gitlab.arm.com will be in the maintainance mode on Wednesday June 29th 01:00 - 10:00 (UTC+1). Repositories is read only during the maintainance.

common.c 26.5 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2
3
4
5
6
7
8
9
10
11
12
13
14
15
/*
 * This file contains common generic and tag-based KASAN code.
 *
 * Copyright (c) 2014 Samsung Electronics Co., Ltd.
 * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
 *
 * Some code borrowed from https://github.com/xairy/kasan-prototype by
 *        Andrey Konovalov <andreyknvl@gmail.com>
 */

#include <linux/export.h>
#include <linux/init.h>
#include <linux/kasan.h>
#include <linux/kernel.h>
16
#include <linux/kfence.h>
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
#include <linux/kmemleak.h>
#include <linux/linkage.h>
#include <linux/memblock.h>
#include <linux/memory.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/printk.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/slab.h>
#include <linux/stacktrace.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
#include <linux/bug.h>

33
#include <asm/cacheflush.h>
34
35
#include <asm/tlbflush.h>

36
37
38
#include "kasan.h"
#include "../slab.h"

39
depot_stack_handle_t kasan_save_stack(gfp_t flags)
40
41
{
	unsigned long entries[KASAN_STACK_DEPTH];
42
	unsigned int nr_entries;
43

44
45
46
	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
	nr_entries = filter_irq_stacks(entries, nr_entries);
	return stack_depot_save(entries, nr_entries, flags);
47
48
}

49
void kasan_set_track(struct kasan_track *track, gfp_t flags)
50
51
{
	track->pid = current->pid;
52
	track->stack = kasan_save_stack(flags);
53
54
55
56
57
58
59
60
61
62
63
64
}

void kasan_enable_current(void)
{
	current->kasan_depth++;
}

void kasan_disable_current(void)
{
	current->kasan_depth--;
}

65
bool __kasan_check_read(const volatile void *p, unsigned int size)
66
{
67
	return check_memory_region((unsigned long)p, size, false, _RET_IP_);
68
}
69
EXPORT_SYMBOL(__kasan_check_read);
70

71
bool __kasan_check_write(const volatile void *p, unsigned int size)
72
{
73
	return check_memory_region((unsigned long)p, size, true, _RET_IP_);
74
}
75
EXPORT_SYMBOL(__kasan_check_write);
76
77
78
79

#undef memset
void *memset(void *addr, int c, size_t len)
{
80
81
	if (!check_memory_region((unsigned long)addr, len, true, _RET_IP_))
		return NULL;
82
83
84
85

	return __memset(addr, c, len);
}

86
#ifdef __HAVE_ARCH_MEMMOVE
87
88
89
#undef memmove
void *memmove(void *dest, const void *src, size_t len)
{
90
91
92
	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
		return NULL;
93
94
95

	return __memmove(dest, src, len);
}
96
#endif
97
98
99
100

#undef memcpy
void *memcpy(void *dest, const void *src, size_t len)
{
101
102
103
	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
		return NULL;
104
105
106
107
108
109
110
111
112
113
114
115

	return __memcpy(dest, src, len);
}

/*
 * Poisons the shadow memory for 'size' bytes starting from 'addr'.
 * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
 */
void kasan_poison_shadow(const void *address, size_t size, u8 value)
{
	void *shadow_start, *shadow_end;

116
117
118
119
120
121
122
	/*
	 * Perform shadow offset calculation based on untagged address, as
	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
	 * addresses to this function.
	 */
	address = reset_tag(address);

123
124
125
126
	/* Skip KFENCE memory if called explicitly outside of sl*b. */
	if (is_kfence_address(address))
		return;

127
128
129
130
131
132
133
134
	shadow_start = kasan_mem_to_shadow(address);
	shadow_end = kasan_mem_to_shadow(address + size);

	__memset(shadow_start, value, shadow_end - shadow_start);
}

void kasan_unpoison_shadow(const void *address, size_t size)
{
135
136
137
138
139
140
141
142
143
	u8 tag = get_tag(address);

	/*
	 * Perform shadow offset calculation based on untagged address, as
	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
	 * addresses to this function.
	 */
	address = reset_tag(address);

