summaryrefslogtreecommitdiff
path: root/lib/stackdepot.c
blob: 4a7055a63d9f8a8a6723563fd8a30115653eea83 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Stack depot - a stack trace storage that avoids duplication.
 *
 * Internally, stack depot maintains a hash table of unique stacktraces. The
 * stack traces themselves are stored contiguously one after another in a set
 * of separate page allocations.
 *
 * Author: Alexander Potapenko <glider@google.com>
 * Copyright (C) 2016 Google, Inc.
 *
 * Based on the code by Dmitry Chernenkov.
 */

#define pr_fmt(fmt) "stackdepot: " fmt

#include <linux/debugfs.h>
#include <linux/gfp.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
#include <linux/kmsan.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/poison.h>
#include <linux/printk.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/stacktrace.h>
#include <linux/stackdepot.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/memblock.h>
#include <linux/kasan-enabled.h>

#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8)

#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */
#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER))
#define DEPOT_STACK_ALIGN 4
#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
			       STACK_DEPOT_EXTRA_BITS)
#define DEPOT_POOLS_CAP 8192
#define DEPOT_MAX_POOLS \
	(((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \
	 (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP)

/* Compact structure that stores a reference to a stack. */
union handle_parts {
	depot_stack_handle_t handle;
	struct {
		u32 pool_index	: DEPOT_POOL_INDEX_BITS;
		u32 offset	: DEPOT_OFFSET_BITS;
		u32 extra	: STACK_DEPOT_EXTRA_BITS;
	};
};

struct stack_record {
	struct list_head hash_list;	/* Links in the hash table */
	u32 hash;			/* Hash in hash table */
	u32 size;			/* Number of stored frames */
	union handle_parts handle;	/* Constant after initialization */
	refcount_t count;
	union {
		unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
		struct {
			/*
			 * An important invariant of the implementation is to
			 * only place a stack record onto the freelist iff its
			 * refcount is zero. Because stack records with a zero
			 * refcount are never considered as valid, it is safe to
			 * union @entries and freelist management state below.
			 * Conversely, as soon as an entry is off the freelist
			 * and its refcount becomes non-zero, the below must not
			 * be accessed until being placed back on the freelist.
			 */
			struct list_head free_list;	/* Links in the freelist */
			unsigned long rcu_state;	/* RCU cookie */
		};
	};
};

static bool stack_depot_disabled;
static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
static bool __stack_depot_early_init_passed __initdata;

/* Use one hash table bucket per 16 KB of memory. */
#define STACK_HASH_TABLE_SCALE 14
/* Limit the number of buckets between 4K and 1M. */
#define STACK_BUCKET_NUMBER_ORDER_MIN 12
#define STACK_BUCKET_NUMBER_ORDER_MAX 20
/* Initial seed for jhash2. */
#define STACK_HASH_SEED 0x9747b28c

/* Hash table of stored stack records. */
static struct list_head *stack_table;
/* Fixed order of the number of table buckets. Used when KASAN is enabled. */
static unsigned int stack_bucket_number_order;
/* Hash mask for indexing the table. */
static unsigned int stack_hash_mask;

/* Array of memory regions that store stack records. */
static void *stack_pools[DEPOT_MAX_POOLS];
/* Newly allocated pool that is not yet added to stack_pools. */
static void *new_pool;
/* Number of pools in stack_pools. */
static int pools_num;
/* Offset to the unused space in the currently used pool. */
static size_t pool_offset = DEPOT_POOL_SIZE;
/* Freelist of stack records within stack_pools. */
static LIST_HEAD(free_stacks);
/* The lock must be held when performing pool or freelist modifications. */
static DEFINE_RAW_SPINLOCK(pool_lock);

/* Statistics counters for debugfs. */
enum depot_counter_id {
	DEPOT_COUNTER_REFD_ALLOCS,
	DEPOT_COUNTER_REFD_FREES,
	DEPOT_COUNTER_REFD_INUSE,
	DEPOT_COUNTER_FREELIST_SIZE,
	DEPOT_COUNTER_PERSIST_COUNT,
	DEPOT_COUNTER_PERSIST_BYTES,
	DEPOT_COUNTER_COUNT,
};
static long counters[DEPOT_COUNTER_COUNT];
static const char *const counter_names[] = {
	[DEPOT_COUNTER_REFD_ALLOCS]	= "refcounted_allocations",
	[DEPOT_COUNTER_REFD_FREES]	= "refcounted_frees",
	[DEPOT_COUNTER_REFD_INUSE]	= "refcounted_in_use",
	[DEPOT_COUNTER_FREELIST_SIZE]	= "freelist_size",
	[DEPOT_COUNTER_PERSIST_COUNT]	= "persistent_count",
	[DEPOT_COUNTER_PERSIST_BYTES]	= "persistent_bytes",
};
static_assert(ARRAY_SIZE(counter_names) == DEPOT_COUNTER_COUNT);

