mirror of https://github.com/FFmpeg/FFmpeg.git
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
386 lines
8.6 KiB
386 lines
8.6 KiB
/* |
|
* default memory allocator for libavutil |
|
* Copyright (c) 2002 Fabrice Bellard |
|
* |
|
* This file is part of FFmpeg. |
|
* |
|
* FFmpeg is free software; you can redistribute it and/or |
|
* modify it under the terms of the GNU Lesser General Public |
|
* License as published by the Free Software Foundation; either |
|
* version 2.1 of the License, or (at your option) any later version. |
|
* |
|
* FFmpeg is distributed in the hope that it will be useful, |
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
|
* Lesser General Public License for more details. |
|
* |
|
* You should have received a copy of the GNU Lesser General Public |
|
* License along with FFmpeg; if not, write to the Free Software |
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
|
*/ |
|
|
|
/** |
|
* @file |
|
* default memory allocator for libavutil |
|
*/ |
|
|
|
#define _XOPEN_SOURCE 600 |
|
|
|
#include "config.h" |
|
|
|
#include <limits.h> |
|
#include <stdint.h> |
|
#include <stdlib.h> |
|
#include <string.h> |
|
#if HAVE_MALLOC_H |
|
#include <malloc.h> |
|
#endif |
|
|
|
#include "avassert.h" |
|
#include "avutil.h" |
|
#include "intreadwrite.h" |
|
#include "mem.h" |
|
|
|
#ifdef MALLOC_PREFIX |
|
|
|
#define malloc AV_JOIN(MALLOC_PREFIX, malloc) |
|
#define memalign AV_JOIN(MALLOC_PREFIX, memalign) |
|
#define posix_memalign AV_JOIN(MALLOC_PREFIX, posix_memalign) |
|
#define realloc AV_JOIN(MALLOC_PREFIX, realloc) |
|
#define free AV_JOIN(MALLOC_PREFIX, free) |
|
|
|
void *malloc(size_t size); |
|
void *memalign(size_t align, size_t size); |
|
int posix_memalign(void **ptr, size_t align, size_t size); |
|
void *realloc(void *ptr, size_t size); |
|
void free(void *ptr); |
|
|
|
#endif /* MALLOC_PREFIX */ |
|
|
|
#define ALIGN (HAVE_AVX ? 32 : 16) |
|
|
|
/* NOTE: if you want to override these functions with your own |
|
* implementations (not recommended) you have to link libav* as |
|
* dynamic libraries and remove -Wl,-Bsymbolic from the linker flags. |
|
* Note that this will cost performance. */ |
|
|
|
static size_t max_alloc_size= INT_MAX; |
|
|
|
void av_max_alloc(size_t max){ |
|
max_alloc_size = max; |
|
} |
|
|
|
void *av_malloc(size_t size) |
|
{ |
|
void *ptr = NULL; |
|
#if CONFIG_MEMALIGN_HACK |
|
long diff; |
|
#endif |
|
|
|
/* let's disallow possible ambiguous cases */ |
|
if (size > (max_alloc_size - 32)) |
|
return NULL; |
|
|
|
#if CONFIG_MEMALIGN_HACK |
|
ptr = malloc(size + ALIGN); |
|
if (!ptr) |
|
return ptr; |
|
diff = ((~(long)ptr)&(ALIGN - 1)) + 1; |
|
ptr = (char *)ptr + diff; |
|
((char *)ptr)[-1] = diff; |
|
#elif HAVE_POSIX_MEMALIGN |
|
if (size) //OS X on SDK 10.6 has a broken posix_memalign implementation |
|
if (posix_memalign(&ptr, ALIGN, size)) |
|
ptr = NULL; |
|
#elif HAVE_ALIGNED_MALLOC |
|
