forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathslab_common.c
1472 lines (1262 loc) · 37.6 KB
/
slab_common.c
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
// SPDX-License-Identifier: GPL-2.0
/*
* Slab allocator functions that are independent of the allocator strategy
*
* (C) 2012 Christoph Lameter <[email protected]>
*/
#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;
if (s->usersize)
return 1;
/*
* 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;
s->useroffset = useroffset;
s->usersize = usersize;
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 (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->usersize)
pr_cont(" size %u", kp.kp_slab_cache->usersize);
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);
s->useroffset = useroffset;
s->usersize = usersize;
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
#define INIT_KMALLOC_INFO(__size, __short_size) \
{ \
.name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \
.name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__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 (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(_RET_IP_, 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(_RET_IP_, 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))) {