Home Research Papers Posters Manuals Talks Download People Help Wiki Internal

conv-core/memory-gnu.c

Go to the documentation of this file.

/* 
Off-the-shelf glibc 2.3.2 malloc routine: useful because it's
   - Portable (should compile everywhere)
   - Compact (uses mmap for big buffers, can shift back sbrk)
   - Self-contained (this file is it)

This is slightly hacked as:
   - Use mm_* routine names, as defined below.
   - Maps charm config. macros to local macros, below.
   - Renamed malloc.h memory-gnu.h
   - Renamed threads-m.h memory-gnu-threads.h
   - Removed error-prone "memcpy" prototypes (use system header).
*/

#define malloc   mm_malloc
#define free     mm_free
#define calloc   mm_calloc
#define cfree    mm_cfree
#define realloc  mm_realloc
#define memalign mm_memalign
#define valloc   mm_valloc

extern CMK_TYPEDEF_UINT8 memory_allocated;
extern CMK_TYPEDEF_UINT8 memory_allocated_max;
extern CMK_TYPEDEF_UINT8 memory_allocated_min;

#define HAVE_MMAP CMK_HAS_MMAP
#ifndef __USE_GNU
#  define __USE_GNU 1 /* enables MREMAP_MAYMOVE in linux mman.h (!) */
#endif

#define attribute_hidden /* empty, needed by memory-gnu.h */

#if 0 /* fixes from 2.2.5 version (now obsolete) */

/* Crashing bug caused by circular dependence:
 calloc calls arena_get2 calls pthread_setspecific calls calloc...
#ifdef CMK_SHARED_VARS_POSIX_THREADS_SMP
#  define MALLOC_HOOKS
#  define USE_PTHREADS
#endif
*/
#define RETURN_ADDRESS(x) (void *)x

#endif

/* Malloc implementation for multiple threads without lock contention.
   Copyright (C) 1996,1997,1998,1999,2000,01,02 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Wolfram Gloger <wg@malloc.de>
   and Doug Lea <dl@cs.oswego.edu>, 2001.

   The GNU C Library 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.

   The GNU C Library 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 the GNU C Library; see the file COPYING.LIB.  If not,
   write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.  */

/*
  This is a version (aka ptmalloc2) of malloc/free/realloc written by
  Doug Lea and adapted to multiple threads/arenas by Wolfram Gloger.

* Version ptmalloc2-20011215
  $Id: memory-gnu.c,v 2.21 2006-04-21 21:02:51 yanshi Exp $
  based on:
  VERSION 2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)

   Note: There may be an updated version of this malloc obtainable at
           http://www.malloc.de/malloc/ptmalloc2.tar.gz
         Check before installing!

* Quickstart

  In order to compile this implementation, a Makefile is provided with
  the ptmalloc2 distribution, which has pre-defined targets for some
  popular systems (e.g. "make posix" for Posix threads).  All that is
  typically required with regard to compiler flags is the selection of
  the thread package via defining one out of USE_PTHREADS, USE_THR or
  USE_SPROC.  Check the thread-m.h file for what effects this has.
  Many/most systems will additionally require USE_TSD_DATA_HACK to be
  defined, so this is the default for "make posix".

* Why use this malloc?

  This is not the fastest, most space-conserving, most portable, or
  most tunable malloc ever written. However it is among the fastest
  while also being among the most space-conserving, portable and tunable.
  Consistent balance across these factors results in a good general-purpose
  allocator for malloc-intensive programs.

  The main properties of the algorithms are:
  * For large (>= 512 bytes) requests, it is a pure best-fit allocator,
    with ties normally decided via FIFO (i.e. least recently used).
  * For small (<= 64 bytes by default) requests, it is a caching
    allocator, that maintains pools of quickly recycled chunks.
  * In between, and for combinations of large and small requests, it does
    the best it can trying to meet both goals at once.
  * For very large requests (>= 128KB by default), it relies on system
    memory mapping facilities, if supported.

  For a longer but slightly out of date high-level description, see
     http://gee.cs.oswego.edu/dl/html/malloc.html

  You may already by default be using a C library containing a malloc
  that is  based on some version of this malloc (for example in
  linux). You might still want to use the one in this file in order to
  customize settings or to avoid overheads associated with library
  versions.

* Contents, described in more detail in "description of public routines" below.

  Standard (ANSI/SVID/...)  functions:
    malloc(size_t n);
    calloc(size_t n_elements, size_t element_size);
    free(Void_t* p);
    realloc(Void_t* p, size_t n);
    memalign(size_t alignment, size_t n);
    valloc(size_t n);
    mallinfo()
    mallopt(int parameter_number, int parameter_value)

  Additional functions:
    independent_calloc(size_t n_elements, size_t size, Void_t* chunks[]);
    independent_comalloc(size_t n_elements, size_t sizes[], Void_t* chunks[]);
    pvalloc(size_t n);
    cfree(Void_t* p);
    malloc_trim(size_t pad);
    malloc_usable_size(Void_t* p);
    malloc_stats();

* Vital statistics:

  Supported pointer representation:       4 or 8 bytes
  Supported size_t  representation:       4 or 8 bytes
       Note that size_t is allowed to be 4 bytes even if pointers are 8.
       You can adjust this by defining INTERNAL_SIZE_T

  Alignment:                              2 * sizeof(size_t) (default)
       (i.e., 8 byte alignment with 4byte size_t). This suffices for
       nearly all current machines and C compilers. However, you can
       define MALLOC_ALIGNMENT to be wider than this if necessary.

