forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathobmalloc.c
More file actions
2227 lines (1939 loc) · 75.2 KB
/
obmalloc.c
File metadata and controls
2227 lines (1939 loc) · 75.2 KB
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
#include "Python.h"
/* Python's malloc wrappers (see pymem.h) */
#ifdef PYMALLOC_DEBUG /* WITH_PYMALLOC && PYMALLOC_DEBUG */
/* Forward declaration */
static void* _PyMem_DebugMalloc(void *ctx, size_t size);
static void _PyMem_DebugFree(void *ctx, void *p);
static void* _PyMem_DebugRealloc(void *ctx, void *ptr, size_t size);
static void _PyObject_DebugDumpAddress(const void *p);
static void _PyMem_DebugCheckAddress(char api_id, const void *p);
#endif
#if defined(__has_feature) /* Clang */
#if __has_feature(address_sanitizer) /* is ASAN enabled? */
#define ATTRIBUTE_NO_ADDRESS_SAFETY_ANALYSIS \
__attribute__((no_address_safety_analysis)) \
__attribute__ ((noinline))
#else
#define ATTRIBUTE_NO_ADDRESS_SAFETY_ANALYSIS
#endif
#else
#if defined(__SANITIZE_ADDRESS__) /* GCC 4.8.x, is ASAN enabled? */
#define ATTRIBUTE_NO_ADDRESS_SAFETY_ANALYSIS \
__attribute__((no_address_safety_analysis)) \
__attribute__ ((noinline))
#else
#define ATTRIBUTE_NO_ADDRESS_SAFETY_ANALYSIS
#endif
#endif
#ifdef WITH_PYMALLOC
#ifdef MS_WINDOWS
# include <windows.h>
#elif defined(HAVE_MMAP)
# include <sys/mman.h>
# ifdef MAP_ANONYMOUS
# define ARENAS_USE_MMAP
# endif
#endif
/* Forward declaration */
static void* _PyObject_Malloc(void *ctx, size_t size);
static void _PyObject_Free(void *ctx, void *p);
static void* _PyObject_Realloc(void *ctx, void *ptr, size_t size);
#endif
static void *
_PyMem_RawMalloc(void *ctx, size_t size)
{
/* PyMem_Malloc(0) means malloc(1). Some systems would return NULL
for malloc(0), which would be treated as an error. Some platforms would
return a pointer with no memory behind it, which would break pymalloc.
To solve these problems, allocate an extra byte. */
if (size == 0)
size = 1;
return malloc(size);
}
static void *
_PyMem_RawRealloc(void *ctx, void *ptr, size_t size)
{
if (size == 0)
size = 1;
return realloc(ptr, size);
}
static void
_PyMem_RawFree(void *ctx, void *ptr)
{
free(ptr);
}
#ifdef MS_WINDOWS
static void *
_PyObject_ArenaVirtualAlloc(void *ctx, size_t size)
{
return VirtualAlloc(NULL, size,
MEM_COMMIT | MEM_RESERVE, PAGE_READWRITE);
}
static void
_PyObject_ArenaVirtualFree(void *ctx, void *ptr, size_t size)
{
VirtualFree(ptr, 0, MEM_RELEASE);
}
#elif defined(ARENAS_USE_MMAP)
static void *
_PyObject_ArenaMmap(void *ctx, size_t size)
{
void *ptr;
ptr = mmap(NULL, size, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
if (ptr == MAP_FAILED)
return NULL;
assert(ptr != NULL);
return ptr;
}
static void
_PyObject_ArenaMunmap(void *ctx, void *ptr, size_t size)
{
munmap(ptr, size);
}
#else
static void *
_PyObject_ArenaMalloc(void *ctx, size_t size)
{
return malloc(size);
}
static void
_PyObject_ArenaFree(void *ctx, void *ptr, size_t size)
{
free(ptr);
}
#endif
#define PYRAW_FUNCS _PyMem_RawMalloc, _PyMem_RawRealloc, _PyMem_RawFree
#ifdef WITH_PYMALLOC
# define PYOBJ_FUNCS _PyObject_Malloc, _PyObject_Realloc, _PyObject_Free
#else
