summaryrefslogtreecommitdiffstats
path: root/net/core/bpf_sk_storage.c
blob: 756b63b6f7b30d43be4db42c982a378c7649a5b9 (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
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
// 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 <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>

static atomic_t cache_idx;

#define SK_STORAGE_CREATE_FLAG_MASK					\
	(BPF_F_NO_PREALLOC | BPF_F_CLONE)

struct bucket {
	struct hlist_head list;
	raw_spinlock_t lock;
};

/* Thp map is not the primary owner of a bpf_sk_storage_elem.
 * Instead, the sk->sk_bpf_storage is.
 *
 * The map (bpf_sk_storage_map) is for two purposes
 * 1. Define the size of the "sk local storage".  It is
 *    the map's value_size.
 *
 * 2. Maintain a list to keep track of all elems such
 *    that they can be cleaned up during the map destruction.
 *
 * When a bpf local storage is being looked up for a
 * particular sk,  the "bpf_map" pointer is actually used
 * as the "key" to search in the list of elem in
 * sk->sk_bpf_storage.
 *
 * Hence, consider sk->sk_bpf_storage is the mini-map
 * with the "bpf_map" pointer as the searching key.
 */
struct bpf_sk_storage_map {
	struct bpf_map map;
	/* Lookup elem does not require accessing the map.
	 *
	 * Updating/Deleting requires a bucket lock to
	 * link/unlink the elem from the map.  Having
	 * multiple buckets to improve contention.
	 */
	struct bucket *buckets;
	u32 bucket_log;
	u16 elem_size;
	u16 cache_idx;
};

struct bpf_sk_storage_data {
	/* smap is used as the searching key when looking up
	 * from sk->sk_bpf_storage.
	 *
	 * Put it in the same cacheline as the data to minimize
	 * the number of cachelines access during the cache hit case.
	 */
	struct bpf_sk_storage_map __rcu *smap;
	u8 data[] __aligned(8);
};

/* Linked to bpf_sk_storage and bpf_sk_storage_map */
struct bpf_sk_storage_elem {
	struct hlist_node map_node;	/* Linked to bpf_sk_storage_map */
	struct hlist_node snode;	/* Linked to bpf_sk_storage */
	struct bpf_sk_storage __rcu *sk_storage;
	struct rcu_head rcu;
	/* 8 bytes hole */
	/* The data is stored in aother cacheline to minimize
	 * the number of cachelines access during a cache hit.
	 */
	struct bpf_sk_storage_data sdata ____cacheline_aligned;
};

#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
#define SDATA(_SELEM) (&(_SELEM)->sdata)
#define BPF_SK_STORAGE_CACHE_SIZE	16

struct bpf_sk_storage {
	struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
	struct hlist_head list;	/* List of bpf_sk_storage_elem */
	struct sock *sk;	/* The sk that owns the the above "list" of
				 * bpf_sk_storage_elem.
				 */
	struct rcu_head rcu;
	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
};

static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
				    struct bpf_sk_storage_elem *selem)
{
	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
}

static int omem_charge(struct sock *sk, unsigned int size)
{
	/* same check as in sock_kmalloc() */
	if (size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		atomic_add(size, &sk->sk_omem_alloc);
		return 0;
	}

	return -ENOMEM;
}

static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
{
	return !hlist_unhashed(&selem->snode);
}

static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
{
	return !hlist_unhashed(&selem->map_node);
}

static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
					       struct sock *sk, void *value,
					       bool charge_omem)
{
	struct bpf_sk_storage_elem *selem;

	if (charge_omem && omem_charge(sk, smap->elem_size))
		return NULL;

	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
	if (selem) {
		if (value)
			memcpy(SDATA(selem)->data, value, smap->map.value_size);
		return selem;
	}

	if (charge_omem)
		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);

	return NULL;
}

/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
 * The caller must ensure selem->smap is still valid to be
 * dereferenced for its smap->elem_size and smap->cache_idx.
 */
static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
			      struct bpf_sk_storage_elem *selem,
			      bool uncharge_omem)
{
	struct bpf_sk_storage_map *smap;
	bool free_sk_storage;
	struct sock *sk;

	smap = rcu_dereference(SDATA(selem)->smap);
	sk = sk_storage->sk;

