summaryrefslogtreecommitdiff
path: root/kernel/bpf/bpf_local_storage.c
blob: dab2ff4c99d95ccb06e9da2f439f41ca96a8b4b8 (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
// 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_ids.h>
#include <linux/bpf_local_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
#include <linux/rcupdate.h>
#include <linux/rcupdate_trace.h>
#include <linux/rcupdate_wait.h>

#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)

static struct bpf_local_storage_map_bucket *
select_bucket(struct bpf_local_storage_map *smap,
	      struct bpf_local_storage_elem *selem)
{
	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
}

static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
{
	struct bpf_map *map = &smap->map;

	if (!map->ops->map_local_storage_charge)
		return 0;

	return map->ops->map_local_storage_charge(smap, owner, size);
}

static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
			 u32 size)
{
	struct bpf_map *map = &smap->map;

	if (map->ops->map_local_storage_uncharge)
		map->ops->map_local_storage_uncharge(smap, owner, size);
}

static struct bpf_local_storage __rcu **
owner_storage(struct bpf_local_storage_map *smap, void *owner)
{
	struct bpf_map *map = &smap->map;

	return map->ops->map_owner_storage_ptr(owner);
}

static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem)
{
	return !hlist_unhashed_lockless(&selem->snode);
}

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

static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem)
{
	return !hlist_unhashed_lockless(&selem->map_node);
}

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

struct bpf_local_storage_elem *
bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
		void *value, bool charge_mem, gfp_t gfp_flags)
{
	struct bpf_local_storage_elem *selem;

	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
		return NULL;

	if (smap->bpf_ma) {
		migrate_disable();
		selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags);
		migrate_enable();
		if (selem)
			/* Keep the original bpf_map_kzalloc behavior
			 * before started using the bpf_mem_cache_alloc.
			 *
			 * No need to use zero_map_value. The bpf_selem_free()
			 * only does bpf_mem_cache_free when there is
			 * no other bpf prog is using the selem.
			 */
			memset(SDATA(selem)->data, 0, smap->map.value_size);
	} else {
		selem = bpf_map_kzalloc(&smap->map, smap->elem_size,
					gfp_flags | __GFP_NOWARN);
	}

	if (selem) {
		if (value)
			copy_map_value(&smap->map, SDATA(selem)->data, value);
		/* No need to call check_and_init_map_value as memory is zero init */
		return selem;
	}

	if (charge_mem)
		mem_uncharge(smap, owner, smap->elem_size);

	return NULL;
}

/* rcu tasks trace callback for bpf_ma == false */
static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
{
	struct bpf_local_storage *local_storage;

	/* If RCU Tasks Trace grace period implies RCU grace period, do
	 * kfree(), else do kfree_rcu().
	 */
	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
	if (rcu_trace_implies_rcu_gp())
		kfree(local_storage);
	else
		kfree_rcu(local_storage, rcu);
}

static void bpf_local_storage_free_rcu(struct rcu_head *rcu)
{
	struct bpf_local_storage *local_storage;

	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
	bpf_mem_cache_raw_free(local_storage);
}

static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
{
	if (rcu_trace_implies_rcu_gp())
		bpf_local_storage_free_rcu(rcu);
	else
		call_rcu(rcu, bpf_local_storage_free_rcu);
}

/* Handle bpf_ma == false */
static void __bpf_local_storage_free(struct bpf_local_storage *local_storage,
				     bool vanilla_rcu)
{
	if (vanilla_rcu)
		kfree_rcu(local_storage, rcu);
	else
		call_rcu_tasks_trace(&local_storage->rcu,
				     __bpf_local_storage_free_trace_rcu);
}

static void bpf_local_storage_free(struct bpf_local_storage *local_storage,
				   struct bpf_local_storage_map *smap,
				   bool bpf_ma, bool reuse_now)
{
	if (!bpf_ma) {
		__bpf_local_storage_free(local_storage, reuse_now);
		return;
	}

	if (!reuse_now) {
		call_rcu_tasks_trace(&local_storage->rcu,
				     bpf_local_storage_free_trace_rcu);
		return;
	}

	if (smap) {
		migrate_disable();
		bpf_mem_cache_free(&smap->storage_ma, local_storage);
		migrate_enable();
	} else {
		/* smap could be NULL if the selem that triggered
		 * this 'local_storage' creation had been long gone.
		 * In this case, directly do call_rcu().
		 */
		call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu);
	}
}