# define PYOBJ_FUNCS PYRAW_FUNCS
#endif
#define PYMEM_FUNCS PYRAW_FUNCS
#ifdef PYMALLOC_DEBUG
typedef struct {
/* We tag each block with an API ID in order to tag API violations */
char api_id;
PyMemAllocator alloc;
} debug_alloc_api_t;
static struct {
debug_alloc_api_t raw;
debug_alloc_api_t mem;
debug_alloc_api_t obj;
} _PyMem_Debug = {
{'r', {NULL, PYRAW_FUNCS}},
{'m', {NULL, PYMEM_FUNCS}},
{'o', {NULL, PYOBJ_FUNCS}}
};
#define PYDBG_FUNCS _PyMem_DebugMalloc, _PyMem_DebugRealloc, _PyMem_DebugFree
#endif
static PyMemAllocator _PyMem_Raw = {
#ifdef PYMALLOC_DEBUG
&_PyMem_Debug.raw, PYDBG_FUNCS
#else
NULL, PYRAW_FUNCS
#endif
};
static PyMemAllocator _PyMem = {
#ifdef PYMALLOC_DEBUG
&_PyMem_Debug.mem, PYDBG_FUNCS
#else
NULL, PYMEM_FUNCS
#endif
};
static PyMemAllocator _PyObject = {
#ifdef PYMALLOC_DEBUG
&_PyMem_Debug.obj, PYDBG_FUNCS
#else
NULL, PYOBJ_FUNCS
#endif
};
#undef PYRAW_FUNCS
#undef PYMEM_FUNCS
#undef PYOBJ_FUNCS
#undef PYDBG_FUNCS
static PyObjectArenaAllocator _PyObject_Arena = {NULL,
#ifdef MS_WINDOWS
_PyObject_ArenaVirtualAlloc, _PyObject_ArenaVirtualFree
#elif defined(ARENAS_USE_MMAP)
_PyObject_ArenaMmap, _PyObject_ArenaMunmap
#else
_PyObject_ArenaMalloc, _PyObject_ArenaFree
#endif
};
void
PyMem_SetupDebugHooks(void)
{
#ifdef PYMALLOC_DEBUG
PyMemAllocator alloc;
alloc.malloc = _PyMem_DebugMalloc;
alloc.realloc = _PyMem_DebugRealloc;
alloc.free = _PyMem_DebugFree;
if (_PyMem_Raw.malloc != _PyMem_DebugMalloc) {
alloc.ctx = &_PyMem_Debug.raw;
PyMem_GetAllocator(PYMEM_DOMAIN_RAW, &_PyMem_Debug.raw.alloc);
PyMem_SetAllocator(PYMEM_DOMAIN_RAW, &alloc);
}
if (_PyMem.malloc != _PyMem_DebugMalloc) {
alloc.ctx = &_PyMem_Debug.mem;
PyMem_GetAllocator(PYMEM_DOMAIN_MEM, &_PyMem_Debug.mem.alloc);
PyMem_SetAllocator(PYMEM_DOMAIN_MEM, &alloc);
}
if (_PyObject.malloc != _PyMem_DebugMalloc) {
alloc.ctx = &_PyMem_Debug.obj;
PyMem_GetAllocator(PYMEM_DOMAIN_OBJ, &_PyMem_Debug.obj.alloc);
PyMem_SetAllocator(PYMEM_DOMAIN_OBJ, &alloc);
}
#endif
}
void
PyMem_GetAllocator(PyMemAllocatorDomain domain, PyMemAllocator *allocator)
{
switch(domain)
{
case PYMEM_DOMAIN_RAW: *allocator = _PyMem_Raw; break;
case PYMEM_DOMAIN_MEM: *allocator = _PyMem; break;
case PYMEM_DOMAIN_OBJ: *allocator = _PyObject; break;
default:
/* unknown domain */
allocator->ctx = NULL;
allocator->malloc = NULL;
allocator->realloc = NULL;
allocator->free = NULL;
}
}
void
PyMem_SetAllocator(PyMemAllocatorDomain domain, PyMemAllocator *allocator)
{
switch(domain)
{
case PYMEM_DOMAIN_RAW: _PyMem_Raw = *allocator; break;
case PYMEM_DOMAIN_MEM: _PyMem = *allocator; break;
case PYMEM_DOMAIN_OBJ: _PyObject = *allocator; break;
/* ignore unknown domain */
}
}
void
PyObject_GetArenaAllocator(PyObjectArenaAllocator *allocator)
{
*allocator = _PyObject_Arena;
}
void
PyObject_SetArenaAllocator(PyObjectArenaAllocator *allocator)
{
_PyObject_Arena = *allocator;
}
void *
PyMem_RawMalloc(size_t size)
{
/*
* Limit ourselves to PY_SSIZE_T_MAX bytes to prevent security holes.
* Most python internals blindly use a signed Py_ssize_t to track
* things without checking for overflows or negatives.
