summaryrefslogtreecommitdiffstats
path: root/mm/slab_common.c
blob: 1cba98acc486251705096ae84238156355a4d374 (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
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
// SPDX-License-Identifier: GPL-2.0
/*
 * Slab allocator functions that are independent of the allocator strategy
 *
 * (C) 2012 Christoph Lameter <cl@linux.com>
 */
#include <linux/slab.h>

#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/interrupt.h>
#include <linux/memory.h>
#include <linux/cache.h>
#include <linux/compiler.h>
#include <linux/kfence.h>
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>
#include <linux/kasan.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <linux/memcontrol.h>
#include <linux/stackdepot.h>

#include "internal.h"
#include "slab.h"

#define CREATE_TRACE_POINTS
#include <trace/events/kmem.h>

enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;

static LIST_HEAD(slab_caches_to_rcu_destroy);
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
		    slab_caches_to_rcu_destroy_workfn);

/*
 * Set of flags that will prevent slab merging
 */
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
		SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
		SLAB_FAILSLAB | kasan_never_merge())

#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
			 SLAB_CACHE_DMA32 | SLAB_ACCOUNT)

/*
 * Merge control. If this is set then no merging of slab caches will occur.
 */
static bool slab_nomerge = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT);

static int __init setup_slab_nomerge(char *str)
{
	slab_nomerge = true;
	return 1;
}

static int __init setup_slab_merge(char *str)
{
	slab_nomerge = false;
	return 1;
}

#ifdef CONFIG_SLUB
__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
__setup_param("slub_merge", slub_merge, setup_slab_merge, 0);
#endif

__setup("slab_nomerge", setup_slab_nomerge);
__setup("slab_merge", setup_slab_merge);

/*
 * Determine the size of a slab object
 */
unsigned int kmem_cache_size(struct kmem_cache *s)
{
	return s->object_size;
}
EXPORT_SYMBOL(kmem_cache_size);

#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(const char *name, unsigned int size)
{
	if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) {
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
	return 0;
}
#else
static inline int kmem_cache_sanity_check(const char *name, unsigned int size)
{
	return 0;
}
#endif

/*
 * Figure out what the alignment of the objects will be given a set of
 * flags, a user specified alignment and the size of the objects.
 */
static unsigned int calculate_alignment(slab_flags_t flags,
		unsigned int align, unsigned int size)
{
	/*
	 * If the user wants hardware cache aligned objects then follow that
	 * suggestion if the object is sufficiently large.
	 *
	 * The hardware cache alignment cannot override the specified
	 * alignment though. If that is greater then use it.
	 */
	if (flags & SLAB_HWCACHE_ALIGN) {
		unsigned int ralign;

		ralign = cache_line_size();
		while (size <= ralign / 2)
			ralign /= 2;
		align = max(align, ralign);
	}

	align = max(align, arch_slab_minalign());

	return ALIGN(align, sizeof(void *));
}

/*
 * Find a mergeable slab cache
 */
int slab_unmergeable(struct kmem_cache *s)
{
	if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
		return 1;

	if (s->ctor)
		return 1;

#ifdef CONFIG_HARDENED_USERCOPY
	if (s->usersize)
		return 1;
#endif

	/*
	 * We may have set a slab to be unmergeable during bootstrap.
	 */
	if (s->refcount < 0)
		return 1;

	return 0;
}

struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
		slab_flags_t flags, const char *name, void (*ctor)(void *))
{
	struct kmem_cache *s;

	if (slab_nomerge)
		return NULL;

	if (ctor)
		return NULL;

	size = ALIGN(size, sizeof(void *));
	align = calculate_alignment(flags, align, size);
	size = ALIGN(size, align);
	flags = kmem_cache_flags(size, flags, name);

	if (flags & SLAB_NEVER_MERGE)
		return NULL;

	list_for_each_entry_reverse(s, &slab_caches, list) {
		if (slab_unmergeable(s))
			continue;

		if (size > s->size)
			continue;

		if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
			continue;
		/*
		 * Check if alignment is compatible.
		 * Courtesy of Adrian Drzewiecki
		 */
		if ((s->size & ~(align - 1)) != s->size)
			continue;

		if (s->size - size >= sizeof(void *))
			continue;

		if (IS_ENABLED(CONFIG_SLAB) && align &&
			(align > s->align || s->align % align))
			continue;

		return s;
	}
	return NULL;
}

static struct kmem_cache *create_cache(const char *name,
		unsigned int object_size, unsigned int align,
		slab_flags_t flags, unsigned int useroffset,
		unsigned int usersize, void (*ctor)(void *),
		struct kmem_cache *root_cache)
{
	struct kmem_cache *s;
	int err;

	if (WARN_ON(useroffset + usersize > object_size))
		useroffset = usersize = 0;

	err = -ENOMEM;
	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
	if (!s)
		goto out;

	s->name = name;
	s->size = s->object_size = object_size;
	s->align = align;
	s->ctor = ctor;
#ifdef CONFIG_HARDENED_USERCOPY
	s->useroffset = useroffset;
	s->usersize = usersize;
#endif