/* rcu tasks trace callback for bpf_ma == false */
static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
{
	struct bpf_local_storage_elem *selem;

	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
	if (rcu_trace_implies_rcu_gp())
		kfree(selem);
	else
		kfree_rcu(selem, rcu);
}

/* Handle bpf_ma == false */
static void __bpf_selem_free(struct bpf_local_storage_elem *selem,
			     bool vanilla_rcu)
{
	if (vanilla_rcu)
		kfree_rcu(selem, rcu);
	else
		call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu);
}

static void bpf_selem_free_rcu(struct rcu_head *rcu)
{
	struct bpf_local_storage_elem *selem;

	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
	bpf_mem_cache_raw_free(selem);
}

static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
{
	if (rcu_trace_implies_rcu_gp())
		bpf_selem_free_rcu(rcu);
	else
		call_rcu(rcu, bpf_selem_free_rcu);
}

void bpf_selem_free(struct bpf_local_storage_elem *selem,
		    struct bpf_local_storage_map *smap,
		    bool reuse_now)
{
	bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);

	if (!smap->bpf_ma) {
		__bpf_selem_free(selem, reuse_now);
		return;
	}

	if (!reuse_now) {
		call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu);
	} else {
		/* Instead of using the vanilla call_rcu(),
		 * bpf_mem_cache_free will be able to reuse selem
		 * immediately.
		 */
		migrate_disable();
		bpf_mem_cache_free(&smap->selem_ma, selem);
		migrate_enable();
	}
}

/* local_storage->lock must be held and selem->local_storage == local_storage.
 * The caller must ensure selem->smap is still valid to be
 * dereferenced for its smap->elem_size and smap->cache_idx.
 */
static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
					    struct bpf_local_storage_elem *selem,
					    bool uncharge_mem, bool reuse_now)
{
	struct bpf_local_storage_map *smap;
	bool free_local_storage;
	void *owner;

	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
	owner = local_storage->owner;

	/* All uncharging on the owner must be done first.
	 * The owner may be freed once the last selem is unlinked
	 * from local_storage.
	 */
	if (uncharge_mem)
		mem_uncharge(smap, owner, smap->elem_size);

	free_local_storage = hlist_is_singular_node(&selem->snode,
						    &local_storage->list);
	if (free_local_storage) {
		mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
		local_storage->owner = NULL;

		/* After this RCU_INIT, owner may be freed and cannot be used */
		RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);

		/* local_storage is not freed now.  local_storage->lock is
		 * still held and raw_spin_unlock_bh(&local_storage->lock)
		 * will be done by the caller.
		 *
		 * Although the unlock will be done under
		 * rcu_read_lock(),  it is more intuitive to
		 * read if the freeing of the storage is done
		 * after the raw_spin_unlock_bh(&local_storage->lock).
		 *
		 * Hence, a "bool free_local_storage" is returned
		 * to the caller which then calls then frees the storage after
		 * all the RCU grace periods have expired.
		 */
	}
	hlist_del_init_rcu(&selem->snode);
	if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
	    SDATA(selem))
		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);

	bpf_selem_free(selem, smap, reuse_now);

	if (rcu_access_pointer(local_storage->smap) == smap)
		RCU_INIT_POINTER(local_storage->smap, NULL);

	return free_local_storage;
}

static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage,
				 struct bpf_local_storage_map *storage_smap,
				 struct bpf_local_storage_elem *selem)
{

	struct bpf_local_storage_map *selem_smap;

	/* local_storage->smap may be NULL. If it is, get the bpf_ma
	 * from any selem in the local_storage->list. The bpf_ma of all
	 * local_storage and selem should have the same value
	 * for the same map type.
	 *
	 * If the local_storage->list is already empty, the caller will not
	 * care about the bpf_ma value also because the caller is not
	 * responsibile to free the local_storage.
	 */

	if (storage_smap)
		return storage_smap->bpf_ma;

	if (!selem) {
		struct hlist_node *n;

		n = rcu_dereference_check(hlist_first_rcu(&local_storage->list),
					  bpf_rcu_lock_held());
		if (!n)
			return false;

		selem = hlist_entry(n, struct bpf_local_storage_elem, snode);
	}
	selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());

	return selem_smap->bpf_ma;
}

static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem,
				     bool reuse_now)
{
	struct bpf_local_storage_map *storage_smap;
	struct bpf_local_storage *local_storage;
	bool bpf_ma, free_local_storage = false;
	unsigned long flags;