* As size_t is unsigned, checking for size < 0 is not required.
*/
if (size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyMem_Raw.malloc(_PyMem_Raw.ctx, size);
}
void*
PyMem_RawRealloc(void *ptr, size_t new_size)
{
/* see PyMem_RawMalloc() */
if (new_size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyMem_Raw.realloc(_PyMem_Raw.ctx, ptr, new_size);
}
void PyMem_RawFree(void *ptr)
{
_PyMem_Raw.free(_PyMem_Raw.ctx, ptr);
}
void *
PyMem_Malloc(size_t size)
{
/* see PyMem_RawMalloc() */
if (size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyMem.malloc(_PyMem.ctx, size);
}
void *
PyMem_Realloc(void *ptr, size_t new_size)
{
/* see PyMem_RawMalloc() */
if (new_size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyMem.realloc(_PyMem.ctx, ptr, new_size);
}
void
PyMem_Free(void *ptr)
{
_PyMem.free(_PyMem.ctx, ptr);
}
char *
_PyMem_RawStrdup(const char *str)
{
size_t size;
char *copy;
size = strlen(str) + 1;
copy = PyMem_RawMalloc(size);
if (copy == NULL)
return NULL;
memcpy(copy, str, size);
return copy;
}
char *
_PyMem_Strdup(const char *str)
{
size_t size;
char *copy;
size = strlen(str) + 1;
copy = PyMem_Malloc(size);
if (copy == NULL)
return NULL;
memcpy(copy, str, size);
return copy;
}
void *
PyObject_Malloc(size_t size)
{
/* see PyMem_RawMalloc() */
if (size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyObject.malloc(_PyObject.ctx, size);
}
void *
PyObject_Realloc(void *ptr, size_t new_size)
{
/* see PyMem_RawMalloc() */
if (new_size > (size_t)PY_SSIZE_T_MAX)
return NULL;
return _PyObject.realloc(_PyObject.ctx, ptr, new_size);
}
void
PyObject_Free(void *ptr)
{
_PyObject.free(_PyObject.ctx, ptr);
}
#ifdef WITH_PYMALLOC
#ifdef WITH_VALGRIND
#include <valgrind/valgrind.h>
/* If we're using GCC, use __builtin_expect() to reduce overhead of
the valgrind checks */
#if defined(__GNUC__) && (__GNUC__ > 2) && defined(__OPTIMIZE__)
# define UNLIKELY(value) __builtin_expect((value), 0)
#else
# define UNLIKELY(value) (value)
#endif
/* -1 indicates that we haven't checked that we're running on valgrind yet. */
static int running_on_valgrind = -1;
#endif
/* An object allocator for Python.
Here is an introduction to the layers of the Python memory architecture,
showing where the object allocator is actually used (layer +2), It is
called for every object allocation and deallocation (PyObject_New/Del),
unless the object-specific allocators implement a proprietary allocation
scheme (ex.: ints use a simple free list). This is also the place where
the cyclic garbage collector operates selectively on container objects.
Object-specific allocators
_____ ______ ______ ________
[ int ] [ dict ] [ list ] ... [ string ] Python core |
+3 | <----- Object-specific memory -----> | <-- Non-object memory --> |
_______________________________ | |
[ Python's object allocator ] | |
+2 | ####### Object memory ####### | <------ Internal buffers ------> |
______________________________________________________________ |
[ Python's raw memory allocator (PyMem_ API) ] |
+1 | <----- Python memory (under PyMem manager's control) ------> | |
__________________________________________________________________
[ Underlying general-purpose allocator (ex: C library malloc) ]
0 | <------ Virtual memory allocated for the python process -------> |
=========================================================================
_______________________________________________________________________
[ OS-specific Virtual Memory Manager (VMM) ]
-1 | <--- Kernel dynamic storage allocation & management (page-based) ---> |
__________________________________ __________________________________
[ ] [ ]
-2 | <-- Physical memory: ROM/RAM --> | | <-- Secondary storage (swap) --> |
*/
/*==========================================================================*/
/* A fast, special-purpose memory allocator for small blocks, to be used
on top of a general-purpose malloc -- heavily based on previous art. */
/* Vladimir Marangozov -- August 2000 */
/*
* "Memory management is where the rubber meets the road -- if we do the wrong
* thing at any level, the results will not be good. And if we don't make the
* levels work well together, we are in serious trouble." (1)
*
* (1) Paul R. Wilson, Mark S. Johnstone, Michael Neely, and David Boles,
* "Dynamic Storage Allocation: A Survey and Critical Review",
* in Proc. 1995 Int'l. Workshop on Memory Management, September 1995.