  Minimum overhead per allocated chunk:   4 or 8 bytes
       Each malloced chunk has a hidden word of overhead holding size
       and status information.

  Minimum allocated size: 4-byte ptrs:  16 bytes    (including 4 overhead)
                          8-byte ptrs:  24/32 bytes (including, 4/8 overhead)

       When a chunk is freed, 12 (for 4byte ptrs) or 20 (for 8 byte
       ptrs but 4 byte size) or 24 (for 8/8) additional bytes are
       needed; 4 (8) for a trailing size field and 8 (16) bytes for
       free list pointers. Thus, the minimum allocatable size is
       16/24/32 bytes.

       Even a request for zero bytes (i.e., malloc(0)) returns a
       pointer to something of the minimum allocatable size.

       The maximum overhead wastage (i.e., number of extra bytes
       allocated than were requested in malloc) is less than or equal
       to the minimum size, except for requests >= mmap_threshold that
       are serviced via mmap(), where the worst case wastage is 2 *
       sizeof(size_t) bytes plus the remainder from a system page (the
       minimal mmap unit); typically 4096 or 8192 bytes.

  Maximum allocated size:  4-byte size_t: 2^32 minus about two pages
                           8-byte size_t: 2^64 minus about two pages

       It is assumed that (possibly signed) size_t values suffice to
       represent chunk sizes. `Possibly signed' is due to the fact
       that `size_t' may be defined on a system as either a signed or
       an unsigned type. The ISO C standard says that it must be
       unsigned, but a few systems are known not to adhere to this.
       Additionally, even when size_t is unsigned, sbrk (which is by
       default used to obtain memory from system) accepts signed
       arguments, and may not be able to handle size_t-wide arguments
       with negative sign bit.  Generally, values that would
       appear as negative after accounting for overhead and alignment
       are supported only via mmap(), which does not have this
       limitation.

       Requests for sizes outside the allowed range will perform an optional
       failure action and then return null. (Requests may also
       also fail because a system is out of memory.)

  Thread-safety: thread-safe unless NO_THREADS is defined

  Compliance: I believe it is compliant with the 1997 Single Unix Specification
       (See http://www.opennc.org). Also SVID/XPG, ANSI C, and probably
       others as well.

* Synopsis of compile-time options:

    People have reported using previous versions of this malloc on all
    versions of Unix, sometimes by tweaking some of the defines
    below. It has been tested most extensively on Solaris and
    Linux. It is also reported to work on WIN32 platforms.
    People also report using it in stand-alone embedded systems.

    The implementation is in straight, hand-tuned ANSI C.  It is not
    at all modular. (Sorry!)  It uses a lot of macros.  To be at all
    usable, this code should be compiled using an optimizing compiler
    (for example gcc -O3) that can simplify expressions and control
    paths. (FAQ: some macros import variables as arguments rather than
    declare locals because people reported that some debuggers
    otherwise get confused.)

    OPTION                     DEFAULT VALUE

    Compilation Environment options:

    __STD_C                    derived from C compiler defines
    WIN32                      NOT defined
    HAVE_MEMCPY                defined
    USE_MEMCPY                 1 if HAVE_MEMCPY is defined
    HAVE_MMAP                  defined as 1
    MMAP_CLEARS                1
    HAVE_MREMAP                0 unless linux defined
    USE_ARENAS                 the same as HAVE_MMAP
    malloc_getpagesize         derived from system #includes, or 4096 if not
    HAVE_USR_INCLUDE_MALLOC_H  NOT defined
    LACKS_UNISTD_H             NOT defined unless WIN32
    LACKS_SYS_PARAM_H          NOT defined unless WIN32
    LACKS_SYS_MMAN_H           NOT defined unless WIN32

    Changing default word sizes:

    INTERNAL_SIZE_T            size_t
    MALLOC_ALIGNMENT           2 * sizeof(INTERNAL_SIZE_T)

    Configuration and functionality options:

    USE_DL_PREFIX              NOT defined
    USE_PUBLIC_MALLOC_WRAPPERS NOT defined
    USE_MALLOC_LOCK            NOT defined
    MALLOC_DEBUG               NOT defined
    REALLOC_ZERO_BYTES_FREES   1
    MALLOC_FAILURE_ACTION      errno = ENOMEM, if __STD_C defined, else no-op
    TRIM_FASTBINS              0

    Options for customizing MORECORE:

    MORECORE                   sbrk
    MORECORE_FAILURE           -1
    MORECORE_CONTIGUOUS        1
    MORECORE_CANNOT_TRIM       NOT defined
    MORECORE_CLEARS            1
    MMAP_AS_MORECORE_SIZE      (1024 * 1024)

    Tuning options that are also dynamically changeable via mallopt:

    DEFAULT_MXFAST             64
    DEFAULT_TRIM_THRESHOLD     128 * 1024
    DEFAULT_TOP_PAD            0
    DEFAULT_MMAP_THRESHOLD     128 * 1024
    DEFAULT_MMAP_MAX           65536

    There are several other #defined constants and macros that you
    probably don't want to touch unless you are extending or adapting malloc.  */

/*
  __STD_C should be nonzero if using ANSI-standard C compiler, a C++
  compiler, or a C compiler sufficiently close to ANSI to get away
  with it.
*/

#ifndef __STD_C
#if defined(__STDC__) || defined(__cplusplus)
#define __STD_C     1
#else
#define __STD_C     0
#endif
#endif /*__STD_C*/

