#include "Yap.h"

#if USE_DL_MALLOC

#include "YapHeap.h"
#if HAVE_STRING_H
#include <string.h>
#endif
#include "alloc.h"
#include "dlmalloc.h"

static struct malloc_chunk *
ChunkPtrAdjust (struct malloc_chunk *ptr)
{
  return (struct malloc_chunk *) ((char *) (ptr) + HDiff);
}



/*
  This is a version (aka dlmalloc) of malloc/free/realloc written by
  Doug Lea and released to the public domain.  Use, modify, and
  redistribute this code without permission or acknowledgement in any
  way you wish.  Send questions, comments, complaints, performance
  data, etc to dl@cs.oswego.edu

* VERSION 2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)

   Note: There may be an updated version of this malloc obtainable at
           ftp://gee.cs.oswego.edu/pub/misc/malloc.c
         Check before installing!

* Quickstart

  This library is all in one file to simplify the most common usage:
  ftp it, compile it (-O), and link it into another program. All
  of the compile-time options default to reasonable values for use on
  most unix platforms. Compile -DWIN32 for reasonable defaults on windows.
  You might later want to step through various compile-time and dynamic
  tuning options.

  For convenience, an include file for code using this malloc is at:
     ftp://gee.cs.oswego.edu/pub/misc/malloc-2.7.1.h
  You don't really need this .h file unless you call functions not
  defined in your system include files.  The .h file contains only the
  excerpts from this file needed for using this malloc on ANSI C/C++
  systems, so long as you haven't changed compile-time options about
  naming and tuning parameters.  If you do, then you can create your
  own malloc.h that does include all settings by cutting at the point
  indicated below.

* 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: NOT thread-safe unless USE_MALLOC_LOCK defined

       When USE_MALLOC_LOCK is defined, wrappers are created to
       surround every public call with either a pthread mutex or
       a win32 spinlock (depending on WIN32). This is not
       especially fast, and can be a major bottleneck.
       It is designed only to provide minimal protection
       in concurrent environments, and to provide a basis for
       extensions.  If you are using malloc in a concurrent program,
       you would be far better off obtaining ptmalloc, which is
       derived from a version of this malloc, and is well-tuned for
       concurrent programs. (See http://www.malloc.de) Note that
       even when USE_MALLOC_LOCK is defined, you can can guarantee
       full thread-safety only if no threads acquire memory through 
       direct calls to MORECORE or other system-level allocators.

  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.

*/

/* vsc: emulation of sbrk with YAP contiguous memory management */

void
Yap_add_memory_hole(ADDR start, ADDR end)
{
  if (Yap_NOfMemoryHoles == MAX_DLMALLOC_HOLES) {
    Yap_Error(OPERATING_SYSTEM_ERROR, 0L, "Unexpected Too Much Memory Fragmentation: please contact YAP maintainers");
    return;
  }
  Yap_MemoryHoles[Yap_NOfMemoryHoles].start = start;
  Yap_MemoryHoles[Yap_NOfMemoryHoles].end = end;
  Yap_HoleSize += (UInt)(start-end);
  Yap_NOfMemoryHoles++;
}

static void *
yapsbrk(long size)
{
  ADDR newHeapTop = HeapTop, oldHeapTop = HeapTop;
  newHeapTop = HeapTop+size;
  while (Yap_NOfMemoryHoles && newHeapTop > Yap_MemoryHoles[0].start) {
    UInt i;

    HeapTop = oldHeapTop = Yap_MemoryHoles[0].end;
    newHeapTop = oldHeapTop+size;
    Yap_NOfMemoryHoles--;
    for (i=0; i < Yap_NOfMemoryHoles; i++) {
      Yap_MemoryHoles[i].start = Yap_MemoryHoles[i+1].start;
      Yap_MemoryHoles[i].end = Yap_MemoryHoles[i+1].end;
    }
  }
  if (newHeapTop > HeapLim - MinHeapGap) {
    if (HeapTop + size < HeapLim) {
      /* small allocations, we can wait */
      HeapTop += size;
      UNLOCK(HeapTopLock);
      Yap_signal(YAP_CDOVF_SIGNAL);
    } else {
     if (size > SizeOfOverflow)
	SizeOfOverflow = size;
      /* big allocations, the caller must handle the problem */
      UNLOCK(HeapUsedLock);
      UNLOCK(HeapTopLock);
      return (void *)MORECORE_FAILURE;
    }
  }
  HeapTop = newHeapTop;
  UNLOCK(HeapTopLock);
  return oldHeapTop;
}

/*
  Compute index for size. We expect this to be inlined when
  compiled with optimization, else not, which works out well.
*/
static int largebin_index(unsigned int sz) {
  unsigned int  x = sz >> SMALLBIN_WIDTH; 
  unsigned int m;            /* bit position of highest set bit of m */

  if (x >= 0x10000) return NBINS-1;

  /* On intel, use BSRL instruction to find highest bit */
#if defined(__GNUC__) && defined(i386)

  __asm__("bsrl %1,%0\n\t"
          : "=r" (m) 
          : "g"  (x));

#else
  {
    /*
      Based on branch-free nlz algorithm in chapter 5 of Henry
      S. Warren Jr's book "Hacker's Delight".
    */

    unsigned int n = ((x - 0x100) >> 16) & 8;
    x <<= n; 
    m = ((x - 0x1000) >> 16) & 4;
    n += m; 
    x <<= m; 
    m = ((x - 0x4000) >> 16) & 2;
    n += m; 
    x = (x << m) >> 14;
    m = 13 - n + (x & ~(x>>1));
  }
#endif

  /* Use next 2 bits to create finer-granularity bins */
  return NSMALLBINS + (m << 2) + ((sz >> (m + 6)) & 3);
}

#define bin_index(sz) \
 ((in_smallbin_range(sz)) ? smallbin_index(sz) : largebin_index(sz))

/*
  FIRST_SORTED_BIN_SIZE is the chunk size corresponding to the
  first bin that is maintained in sorted order. This must
  be the smallest size corresponding to a given bin.

  Normally, this should be MIN_LARGE_SIZE. But you can weaken
  best fit guarantees to sometimes speed up malloc by increasing value.
  Doing this means that malloc may choose a chunk that is 
  non-best-fitting by up to the width of the bin.

  Some useful cutoff values:
      512 - all bins sorted
     2560 - leaves bins <=     64 bytes wide unsorted  
    12288 - leaves bins <=    512 bytes wide unsorted
    65536 - leaves bins <=   4096 bytes wide unsorted
   262144 - leaves bins <=  32768 bytes wide unsorted
       -1 - no bins sorted (not recommended!)
*/

/*#define FIRST_SORTED_BIN_SIZE MIN_LARGE_SIZE */
#define FIRST_SORTED_BIN_SIZE 2056

/*
  Unsorted chunks

    All remainders from chunk splits, as well as all returned chunks,
    are first placed in the "unsorted" bin. They are then placed
    in regular bins after malloc gives them ONE chance to be used before
    binning. So, basically, the unsorted_chunks list acts as a queue,
    with chunks being placed on it in free (and malloc_consolidate),
    and taken off (to be either used or placed in bins) in malloc.
*/

/* The otherwise unindexable 1-bin is used to hold unsorted chunks. */
#define unsorted_chunks(M)          (bin_at(M, 1))

/*
  Top

    The top-most available chunk (i.e., the one bordering the end of
    available memory) is treated specially. It is never included in
    any bin, is used only if no other chunk is available, and is
    released back to the system if it is very large (see
    M_TRIM_THRESHOLD).  Because top initially
    points to its own bin with initial zero size, thus forcing
    extension on the first malloc request, we avoid having any special
    code in malloc to check whether it even exists yet. But we still
    need to do so when getting memory from system, so we make
    initial_top treat the bin as a legal but unusable chunk during the
    interval between initialization and the first call to
    sYSMALLOc. (This is somewhat delicate, since it relies on
    the 2 preceding words to be zero during this interval as well.)
*/

/* Conveniently, the unsorted bin can be used as dummy top on first call */
#define initial_top(M)              (unsorted_chunks(M))

/*
  Binmap

    To help compensate for the large number of bins, a one-level index
    structure is used for bin-by-bin searching.  `binmap' is a
    bitvector recording whether bins are definitely empty so they can
    be skipped over during during traversals.  The bits are NOT always
    cleared as soon as bins are empty, but instead only
    when they are noticed to be empty during traversal in malloc.
*/

#define idx2block(i)     ((i) >> BINMAPSHIFT)
#define idx2bit(i)       ((1U << ((i) & ((1U << BINMAPSHIFT)-1))))

#define mark_bin(m,i)    ((m)->binmap[idx2block(i)] |=  idx2bit(i))
#define unmark_bin(m,i)  ((m)->binmap[idx2block(i)] &= ~(idx2bit(i)))
#define get_binmap(m,i)  ((m)->binmap[idx2block(i)] &   idx2bit(i))

/*
  Fastbins

    An array of lists holding recently freed small chunks.  Fastbins
    are not doubly linked.  It is faster to single-link them, and
    since chunks are never removed from the middles of these lists,
    double linking is not necessary. Also, unlike regular bins, they
    are not even processed in FIFO order (they use faster LIFO) since
    ordering doesn't much matter in the transient contexts in which
    fastbins are normally used.

    Chunks in fastbins keep their inuse bit set, so they cannot
    be consolidated with other free chunks. malloc_consolidate
    releases all chunks in fastbins and consolidates them with
    other free chunks. 
*/

/*
  FASTBIN_CONSOLIDATION_THRESHOLD is the size of a chunk in free()
  that triggers automatic consolidation of possibly-surrounding
  fastbin chunks. This is a heuristic, so the exact value should not
  matter too much. It is defined at half the default trim threshold as a
  compromise heuristic to only attempt consolidation if it is likely
  to lead to trimming. However, it is not dynamically tunable, since
  consolidation reduces fragmentation surrounding loarge chunks even 
  if trimming is not used.
*/

#define FASTBIN_CONSOLIDATION_THRESHOLD  \
  ((unsigned long)(DEFAULT_TRIM_THRESHOLD) >> 1)

/*
  Since the lowest 2 bits in max_fast don't matter in size comparisons, 
  they are used as flags.
*/

/*
  ANYCHUNKS_BIT held in max_fast indicates that there may be any
  freed chunks at all. It is set true when entering a chunk into any
  bin.
*/

#define ANYCHUNKS_BIT        (1U)

#define have_anychunks(M)     (((M)->max_fast &  ANYCHUNKS_BIT))
#define set_anychunks(M)      ((M)->max_fast |=  ANYCHUNKS_BIT)
#define clear_anychunks(M)    ((M)->max_fast &= ~ANYCHUNKS_BIT)

/*
  FASTCHUNKS_BIT held in max_fast indicates that there are probably
  some fastbin chunks. It is set true on entering a chunk into any
  fastbin, and cleared only in malloc_consolidate.
*/

#define FASTCHUNKS_BIT        (2U)

#define have_fastchunks(M)   (((M)->max_fast &  FASTCHUNKS_BIT))
#define set_fastchunks(M)    ((M)->max_fast |=  (FASTCHUNKS_BIT|ANYCHUNKS_BIT))
#define clear_fastchunks(M)  ((M)->max_fast &= ~(FASTCHUNKS_BIT))

/* 
   Set value of max_fast. 
   Use impossibly small value if 0.
*/

#define set_max_fast(M, s) \
  (M)->max_fast = (((s) == 0)? SMALLBIN_WIDTH: request2size(s)) | \
  ((M)->max_fast &  (FASTCHUNKS_BIT|ANYCHUNKS_BIT))

#define get_max_fast(M) \
  ((M)->max_fast & ~(FASTCHUNKS_BIT | ANYCHUNKS_BIT))


/*
  morecore_properties is a status word holding dynamically discovered
  or controlled properties of the morecore function
*/

#define MORECORE_CONTIGUOUS_BIT  (1U)

#define contiguous(M) \
        (((M)->morecore_properties &  MORECORE_CONTIGUOUS_BIT))
#define noncontiguous(M) \
        (((M)->morecore_properties &  MORECORE_CONTIGUOUS_BIT) == 0)
#define set_contiguous(M) \
        ((M)->morecore_properties |=  MORECORE_CONTIGUOUS_BIT)
#define set_noncontiguous(M) \
        ((M)->morecore_properties &= ~MORECORE_CONTIGUOUS_BIT)


/* 
   There is exactly one instance of this struct in this malloc.
   If you are adapting this malloc in a way that does NOT use a static
   malloc_state, you MUST explicitly zero-fill it before using. This
   malloc relies on the property that malloc_state is initialized to
   all zeroes (as is true of C statics).
*/

/* static struct malloc_state av_; */  /* never directly referenced */

/*
   All uses of av_ are via get_malloc_state().
   At most one "call" to get_malloc_state is made per invocation of
   the public versions of malloc and free, but other routines
   that in turn invoke malloc and/or free may call more then once. 
   Also, it is called in check* routines if DEBUG is set.
*/

/* #define get_malloc_state() (&(av_)) */
#define get_malloc_state()  Yap_av

/*
  Initialize a malloc_state struct.