	err = __kmem_cache_create(s, flags);
	if (err)
		goto out_free_cache;

	s->refcount = 1;
	list_add(&s->list, &slab_caches);
out:
	if (err)
		return ERR_PTR(err);
	return s;

out_free_cache:
	kmem_cache_free(kmem_cache, s);
	goto out;
}

/**
 * kmem_cache_create_usercopy - Create a cache with a region suitable
 * for copying to userspace
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @useroffset: Usercopy region offset
 * @usersize: Usercopy region size
 * @ctor: A constructor for the objects.
 *
 * Cannot be called within a interrupt, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 *
 * Return: a pointer to the cache on success, NULL on failure.
 */
struct kmem_cache *
kmem_cache_create_usercopy(const char *name,
		  unsigned int size, unsigned int align,
		  slab_flags_t flags,
		  unsigned int useroffset, unsigned int usersize,
		  void (*ctor)(void *))
{
	struct kmem_cache *s = NULL;
	const char *cache_name;
	int err;

#ifdef CONFIG_SLUB_DEBUG
	/*
	 * If no slub_debug was enabled globally, the static key is not yet
	 * enabled by setup_slub_debug(). Enable it if the cache is being
	 * created with any of the debugging flags passed explicitly.
	 * It's also possible that this is the first cache created with
	 * SLAB_STORE_USER and we should init stack_depot for it.
	 */
	if (flags & SLAB_DEBUG_FLAGS)
		static_branch_enable(&slub_debug_enabled);
	if (flags & SLAB_STORE_USER)
		stack_depot_init();
#endif

	mutex_lock(&slab_mutex);

	err = kmem_cache_sanity_check(name, size);
	if (err) {
		goto out_unlock;
	}

	/* Refuse requests with allocator specific flags */
	if (flags & ~SLAB_FLAGS_PERMITTED) {
		err = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Some allocators will constraint the set of valid flags to a subset
	 * of all flags. We expect them to define CACHE_CREATE_MASK in this
	 * case, and we'll just provide them with a sanitized version of the
	 * passed flags.
	 */
	flags &= CACHE_CREATE_MASK;

	/* Fail closed on bad usersize of useroffset values. */
	if (!IS_ENABLED(CONFIG_HARDENED_USERCOPY) ||
	    WARN_ON(!usersize && useroffset) ||
	    WARN_ON(size < usersize || size - usersize < useroffset))
		usersize = useroffset = 0;

	if (!usersize)
		s = __kmem_cache_alias(name, size, align, flags, ctor);
	if (s)
		goto out_unlock;

	cache_name = kstrdup_const(name, GFP_KERNEL);
	if (!cache_name) {
		err = -ENOMEM;
		goto out_unlock;
	}

	s = create_cache(cache_name, size,
			 calculate_alignment(flags, align, size),
			 flags, useroffset, usersize, ctor, NULL);
	if (IS_ERR(s)) {
		err = PTR_ERR(s);
		kfree_const(cache_name);
	}

out_unlock:
	mutex_unlock(&slab_mutex);

	if (err) {
		if (flags & SLAB_PANIC)
			panic("%s: Failed to create slab '%s'. Error %d\n",
				__func__, name, err);
		else {
			pr_warn("%s(%s) failed with error %d\n",
				__func__, name, err);
			dump_stack();
		}
		return NULL;
	}
	return s;
}
EXPORT_SYMBOL(kmem_cache_create_usercopy);

/**
 * kmem_cache_create - Create a cache.
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @ctor: A constructor for the objects.
 *
 * Cannot be called within a interrupt, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 *
 * Return: a pointer to the cache on success, NULL on failure.
 */
struct kmem_cache *
kmem_cache_create(const char *name, unsigned int size, unsigned int align,
		slab_flags_t flags, void (*ctor)(void *))
{
	return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
					  ctor);
}
EXPORT_SYMBOL(kmem_cache_create);

#ifdef SLAB_SUPPORTS_SYSFS
/*
 * For a given kmem_cache, kmem_cache_destroy() should only be called
 * once or there will be a use-after-free problem. The actual deletion
 * and release of the kobject does not need slab_mutex or cpu_hotplug_lock
 * protection. So they are now done without holding those locks.
 *
 * Note that there will be a slight delay in the deletion of sysfs files
 * if kmem_cache_release() is called indrectly from a work function.
 */
static void kmem_cache_release(struct kmem_cache *s)
{
	sysfs_slab_unlink(s);
	sysfs_slab_release(s);
}
#else
static void kmem_cache_release(struct kmem_cache *s)
{
	slab_kmem_cache_release(s);
}
#endif

static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
{
	LIST_HEAD(to_destroy);
	struct kmem_cache *s, *s2;