#if __STD_C && !__STDC__
#define  __STDC__   1
#endif

/*
  Void_t* is the pointer type that malloc should say it returns
*/

#ifndef Void_t
#if (__STD_C || defined(WIN32))
#define Void_t      void
#else
#define Void_t      char
#endif
#endif /*Void_t*/

#if __STD_C
#include <stddef.h>   /* for size_t */
#include <stdlib.h>   /* for getenv(), abort() */
#else
#include <sys/types.h>
#endif

#ifdef __cplusplus
extern "C" {
#endif

/* define LACKS_UNISTD_H if your system does not have a <unistd.h>. */

/* #define  LACKS_UNISTD_H */

#ifndef LACKS_UNISTD_H
#include <unistd.h>
#endif

/* define LACKS_SYS_PARAM_H if your system does not have a <sys/param.h>. */

/* #define  LACKS_SYS_PARAM_H */


#include <stdio.h>    /* needed for malloc_stats */
#include <errno.h>    /* needed for optional MALLOC_FAILURE_ACTION */


/*
  Debugging:

  Because freed chunks may be overwritten with bookkeeping fields, this
  malloc will often die when freed memory is overwritten by user
  programs.  This can be very effective (albeit in an annoying way)
  in helping track down dangling pointers.

  If you compile with -DMALLOC_DEBUG, a number of assertion checks are
  enabled that will catch more memory errors. You probably won't be
  able to make much sense of the actual assertion errors, but they
  should help you locate incorrectly overwritten memory.  The checking
  is fairly extensive, and will slow down execution
  noticeably. Calling malloc_stats or mallinfo with MALLOC_DEBUG set
  will attempt to check every non-mmapped allocated and free chunk in
  the course of computing the summmaries. (By nature, mmapped regions
  cannot be checked very much automatically.)

  Setting MALLOC_DEBUG may also be helpful if you are trying to modify
  this code. The assertions in the check routines spell out in more
  detail the assumptions and invariants underlying the algorithms.

  Setting MALLOC_DEBUG does NOT provide an automated mechanism for
  checking that all accesses to malloced memory stay within their
  bounds. However, there are several add-ons and adaptations of this
  or other mallocs available that do this.
*/

#if MALLOC_DEBUG
#include <assert.h>
#else
#undef  assert
#define assert(x) ((void)0)
#endif


/*
  INTERNAL_SIZE_T is the word-size used for internal bookkeeping
  of chunk sizes.

  The default version is the same as size_t.

  While not strictly necessary, it is best to define this as an
  unsigned type, even if size_t is a signed type. This may avoid some
  artificial size limitations on some systems.

  On a 64-bit machine, you may be able to reduce malloc overhead by
  defining INTERNAL_SIZE_T to be a 32 bit `unsigned int' at the
  expense of not being able to handle more than 2^32 of malloced
  space. If this limitation is acceptable, you are encouraged to set
  this unless you are on a platform requiring 16byte alignments. In
  this case the alignment requirements turn out to negate any
  potential advantages of decreasing size_t word size.

  Implementors: Beware of the possible combinations of:
     - INTERNAL_SIZE_T might be signed or unsigned, might be 32 or 64 bits,
       and might be the same width as int or as long
     - size_t might have different width and signedness as INTERNAL_SIZE_T
     - int and long might be 32 or 64 bits, and might be the same width
  To deal with this, most comparisons and difference computations
  among INTERNAL_SIZE_Ts should cast them to unsigned long, being
  aware of the fact that casting an unsigned int to a wider long does
  not sign-extend. (This also makes checking for negative numbers
  awkward.) Some of these casts result in harmless compiler warnings
  on some systems.
*/

#ifndef INTERNAL_SIZE_T
#define INTERNAL_SIZE_T size_t
#endif

/* The corresponding word size */
#define SIZE_SZ                (sizeof(INTERNAL_SIZE_T))


/*
  MALLOC_ALIGNMENT is the minimum alignment for malloc'ed chunks.
  It must be a power of two at least 2 * SIZE_SZ, even on machines
  for which smaller alignments would suffice. It may be defined as
  larger than this though. Note however that code and data structures
  are optimized for the case of 8-byte alignment.
*/


#ifndef MALLOC_ALIGNMENT
#define MALLOC_ALIGNMENT       (4 * SIZE_SZ)
#endif

/* The corresponding bit mask value */
#define MALLOC_ALIGN_MASK      (MALLOC_ALIGNMENT - 1)



/*
  REALLOC_ZERO_BYTES_FREES should be set if a call to
  realloc with zero bytes should be the same as a call to free.
  This is required by the C standard. Otherwise, since this malloc
  returns a unique pointer for malloc(0), so does realloc(p, 0).
*/

#ifndef REALLOC_ZERO_BYTES_FREES
#define REALLOC_ZERO_BYTES_FREES 1
#endif

/*
  TRIM_FASTBINS controls whether free() of a very small chunk can
  immediately lead to trimming. Setting to true (1) can reduce memory
  footprint, but will almost always slow down programs that use a lot
  of small chunks.