144
145
146
147
148
149
150
151
	/*
	 * Skip KFENCE memory if called explicitly outside of sl*b. Also note
	 * that calls to ksize(), where size is not a multiple of machine-word
	 * size, would otherwise poison the invalid portion of the word.
	 */
	if (is_kfence_address(address))
		return;

152
	kasan_poison_shadow(address, size, tag);
153
154
155

	if (size & KASAN_SHADOW_MASK) {
		u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size);
156
157
158
159
160

		if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
			*shadow = tag;
		else
			*shadow = size & KASAN_SHADOW_MASK;
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
	}
}

static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
{
	void *base = task_stack_page(task);
	size_t size = sp - base;

	kasan_unpoison_shadow(base, size);
}

/* Unpoison the entire stack for a task. */
void kasan_unpoison_task_stack(struct task_struct *task)
{
	__kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE);
}

/* Unpoison the stack for the current task beyond a watermark sp value. */
asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
{
	/*
	 * Calculate the task stack base address.  Avoid using 'current'
	 * because this function is called by early resume code which hasn't
	 * yet set up the percpu register (%gs).
	 */
	void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));

	kasan_unpoison_shadow(base, watermark - base);
}

void kasan_alloc_pages(struct page *page, unsigned int order)
{
193
194
195
	u8 tag;
	unsigned long i;

196
197
	if (unlikely(PageHighMem(page)))
		return;
198
199
200
201

	tag = random_tag();
	for (i = 0; i < (1 << order); i++)
		page_kasan_tag_set(page + i, tag);
202
	kasan_unpoison_shadow(page_address(page), PAGE_SIZE << order);
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
}

void kasan_free_pages(struct page *page, unsigned int order)
{
	if (likely(!PageHighMem(page)))
		kasan_poison_shadow(page_address(page),
				PAGE_SIZE << order,
				KASAN_FREE_PAGE);
}

/*
 * Adaptive redzone policy taken from the userspace AddressSanitizer runtime.
 * For larger allocations larger redzones are used.
 */
static inline unsigned int optimal_redzone(unsigned int object_size)
{
219
220
221
	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
		return 0;

222
223
224
225
226
227
228
229
230
231
232
233
234
235
	return
		object_size <= 64        - 16   ? 16 :
		object_size <= 128       - 32   ? 32 :
		object_size <= 512       - 64   ? 64 :
		object_size <= 4096      - 128  ? 128 :
		object_size <= (1 << 14) - 256  ? 256 :
		object_size <= (1 << 15) - 512  ? 512 :
		object_size <= (1 << 16) - 1024 ? 1024 : 2048;
}

void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
			slab_flags_t *flags)
{
	unsigned int orig_size = *size;
236
	unsigned int redzone_size;
237
238
239
240
241
242
243
	int redzone_adjust;

	/* Add alloc meta. */
	cache->kasan_info.alloc_meta_offset = *size;
	*size += sizeof(struct kasan_alloc_meta);

	/* Add free meta. */
244
245
246
	if (IS_ENABLED(CONFIG_KASAN_GENERIC) &&
	    (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor ||
	     cache->object_size < sizeof(struct kasan_free_meta))) {
247
248
249
250
		cache->kasan_info.free_meta_offset = *size;
		*size += sizeof(struct kasan_free_meta);
	}

251
252
	redzone_size = optimal_redzone(cache->object_size);
	redzone_adjust = redzone_size -	(*size - cache->object_size);
253
254
255
256
	if (redzone_adjust > 0)
		*size += redzone_adjust;

	*size = min_t(unsigned int, KMALLOC_MAX_SIZE,
257
			max(*size, cache->object_size + redzone_size));
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

	/*
	 * If the metadata doesn't fit, don't enable KASAN at all.
	 */
	if (*size <= cache->kasan_info.alloc_meta_offset ||
			*size <= cache->kasan_info.free_meta_offset) {
		cache->kasan_info.alloc_meta_offset = 0;
		cache->kasan_info.free_meta_offset = 0;
		*size = orig_size;
		return;
	}