	/*
	 * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
	 * @slab_caches_to_rcu_destroy list.  The slab pages are freed
	 * through RCU and the associated kmem_cache are dereferenced
	 * while freeing the pages, so the kmem_caches should be freed only
	 * after the pending RCU operations are finished.  As rcu_barrier()
	 * is a pretty slow operation, we batch all pending destructions
	 * asynchronously.
	 */
	mutex_lock(&slab_mutex);
	list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy);
	mutex_unlock(&slab_mutex);

	if (list_empty(&to_destroy))
		return;

	rcu_barrier();

	list_for_each_entry_safe(s, s2, &to_destroy, list) {
		debugfs_slab_release(s);
		kfence_shutdown_cache(s);
		kmem_cache_release(s);
	}
}

static int shutdown_cache(struct kmem_cache *s)
{
	/* free asan quarantined objects */
	kasan_cache_shutdown(s);

	if (__kmem_cache_shutdown(s) != 0)
		return -EBUSY;

	list_del(&s->list);

	if (s->flags & SLAB_TYPESAFE_BY_RCU) {
		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
		schedule_work(&slab_caches_to_rcu_destroy_work);
	} else {
		kfence_shutdown_cache(s);
		debugfs_slab_release(s);
	}

	return 0;
}

void slab_kmem_cache_release(struct kmem_cache *s)
{
	__kmem_cache_release(s);
	kfree_const(s->name);
	kmem_cache_free(kmem_cache, s);
}

void kmem_cache_destroy(struct kmem_cache *s)
{
	int refcnt;
	bool rcu_set;

	if (unlikely(!s) || !kasan_check_byte(s))
		return;

	cpus_read_lock();
	mutex_lock(&slab_mutex);

	rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU;

	refcnt = --s->refcount;
	if (refcnt)
		goto out_unlock;

	WARN(shutdown_cache(s),
	     "%s %s: Slab cache still has objects when called from %pS",
	     __func__, s->name, (void *)_RET_IP_);
out_unlock:
	mutex_unlock(&slab_mutex);
	cpus_read_unlock();
	if (!refcnt && !rcu_set)
		kmem_cache_release(s);
}
EXPORT_SYMBOL(kmem_cache_destroy);

/**
 * kmem_cache_shrink - Shrink a cache.
 * @cachep: The cache to shrink.
 *
 * Releases as many slabs as possible for a cache.
 * To help debugging, a zero exit status indicates all slabs were released.
 *
 * Return: %0 if all slabs were released, non-zero otherwise
 */
int kmem_cache_shrink(struct kmem_cache *cachep)
{
	kasan_cache_shrink(cachep);

	return __kmem_cache_shrink(cachep);
}
EXPORT_SYMBOL(kmem_cache_shrink);

bool slab_is_available(void)
{
	return slab_state >= UP;
}

#ifdef CONFIG_PRINTK
/**
 * kmem_valid_obj - does the pointer reference a valid slab object?
 * @object: pointer to query.
 *
 * Return: %true if the pointer is to a not-yet-freed object from
 * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
 * is to an already-freed object, and %false otherwise.
 */
bool kmem_valid_obj(void *object)
{
	struct folio *folio;

	/* Some arches consider ZERO_SIZE_PTR to be a valid address. */
	if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
		return false;
	folio = virt_to_folio(object);
	return folio_test_slab(folio);
}
EXPORT_SYMBOL_GPL(kmem_valid_obj);

static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{
	if (__kfence_obj_info(kpp, object, slab))
		return;
	__kmem_obj_info(kpp, object, slab);
}

/**
 * kmem_dump_obj - Print available slab provenance information
 * @object: slab object for which to find provenance information.
 *
 * This function uses pr_cont(), so that the caller is expected to have
 * printed out whatever preamble is appropriate.  The provenance information
 * depends on the type of object and on how much debugging is enabled.
 * For a slab-cache object, the fact that it is a slab object is printed,
 * and, if available, the slab name, return address, and stack trace from
 * the allocation and last free path of that object.
 *
 * This function will splat if passed a pointer to a non-slab object.
 * If you are not sure what type of object you have, you should instead
 * use mem_dump_obj().
 */
void kmem_dump_obj(void *object)
{
	char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc";
	int i;
	struct slab *slab;
	unsigned long ptroffset;
	struct kmem_obj_info kp = { };

	if (WARN_ON_ONCE(!virt_addr_valid(object)))
		return;
	slab = virt_to_slab(object);
	if (WARN_ON_ONCE(!slab)) {
		pr_cont(" non-slab memory.\n");
		return;
	}
	kmem_obj_info(&kp, object, slab);
	if (kp.kp_slab_cache)
		pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name);
	else
		pr_cont(" slab%s", cp);
	if (is_kfence_address(object))
		pr_cont(" (kfence)");
	if (kp.kp_objp)
		pr_cont(" start %px", kp.kp_objp);
	if (kp.kp_data_offset)
		pr_cont(" data offset %lu", kp.kp_data_offset);
	if (kp.kp_objp) {
		ptroffset = ((char *)object - (char *)kp.kp_objp) - kp.kp_data_offset;
		pr_cont(" pointer offset %lu", ptroffset);
	}
	if (kp.kp_slab_cache && kp.kp_slab_cache->object_size)
		pr_cont(" size %u", kp.kp_slab_cache->object_size);
	if (kp.kp_ret)
		pr_cont(" allocated at %pS\n", kp.kp_ret);
	else
		pr_cont("\n");
	for (i = 0; i < ARRAY_SIZE(kp.kp_stack); i++) {
		if (!kp.kp_stack[i])
			break;
		pr_info("    %pS\n", kp.kp_stack[i]);
	}

	if (kp.kp_free_stack[0])
		pr_cont(" Free path:\n");

	for (i = 0; i < ARRAY_SIZE(kp.kp_free_stack); i++) {
		if (!kp.kp_free_stack[i])
			break;
		pr_info("    %pS\n", kp.kp_free_stack[i]);
	}