  This is called only from within malloc_consolidate, which needs
  be called in the same contexts anyway.  It is never called directly
  outside of malloc_consolidate because some optimizing compilers try
  to inline it at all call points, which turns out not to be an
  optimization at all. (Inlining it in malloc_consolidate is fine though.)
*/

#if __STD_C
static void malloc_init_state(mstate av)
#else
static void malloc_init_state(av) mstate av;
#endif
{
  int     i;
  mbinptr bin;
  
  /* Establish circular links for normal bins */
  for (i = 1; i < NBINS; ++i) { 
    bin = bin_at(av,i);
    bin->fd = bin->bk = bin;
  }

  av->top_pad        = DEFAULT_TOP_PAD;
  av->trim_threshold = DEFAULT_TRIM_THRESHOLD;

#if MORECORE_CONTIGUOUS
  set_contiguous(av);
#else
  set_noncontiguous(av);
#endif


  set_max_fast(av, DEFAULT_MXFAST);

  av->top            = initial_top(av);
  av->pagesize       = malloc_getpagesize;
}

/* 
   Other internal utilities operating on mstates
*/

#if __STD_C
static Void_t*  sYSMALLOc(INTERNAL_SIZE_T, mstate);
static int      sYSTRIm(size_t, mstate);
static void     malloc_consolidate(mstate);
static Void_t** iALLOc(size_t, size_t*, int, Void_t**);
#else
static Void_t*  sYSMALLOc();
static int      sYSTRIm();
static void     malloc_consolidate();
static Void_t** iALLOc();
#endif

/*
  Debugging support

  These routines make a number of assertions about the states
  of data structures that should be true at all times. If any
  are not true, it's very likely that a user program has somehow
  trashed memory. (It's also possible that there is a coding error
  in malloc. In which case, please report it!)
*/

#if ! DEBUG_DLMALLOC

#define check_chunk(P)
#define check_free_chunk(P)
#define check_inuse_chunk(P)
#define check_remalloced_chunk(P,N)
#define check_malloced_chunk(P,N)
#define check_malloc_state()

#else
#define check_chunk(P)              do_check_chunk(P)
#define check_free_chunk(P)         do_check_free_chunk(P)
#define check_inuse_chunk(P)        do_check_inuse_chunk(P)
#define check_remalloced_chunk(P,N) do_check_remalloced_chunk(P,N)
#define check_malloced_chunk(P,N)   do_check_malloced_chunk(P,N)
#define check_malloc_state()        do_check_malloc_state()

/*
  Properties of all chunks
*/

#if __STD_C
static void do_check_chunk(mchunkptr p)
#else
static void do_check_chunk(p) mchunkptr p;
#endif
{
  mstate av = get_malloc_state();
#if DEBUG_DLMALLOC
  /* min and max possible addresses assuming contiguous allocation */
  char* max_address = (char*)(av->top) + chunksize(av->top);
  CHUNK_SIZE_T  sz = chunksize(p);
  char* min_address = max_address - av->sbrked_mem;
#endif

  if (!chunk_is_mmapped(p)) {
    
    /* Has legal address ... */
    if (p != av->top) {
      if (contiguous(av)) {
        assert(((char*)p) >= min_address);
        assert(((char*)p + sz) <= ((char*)(av->top)));
      }
    }
    else {
      /* top size is always at least MINSIZE */
      assert((CHUNK_SIZE_T)(sz) >= MINSIZE);
      /* top predecessor always marked inuse */
      assert(prev_inuse(p));
    }
      
  }
  else {
#if HAVE_MMAP
    /* address is outside main heap  */
    if (contiguous(av) && av->top != initial_top(av)) {
      assert(((char*)p) < min_address || ((char*)p) > max_address);
    }
    /* chunk is page-aligned */
    assert(((p->prev_size + sz) & (av->pagesize-1)) == 0);
    /* mem is aligned */
    assert(aligned_OK(chunk2mem(p)));
#else
    /* force an appropriate assert violation if debug set */
    assert(!chunk_is_mmapped(p));
#endif
  }
}

/*
  Properties of free chunks
*/

#if __STD_C
static void do_check_free_chunk(mchunkptr p)
#else
static void do_check_free_chunk(p) mchunkptr p;
#endif
{
#if DEBUG_DLMALLOC 
 mstate av = get_malloc_state();
#endif

  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;
#if DEBUG_DLMALLOC 
  mchunkptr next = chunk_at_offset(p, sz);
#endif

  do_check_chunk(p);

  /* Chunk must claim to be free ... */
  assert(!inuse(p));
  assert (!chunk_is_mmapped(p));

  /* Unless a special marker, must have OK fields */
  if ((CHUNK_SIZE_T)(sz) >= MINSIZE)
  {
    assert((sz & MALLOC_ALIGN_MASK) == 0);
    assert(aligned_OK(chunk2mem(p)));
    /* ... matching footer field */
    assert(next->prev_size == sz);
    /* ... and is fully consolidated */
    assert(prev_inuse(p));
    assert (next == av->top || inuse(next));

    /* ... and has minimally sane links */
    assert(p->fd->bk == p);
    assert(p->bk->fd == p);
  }
  else /* markers are always of size SIZE_SZ */
    assert(sz == SIZE_SZ);
}

/*
  Properties of inuse chunks
*/

#if __STD_C
static void do_check_inuse_chunk(mchunkptr p)
#else
static void do_check_inuse_chunk(p) mchunkptr p;
#endif
{
  mstate av = get_malloc_state();
  mchunkptr next;
  do_check_chunk(p);

  if (chunk_is_mmapped(p))
    return; /* mmapped chunks have no next/prev */

  /* Check whether it claims to be in use ... */
  assert(inuse(p));

  next = next_chunk(p);

  /* ... and is surrounded by OK chunks.
    Since more things can be checked with free chunks than inuse ones,
    if an inuse chunk borders them and debug is on, it's worth doing them.
  */
  if (!prev_inuse(p))  {
    /* Note that we cannot even look at prev unless it is not inuse */
    mchunkptr prv = prev_chunk(p);
    assert(next_chunk(prv) == p);
    do_check_free_chunk(prv);
  }

  if (next == av->top) {
    assert(prev_inuse(next));
    assert(chunksize(next) >= MINSIZE);
  }
  else if (!inuse(next))
    do_check_free_chunk(next);
}

/*
  Properties of chunks recycled from fastbins
*/

#if __STD_C
static void do_check_remalloced_chunk(mchunkptr p, INTERNAL_SIZE_T s)
#else
static void do_check_remalloced_chunk(p, s) mchunkptr p; INTERNAL_SIZE_T s;
#endif
{
#if DEBUG_DLMALLOC 
  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;
#endif

  do_check_inuse_chunk(p);

  /* Legal size ... */
  assert((sz & MALLOC_ALIGN_MASK) == 0);
  assert((CHUNK_SIZE_T)(sz) >= MINSIZE);
  /* ... and alignment */
  assert(aligned_OK(chunk2mem(p)));
  /* chunk is less than MINSIZE more than request */
  assert((long)(sz) - (long)(s) >= 0);
  assert((long)(sz) - (long)(s + MINSIZE) < 0);
}

/*
  Properties of nonrecycled chunks at the point they are malloced
*/

#if __STD_C
static void do_check_malloced_chunk(mchunkptr p, INTERNAL_SIZE_T s)
#else
static void do_check_malloced_chunk(p, s) mchunkptr p; INTERNAL_SIZE_T s;
#endif
{
  /* same as recycled case ... */
  do_check_remalloced_chunk(p, s);

  /*
    ... plus,  must obey implementation invariant that prev_inuse is
    always true of any allocated chunk; i.e., that each allocated
    chunk borders either a previously allocated and still in-use
    chunk, or the base of its memory arena. This is ensured
    by making all allocations from the the `lowest' part of any found
    chunk.  This does not necessarily hold however for chunks
    recycled via fastbins.
  */

  assert(prev_inuse(p));
}


/*
  Properties of malloc_state.

  This may be useful for debugging malloc, as well as detecting user
  programmer errors that somehow write into malloc_state.

  If you are extending or experimenting with this malloc, you can
  probably figure out how to hack this routine to print out or
  display chunk addresses, sizes, bins, and other instrumentation.
*/

static void do_check_malloc_state(void)
{
  mstate av = get_malloc_state();
  int i;
  mchunkptr p;
  mchunkptr q;
  mbinptr b;
  unsigned int binbit;
  int empty;
  unsigned int idx;
  INTERNAL_SIZE_T size;
  CHUNK_SIZE_T  total = 0;
  int max_fast_bin;

  /* internal size_t must be no wider than pointer type */
  assert(sizeof(INTERNAL_SIZE_T) <= sizeof(char*));

  /* alignment is a power of 2 */
  assert((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-1)) == 0);

  /* cannot run remaining checks until fully initialized */
  if (av->top == 0 || av->top == initial_top(av))
    return;

  /* pagesize is a power of 2 */
  assert((av->pagesize & (av->pagesize-1)) == 0);

  /* properties of fastbins */

  /* max_fast is in allowed range */
  assert(get_max_fast(av) <= request2size(MAX_FAST_SIZE));

  max_fast_bin = fastbin_index(av->max_fast);

  for (i = 0; i < NFASTBINS; ++i) {
    p = av->fastbins[i];

    /* all bins past max_fast are empty */
    if (i > max_fast_bin)
      assert(p == 0);

    while (p != 0) {
      /* each chunk claims to be inuse */
      do_check_inuse_chunk(p);
      total += chunksize(p);
      /* chunk belongs in this bin */
      assert(fastbin_index(chunksize(p)) == i);
      p = p->fd;
    }
  }

  if (total != 0)
    assert(have_fastchunks(av));
  else if (!have_fastchunks(av))
    assert(total == 0);

  /* check normal bins */
  for (i = 1; i < NBINS; ++i) {
    b = bin_at(av,i);

