dlmalloc.c

  mmapped_mem -= (size + p->prev_size);

  ret = munmap((char *)p - p->prev_size, size + p->prev_size);

  /* munmap returns non-zero on failure */
  assert(ret == 0);
}

#if HAVE_MREMAP

#if __STD_C
static mchunkptr mremap_chunk(mchunkptr p, size_t new_size)
#else
static mchunkptr mremap_chunk(p, new_size) mchunkptr p; size_t new_size;
#endif
{
  size_t page_mask = malloc_getpagesize - 1;
  INTERNAL_SIZE_T offset = p->prev_size;
  INTERNAL_SIZE_T size = chunksize(p);
  char *cp;

  assert (chunk_is_mmapped(p));
  assert(! ((char*)p >= sbrk_base && (char*)p < sbrk_base + sbrked_mem));
  assert((n_mmaps > 0));
  assert(((size + offset) & (malloc_getpagesize-1)) == 0);

  /* Note the extra SIZE_SZ overhead as in mmap_chunk(). */
  new_size = (new_size + offset + SIZE_SZ + page_mask) & ~page_mask;

  cp = (char *)mremap((char *)p - offset, size + offset, new_size, 1);

  if (cp == (char *)-1) return 0;

  p = (mchunkptr)(cp + offset);

  assert(aligned_OK(chunk2mem(p)));

  assert((p->prev_size == offset));
  set_head(p, (new_size - offset)|IS_MMAPPED);

  mmapped_mem -= size + offset;
  mmapped_mem += new_size;
  if ((unsigned long)mmapped_mem > (unsigned long)max_mmapped_mem)
    max_mmapped_mem = mmapped_mem;
  if ((unsigned long)(mmapped_mem + sbrked_mem) > (unsigned long)max_total_mem)
    max_total_mem = mmapped_mem + sbrked_mem;
  return p;
}

#endif /* HAVE_MREMAP */

#endif /* HAVE_MMAP */




/*
  Extend the top-most chunk by obtaining memory from system.
  Main interface to sbrk (but see also malloc_trim).
*/

#if __STD_C
static void malloc_extend_top(INTERNAL_SIZE_T nb)
#else
static void malloc_extend_top(nb) INTERNAL_SIZE_T nb;
#endif
{
  char*     brk;                  /* return value from sbrk */
  INTERNAL_SIZE_T front_misalign; /* unusable bytes at front of sbrked space */
  INTERNAL_SIZE_T correction;     /* bytes for 2nd sbrk call */
  char*     new_brk;              /* return of 2nd sbrk call */
  INTERNAL_SIZE_T top_size;       /* new size of top chunk */

  mchunkptr old_top     = top;  /* Record state of old top */
  INTERNAL_SIZE_T old_top_size = chunksize(old_top);
  char*     old_end      = (char*)(chunk_at_offset(old_top, old_top_size));

  /* Pad request with top_pad plus minimal overhead */

  INTERNAL_SIZE_T    sbrk_size     = nb + top_pad + MINSIZE;
  unsigned long pagesz    = malloc_getpagesize;

  /* If not the first time through, round to preserve page boundary */
  /* Otherwise, we need to correct to a page size below anyway. */
  /* (We also correct below if an intervening foreign sbrk call.) */

  if (sbrk_base != (char*)(-1))
    sbrk_size = (sbrk_size + (pagesz - 1)) & ~(pagesz - 1);

  brk = (char*)(MORECORE (sbrk_size));

  /* Fail if sbrk failed or if a foreign sbrk call killed our space */
  if (brk == (char*)(MORECORE_FAILURE) ||
      (brk < old_end && old_top != initial_top))
    return;

  sbrked_mem += sbrk_size;

  if (brk == old_end) /* can just add bytes to current top */
  {
    top_size = sbrk_size + old_top_size;
    set_head(top, top_size | PREV_INUSE);
  }
  else
  {
    if (sbrk_base == (char*)(-1))  /* First time through. Record base */
      sbrk_base = brk;
    else  /* Someone else called sbrk().  Count those bytes as sbrked_mem. */
      sbrked_mem += brk - (char*)old_end;

    /* Guarantee alignment of first new chunk made from this space */
    front_misalign = (unsigned long)chunk2mem(brk) & MALLOC_ALIGN_MASK;
    if (front_misalign > 0)
    {
      correction = (MALLOC_ALIGNMENT) - front_misalign;
      brk += correction;
    }
    else
      correction = 0;