static int __init disable_stack_depot(char *str)
{
	return kstrtobool(str, &stack_depot_disabled);
}
early_param("stack_depot_disable", disable_stack_depot);

void __init stack_depot_request_early_init(void)
{
	/* Too late to request early init now. */
	WARN_ON(__stack_depot_early_init_passed);

	__stack_depot_early_init_requested = true;
}

/* Initialize list_head's within the hash table. */
static void init_stack_table(unsigned long entries)
{
	unsigned long i;

	for (i = 0; i < entries; i++)
		INIT_LIST_HEAD(&stack_table[i]);
}

/* Allocates a hash table via memblock. Can only be used during early boot. */
int __init stack_depot_early_init(void)
{
	unsigned long entries = 0;

	/* This function must be called only once, from mm_init(). */
	if (WARN_ON(__stack_depot_early_init_passed))
		return 0;
	__stack_depot_early_init_passed = true;

	/*
	 * Print disabled message even if early init has not been requested:
	 * stack_depot_init() will not print one.
	 */
	if (stack_depot_disabled) {
		pr_info("disabled\n");
		return 0;
	}

	/*
	 * If KASAN is enabled, use the maximum order: KASAN is frequently used
	 * in fuzzing scenarios, which leads to a large number of different
	 * stack traces being stored in stack depot.
	 */
	if (kasan_enabled() && !stack_bucket_number_order)
		stack_bucket_number_order = STACK_BUCKET_NUMBER_ORDER_MAX;

	/*
	 * Check if early init has been requested after setting
	 * stack_bucket_number_order: stack_depot_init() uses its value.
	 */
	if (!__stack_depot_early_init_requested)
		return 0;

	/*
	 * If stack_bucket_number_order is not set, leave entries as 0 to rely
	 * on the automatic calculations performed by alloc_large_system_hash().
	 */
	if (stack_bucket_number_order)
		entries = 1UL << stack_bucket_number_order;
	pr_info("allocating hash table via alloc_large_system_hash\n");
	stack_table = alloc_large_system_hash("stackdepot",
						sizeof(struct list_head),
						entries,
						STACK_HASH_TABLE_SCALE,
						HASH_EARLY,
						NULL,
						&stack_hash_mask,
						1UL << STACK_BUCKET_NUMBER_ORDER_MIN,
						1UL << STACK_BUCKET_NUMBER_ORDER_MAX);
	if (!stack_table) {
		pr_err("hash table allocation failed, disabling\n");
		stack_depot_disabled = true;
		return -ENOMEM;
	}
	if (!entries) {
		/*
		 * Obtain the number of entries that was calculated by
		 * alloc_large_system_hash().
		 */
		entries = stack_hash_mask + 1;
	}
	init_stack_table(entries);

	return 0;
}

/* Allocates a hash table via kvcalloc. Can be used after boot. */
int stack_depot_init(void)
{
	static DEFINE_MUTEX(stack_depot_init_mutex);
	unsigned long entries;
	int ret = 0;

	mutex_lock(&stack_depot_init_mutex);

	if (stack_depot_disabled || stack_table)
		goto out_unlock;

	/*
	 * Similarly to stack_depot_early_init, use stack_bucket_number_order
	 * if assigned, and rely on automatic scaling otherwise.
	 */
	if (stack_bucket_number_order) {
		entries = 1UL << stack_bucket_number_order;
	} else {
		int scale = STACK_HASH_TABLE_SCALE;

		entries = nr_free_buffer_pages();
		entries = roundup_pow_of_two(entries);

		if (scale > PAGE_SHIFT)
			entries >>= (scale - PAGE_SHIFT);
		else
			entries <<= (PAGE_SHIFT - scale);
	}

	if (entries < 1UL << STACK_BUCKET_NUMBER_ORDER_MIN)
		entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MIN;
	if (entries > 1UL << STACK_BUCKET_NUMBER_ORDER_MAX)
		entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MAX;

	pr_info("allocating hash table of %lu entries via kvcalloc\n", entries);
	stack_table = kvcalloc(entries, sizeof(struct list_head), GFP_KERNEL);
	if (!stack_table) {
		pr_err("hash table allocation failed, disabling\n");
		stack_depot_disabled = true;
		ret = -ENOMEM;
		goto out_unlock;
	}
	stack_hash_mask = entries - 1;
	init_stack_table(entries);

out_unlock:
	mutex_unlock(&stack_depot_init_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(stack_depot_init);