  Define this only if you are willing to give up some speed to more
  aggressively reduce system-level memory footprint when releasing
  memory in programs that use many small chunks.  You can get
  essentially the same effect by setting MXFAST to 0, but this can
  lead to even greater slowdowns in programs using many small chunks.
  TRIM_FASTBINS is an in-between compile-time option, that disables
  only those chunks bordering topmost memory from being placed in
  fastbins.
*/

#ifndef TRIM_FASTBINS
#define TRIM_FASTBINS  0
#endif


/*
  USE_DL_PREFIX will prefix all public routines with the string 'dl'.
  This is necessary when you only want to use this malloc in one part
  of a program, using your regular system malloc elsewhere.
*/

/* #define USE_DL_PREFIX */


/*
   Two-phase name translation.
   All of the actual routines are given mangled names.
   When wrappers are used, they become the public callable versions.
   When DL_PREFIX is used, the callable names are prefixed.
*/

#ifdef USE_DL_PREFIX
#define public_cALLOc    dlcalloc
#define public_fREe      dlfree
#define public_cFREe     dlcfree
#define public_mALLOc    dlmalloc
#define public_mEMALIGn  dlmemalign
#define public_rEALLOc   dlrealloc
#define public_vALLOc    dlvalloc
#define public_pVALLOc   dlpvalloc
#define public_mALLINFo  dlmallinfo
#define public_mALLOPt   dlmallopt
#define public_mTRIm     dlmalloc_trim
#define public_mSTATs    dlmalloc_stats
#define public_mUSABLe   dlmalloc_usable_size
#define public_iCALLOc   dlindependent_calloc
#define public_iCOMALLOc dlindependent_comalloc
#define public_gET_STATe dlget_state
#define public_sET_STATe dlset_state
#else /* USE_DL_PREFIX */
#ifdef _LIBC

/* Special defines for the GNU C library.  */
#define public_cALLOc    __libc_calloc
#define public_fREe      __libc_free
#define public_cFREe     __libc_cfree
#define public_mALLOc    __libc_malloc
#define public_mEMALIGn  __libc_memalign
#define public_rEALLOc   __libc_realloc
#define public_vALLOc    __libc_valloc
#define public_pVALLOc   __libc_pvalloc
#define public_mALLINFo  __libc_mallinfo
#define public_mALLOPt   __libc_mallopt
#define public_mTRIm     __malloc_trim
#define public_mSTATs    __malloc_stats
#define public_mUSABLe   __malloc_usable_size
#define public_iCALLOc   __libc_independent_calloc
#define public_iCOMALLOc __libc_independent_comalloc
#define public_gET_STATe __malloc_get_state
#define public_sET_STATe __malloc_set_state
#define malloc_getpagesize __getpagesize()
#define open             __open
#define mmap             __mmap
#define munmap           __munmap
#define mremap           __mremap
#define mprotect         __mprotect
#define MORECORE         (*__morecore)
#define MORECORE_FAILURE 0

Void_t * __default_morecore (ptrdiff_t);
Void_t *(*__morecore)(ptrdiff_t) = __default_morecore;

#else /* !_LIBC */
#define public_cALLOc    calloc
#define public_fREe      free
#define public_cFREe     cfree
#define public_mALLOc    malloc
#define public_mEMALIGn  memalign
#define public_rEALLOc   realloc
#define public_vALLOc    valloc
#define public_pVALLOc   pvalloc
#define public_mALLINFo  mallinfo
#define public_mALLOPt   mallopt
#define public_mTRIm     malloc_trim
#define public_mSTATs    malloc_stats
#define public_mUSABLe   malloc_usable_size
#define public_iCALLOc   independent_calloc
#define public_iCOMALLOc independent_comalloc
#define public_gET_STATe malloc_get_state
#define public_sET_STATe malloc_set_state
#endif /* _LIBC */
#endif /* USE_DL_PREFIX */

#ifndef _LIBC
#define __builtin_expect(expr, val)     (expr)

#define fwrite(buf, size, count, fp) _IO_fwrite (buf, size, count, fp)
#endif

/*
  HAVE_MEMCPY should be defined if you are not otherwise using
  ANSI STD C, but still have memcpy and memset in your C library
  and want to use them in calloc and realloc. Otherwise simple
  macro versions are defined below.

  USE_MEMCPY should be defined as 1 if you actually want to
  have memset and memcpy called. People report that the macro
  versions are faster than libc versions on some systems.

  Even if USE_MEMCPY is set to 1, loops to copy/clear small chunks
  (of <= 36 bytes) are manually unrolled in realloc and calloc.
*/

#include <string.h>

/*
  MALLOC_FAILURE_ACTION is the action to take before "return 0" when
  malloc fails to be able to return memory, either because memory is
  exhausted or because of illegal arguments.

  By default, sets errno if running on STD_C platform, else does nothing.
*/

#ifndef MALLOC_FAILURE_ACTION
#if __STD_C
#define MALLOC_FAILURE_ACTION \
   errno = ENOMEM;

#else
#define MALLOC_FAILURE_ACTION
#endif
#endif

/*
  MORECORE-related declarations. By default, rely on sbrk
*/


#ifdef LACKS_UNISTD_H
#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
#if __STD_C
extern Void_t*     sbrk(ptrdiff_t);
#else
extern Void_t*     sbrk();
#endif
#endif
#endif

/*
  MORECORE is the name of the routine to call to obtain more memory
  from the system.  See below for general guidance on writing
  alternative MORECORE functions, as well as a version for WIN32 and a
  sample version for pre-OSX macos.
*/

#ifndef MORECORE
#define MORECORE sbrk
#endif

/*
  MORECORE_FAILURE is the value returned upon failure of MORECORE
  as well as mmap. Since it cannot be an otherwise valid memory address,
  and must reflect values of standard sys calls, you probably ought not
  try to redefine it.
*/

#ifndef MORECORE_FAILURE
#define MORECORE_FAILURE (-1)
#endif

/*
  If MORECORE_CONTIGUOUS is true, take advantage of fact that
  consecutive calls to MORECORE with positive arguments always return
  contiguous increasing addresses.  This is true of unix sbrk.  Even
  if not defined, when regions happen to be contiguous, malloc will
  permit allocations spanning regions obtained from different
  calls. But defining this when applicable enables some stronger
  consistency checks and space efficiencies.
*/