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

	local_storage = rcu_dereference_check(selem->local_storage,
					      bpf_rcu_lock_held());
	storage_smap = rcu_dereference_check(local_storage->smap,
					     bpf_rcu_lock_held());
	bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem);

	raw_spin_lock_irqsave(&local_storage->lock, flags);
	if (likely(selem_linked_to_storage(selem)))
		free_local_storage = bpf_selem_unlink_storage_nolock(
			local_storage, selem, true, reuse_now);
	raw_spin_unlock_irqrestore(&local_storage->lock, flags);

	if (free_local_storage)
		bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now);
}

void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
				   struct bpf_local_storage_elem *selem)
{
	RCU_INIT_POINTER(selem->local_storage, local_storage);
	hlist_add_head_rcu(&selem->snode, &local_storage->list);
}

static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
{
	struct bpf_local_storage_map *smap;
	struct bpf_local_storage_map_bucket *b;
	unsigned long flags;

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

	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
	b = select_bucket(smap, selem);
	raw_spin_lock_irqsave(&b->lock, flags);
	if (likely(selem_linked_to_map(selem)))
		hlist_del_init_rcu(&selem->map_node);
	raw_spin_unlock_irqrestore(&b->lock, flags);
}

void bpf_selem_link_map(struct bpf_local_storage_map *smap,
			struct bpf_local_storage_elem *selem)
{
	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
	unsigned long flags;

	raw_spin_lock_irqsave(&b->lock, flags);
	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
	hlist_add_head_rcu(&selem->map_node, &b->list);
	raw_spin_unlock_irqrestore(&b->lock, flags);
}

void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now)
{
	/* Always unlink from map before unlinking from local_storage
	 * because selem will be freed after successfully unlinked from
	 * the local_storage.
	 */
	bpf_selem_unlink_map(selem);
	bpf_selem_unlink_storage(selem, reuse_now);
}

/* If cacheit_lockit is false, this lookup function is lockless */
struct bpf_local_storage_data *
bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
			 struct bpf_local_storage_map *smap,
			 bool cacheit_lockit)
{
	struct bpf_local_storage_data *sdata;
	struct bpf_local_storage_elem *selem;

	/* Fast path (cache hit) */
	sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
				      bpf_rcu_lock_held());
	if (sdata && rcu_access_pointer(sdata->smap) == smap)
		return sdata;

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

	if (!selem)
		return NULL;

	sdata = SDATA(selem);
	if (cacheit_lockit) {
		unsigned long flags;

		/* 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 bpf_local_storage_lookup().
		 */
		raw_spin_lock_irqsave(&local_storage->lock, flags);
		if (selem_linked_to_storage(selem))
			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
					   sdata);
		raw_spin_unlock_irqrestore(&local_storage->lock, flags);
	}

	return sdata;
}

static int check_flags(const struct bpf_local_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;
}

int bpf_local_storage_alloc(void *owner,
			    struct bpf_local_storage_map *smap,
			    struct bpf_local_storage_elem *first_selem,
			    gfp_t gfp_flags)
{
	struct bpf_local_storage *prev_storage, *storage;
	struct bpf_local_storage **owner_storage_ptr;
	int err;

	err = mem_charge(smap, owner, sizeof(*storage));
	if (err)
		return err;

	if (smap->bpf_ma) {
		migrate_disable();
		storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags);
		migrate_enable();
	} else {
		storage = bpf_map_kzalloc(&smap->map, sizeof(*storage),
					  gfp_flags | __GFP_NOWARN);
	}

	if (!storage) {
		err = -ENOMEM;
		goto uncharge;
	}

	RCU_INIT_POINTER(storage->smap, smap);
	INIT_HLIST_HEAD(&storage->list);
	raw_spin_lock_init(&storage->lock);
	storage->owner = owner;

	bpf_selem_link_storage_nolock(storage, first_selem);
	bpf_selem_link_map(smap, first_selem);

	owner_storage_ptr =
		(struct bpf_local_storage **)owner_storage(smap, owner);
	/* Publish storage to the owner.
	 * Instead of using any lock of the kernel object (i.e. owner),
	 * cmpxchg will work with any kernel object regardless what
	 * the running context is, bh, irq...etc.
	 *
	 * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage)
	 * is protected by the storage->lock.  Hence, when freeing
	 * the owner->storage, the storage->lock must be held before
	 * setting owner->storage ptr to NULL.
	 */
	prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
	if (unlikely(prev_storage)) {
		bpf_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_local_storage_map_free() does a
		 * synchronize_rcu_mult (waiting for both sleepable and
		 * normal programs) before walking the bucket->list.
		 * Hence, no one is accessing selem from the
		 * bucket->list under rcu_read_lock().
		 */
	}