}
EXPORT_SYMBOL_GPL(kmem_dump_obj);
#endif

#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name,
		unsigned int size, slab_flags_t flags,
		unsigned int useroffset, unsigned int usersize)
{
	int err;
	unsigned int align = ARCH_KMALLOC_MINALIGN;

	s->name = name;
	s->size = s->object_size = size;

	/*
	 * For power of two sizes, guarantee natural alignment for kmalloc
	 * caches, regardless of SL*B debugging options.
	 */
	if (is_power_of_2(size))
		align = max(align, size);
	s->align = calculate_alignment(flags, align, size);

#ifdef CONFIG_HARDENED_USERCOPY
	s->useroffset = useroffset;
	s->usersize = usersize;
#endif

	err = __kmem_cache_create(s, flags);

	if (err)
		panic("Creation of kmalloc slab %s size=%u failed. Reason %d\n",
					name, size, err);

	s->refcount = -1;	/* Exempt from merging for now */
}

struct kmem_cache *__init create_kmalloc_cache(const char *name,
		unsigned int size, slab_flags_t flags,
		unsigned int useroffset, unsigned int usersize)
{
	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);

	if (!s)
		panic("Out of memory when creating slab %s\n", name);

	create_boot_cache(s, name, size, flags | SLAB_KMALLOC, useroffset,
								usersize);
	kasan_cache_create_kmalloc(s);
	list_add(&s->list, &slab_caches);
	s->refcount = 1;
	return s;
}

struct kmem_cache *
kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init =
{ /* initialization for https://bugs.llvm.org/show_bug.cgi?id=42570 */ };
EXPORT_SYMBOL(kmalloc_caches);

/*
 * Conversion table for small slabs sizes / 8 to the index in the
 * kmalloc array. This is necessary for slabs < 192 since we have non power
 * of two cache sizes there. The size of larger slabs can be determined using
 * fls.
 */
static u8 size_index[24] __ro_after_init = {
	3,	/* 8 */
	4,	/* 16 */
	5,	/* 24 */
	5,	/* 32 */
	6,	/* 40 */
	6,	/* 48 */
	6,	/* 56 */
	6,	/* 64 */
	1,	/* 72 */
	1,	/* 80 */
	1,	/* 88 */
	1,	/* 96 */
	7,	/* 104 */
	7,	/* 112 */
	7,	/* 120 */
	7,	/* 128 */
	2,	/* 136 */
	2,	/* 144 */
	2,	/* 152 */
	2,	/* 160 */
	2,	/* 168 */
	2,	/* 176 */
	2,	/* 184 */
	2	/* 192 */
};

static inline unsigned int size_index_elem(unsigned int bytes)
{
	return (bytes - 1) / 8;
}

/*
 * Find the kmem_cache structure that serves a given size of
 * allocation
 */
struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
{
	unsigned int index;

	if (size <= 192) {
		if (!size)
			return ZERO_SIZE_PTR;

		index = size_index[size_index_elem(size)];
	} else {
		if (WARN_ON_ONCE(size > KMALLOC_MAX_CACHE_SIZE))
			return NULL;
		index = fls(size - 1);
	}

	return kmalloc_caches[kmalloc_type(flags)][index];
}

size_t kmalloc_size_roundup(size_t size)
{
	struct kmem_cache *c;

	/* Short-circuit the 0 size case. */
	if (unlikely(size == 0))
		return 0;
	/* Short-circuit saturated "too-large" case. */
	if (unlikely(size == SIZE_MAX))
		return SIZE_MAX;
	/* Above the smaller buckets, size is a multiple of page size. */
	if (size > KMALLOC_MAX_CACHE_SIZE)
		return PAGE_SIZE << get_order(size);

	/* The flags don't matter since size_index is common to all. */
	c = kmalloc_slab(size, GFP_KERNEL);
	return c ? c->object_size : 0;
}
EXPORT_SYMBOL(kmalloc_size_roundup);

#ifdef CONFIG_ZONE_DMA
#define KMALLOC_DMA_NAME(sz)	.name[KMALLOC_DMA] = "dma-kmalloc-" #sz,
#else
#define KMALLOC_DMA_NAME(sz)
#endif

#ifdef CONFIG_MEMCG_KMEM
#define KMALLOC_CGROUP_NAME(sz)	.name[KMALLOC_CGROUP] = "kmalloc-cg-" #sz,
#else
#define KMALLOC_CGROUP_NAME(sz)
#endif

