summaryrefslogtreecommitdiff
path: root/deps/jemalloc/include/jemalloc/internal/jemalloc_internal.h.in
blob: 0dd9995cfe7779f639b7d9fa216b7b83ed0ec99a (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
#include <sys/mman.h>
#include <sys/param.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/sysctl.h>
#include <sys/uio.h>

#include <errno.h>
#include <limits.h>
#ifndef SIZE_T_MAX
#  define SIZE_T_MAX	SIZE_MAX
#endif
#include <pthread.h>
#include <sched.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stddef.h>
#ifndef offsetof
#  define offsetof(type, member)	((size_t)&(((type *)NULL)->member))
#endif
#include <inttypes.h>
#include <string.h>
#include <strings.h>
#include <ctype.h>
#include <unistd.h>
#include <fcntl.h>
#include <pthread.h>
#include <math.h>

#define	JEMALLOC_MANGLE
#include "../jemalloc@install_suffix@.h"

#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN))
#include <libkern/OSAtomic.h>
#endif

#ifdef JEMALLOC_ZONE
#include <mach/mach_error.h>
#include <mach/mach_init.h>
#include <mach/vm_map.h>
#include <malloc/malloc.h>
#endif

#ifdef JEMALLOC_LAZY_LOCK
#include <dlfcn.h>
#endif

#define	RB_COMPACT
#include "jemalloc/internal/rb.h"
#include "jemalloc/internal/qr.h"
#include "jemalloc/internal/ql.h"

extern void	(*JEMALLOC_P(malloc_message))(void *wcbopaque, const char *s);

/*
 * Define a custom assert() in order to reduce the chances of deadlock during
 * assertion failure.
 */
#ifndef assert
#  ifdef JEMALLOC_DEBUG
#    define assert(e) do {						\
	if (!(e)) {							\
		char line_buf[UMAX2S_BUFSIZE];				\
		malloc_write("<jemalloc>: ");				\
		malloc_write(__FILE__);					\
		malloc_write(":");					\
		malloc_write(u2s(__LINE__, 10, line_buf));		\
		malloc_write(": Failed assertion: ");			\
		malloc_write("\"");					\
		malloc_write(#e);					\
		malloc_write("\"\n");					\
		abort();						\
	}								\
} while (0)
#  else
#    define assert(e)
#  endif
#endif

#ifdef JEMALLOC_DEBUG
#  define dassert(e) assert(e)
#else
#  define dassert(e)
#endif

/*
 * jemalloc can conceptually be broken into components (arena, tcache, etc.),
 * but there are circular dependencies that cannot be broken without
 * substantial performance degradation.  In order to reduce the effect on
 * visual code flow, read the header files in multiple passes, with one of the
 * following cpp variables defined during each pass:
 *
 *   JEMALLOC_H_TYPES   : Preprocessor-defined constants and psuedo-opaque data
 *                        types.
 *   JEMALLOC_H_STRUCTS : Data structures.
 *   JEMALLOC_H_EXTERNS : Extern data declarations and function prototypes.
 *   JEMALLOC_H_INLINES : Inline functions.
 */
/******************************************************************************/
#define JEMALLOC_H_TYPES

#define	ALLOCM_LG_ALIGN_MASK	((int)0x3f)

#define	ZU(z)	((size_t)z)

#ifndef __DECONST
#  define	__DECONST(type, var)	((type)(uintptr_t)(const void *)(var))
#endif

#ifdef JEMALLOC_DEBUG
   /* Disable inlining to make debugging easier. */
#  define JEMALLOC_INLINE
#  define inline
#else
#  define JEMALLOC_ENABLE_INLINE
#  define JEMALLOC_INLINE static inline
#endif

/* Size of stack-allocated buffer passed to buferror(). */
#define	BUFERROR_BUF		64