    /* binmap is accurate (except for bin 1 == unsorted_chunks) */
    if (i >= 2) {
      binbit = get_binmap(av,i);
      empty = last(b) == b;
      if (!binbit)
        assert(empty);
      else if (!empty)
        assert(binbit);
    }

    for (p = last(b); p != b; p = p->bk) {
      /* each chunk claims to be free */
      do_check_free_chunk(p);
      size = chunksize(p);
      total += size;
      if (i >= 2) {
        /* chunk belongs in bin */
        idx = bin_index(size);
        assert(idx == i);
        /* lists are sorted */
        if ((CHUNK_SIZE_T) size >= (CHUNK_SIZE_T)(FIRST_SORTED_BIN_SIZE)) {
          assert(p->bk == b || 
                 (CHUNK_SIZE_T)chunksize(p->bk) >= 
                 (CHUNK_SIZE_T)chunksize(p));
        }
      }
      /* chunk is followed by a legal chain of inuse chunks */
      for (q = next_chunk(p);
           (q != av->top && inuse(q) && 
             (CHUNK_SIZE_T)(chunksize(q)) >= MINSIZE);
           q = next_chunk(q))
        do_check_inuse_chunk(q);
    }
  }

  /* top chunk is OK */
  check_chunk(av->top);

  /* sanity checks for statistics */

  assert(total <= (CHUNK_SIZE_T)(av->max_total_mem));

  assert((CHUNK_SIZE_T)(av->sbrked_mem) <=
         (CHUNK_SIZE_T)(av->max_sbrked_mem));

  assert((CHUNK_SIZE_T)(av->max_total_mem) >=
         (CHUNK_SIZE_T)(av->sbrked_mem));
}
#endif


/* ----------- Routines dealing with system allocation -------------- */

/*
  sysmalloc handles malloc cases requiring more memory from the system.
  On entry, it is assumed that av->top does not have enough
  space to service request for nb bytes, thus requiring that av->top
  be extended or replaced.
*/

#if __STD_C
static Void_t* sYSMALLOc(INTERNAL_SIZE_T nb, mstate av)
#else
static Void_t* sYSMALLOc(nb, av) INTERNAL_SIZE_T nb; mstate av;
#endif
{
  mchunkptr       old_top;        /* incoming value of av->top */
  INTERNAL_SIZE_T old_size;       /* its size */
  char*           old_end;        /* its end address */

  long            size;           /* arg to first MORECORE or mmap call */
  char*           brk;            /* return value from MORECORE */

  long            correction;     /* arg to 2nd MORECORE call */
  char*           snd_brk;        /* 2nd return val */

  INTERNAL_SIZE_T front_misalign; /* unusable bytes at front of new space */
  INTERNAL_SIZE_T end_misalign;   /* partial page left at end of new space */
  char*           aligned_brk;    /* aligned offset into brk */

  mchunkptr       p;              /* the allocated/returned chunk */
  mchunkptr       remainder;      /* remainder from allocation */
  CHUNK_SIZE_T    remainder_size; /* its size */

  CHUNK_SIZE_T    sum;            /* for updating stats */

  size_t          pagemask  = av->pagesize - 1;

  /*
    If there is space available in fastbins, consolidate and retry
    malloc from scratch rather than getting memory from system.  This
    can occur only if nb is in smallbin range so we didn't consolidate
    upon entry to malloc. It is much easier to handle this case here
    than in malloc proper.
  */

  if (have_fastchunks(av)) {
    assert(in_smallbin_range(nb));
    malloc_consolidate(av);
    return mALLOc(nb - MALLOC_ALIGN_MASK);
  }


  /* Record incoming configuration of top */

  old_top  = av->top;
  old_size = chunksize(old_top);
  old_end  = (char*)(chunk_at_offset(old_top, old_size));

  brk = snd_brk = (char*)(MORECORE_FAILURE); 

  /* 
     If not the first time through, we require old_size to be
     at least MINSIZE and to have prev_inuse set.
  */

  assert((old_top == initial_top(av) && old_size == 0) || 
         ((CHUNK_SIZE_T) (old_size) >= MINSIZE &&
          prev_inuse(old_top)));

  /* Precondition: not enough current space to satisfy nb request */
  assert((CHUNK_SIZE_T)(old_size) < (CHUNK_SIZE_T)(nb + MINSIZE));

  /* Precondition: all fastbins are consolidated */
  assert(!have_fastchunks(av));


  /* Request enough space for nb + pad + overhead */

  size = nb + av->top_pad + MINSIZE;

  /*
    If contiguous, we can subtract out existing space that we hope to
    combine with new space. We add it back later only if
    we don't actually get contiguous space.
  */

  if (contiguous(av))
    size -= old_size;

  /*
    Round to a multiple of page size.
    If MORECORE is not contiguous, this ensures that we only call it
    with whole-page arguments.  And if MORECORE is contiguous and
    this is not first time through, this preserves page-alignment of
    previous calls. Otherwise, we correct to page-align below.
  */

  size = (size + pagemask) & ~pagemask;

  /*
    Don't try to call MORECORE if argument is so big as to appear
    negative. Note that since mmap takes size_t arg, it may succeed
    below even if we cannot call MORECORE.
  */

  if (size > 0) 
    brk = (char*)(MORECORE(size));

  /*
    If have mmap, try using it as a backup when MORECORE fails or
    cannot be used. This is worth doing on systems that have "holes" in
    address space, so sbrk cannot extend to give contiguous space, but
    space is available elsewhere.  Note that we ignore mmap max count
    and threshold limits, since the space will not be used as a
    segregated mmap region.
  */


  if (brk != (char*)(MORECORE_FAILURE)) {
    av->sbrked_mem += size;

    /*
      If MORECORE extends previous space, we can likewise extend top size.
    */
    
    if (brk == old_end && snd_brk == (char*)(MORECORE_FAILURE)) {
      set_head(old_top, (size + old_size) | PREV_INUSE);
    }

    /*
      Otherwise, make adjustments:
      
      * If the first time through or noncontiguous, we need to call sbrk
        just to find out where the end of memory lies.

      * We need to ensure that all returned chunks from malloc will meet
        MALLOC_ALIGNMENT

      * If there was an intervening foreign sbrk, we need to adjust sbrk
        request size to account for fact that we will not be able to
        combine new space with existing space in old_top.

      * Almost all systems internally allocate whole pages at a time, in
        which case we might as well use the whole last page of request.
        So we allocate enough more memory to hit a page boundary now,
        which in turn causes future contiguous calls to page-align.
    */
    
    else {
      front_misalign = 0;
      end_misalign = 0;
      correction = 0;
      aligned_brk = brk;

      /*
        If MORECORE returns an address lower than we have seen before,
        we know it isn't really contiguous.  This and some subsequent
        checks help cope with non-conforming MORECORE functions and
        the presence of "foreign" calls to MORECORE from outside of
        malloc or by other threads.  We cannot guarantee to detect
        these in all cases, but cope with the ones we do detect.
      */
      if (contiguous(av) && old_size != 0 && brk < old_end) {
        set_noncontiguous(av);
      }
      
      /* handle contiguous cases */
      if (contiguous(av)) { 

        /* 
           We can tolerate forward non-contiguities here (usually due
           to foreign calls) but treat them as part of our space for
           stats reporting.
        */
        if (old_size != 0) 
          av->sbrked_mem += brk - old_end;
        
        /* Guarantee alignment of first new chunk made from this space */

        front_misalign = (INTERNAL_SIZE_T)chunk2mem(brk) & MALLOC_ALIGN_MASK;
        if (front_misalign > 0) {

          /*
            Skip over some bytes to arrive at an aligned position.
            We don't need to specially mark these wasted front bytes.
            They will never be accessed anyway because
            prev_inuse of av->top (and any chunk created from its start)
            is always true after initialization.
          */

          correction = MALLOC_ALIGNMENT - front_misalign;
          aligned_brk += correction;
        }
        
        /*
          If this isn't adjacent to existing space, then we will not
          be able to merge with old_top space, so must add to 2nd request.
        */
        
        correction += old_size;
        
        /* Extend the end address to hit a page boundary */
        end_misalign = (INTERNAL_SIZE_T)(brk + size + correction);
        correction += ((end_misalign + pagemask) & ~pagemask) - end_misalign;
        
        assert(correction >= 0);
        snd_brk = (char*)(MORECORE(correction));
        
        if (snd_brk == (char*)(MORECORE_FAILURE)) {
          /*
            If can't allocate correction, try to at least find out current
            brk.  It might be enough to proceed without failing.
          */
          correction = 0;
          snd_brk = (char*)(MORECORE(0));
        }
        else if (snd_brk < brk) {
          /*
            If the second call gives noncontiguous space even though
            it says it won't, the only course of action is to ignore
            results of second call, and conservatively estimate where
            the first call left us. Also set noncontiguous, so this
            won't happen again, leaving at most one hole.
            
            Note that this check is intrinsically incomplete.  Because
            MORECORE is allowed to give more space than we ask for,
            there is no reliable way to detect a noncontiguity
            producing a forward gap for the second call.
          */
          snd_brk = brk + size;
          correction = 0;
          set_noncontiguous(av);
        }

      }
      
      /* handle non-contiguous cases */
      else { 
        /* MORECORE/mmap must correctly align */
        assert(aligned_OK(chunk2mem(brk)));
        
        /* Find out current end of memory */
        if (snd_brk == (char*)(MORECORE_FAILURE)) {
          snd_brk = (char*)(MORECORE(0));
          av->sbrked_mem += snd_brk - brk - size;
        }
      }
      
      /* Adjust top based on results of second sbrk */
      if (snd_brk != (char*)(MORECORE_FAILURE)) {
        av->top = (mchunkptr)aligned_brk;
        set_head(av->top, (snd_brk - aligned_brk + correction) | PREV_INUSE);
        av->sbrked_mem += correction;
     
        /*
          If not the first time through, we either have a
          gap due to foreign sbrk or a non-contiguous region.  Insert a
          double fencepost at old_top to prevent consolidation with space
          we don't own. These fenceposts are artificial chunks that are
          marked as inuse and are in any case too small to use.  We need
          two to make sizes and alignments work out.
        */
   
        if (old_size != 0) {
          /* 
             Shrink old_top to insert fenceposts, keeping size a
             multiple of MALLOC_ALIGNMENT. We know there is at least
             enough space in old_top to do this.
          */
          old_size = (old_size - 3*SIZE_SZ) & ~MALLOC_ALIGN_MASK;
          set_head(old_top, old_size | PREV_INUSE);
          
          /*
            Note that the following assignments completely overwrite
            old_top when old_size was previously MINSIZE.  This is
            intentional. We need the fencepost, even if old_top otherwise gets
            lost.
          */
          chunk_at_offset(old_top, old_size          )->size =
            SIZE_SZ|PREV_INUSE;

          chunk_at_offset(old_top, old_size + SIZE_SZ)->size =
            SIZE_SZ|PREV_INUSE;

          /* 
             If possible, release the rest, suppressing trimming.
          */
          if (old_size >= MINSIZE) {
            INTERNAL_SIZE_T tt = av->trim_threshold;
            av->trim_threshold = (INTERNAL_SIZE_T)(-1);
            fREe(chunk2mem(old_top));
            av->trim_threshold = tt;
          }
        }
      }
    }
    
    /* Update statistics */
    sum = av->sbrked_mem;
    if (sum > (CHUNK_SIZE_T)(av->max_sbrked_mem))
      av->max_sbrked_mem = sum;
    
    sum += av->mmapped_mem;
    if (sum > (CHUNK_SIZE_T)(av->max_total_mem))
      av->max_total_mem = sum;

    check_malloc_state();
    
    /* finally, do the allocation */

    p = av->top;
    size = chunksize(p);
    