ptr = _aligned_malloc(size, ALIGN); |
|
#elif HAVE_MEMALIGN |
|
#ifndef __DJGPP__ |
|
ptr = memalign(ALIGN, size); |
|
#else |
|
ptr = memalign(size, ALIGN); |
|
#endif |
|
/* Why 64? |
|
* Indeed, we should align it: |
|
* on 4 for 386 |
|
* on 16 for 486 |
|
* on 32 for 586, PPro - K6-III |
|
* on 64 for K7 (maybe for P3 too). |
|
* Because L1 and L2 caches are aligned on those values. |
|
* But I don't want to code such logic here! |
|
*/ |
|
/* Why 32? |
|
* For AVX ASM. SSE / NEON needs only 16. |
|
* Why not larger? Because I did not see a difference in benchmarks ... |
|
*/ |
|
/* benchmarks with P3 |
|
* memalign(64) + 1 3071, 3051, 3032 |
|
* memalign(64) + 2 3051, 3032, 3041 |
|
* memalign(64) + 4 2911, 2896, 2915 |
|
* memalign(64) + 8 2545, 2554, 2550 |
|
* memalign(64) + 16 2543, 2572, 2563 |
|
* memalign(64) + 32 2546, 2545, 2571 |
|
* memalign(64) + 64 2570, 2533, 2558 |
|
* |
|
* BTW, malloc seems to do 8-byte alignment by default here. |
|
*/ |
|
#else |
|
ptr = malloc(size); |
|
#endif |
|
if(!ptr && !size) { |
|
size = 1; |
|
ptr= av_malloc(1); |
|
} |
|
#if CONFIG_MEMORY_POISONING |
|
if (ptr) |
|
memset(ptr, 0x2a, size); |
|
#endif |
|
return ptr; |
|
} |
|
|
|
void *av_realloc(void *ptr, size_t size) |
|
{ |
|
#if CONFIG_MEMALIGN_HACK |
|
int diff; |
|
#endif |
|
|
|
/* let's disallow possible ambiguous cases */ |
|
if (size > (max_alloc_size - 32)) |
|
return NULL; |
|
|
|
#if CONFIG_MEMALIGN_HACK |
|
//FIXME this isn't aligned correctly, though it probably isn't needed |
|
if (!ptr) |
|
return av_malloc(size); |
|
diff = ((char *)ptr)[-1]; |
|
av_assert0(diff>0 && diff<=ALIGN); |
|
ptr = realloc((char *)ptr - diff, size + diff); |
|
if (ptr) |
|
ptr = (char *)ptr + diff; |
|
return ptr; |
|
#elif HAVE_ALIGNED_MALLOC |
|
return _aligned_realloc(ptr, size + !size, ALIGN); |
|
#else |
|
return realloc(ptr, size + !size); |
|
#endif |
|
} |
|
|
|
void *av_realloc_f(void *ptr, size_t nelem, size_t elsize) |
|
{ |
|
size_t size; |
|
void *r; |
|
|
|
if (av_size_mult(elsize, nelem, &size)) { |
|
av_free(ptr); |
|
return NULL; |
|
} |
|
r = av_realloc(ptr, size); |
|
if (!r && size) |
|
av_free(ptr); |
|
return r; |
|
} |
|
|
|
void av_free(void *ptr) |
|
{ |
|
#if CONFIG_MEMALIGN_HACK |
|
if (ptr) { |
|
int v= ((char *)ptr)[-1]; |
|
av_assert0(v>0 && v<=ALIGN); |
|
free((char *)ptr - v); |
|
} |
|
#elif HAVE_ALIGNED_MALLOC |
|
_aligned_free(ptr); |
|
#else |
|
free(ptr); |
|
#endif |
|
} |
|
|
|
void av_freep(void *arg) |
|
{ |
|
void **ptr = (void **)arg; |
|
av_free(*ptr); |
|
*ptr = NULL; |
|
} |
|
|
|
void *av_mallocz(size_t size) |
|
{ |
|
void *ptr = av_malloc(size); |
|
if (ptr) |
|
memset(ptr, 0, size); |
|
return ptr; |
|
} |
|
|
|
void *av_calloc(size_t nmemb, size_t size) |
|
{ |
|
if (size <= 0 || nmemb >= INT_MAX / size) |
|
return NULL; |
|
return av_mallocz(nmemb * size); |
|
} |
|
|
|
char *av_strdup(const char *s) |
|
{ |
|
char *ptr = NULL; |
|
if (s) { |
|