/*
 * Initializes new stack pool, and updates the list of pools.
 */
static bool depot_init_pool(void **prealloc)
{
	lockdep_assert_held(&pool_lock);

	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
		/* Bail out if we reached the pool limit. */
		WARN_ON_ONCE(pools_num > DEPOT_MAX_POOLS); /* should never happen */
		WARN_ON_ONCE(!new_pool); /* to avoid unnecessary pre-allocation */
		WARN_ONCE(1, "Stack depot reached limit capacity");
		return false;
	}

	if (!new_pool && *prealloc) {
		/* We have preallocated memory, use it. */
		WRITE_ONCE(new_pool, *prealloc);
		*prealloc = NULL;
	}

	if (!new_pool)
		return false; /* new_pool and *prealloc are NULL */

	/* Save reference to the pool to be used by depot_fetch_stack(). */
	stack_pools[pools_num] = new_pool;

	/*
	 * Stack depot tries to keep an extra pool allocated even before it runs
	 * out of space in the currently used pool.
	 *
	 * To indicate that a new preallocation is needed new_pool is reset to
	 * NULL; do not reset to NULL if we have reached the maximum number of
	 * pools.
	 */
	if (pools_num < DEPOT_MAX_POOLS)
		WRITE_ONCE(new_pool, NULL);
	else
		WRITE_ONCE(new_pool, STACK_DEPOT_POISON);

	/* Pairs with concurrent READ_ONCE() in depot_fetch_stack(). */
	WRITE_ONCE(pools_num, pools_num + 1);
	ASSERT_EXCLUSIVE_WRITER(pools_num);

	pool_offset = 0;

	return true;
}

/* Keeps the preallocated memory to be used for a new stack depot pool. */
static void depot_keep_new_pool(void **prealloc)
{
	lockdep_assert_held(&pool_lock);

	/*
	 * If a new pool is already saved or the maximum number of
	 * pools is reached, do not use the preallocated memory.
	 */
	if (new_pool)
		return;

	WRITE_ONCE(new_pool, *prealloc);
	*prealloc = NULL;
}

/*
 * Try to initialize a new stack record from the current pool, a cached pool, or
 * the current pre-allocation.
 */
static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
{
	struct stack_record *stack;
	void *current_pool;
	u32 pool_index;

	lockdep_assert_held(&pool_lock);

	if (pool_offset + size > DEPOT_POOL_SIZE) {
		if (!depot_init_pool(prealloc))
			return NULL;
	}

	if (WARN_ON_ONCE(pools_num < 1))
		return NULL;
	pool_index = pools_num - 1;
	current_pool = stack_pools[pool_index];
	if (WARN_ON_ONCE(!current_pool))
		return NULL;

	stack = current_pool + pool_offset;

	/* Pre-initialize handle once. */
	stack->handle.pool_index = pool_index;
	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
	stack->handle.extra = 0;
	INIT_LIST_HEAD(&stack->hash_list);

	pool_offset += size;

	return stack;
}

/* Try to find next free usable entry from the freelist. */
static struct stack_record *depot_pop_free(void)
{
	struct stack_record *stack;

	lockdep_assert_held(&pool_lock);

	if (list_empty(&free_stacks))
		return NULL;

	/*
	 * We maintain the invariant that the elements in front are least
	 * recently used, and are therefore more likely to be associated with an
	 * RCU grace period in the past. Consequently it is sufficient to only
	 * check the first entry.
	 */
	stack = list_first_entry(&free_stacks, struct stack_record, free_list);
	if (!poll_state_synchronize_rcu(stack->rcu_state))
		return NULL;

	list_del(&stack->free_list);
	counters[DEPOT_COUNTER_FREELIST_SIZE]--;

	return stack;
}

static inline size_t depot_stack_record_size(struct stack_record *s, unsigned int nr_entries)
{
	const size_t used = flex_array_size(s, entries, nr_entries);
	const size_t unused = sizeof(s->entries) - used;