/* Minimum alignment of allocations is 2^LG_QUANTUM bytes. */
#ifdef __i386__
#  define LG_QUANTUM		4
#endif
#ifdef __ia64__
#  define LG_QUANTUM		4
#endif
#ifdef __alpha__
#  define LG_QUANTUM		4
#endif
#ifdef __sparc64__
#  define LG_QUANTUM		4
#endif
#if (defined(__amd64__) || defined(__x86_64__))
#  define LG_QUANTUM		4
#endif
#ifdef __arm__
#  define LG_QUANTUM		3
#endif
#ifdef __mips__
#  define LG_QUANTUM		3
#endif
#ifdef __powerpc__
#  define LG_QUANTUM		4
#endif
#ifdef __s390x__
#  define LG_QUANTUM		4
#endif

#define	QUANTUM			((size_t)(1U << LG_QUANTUM))
#define	QUANTUM_MASK		(QUANTUM - 1)

/* Return the smallest quantum multiple that is >= a. */
#define	QUANTUM_CEILING(a)						\
	(((a) + QUANTUM_MASK) & ~QUANTUM_MASK)

#define	LONG			((size_t)(1U << LG_SIZEOF_LONG))
#define	LONG_MASK		(LONG - 1)

/* Return the smallest long multiple that is >= a. */
#define	LONG_CEILING(a)						\
	(((a) + LONG_MASK) & ~LONG_MASK)

#define	SIZEOF_PTR		(1U << LG_SIZEOF_PTR)
#define	PTR_MASK		(SIZEOF_PTR - 1)

/* Return the smallest (void *) multiple that is >= a. */
#define	PTR_CEILING(a)						\
	(((a) + PTR_MASK) & ~PTR_MASK)

/*
 * Maximum size of L1 cache line.  This is used to avoid cache line aliasing.
 * In addition, this controls the spacing of cacheline-spaced size classes.
 */
#define	LG_CACHELINE		6
#define	CACHELINE		((size_t)(1U << LG_CACHELINE))
#define	CACHELINE_MASK		(CACHELINE - 1)

/* Return the smallest cacheline multiple that is >= s. */
#define	CACHELINE_CEILING(s)						\
	(((s) + CACHELINE_MASK) & ~CACHELINE_MASK)

/*
 * Page size.  STATIC_PAGE_SHIFT is determined by the configure script.  If
 * DYNAMIC_PAGE_SHIFT is enabled, only use the STATIC_PAGE_* macros where
 * compile-time values are required for the purposes of defining data
 * structures.
 */
#define	STATIC_PAGE_SIZE ((size_t)(1U << STATIC_PAGE_SHIFT))
#define	STATIC_PAGE_MASK ((size_t)(STATIC_PAGE_SIZE - 1))

#ifdef PAGE_SHIFT
#  undef PAGE_SHIFT
#endif
#ifdef PAGE_SIZE
#  undef PAGE_SIZE
#endif
#ifdef PAGE_MASK
#  undef PAGE_MASK
#endif

#ifdef DYNAMIC_PAGE_SHIFT
#  define PAGE_SHIFT	lg_pagesize
#  define PAGE_SIZE	pagesize
#  define PAGE_MASK	pagesize_mask
#else
#  define PAGE_SHIFT	STATIC_PAGE_SHIFT
#  define PAGE_SIZE	STATIC_PAGE_SIZE
#  define PAGE_MASK	STATIC_PAGE_MASK
#endif

/* Return the smallest pagesize multiple that is >= s. */
#define	PAGE_CEILING(s)							\
	(((s) + PAGE_MASK) & ~PAGE_MASK)

#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/prn.h"
#include "jemalloc/internal/ckh.h"
#include "jemalloc/internal/stats.h"
#include "jemalloc/internal/ctl.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/mb.h"
#include "jemalloc/internal/extent.h"
#include "jemalloc/internal/arena.h"
#include "jemalloc/internal/bitmap.h"
#include "jemalloc/internal/base.h"
#include "jemalloc/internal/chunk.h"
#include "jemalloc/internal/huge.h"
#include "jemalloc/internal/rtree.h"
#include "jemalloc/internal/tcache.h"
#include "jemalloc/internal/hash.h"
#ifdef JEMALLOC_ZONE
#include "jemalloc/internal/zone.h"
#endif
#include "jemalloc/internal/prof.h"

#undef JEMALLOC_H_TYPES
/******************************************************************************/
#define JEMALLOC_H_STRUCTS