	return 0;

uncharge:
	bpf_local_storage_free(storage, smap, smap->bpf_ma, true);
	mem_uncharge(smap, owner, sizeof(*storage));
	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).
 */
struct bpf_local_storage_data *
bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
			 void *value, u64 map_flags, gfp_t gfp_flags)
{
	struct bpf_local_storage_data *old_sdata = NULL;
	struct bpf_local_storage_elem *selem = NULL;
	struct bpf_local_storage *local_storage;
	unsigned long flags;
	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) &&
		     !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)))
		return ERR_PTR(-EINVAL);

	if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST)
		return ERR_PTR(-EINVAL);

	local_storage = rcu_dereference_check(*owner_storage(smap, owner),
					      bpf_rcu_lock_held());
	if (!local_storage || hlist_empty(&local_storage->list)) {
		/* Very first elem for the owner */
		err = check_flags(NULL, map_flags);
		if (err)
			return ERR_PTR(err);

		selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
		if (!selem)
			return ERR_PTR(-ENOMEM);

		err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags);
		if (err) {
			bpf_selem_free(selem, smap, true);
			mem_uncharge(smap, owner, smap->elem_size);
			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 local_storage->lock
		 * and changing the lists.
		 */
		old_sdata =
			bpf_local_storage_lookup(local_storage, smap, false);
		err = check_flags(old_sdata, map_flags);
		if (err)
			return ERR_PTR(err);
		if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) {
			copy_map_value_locked(&smap->map, old_sdata->data,
					      value, false);
			return old_sdata;
		}
	}

	if (gfp_flags == GFP_KERNEL) {
		selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
		if (!selem)
			return ERR_PTR(-ENOMEM);
	}

	raw_spin_lock_irqsave(&local_storage->lock, flags);

	/* Recheck local_storage->list under local_storage->lock */
	if (unlikely(hlist_empty(&local_storage->list))) {
		/* A parallel del is happening and local_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 = bpf_local_storage_lookup(local_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(&smap->map, old_sdata->data, value,
				      false);
		selem = SELEM(old_sdata);
		goto unlock;
	}

	if (gfp_flags != GFP_KERNEL) {
		/* local_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
		 * bpf_selem_unlink_storage_nolock().
		 */
		selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags);
		if (!selem) {
			err = -ENOMEM;
			goto unlock_err;
		}
	}

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

	/* Second, link (and publish) the new selem to local_storage */
	bpf_selem_link_storage_nolock(local_storage, selem);

	/* Third, remove old selem, SELEM(old_sdata) */
	if (old_sdata) {
		bpf_selem_unlink_map(SELEM(old_sdata));
		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
						false, false);
	}

unlock:
	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
	return SDATA(selem);

unlock_err:
	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
	if (selem) {
		mem_uncharge(smap, owner, smap->elem_size);
		bpf_selem_free(selem, smap, true);
	}
	return ERR_PTR(err);
}

static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
{
	u64 min_usage = U64_MAX;
	u16 i, res = 0;

	spin_lock(&cache->idx_lock);

	for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
		if (cache->idx_usage_counts[i] < min_usage) {
			min_usage = cache->idx_usage_counts[i];
			res = i;

			/* Found a free cache_idx */
			if (!min_usage)
				break;
		}
	}
	cache->idx_usage_counts[res]++;

	spin_unlock(&cache->idx_lock);

	return res;
}

static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
					     u16 idx)
{
	spin_lock(&cache->idx_lock);
	cache->idx_usage_counts[idx]--;
	spin_unlock(&cache->idx_lock);
}

int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
{
	if (attr->map_flags & ~BPF_LOCAL_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 (!bpf_capable())
		return -EPERM;

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

	return 0;
}

int bpf_local_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;
}

void bpf_local_storage_destroy(struct bpf_local_storage *local_storage)
{
	struct bpf_local_storage_map *storage_smap;
	struct bpf_local_storage_elem *selem;
	bool bpf_ma, free_storage = false;
	struct hlist_node *n;
	unsigned long flags;

	storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held());
	bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL);