	/* All uncharging on sk->sk_omem_alloc must be done first.
	 * sk may be freed once the last selem is unlinked from sk_storage.
	 */
	if (uncharge_omem)
		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);

	free_sk_storage = hlist_is_singular_node(&selem->snode,
						 &sk_storage->list);
	if (free_sk_storage) {
		atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
		sk_storage->sk = NULL;
		/* After this RCU_INIT, sk may be freed and cannot be used */
		RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);

		/* sk_storage is not freed now.  sk_storage->lock is
		 * still held and raw_spin_unlock_bh(&sk_storage->lock)
		 * will be done by the caller.
		 *
		 * Although the unlock will be done under
		 * rcu_read_lock(),  it is more intutivie to
		 * read if kfree_rcu(sk_storage, rcu) is done
		 * after the raw_spin_unlock_bh(&sk_storage->lock).
		 *
		 * Hence, a "bool free_sk_storage" is returned
		 * to the caller which then calls the kfree_rcu()
		 * after unlock.
		 */
	}
	hlist_del_init_rcu(&selem->snode);
	if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
	    SDATA(selem))
		RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);

	kfree_rcu(selem, rcu);

	return free_sk_storage;
}

static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
{
	struct bpf_sk_storage *sk_storage;
	bool free_sk_storage = false;

	if (unlikely(!selem_linked_to_sk(selem)))
		/* selem has already been unlinked from sk */
		return;

	sk_storage = rcu_dereference(selem->sk_storage);
	raw_spin_lock_bh(&sk_storage->lock);
	if (likely(selem_linked_to_sk(selem)))
		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
	raw_spin_unlock_bh(&sk_storage->lock);

	if (free_sk_storage)
		kfree_rcu(sk_storage, rcu);
}

static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
			    struct bpf_sk_storage_elem *selem)
{
	RCU_INIT_POINTER(selem->sk_storage, sk_storage);
	hlist_add_head(&selem->snode, &sk_storage->list);
}

static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
{
	struct bpf_sk_storage_map *smap;
	struct bucket *b;

	if (unlikely(!selem_linked_to_map(selem)))
		/* selem has already be unlinked from smap */
		return;

	smap = rcu_dereference(SDATA(selem)->smap);
	b = select_bucket(smap, selem);
	raw_spin_lock_bh(&b->lock);
	if (likely(selem_linked_to_map(selem)))
		hlist_del_init_rcu(&selem->map_node);
	raw_spin_unlock_bh(&b->lock);
}

static void selem_link_map(struct bpf_sk_storage_map *smap,
			   struct bpf_sk_storage_elem *selem)
{
	struct bucket *b = select_bucket(smap, selem);

	raw_spin_lock_bh(&b->lock);
	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
	hlist_add_head_rcu(&selem->map_node, &b->list);
	raw_spin_unlock_bh(&b->lock);
}

static void selem_unlink(struct bpf_sk_storage_elem *selem)
{
	/* Always unlink from map before unlinking from sk_storage
	 * because selem will be freed after successfully unlinked from
	 * the sk_storage.
	 */
	selem_unlink_map(selem);
	selem_unlink_sk(selem);
}

static struct bpf_sk_storage_data *
__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
		    struct bpf_sk_storage_map *smap,
		    bool cacheit_lockit)
{
	struct bpf_sk_storage_data *sdata;
	struct bpf_sk_storage_elem *selem;

	/* Fast path (cache hit) */
	sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
	if (sdata && rcu_access_pointer(sdata->smap) == smap)
		return sdata;

	/* Slow path (cache miss) */
	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
			break;

	if (!selem)
		return NULL;

	sdata = SDATA(selem);
	if (cacheit_lockit) {
		/* spinlock is needed to avoid racing with the
		 * parallel delete.  Otherwise, publishing an already
		 * deleted sdata to the cache will become a use-after-free
		 * problem in the next __sk_storage_lookup().
		 */
		raw_spin_lock_bh(&sk_storage->lock);
		if (selem_linked_to_sk(selem))
			rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
					   sdata);
		raw_spin_unlock_bh(&sk_storage->lock);
	}

	return sdata;
}

static struct bpf_sk_storage_data *
sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
	struct bpf_sk_storage *sk_storage;
	struct bpf_sk_storage_map *smap;

	sk_storage = rcu_dereference(sk->sk_bpf_storage);
	if (!sk_storage)
		return NULL;

	smap = (struct bpf_sk_storage_map *)map;
	return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
}

static int check_flags(const struct bpf_sk_storage_data *old_sdata,
		       u64 map_flags)
{
	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
		/* elem already exists */
		return -EEXIST;