#ifndef CONFIG_SLUB_TINY
#define KMALLOC_RCL_NAME(sz)	.name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #sz,
#else
#define KMALLOC_RCL_NAME(sz)
#endif

#define INIT_KMALLOC_INFO(__size, __short_size)			\
{								\
	.name[KMALLOC_NORMAL]  = "kmalloc-" #__short_size,	\
	KMALLOC_RCL_NAME(__short_size)				\
	KMALLOC_CGROUP_NAME(__short_size)			\
	KMALLOC_DMA_NAME(__short_size)				\
	.size = __size,						\
}

/*
 * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time.
 * kmalloc_index() supports up to 2^21=2MB, so the final entry of the table is
 * kmalloc-2M.
 */
const struct kmalloc_info_struct kmalloc_info[] __initconst = {
	INIT_KMALLOC_INFO(0, 0),
	INIT_KMALLOC_INFO(96, 96),
	INIT_KMALLOC_INFO(192, 192),
	INIT_KMALLOC_INFO(8, 8),
	INIT_KMALLOC_INFO(16, 16),
	INIT_KMALLOC_INFO(32, 32),
	INIT_KMALLOC_INFO(64, 64),
	INIT_KMALLOC_INFO(128, 128),
	INIT_KMALLOC_INFO(256, 256),
	INIT_KMALLOC_INFO(512, 512),
	INIT_KMALLOC_INFO(1024, 1k),
	INIT_KMALLOC_INFO(2048, 2k),
	INIT_KMALLOC_INFO(4096, 4k),
	INIT_KMALLOC_INFO(8192, 8k),
	INIT_KMALLOC_INFO(16384, 16k),
	INIT_KMALLOC_INFO(32768, 32k),
	INIT_KMALLOC_INFO(65536, 64k),
	INIT_KMALLOC_INFO(131072, 128k),
	INIT_KMALLOC_INFO(262144, 256k),
	INIT_KMALLOC_INFO(524288, 512k),
	INIT_KMALLOC_INFO(1048576, 1M),
	INIT_KMALLOC_INFO(2097152, 2M)
};

/*
 * Patch up the size_index table if we have strange large alignment
 * requirements for the kmalloc array. This is only the case for
 * MIPS it seems. The standard arches will not generate any code here.
 *
 * Largest permitted alignment is 256 bytes due to the way we
 * handle the index determination for the smaller caches.
 *
 * Make sure that nothing crazy happens if someone starts tinkering
 * around with ARCH_KMALLOC_MINALIGN
 */
void __init setup_kmalloc_cache_index_table(void)
{
	unsigned int i;

	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
		!is_power_of_2(KMALLOC_MIN_SIZE));

	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
		unsigned int elem = size_index_elem(i);

		if (elem >= ARRAY_SIZE(size_index))
			break;
		size_index[elem] = KMALLOC_SHIFT_LOW;
	}

	if (KMALLOC_MIN_SIZE >= 64) {
		/*
		 * The 96 byte sized cache is not used if the alignment
		 * is 64 byte.
		 */
		for (i = 64 + 8; i <= 96; i += 8)
			size_index[size_index_elem(i)] = 7;

	}

	if (KMALLOC_MIN_SIZE >= 128) {
		/*
		 * The 192 byte sized cache is not used if the alignment
		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
		 * instead.
		 */
		for (i = 128 + 8; i <= 192; i += 8)
			size_index[size_index_elem(i)] = 8;
	}
}

static void __init
new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
{
	if ((KMALLOC_RECLAIM != KMALLOC_NORMAL) && (type == KMALLOC_RECLAIM)) {
		flags |= SLAB_RECLAIM_ACCOUNT;
	} else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) {
		if (mem_cgroup_kmem_disabled()) {
			kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx];
			return;
		}
		flags |= SLAB_ACCOUNT;
	} else if (IS_ENABLED(CONFIG_ZONE_DMA) && (type == KMALLOC_DMA)) {
		flags |= SLAB_CACHE_DMA;
	}

	kmalloc_caches[type][idx] = create_kmalloc_cache(
					kmalloc_info[idx].name[type],
					kmalloc_info[idx].size, flags, 0,
					kmalloc_info[idx].size);

	/*
	 * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for
	 * KMALLOC_NORMAL caches.
	 */
	if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_NORMAL))
		kmalloc_caches[type][idx]->refcount = -1;
}

/*
 * Create the kmalloc array. Some of the regular kmalloc arrays
 * may already have been created because they were needed to
 * enable allocations for slab creation.
 */
void __init create_kmalloc_caches(slab_flags_t flags)
{
	int i;
	enum kmalloc_cache_type type;

	/*
	 * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined
	 */
	for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) {
		for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
			if (!kmalloc_caches[type][i])
				new_kmalloc_cache(i, type, flags);