#ifndef MORECORE_CONTIGUOUS
#define MORECORE_CONTIGUOUS 1
#endif

/*
  Define MORECORE_CANNOT_TRIM if your version of MORECORE
  cannot release space back to the system when given negative
  arguments. This is generally necessary only if you are using
  a hand-crafted MORECORE function that cannot handle negative arguments.
*/

/* #define MORECORE_CANNOT_TRIM */

/*  MORECORE_CLEARS           (default 1)
     The degree to which the routine mapped to MORECORE zeroes out
     memory: never (0), only for newly allocated space (1) or always
     (2).  The distinction between (1) and (2) is necessary because on
     some systems, if the application first decrements and then
     increments the break value, the contents of the reallocated space
     are unspecified.
*/

#ifndef MORECORE_CLEARS
#define MORECORE_CLEARS 1
#endif


/*
  Define HAVE_MMAP as true to optionally make malloc() use mmap() to
  allocate very large blocks.  These will be returned to the
  operating system immediately after a free(). Also, if mmap
  is available, it is used as a backup strategy in cases where
  MORECORE fails to provide space from system.

  This malloc is best tuned to work with mmap for large requests.
  If you do not have mmap, operations involving very large chunks (1MB
  or so) may be slower than you'd like.
*/

#ifndef HAVE_MMAP
#define HAVE_MMAP 1

/*
   Standard unix mmap using /dev/zero clears memory so calloc doesn't
   need to.
*/

#ifndef MMAP_CLEARS
#define MMAP_CLEARS 1
#endif

#else /* no mmap */
#ifndef MMAP_CLEARS
#define MMAP_CLEARS 0
#endif
#endif


/*
   MMAP_AS_MORECORE_SIZE is the minimum mmap size argument to use if
   sbrk fails, and mmap is used as a backup (which is done only if
   HAVE_MMAP).  The value must be a multiple of page size.  This
   backup strategy generally applies only when systems have "holes" in
   address space, so sbrk cannot perform contiguous expansion, but
   there is still space available on system.  On systems for which
   this is known to be useful (i.e. most linux kernels), this occurs
   only when programs allocate huge amounts of memory.  Between this,
   and the fact that mmap regions tend to be limited, the size should
   be large, to avoid too many mmap calls and thus avoid running out
   of kernel resources.
*/

#ifndef MMAP_AS_MORECORE_SIZE
#define MMAP_AS_MORECORE_SIZE (1024 * 1024)
#endif

/*
  Define HAVE_MREMAP to make realloc() use mremap() to re-allocate
  large blocks.  This is currently only possible on Linux with
  kernel versions newer than 1.3.77.
*/

#ifndef HAVE_MREMAP
#ifdef linux
#define HAVE_MREMAP 1
#else
#define HAVE_MREMAP 0
#endif

#endif /* HAVE_MMAP */

/* Define USE_ARENAS to enable support for multiple `arenas'.  These
   are allocated using mmap(), are necessary for threads and
   occasionally useful to overcome address space limitations affecting
   sbrk(). */

#ifndef USE_ARENAS
#define USE_ARENAS HAVE_MMAP
#endif


/*
  The system page size. To the extent possible, this malloc manages
  memory from the system in page-size units.  Note that this value is
  cached during initialization into a field of malloc_state. So even
  if malloc_getpagesize is a function, it is only called once.

  The following mechanics for getpagesize were adapted from bsd/gnu
  getpagesize.h. If none of the system-probes here apply, a value of
  4096 is used, which should be OK: If they don't apply, then using
  the actual value probably doesn't impact performance.
*/


#ifndef malloc_getpagesize

#ifndef LACKS_UNISTD_H
#  include <unistd.h>
#endif

#  ifdef _SC_PAGESIZE         /* some SVR4 systems omit an underscore */
#    ifndef _SC_PAGE_SIZE
#      define _SC_PAGE_SIZE _SC_PAGESIZE
#    endif
#  endif

#  ifdef _SC_PAGE_SIZE
#    define malloc_getpagesize sysconf(_SC_PAGE_SIZE)
#  else
#    if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE)
       extern size_t getpagesize();
#      define malloc_getpagesize getpagesize()
#    else
#      ifdef WIN32 /* use supplied emulation of getpagesize */
#        define malloc_getpagesize getpagesize()
#      else
#        ifndef LACKS_SYS_PARAM_H
#          include <sys/param.h>
#        endif
#        ifdef EXEC_PAGESIZE
#          define malloc_getpagesize EXEC_PAGESIZE
#        else
#          ifdef NBPG
#            ifndef CLSIZE
#              define malloc_getpagesize NBPG
#            else
#              define malloc_getpagesize (NBPG * CLSIZE)
#            endif
#          else
#            ifdef NBPC
#              define malloc_getpagesize NBPC
#            else
#              ifdef PAGESIZE
#                define malloc_getpagesize PAGESIZE
#              else /* just guess */
#                define malloc_getpagesize (4096)
#              endif
#            endif
#          endif
#        endif
#      endif
#    endif
#  endif
#endif

/*
  This version of malloc supports the standard SVID/XPG mallinfo
  routine that returns a struct containing usage properties and
  statistics. It should work on any SVID/XPG compliant system that has
  a /usr/include/malloc.h defining struct mallinfo. (If you'd like to
  install such a thing yourself, cut out the preliminary declarations
  as described above and below and save them in a malloc.h file. But
  there's no compelling reason to bother to do this.)

