_info *linfo,
			       struct bpf_iter_aux_info *aux)
{
	struct bpf_map *map;
	int err = -EINVAL;

	if (!linfo->map.map_fd)
		return -EBADF;

	map = bpf_map_get_with_uref(linfo->map.map_fd);
	if (IS_ERR(map))
		return PTR_ERR(map);

	if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
		goto put_map;

	if (prog->aux->max_rdwr_access > map->value_size) {
		err = -EACCES;
		goto put_map;
	}

	aux->map = map;
	return 0;

put_map:
	bpf_map_put_with_uref(map);
	return err;
}

static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
{
	bpf_map_put_with_uref(aux->map);
}

static const struct seq_operations bpf_sk_storage_map_seq_ops = {
	.start  = bpf_sk_storage_map_seq_start,
	.next   = bpf_sk_storage_map_seq_next,
	.stop   = bpf_sk_storage_map_seq_stop,
	.show   = bpf_sk_storage_map_seq_show,
};

static const struct bpf_iter_seq_info iter_seq_info = {
	.seq_ops		= &bpf_sk_storage_map_seq_ops,
	.init_seq_private	= bpf_iter_init_sk_storage_map,
	.fini_seq_private	= bpf_iter_fini_sk_storage_map,
	.seq_priv_size		= sizeof(struct bpf_iter_seq_sk_storage_map_info),
};

static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
	.target			= "bpf_sk_storage_map",
	.attach_target		= bpf_iter_attach_map,
	.detach_target		= bpf_iter_detach_map,
	.show_fdinfo		= bpf_iter_map_show_fdinfo,
	.fill_link_info		= bpf_iter_map_fill_link_info,
	.ctx_arg_info_size	= 2,
	.ctx_arg_info		= {
		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
		  PTR_TO_BTF_ID_OR_NULL },
		{ offsetof(struct bpf_iter__bpf_sk_storage_map, value),
		  PTR_TO_BUF | PTR_MAYBE_NULL },
	},
	.seq_info		= &iter_seq_info,
};

static int __init bpf_sk_storage_map_iter_init(void)
{
	bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id =
		btf_sock_ids[BTF_SOCK_TYPE_SOCK];
	return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info);
}
late_initcall(bpf_sk_storage_map_iter_init);