*/
/* #undef WITH_MEMORY_LIMITS */ /* disable mem limit checks */
/*==========================================================================*/
/*
* Allocation strategy abstract:
*
* For small requests, the allocator sub-allocates <Big> blocks of memory.
* Requests greater than SMALL_REQUEST_THRESHOLD bytes are routed to the
* system's allocator.
*
* Small requests are grouped in size classes spaced 8 bytes apart, due
* to the required valid alignment of the returned address. Requests of
* a particular size are serviced from memory pools of 4K (one VMM page).
* Pools are fragmented on demand and contain free lists of blocks of one
* particular size class. In other words, there is a fixed-size allocator
* for each size class. Free pools are shared by the different allocators
* thus minimizing the space reserved for a particular size class.
*
* This allocation strategy is a variant of what is known as "simple
* segregated storage based on array of free lists". The main drawback of
* simple segregated storage is that we might end up with lot of reserved
* memory for the different free lists, which degenerate in time. To avoid
* this, we partition each free list in pools and we share dynamically the
* reserved space between all free lists. This technique is quite efficient
* for memory intensive programs which allocate mainly small-sized blocks.
*
* For small requests we have the following table:
*
* Request in bytes Size of allocated block Size class idx
* ----------------------------------------------------------------
* 1-8 8 0
* 9-16 16 1
* 17-24 24 2
* 25-32 32 3
* 33-40 40 4
* 41-48 48 5
* 49-56 56 6
* 57-64 64 7
* 65-72 72 8
* ... ... ...
* 497-504 504 62
* 505-512 512 63
*
* 0, SMALL_REQUEST_THRESHOLD + 1 and up: routed to the underlying
* allocator.
*/
/*==========================================================================*/
/*
* -- Main tunable settings section --
*/
/*
* Alignment of addresses returned to the user. 8-bytes alignment works
* on most current architectures (with 32-bit or 64-bit address busses).
* The alignment value is also used for grouping small requests in size
* classes spaced ALIGNMENT bytes apart.
*
* You shouldn't change this unless you know what you are doing.
*/
#define ALIGNMENT 8 /* must be 2^N */
#define ALIGNMENT_SHIFT 3
/* Return the number of bytes in size class I, as a uint. */
#define INDEX2SIZE(I) (((uint)(I) + 1) << ALIGNMENT_SHIFT)
/*
* Max size threshold below which malloc requests are considered to be
* small enough in order to use preallocated memory pools. You can tune
* this value according to your application behaviour and memory needs.
*
* Note: a size threshold of 512 guarantees that newly created dictionaries
* will be allocated from preallocated memory pools on 64-bit.
*
* The following invariants must hold:
* 1) ALIGNMENT <= SMALL_REQUEST_THRESHOLD <= 512
* 2) SMALL_REQUEST_THRESHOLD is evenly divisible by ALIGNMENT
*
* Although not required, for better performance and space efficiency,
* it is recommended that SMALL_REQUEST_THRESHOLD is set to a power of 2.
*/
#define SMALL_REQUEST_THRESHOLD 512
#define NB_SMALL_SIZE_CLASSES (SMALL_REQUEST_THRESHOLD / ALIGNMENT)
/*
* The system's VMM page size can be obtained on most unices with a
* getpagesize() call or deduced from various header files. To make
* things simpler, we assume that it is 4K, which is OK for most systems.
* It is probably better if this is the native page size, but it doesn't
* have to be. In theory, if SYSTEM_PAGE_SIZE is larger than the native page
* size, then `POOL_ADDR(p)->arenaindex' could rarely cause a segmentation
* violation fault. 4K is apparently OK for all the platforms that python
* currently targets.
*/
#define SYSTEM_PAGE_SIZE (4 * 1024)
#define SYSTEM_PAGE_SIZE_MASK (SYSTEM_PAGE_SIZE - 1)
/*
* Maximum amount of memory managed by the allocator for small requests.
*/
#ifdef WITH_MEMORY_LIMITS
#ifndef SMALL_MEMORY_LIMIT
#define SMALL_MEMORY_LIMIT (64 * 1024 * 1024) /* 64 MB -- more? */
#endif
#endif
/*
* The allocator sub-allocates <Big> blocks of memory (called arenas) aligned
* on a page boundary. This is a reserved virtual address space for the
* current process (obtained through a malloc()/mmap() call). In no way this
* means that the memory arenas will be used entirely. A malloc(<Big>) is
* usually an address range reservation for <Big> bytes, unless all pages within
* this space are referenced subsequently. So malloc'ing big blocks and not
* using them does not mean "wasting memory". It's an addressable range
* wastage...