  The main declaration needed is the mallinfo struct that is returned
  (by-copy) by mallinfo().  The SVID/XPG malloinfo struct contains a
  bunch of fields that are not even meaningful in this version of
  malloc.  These fields are are instead filled by mallinfo() with
  other numbers that might be of interest.

  HAVE_USR_INCLUDE_MALLOC_H should be set if you have a
  /usr/include/malloc.h file that includes a declaration of struct
  mallinfo.  If so, it is included; else an SVID2/XPG2 compliant
  version is declared below.  These must be precisely the same for
  mallinfo() to work.  The original SVID version of this struct,
  defined on most systems with mallinfo, declares all fields as
  ints. But some others define as unsigned long. If your system
  defines the fields using a type of different width than listed here,
  you must #include your system version and #define
  HAVE_USR_INCLUDE_MALLOC_H.
*/

/* #define HAVE_USR_INCLUDE_MALLOC_H */

#ifdef HAVE_USR_INCLUDE_MALLOC_H
#include "/usr/include/malloc.h"
#endif


/* ---------- description of public routines ------------ */

/*
  malloc(size_t n)
  Returns a pointer to a newly allocated chunk of at least n bytes, or null
  if no space is available. Additionally, on failure, errno is
  set to ENOMEM on ANSI C systems.

  If n is zero, malloc returns a minumum-sized chunk. (The minimum
  size is 16 bytes on most 32bit systems, and 24 or 32 bytes on 64bit
  systems.)  On most systems, size_t is an unsigned type, so calls
  with negative arguments are interpreted as requests for huge amounts
  of space, which will often fail. The maximum supported value of n
  differs across systems, but is in all cases less than the maximum
  representable value of a size_t.
*/
#if __STD_C
Void_t*  public_mALLOc(size_t);
#else
Void_t*  public_mALLOc();
#endif

/*
  free(Void_t* p)
  Releases the chunk of memory pointed to by p, that had been previously
  allocated using malloc or a related routine such as realloc.
  It has no effect if p is null. It can have arbitrary (i.e., bad!)
  effects if p has already been freed.

  Unless disabled (using mallopt), freeing very large spaces will
  when possible, automatically trigger operations that give
  back unused memory to the system, thus reducing program footprint.
*/
#if __STD_C
void     public_fREe(Void_t*);
#else
void     public_fREe();
#endif

/*
  calloc(size_t n_elements, size_t element_size);
  Returns a pointer to n_elements * element_size bytes, with all locations
  set to zero.
*/
#if __STD_C
Void_t*  public_cALLOc(size_t, size_t);
#else
Void_t*  public_cALLOc();
#endif

/*
  realloc(Void_t* p, size_t n)
  Returns a pointer to a chunk of size n that contains the same data
  as does chunk p up to the minimum of (n, p's size) bytes, or null
  if no space is available.

  The returned pointer may or may not be the same as p. The algorithm
  prefers extending p when possible, otherwise it employs the
  equivalent of a malloc-copy-free sequence.

  If p is null, realloc is equivalent to malloc.

  If space is not available, realloc returns null, errno is set (if on
  ANSI) and p is NOT freed.

  if n is for fewer bytes than already held by p, the newly unused
  space is lopped off and freed if possible.  Unless the #define
  REALLOC_ZERO_BYTES_FREES is set, realloc with a size argument of
  zero (re)allocates a minimum-sized chunk.

  Large chunks that were internally obtained via mmap will always
  be reallocated using malloc-copy-free sequences unless
  the system supports MREMAP (currently only linux).

  The old unix realloc convention of allowing the last-free'd chunk
  to be used as an argument to realloc is not supported.
*/
#if __STD_C
Void_t*  public_rEALLOc(Void_t*, size_t);
#else
Void_t*  public_rEALLOc();
#endif

/*
  memalign(size_t alignment, size_t n);
  Returns a pointer to a newly allocated chunk of n bytes, aligned
  in accord with the alignment argument.

  The alignment argument should be a power of two. If the argument is
  not a power of two, the nearest greater power is used.
  8-byte alignment is guaranteed by normal malloc calls, so don't
  bother calling memalign with an argument of 8 or less.

  Overreliance on memalign is a sure way to fragment space.
*/
#if __STD_C
Void_t*  public_mEMALIGn(size_t, size_t);
#else
Void_t*  public_mEMALIGn();
#endif

/*
  valloc(size_t n);
  Equivalent to memalign(pagesize, n), where pagesize is the page
  size of the system. If the pagesize is unknown, 4096 is used.
*/
#if __STD_C
Void_t*  public_vALLOc(size_t);
#else
Void_t*  public_vALLOc();
#endif



/*
  mallopt(int parameter_number, int parameter_value)
  Sets tunable parameters The format is to provide a
  (parameter-number, parameter-value) pair.  mallopt then sets the
  corresponding parameter to the argument value if it can (i.e., so
  long as the value is meaningful), and returns 1 if successful else
  0.  SVID/XPG/ANSI defines four standard param numbers for mallopt,
  normally defined in malloc.h.  Only one of these (M_MXFAST) is used
  in this malloc. The others (M_NLBLKS, M_GRAIN, M_KEEP) don't apply,
  so setting them has no effect. But this malloc also supports four
  other options in mallopt. See below for details.  Briefly, supported
  parameters are as follows (listed defaults are for "typical"
  configurations).