    /* Guarantee the next brk will be at a page boundary */

    correction += ((((unsigned long)(brk + sbrk_size))+(pagesz-1)) &
		   ~(pagesz - 1)) - ((unsigned long)(brk + sbrk_size));

    /* Allocate correction */
    new_brk = (char*)(MORECORE (correction));
    if (new_brk == (char*)(MORECORE_FAILURE)) return;

    sbrked_mem += correction;

    top = (mchunkptr)brk;
    top_size = new_brk - brk + correction;
    set_head(top, top_size | PREV_INUSE);

    if (old_top != initial_top)
    {

      /* There must have been an intervening foreign sbrk call. */
      /* A double fencepost is necessary to prevent consolidation */

      /* If not enough space to do this, then user did something very wrong */
      if (old_top_size < MINSIZE)
      {
	set_head(top, PREV_INUSE); /* will force null return from malloc */
	return;
      }

      /* Also keep size a multiple of MALLOC_ALIGNMENT */
      old_top_size = (old_top_size - 3*SIZE_SZ) & ~MALLOC_ALIGN_MASK;
      set_head_size(old_top, old_top_size);
      chunk_at_offset(old_top, old_top_size          )->size =
	SIZE_SZ|PREV_INUSE;
      chunk_at_offset(old_top, old_top_size + SIZE_SZ)->size =
	SIZE_SZ|PREV_INUSE;
      /* If possible, release the rest. */
      if (old_top_size >= MINSIZE)
	fREe(chunk2mem(old_top));
    }
  }

  if ((unsigned long)sbrked_mem > (unsigned long)max_sbrked_mem)
    max_sbrked_mem = sbrked_mem;
  if ((unsigned long)(mmapped_mem + sbrked_mem) > (unsigned long)max_total_mem)
    max_total_mem = mmapped_mem + sbrked_mem;

  /* We always land on a page boundary */
  assert(((unsigned long)((char*)top + top_size) & (pagesz - 1)) == 0);
}




/* Main public routines */


/*
  Malloc Algorthim:

    The requested size is first converted into a usable form, `nb'.
    This currently means to add 4 bytes overhead plus possibly more to
    obtain 8-byte alignment and/or to obtain a size of at least
    MINSIZE (currently 16 bytes), the smallest allocatable size.
    (All fits are considered `exact' if they are within MINSIZE bytes.)

    From there, the first successful of the following steps is taken:

      1. The bin corresponding to the request size is scanned, and if
	 a chunk of exactly the right size is found, it is taken.

      2. The most recently remaindered chunk is used if it is big
	 enough.  This is a form of (roving) first fit, used only in
	 the absence of exact fits. Runs of consecutive requests use
	 the remainder of the chunk used for the previous such request
	 whenever possible. This limited use of a first-fit style
	 allocation strategy tends to give contiguous chunks
	 coextensive lifetimes, which improves locality and can reduce
	 fragmentation in the long run.

      3. Other bins are scanned in increasing size order, using a
	 chunk big enough to fulfill the request, and splitting off
	 any remainder.  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.

      4. If large enough, the chunk bordering the end of memory
	 (`top') is split off. (This use of `top' is in accord with
	 the best-fit search rule.  In effect, `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).

      5. If the request size meets the mmap threshold and the
	 system supports mmap, and there are few enough currently
	 allocated mmapped regions, and a call to mmap succeeds,
	 the request is allocated via direct memory mapping.

      6. Otherwise, the top of memory is extended by
	 obtaining more space from the system (normally using sbrk,
	 but definable to anything else via the MORECORE macro).
	 Memory is gathered from the system (in system page-sized
	 units) in a way that allows chunks obtained across different
	 sbrk calls to be consolidated, but does not require
	 contiguous memory. Thus, it should be safe to intersperse
	 mallocs with other sbrk calls.


      All allocations are made from the the `lowest' part of any found
      chunk. (The implementation invariant is 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.)