*
* Arenas are allocated with mmap() on systems supporting anonymous memory
* mappings to reduce heap fragmentation.
*/
#define ARENA_SIZE (256 << 10) /* 256KB */
#ifdef WITH_MEMORY_LIMITS
#define MAX_ARENAS (SMALL_MEMORY_LIMIT / ARENA_SIZE)
#endif
/*
* Size of the pools used for small blocks. Should be a power of 2,
* between 1K and SYSTEM_PAGE_SIZE, that is: 1k, 2k, 4k.
*/
#define POOL_SIZE SYSTEM_PAGE_SIZE /* must be 2^N */
#define POOL_SIZE_MASK SYSTEM_PAGE_SIZE_MASK
/*
* -- End of tunable settings section --
*/
/*==========================================================================*/
/*
* Locking
*
* To reduce lock contention, it would probably be better to refine the
* crude function locking with per size class locking. I'm not positive
* however, whether it's worth switching to such locking policy because
* of the performance penalty it might introduce.
*
* The following macros describe the simplest (should also be the fastest)
* lock object on a particular platform and the init/fini/lock/unlock
* operations on it. The locks defined here are not expected to be recursive
* because it is assumed that they will always be called in the order:
* INIT, [LOCK, UNLOCK]*, FINI.
*/
/*
* Python's threads are serialized, so object malloc locking is disabled.
*/
#define SIMPLELOCK_DECL(lock) /* simple lock declaration */
#define SIMPLELOCK_INIT(lock) /* allocate (if needed) and initialize */
#define SIMPLELOCK_FINI(lock) /* free/destroy an existing lock */
#define SIMPLELOCK_LOCK(lock) /* acquire released lock */
#define SIMPLELOCK_UNLOCK(lock) /* release acquired lock */
/*
* Basic types
* I don't care if these are defined in <sys/types.h> or elsewhere. Axiom.
*/
#undef uchar
#define uchar unsigned char /* assuming == 8 bits */
#undef uint
#define uint unsigned int /* assuming >= 16 bits */
#undef ulong
#define ulong unsigned long /* assuming >= 32 bits */
#undef uptr
#define uptr Py_uintptr_t
/* When you say memory, my mind reasons in terms of (pointers to) blocks */
typedef uchar block;
/* Pool for small blocks. */
struct pool_header {
union { block *_padding;
uint count; } ref; /* number of allocated blocks */
block *freeblock; /* pool's free list head */
struct pool_header *nextpool; /* next pool of this size class */
struct pool_header *prevpool; /* previous pool "" */
uint arenaindex; /* index into arenas of base adr */
uint szidx; /* block size class index */
uint nextoffset; /* bytes to virgin block */
uint maxnextoffset; /* largest valid nextoffset */
};
typedef struct pool_header *poolp;
/* Record keeping for arenas. */
struct arena_object {
/* The address of the arena, as returned by malloc. Note that 0
* will never be returned by a successful malloc, and is used
* here to mark an arena_object that doesn't correspond to an
* allocated arena.
*/
uptr address;
/* Pool-aligned pointer to the next pool to be carved off. */
block* pool_address;
/* The number of available pools in the arena: free pools + never-
* allocated pools.
*/
uint nfreepools;
/* The total number of pools in the arena, whether or not available. */
uint ntotalpools;
/* Singly-linked list of available pools. */
struct pool_header* freepools;
/* Whenever this arena_object is not associated with an allocated
* arena, the nextarena member is used to link all unassociated
* arena_objects in the singly-linked `unused_arena_objects` list.
* The prevarena member is unused in this case.
*
* When this arena_object is associated with an allocated arena
* with at least one available pool, both members are used in the
* doubly-linked `usable_arenas` list, which is maintained in
* increasing order of `nfreepools` values.
*
* Else this arena_object is associated with an allocated arena
* all of whose pools are in use. `nextarena` and `prevarena`
* are both meaningless in this case.