	WARN_ON_ONCE(sizeof(s->entries) < used);

	return ALIGN(sizeof(struct stack_record) - unused, 1 << DEPOT_STACK_ALIGN);
}

/* Allocates a new stack in a stack depot pool. */
static struct stack_record *
depot_alloc_stack(unsigned long *entries, unsigned int nr_entries, u32 hash, depot_flags_t flags, void **prealloc)
{
	struct stack_record *stack = NULL;
	size_t record_size;

	lockdep_assert_held(&pool_lock);

	/* This should already be checked by public API entry points. */
	if (WARN_ON_ONCE(!nr_entries))
		return NULL;

	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
	if (nr_entries > CONFIG_STACKDEPOT_MAX_FRAMES)
		nr_entries = CONFIG_STACKDEPOT_MAX_FRAMES;

	if (flags & STACK_DEPOT_FLAG_GET) {
		/*
		 * Evictable entries have to allocate the max. size so they may
		 * safely be re-used by differently sized allocations.
		 */
		record_size = depot_stack_record_size(stack, CONFIG_STACKDEPOT_MAX_FRAMES);
		stack = depot_pop_free();
	} else {
		record_size = depot_stack_record_size(stack, nr_entries);
	}

	if (!stack) {
		stack = depot_pop_free_pool(prealloc, record_size);
		if (!stack)
			return NULL;
	}

	/* Save the stack trace. */
	stack->hash = hash;
	stack->size = nr_entries;
	/* stack->handle is already filled in by depot_pop_free_pool(). */
	memcpy(stack->entries, entries, flex_array_size(stack, entries, nr_entries));

	if (flags & STACK_DEPOT_FLAG_GET) {
		refcount_set(&stack->count, 1);
		counters[DEPOT_COUNTER_REFD_ALLOCS]++;
		counters[DEPOT_COUNTER_REFD_INUSE]++;
	} else {
		/* Warn on attempts to switch to refcounting this entry. */
		refcount_set(&stack->count, REFCOUNT_SATURATED);
		counters[DEPOT_COUNTER_PERSIST_COUNT]++;
		counters[DEPOT_COUNTER_PERSIST_BYTES] += record_size;
	}

	/*
	 * Let KMSAN know the stored stack record is initialized. This shall
	 * prevent false positive reports if instrumented code accesses it.
	 */
	kmsan_unpoison_memory(stack, record_size);

	return stack;
}

static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
{
	const int pools_num_cached = READ_ONCE(pools_num);
	union handle_parts parts = { .handle = handle };
	void *pool;
	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
	struct stack_record *stack;

	lockdep_assert_not_held(&pool_lock);

	if (parts.pool_index > pools_num_cached) {
		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
		     parts.pool_index, pools_num_cached, handle);
		return NULL;
	}

	pool = stack_pools[parts.pool_index];
	if (WARN_ON(!pool))
		return NULL;

	stack = pool + offset;
	if (WARN_ON(!refcount_read(&stack->count)))
		return NULL;

	return stack;
}

/* Links stack into the freelist. */
static void depot_free_stack(struct stack_record *stack)
{
	unsigned long flags;

	lockdep_assert_not_held(&pool_lock);

	raw_spin_lock_irqsave(&pool_lock, flags);
	printk_deferred_enter();

	/*
	 * Remove the entry from the hash list. Concurrent list traversal may
	 * still observe the entry, but since the refcount is zero, this entry
	 * will no longer be considered as valid.
	 */
	list_del_rcu(&stack->hash_list);

	/*
	 * Due to being used from constrained contexts such as the allocators,
	 * NMI, or even RCU itself, stack depot cannot rely on primitives that
	 * would sleep (such as synchronize_rcu()) or recursively call into
	 * stack depot again (such as call_rcu()).
	 *
	 * Instead, get an RCU cookie, so that we can ensure this entry isn't
	 * moved onto another list until the next grace period, and concurrent
	 * RCU list traversal remains safe.
	 */
	stack->rcu_state = get_state_synchronize_rcu();

	/*
	 * Add the entry to the freelist tail, so that older entries are
	 * considered first - their RCU cookie is more likely to no longer be
	 * associated with the current grace period.
	 */
	list_add_tail(&stack->free_list, &free_stacks);

	counters[DEPOT_COUNTER_FREELIST_SIZE]++;
	counters[DEPOT_COUNTER_REFD_FREES]++;
	counters[DEPOT_COUNTER_REFD_INUSE]--;

	printk_deferred_exit();
	raw_spin_unlock_irqrestore(&pool_lock, flags);
}

/* Calculates the hash for a stack. */
static inline u32 hash_stack(unsigned long *entries, unsigned int size)
{
	return jhash2((u32 *)entries,
		      array_size(size,  sizeof(*entries)) / sizeof(u32),
		      STACK_HASH_SEED);
}