*/

#if __STD_C
Void_t* mALLOc(size_t bytes)
#else
Void_t* mALLOc(bytes) size_t bytes;
#endif
{
  mchunkptr victim;                  /* inspected/selected chunk */
  INTERNAL_SIZE_T victim_size;       /* its size */
  int       idx;                     /* index for bin traversal */
  mbinptr   bin;                     /* associated bin */
  mchunkptr remainder;               /* remainder from a split */
  long      remainder_size;          /* its size */
  int       remainder_index;         /* its bin index */
  unsigned long block;               /* block traverser bit */
  int       startidx;                /* first bin of a traversed block */
  mchunkptr fwd;                     /* misc temp for linking */
  mchunkptr bck;                     /* misc temp for linking */
  mbinptr q;                         /* misc temp */

  INTERNAL_SIZE_T nb;

#if CONFIG_VAL(SYS_MALLOC_F_LEN)
	if (!(gd->flags & GD_FLG_FULL_MALLOC_INIT))
		return malloc_simple(bytes);
#endif

  /* check if mem_malloc_init() was run */
  if ((mem_malloc_start == 0) && (mem_malloc_end == 0)) {
    /* not initialized yet */
    return NULL;
  }

  if ((long)bytes < 0) return NULL;

  nb = request2size(bytes);  /* padded request size; */

  /* Check for exact match in a bin */

  if (is_small_request(nb))  /* Faster version for small requests */
  {
    idx = smallbin_index(nb);

    /* No traversal or size check necessary for small bins.  */

    q = bin_at(idx);
    victim = last(q);

    /* Also scan the next one, since it would have a remainder < MINSIZE */
    if (victim == q)
    {
      q = next_bin(q);
      victim = last(q);
    }
    if (victim != q)
    {
      victim_size = chunksize(victim);
      unlink(victim, bck, fwd);
      set_inuse_bit_at_offset(victim, victim_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    idx += 2; /* Set for bin scan below. We've already scanned 2 bins. */

  }
  else
  {
    idx = bin_index(nb);
    bin = bin_at(idx);

    for (victim = last(bin); victim != bin; victim = victim->bk)
    {
      victim_size = chunksize(victim);
      remainder_size = victim_size - nb;

      if (remainder_size >= (long)MINSIZE) /* too big */
      {
	--idx; /* adjust to rescan below after checking last remainder */
	break;
      }

      else if (remainder_size >= 0) /* exact fit */
      {
	unlink(victim, bck, fwd);
	set_inuse_bit_at_offset(victim, victim_size);
	check_malloced_chunk(victim, nb);
	return chunk2mem(victim);
      }
    }

    ++idx;

  }

  /* Try to use the last split-off remainder */

  if ( (victim = last_remainder->fd) != last_remainder)
  {
    victim_size = chunksize(victim);
    remainder_size = victim_size - nb;

    if (remainder_size >= (long)MINSIZE) /* re-split */
    {
      remainder = chunk_at_offset(victim, nb);
      set_head(victim, nb | PREV_INUSE);
      link_last_remainder(remainder);
      set_head(remainder, remainder_size | PREV_INUSE);
      set_foot(remainder, remainder_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    clear_last_remainder;

    if (remainder_size >= 0)  /* exhaust */
    {
      set_inuse_bit_at_offset(victim, victim_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    /* Else place in bin */

    frontlink(victim, victim_size, remainder_index, bck, fwd);
  }

  /*
     If there are any possibly nonempty big-enough blocks,
     search for best fitting chunk by scanning bins in blockwidth units.
  */

  if ( (block = idx2binblock(idx)) <= binblocks_r)
  {

    /* Get to the first marked block */

    if ( (block & binblocks_r) == 0)
    {
      /* force to an even block boundary */
      idx = (idx & ~(BINBLOCKWIDTH - 1)) + BINBLOCKWIDTH;
      block <<= 1;
      while ((block & binblocks_r) == 0)
      {
	idx += BINBLOCKWIDTH;
	block <<= 1;
      }
    }

    /* For each possibly nonempty block ... */
    for (;;)
    {
      startidx = idx;          /* (track incomplete blocks) */
      q = bin = bin_at(idx);

      /* For each bin in this block ... */
      do
      {
	/* Find and use first big enough chunk ... */

	for (victim = last(bin); victim != bin; victim = victim->bk)
	{
	  victim_size = chunksize(victim);
	  remainder_size = victim_size - nb;

	  if (remainder_size >= (long)MINSIZE) /* split */
	  {
	    remainder = chunk_at_offset(victim, nb);
	    set_head(victim, nb | PREV_INUSE);
	    unlink(victim, bck, fwd);
	    link_last_remainder(remainder);
	    set_head(remainder, remainder_size | PREV_INUSE);
	    set_foot(remainder, remainder_size);
	    check_malloced_chunk(victim, nb);
	    return chunk2mem(victim);
	  }

	  else if (remainder_size >= 0)  /* take */
	  {
	    set_inuse_bit_at_offset(victim, victim_size);
	    unlink(victim, bck, fwd);
	    check_malloced_chunk(victim, nb);
	    return chunk2mem(victim);
	  }