*/
struct arena_object* nextarena;
struct arena_object* prevarena;
};
#define POOL_OVERHEAD _Py_SIZE_ROUND_UP(sizeof(struct pool_header), ALIGNMENT)
#define DUMMY_SIZE_IDX 0xffff /* size class of newly cached pools */
/* Round pointer P down to the closest pool-aligned address <= P, as a poolp */
#define POOL_ADDR(P) ((poolp)_Py_ALIGN_DOWN((P), POOL_SIZE))
/* Return total number of blocks in pool of size index I, as a uint. */
#define NUMBLOCKS(I) ((uint)(POOL_SIZE - POOL_OVERHEAD) / INDEX2SIZE(I))
/*==========================================================================*/
/*
* This malloc lock
*/
SIMPLELOCK_DECL(_malloc_lock)
#define LOCK() SIMPLELOCK_LOCK(_malloc_lock)
#define UNLOCK() SIMPLELOCK_UNLOCK(_malloc_lock)
#define LOCK_INIT() SIMPLELOCK_INIT(_malloc_lock)
#define LOCK_FINI() SIMPLELOCK_FINI(_malloc_lock)
/*
* Pool table -- headed, circular, doubly-linked lists of partially used pools.
This is involved. For an index i, usedpools[i+i] is the header for a list of
all partially used pools holding small blocks with "size class idx" i. So
usedpools[0] corresponds to blocks of size 8, usedpools[2] to blocks of size
16, and so on: index 2*i <-> blocks of size (i+1)<<ALIGNMENT_SHIFT.
Pools are carved off an arena's highwater mark (an arena_object's pool_address
member) as needed. Once carved off, a pool is in one of three states forever
after:
used == partially used, neither empty nor full
At least one block in the pool is currently allocated, and at least one
block in the pool is not currently allocated (note this implies a pool
has room for at least two blocks).
This is a pool's initial state, as a pool is created only when malloc
needs space.
The pool holds blocks of a fixed size, and is in the circular list headed
at usedpools[i] (see above). It's linked to the other used pools of the
same size class via the pool_header's nextpool and prevpool members.
If all but one block is currently allocated, a malloc can cause a
transition to the full state. If all but one block is not currently
allocated, a free can cause a transition to the empty state.
full == all the pool's blocks are currently allocated
On transition to full, a pool is unlinked from its usedpools[] list.
It's not linked to from anything then anymore, and its nextpool and
prevpool members are meaningless until it transitions back to used.
A free of a block in a full pool puts the pool back in the used state.
Then it's linked in at the front of the appropriate usedpools[] list, so
that the next allocation for its size class will reuse the freed block.
empty == all the pool's blocks are currently available for allocation
On transition to empty, a pool is unlinked from its usedpools[] list,
and linked to the front of its arena_object's singly-linked freepools list,
via its nextpool member. The prevpool member has no meaning in this case.
Empty pools have no inherent size class: the next time a malloc finds
an empty list in usedpools[], it takes the first pool off of freepools.
If the size class needed happens to be the same as the size class the pool
last had, some pool initialization can be skipped.
Block Management
Blocks within pools are again carved out as needed. pool->freeblock points to
the start of a singly-linked list of free blocks within the pool. When a
block is freed, it's inserted at the front of its pool's freeblock list. Note
that the available blocks in a pool are *not* linked all together when a pool
is initialized. Instead only "the first two" (lowest addresses) blocks are
set up, returning the first such block, and setting pool->freeblock to a
one-block list holding the second such block. This is consistent with that
pymalloc strives at all levels (arena, pool, and block) never to touch a piece
of memory until it's actually needed.
So long as a pool is in the used state, we're certain there *is* a block
available for allocating, and pool->freeblock is not NULL. If pool->freeblock
points to the end of the free list before we've carved the entire pool into
blocks, that means we simply haven't yet gotten to one of the higher-address
blocks. The offset from the pool_header to the start of "the next" virgin
block is stored in the pool_header nextoffset member, and the largest value
of nextoffset that makes sense is stored in the maxnextoffset member when a
pool is initialized. All the blocks in a pool have been passed out at least
once when and only when nextoffset > maxnextoffset.
Major obscurity: While the usedpools vector is declared to have poolp
entries, it doesn't really. It really contains two pointers per (conceptual)
poolp entry, the nextpool and prevpool members of a pool_header. The
excruciating initialization code below fools C so that
usedpool[i+i]
"acts like" a genuine poolp, but only so long as you only reference its
nextpool and prevpool members. The "- 2*sizeof(block *)" gibberish is
compensating for that a pool_header's nextpool and prevpool members
immediately follow a pool_header's first two members:
union { block *_padding;
uint count; } ref;
block *freeblock;
each of which consume sizeof(block *) bytes. So what usedpools[i+i] really
contains is a fudged-up pointer p such that *if* C believes it's a poolp
pointer, then p->nextpool and p->prevpool are both p (meaning that the headed
circular list is empty).
