dlmalloc.c

来自「minimal python variant for small footpri」· C语言 代码 · 共 1,900 行 · 第 1/5 页

  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**);
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);
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

#endif /*DL_MINIMAL*/

/*
  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

#ifndef DL_MINIMAL
/*
  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();
#else
void     public_mSTATs();
#endif

#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     64
#endif


/*
  M_TRIM_THRESHOLD is the maximum amount of unused top-most memory
  to keep before releasing via malloc_trim in free().

  Automatic trimming is mainly useful in long-lived programs.
  Because trimming via sbrk can be slow on some systems, and can
  sometimes be wasteful (in cases where programs immediately
  afterward allocate more large chunks) the value should be high
  enough so that your overall system performance would improve by
  releasing this much memory.

  The trim threshold and the mmap control parameters (see below)
  can be traded off with one another. Trimming and mmapping are
  two different ways of releasing unused memory back to the
  system. Between these two, it is often possible to keep
  system-level demands of a long-lived program down to a bare
  minimum. For example, in one test suite of sessions measuring
  the XF86 X server on Linux, using a trim threshold of 128K and a
  mmap threshold of 192K led to near-minimal long term resource
  consumption.

  If you are using this malloc in a long-lived program, it should
  pay to experiment with these values.  As a rough guide, you
  might set to a value close to the average size of a process
  (program) running on your system.  Releasing this much memory
  would allow such a process to run in memory.  Generally, it's
  worth it to tune for trimming rather tham memory mapping when a
  program undergoes phases where several large chunks are
  allocated and released in ways that can reuse each other's
  storage, perhaps mixed with phases where there are no such
  chunks at all.  And in well-behaved long-lived programs,
  controlling release of large blocks via trimming versus mapping
  is usually faster.

  However, in most programs, these parameters serve mainly as
  protection against the system-level effects of carrying around
  massive amounts of unneeded memory. Since frequent calls to
  sbrk, mmap, and munmap otherwise degrade performance, the default
  parameters are set to relatively high values that serve only as
  safeguards.

  The trim value It must be greater than page size to have any useful
  effect.  To disable trimming completely, you can set to 
  (unsigned long)(-1)

  Trim settings interact with fastbin (MXFAST) settings: Unless
  TRIM_FASTBINS is defined, automatic trimming never takes place upon
  freeing a chunk with size less than or equal to MXFAST. Trimming is
  instead delayed until subsequent freeing of larger chunks. However,
  you can still force an attempted trim by calling malloc_trim.

  Also, trimming is not generally possible in cases where
  the main arena is obtained via mmap.

  Note that the trick some people use of mallocing a huge space and
  then freeing it at program startup, in an attempt to reserve system
  memory, doesn't have the intended effect under automatic trimming,
  since that memory will immediately be returned to the system.
*/

#define M_TRIM_THRESHOLD       -1

#ifndef DEFAULT_TRIM_THRESHOLD
#define DEFAULT_TRIM_THRESHOLD (128L * 1024L)
#endif

/*
  M_TOP_PAD is the amount of extra `padding' space to allocate or
  retain whenever sbrk is called. It is used in two ways internally:

  * When sbrk is called to extend the top of the arena to satisfy
  a new malloc request, this much padding is added to the sbrk
  request.

  * When malloc_trim is called automatically from free(),
  it is used as the `pad' argument.

  In both cases, the actual amount of padding is rounded
  so that the end of the arena is always a system page boundary.

  The main reason for using padding is to avoid calling sbrk so
  often. Having even a small pad greatly reduces the likelihood
  that nearly every malloc request during program start-up (or
  after trimming) will invoke sbrk, which needlessly wastes
  time.

  Automatic rounding-up to page-size units is normally sufficient
  to avoid measurable overhead, so the default is 0.  However, in
  systems where sbrk is relatively slow, it can pay to increase
  this value, at the expense of carrying around more memory than
  the program needs.
*/

#define M_TOP_PAD              -2

#ifndef DEFAULT_TOP_PAD
#define DEFAULT_TOP_PAD        (0)
#endif

/*
  M_MMAP_THRESHOLD is the request size threshold for using mmap()
  to service a request. Requests of at least this size that cannot
  be allocated using already-existing space will be serviced via mmap.
  (If enough normal freed space already exists it is used instead.)

  Using mmap segregates relatively large chunks of memory so that
  they can be individually obtained and released from the host
  system. A request serviced through mmap is never reused by any
  other request (at least not directly; the system may just so
  happen to remap successive requests to the same locations).

  Segregating space in this way has the benefits that:

   1. Mmapped space can ALWAYS be individually released back 
      to the system, which helps keep the system level memory 
      demands of a long-lived program low. 
   2. Mapped memory can never become `locked' between
      other chunks, as can happen with normally allocated chunks, which
      means that even trimming via malloc_trim would not release them.
   3. On some systems with "holes" in address spaces, mmap can obtain
      memory that sbrk cannot.

  However, it has the disadvantages that:

   1. The space cannot be reclaimed, consolidated, and then
      used to service later requests, as happens with normal chunks.
   2. It can lead to more wastage because of mmap page alignment
      requirements
   3. It causes malloc performance to be more dependent on host
      system memory management support routines which may vary in
      implementation quality and may impose arbitrary
      limitations. Generally, servicing a request via normal
      malloc steps is faster than going through a system's mmap.

  The advantages of mmap nearly always outweigh disadvantages for
  "large" chunks, but the value of "large" varies across systems.  The
  default is an empirically derived value that works well in most
  systems.
*/

#define M_MMAP_THRESHOLD      -3

#ifndef DEFAULT_MMAP_THRESHOLD
#define DEFAULT_MMAP_THRESHOLD (128L * 1024L)
#endif

/*
  M_MMAP_MAX is the maximum number of requests to simultaneously
  service using mmap. This parameter exists because
. Some systems have a limited number of internal tables for
  use by mmap, and using more than a few of them may degrade
  performance.

  The default is set to a value that serves only as a safeguard.
  Setting to 0 disables use of mmap for servicing large requests.  If
  HAVE_MMAP is not set, the default value is 0, and attempts to set it
  to non-zero values in mallopt will fail.
*/

#define M_MMAP_MAX             -4

#ifndef DEFAULT_MMAP_MAX
#if HAVE_MMAP
#define DEFAULT_MMAP_MAX       (65536)
#else
#define DEFAULT_MMAP_MAX       (0)
#endif
#endif

#ifdef __cplusplus
};  /* end of extern "C" */
#endif

/* 
  ========================================================================
  To make a fully customizable malloc.h header file, cut everything
  above this line, put into file malloc.h, edit to suit, and #include it 
  on the next line, as well as in programs that use this malloc.
  ========================================================================
*/

/* #include "malloc.h" */

/* --------------------- public wrappers ---------------------- */

#ifdef USE_PUBLIC_MALLOC_WRAPPERS

/* Declare all routines as internal */
#if __STD_C
static Void_t*  mALLOc(size_t);
static void     fREe(Void_t*);
static Void_t*  rEALLOc(Void_t*, size_t);
static Void_t*  mEMALIGn(size_t, size_t);
static Void_t*  vALLOc(size_t);
static Void_t*  pVALLOc(size_t);
static Void_t*  cALLOc(size_t, size_t);
static Void_t** iCALLOc(size_t, size_t, Void_t**);
static Void_t** iCOMALLOc(size_t, size_t*, Void_t**);