    /* check that one of the above allocation paths succeeded */
    if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb + MINSIZE)) {

      remainder_size = size - nb;
      remainder = chunk_at_offset(p, nb);
      av->top = remainder;
      set_head(p, nb | PREV_INUSE);
      set_head(remainder, remainder_size | PREV_INUSE);
      check_malloced_chunk(p, nb);
      return chunk2mem(p);
    }

  }

  /* catch all failure paths */
  MALLOC_FAILURE_ACTION;
  return 0;
}



/*
  sYSTRIm is an inverse of sorts to sYSMALLOc.  It gives memory back
  to the system (via negative arguments to sbrk) if there is unused
  memory at the `high' end of the malloc pool. It is called
  automatically by free() when top space exceeds the trim
  threshold. It is also called by the public malloc_trim routine.  It
  returns 1 if it actually released any memory, else 0.
*/

#if __STD_C
static int sYSTRIm(size_t pad, mstate av)
#else
static int sYSTRIm(pad, av) size_t pad; mstate av;
#endif
{
  long  top_size;        /* Amount of top-most memory */
  long  extra;           /* Amount to release */
  long  released;        /* Amount actually released */
  char* current_brk;     /* address returned by pre-check sbrk call */
  char* new_brk;         /* address returned by post-check sbrk call */
  size_t pagesz;

  pagesz = av->pagesize;
  top_size = chunksize(av->top);
  
  /* Release in pagesize units, keeping at least one page */
  extra = ((top_size - pad - MINSIZE + (pagesz-1)) / pagesz - 1) * pagesz;
  
  if (extra > 0) {
    
    /*
      Only proceed if end of memory is where we last set it.
      This avoids problems if there were foreign sbrk calls.
    */
    current_brk = (char*)(MORECORE(0));
    if (current_brk == (char*)(av->top) + top_size) {
      
      /*
        Attempt to release memory. We ignore MORECORE return value,
        and instead call again to find out where new end of memory is.
        This avoids problems if first call releases less than we asked,
        of if failure somehow altered brk value. (We could still
        encounter problems if it altered brk in some very bad way,
        but the only thing we can do is adjust anyway, which will cause
        some downstream failure.)
      */
      
      MORECORE(-extra);
      new_brk = (char*)(MORECORE(0));
      
      if (new_brk != (char*)MORECORE_FAILURE) {
        released = (long)(current_brk - new_brk);
        
        if (released != 0) {
          /* Success. Adjust top. */
          av->sbrked_mem -= released;
          set_head(av->top, (top_size - released) | PREV_INUSE);
          check_malloc_state();
          return 1;
        }
      }
    }
  }
  return 0;
}

/*
  ------------------------------ malloc ------------------------------
*/


#if __STD_C
Void_t* mALLOc(size_t bytes)
#else
  Void_t* mALLOc(bytes) size_t bytes;
#endif
{
  mstate av = get_malloc_state();

  INTERNAL_SIZE_T nb;               /* normalized request size */
  unsigned int    idx;              /* associated bin index */
  mbinptr         bin;              /* associated bin */
  mfastbinptr*    fb;               /* associated fastbin */

  mchunkptr       victim;           /* inspected/selected chunk */
  INTERNAL_SIZE_T size;             /* its size */
  int             victim_index;     /* its bin index */

  mchunkptr       remainder;        /* remainder from a split */
  CHUNK_SIZE_T    remainder_size;   /* its size */

  unsigned int    block;            /* bit map traverser */
  unsigned int    bit;              /* bit map traverser */
  unsigned int    map;              /* current word of binmap */

  mchunkptr       fwd;              /* misc temp for linking */
  mchunkptr       bck;              /* misc temp for linking */

  /*
    Convert request size to internal form by adding SIZE_SZ bytes
    overhead plus possibly more to obtain necessary alignment and/or
    to obtain a size of at least MINSIZE, the smallest allocatable
    size. Also, checked_request2size traps (returning 0) request sizes
    that are so large that they wrap around zero when padded and
    aligned.
  */

  checked_request2size(bytes, nb);

  /*
    Bypass search if no frees yet
   */
  if (!have_anychunks(av)) {
    if (av->max_fast == 0) /* initialization check */
      malloc_consolidate(av);
    goto use_top;
  }

  /*
    If the size qualifies as a fastbin, first check corresponding bin.
  */

  if ((CHUNK_SIZE_T)(nb) <= (CHUNK_SIZE_T)(av->max_fast)) { 
    fb = &(av->fastbins[(fastbin_index(nb))]);
    if ( (victim = *fb) != 0) {
      *fb = victim->fd;
      check_remalloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
  }

  /*
    If a small request, check regular bin.  Since these "smallbins"
    hold one size each, no searching within bins is necessary.
    (For a large request, we need to wait until unsorted chunks are
    processed to find best fit. But for small ones, fits are exact
    anyway, so we can check now, which is faster.)
  */

  if (in_smallbin_range(nb)) {
    idx = smallbin_index(nb);
    bin = bin_at(av,idx);

    if ( (victim = last(bin)) != bin) {
      bck = victim->bk;
      set_inuse_bit_at_offset(victim, nb);
      bin->bk = bck;
      bck->fd = bin;
      
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
  }

  /* 
     If this is a large request, consolidate fastbins before continuing.
     While it might look excessive to kill all fastbins before
     even seeing if there is space available, this avoids
     fragmentation problems normally associated with fastbins.
     Also, in practice, programs tend to have runs of either small or
     large requests, but less often mixtures, so consolidation is not 
     invoked all that often in most programs. And the programs that
     it is called frequently in otherwise tend to fragment.
  */

  else {
    idx = largebin_index(nb);
    if (have_fastchunks(av)) 
      malloc_consolidate(av);
  }

  /*
    Process recently freed or remaindered chunks, taking one only if
    it is exact fit, or, if this a small request, the chunk is remainder from
    the most recent non-exact fit.  Place other traversed chunks in
    bins.  Note that this step is the only place in any routine where
    chunks are placed in bins.
  */
    
  while ( (victim = unsorted_chunks(av)->bk) != unsorted_chunks(av)) {
    bck = victim->bk;
    size = chunksize(victim);
    
    /* 
       If a small request, try to use last remainder if it is the
       only chunk in unsorted bin.  This helps promote locality for
       runs of consecutive small requests. This is the only
       exception to best-fit, and applies only when there is
       no exact fit for a small chunk.
    */
    
    if (in_smallbin_range(nb) && 
        bck == unsorted_chunks(av) &&
        victim == av->last_remainder &&
        (CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb + MINSIZE)) {
      
      /* split and reattach remainder */
      remainder_size = size - nb;
      remainder = chunk_at_offset(victim, nb);
      unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
      av->last_remainder = remainder; 
      remainder->bk = remainder->fd = unsorted_chunks(av);
      
      set_head(victim, nb | PREV_INUSE);
      set_head(remainder, remainder_size | PREV_INUSE);
      set_foot(remainder, remainder_size);
      
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
    
    /* remove from unsorted list */
    unsorted_chunks(av)->bk = bck;
    bck->fd = unsorted_chunks(av);
    
    /* Take now instead of binning if exact fit */
    
    if (size == nb) {
      set_inuse_bit_at_offset(victim, size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
    
    /* place chunk in bin */
    
    if (in_smallbin_range(size)) {
      victim_index = smallbin_index(size);
      bck = bin_at(av, victim_index);
      fwd = bck->fd;
    }
    else {
      victim_index = largebin_index(size);
      bck = bin_at(av, victim_index);
      fwd = bck->fd;
      
      if (fwd != bck) {
        /* if smaller than smallest, place first */
        if ((CHUNK_SIZE_T)(size) < (CHUNK_SIZE_T)(bck->bk->size)) {
          fwd = bck;
          bck = bck->bk;
        }
        else if ((CHUNK_SIZE_T)(size) >= 
                 (CHUNK_SIZE_T)(FIRST_SORTED_BIN_SIZE)) {
          
          /* maintain large bins in sorted order */
          size |= PREV_INUSE; /* Or with inuse bit to speed comparisons */
          while ((CHUNK_SIZE_T)(size) < (CHUNK_SIZE_T)(fwd->size)) 
            fwd = fwd->fd;
          bck = fwd->bk;
        }
      }
    }
      
    mark_bin(av, victim_index);
    victim->bk = bck;
    victim->fd = fwd;
    fwd->bk = victim;
    bck->fd = victim;
  }
  
  /*
    If a large request, scan through the chunks of current bin to
    find one that fits.  (This will be the smallest that fits unless
    FIRST_SORTED_BIN_SIZE has been changed from default.)  This is
    the only step where an unbounded number of chunks might be
    scanned without doing anything useful with them. However the
    lists tend to be short.
  */
  
  if (!in_smallbin_range(nb)) {
    bin = bin_at(av, idx);
    
    for (victim = last(bin); victim != bin; victim = victim->bk) {
      size = chunksize(victim);
      
      if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb)) {
        remainder_size = size - nb;
        dl_unlink(victim, bck, fwd);
        
        /* Exhaust */
        if (remainder_size < MINSIZE)  {
          set_inuse_bit_at_offset(victim, size);
          check_malloced_chunk(victim, nb);
          return chunk2mem(victim);
        }
        /* Split */
        else {
          remainder = chunk_at_offset(victim, nb);
          unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
          remainder->bk = remainder->fd = unsorted_chunks(av);
          set_head(victim, nb | PREV_INUSE);
          set_head(remainder, remainder_size | PREV_INUSE);
          set_foot(remainder, remainder_size);
          check_malloced_chunk(victim, nb);
          return chunk2mem(victim);
        } 
      }
    }    
  }

  /*
    Search for a chunk by scanning bins, starting with next largest
    bin. This search is strictly by best-fit; i.e., the smallest
    (with ties going to approximately the least recently used) chunk
    that fits is selected.
    
    The bitmap avoids needing to check that most blocks are nonempty.
  */
    
  ++idx;
  bin = bin_at(av,idx);
  block = idx2block(idx);
  map = av->binmap[block];
  bit = idx2bit(idx);
  
  for (;;) {
    
    /* Skip rest of block if there are no more set bits in this block.  */
    if (bit > map || bit == 0) {
      do {
        if (++block >= BINMAPSIZE)  /* out of bins */
          goto use_top;
      } while ( (map = av->binmap[block]) == 0);
      
      bin = bin_at(av, (block << BINMAPSHIFT));
      bit = 1;
    }
    
    /* Advance to bin with set bit. There must be one. */
    while ((bit & map) == 0) {
      bin = next_bin(bin);
      bit <<= 1;
      assert(bit != 0);
    }
    
    /* Inspect the bin. It is likely to be non-empty */
    victim = last(bin);
    
    /*  If a false alarm (empty bin), clear the bit. */
    if (victim == bin) {
      av->binmap[block] = map &= ~bit; /* Write through */
      bin = next_bin(bin);
      bit <<= 1;
    }
    
    else {
      size = chunksize(victim);
      
      /*  We know the first chunk in this bin is big enough to use. */
      assert((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb));
      
      remainder_size = size - nb;
      
      /* dl_unlink */
      bck = victim->bk;
      bin->bk = bck;
      bck->fd = bin;
      
      /* Exhaust */
      if (remainder_size < MINSIZE) {
        set_inuse_bit_at_offset(victim, size);
        check_malloced_chunk(victim, nb);
        return chunk2mem(victim);
      }
      
      /* Split */
      else {
        remainder = chunk_at_offset(victim, nb);
        
        unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
        remainder->bk = remainder->fd = unsorted_chunks(av);
        /* advertise as last remainder */
        if (in_smallbin_range(nb)) 
          av->last_remainder = remainder; 
        
        set_head(victim, nb | PREV_INUSE);
        set_head(remainder, remainder_size | PREV_INUSE);
        set_foot(remainder, remainder_size);
        check_malloced_chunk(victim, nb);
        return chunk2mem(victim);
      }
    }
  }

  use_top:    
  /*
    If large enough, split off the chunk bordering the end of memory
    (held in av->top). Note that this is in accord with the best-fit
    search rule.  In effect, av->top is treated as larger (and thus
    less well fitting) than any other available chunk since it can
    be extended to be as large as necessary (up to system
    limitations).
    