	*flags |= SLAB_KASAN;
}

size_t kasan_metadata_size(struct kmem_cache *cache)
{
	return (cache->kasan_info.alloc_meta_offset ?
		sizeof(struct kasan_alloc_meta) : 0) +
		(cache->kasan_info.free_meta_offset ?
		sizeof(struct kasan_free_meta) : 0);
}

struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
					const void *object)
{
	return (void *)object + cache->kasan_info.alloc_meta_offset;
}

struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
				      const void *object)
{
	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
	return (void *)object + cache->kasan_info.free_meta_offset;
}

void kasan_poison_slab(struct page *page)
{
296
297
	unsigned long i;

298
	for (i = 0; i < compound_nr(page); i++)
299
		page_kasan_tag_reset(page + i);
300
	kasan_poison_shadow(page_address(page), page_size(page),
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
			KASAN_KMALLOC_REDZONE);
}

void kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
{
	kasan_unpoison_shadow(object, cache->object_size);
}

void kasan_poison_object_data(struct kmem_cache *cache, void *object)
{
	kasan_poison_shadow(object,
			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
			KASAN_KMALLOC_REDZONE);
}

316
/*
317
318
319
320
321
322
323
324
325
326
327
328
 * This function assigns a tag to an object considering the following:
 * 1. A cache might have a constructor, which might save a pointer to a slab
 *    object somewhere (e.g. in the object itself). We preassign a tag for
 *    each object in caches with constructors during slab creation and reuse
 *    the same tag each time a particular object is allocated.
 * 2. A cache might be SLAB_TYPESAFE_BY_RCU, which means objects can be
 *    accessed after being freed. We preassign tags for objects in these
 *    caches as well.
 * 3. For SLAB allocator we can't preassign tags randomly since the freelist
 *    is stored as an array of indexes instead of a linked list. Assign tags
 *    based on objects indexes, so that objects that are next to each other
 *    get different tags.
329
 */
330
static u8 assign_tag(struct kmem_cache *cache, const void *object,
331
			bool init, bool keep_tag)
332
{
333
334
335
336
337
338
339
	/*
	 * 1. When an object is kmalloc()'ed, two hooks are called:
	 *    kasan_slab_alloc() and kasan_kmalloc(). We assign the
	 *    tag only in the first one.
	 * 2. We reuse the same tag for krealloc'ed objects.
	 */
	if (keep_tag)
340
341
342
343
344
345
		return get_tag(object);

	/*
	 * If the cache neither has a constructor nor has SLAB_TYPESAFE_BY_RCU
	 * set, assign a tag when the object is being allocated (init == false).
	 */
346
	if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU))
347
		return init ? KASAN_TAG_KERNEL : random_tag();
348

349
	/* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */
350
#ifdef CONFIG_SLAB
351
	/* For SLAB assign tags based on the object index in the freelist. */
352
353
	return (u8)obj_to_index(cache, virt_to_page(object), (void *)object);
#else
354
355
356
357
358
	/*
	 * For SLUB assign a random tag during slab creation, otherwise reuse
	 * the already assigned tag.
	 */
	return init ? random_tag() : get_tag(object);
359
360
361
#endif
}

362
363
void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
						const void *object)
364
365
366
367
368
369
370
371
372
{
	struct kasan_alloc_meta *alloc_info;

	if (!(cache->flags & SLAB_KASAN))
		return (void *)object;

	alloc_info = get_alloc_info(cache, object);
	__memset(alloc_info, 0, sizeof(*alloc_info));

373
	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
374
375
		object = set_tag(object,
				assign_tag(cache, object, true, false));
376

377
378
379
	return (void *)object;
}

380
381
382
383
384
static inline bool shadow_invalid(u8 tag, s8 shadow_byte)
{
	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
		return shadow_byte < 0 ||
			shadow_byte >= KASAN_SHADOW_SCALE_SIZE;
385
386
387
388
389
390
391
392

	/* else CONFIG_KASAN_SW_TAGS: */
	if ((u8)shadow_byte == KASAN_TAG_INVALID)
		return true;
	if ((tag != KASAN_TAG_KERNEL) && (tag != (u8)shadow_byte))
		return true;

	return false;
393
394
}

395
396
397
398
static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
			      unsigned long ip, bool quarantine)
{
	s8 shadow_byte;
399
400
	u8 tag;
	void *tagged_object;
401
402
	unsigned long rounded_up_size;