	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
		/* elem doesn't exist, cannot update it */
		return -ENOENT;

	return 0;
}

static int sk_storage_alloc(struct sock *sk,
			    struct bpf_sk_storage_map *smap,
			    struct bpf_sk_storage_elem *first_selem)
{
	struct bpf_sk_storage *prev_sk_storage, *sk_storage;
	int err;

	err = omem_charge(sk, sizeof(*sk_storage));
	if (err)
		return err;

	sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
	if (!sk_storage) {
		err = -ENOMEM;
		goto uncharge;
	}
	INIT_HLIST_HEAD(&sk_storage->list);
	raw_spin_lock_init(&sk_storage->lock);
	sk_storage->sk = sk;

	__selem_link_sk(sk_storage, first_selem);
	selem_link_map(smap, first_selem);
	/* Publish sk_storage to sk.  sk->sk_lock cannot be acquired.
	 * Hence, atomic ops is used to set sk->sk_bpf_storage
	 * from NULL to the newly allocated sk_storage ptr.
	 *
	 * From now on, the sk->sk_bpf_storage pointer is protected
	 * by the sk_storage->lock.  Hence,  when freeing
	 * the sk->sk_bpf_storage, the sk_storage->lock must
	 * be held before setting sk->sk_bpf_storage to NULL.
	 */
	prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
				  NULL, sk_storage);
	if (unlikely(prev_sk_storage)) {
		selem_unlink_map(first_selem);
		err = -EAGAIN;
		goto uncharge;

		/* Note that even first_selem was linked to smap's
		 * bucket->list, first_selem can be freed immediately
		 * (instead of kfree_rcu) because
		 * bpf_sk_storage_map_free() does a
		 * synchronize_rcu() before walking the bucket->list.
		 * Hence, no one is accessing selem from the
		 * bucket->list under rcu_read_lock().
		 */
	}

	return 0;

uncharge:
	kfree(sk_storage);
	atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
	return err;
}

/* sk cannot be going away because it is linking new elem
 * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
 * Otherwise, it will become a leak (and other memory issues
 * during map destruction).
 */
static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
						     struct bpf_map *map,
						     void *value,
						     u64 map_flags)
{
	struct bpf_sk_storage_data *old_sdata = NULL;
	struct bpf_sk_storage_elem *selem;
	struct bpf_sk_storage *sk_storage;
	struct bpf_sk_storage_map *smap;
	int err;

	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
	    /* BPF_F_LOCK can only be used in a value with spin_lock */
	    unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
		return ERR_PTR(-EINVAL);

	smap = (struct bpf_sk_storage_map *)map;
	sk_storage = rcu_dereference(sk->sk_bpf_storage);
	if (!sk_storage || hlist_empty(&sk_storage->list)) {
		/* Very first elem for this sk */
		err = check_flags(NULL, map_flags);
		if (err)
			return ERR_PTR(err);

		selem = selem_alloc(smap, sk, value, true);
		if (!selem)
			return ERR_PTR(-ENOMEM);

		err = sk_storage_alloc(sk, smap, selem);
		if (err) {
			kfree(selem);
			atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
			return ERR_PTR(err);
		}

		return SDATA(selem);
	}

	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
		/* Hoping to find an old_sdata to do inline update
		 * such that it can avoid taking the sk_storage->lock
		 * and changing the lists.
		 */
		old_sdata = __sk_storage_lookup(sk_storage, smap, false);
		err = check_flags(old_sdata, map_flags);
		if (err)
			return ERR_PTR(err);
		if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
			copy_map_value_locked(map, old_sdata->data,
					      value, false);
			return old_sdata;
		}
	}

	raw_spin_lock_bh(&sk_storage->lock);

	/* Recheck sk_storage->list under sk_storage->lock */
	if (unlikely(hlist_empty(&sk_storage->list))) {
		/* A parallel del is happening and sk_storage is going
		 * away.  It has just been checked before, so very
		 * unlikely.  Return instead of retry to keep things
		 * simple.
		 */
		err = -EAGAIN;
		goto unlock_err;
	}

	old_sdata = __sk_storage_lookup(sk_storage, smap, false);
	err = check_flags(old_sdata, map_flags);
	if (err)
		goto unlock_err;

	if (old_sdata && (map_flags & BPF_F_LOCK)) {
		copy_map_value_locked(map, old_sdata->data, value, false);
		selem = SELEM(old_sdata);
		goto unlock;
	}