/*
 * Non-instrumented version of memcmp().
 * Does not check the lexicographical order, only the equality.
 */
static inline
int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
			unsigned int n)
{
	for ( ; n-- ; u1++, u2++) {
		if (*u1 != *u2)
			return 1;
	}
	return 0;
}

/* Finds a stack in a bucket of the hash table. */
static inline struct stack_record *find_stack(struct list_head *bucket,
					      unsigned long *entries, int size,
					      u32 hash, depot_flags_t flags)
{
	struct stack_record *stack, *ret = NULL;

	/*
	 * Stack depot may be used from instrumentation that instruments RCU or
	 * tracing itself; use variant that does not call into RCU and cannot be
	 * traced.
	 *
	 * Note: Such use cases must take care when using refcounting to evict
	 * unused entries, because the stack record free-then-reuse code paths
	 * do call into RCU.
	 */
	rcu_read_lock_sched_notrace();

	list_for_each_entry_rcu(stack, bucket, hash_list) {
		if (stack->hash != hash || stack->size != size)
			continue;

		/*
		 * This may race with depot_free_stack() accessing the freelist
		 * management state unioned with @entries. The refcount is zero
		 * in that case and the below refcount_inc_not_zero() will fail.
		 */
		if (data_race(stackdepot_memcmp(entries, stack->entries, size)))
			continue;

		/*
		 * Try to increment refcount. If this succeeds, the stack record
		 * is valid and has not yet been freed.
		 *
		 * If STACK_DEPOT_FLAG_GET is not used, it is undefined behavior
		 * to then call stack_depot_put() later, and we can assume that
		 * a stack record is never placed back on the freelist.
		 */
		if ((flags & STACK_DEPOT_FLAG_GET) && !refcount_inc_not_zero(&stack->count))
			continue;

		ret = stack;
		break;
	}

	rcu_read_unlock_sched_notrace();

	return ret;
}

depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
					    unsigned int nr_entries,
					    gfp_t alloc_flags,
					    depot_flags_t depot_flags)
{
	struct list_head *bucket;
	struct stack_record *found = NULL;
	depot_stack_handle_t handle = 0;
	struct page *page = NULL;
	void *prealloc = NULL;
	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
	unsigned long flags;
	u32 hash;

	if (WARN_ON(depot_flags & ~STACK_DEPOT_FLAGS_MASK))
		return 0;

	/*
	 * If this stack trace is from an interrupt, including anything before
	 * interrupt entry usually leads to unbounded stack depot growth.
	 *
	 * Since use of filter_irq_stacks() is a requirement to ensure stack
	 * depot can efficiently deduplicate interrupt stacks, always
	 * filter_irq_stacks() to simplify all callers' use of stack depot.
	 */
	nr_entries = filter_irq_stacks(entries, nr_entries);

	if (unlikely(nr_entries == 0) || stack_depot_disabled)
		return 0;

	hash = hash_stack(entries, nr_entries);
	bucket = &stack_table[hash & stack_hash_mask];

	/* Fast path: look the stack trace up without locking. */
	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
	if (found)
		goto exit;

	/*
	 * Allocate memory for a new pool if required now:
	 * we won't be able to do that under the lock.
	 */
	if (unlikely(can_alloc && !READ_ONCE(new_pool))) {
		/*
		 * Zero out zone modifiers, as we don't have specific zone
		 * requirements. Keep the flags related to allocation in atomic
		 * contexts and I/O.
		 */
		alloc_flags &= ~GFP_ZONEMASK;
		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL);
		alloc_flags |= __GFP_NOWARN;
		page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER);
		if (page)
			prealloc = page_address(page);
	}

	raw_spin_lock_irqsave(&pool_lock, flags);
	printk_deferred_enter();