403
404
405
406
	tag = get_tag(object);
	tagged_object = object;
	object = reset_tag(object);

407
408
409
	if (is_kfence_address(object))
		return false;

410
411
	if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) !=
	    object)) {
412
		kasan_report_invalid_free(tagged_object, ip);
413
414
415
416
417
418
419
420
		return true;
	}

	/* RCU slabs could be legally used after free within the RCU period */
	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
		return false;

	shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
421
422
	if (shadow_invalid(tag, shadow_byte)) {
		kasan_report_invalid_free(tagged_object, ip);
423
424
425
426
427
428
		return true;
	}

	rounded_up_size = round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE);
	kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);

429
430
	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine) ||
			unlikely(!(cache->flags & SLAB_KASAN)))
431
432
		return false;

433
434
	kasan_set_free_info(cache, object, tag);

435
	quarantine_put(get_free_info(cache, object), cache);
436
437

	return IS_ENABLED(CONFIG_KASAN_GENERIC);
438
439
440
441
442
443
444
}

bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
{
	return __kasan_slab_free(cache, object, ip, true);
}

445
static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
446
				size_t size, gfp_t flags, bool keep_tag)
447
448
449
{
	unsigned long redzone_start;
	unsigned long redzone_end;
450
	u8 tag = 0xff;
451
452
453
454
455
456
457

	if (gfpflags_allow_blocking(flags))
		quarantine_reduce();

	if (unlikely(object == NULL))
		return NULL;

458
459
460
	if (is_kfence_address(object))
		return (void *)object;

461
462
463
464
465
	redzone_start = round_up((unsigned long)(object + size),
				KASAN_SHADOW_SCALE_SIZE);
	redzone_end = round_up((unsigned long)object + cache->object_size,
				KASAN_SHADOW_SCALE_SIZE);

466
	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
467
		tag = assign_tag(cache, object, false, keep_tag);
468
469
470

	/* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */
	kasan_unpoison_shadow(set_tag(object, tag), size);
471
472
473
474
	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
		KASAN_KMALLOC_REDZONE);

	if (cache->flags & SLAB_KASAN)
475
		kasan_set_track(&get_alloc_info(cache, object)->alloc_track, flags);
476

477
	return set_tag(object, tag);
478
}
479

480
481
482
483
484
485
void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object,
					gfp_t flags)
{
	return __kasan_kmalloc(cache, object, cache->object_size, flags, false);
}

486
487
488
void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object,
				size_t size, gfp_t flags)
{
489
	return __kasan_kmalloc(cache, object, size, flags, true);
490
}
491
492
EXPORT_SYMBOL(kasan_kmalloc);

493
494
void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
						gfp_t flags)
495
496
497
498
499
500
501
502
503
504
505
506
507
508
{
	struct page *page;
	unsigned long redzone_start;
	unsigned long redzone_end;

	if (gfpflags_allow_blocking(flags))
		quarantine_reduce();

	if (unlikely(ptr == NULL))
		return NULL;

	page = virt_to_page(ptr);
	redzone_start = round_up((unsigned long)(ptr + size),
				KASAN_SHADOW_SCALE_SIZE);
509
	redzone_end = (unsigned long)ptr + page_size(page);
510
511
512
513
514
515
516
517

	kasan_unpoison_shadow(ptr, size);
	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
		KASAN_PAGE_REDZONE);

	return (void *)ptr;
}

518
void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags)
519
520
521
522
523
524
525
526
527
528
529
{
	struct page *page;

	if (unlikely(object == ZERO_SIZE_PTR))
		return (void *)object;

	page = virt_to_head_page(object);

	if (unlikely(!PageSlab(page)))
		return kasan_kmalloc_large(object, size, flags);
	else
530
531
		return __kasan_kmalloc(page->slab_cache, object, size,
						flags, true);
532
533
534
535
536
537
538
539
540
}

void kasan_poison_kfree(void *ptr, unsigned long ip)
{
	struct page *page;

	page = virt_to_head_page(ptr);