int len = strlen(s) + 1; |
|
ptr = av_malloc(len); |
|
if (ptr) |
|
memcpy(ptr, s, len); |
|
} |
|
return ptr; |
|
} |
|
|
|
void *av_memdup(const void *p, size_t size) |
|
{ |
|
void *ptr = NULL; |
|
if (p) { |
|
ptr = av_malloc(size); |
|
if (ptr) |
|
memcpy(ptr, p, size); |
|
} |
|
return ptr; |
|
} |
|
|
|
void av_dynarray_add(void *tab_ptr, int *nb_ptr, void *elem) |
|
{ |
|
/* see similar ffmpeg.c:grow_array() */ |
|
int nb, nb_alloc; |
|
intptr_t *tab; |
|
|
|
nb = *nb_ptr; |
|
tab = *(intptr_t**)tab_ptr; |
|
if ((nb & (nb - 1)) == 0) { |
|
if (nb == 0) |
|
nb_alloc = 1; |
|
else |
|
nb_alloc = nb * 2; |
|
tab = av_realloc(tab, nb_alloc * sizeof(intptr_t)); |
|
*(intptr_t**)tab_ptr = tab; |
|
} |
|
tab[nb++] = (intptr_t)elem; |
|
*nb_ptr = nb; |
|
} |
|
|
|
static void fill16(uint8_t *dst, int len) |
|
{ |
|
uint32_t v = AV_RN16(dst - 2); |
|
|
|
v |= v << 16; |
|
|
|
while (len >= 4) { |
|
AV_WN32(dst, v); |
|
dst += 4; |
|
len -= 4; |
|
} |
|
|
|
while (len--) { |
|
*dst = dst[-2]; |
|
dst++; |
|
} |
|
} |
|
|
|
static void fill24(uint8_t *dst, int len) |
|
{ |
|
#if HAVE_BIGENDIAN |
|
uint32_t v = AV_RB24(dst - 3); |
|
uint32_t a = v << 8 | v >> 16; |
|
uint32_t b = v << 16 | v >> 8; |
|
uint32_t c = v << 24 | v; |
|
#else |
|
uint32_t v = AV_RL24(dst - 3); |
|
uint32_t a = v | v << 24; |
|
uint32_t b = v >> 8 | v << 16; |
|
uint32_t c = v >> 16 | v << 8; |
|
#endif |
|
|
|
while (len >= 12) { |
|
AV_WN32(dst, a); |
|
AV_WN32(dst + 4, b); |
|
AV_WN32(dst + 8, c); |
|
dst += 12; |
|
len -= 12; |
|
} |
|
|
|
if (len >= 4) { |
|
AV_WN32(dst, a); |
|
dst += 4; |
|
len -= 4; |
|
} |
|
|
|
if (len >= 4) { |
|
AV_WN32(dst, b); |
|
dst += 4; |
|
len -= 4; |
|
} |
|
|
|
while (len--) { |
|
*dst = dst[-3]; |
|
dst++; |
|
} |
|
} |
|
|
|
static void fill32(uint8_t *dst, int len) |
|
{ |
|
uint32_t v = AV_RN32(dst - 4); |
|
|
|
while (len >= 4) { |
|
AV_WN32(dst, v); |
|
dst += 4; |
|
len -= 4; |
|
} |
|
|
|
while (len--) { |
|
*dst = dst[-4]; |
|
dst++; |
|
} |
|
} |
|
|
|
void av_memcpy_backptr(uint8_t *dst, int back, int cnt) |
|
{ |
|
const uint8_t *src = &dst[-back]; |
|
if (!back) |
|
return; |
|
|
|
if (back == 1) { |
|
memset(dst, *src, cnt); |
|
} else if (back == 2) { |
|
fill16(dst, cnt); |
|
} else if (back == 3) { |
|
fill24(dst, cnt); |
|
} else if (back == 4) { |
|
fill32(dst, cnt); |
|
} else { |
|
if (cnt >= 16) { |
|
int blocklen = back; |
|
while (cnt > blocklen) { |
|
memcpy(dst, src, blocklen); |
|
dst += blocklen; |
|
cnt -= blocklen; |
|
blocklen <<= 1; |
|
} |
|
memcpy(dst, src, cnt); |
|
return; |
|
} |
|
if (cnt >= 8) { |
|
AV_COPY32U(dst, src); |
|
AV_COPY32U(dst + 4, src + 4); |
|
src += 8; |
|
dst += 8; |
|
cnt -= 8; |
|
} |
|
if (cnt >= 4) { |
|
AV_COPY32U(dst, src); |
|
src += 4; |
|
dst += 4; |
|
cnt -= 4; |
|
} |
|
if (cnt >= 2) { |
|
AV_COPY16U(dst, src); |
|
src += 2; |
|
dst += 2; |
|
cnt -= 2; |
|
} |
|
if (cnt) |
|
*dst = *src; |
|
} |
|
} |
|
|
|
|