    We require that av->top always exists (i.e., has size >=
    MINSIZE) after initialization, so if it would otherwise be
    exhuasted by current request, it is replenished. (The main
    reason for ensuring it exists is that we may need MINSIZE space
    to put in fenceposts in sysmalloc.)
  */
  
  victim = av->top;
  size = chunksize(victim);

  if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb + MINSIZE)) {
    remainder_size = size - nb;
    remainder = chunk_at_offset(victim, nb);
    av->top = remainder;
    set_head(victim, nb | PREV_INUSE);
    set_head(remainder, remainder_size | PREV_INUSE);
    
    check_malloced_chunk(victim, nb);
    return chunk2mem(victim);
  }
  
  /* 
     If no space in top, relay to handle system-dependent cases 
  */
  return sYSMALLOc(nb, av);    
}

/*
  ------------------------------ free ------------------------------
*/

#if __STD_C
void fREe(Void_t* mem)
#else
void fREe(mem) Void_t* mem;
#endif
{
  mstate av = get_malloc_state();

  mchunkptr       p;           /* chunk corresponding to mem */
  INTERNAL_SIZE_T size;        /* its size */
  mfastbinptr*    fb;          /* associated fastbin */
  mchunkptr       nextchunk;   /* next contiguous chunk */
  INTERNAL_SIZE_T nextsize;    /* its size */
  int             nextinuse;   /* true if nextchunk is used */
  INTERNAL_SIZE_T prevsize;    /* size of previous contiguous chunk */
  mchunkptr       bck;         /* misc temp for linking */
  mchunkptr       fwd;         /* misc temp for linking */

  /* free(0) has no effect */
  if (mem != 0) {
    p = mem2chunk(mem);
    size = chunksize(p);

    check_inuse_chunk(p);

    /*
      If eligible, place chunk on a fastbin so it can be found
      and used quickly in malloc.
    */

    if ((CHUNK_SIZE_T)(size) <= (CHUNK_SIZE_T)(av->max_fast)

#if TRIM_FASTBINS
        /* 
           If TRIM_FASTBINS set, don't place chunks
           bordering top into fastbins
        */
        && (chunk_at_offset(p, size) != av->top)
#endif
        ) {

      set_fastchunks(av);
      fb = &(av->fastbins[fastbin_index(size)]);
      p->fd = *fb;
      *fb = p;
    }

    /*
       Consolidate other non-mmapped chunks as they arrive.
    */

    else if (!chunk_is_mmapped(p)) {
      set_anychunks(av);

      nextchunk = chunk_at_offset(p, size);
      nextsize = chunksize(nextchunk);

      /* consolidate backward */
      if (!prev_inuse(p)) {
        prevsize = p->prev_size;
        size += prevsize;
        p = chunk_at_offset(p, -((long) prevsize));
        dl_unlink(p, bck, fwd);
      }

      if (nextchunk != av->top) {
        /* get and clear inuse bit */
        nextinuse = inuse_bit_at_offset(nextchunk, nextsize);
        set_head(nextchunk, nextsize);

        /* consolidate forward */
        if (!nextinuse) {
          dl_unlink(nextchunk, bck, fwd);
          size += nextsize;
        }

        /*
          Place the chunk in unsorted chunk list. Chunks are
          not placed into regular bins until after they have
          been given one chance to be used in malloc.
        */

        bck = unsorted_chunks(av);
        fwd = bck->fd;
        p->bk = bck;
        p->fd = fwd;
        bck->fd = p;
        fwd->bk = p;

        set_head(p, size | PREV_INUSE);
        set_foot(p, size);
        
        check_free_chunk(p);
      }

      /*
         If the chunk borders the current high end of memory,
         consolidate into top
      */

      else {
        size += nextsize;
        set_head(p, size | PREV_INUSE);
        av->top = p;
        check_chunk(p);
      }

      /*
        If freeing a large space, consolidate possibly-surrounding
        chunks. Then, if the total unused topmost memory exceeds trim
        threshold, ask malloc_trim to reduce top.

        Unless max_fast is 0, we don't know if there are fastbins
        bordering top, so we cannot tell for sure whether threshold
        has been reached unless fastbins are consolidated.  But we
        don't want to consolidate on each free.  As a compromise,
        consolidation is performed if FASTBIN_CONSOLIDATION_THRESHOLD
        is reached.
      */

      if ((CHUNK_SIZE_T)(size) >= FASTBIN_CONSOLIDATION_THRESHOLD) { 
        if (have_fastchunks(av)) 
          malloc_consolidate(av);

#ifndef MORECORE_CANNOT_TRIM        
        if ((CHUNK_SIZE_T)(chunksize(av->top)) >= 
            (CHUNK_SIZE_T)(av->trim_threshold))
          sYSTRIm(av->top_pad, av);
#endif
      }

    }
    /*
      If the chunk was allocated via mmap, release via munmap()
      Note that if HAVE_MMAP is false but chunk_is_mmapped is
      true, then user must have overwritten memory. There's nothing
      we can do to catch this error unless DEBUG is set, in which case
      check_inuse_chunk (above) will have triggered error.
    */

    else {
    }
  }
}

/*
  ------------------------- malloc_consolidate -------------------------

  malloc_consolidate is a specialized version of free() that tears
  down chunks held in fastbins.  Free itself cannot be used for this
  purpose since, among other things, it might place chunks back onto
  fastbins.  So, instead, we need to use a minor variant of the same
  code.
  
  Also, because this routine needs to be called the first time through
  malloc anyway, it turns out to be the perfect place to trigger
  initialization code.
*/

#if __STD_C
static void malloc_consolidate(mstate av)
#else
static void malloc_consolidate(av) mstate av;
#endif
{
  mfastbinptr*    fb;                 /* current fastbin being consolidated */
  mfastbinptr*    maxfb;              /* last fastbin (for loop control) */
  mchunkptr       p;                  /* current chunk being consolidated */
  mchunkptr       nextp;              /* next chunk to consolidate */
  mchunkptr       unsorted_bin;       /* bin header */
  mchunkptr       first_unsorted;     /* chunk to link to */

  /* These have same use as in free() */
  mchunkptr       nextchunk;
  INTERNAL_SIZE_T size;
  INTERNAL_SIZE_T nextsize;
  INTERNAL_SIZE_T prevsize;
  int             nextinuse;
  mchunkptr       bck;
  mchunkptr       fwd;

  /*
    If max_fast is 0, we know that av hasn't
    yet been initialized, in which case do so below
  */

  if (av->max_fast != 0) {
    clear_fastchunks(av);

    unsorted_bin = unsorted_chunks(av);

    /*
      Remove each chunk from fast bin and consolidate it, placing it
      then in unsorted bin. Among other reasons for doing this,
      placing in unsorted bin avoids needing to calculate actual bins
      until malloc is sure that chunks aren't immediately going to be
      reused anyway.
    */
    
    maxfb = &(av->fastbins[fastbin_index(av->max_fast)]);
    fb = &(av->fastbins[0]);
    do {
      if ( (p = *fb) != 0) {
        *fb = 0;
        
        do {
          check_inuse_chunk(p);
          nextp = p->fd;
          
          /* Slightly streamlined version of consolidation code in free() */
          size = p->size & ~PREV_INUSE;
          nextchunk = chunk_at_offset(p, size);
          nextsize = chunksize(nextchunk);
          
          if (!prev_inuse(p)) {
            prevsize = p->prev_size;
            size += prevsize;
            p = chunk_at_offset(p, -((long) prevsize));
            dl_unlink(p, bck, fwd);
          }
          
          if (nextchunk != av->top) {
            nextinuse = inuse_bit_at_offset(nextchunk, nextsize);
            set_head(nextchunk, nextsize);
            
            if (!nextinuse) {
              size += nextsize;
              dl_unlink(nextchunk, bck, fwd);
            }
            
            first_unsorted = unsorted_bin->fd;
            unsorted_bin->fd = p;
            first_unsorted->bk = p;
            
            set_head(p, size | PREV_INUSE);
            p->bk = unsorted_bin;
            p->fd = first_unsorted;
            set_foot(p, size);
          }
          
          else {
            size += nextsize;
            set_head(p, size | PREV_INUSE);
            av->top = p;
          }
          
        } while ( (p = nextp) != 0);
        
      }
    } while (fb++ != maxfb);
  }
  else {
    malloc_init_state(av);
    check_malloc_state();
  }
}

/*
  ------------------------------ realloc ------------------------------
*/


#if __STD_C
Void_t* rEALLOc(Void_t* oldmem, size_t bytes)
#else
Void_t* rEALLOc(oldmem, bytes) Void_t* oldmem; size_t bytes;
#endif
{
  mstate av = get_malloc_state();

  INTERNAL_SIZE_T  nb;              /* padded request size */

  mchunkptr        oldp;            /* chunk corresponding to oldmem */
  INTERNAL_SIZE_T  oldsize;         /* its size */

  mchunkptr        newp;            /* chunk to return */
  INTERNAL_SIZE_T  newsize;         /* its size */
  Void_t*          newmem;          /* corresponding user mem */

  mchunkptr        next;            /* next contiguous chunk after oldp */

  mchunkptr        remainder;       /* extra space at end of newp */
  CHUNK_SIZE_T     remainder_size;  /* its size */

  mchunkptr        bck;             /* misc temp for linking */
  mchunkptr        fwd;             /* misc temp for linking */

  CHUNK_SIZE_T     copysize;        /* bytes to copy */
  unsigned int     ncopies;         /* INTERNAL_SIZE_T words to copy */
  INTERNAL_SIZE_T* s;               /* copy source */ 
  INTERNAL_SIZE_T* d;               /* copy destination */


#ifdef REALLOC_ZERO_BYTES_FREES
  if (bytes == 0) {
    fREe(oldmem);
    return 0;
  }
#endif

  /* realloc of null is supposed to be same as malloc */
  if (oldmem == 0) return mALLOc(bytes);

  checked_request2size(bytes, nb);

  oldp    = mem2chunk(oldmem);
  oldsize = chunksize(oldp);

  check_inuse_chunk(oldp);

  if (!chunk_is_mmapped(oldp)) {

    if ((CHUNK_SIZE_T)(oldsize) >= (CHUNK_SIZE_T)(nb)) {
      /* already big enough; split below */
      newp = oldp;
      newsize = oldsize;
    }

    else {
      next = chunk_at_offset(oldp, oldsize);

      /* Try to expand forward into top */
      if (next == av->top &&
          (CHUNK_SIZE_T)(newsize = oldsize + chunksize(next)) >=
          (CHUNK_SIZE_T)(nb + MINSIZE)) {
        set_head_size(oldp, nb);
        av->top = chunk_at_offset(oldp, nb);
        set_head(av->top, (newsize - nb) | PREV_INUSE);
        return chunk2mem(oldp);
      }
      
      /* Try to expand forward into next chunk;  split off remainder below */
      else if (next != av->top && 
               !inuse(next) &&
               (CHUNK_SIZE_T)(newsize = oldsize + chunksize(next)) >=
               (CHUNK_SIZE_T)(nb)) {
        newp = oldp;
        dl_unlink(next, bck, fwd);
      }