	if (unlikely(!PageSlab(page))) {
541
		if (ptr != page_address(page)) {
542
543
544
			kasan_report_invalid_free(ptr, ip);
			return;
		}
545
		kasan_poison_shadow(ptr, page_size(page), KASAN_FREE_PAGE);
546
547
548
549
550
551
552
	} else {
		__kasan_slab_free(page->slab_cache, ptr, ip, false);
	}
}

void kasan_kfree_large(void *ptr, unsigned long ip)
{
553
	if (ptr != page_address(virt_to_head_page(ptr)))
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
		kasan_report_invalid_free(ptr, ip);
	/* The object will be poisoned by page_alloc. */
}

#ifdef CONFIG_MEMORY_HOTPLUG
static bool shadow_mapped(unsigned long addr)
{
	pgd_t *pgd = pgd_offset_k(addr);
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (pgd_none(*pgd))
		return false;
	p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d))
		return false;
	pud = pud_offset(p4d, addr);
	if (pud_none(*pud))
		return false;

	/*
	 * We can't use pud_large() or pud_huge(), the first one is
	 * arch-specific, the last one depends on HUGETLB_PAGE.  So let's abuse
	 * pud_bad(), if pud is bad then it's bad because it's huge.
	 */
	if (pud_bad(*pud))
		return true;
	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return false;

	if (pmd_bad(*pmd))
		return true;
	pte = pte_offset_kernel(pmd, addr);
	return !pte_none(*pte);
}

static int __meminit kasan_mem_notifier(struct notifier_block *nb,
			unsigned long action, void *data)
{
	struct memory_notify *mem_data = data;
	unsigned long nr_shadow_pages, start_kaddr, shadow_start;
	unsigned long shadow_end, shadow_size;

	nr_shadow_pages = mem_data->nr_pages >> KASAN_SHADOW_SCALE_SHIFT;
	start_kaddr = (unsigned long)pfn_to_kaddr(mem_data->start_pfn);
	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)start_kaddr);
	shadow_size = nr_shadow_pages << PAGE_SHIFT;
	shadow_end = shadow_start + shadow_size;

	if (WARN_ON(mem_data->nr_pages % KASAN_SHADOW_SCALE_SIZE) ||
		WARN_ON(start_kaddr % (KASAN_SHADOW_SCALE_SIZE << PAGE_SHIFT)))
		return NOTIFY_BAD;

	switch (action) {
	case MEM_GOING_ONLINE: {
		void *ret;

		/*
		 * If shadow is mapped already than it must have been mapped
		 * during the boot. This could happen if we onlining previously
		 * offlined memory.
		 */
		if (shadow_mapped(shadow_start))
			return NOTIFY_OK;

		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
					shadow_end, GFP_KERNEL,
					PAGE_KERNEL, VM_NO_GUARD,
					pfn_to_nid(mem_data->start_pfn),
					__builtin_return_address(0));
		if (!ret)
			return NOTIFY_BAD;

		kmemleak_ignore(ret);
		return NOTIFY_OK;
	}
	case MEM_CANCEL_ONLINE:
	case MEM_OFFLINE: {
		struct vm_struct *vm;

		/*
		 * shadow_start was either mapped during boot by kasan_init()
		 * or during memory online by __vmalloc_node_range().
		 * In the latter case we can use vfree() to free shadow.
		 * Non-NULL result of the find_vm_area() will tell us if
		 * that was the second case.
		 *
		 * Currently it's not possible to free shadow mapped
		 * during boot by kasan_init(). It's because the code
		 * to do that hasn't been written yet. So we'll just
		 * leak the memory.
		 */
		vm = find_vm_area((void *)shadow_start);
		if (vm)
			vfree((void *)shadow_start);
	}
	}

	return NOTIFY_OK;
}

static int __init kasan_memhotplug_init(void)
{
	hotplug_memory_notifier(kasan_mem_notifier, 0);

	return 0;
}

core_initcall(kasan_memhotplug_init);
#endif
667
668

#ifdef CONFIG_KASAN_VMALLOC
Andrey Konovalov's avatar
Andrey Konovalov committed
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
static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
				      void *unused)
{
	unsigned long page;
	pte_t pte;

	if (likely(!pte_none(*ptep)))
		return 0;

	page = __get_free_page(GFP_KERNEL);
	if (!page)
		return -ENOMEM;

	memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE);
	pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL);

	spin_lock(&init_mm.page_table_lock);
	if (likely(pte_none(*ptep))) {
		set_pte_at(&init_mm, addr, ptep, pte);
		page = 0;
	}
	spin_unlock(&init_mm.page_table_lock);
	if (page)
		free_page(page);
	return 0;
}