#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/prn.h"
#include "jemalloc/internal/ckh.h"
#include "jemalloc/internal/stats.h"
#include "jemalloc/internal/ctl.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/mb.h"
#include "jemalloc/internal/bitmap.h"
#include "jemalloc/internal/extent.h"
#include "jemalloc/internal/arena.h"
#include "jemalloc/internal/base.h"
#include "jemalloc/internal/chunk.h"
#include "jemalloc/internal/huge.h"
#include "jemalloc/internal/rtree.h"
#include "jemalloc/internal/tcache.h"
#include "jemalloc/internal/hash.h"
#ifdef JEMALLOC_ZONE
#include "jemalloc/internal/zone.h"
#endif
#include "jemalloc/internal/prof.h"

#ifdef JEMALLOC_STATS
typedef struct {
	uint64_t	allocated;
	uint64_t	deallocated;
} thread_allocated_t;
#endif

#undef JEMALLOC_H_STRUCTS
/******************************************************************************/
#define JEMALLOC_H_EXTERNS

extern bool	opt_abort;
#ifdef JEMALLOC_FILL
extern bool	opt_junk;
#endif
#ifdef JEMALLOC_SYSV
extern bool	opt_sysv;
#endif
#ifdef JEMALLOC_XMALLOC
extern bool	opt_xmalloc;
#endif
#ifdef JEMALLOC_FILL
extern bool	opt_zero;
#endif
extern size_t	opt_narenas;

#ifdef DYNAMIC_PAGE_SHIFT
extern size_t		pagesize;
extern size_t		pagesize_mask;
extern size_t		lg_pagesize;
#endif

/* Number of CPUs. */
extern unsigned		ncpus;

extern malloc_mutex_t	arenas_lock; /* Protects arenas initialization. */
extern pthread_key_t	arenas_tsd;
#ifndef NO_TLS
/*
 * Map of pthread_self() --> arenas[???], used for selecting an arena to use
 * for allocations.
 */
extern __thread arena_t	*arenas_tls JEMALLOC_ATTR(tls_model("initial-exec"));
#  define ARENA_GET()	arenas_tls
#  define ARENA_SET(v)	do {						\
	arenas_tls = (v);						\
	pthread_setspecific(arenas_tsd, (void *)(v));			\
} while (0)
#else
#  define ARENA_GET()	((arena_t *)pthread_getspecific(arenas_tsd))
#  define ARENA_SET(v)	do {						\
	pthread_setspecific(arenas_tsd, (void *)(v));			\
} while (0)
#endif

/*
 * Arenas that are used to service external requests.  Not all elements of the
 * arenas array are necessarily used; arenas are created lazily as needed.
 */
extern arena_t		**arenas;
extern unsigned		narenas;

#ifdef JEMALLOC_STATS
#  ifndef NO_TLS
extern __thread thread_allocated_t	thread_allocated_tls;
#    define ALLOCATED_GET() (thread_allocated_tls.allocated)
#    define ALLOCATEDP_GET() (&thread_allocated_tls.allocated)
#    define DEALLOCATED_GET() (thread_allocated_tls.deallocated)
#    define DEALLOCATEDP_GET() (&thread_allocated_tls.deallocated)
#    define ALLOCATED_ADD(a, d) do {					\
	thread_allocated_tls.allocated += a;				\
	thread_allocated_tls.deallocated += d;				\
} while (0)
#  else
extern pthread_key_t	thread_allocated_tsd;
thread_allocated_t	*thread_allocated_get_hard(void);

#    define ALLOCATED_GET() (thread_allocated_get()->allocated)
#    define ALLOCATEDP_GET() (&thread_allocated_get()->allocated)
#    define DEALLOCATED_GET() (thread_allocated_get()->deallocated)
#    define DEALLOCATEDP_GET() (&thread_allocated_get()->deallocated)
#    define ALLOCATED_ADD(a, d) do {					\
	thread_allocated_t *thread_allocated = thread_allocated_get();	\
	thread_allocated->allocated += (a);				\
	thread_allocated->deallocated += (d);				\
} while (0)
#  endif
#endif

arena_t	*arenas_extend(unsigned ind);
arena_t	*choose_arena_hard(void);
int	buferror(int errnum, char *buf, size_t buflen);
void	jemalloc_prefork(void);
void	jemalloc_postfork(void);