      /* allocate, copy, free */
      else {
        newmem = mALLOc(nb - MALLOC_ALIGN_MASK);
        if (newmem == 0)
          return 0; /* propagate failure */
      
        newp = mem2chunk(newmem);
        newsize = chunksize(newp);
        
        /*
          Avoid copy if newp is next chunk after oldp.
        */
        if (newp == next) {
          newsize += oldsize;
          newp = oldp;
        }
        else {
          /*
            Unroll copy of <= 36 bytes (72 if 8byte sizes)
            We know that contents have an odd number of
            INTERNAL_SIZE_T-sized words; minimally 3.
          */
          
          copysize = oldsize - SIZE_SZ;
          s = (INTERNAL_SIZE_T*)(oldmem);
          d = (INTERNAL_SIZE_T*)(newmem);
          ncopies = copysize / sizeof(INTERNAL_SIZE_T);
          assert(ncopies >= 3);
          
          if (ncopies > 9)
            memcpy(d, s, copysize);
          
          else {
            *(d+0) = *(s+0);
            *(d+1) = *(s+1);
            *(d+2) = *(s+2);
            if (ncopies > 4) {
              *(d+3) = *(s+3);
              *(d+4) = *(s+4);
              if (ncopies > 6) {
                *(d+5) = *(s+5);
                *(d+6) = *(s+6);
                if (ncopies > 8) {
                  *(d+7) = *(s+7);
                  *(d+8) = *(s+8);
                }
              }
            }
          }
          
          fREe(oldmem);
          check_inuse_chunk(newp);
          return chunk2mem(newp);
        }
      }
    }

    /* If possible, free extra space in old or extended chunk */

    assert((CHUNK_SIZE_T)(newsize) >= (CHUNK_SIZE_T)(nb));

    remainder_size = newsize - nb;

    if (remainder_size < MINSIZE) { /* not enough extra to split off */
      set_head_size(newp, newsize);
      set_inuse_bit_at_offset(newp, newsize);
    }
    else { /* split remainder */
      remainder = chunk_at_offset(newp, nb);
      set_head_size(newp, nb);
      set_head(remainder, remainder_size | PREV_INUSE);
      /* Mark remainder as inuse so free() won't complain */
      set_inuse_bit_at_offset(remainder, remainder_size);
      fREe(chunk2mem(remainder)); 
    }

    check_inuse_chunk(newp);
    return chunk2mem(newp);
  }

  /*
    Handle mmap cases
  */

  else {
#if HAVE_MMAP

#if HAVE_MREMAP
    INTERNAL_SIZE_T offset = oldp->prev_size;
    size_t pagemask = av->pagesize - 1;
    char *cp;
    CHUNK_SIZE_T  sum;
    
    /* Note the extra SIZE_SZ overhead */
    newsize = (nb + offset + SIZE_SZ + pagemask) & ~pagemask;

    /* don't need to remap if still within same page */
    if (oldsize == newsize - offset) 
      return oldmem;

    cp = (char*)mremap((char*)oldp - offset, oldsize + offset, newsize, 1);
    
    if (cp != (char*)MORECORE_FAILURE) {

      newp = (mchunkptr)(cp + offset);
      set_head(newp, (newsize - offset)|IS_MMAPPED);
      
      assert(aligned_OK(chunk2mem(newp)));
      assert((newp->prev_size == offset));
      
      /* update statistics */
      sum = av->mmapped_mem += newsize - oldsize;
      if (sum > (CHUNK_SIZE_T)(av->max_mmapped_mem)) 
        av->max_mmapped_mem = sum;
      sum += av->sbrked_mem;
      if (sum > (CHUNK_SIZE_T)(av->max_total_mem)) 
        av->max_total_mem = sum;
      
      return chunk2mem(newp);
    }
#endif

    /* Note the extra SIZE_SZ overhead. */
    if ((CHUNK_SIZE_T)(oldsize) >= (CHUNK_SIZE_T)(nb + SIZE_SZ)) 
      newmem = oldmem; /* do nothing */
    else {
      /* Must alloc, copy, free. */
      newmem = mALLOc(nb - MALLOC_ALIGN_MASK);
      if (newmem != 0) {
        memcpy(newmem, oldmem, oldsize - 2*SIZE_SZ);
        fREe(oldmem);
      }
    }
    return newmem;

#else 
    /* If !HAVE_MMAP, but chunk_is_mmapped, user must have overwritten mem */
    check_malloc_state();
    MALLOC_FAILURE_ACTION;
    return 0;
#endif
  }
}

/*
  ------------------------------ memalign ------------------------------
*/

#if __STD_C
Void_t* mEMALIGn(size_t alignment, size_t bytes)
#else
Void_t* mEMALIGn(alignment, bytes) size_t alignment; size_t bytes;
#endif
{
  INTERNAL_SIZE_T nb;             /* padded  request size */
  char*           m;              /* memory returned by malloc call */
  mchunkptr       p;              /* corresponding chunk */
  char*           brk;            /* alignment point within p */
  mchunkptr       newp;           /* chunk to return */
  INTERNAL_SIZE_T newsize;        /* its size */
  INTERNAL_SIZE_T leadsize;       /* leading space before alignment point */
  mchunkptr       remainder;      /* spare room at end to split off */
  CHUNK_SIZE_T    remainder_size; /* its size */
  INTERNAL_SIZE_T size;

  /* If need less alignment than we give anyway, just relay to malloc */

  if (alignment <= MALLOC_ALIGNMENT) return mALLOc(bytes);

  /* Otherwise, ensure that it is at least a minimum chunk size */

  if (alignment <  MINSIZE) alignment = MINSIZE;

  /* Make sure alignment is power of 2 (in case MINSIZE is not).  */
  if ((alignment & (alignment - 1)) != 0) {
    size_t a = MALLOC_ALIGNMENT * 2;
    while ((CHUNK_SIZE_T)a < (CHUNK_SIZE_T)alignment) a <<= 1;
    alignment = a;
  }

  checked_request2size(bytes, nb);

  /*
    Strategy: find a spot within that chunk that meets the alignment
    request, and then possibly free the leading and trailing space.
  */


  /* Call malloc with worst case padding to hit alignment. */

  m  = (char*)(mALLOc(nb + alignment + MINSIZE));

  if (m == 0) return 0; /* propagate failure */

  p = mem2chunk(m);

  if ((((PTR_UINT)(m)) % alignment) != 0) { /* misaligned */

    /*
      Find an aligned spot inside chunk.  Since we need to give back
      leading space in a chunk of at least MINSIZE, if the first
      calculation places us at a spot with less than MINSIZE leader,
      we can move to the next aligned spot -- we've allocated enough
      total room so that this is always possible.
    */

    brk = (char*)mem2chunk((PTR_UINT)(((PTR_UINT)(m + alignment - 1)) &
                           -((signed long) alignment)));
    if ((CHUNK_SIZE_T)(brk - (char*)(p)) < MINSIZE)
      brk += alignment;

    newp = (mchunkptr)brk;
    leadsize = brk - (char*)(p);
    newsize = chunksize(p) - leadsize;

    /* For mmapped chunks, just adjust offset */
    if (chunk_is_mmapped(p)) {
      newp->prev_size = p->prev_size + leadsize;
      set_head(newp, newsize|IS_MMAPPED);
      return chunk2mem(newp);
    }

    /* Otherwise, give back leader, use the rest */
    set_head(newp, newsize | PREV_INUSE);
    set_inuse_bit_at_offset(newp, newsize);
    set_head_size(p, leadsize);
    fREe(chunk2mem(p));
    p = newp;

    assert (newsize >= nb &&
            (((PTR_UINT)(chunk2mem(p))) % alignment) == 0);
  }

  /* Also give back spare room at the end */
  if (!chunk_is_mmapped(p)) {
    size = chunksize(p);
    if ((CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb + MINSIZE)) {
      remainder_size = size - nb;
      remainder = chunk_at_offset(p, nb);
      set_head(remainder, remainder_size | PREV_INUSE);
      set_head_size(p, nb);
      fREe(chunk2mem(remainder));
    }
  }

  check_inuse_chunk(p);
  return chunk2mem(p);
}

/*
  ------------------------------ calloc ------------------------------
*/

#if __STD_C
Void_t* cALLOc(size_t n_elements, size_t elem_size)
#else
Void_t* cALLOc(n_elements, elem_size) size_t n_elements; size_t elem_size;
#endif
{
  mchunkptr p;
  CHUNK_SIZE_T  clearsize;
  CHUNK_SIZE_T  nclears;
  INTERNAL_SIZE_T* d;

  Void_t* mem = mALLOc(n_elements * elem_size);

  if (mem != 0) {
    p = mem2chunk(mem);

    if (!chunk_is_mmapped(p))
    {  
      /*
        Unroll clear of <= 36 bytes (72 if 8byte sizes)
        We know that contents have an odd number of
        INTERNAL_SIZE_T-sized words; minimally 3.
      */

      d = (INTERNAL_SIZE_T*)mem;
      clearsize = chunksize(p) - SIZE_SZ;
      nclears = clearsize / sizeof(INTERNAL_SIZE_T);
      assert(nclears >= 3);

      if (nclears > 9)
        memset(d, 0, clearsize);

      else {
        *(d+0) = 0;
        *(d+1) = 0;
        *(d+2) = 0;
        if (nclears > 4) {
          *(d+3) = 0;
          *(d+4) = 0;
          if (nclears > 6) {
            *(d+5) = 0;
            *(d+6) = 0;
            if (nclears > 8) {
              *(d+7) = 0;
              *(d+8) = 0;
            }
          }
        }
      }
    }
  }
  return mem;
}

/*
  ------------------------------ cfree ------------------------------
*/

#if __STD_C
void cFREe(Void_t *mem)
#else
void cFREe(mem) Void_t *mem;
#endif
{
  fREe(mem);
}

/*
  ------------------------- independent_calloc -------------------------
*/

#if __STD_C
Void_t** iCALLOc(size_t n_elements, size_t elem_size, Void_t* chunks[])
#else
Void_t** iCALLOc(n_elements, elem_size, chunks) size_t n_elements; size_t elem_size; Void_t* chunks[];
#endif
{
  size_t sz = elem_size; /* serves as 1-element array */
  /* opts arg of 3 means all elements are same size, and should be cleared */
  return iALLOc(n_elements, &sz, 3, chunks);
}

/*
  ------------------------- independent_comalloc -------------------------
*/

#if __STD_C
Void_t** iCOMALLOc(size_t n_elements, size_t sizes[], Void_t* chunks[])
#else
Void_t** iCOMALLOc(n_elements, sizes, chunks) size_t n_elements; size_t sizes[]; Void_t* chunks[];
#endif
{
  return iALLOc(n_elements, sizes, 0, chunks);
}


/*
  ------------------------------ ialloc ------------------------------
  ialloc provides common support for independent_X routines, handling all of
  the combinations that can result.