	/* Try to find again, to avoid concurrently inserting duplicates. */
	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
	if (!found) {
		struct stack_record *new =
			depot_alloc_stack(entries, nr_entries, hash, depot_flags, &prealloc);

		if (new) {
			/*
			 * This releases the stack record into the bucket and
			 * makes it visible to readers in find_stack().
			 */
			list_add_rcu(&new->hash_list, bucket);
			found = new;
		}
	}

	if (prealloc) {
		/*
		 * Either stack depot already contains this stack trace, or
		 * depot_alloc_stack() did not consume the preallocated memory.
		 * Try to keep the preallocated memory for future.
		 */
		depot_keep_new_pool(&prealloc);
	}

	printk_deferred_exit();
	raw_spin_unlock_irqrestore(&pool_lock, flags);
exit:
	if (prealloc) {
		/* Stack depot didn't use this memory, free it. */
		free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER);
	}
	if (found)
		handle = found->handle.handle;
	return handle;
}
EXPORT_SYMBOL_GPL(stack_depot_save_flags);

depot_stack_handle_t stack_depot_save(unsigned long *entries,
				      unsigned int nr_entries,
				      gfp_t alloc_flags)
{
	return stack_depot_save_flags(entries, nr_entries, alloc_flags,
				      STACK_DEPOT_FLAG_CAN_ALLOC);
}
EXPORT_SYMBOL_GPL(stack_depot_save);

unsigned int stack_depot_fetch(depot_stack_handle_t handle,
			       unsigned long **entries)
{
	struct stack_record *stack;

	*entries = NULL;
	/*
	 * Let KMSAN know *entries is initialized. This shall prevent false
	 * positive reports if instrumented code accesses it.
	 */
	kmsan_unpoison_memory(entries, sizeof(*entries));

	if (!handle || stack_depot_disabled)
		return 0;

	stack = depot_fetch_stack(handle);
	/*
	 * Should never be NULL, otherwise this is a use-after-put (or just a
	 * corrupt handle).
	 */
	if (WARN(!stack, "corrupt handle or use after stack_depot_put()"))
		return 0;

	*entries = stack->entries;
	return stack->size;
}
EXPORT_SYMBOL_GPL(stack_depot_fetch);

void stack_depot_put(depot_stack_handle_t handle)
{
	struct stack_record *stack;

	if (!handle || stack_depot_disabled)
		return;

	stack = depot_fetch_stack(handle);
	/*
	 * Should always be able to find the stack record, otherwise this is an
	 * unbalanced put attempt (or corrupt handle).
	 */
	if (WARN(!stack, "corrupt handle or unbalanced stack_depot_put()"))
		return;

	if (refcount_dec_and_test(&stack->count))
		depot_free_stack(stack);
}
EXPORT_SYMBOL_GPL(stack_depot_put);

void stack_depot_print(depot_stack_handle_t stack)
{
	unsigned long *entries;
	unsigned int nr_entries;

	nr_entries = stack_depot_fetch(stack, &entries);
	if (nr_entries > 0)
		stack_trace_print(entries, nr_entries, 0);
}
EXPORT_SYMBOL_GPL(stack_depot_print);

int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size,
		       int spaces)
{
	unsigned long *entries;
	unsigned int nr_entries;

	nr_entries = stack_depot_fetch(handle, &entries);
	return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries,
						spaces) : 0;
}
EXPORT_SYMBOL_GPL(stack_depot_snprint);

depot_stack_handle_t __must_check stack_depot_set_extra_bits(
			depot_stack_handle_t handle, unsigned int extra_bits)
{
	union handle_parts parts = { .handle = handle };

	/* Don't set extra bits on empty handles. */
	if (!handle)
		return 0;

	parts.extra = extra_bits;
	return parts.handle;
}
EXPORT_SYMBOL(stack_depot_set_extra_bits);

unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
{
	union handle_parts parts = { .handle = handle };

	return parts.extra;
}
EXPORT_SYMBOL(stack_depot_get_extra_bits);

static int stats_show(struct seq_file *seq, void *v)
{
	/*
	 * data race ok: These are just statistics counters, and approximate
	 * statistics are ok for debugging.
	 */
	seq_printf(seq, "pools: %d\n", data_race(pools_num));
	for (int i = 0; i < DEPOT_COUNTER_COUNT; i++)
		seq_printf(seq, "%s: %ld\n", counter_names[i], data_race(counters[i]));

	return 0;
}
DEFINE_SHOW_ATTRIBUTE(stats);

static int depot_debugfs_init(void)
{
	struct dentry *dir;

	if (stack_depot_disabled)
		return 0;

	dir = debugfs_create_dir("stackdepot", NULL);
	debugfs_create_file("stats", 0444, dir, NULL, &stats_fops);
	return 0;
}
late_initcall(depot_debugfs_init);