#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/prn.h"
#include "jemalloc/internal/ckh.h"
#include "jemalloc/internal/stats.h"
#include "jemalloc/internal/ctl.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/mb.h"
#include "jemalloc/internal/bitmap.h"
#include "jemalloc/internal/extent.h"
#include "jemalloc/internal/arena.h"
#include "jemalloc/internal/base.h"
#include "jemalloc/internal/chunk.h"
#include "jemalloc/internal/huge.h"
#include "jemalloc/internal/rtree.h"
#include "jemalloc/internal/tcache.h"
#include "jemalloc/internal/hash.h"
#ifdef JEMALLOC_ZONE
#include "jemalloc/internal/zone.h"
#endif
#include "jemalloc/internal/prof.h"

#undef JEMALLOC_H_EXTERNS
/******************************************************************************/
#define JEMALLOC_H_INLINES

#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/prn.h"
#include "jemalloc/internal/ckh.h"
#include "jemalloc/internal/stats.h"
#include "jemalloc/internal/ctl.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/mb.h"
#include "jemalloc/internal/extent.h"
#include "jemalloc/internal/base.h"
#include "jemalloc/internal/chunk.h"
#include "jemalloc/internal/huge.h"

#ifndef JEMALLOC_ENABLE_INLINE
size_t	pow2_ceil(size_t x);
size_t	s2u(size_t size);
size_t	sa2u(size_t size, size_t alignment, size_t *run_size_p);
void	malloc_write(const char *s);
arena_t	*choose_arena(void);
#  if (defined(JEMALLOC_STATS) && defined(NO_TLS))
thread_allocated_t	*thread_allocated_get(void);
#  endif
#endif

#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_C_))
/* Compute the smallest power of 2 that is >= x. */
JEMALLOC_INLINE size_t
pow2_ceil(size_t x)
{

	x--;
	x |= x >> 1;
	x |= x >> 2;
	x |= x >> 4;
	x |= x >> 8;
	x |= x >> 16;
#if (LG_SIZEOF_PTR == 3)
	x |= x >> 32;
#endif
	x++;
	return (x);
}

/*
 * Compute usable size that would result from allocating an object with the
 * specified size.
 */
JEMALLOC_INLINE size_t
s2u(size_t size)
{

	if (size <= small_maxclass)
		return (arena_bin_info[SMALL_SIZE2BIN(size)].reg_size);
	if (size <= arena_maxclass)
		return (PAGE_CEILING(size));
	return (CHUNK_CEILING(size));
}

/*
 * Compute usable size that would result from allocating an object with the
 * specified size and alignment.
 */
JEMALLOC_INLINE size_t
sa2u(size_t size, size_t alignment, size_t *run_size_p)
{
	size_t usize;

	/*
	 * Round size up to the nearest multiple of alignment.
	 *
	 * This done, we can take advantage of the fact that for each small
	 * size class, every object is aligned at the smallest power of two
	 * that is non-zero in the base two representation of the size.  For
	 * example:
	 *
	 *   Size |   Base 2 | Minimum alignment
	 *   -----+----------+------------------
	 *     96 |  1100000 |  32
	 *    144 | 10100000 |  32
	 *    192 | 11000000 |  64
	 *
	 * Depending on runtime settings, it is possible that arena_malloc()
	 * will further round up to a power of two, but that never causes
	 * correctness issues.
	 */
	usize = (size + (alignment - 1)) & (-alignment);
	/*
	 * (usize < size) protects against the combination of maximal
	 * alignment and size greater than maximal alignment.
	 */
	if (usize < size) {
		/* size_t overflow. */
		return (0);
	}

	if (usize <= arena_maxclass && alignment <= PAGE_SIZE) {
		if (usize <= small_maxclass)
			return (arena_bin_info[SMALL_SIZE2BIN(usize)].reg_size);
		return (PAGE_CEILING(usize));
	} else {
		size_t run_size;