  The opts arg has:
    bit 0 set if all elements are same size (using sizes[0])
    bit 1 set if elements should be zeroed
*/


#if __STD_C
static Void_t** iALLOc(size_t n_elements, 
                       size_t* sizes,  
                       int opts,
                       Void_t* chunks[])
#else
static Void_t** iALLOc(n_elements, sizes, opts, chunks) size_t n_elements; size_t* sizes; int opts; Void_t* chunks[];
#endif
{
  mstate av = get_malloc_state();
  INTERNAL_SIZE_T element_size;   /* chunksize of each element, if all same */
  INTERNAL_SIZE_T contents_size;  /* total size of elements */
  INTERNAL_SIZE_T array_size;     /* request size of pointer array */
  Void_t*         mem;            /* malloced aggregate space */
  mchunkptr       p;              /* corresponding chunk */
  INTERNAL_SIZE_T remainder_size; /* remaining bytes while splitting */
  Void_t**        marray;         /* either "chunks" or malloced ptr array */
  mchunkptr       array_chunk;    /* chunk for malloced ptr array */
  INTERNAL_SIZE_T size;           
  size_t          i;

  /* Ensure initialization */
  if (av->max_fast == 0) malloc_consolidate(av);

  /* compute array length, if needed */
  if (chunks != 0) {
    if (n_elements == 0)
      return chunks; /* nothing to do */
    marray = chunks;
    array_size = 0;
  }
  else {
    /* if empty req, must still return chunk representing empty array */
    if (n_elements == 0) 
      return (Void_t**) mALLOc(0);
    marray = 0;
    array_size = request2size(n_elements * (sizeof(Void_t*)));
  }

  /* compute total element size */
  if (opts & 0x1) { /* all-same-size */
    element_size = request2size(*sizes);
    contents_size = n_elements * element_size;
  }
  else { /* add up all the sizes */
    element_size = 0;
    contents_size = 0;
    for (i = 0; i != n_elements; ++i) 
      contents_size += request2size(sizes[i]);     
  }

  /* subtract out alignment bytes from total to minimize overallocation */
  size = contents_size + array_size - MALLOC_ALIGN_MASK;
  
  /* 
     Allocate the aggregate chunk.
     But first disable mmap so malloc won't use it, since
     we would not be able to later free/realloc space internal
     to a segregated mmap region.
 */
  mem = mALLOc(size);
  if (mem == 0) 
    return 0;

  p = mem2chunk(mem);
  assert(!chunk_is_mmapped(p)); 
  remainder_size = chunksize(p);

  if (opts & 0x2) {       /* optionally clear the elements */
    memset(mem, 0, remainder_size - SIZE_SZ - array_size);
  }

  /* If not provided, allocate the pointer array as final part of chunk */
  if (marray == 0) {
    array_chunk = chunk_at_offset(p, contents_size);
    marray = (Void_t**) (chunk2mem(array_chunk));
    set_head(array_chunk, (remainder_size - contents_size) | PREV_INUSE);
    remainder_size = contents_size;
  }

  /* split out elements */
  for (i = 0; ; ++i) {
    marray[i] = chunk2mem(p);
    if (i != n_elements-1) {
      if (element_size != 0) 
        size = element_size;
      else
        size = request2size(sizes[i]);          
      remainder_size -= size;
      set_head(p, size | PREV_INUSE);
      p = chunk_at_offset(p, size);
    }
    else { /* the final element absorbs any overallocation slop */
      set_head(p, remainder_size | PREV_INUSE);
      break;
    }
  }

#if DEBUG_DLMALLOC
  if (marray != chunks) {
    /* final element must have exactly exhausted chunk */
    if (element_size != 0) 
      assert(remainder_size == element_size);
    else
      assert(remainder_size == request2size(sizes[i]));
    check_inuse_chunk(mem2chunk(marray));
  }

  for (i = 0; i != n_elements; ++i)
    check_inuse_chunk(mem2chunk(marray[i]));
#endif

  return marray;
}


/*
  ------------------------------ valloc ------------------------------
*/

#if __STD_C
Void_t* vALLOc(size_t bytes)
#else
Void_t* vALLOc(bytes) size_t bytes;
#endif
{
  /* Ensure initialization */
  mstate av = get_malloc_state();
  if (av->max_fast == 0) malloc_consolidate(av);
  return mEMALIGn(av->pagesize, bytes);
}

/*
  ------------------------------ pvalloc ------------------------------
*/


#if __STD_C
Void_t* pVALLOc(size_t bytes)
#else
Void_t* pVALLOc(bytes) size_t bytes;
#endif
{
  mstate av = get_malloc_state();
  size_t pagesz;

  /* Ensure initialization */
  if (av->max_fast == 0) malloc_consolidate(av);
  pagesz = av->pagesize;
  return mEMALIGn(pagesz, (bytes + pagesz - 1) & ~(pagesz - 1));
}
   

/*
  ------------------------------ malloc_trim ------------------------------
*/

#if __STD_C
int mTRIm(size_t pad)
#else
int mTRIm(pad) size_t pad;
#endif
{
  mstate av = get_malloc_state();
  /* Ensure initialization/consolidation */
  malloc_consolidate(av);

#ifndef MORECORE_CANNOT_TRIM        
  return sYSTRIm(pad, av);
#else
  return 0;
#endif
}


/*
  ------------------------- malloc_usable_size -------------------------
*/

#if __STD_C
size_t mUSABLe(Void_t* mem)
#else
size_t mUSABLe(mem) Void_t* mem;
#endif
{
  mchunkptr p;
  if (mem != 0) {
    p = mem2chunk(mem);
    if (chunk_is_mmapped(p))
      return chunksize(p) - 2*SIZE_SZ;
    else if (inuse(p))
      return chunksize(p) - SIZE_SZ;
  }
  return 0;
}

/*
  ------------------------------ mallinfo ------------------------------
*/

struct mallinfo mALLINFo()
{
  mstate av = get_malloc_state();
  struct mallinfo mi;
  int i;
  mbinptr b;
  mchunkptr p;
  INTERNAL_SIZE_T avail;
  INTERNAL_SIZE_T fastavail;
  int nblocks;
  int nfastblocks;

  /* Ensure initialization */
  if (av->top == 0)  malloc_consolidate(av);

  check_malloc_state();

  /* Account for top */
  avail = chunksize(av->top);
  nblocks = 1;  /* top always exists */

  /* traverse fastbins */
  nfastblocks = 0;
  fastavail = 0;

  for (i = 0; i < NFASTBINS; ++i) {
    for (p = av->fastbins[i]; p != 0; p = p->fd) {
      ++nfastblocks;
      fastavail += chunksize(p);
    }
  }

  avail += fastavail;

  /* traverse regular bins */
  for (i = 1; i < NBINS; ++i) {
    b = bin_at(av, i);
    for (p = last(b); p != b; p = p->bk) {
      ++nblocks;
      avail += chunksize(p);
    }
  }

  mi.smblks = nfastblocks;
  mi.ordblks = nblocks;
  mi.fordblks = avail;
  mi.uordblks = av->sbrked_mem - avail;
  mi.arena = av->sbrked_mem;
  mi.fsmblks = fastavail;
  mi.keepcost = chunksize(av->top);
  mi.usmblks = av->max_total_mem;
  /* YAP doesn't have special mmapped regions */
  mi.hblkhd = 0L;
  mi.hblks = 0L;
  return mi;
}

/*
  ------------------------------ malloc_stats ------------------------------
*/

UInt
Yap_givemallinfo(void)
{
  struct mallinfo mi = mALLINFo();
  return mi.uordblks;
}


void mSTATs(void)
{
  struct mallinfo mi = mALLINFo();



  fprintf(stderr, "max system bytes = %10lu\n",
          (CHUNK_SIZE_T)(mi.usmblks));
  fprintf(stderr, "system bytes     = %10lu\n",
          (CHUNK_SIZE_T)(mi.arena + mi.hblkhd));
  fprintf(stderr, "in use bytes     = %10lu\n",
          (CHUNK_SIZE_T)(mi.uordblks + mi.hblkhd));

}


/*
  ------------------------------ mallopt ------------------------------
*/

#if __STD_C
int mALLOPt(int param_number, int value)
#else
int mALLOPt(param_number, value) int param_number; int value;
#endif
{
  mstate av = get_malloc_state();
  /* Ensure initialization/consolidation */
  malloc_consolidate(av);

  switch(param_number) {
  case M_MXFAST:
    if (value >= 0 && value <= MAX_FAST_SIZE) {
      set_max_fast(av, value);
      return 1;
    }
    else
      return 0;

  case M_TRIM_THRESHOLD:
    av->trim_threshold = value;
    return 1;

  case M_TOP_PAD:
    av->top_pad = value;
    return 1;

  default:
    return 0;
  }
}

/* 
  -------------------- Alternative MORECORE functions --------------------
*/


/*
  General Requirements for MORECORE.

  The MORECORE function must have the following properties:

  If MORECORE_CONTIGUOUS is false:

    * MORECORE must allocate in multiples of pagesize. It will
      only be called with arguments that are multiples of pagesize.

    * MORECORE(0) must return an address that is at least 
      MALLOC_ALIGNMENT aligned. (Page-aligning always suffices.)

  else (i.e. If MORECORE_CONTIGUOUS is true):

    * Consecutive calls to MORECORE with positive arguments
      return increasing addresses, indicating that space has been
      contiguously extended. 

    * MORECORE need not allocate in multiples of pagesize.
      Calls to MORECORE need not have args of multiples of pagesize.

    * MORECORE need not page-align.

  In either case:

    * MORECORE may allocate more memory than requested. (Or even less,
      but this will generally result in a malloc failure.)

    * MORECORE must not allocate memory when given argument zero, but
      instead return one past the end address of memory from previous
      nonzero call. This malloc does NOT call MORECORE(0)
      until at least one call with positive arguments is made, so
      the initial value returned is not important.

    * Even though consecutive calls to MORECORE need not return contiguous
      addresses, it must be OK for malloc'ed chunks to span multiple
      regions in those cases where they do happen to be contiguous.

    * MORECORE need not handle negative arguments -- it may instead
      just return MORECORE_FAILURE when given negative arguments.
      Negative arguments are always multiples of pagesize. MORECORE
      must not misinterpret negative args as large positive unsigned
      args. You can suppress all such calls from even occurring by defining
      MORECORE_CANNOT_TRIM,

  There is some variation across systems about the type of the
  argument to sbrk/MORECORE. If size_t is unsigned, then it cannot
  actually be size_t, because sbrk supports negative args, so it is
  normally the signed type of the same width as size_t (sometimes
  declared as "intptr_t", and sometimes "ptrdiff_t").  It doesn't much
  matter though. Internally, we use "long" as arguments, which should
  work across all reasonable possibilities.

  Additionally, if MORECORE ever returns failure for a positive
  request, and HAVE_MMAP is true, then mmap is used as a noncontiguous
  system allocator. This is a useful backup strategy for systems with
  holes in address spaces -- in this case sbrk cannot contiguously
  expand the heap, but mmap may be able to map noncontiguous space.

  If you'd like mmap to ALWAYS be used, you can define MORECORE to be
  a function that always returns MORECORE_FAILURE.

  Malloc only has limited ability to detect failures of MORECORE
  to supply contiguous space when it says it can. In particular,
  multithreaded programs that do not use locks may result in
  rece conditions across calls to MORECORE that result in gaps
  that cannot be detected as such, and subsequent corruption.

  If you are using this malloc with something other than sbrk (or its
  emulation) to supply memory regions, you probably want to set
  MORECORE_CONTIGUOUS as false.  As an example, here is a custom
  allocator kindly contributed for pre-OSX macOS.  It uses virtually
  but not necessarily physically contiguous non-paged memory (locked
  in, present and won't get swapped out).  You can use it by
  uncommenting this section, adding some #includes, and setting up the
  appropriate defines above:

      #define MORECORE osMoreCore
      #define MORECORE_CONTIGUOUS 0

  There is also a shutdown routine that should somehow be called for
  cleanup upon program exit.