697
int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
698
699
700
701
{
	unsigned long shadow_start, shadow_end;
	int ret;

702
703
704
705
	if (!is_vmalloc_or_module_addr((void *)addr))
		return 0;

	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr);
706
	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
707
	shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size);
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
	shadow_end = ALIGN(shadow_end, PAGE_SIZE);

	ret = apply_to_page_range(&init_mm, shadow_start,
				  shadow_end - shadow_start,
				  kasan_populate_vmalloc_pte, NULL);
	if (ret)
		return ret;

	flush_cache_vmap(shadow_start, shadow_end);

	/*
	 * We need to be careful about inter-cpu effects here. Consider:
	 *
	 *   CPU#0				  CPU#1
	 * WRITE_ONCE(p, vmalloc(100));		while (x = READ_ONCE(p)) ;
	 *					p[99] = 1;
	 *
	 * With compiler instrumentation, that ends up looking like this:
	 *
	 *   CPU#0				  CPU#1
	 * // vmalloc() allocates memory
	 * // let a = area->addr
	 * // we reach kasan_populate_vmalloc
	 * // and call kasan_unpoison_shadow:
	 * STORE shadow(a), unpoison_val
	 * ...
	 * STORE shadow(a+99), unpoison_val	x = LOAD p
	 * // rest of vmalloc process		<data dependency>
	 * STORE p, a				LOAD shadow(x+99)
	 *
	 * If there is no barrier between the end of unpoisioning the shadow
	 * and the store of the result to p, the stores could be committed
	 * in a different order by CPU#0, and CPU#1 could erroneously observe
	 * poison in the shadow.
	 *
	 * We need some sort of barrier between the stores.
	 *
	 * In the vmalloc() case, this is provided by a smp_wmb() in
	 * clear_vm_uninitialized_flag(). In the per-cpu allocator and in
	 * get_vm_area() and friends, the caller gets shadow allocated but
	 * doesn't have any pages mapped into the virtual address space that
	 * has been reserved. Mapping those pages in will involve taking and
	 * releasing a page-table lock, which will provide the barrier.
	 */

	return 0;
}

/*
 * Poison the shadow for a vmalloc region. Called as part of the
 * freeing process at the time the region is freed.
 */
760
void kasan_poison_vmalloc(const void *start, unsigned long size)
761
{
762
763
764
	if (!is_vmalloc_or_module_addr(start))
		return;

765
766
767
768
	size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
	kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID);
}

769
770
771
772
773
774
775
776
void kasan_unpoison_vmalloc(const void *start, unsigned long size)
{
	if (!is_vmalloc_or_module_addr(start))
		return;

	kasan_unpoison_shadow(start, size);
}

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
static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
					void *unused)
{
	unsigned long page;

	page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT);

	spin_lock(&init_mm.page_table_lock);

	if (likely(!pte_none(*ptep))) {
		pte_clear(&init_mm, addr, ptep);
		free_page(page);
	}
	spin_unlock(&init_mm.page_table_lock);