  Symbol            param #   default    allowed param values
  M_MXFAST          1         64         0-80  (0 disables fastbins)
  M_TRIM_THRESHOLD -1         128*1024   any   (-1U disables trimming)
  M_TOP_PAD        -2         0          any
  M_MMAP_THRESHOLD -3         128*1024   any   (or 0 if no MMAP support)
  M_MMAP_MAX       -4         65536      any   (0 disables use of mmap)
*/
#if __STD_C
int      public_mALLOPt(int, int);
#else
int      public_mALLOPt();
#endif


/*
  mallinfo()
  Returns (by copy) a struct containing various summary statistics:

  arena:     current total non-mmapped bytes allocated from system
  ordblks:   the number of free chunks
  smblks:    the number of fastbin blocks (i.e., small chunks that
               have been freed but not use resused or consolidated)
  hblks:     current number of mmapped regions
  hblkhd:    total bytes held in mmapped regions
  usmblks:   the maximum total allocated space. This will be greater
                than current total if trimming has occurred.
  fsmblks:   total bytes held in fastbin blocks
  uordblks:  current total allocated space (normal or mmapped)
  fordblks:  total free space
  keepcost:  the maximum number of bytes that could ideally be released
               back to system via malloc_trim. ("ideally" means that
               it ignores page restrictions etc.)

  Because these fields are ints, but internal bookkeeping may
  be kept as longs, the reported values may wrap around zero and
  thus be inaccurate.
*/
#if __STD_C
struct mallinfo public_mALLINFo(void);
#else
struct mallinfo public_mALLINFo();
#endif

/*
  independent_calloc(size_t n_elements, size_t element_size, Void_t* chunks[]);

  independent_calloc is similar to calloc, but instead of returning a
  single cleared space, it returns an array of pointers to n_elements
  independent elements that can hold contents of size elem_size, each
  of which starts out cleared, and can be independently freed,
  realloc'ed etc. The elements are guaranteed to be adjacently
  allocated (this is not guaranteed to occur with multiple callocs or
  mallocs), which may also improve cache locality in some
  applications.

  The "chunks" argument is optional (i.e., may be null, which is
  probably the most typical usage). If it is null, the returned array
  is itself dynamically allocated and should also be freed when it is
  no longer needed. Otherwise, the chunks array must be of at least
  n_elements in length. It is filled in with the pointers to the
  chunks.

  In either case, independent_calloc returns this pointer array, or
  null if the allocation failed.  If n_elements is zero and "chunks"
  is null, it returns a chunk representing an array with zero elements
  (which should be freed if not wanted).

  Each element must be individually freed when it is no longer
  needed. If you'd like to instead be able to free all at once, you
  should instead use regular calloc and assign pointers into this
  space to represent elements.  (In this case though, you cannot
  independently free elements.)

  independent_calloc simplifies and speeds up implementations of many
  kinds of pools.  It may also be useful when constructing large data
  structures that initially have a fixed number of fixed-sized nodes,
  but the number is not known at compile time, and some of the nodes
  may later need to be freed. For example:

  struct Node { int item; struct Node* next; };

  struct Node* build_list() {
    struct Node** pool;
    int n = read_number_of_nodes_needed();
    if (n <= 0) return 0;
    pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
    if (pool == 0) die();
    // organize into a linked list...
    struct Node* first = pool[0];
    for (i = 0; i < n-1; ++i)
      pool[i]->next = pool[i+1];
    free(pool);     // Can now free the array (or not, if it is needed later)
    return first;
  }
*/
#if __STD_C
Void_t** public_iCALLOc(size_t, size_t, Void_t**);
#else
Void_t** public_iCALLOc();
#endif

/*
  independent_comalloc(size_t n_elements, size_t sizes[], Void_t* chunks[]);

  independent_comalloc allocates, all at once, a set of n_elements
  chunks with sizes indicated in the "sizes" array.    It returns
  an array of pointers to these elements, each of which can be
  independently freed, realloc'ed etc. The elements are guaranteed to
  be adjacently allocated (this is not guaranteed to occur with
  multiple callocs or mallocs), which may also improve cache locality
  in some applications.

  The "chunks" argument is optional (i.e., may be null). If it is null
  the returned array is itself dynamically allocated and should also
  be freed when it is no longer needed. Otherwise, the chunks array
  must be of at least n_elements in length. It is filled in with the
  pointers to the chunks.

  In either case, independent_comalloc returns this pointer array, or
  null if the allocation failed.  If n_elements is zero and chunks is
  null, it returns a chunk representing an array with zero elements
  (which should be freed if not wanted).

  Each element must be individually freed when it is no longer
  needed. If you'd like to instead be able to free all at once, you
  should instead use a single regular malloc, and assign pointers at
  particular offsets in the aggregate space. (In this case though, you
  cannot independently free elements.)

  independent_comallac differs from independent_calloc in that each
  element may have a different size, and also that it does not
  automatically clear elements.

  independent_comalloc can be used to speed up allocation in cases
  where several structs or objects must always be allocated at the
  same time.  For example:

  struct Head { ... }
  struct Foot { ... }

  void send_message(char* msg) {
    int msglen = strlen(msg);
    size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
    void* chunks[3];
    if (independent_comalloc(3, sizes, chunks) == 0)
      die();
    struct Head* head = (struct Head*)(chunks[0]);
    char*        body = (char*)(chunks[1]);
    struct Foot* foot = (struct Foot*)(chunks[2]);
    // ...
  }

  In general though, independent_comalloc is worth using only for
  larger values of n_elements. For small values, you probably won't
  detect enough difference from series of malloc calls to bother.