	/* sk_storage->lock is held.  Hence, we are sure
	 * we can unlink and uncharge the old_sdata successfully
	 * later.  Hence, instead of charging the new selem now
	 * and then uncharge the old selem later (which may cause
	 * a potential but unnecessary charge failure),  avoid taking
	 * a charge at all here (the "!old_sdata" check) and the
	 * old_sdata will not be uncharged later during __selem_unlink_sk().
	 */
	selem = selem_alloc(smap, sk, value, !old_sdata);
	if (!selem) {
		err = -ENOMEM;
		goto unlock_err;
	}

	/* First, link the new selem to the map */
	selem_link_map(smap, selem);

	/* Second, link (and publish) the new selem to sk_storage */
	__selem_link_sk(sk_storage, selem);

	/* Third, remove old selem, SELEM(old_sdata) */
	if (old_sdata) {
		selem_unlink_map(SELEM(old_sdata));
		__selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
	}

unlock:
	raw_spin_unlock_bh(&sk_storage->lock);
	return SDATA(selem);

unlock_err:
	raw_spin_unlock_bh(&sk_storage->lock);
	return ERR_PTR(err);
}

static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
{
	struct bpf_sk_storage_data *sdata;

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

	selem_unlink(SELEM(sdata));

	return 0;
}

/* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk)
{
	struct bpf_sk_storage_elem *selem;
	struct bpf_sk_storage *sk_storage;
	bool free_sk_storage = false;
	struct hlist_node *n;

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

	/* Netiher the bpf_prog nor the bpf-map's syscall
	 * could be modifying the sk_storage->list now.
	 * Thus, no elem can be added-to or deleted-from the
	 * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
	 *
	 * It is racing with bpf_sk_storage_map_free() alone
	 * when unlinking elem from the sk_storage->list and
	 * the map's bucket->list.
	 */
	raw_spin_lock_bh(&sk_storage->lock);
	hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) {
		/* Always unlink from map before unlinking from
		 * sk_storage.
		 */
		selem_unlink_map(selem);
		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
	}
	raw_spin_unlock_bh(&sk_storage->lock);
	rcu_read_unlock();

	if (free_sk_storage)
		kfree_rcu(sk_storage, rcu);
}

static void bpf_sk_storage_map_free(struct bpf_map *map)
{
	struct bpf_sk_storage_elem *selem;
	struct bpf_sk_storage_map *smap;
	struct bucket *b;
	unsigned int i;

	smap = (struct bpf_sk_storage_map *)map;

	/* Note that this map might be concurrently cloned from
	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
	 * RCU read section to finish before proceeding. New RCU
	 * read sections should be prevented via bpf_map_inc_not_zero.
	 */
	synchronize_rcu();

	/* bpf prog and the userspace can no longer access this map
	 * now.  No new selem (of this map) can be added
	 * to the sk->sk_bpf_storage or to the map bucket's list.
	 *
	 * The elem of this map can be cleaned up here
	 * or
	 * by bpf_sk_storage_free() during __sk_destruct().
	 */
	for (i = 0; i < (1U << smap->bucket_log); i++) {
		b = &smap->buckets[i];

		rcu_read_lock();
		/* No one is adding to b->list now */
		while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
						 struct bpf_sk_storage_elem,
						 map_node))) {
			selem_unlink(selem);
			cond_resched_rcu();
		}
		rcu_read_unlock();
	}

	/* bpf_sk_storage_free() may still need to access the map.
	 * e.g. bpf_sk_storage_free() has unlinked selem from the map
	 * which then made the above while((selem = ...)) loop
	 * exited immediately.
	 *
	 * However, the bpf_sk_storage_free() still needs to access
	 * the smap->elem_size to do the uncharging in
	 * __selem_unlink_sk().
	 *
	 * Hence, wait another rcu grace period for the
	 * bpf_sk_storage_free() to finish.
	 */
	synchronize_rcu();

	kvfree(smap->buckets);
	kfree(map);
}

/* U16_MAX is much more than enough for sk local storage
 * considering a tcp_sock is ~2k.
 */
#define MAX_VALUE_SIZE							\
	min_t(u32,							\
	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
	      (U16_MAX - sizeof(struct bpf_sk_storage_elem)))

static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
{
	if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
	    attr->max_entries ||
	    attr->key_size != sizeof(int) || !attr->value_size ||
	    /* Enforce BTF for userspace sk dumping */
	    !attr->btf_key_type_id || !attr->btf_value_type_id)
		return -EINVAL;