	return 0;
}

/*
 * Release the backing for the vmalloc region [start, end), which
 * lies within the free region [free_region_start, free_region_end).
 *
 * This can be run lazily, long after the region was freed. It runs
 * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap
 * infrastructure.
 *
 * How does this work?
 * -------------------
 *
 * We have a region that is page aligned, labelled as A.
 * That might not map onto the shadow in a way that is page-aligned:
 *
 *                    start                     end
 *                    v                         v
 * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc
 *  -------- -------- --------          -------- --------
 *      |        |       |                 |        |
 *      |        |       |         /-------/        |
 *      \-------\|/------/         |/---------------/
 *              |||                ||
 *             |??AAAAAA|AAAAAAAA|AA??????|                < shadow
 *                 (1)      (2)      (3)
 *
 * First we align the start upwards and the end downwards, so that the
 * shadow of the region aligns with shadow page boundaries. In the
 * example, this gives us the shadow page (2). This is the shadow entirely
 * covered by this allocation.
 *
 * Then we have the tricky bits. We want to know if we can free the
 * partially covered shadow pages - (1) and (3) in the example. For this,
 * we are given the start and end of the free region that contains this
 * allocation. Extending our previous example, we could have:
 *
 *  free_region_start                                    free_region_end
 *  |                 start                     end      |
 *  v                 v                         v        v
 * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc
 *  -------- -------- --------          -------- --------
 *      |        |       |                 |        |
 *      |        |       |         /-------/        |
 *      \-------\|/------/         |/---------------/
 *              |||                ||
 *             |FFAAAAAA|AAAAAAAA|AAF?????|                < shadow
 *                 (1)      (2)      (3)
 *
 * Once again, we align the start of the free region up, and the end of
 * the free region down so that the shadow is page aligned. So we can free
 * page (1) - we know no allocation currently uses anything in that page,
 * because all of it is in the vmalloc free region. But we cannot free
 * page (3), because we can't be sure that the rest of it is unused.
 *
 * We only consider pages that contain part of the original region for
 * freeing: we don't try to free other pages from the free region or we'd
 * end up trying to free huge chunks of virtual address space.
 *
 * Concurrency
 * -----------
 *
 * How do we know that we're not freeing a page that is simultaneously
 * being used for a fresh allocation in kasan_populate_vmalloc(_pte)?
 *
 * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running
 * at the same time. While we run under free_vmap_area_lock, the population
 * code does not.
 *
 * free_vmap_area_lock instead operates to ensure that the larger range
 * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and
 * the per-cpu region-finding algorithm both run under free_vmap_area_lock,
 * no space identified as free will become used while we are running. This
 * means that so long as we are careful with alignment and only free shadow
 * pages entirely covered by the free region, we will not run in to any
 * trouble - any simultaneous allocations will be for disjoint regions.
 */
void kasan_release_vmalloc(unsigned long start, unsigned long end,
			   unsigned long free_region_start,
			   unsigned long free_region_end)
{
	void *shadow_start, *shadow_end;
	unsigned long region_start, region_end;
876
	unsigned long size;
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898

	region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
	region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);

	free_region_start = ALIGN(free_region_start,
				  PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);

	if (start != region_start &&
	    free_region_start < region_start)
		region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;

	free_region_end = ALIGN_DOWN(free_region_end,
				     PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);

	if (end != region_end &&
	    free_region_end > region_end)
		region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;

	shadow_start = kasan_mem_to_shadow((void *)region_start);
	shadow_end = kasan_mem_to_shadow((void *)region_end);

	if (shadow_end > shadow_start) {
899
900
901
902
903
		size = shadow_end - shadow_start;
		apply_to_existing_page_range(&init_mm,
					     (unsigned long)shadow_start,
					     size, kasan_depopulate_vmalloc_pte,
					     NULL);
904
905
906
907
		flush_tlb_kernel_range((unsigned long)shadow_start,
				       (unsigned long)shadow_end);
	}
}
Andrey Konovalov's avatar
Andrey Konovalov committed
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

#else /* CONFIG_KASAN_VMALLOC */

int kasan_module_alloc(void *addr, size_t size)
{
	void *ret;
	size_t scaled_size;
	size_t shadow_size;
	unsigned long shadow_start;

	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
	shadow_size = round_up(scaled_size, PAGE_SIZE);

	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
		return -EINVAL;

	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
			shadow_start + shadow_size,
			GFP_KERNEL,
			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
			__builtin_return_address(0));

	if (ret) {
		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
		find_vm_area(addr)->flags |= VM_KASAN;
		kmemleak_ignore(ret);
		return 0;
	}

	return -ENOMEM;
}

void kasan_free_shadow(const struct vm_struct *vm)
{
	if (vm->flags & VM_KASAN)
		vfree(kasan_mem_to_shadow(vm->addr));
}

947
#endif