			/*
			 * Caches that are not of the two-to-the-power-of size.
			 * These have to be created immediately after the
			 * earlier power of two caches
			 */
			if (KMALLOC_MIN_SIZE <= 32 && i == 6 &&
					!kmalloc_caches[type][1])
				new_kmalloc_cache(1, type, flags);
			if (KMALLOC_MIN_SIZE <= 64 && i == 7 &&
					!kmalloc_caches[type][2])
				new_kmalloc_cache(2, type, flags);
		}
	}

	/* Kmalloc array is now usable */
	slab_state = UP;
}

void free_large_kmalloc(struct folio *folio, void *object)
{
	unsigned int order = folio_order(folio);

	if (WARN_ON_ONCE(order == 0))
		pr_warn_once("object pointer: 0x%p\n", object);

	kmemleak_free(object);
	kasan_kfree_large(object);
	kmsan_kfree_large(object);

	mod_lruvec_page_state(folio_page(folio, 0), NR_SLAB_UNRECLAIMABLE_B,
			      -(PAGE_SIZE << order));
	__free_pages(folio_page(folio, 0), order);
}

static void *__kmalloc_large_node(size_t size, gfp_t flags, int node);
static __always_inline
void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
	struct kmem_cache *s;
	void *ret;

	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
		ret = __kmalloc_large_node(size, flags, node);
		trace_kmalloc(caller, ret, size,
			      PAGE_SIZE << get_order(size), flags, node);
		return ret;
	}

	s = kmalloc_slab(size, flags);

	if (unlikely(ZERO_OR_NULL_PTR(s)))
		return s;

	ret = __kmem_cache_alloc_node(s, flags, node, size, caller);
	ret = kasan_kmalloc(s, ret, size, flags);
	trace_kmalloc(caller, ret, size, s->size, flags, node);
	return ret;
}

void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
	return __do_kmalloc_node(size, flags, node, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc_node);

void *__kmalloc(size_t size, gfp_t flags)
{
	return __do_kmalloc_node(size, flags, NUMA_NO_NODE, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc);

void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
				  int node, unsigned long caller)
{
	return __do_kmalloc_node(size, flags, node, caller);
}
EXPORT_SYMBOL(__kmalloc_node_track_caller);

/**
 * kfree - free previously allocated memory
 * @object: pointer returned by kmalloc.
 *
 * If @object is NULL, no operation is performed.
 *
 * Don't free memory not originally allocated by kmalloc()
 * or you will run into trouble.
 */
void kfree(const void *object)
{
	struct folio *folio;
	struct slab *slab;
	struct kmem_cache *s;

	trace_kfree(_RET_IP_, object);

	if (unlikely(ZERO_OR_NULL_PTR(object)))
		return;

	folio = virt_to_folio(object);
	if (unlikely(!folio_test_slab(folio))) {
		free_large_kmalloc(folio, (void *)object);
		return;
	}

	slab = folio_slab(folio);
	s = slab->slab_cache;
	__kmem_cache_free(s, (void *)object, _RET_IP_);
}
EXPORT_SYMBOL(kfree);

/**
 * __ksize -- Report full size of underlying allocation
 * @object: pointer to the object
 *
 * This should only be used internally to query the true size of allocations.
 * It is not meant to be a way to discover the usable size of an allocation
 * after the fact. Instead, use kmalloc_size_roundup(). Using memory beyond
 * the originally requested allocation size may trigger KASAN, UBSAN_BOUNDS,
 * and/or FORTIFY_SOURCE.
 *
 * Return: size of the actual memory used by @object in bytes
 */
size_t __ksize(const void *object)
{
	struct folio *folio;

	if (unlikely(object == ZERO_SIZE_PTR))
		return 0;

	folio = virt_to_folio(object);

	if (unlikely(!folio_test_slab(folio))) {
		if (WARN_ON(folio_size(folio) <= KMALLOC_MAX_CACHE_SIZE))
			return 0;
		if (WARN_ON(object != folio_address(folio)))
			return 0;
		return folio_size(folio);
	}

#ifdef CONFIG_SLUB_DEBUG
	skip_orig_size_check(folio_slab(folio)->slab_cache, object);
#endif

	return slab_ksize(folio_slab(folio)->slab_cache);
}

void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
	void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE,
					    size, _RET_IP_);

	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, NUMA_NO_NODE);

	ret = kasan_kmalloc(s, ret, size, gfpflags);
	return ret;
}
EXPORT_SYMBOL(kmalloc_trace);

void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
			 int node, size_t size)
{
	void *ret = __kmem_cache_alloc_node(s, gfpflags, node, size, _RET_IP_);