It's unclear why the usedpools setup is so convoluted. It could be to
minimize the amount of cache required to hold this heavily-referenced table
(which only *needs* the two interpool pointer members of a pool_header). OTOH,
referencing code has to remember to "double the index" and doing so isn't
free, usedpools[0] isn't a strictly legal pointer, and we're crucially relying
on that C doesn't insert any padding anywhere in a pool_header at or before
the prevpool member.
**************************************************************************** */
#define PTA(x) ((poolp )((uchar *)&(usedpools[2*(x)]) - 2*sizeof(block *)))
#define PT(x) PTA(x), PTA(x)
static poolp usedpools[2 * ((NB_SMALL_SIZE_CLASSES + 7) / 8) * 8] = {
PT(0), PT(1), PT(2), PT(3), PT(4), PT(5), PT(6), PT(7)
#if NB_SMALL_SIZE_CLASSES > 8
, PT(8), PT(9), PT(10), PT(11), PT(12), PT(13), PT(14), PT(15)
#if NB_SMALL_SIZE_CLASSES > 16
, PT(16), PT(17), PT(18), PT(19), PT(20), PT(21), PT(22), PT(23)
#if NB_SMALL_SIZE_CLASSES > 24
, PT(24), PT(25), PT(26), PT(27), PT(28), PT(29), PT(30), PT(31)
#if NB_SMALL_SIZE_CLASSES > 32
, PT(32), PT(33), PT(34), PT(35), PT(36), PT(37), PT(38), PT(39)
#if NB_SMALL_SIZE_CLASSES > 40
, PT(40), PT(41), PT(42), PT(43), PT(44), PT(45), PT(46), PT(47)
#if NB_SMALL_SIZE_CLASSES > 48
, PT(48), PT(49), PT(50), PT(51), PT(52), PT(53), PT(54), PT(55)
#if NB_SMALL_SIZE_CLASSES > 56
, PT(56), PT(57), PT(58), PT(59), PT(60), PT(61), PT(62), PT(63)
#if NB_SMALL_SIZE_CLASSES > 64
#error "NB_SMALL_SIZE_CLASSES should be less than 64"
#endif /* NB_SMALL_SIZE_CLASSES > 64 */
#endif /* NB_SMALL_SIZE_CLASSES > 56 */
#endif /* NB_SMALL_SIZE_CLASSES > 48 */
#endif /* NB_SMALL_SIZE_CLASSES > 40 */
#endif /* NB_SMALL_SIZE_CLASSES > 32 */
#endif /* NB_SMALL_SIZE_CLASSES > 24 */
#endif /* NB_SMALL_SIZE_CLASSES > 16 */
#endif /* NB_SMALL_SIZE_CLASSES > 8 */
};
/*==========================================================================
Arena management.
`arenas` is a vector of arena_objects. It contains maxarenas entries, some of
which may not be currently used (== they're arena_objects that aren't
currently associated with an allocated arena). Note that arenas proper are
separately malloc'ed.
Prior to Python 2.5, arenas were never free()'ed. Starting with Python 2.5,
we do try to free() arenas, and use some mild heuristic strategies to increase
the likelihood that arenas eventually can be freed.
unused_arena_objects
This is a singly-linked list of the arena_objects that are currently not
being used (no arena is associated with them). Objects are taken off the
head of the list in new_arena(), and are pushed on the head of the list in
PyObject_Free() when the arena is empty. Key invariant: an arena_object
is on this list if and only if its .address member is 0.
usable_arenas
This is a doubly-linked list of the arena_objects associated with arenas
that have pools available. These pools are either waiting to be reused,
or have not been used before. The list is sorted to have the most-
allocated arenas first (ascending order based on the nfreepools member).
This means that the next allocation will come from a heavily used arena,
which gives the nearly empty arenas a chance to be returned to the system.
In my unscientific tests this dramatically improved the number of arenas
that could be freed.
Note that an arena_object associated with an arena all of whose pools are
currently in use isn't on either list.
*/
/* Array of objects used to track chunks of memory (arenas). */
static struct arena_object* arenas = NULL;
/* Number of slots currently allocated in the `arenas` vector. */
static uint maxarenas = 0;
/* The head of the singly-linked, NULL-terminated list of available
* arena_objects.
*/
static struct arena_object* unused_arena_objects = NULL;
/* The head of the doubly-linked, NULL-terminated at each end, list of
* arena_objects associated with arenas that have pools available.
*/
static struct arena_object* usable_arenas = NULL;
/* How many arena_objects do we initially allocate?
* 16 = can allocate 16 arenas = 16 * ARENA_SIZE = 4MB before growing the
* `arenas` vector.