		/*
		 * We can't achieve subpage alignment, so round up alignment
		 * permanently; it makes later calculations simpler.
		 */
		alignment = PAGE_CEILING(alignment);
		usize = PAGE_CEILING(size);
		/*
		 * (usize < size) protects against very large sizes within
		 * PAGE_SIZE of SIZE_T_MAX.
		 *
		 * (usize + alignment < usize) protects against the
		 * combination of maximal alignment and usize large enough
		 * to cause overflow.  This is similar to the first overflow
		 * check above, but it needs to be repeated due to the new
		 * usize value, which may now be *equal* to maximal
		 * alignment, whereas before we only detected overflow if the
		 * original size was *greater* than maximal alignment.
		 */
		if (usize < size || usize + alignment < usize) {
			/* size_t overflow. */
			return (0);
		}

		/*
		 * Calculate the size of the over-size run that arena_palloc()
		 * would need to allocate in order to guarantee the alignment.
		 */
		if (usize >= alignment)
			run_size = usize + alignment - PAGE_SIZE;
		else {
			/*
			 * It is possible that (alignment << 1) will cause
			 * overflow, but it doesn't matter because we also
			 * subtract PAGE_SIZE, which in the case of overflow
			 * leaves us with a very large run_size.  That causes
			 * the first conditional below to fail, which means
			 * that the bogus run_size value never gets used for
			 * anything important.
			 */
			run_size = (alignment << 1) - PAGE_SIZE;
		}
		if (run_size_p != NULL)
			*run_size_p = run_size;

		if (run_size <= arena_maxclass)
			return (PAGE_CEILING(usize));
		return (CHUNK_CEILING(usize));
	}
}

/*
 * Wrapper around malloc_message() that avoids the need for
 * JEMALLOC_P(malloc_message)(...) throughout the code.
 */
JEMALLOC_INLINE void
malloc_write(const char *s)
{

	JEMALLOC_P(malloc_message)(NULL, s);
}

/*
 * Choose an arena based on a per-thread value (fast-path code, calls slow-path
 * code if necessary).
 */
JEMALLOC_INLINE arena_t *
choose_arena(void)
{
	arena_t *ret;

	ret = ARENA_GET();
	if (ret == NULL) {
		ret = choose_arena_hard();
		assert(ret != NULL);
	}

	return (ret);
}

#if (defined(JEMALLOC_STATS) && defined(NO_TLS))
JEMALLOC_INLINE thread_allocated_t *
thread_allocated_get(void)
{
	thread_allocated_t *thread_allocated = (thread_allocated_t *)
	    pthread_getspecific(thread_allocated_tsd);

	if (thread_allocated == NULL)
		return (thread_allocated_get_hard());
	return (thread_allocated);
}
#endif
#endif

#include "jemalloc/internal/bitmap.h"
#include "jemalloc/internal/rtree.h"
#include "jemalloc/internal/tcache.h"
#include "jemalloc/internal/arena.h"
#include "jemalloc/internal/hash.h"
#ifdef JEMALLOC_ZONE
#include "jemalloc/internal/zone.h"
#endif

#ifndef JEMALLOC_ENABLE_INLINE
void	*imalloc(size_t size);
void	*icalloc(size_t size);
void	*ipalloc(size_t usize, size_t alignment, bool zero);
size_t	isalloc(const void *ptr);
#  ifdef JEMALLOC_IVSALLOC
size_t	ivsalloc(const void *ptr);
#  endif
void	idalloc(void *ptr);
void	*iralloc(void *ptr, size_t size, size_t extra, size_t alignment,
    bool zero, bool no_move);
#endif

#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_C_))
JEMALLOC_INLINE void *
imalloc(size_t size)
{

	assert(size != 0);

	if (size <= arena_maxclass)
		return (arena_malloc(size, false));
	else
		return (huge_malloc(size, false));
}

JEMALLOC_INLINE void *
icalloc(size_t size)
{

	if (size <= arena_maxclass)
		return (arena_malloc(size, true));
	else
		return (huge_malloc(size, true));
}

JEMALLOC_INLINE void *
ipalloc(size_t usize, size_t alignment, bool zero)
{
	void *ret;

	assert(usize != 0);
	assert(usize == sa2u(usize, alignment, NULL));

	if (usize <= arena_maxclass && alignment <= PAGE_SIZE)
		ret = arena_malloc(usize, zero);
	else {
		size_t run_size = 0;