	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, node);

	ret = kasan_kmalloc(s, ret, size, gfpflags);
	return ret;
}
EXPORT_SYMBOL(kmalloc_node_trace);
#endif /* !CONFIG_SLOB */

gfp_t kmalloc_fix_flags(gfp_t flags)
{
	gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK;

	flags &= ~GFP_SLAB_BUG_MASK;
	pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n",
			invalid_mask, &invalid_mask, flags, &flags);
	dump_stack();

	return flags;
}

/*
 * To avoid unnecessary overhead, we pass through large allocation requests
 * directly to the page allocator. We use __GFP_COMP, because we will need to
 * know the allocation order to free the pages properly in kfree.
 */

static void *__kmalloc_large_node(size_t size, gfp_t flags, int node)
{
	struct page *page;
	void *ptr = NULL;
	unsigned int order = get_order(size);

	if (unlikely(flags & GFP_SLAB_BUG_MASK))
		flags = kmalloc_fix_flags(flags);

	flags |= __GFP_COMP;
	page = alloc_pages_node(node, flags, order);
	if (page) {
		ptr = page_address(page);
		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
				      PAGE_SIZE << order);
	}

	ptr = kasan_kmalloc_large(ptr, size, flags);
	/* As ptr might get tagged, call kmemleak hook after KASAN. */
	kmemleak_alloc(ptr, size, 1, flags);
	kmsan_kmalloc_large(ptr, size, flags);

	return ptr;
}

void *kmalloc_large(size_t size, gfp_t flags)
{
	void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE);

	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
		      flags, NUMA_NO_NODE);
	return ret;
}
EXPORT_SYMBOL(kmalloc_large);

void *kmalloc_large_node(size_t size, gfp_t flags, int node)
{
	void *ret = __kmalloc_large_node(size, flags, node);

	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size),
		      flags, node);
	return ret;
}
EXPORT_SYMBOL(kmalloc_large_node);

#ifdef CONFIG_SLAB_FREELIST_RANDOM
/* Randomize a generic freelist */
static void freelist_randomize(struct rnd_state *state, unsigned int *list,
			       unsigned int count)
{
	unsigned int rand;
	unsigned int i;

	for (i = 0; i < count; i++)
		list[i] = i;

	/* Fisher-Yates shuffle */
	for (i = count - 1; i > 0; i--) {
		rand = prandom_u32_state(state);
		rand %= (i + 1);
		swap(list[i], list[rand]);
	}
}

/* Create a random sequence per cache */
int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count,
				    gfp_t gfp)
{
	struct rnd_state state;

	if (count < 2 || cachep->random_seq)
		return 0;

	cachep->random_seq = kcalloc(count, sizeof(unsigned int), gfp);
	if (!cachep->random_seq)
		return -ENOMEM;

	/* Get best entropy at this stage of boot */
	prandom_seed_state(&state, get_random_long());

	freelist_randomize(&state, cachep->random_seq, count);
	return 0;
}

/* Destroy the per-cache random freelist sequence */
void cache_random_seq_destroy(struct kmem_cache *cachep)
{
	kfree(cachep->random_seq);
	cachep->random_seq = NULL;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */

#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
#ifdef CONFIG_SLAB
#define SLABINFO_RIGHTS (0600)
#else
#define SLABINFO_RIGHTS (0400)
#endif

static void print_slabinfo_header(struct seq_file *m)
{
	/*
	 * Output format version, so at least we can change it
	 * without _too_ many complaints.
	 */
#ifdef CONFIG_DEBUG_SLAB
	seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
#else
	seq_puts(m, "slabinfo - version: 2.1\n");
#endif
	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>");
	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
	seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
	seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
	seq_putc(m, '\n');
}

static void *slab_start(struct seq_file *m, loff_t *pos)
{
	mutex_lock(&slab_mutex);
	return seq_list_start(&slab_caches, *pos);
}

static void *slab_next(struct seq_file *m, void *p, loff_t *pos)
{
	return seq_list_next(p, &slab_caches, pos);
}

static void slab_stop(struct seq_file *m, void *p)
{
	mutex_unlock(&slab_mutex);
}

static void cache_show(struct kmem_cache *s, struct seq_file *m)
{
	struct slabinfo sinfo;

	memset(&sinfo, 0, sizeof(sinfo));
	get_slabinfo(s, &sinfo);

	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
		   s->name, sinfo.active_objs, sinfo.num_objs, s->size,
		   sinfo.objects_per_slab, (1 << sinfo.cache_order));

	seq_printf(m, " : tunables %4u %4u %4u",
		   sinfo.limit, sinfo.batchcount, sinfo.shared);
	seq_printf(m, " : slabdata %6lu %6lu %6lu",
		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
	slabinfo_show_stats(m, s);
	seq_putc(m, '\n');
}

static int slab_show(struct seq_file *m, void *p)
{
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);

	if (p == slab_caches.next)
		print_slabinfo_header(m);
	cache_show(s, m);
	return 0;
}

void dump_unreclaimable_slab(void)
{
	struct kmem_cache *s;
	struct slabinfo sinfo;

	/*
	 * Here acquiring slab_mutex is risky since we don't prefer to get
	 * sleep in oom path. But, without mutex hold, it may introduce a
	 * risk of crash.
	 * Use mutex_trylock to protect the list traverse, dump nothing
	 * without acquiring the mutex.
	 */
	if (!mutex_trylock(&slab_mutex)) {
		pr_warn("excessive unreclaimable slab but cannot dump stats\n");
		return;
	}

	pr_info("Unreclaimable slab info:\n");
	pr_info("Name                      Used          Total\n");

	list_for_each_entry(s, &slab_caches, list) {
		if (s->flags & SLAB_RECLAIM_ACCOUNT)
			continue;

		get_slabinfo(s, &sinfo);

		if (sinfo.num_objs > 0)
			pr_info("%-17s %10luKB %10luKB\n", s->name,
				(sinfo.active_objs * s->size) / 1024,
				(sinfo.num_objs * s->size) / 1024);
	}
	mutex_unlock(&slab_mutex);
}