  Overuse of independent_comalloc can increase overall memory usage,
  since it cannot reuse existing noncontiguous small chunks that
  might be available for some of the elements.
*/
#if __STD_C
Void_t** public_iCOMALLOc(size_t, size_t*, Void_t**);
#else
Void_t** public_iCOMALLOc();
#endif


/*
  pvalloc(size_t n);
  Equivalent to valloc(minimum-page-that-holds(n)), that is,
  round up n to nearest pagesize.
 */
#if __STD_C
Void_t*  public_pVALLOc(size_t);
#else
Void_t*  public_pVALLOc();
#endif

/*
  cfree(Void_t* p);
  Equivalent to free(p).

  cfree is needed/defined on some systems that pair it with calloc,
  for odd historical reasons (such as: cfree is used in example
  code in the first edition of K&R).
*/
#if __STD_C
void     public_cFREe(Void_t*);
#else
void     public_cFREe();
#endif

/*
  malloc_trim(size_t pad);

  If possible, gives memory back to the system (via negative
  arguments to sbrk) if there is unused memory at the `high' end of
  the malloc pool. You can call this after freeing large blocks of
  memory to potentially reduce the system-level memory requirements
  of a program. However, it cannot guarantee to reduce memory. Under
  some allocation patterns, some large free blocks of memory will be
  locked between two used chunks, so they cannot be given back to
  the system.

  The `pad' argument to malloc_trim represents the amount of free
  trailing space to leave untrimmed. If this argument is zero,
  only the minimum amount of memory to maintain internal data
  structures will be left (one page or less). Non-zero arguments
  can be supplied to maintain enough trailing space to service
  future expected allocations without having to re-obtain memory
  from the system.

  Malloc_trim returns 1 if it actually released any memory, else 0.
  On systems that do not support "negative sbrks", it will always
  rreturn 0.
*/
#if __STD_C
int      public_mTRIm(size_t);
#else
int      public_mTRIm();
#endif

/*
  malloc_usable_size(Void_t* p);

  Returns the number of bytes you can actually use in
  an allocated chunk, which may be more than you requested (although
  often not) due to alignment and minimum size constraints.
  You can use this many bytes without worrying about
  overwriting other allocated objects. This is not a particularly great
  programming practice. malloc_usable_size can be more useful in
  debugging and assertions, for example:

  p = malloc(n);
  assert(malloc_usable_size(p) >= 256);

*/
#if __STD_C
size_t   public_mUSABLe(Void_t*);
#else
size_t   public_mUSABLe();
#endif

/*
  malloc_stats();
  Prints on stderr the amount of space obtained from the system (both
  via sbrk and mmap), the maximum amount (which may be more than
  current if malloc_trim and/or munmap got called), and the current
  number of bytes allocated via malloc (or realloc, etc) but not yet
  freed. Note that this is the number of bytes allocated, not the
  number requested. It will be larger than the number requested
  because of alignment and bookkeeping overhead. Because it includes
  alignment wastage as being in use, this figure may be greater than
  zero even when no user-level chunks are allocated.

  The reported current and maximum system memory can be inaccurate if
  a program makes other calls to system memory allocation functions
  (normally sbrk) outside of malloc.

  malloc_stats prints only the most commonly interesting statistics.
  More information can be obtained by calling mallinfo.

*/
#if __STD_C
void     public_mSTATs(void);
#else
void     public_mSTATs();
#endif

/*
  malloc_get_state(void);

  Returns the state of all malloc variables in an opaque data
  structure.
*/
#if __STD_C
Void_t*  public_gET_STATe(void);
#else
Void_t*  public_gET_STATe();
#endif

/*
  malloc_set_state(Void_t* state);

  Restore the state of all malloc variables from data obtained with
  malloc_get_state().
*/
#if __STD_C
int      public_sET_STATe(Void_t*);
#else
int      public_sET_STATe();
#endif

#ifdef _LIBC
/*
  posix_memalign(void **memptr, size_t alignment, size_t size);

  POSIX wrapper like memalign(), checking for validity of size.
*/
int      __posix_memalign(void **, size_t, size_t);
#endif

/* mallopt tuning options */

/*
  M_MXFAST is the maximum request size used for "fastbins", special bins
  that hold returned chunks without consolidating their spaces. This
  enables future requests for chunks of the same size to be handled
  very quickly, but can increase fragmentation, and thus increase the
  overall memory footprint of a program.

  This malloc manages fastbins very conservatively yet still
  efficiently, so fragmentation is rarely a problem for values less
  than or equal to the default.  The maximum supported value of MXFAST
  is 80. You wouldn't want it any higher than this anyway.  Fastbins
  are designed especially for use with many small structs, objects or
  strings -- the default handles structs/objects/arrays with sizes up
  to 8 4byte fields, or small strings representing words, tokens,
  etc. Using fastbins for larger objects normally worsens
  fragmentation without improving speed.

  M_MXFAST is set in REQUEST size units. It is internally used in
  chunksize units, which adds padding and alignment.  You can reduce
  M_MXFAST to 0 to disable all use of fastbins.  This causes the malloc
  algorithm to be a closer approximation of fifo-best-fit in all cases,
  not just for larger requests, but will generally cause it to be
  slower.
*/


/* M_MXFAST is a standard SVID/XPG tuning option, usually listed in malloc.h */
#ifndef M_MXFAST
#define M_MXFAST            1
#endif

#ifndef DEFAULT_MXFAST
#define DEFAULT_MXFAST     128
#endif


/*
  M_TRIM_THRESHOLD is the maximum amount of unused top-most