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

	if (attr->value_size > MAX_VALUE_SIZE)
		return -E2BIG;

	return 0;
}

static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
{
	struct bpf_sk_storage_map *smap;
	unsigned int i;
	u32 nbuckets;
	u64 cost;
	int ret;

	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
	if (!smap)
		return ERR_PTR(-ENOMEM);
	bpf_map_init_from_attr(&smap->map, attr);

	nbuckets = roundup_pow_of_two(num_possible_cpus());
	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
	nbuckets = max_t(u32, 2, nbuckets);
	smap->bucket_log = ilog2(nbuckets);
	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);

	ret = bpf_map_charge_init(&smap->map.memory, cost);
	if (ret < 0) {
		kfree(smap);
		return ERR_PTR(ret);
	}

	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
				 GFP_USER | __GFP_NOWARN);
	if (!smap->buckets) {
		bpf_map_charge_finish(&smap->map.memory);
		kfree(smap);
		return ERR_PTR(-ENOMEM);
	}

	for (i = 0; i < nbuckets; i++) {
		INIT_HLIST_HEAD(&smap->buckets[i].list);
		raw_spin_lock_init(&smap->buckets[i].lock);
	}

	smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
	smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) %
		BPF_SK_STORAGE_CACHE_SIZE;

	return &smap->map;
}

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

static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
					const struct btf *btf,
					const struct btf_type *key_type,
					const struct btf_type *value_type)
{
	u32 int_data;

	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
		return -EINVAL;

	int_data = *(u32 *)(key_type + 1);
	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
		return -EINVAL;

	return 0;
}

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

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

	return ERR_PTR(err);
}

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

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

	return err;
}

static int 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 = sk_storage_delete(sock->sk, map);
		sockfd_put(sock);
		return err;
	}

	return err;
}

static struct bpf_sk_storage_elem *
bpf_sk_storage_clone_elem(struct sock *newsk,
			  struct bpf_sk_storage_map *smap,
			  struct bpf_sk_storage_elem *selem)
{
	struct bpf_sk_storage_elem *copy_selem;

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

	if (map_value_has_spin_lock(&smap->map))
		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_sk_storage *new_sk_storage = NULL;
	struct bpf_sk_storage *sk_storage;
	struct bpf_sk_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_sk_storage_elem *copy_selem;
		struct bpf_sk_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_sk_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) {
			selem_link_map(smap, copy_selem);
			__selem_link_sk(new_sk_storage, copy_selem);
		} else {
			ret = sk_storage_alloc(newsk, smap, copy_selem);
			if (ret) {
				kfree(copy_selem);
				atomic_sub(smap->elem_size,
					   &newsk->sk_omem_alloc);
				bpf_map_put(map);
				goto out;
			}

			new_sk_storage = rcu_dereference(copy_selem->sk_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;
}

BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
	   void *, value, u64, flags)
{
	struct bpf_sk_storage_data *sdata;

	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
		return (unsigned long)NULL;

	sdata = 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 = sk_storage_update(sk, map, value, BPF_NOEXIST);
		/* 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)
{
	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
		int err;

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

	return -ENOENT;
}

const struct bpf_map_ops sk_storage_map_ops = {
	.map_alloc_check = bpf_sk_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_sk_storage_map_check_btf,
};

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_SOCKET,
	.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_SOCKET,
};

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

	nla_for_each_nested(nla, nla_stgs, rem) {
		if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD)
			nr_maps++;
	}

	diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * 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_sk_storage_data *sdata, struct sk_buff *skb)
{
	struct nlattr *nla_stg, *nla_value;
	struct bpf_sk_storage_map *smap;

	/* It cannot exceed max nlattr's payload */
	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < 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 (map_value_has_spin_lock(&smap->map))
		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_sk_storage *sk_storage;
	struct bpf_sk_storage_elem *selem;
	struct bpf_sk_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_sk_storage *sk_storage;
	struct bpf_sk_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 = __sk_storage_lookup(sk_storage,
				(struct bpf_sk_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);