/*
 * slabinfo_op - iterator that generates /proc/slabinfo
 *
 * Output layout:
 * cache-name
 * num-active-objs
 * total-objs
 * object size
 * num-active-slabs
 * total-slabs
 * num-pages-per-slab
 * + further values on SMP and with statistics enabled
 */
static const struct seq_operations slabinfo_op = {
	.start = slab_start,
	.next = slab_next,
	.stop = slab_stop,
	.show = slab_show,
};

static int slabinfo_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &slabinfo_op);
}

static const struct proc_ops slabinfo_proc_ops = {
	.proc_flags	= PROC_ENTRY_PERMANENT,
	.proc_open	= slabinfo_open,
	.proc_read	= seq_read,
	.proc_write	= slabinfo_write,
	.proc_lseek	= seq_lseek,
	.proc_release	= seq_release,
};

static int __init slab_proc_init(void)
{
	proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &slabinfo_proc_ops);
	return 0;
}
module_init(slab_proc_init);

#endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */

static __always_inline __realloc_size(2) void *
__do_krealloc(const void *p, size_t new_size, gfp_t flags)
{
	void *ret;
	size_t ks;

	/* Check for double-free before calling ksize. */
	if (likely(!ZERO_OR_NULL_PTR(p))) {
		if (!kasan_check_byte(p))
			return NULL;
		ks = ksize(p);
	} else
		ks = 0;

	/* If the object still fits, repoison it precisely. */
	if (ks >= new_size) {
		p = kasan_krealloc((void *)p, new_size, flags);
		return (void *)p;
	}

	ret = kmalloc_track_caller(new_size, flags);
	if (ret && p) {
		/* Disable KASAN checks as the object's redzone is accessed. */
		kasan_disable_current();
		memcpy(ret, kasan_reset_tag(p), ks);
		kasan_enable_current();
	}

	return ret;
}

/**
 * krealloc - reallocate memory. The contents will remain unchanged.
 * @p: object to reallocate memory for.
 * @new_size: how many bytes of memory are required.
 * @flags: the type of memory to allocate.
 *
 * The contents of the object pointed to are preserved up to the
 * lesser of the new and old sizes (__GFP_ZERO flag is effectively ignored).
 * If @p is %NULL, krealloc() behaves exactly like kmalloc().  If @new_size
 * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
 *
 * Return: pointer to the allocated memory or %NULL in case of error
 */
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
	void *ret;

	if (unlikely(!new_size)) {
		kfree(p);
		return ZERO_SIZE_PTR;
	}

	ret = __do_krealloc(p, new_size, flags);
	if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
		kfree(p);

	return ret;
}
EXPORT_SYMBOL(krealloc);

/**
 * kfree_sensitive - Clear sensitive information in memory before freeing
 * @p: object to free memory of
 *
 * The memory of the object @p points to is zeroed before freed.
 * If @p is %NULL, kfree_sensitive() does nothing.
 *
 * Note: this function zeroes the whole allocated buffer which can be a good
 * deal bigger than the requested buffer size passed to kmalloc(). So be
 * careful when using this function in performance sensitive code.
 */
void kfree_sensitive(const void *p)
{
	size_t ks;
	void *mem = (void *)p;

	ks = ksize(mem);
	if (ks) {
		kasan_unpoison_range(mem, ks);
		memzero_explicit(mem, ks);
	}
	kfree(mem);
}
EXPORT_SYMBOL(kfree_sensitive);

size_t ksize(const void *objp)
{
	/*
	 * We need to first check that the pointer to the object is valid.
	 * The KASAN report printed from ksize() is more useful, then when
	 * it's printed later when the behaviour could be undefined due to
	 * a potential use-after-free or double-free.
	 *
	 * We use kasan_check_byte(), which is supported for the hardware
	 * tag-based KASAN mode, unlike kasan_check_read/write().
	 *
	 * If the pointed to memory is invalid, we return 0 to avoid users of
	 * ksize() writing to and potentially corrupting the memory region.
	 *
	 * We want to perform the check before __ksize(), to avoid potentially
	 * crashing in __ksize() due to accessing invalid metadata.
	 */
	if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp))
		return 0;

	return kfence_ksize(objp) ?: __ksize(objp);
}
EXPORT_SYMBOL(ksize);

/* Tracepoints definitions. */
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
EXPORT_TRACEPOINT_SYMBOL(kfree);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);

int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
{
	if (__should_failslab(s, gfpflags))
		return -ENOMEM;
	return 0;
}
ALLOW_ERROR_INJECTION(should_failslab, ERRNO);