	/* Neither the bpf_prog nor the bpf_map's syscall
	 * could be modifying the local_storage->list now.
	 * Thus, no elem can be added to or deleted from the
	 * local_storage->list by the bpf_prog or by the bpf_map's syscall.
	 *
	 * It is racing with bpf_local_storage_map_free() alone
	 * when unlinking elem from the local_storage->list and
	 * the map's bucket->list.
	 */
	raw_spin_lock_irqsave(&local_storage->lock, flags);
	hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
		/* Always unlink from map before unlinking from
		 * local_storage.
		 */
		bpf_selem_unlink_map(selem);
		/* If local_storage list has only one element, the
		 * bpf_selem_unlink_storage_nolock() will return true.
		 * Otherwise, it will return false. The current loop iteration
		 * intends to remove all local storage. So the last iteration
		 * of the loop will set the free_cgroup_storage to true.
		 */
		free_storage = bpf_selem_unlink_storage_nolock(
			local_storage, selem, false, true);
	}
	raw_spin_unlock_irqrestore(&local_storage->lock, flags);

	if (free_storage)
		bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true);
}

u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map)
{
	struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map;
	u64 usage = sizeof(*smap);

	/* The dynamically callocated selems are not counted currently. */
	usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log);
	return usage;
}

/* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory.
 * A deadlock free allocator is useful for storage that the bpf prog can easily
 * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf.
 * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses
 * memory immediately. To be reuse-immediate safe, the owner destruction
 * code path needs to go through a rcu grace period before calling
 * bpf_local_storage_destroy().
 *
 * When bpf_ma == false, the kmalloc and kfree are used.
 */
struct bpf_map *
bpf_local_storage_map_alloc(union bpf_attr *attr,
			    struct bpf_local_storage_cache *cache,
			    bool bpf_ma)
{
	struct bpf_local_storage_map *smap;
	unsigned int i;
	u32 nbuckets;
	int err;

	smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE);
	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);

	smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets),
					 nbuckets, GFP_USER | __GFP_NOWARN);
	if (!smap->buckets) {
		err = -ENOMEM;
		goto free_smap;
	}

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

	smap->elem_size = offsetof(struct bpf_local_storage_elem,
				   sdata.data[attr->value_size]);

	smap->bpf_ma = bpf_ma;
	if (bpf_ma) {
		err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false);
		if (err)
			goto free_smap;

		err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false);
		if (err) {
			bpf_mem_alloc_destroy(&smap->selem_ma);
			goto free_smap;
		}
	}

	smap->cache_idx = bpf_local_storage_cache_idx_get(cache);
	return &smap->map;

free_smap:
	kvfree(smap->buckets);
	bpf_map_area_free(smap);
	return ERR_PTR(err);
}

void bpf_local_storage_map_free(struct bpf_map *map,
				struct bpf_local_storage_cache *cache,
				int __percpu *busy_counter)
{
	struct bpf_local_storage_map_bucket *b;
	struct bpf_local_storage_elem *selem;
	struct bpf_local_storage_map *smap;
	unsigned int i;

	smap = (struct bpf_local_storage_map *)map;
	bpf_local_storage_cache_idx_free(cache, smap->cache_idx);

	/* 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 owner->storage or to the map bucket's list.
	 *
	 * The elem of this map can be cleaned up here
	 * or when the storage is freed e.g.
	 * 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_local_storage_elem, map_node))) {
			if (busy_counter) {
				migrate_disable();
				this_cpu_inc(*busy_counter);
			}
			bpf_selem_unlink(selem, true);
			if (busy_counter) {
				this_cpu_dec(*busy_counter);
				migrate_enable();
			}
			cond_resched_rcu();
		}
		rcu_read_unlock();
	}

	/* While freeing the storage we may still need to access the map.
	 *
	 * e.g. when bpf_sk_storage_free() has unlinked selem from the map
	 * which then made the above while((selem = ...)) loop
	 * exit immediately.
	 *
	 * However, while freeing the storage one still needs to access the
	 * smap->elem_size to do the uncharging in
	 * bpf_selem_unlink_storage_nolock().
	 *
	 * Hence, wait another rcu grace period for the storage to be freed.
	 */
	synchronize_rcu();

	if (smap->bpf_ma) {
		bpf_mem_alloc_destroy(&smap->selem_ma);
		bpf_mem_alloc_destroy(&smap->storage_ma);
	}
	kvfree(smap->buckets);
	bpf_map_area_free(smap);
}