  #define MAX_POOL_ENTRIES 100
  #define MINIMUM_MORECORE_SIZE  (64 * 1024)
  static int next_os_pool;
  void *our_os_pools[MAX_POOL_ENTRIES];

  void *osMoreCore(int size)
  {
    void *ptr = 0;
    static void *sbrk_top = 0;

    if (size > 0)
    {
      if (size < MINIMUM_MORECORE_SIZE)
         size = MINIMUM_MORECORE_SIZE;
      if (CurrentExecutionLevel() == kTaskLevel)
         ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0);
      if (ptr == 0)
      {
        return (void *) MORECORE_FAILURE;
      }
      // save ptrs so they can be freed during cleanup
      our_os_pools[next_os_pool] = ptr;
      next_os_pool++;
      ptr = (void *) ((((CHUNK_SIZE_T) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK);
      sbrk_top = (char *) ptr + size;
      return ptr;
    }
    else if (size < 0)
    {
      // we don't currently support shrink behavior
      return (void *) MORECORE_FAILURE;
    }
    else
    {
      return sbrk_top;
    }
  }

  // cleanup any allocated memory pools
  // called as last thing before shutting down driver

  void osCleanupMem(void)
  {
    void **ptr;

    for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++)
      if (*ptr)
      {
         PoolDeallocate(*ptr);
         *ptr = 0;
      }
  }

*/



/* ------------------------------------------------------------
History:
    V2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)
      * Fix malloc_state bitmap array misdeclaration

    V2.7.1 Thu Jul 25 10:58:03 2002  Doug Lea  (dl at gee)
      * Allow tuning of FIRST_SORTED_BIN_SIZE
      * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte.
      * Better detection and support for non-contiguousness of MORECORE. 
        Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger
      * Bypass most of malloc if no frees. Thanks To Emery Berger.
      * Fix freeing of old top non-contiguous chunk im sysmalloc.
      * Raised default trim and map thresholds to 256K.
      * Fix mmap-related #defines. Thanks to Lubos Lunak.
      * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield.
      * Branch-free bin calculation
      * Default trim and mmap thresholds now 256K.

    V2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)
      * Introduce independent_comalloc and independent_calloc.
        Thanks to Michael Pachos for motivation and help.
      * Make optional .h file available
      * Allow > 2GB requests on 32bit systems.
      * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>.
        Thanks also to Andreas Mueller <a.mueller at paradatec.de>,
        and Anonymous.
      * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for 
        helping test this.)
      * memalign: check alignment arg
      * realloc: don't try to shift chunks backwards, since this
        leads to  more fragmentation in some programs and doesn't
        seem to help in any others.
      * Collect all cases in malloc requiring system memory into sYSMALLOc
      * Use mmap as backup to sbrk
      * Place all internal state in malloc_state
      * Introduce fastbins (although similar to 2.5.1)
      * Many minor tunings and cosmetic improvements
      * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK 
      * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS
        Thanks to Tony E. Bennett <tbennett@nvidia.com> and others.
      * Include errno.h to support default failure action.

    V2.6.6 Sun Dec  5 07:42:19 1999  Doug Lea  (dl at gee)
      * return null for negative arguments
      * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com>
         * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
          (e.g. WIN32 platforms)
         * Cleanup header file inclusion for WIN32 platforms
         * Cleanup code to avoid Microsoft Visual C++ compiler complaints
         * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing
           memory allocation routines
         * Set 'malloc_getpagesize' for WIN32 platforms (needs more work)
         * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to
           usage of 'assert' in non-WIN32 code
         * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to
           avoid infinite loop
      * Always call 'fREe()' rather than 'free()'

    V2.6.5 Wed Jun 17 15:57:31 1998  Doug Lea  (dl at gee)
      * Fixed ordering problem with boundary-stamping

    V2.6.3 Sun May 19 08:17:58 1996  Doug Lea  (dl at gee)
      * Added pvalloc, as recommended by H.J. Liu
      * Added 64bit pointer support mainly from Wolfram Gloger
      * Added anonymously donated WIN32 sbrk emulation
      * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen
      * malloc_extend_top: fix mask error that caused wastage after
        foreign sbrks
      * Add linux mremap support code from HJ Liu

    V2.6.2 Tue Dec  5 06:52:55 1995  Doug Lea  (dl at gee)
      * Integrated most documentation with the code.
      * Add support for mmap, with help from
        Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
      * Use last_remainder in more cases.
      * Pack bins using idea from  colin@nyx10.cs.du.edu
      * Use ordered bins instead of best-fit threshhold
      * Eliminate block-local decls to simplify tracing and debugging.
      * Support another case of realloc via move into top
      * Fix error occuring when initial sbrk_base not word-aligned.
      * Rely on page size for units instead of SBRK_UNIT to
        avoid surprises about sbrk alignment conventions.
      * Add mallinfo, mallopt. Thanks to Raymond Nijssen
        (raymond@es.ele.tue.nl) for the suggestion.
      * Add `pad' argument to malloc_trim and top_pad mallopt parameter.
      * More precautions for cases where other routines call sbrk,
        courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
      * Added macros etc., allowing use in linux libc from
        H.J. Lu (hjl@gnu.ai.mit.edu)
      * Inverted this history list

    V2.6.1 Sat Dec  2 14:10:57 1995  Doug Lea  (dl at gee)
      * Re-tuned and fixed to behave more nicely with V2.6.0 changes.
      * Removed all preallocation code since under current scheme
        the work required to undo bad preallocations exceeds
        the work saved in good cases for most test programs.
      * No longer use return list or unconsolidated bins since
        no scheme using them consistently outperforms those that don't
        given above changes.
      * Use best fit for very large chunks to prevent some worst-cases.
      * Added some support for debugging

    V2.6.0 Sat Nov  4 07:05:23 1995  Doug Lea  (dl at gee)
      * Removed footers when chunks are in use. Thanks to
        Paul Wilson (wilson@cs.texas.edu) for the suggestion.

    V2.5.4 Wed Nov  1 07:54:51 1995  Doug Lea  (dl at gee)
      * Added malloc_trim, with help from Wolfram Gloger
        (wmglo@Dent.MED.Uni-Muenchen.DE).

    V2.5.3 Tue Apr 26 10:16:01 1994  Doug Lea  (dl at g)

    V2.5.2 Tue Apr  5 16:20:40 1994  Doug Lea  (dl at g)
      * realloc: try to expand in both directions
      * malloc: swap order of clean-bin strategy;
      * realloc: only conditionally expand backwards
      * Try not to scavenge used bins
      * Use bin counts as a guide to preallocation
      * Occasionally bin return list chunks in first scan
      * Add a few optimizations from colin@nyx10.cs.du.edu

    V2.5.1 Sat Aug 14 15:40:43 1993  Doug Lea  (dl at g)
      * faster bin computation & slightly different binning
      * merged all consolidations to one part of malloc proper
         (eliminating old malloc_find_space & malloc_clean_bin)
      * Scan 2 returns chunks (not just 1)
      * Propagate failure in realloc if malloc returns 0
      * Add stuff to allow compilation on non-ANSI compilers
          from kpv@research.att.com

    V2.5 Sat Aug  7 07:41:59 1993  Doug Lea  (dl at g.oswego.edu)
      * removed potential for odd address access in prev_chunk
      * removed dependency on getpagesize.h
      * misc cosmetics and a bit more internal documentation
      * anticosmetics: mangled names in macros to evade debugger strangeness
      * tested on sparc, hp-700, dec-mips, rs6000
          with gcc & native cc (hp, dec only) allowing
          Detlefs & Zorn comparison study (in SIGPLAN Notices.)

    Trial version Fri Aug 28 13:14:29 1992  Doug Lea  (dl at g.oswego.edu)
      * Based loosely on libg++-1.2X malloc. (It retains some of the overall
         structure of old version,  but most details differ.)

*/

void
Yap_initdlmalloc(void)
{
  HeapTop = (ADDR)ALIGN_SIZE(HeapTop,16);
  Yap_NOfMemoryHoles = 0;
  Yap_av = (struct malloc_state *)HeapTop;
  memset((void *)Yap_av, 0, sizeof(struct malloc_state));
  HeapTop += sizeof(struct malloc_state);
  HeapTop = (ADDR)ALIGN_SIZE(HeapTop,2*SIZEOF_LONG_LONG_INT);
  HeapMax = HeapTop-Yap_HeapBase;
}

void Yap_RestoreDLMalloc(void)
{
  mstate av = Yap_av;
  int i;
  mchunkptr p;
  mchunkptr q;
  mbinptr b;
  unsigned int binbit;
  int empty;
  unsigned int idx;
  INTERNAL_SIZE_T size;
  CHUNK_SIZE_T  total = 0;
  int max_fast_bin;

  /* internal size_t must be no wider than pointer type */
  assert(sizeof(INTERNAL_SIZE_T) <= sizeof(char*));

  /* alignment is a power of 2 */
  assert((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-1)) == 0);

  /* cannot run remaining checks until fully initialized */
  if (av->top == 0 || av->top == initial_top(av))
    return;

  /* pagesize is a power of 2 */
  assert((av->pagesize & (av->pagesize-1)) == 0);

  /* properties of fastbins */

  /* max_fast is in allowed range */
  assert(get_max_fast(av) <= request2size(MAX_FAST_SIZE));

  max_fast_bin = fastbin_index(av->max_fast);

  if (av->top) {
    av->top = ChunkPtrAdjust(av->top);
  }
  if (av->last_remainder) {
    av->last_remainder = ChunkPtrAdjust(av->last_remainder);
  }
  for (i = 0; i < NFASTBINS; ++i) {
    
    if (av->fastbins[i]) {
      av->fastbins[i] = ChunkPtrAdjust(av->fastbins[i]);
    }
    p = av->fastbins[i];

    /* all bins past max_fast are empty */
    if (i > max_fast_bin)
      assert(p == 0);

    while (p != 0) {
      /* each chunk claims to be inuse */
      check_inuse_chunk(p);
      total += chunksize(p);
      /* chunk belongs in this bin */
      assert(fastbin_index(chunksize(p)) == i);
      if (p->fd)
	p->fd = ChunkPtrAdjust(p->fd);
      if (p->bk)
	p->bk = ChunkPtrAdjust(p->bk);
      p = p->fd;
    }
  }

  if (total != 0)
    assert(have_fastchunks(av));
  else if (!have_fastchunks(av))
    assert(total == 0);

  for (i = 0; i < NBINS*2; i++) {
    if (av->bins[i]) {
      av->bins[i] = ChunkPtrAdjust(av->bins[i]);
    }
  }

  /* check normal bins */
  for (i = 1; i < NBINS; ++i) {
    b = bin_at(av,i);

    /* binmap is accurate (except for bin 1 == unsorted_chunks) */
    if (i >= 2) {
      binbit = get_binmap(av,i);
      empty = last(b) == b;
      if (!binbit)
        assert(empty);
      else if (!empty)
        assert(binbit);
    }

    for (p = last(b); p != b; p = p->bk) {
      /* each chunk claims to be free */
      check_free_chunk(p);
      if (p->fd)
	p->fd = ChunkPtrAdjust(p->fd);
      if (p->bk)
	p->bk = ChunkPtrAdjust(p->bk);
      size = chunksize(p);
      total += size;
      if (i >= 2) {
        /* chunk belongs in bin */
        idx = bin_index(size);
        assert(idx == i);
        /* lists are sorted */
        if ((CHUNK_SIZE_T) size >= (CHUNK_SIZE_T)(FIRST_SORTED_BIN_SIZE)) {
          assert(p->bk == b || 
                 (CHUNK_SIZE_T)chunksize(p->bk) >= 
                 (CHUNK_SIZE_T)chunksize(p));
        }
      }
      /* chunk is followed by a legal chain of inuse chunks */
      for (q = next_chunk(p);
           (q != av->top && inuse(q) && 
             (CHUNK_SIZE_T)(chunksize(q)) >= MINSIZE);
           q = next_chunk(q)) {
	check_inuse_chunk(q);
      }
    }
  }

}


#endif /* USE_DL_MALLOC */