		/*
		 * Ideally we would only ever call sa2u() once per aligned
		 * allocation request, and the caller of this function has
		 * already done so once.  However, it's rather burdensome to
		 * require every caller to pass in run_size, especially given
		 * that it's only relevant to large allocations.  Therefore,
		 * just call it again here in order to get run_size.
		 */
		sa2u(usize, alignment, &run_size);
		if (run_size <= arena_maxclass) {
			ret = arena_palloc(choose_arena(), usize, run_size,
			    alignment, zero);
		} else if (alignment <= chunksize)
			ret = huge_malloc(usize, zero);
		else
			ret = huge_palloc(usize, alignment, zero);
	}

	assert(((uintptr_t)ret & (alignment - 1)) == 0);
	return (ret);
}

JEMALLOC_INLINE size_t
isalloc(const void *ptr)
{
	size_t ret;
	arena_chunk_t *chunk;

	assert(ptr != NULL);

	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
	if (chunk != ptr) {
		/* Region. */
		dassert(chunk->arena->magic == ARENA_MAGIC);

#ifdef JEMALLOC_PROF
		ret = arena_salloc_demote(ptr);
#else
		ret = arena_salloc(ptr);
#endif
	} else
		ret = huge_salloc(ptr);

	return (ret);
}

#ifdef JEMALLOC_IVSALLOC
JEMALLOC_INLINE size_t
ivsalloc(const void *ptr)
{

	/* Return 0 if ptr is not within a chunk managed by jemalloc. */
	if (rtree_get(chunks_rtree, (uintptr_t)CHUNK_ADDR2BASE(ptr)) == NULL)
		return (0);

	return (isalloc(ptr));
}
#endif

JEMALLOC_INLINE void
idalloc(void *ptr)
{
	arena_chunk_t *chunk;

	assert(ptr != NULL);

	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
	if (chunk != ptr)
		arena_dalloc(chunk->arena, chunk, ptr);
	else
		huge_dalloc(ptr, true);
}

JEMALLOC_INLINE void *
iralloc(void *ptr, size_t size, size_t extra, size_t alignment, bool zero,
    bool no_move)
{
	void *ret;
	size_t oldsize;

	assert(ptr != NULL);
	assert(size != 0);

	oldsize = isalloc(ptr);

	if (alignment != 0 && ((uintptr_t)ptr & ((uintptr_t)alignment-1))
	    != 0) {
		size_t usize, copysize;

		/*
		 * Existing object alignment is inadquate; allocate new space
		 * and copy.
		 */
		if (no_move)
			return (NULL);
		usize = sa2u(size + extra, alignment, NULL);
		if (usize == 0)
			return (NULL);
		ret = ipalloc(usize, alignment, zero);
		if (ret == NULL) {
			if (extra == 0)
				return (NULL);
			/* Try again, without extra this time. */
			usize = sa2u(size, alignment, NULL);
			if (usize == 0)
				return (NULL);
			ret = ipalloc(usize, alignment, zero);
			if (ret == NULL)
				return (NULL);
		}
		/*
		 * Copy at most size bytes (not size+extra), since the caller
		 * has no expectation that the extra bytes will be reliably
		 * preserved.
		 */
		copysize = (size < oldsize) ? size : oldsize;
		memcpy(ret, ptr, copysize);
		idalloc(ptr);
		return (ret);
	}

	if (no_move) {
		if (size <= arena_maxclass) {
			return (arena_ralloc_no_move(ptr, oldsize, size,
			    extra, zero));
		} else {
			return (huge_ralloc_no_move(ptr, oldsize, size,
			    extra));
		}
	} else {
		if (size + extra <= arena_maxclass) {
			return (arena_ralloc(ptr, oldsize, size, extra,
			    alignment, zero));
		} else {
			return (huge_ralloc(ptr, oldsize, size, extra,
			    alignment, zero));
		}
	}
}
#endif

#include "jemalloc/internal/prof.h"

#undef JEMALLOC_H_INLINES
/******************************************************************************/