*/
#define INITIAL_ARENA_OBJECTS 16
/* Number of arenas allocated that haven't been free()'d. */
static size_t narenas_currently_allocated = 0;
/* Total number of times malloc() called to allocate an arena. */
static size_t ntimes_arena_allocated = 0;
/* High water mark (max value ever seen) for narenas_currently_allocated. */
static size_t narenas_highwater = 0;
static Py_ssize_t _Py_AllocatedBlocks = 0;
Py_ssize_t
_Py_GetAllocatedBlocks(void)
{
return _Py_AllocatedBlocks;
}
/* Allocate a new arena. If we run out of memory, return NULL. Else
* allocate a new arena, and return the address of an arena_object
* describing the new arena. It's expected that the caller will set
* `usable_arenas` to the return value.
*/
static struct arena_object*
new_arena(void)
{
struct arena_object* arenaobj;
uint excess; /* number of bytes above pool alignment */
void *address;
#ifdef PYMALLOC_DEBUG
if (Py_GETENV("PYTHONMALLOCSTATS"))
_PyObject_DebugMallocStats(stderr);
#endif
if (unused_arena_objects == NULL) {
uint i;
uint numarenas;
size_t nbytes;
/* Double the number of arena objects on each allocation.
* Note that it's possible for `numarenas` to overflow.
*/
numarenas = maxarenas ? maxarenas << 1 : INITIAL_ARENA_OBJECTS;
if (numarenas <= maxarenas)
return NULL; /* overflow */
#if SIZEOF_SIZE_T <= SIZEOF_INT
if (numarenas > PY_SIZE_MAX / sizeof(*arenas))
return NULL; /* overflow */
#endif
nbytes = numarenas * sizeof(*arenas);
arenaobj = (struct arena_object *)PyMem_RawRealloc(arenas, nbytes);
if (arenaobj == NULL)
return NULL;
arenas = arenaobj;
/* We might need to fix pointers that were copied. However,
* new_arena only gets called when all the pages in the
* previous arenas are full. Thus, there are *no* pointers
* into the old array. Thus, we don't have to worry about
* invalid pointers. Just to be sure, some asserts:
*/
assert(usable_arenas == NULL);
assert(unused_arena_objects == NULL);
/* Put the new arenas on the unused_arena_objects list. */
for (i = maxarenas; i < numarenas; ++i) {
arenas[i].address = 0; /* mark as unassociated */
arenas[i].nextarena = i < numarenas - 1 ?
&arenas[i+1] : NULL;
}
/* Update globals. */
unused_arena_objects = &arenas[maxarenas];
maxarenas = numarenas;
}
/* Take the next available arena object off the head of the list. */
assert(unused_arena_objects != NULL);
arenaobj = unused_arena_objects;
unused_arena_objects = arenaobj->nextarena;
assert(arenaobj->address == 0);
address = _PyObject_Arena.alloc(_PyObject_Arena.ctx, ARENA_SIZE);
if (address == NULL) {
/* The allocation failed: return NULL after putting the
* arenaobj back.
*/
arenaobj->nextarena = unused_arena_objects;
unused_arena_objects = arenaobj;
return NULL;
}
arenaobj->address = (uptr)address;
++narenas_currently_allocated;
++ntimes_arena_allocated;
if (narenas_currently_allocated > narenas_highwater)
narenas_highwater = narenas_currently_allocated;
arenaobj->freepools = NULL;
/* pool_address <- first pool-aligned address in the arena
nfreepools <- number of whole pools that fit after alignment */
arenaobj->pool_address = (block*)arenaobj->address;
arenaobj->nfreepools = ARENA_SIZE / POOL_SIZE;
assert(POOL_SIZE * arenaobj->nfreepools == ARENA_SIZE);
excess = (uint)(arenaobj->address & POOL_SIZE_MASK);
if (excess != 0) {
--arenaobj->nfreepools;
arenaobj->pool_address += POOL_SIZE - excess;
}
arenaobj->ntotalpools = arenaobj->nfreepools;
return arenaobj;
}
/*
Py_ADDRESS_IN_RANGE(P, POOL)
Return true if and only if P is an address that was allocated by pymalloc.
POOL must be the pool address associated with P, i.e., POOL = POOL_ADDR(P)
(the caller is asked to compute this because the macro expands POOL more than
once, and for efficiency it's best for the caller to assign POOL_ADDR(P) to a
variable and pass the latter to the macro; because Py_ADDRESS_IN_RANGE is
called on every alloc/realloc/free, micro-efficiency is important here).