	}

       bin = next_bin(bin);

      } while ((++idx & (BINBLOCKWIDTH - 1)) != 0);

      /* Clear out the block bit. */

      do   /* Possibly backtrack to try to clear a partial block */
      {
	if ((startidx & (BINBLOCKWIDTH - 1)) == 0)
	{
	  av_[1] = (mbinptr)(binblocks_r & ~block);
	  break;
	}
	--startidx;
       q = prev_bin(q);
      } while (first(q) == q);

      /* Get to the next possibly nonempty block */

      if ( (block <<= 1) <= binblocks_r && (block != 0) )
      {
	while ((block & binblocks_r) == 0)
	{
	  idx += BINBLOCKWIDTH;
	  block <<= 1;
	}
      }
      else
	break;
    }
  }


  /* Try to use top chunk */

  /* Require that there be a remainder, ensuring top always exists  */
  if ( (remainder_size = chunksize(top) - nb) < (long)MINSIZE)
  {

#if HAVE_MMAP
    /* If big and would otherwise need to extend, try to use mmap instead */
    if ((unsigned long)nb >= (unsigned long)mmap_threshold &&
	(victim = mmap_chunk(nb)) != 0)
      return chunk2mem(victim);
#endif

    /* Try to extend */
    malloc_extend_top(nb);
    if ( (remainder_size = chunksize(top) - nb) < (long)MINSIZE)
      return NULL; /* propagate failure */
  }

  victim = top;
  set_head(victim, nb | PREV_INUSE);
  top = chunk_at_offset(victim, nb);
  set_head(top, remainder_size | PREV_INUSE);
  check_malloced_chunk(victim, nb);
  return chunk2mem(victim);

}




/*

  free() algorithm :

    cases:

       1. free(0) has no effect.

       2. If the chunk was allocated via mmap, it is release via munmap().

       3. If a returned chunk borders the current high end of memory,
	  it is consolidated into the top, and if the total unused
	  topmost memory exceeds the trim threshold, malloc_trim is
	  called.

       4. Other chunks are consolidated as they arrive, and
	  placed in corresponding bins. (This includes the case of
	  consolidating with the current `last_remainder').

*/


#if __STD_C
void fREe(Void_t* mem)
#else
void fREe(mem) Void_t* mem;
#endif
{
  mchunkptr p;         /* chunk corresponding to mem */
  INTERNAL_SIZE_T hd;  /* its head field */
  INTERNAL_SIZE_T sz;  /* its size */
  int       idx;       /* its bin index */
  mchunkptr next;      /* next contiguous chunk */
  INTERNAL_SIZE_T nextsz; /* its size */
  INTERNAL_SIZE_T prevsz; /* size of previous contiguous chunk */
  mchunkptr bck;       /* misc temp for linking */
  mchunkptr fwd;       /* misc temp for linking */
  int       islr;      /* track whether merging with last_remainder */

#if CONFIG_VAL(SYS_MALLOC_F_LEN)
	/* free() is a no-op - all the memory will be freed on relocation */
	if (!(gd->flags & GD_FLG_FULL_MALLOC_INIT))
		return;
#endif

  if (mem == NULL)                              /* free(0) has no effect */
    return;

  p = mem2chunk(mem);
  hd = p->size;

#if HAVE_MMAP
  if (hd & IS_MMAPPED)                       /* release mmapped memory. */
  {
    munmap_chunk(p);
    return;
  }
#endif

  check_inuse_chunk(p);

  sz = hd & ~PREV_INUSE;
  next = chunk_at_offset(p, sz);
  nextsz = chunksize(next);

  if (next == top)                            /* merge with top */
  {
    sz += nextsz;

    if (!(hd & PREV_INUSE))                    /* consolidate backward */
    {
      prevsz = p->prev_size;
      p = chunk_at_offset(p, -((long) prevsz));
      sz += prevsz;
      unlink(p, bck, fwd);
    }

    set_head(p, sz | PREV_INUSE);
    top = p;
    if ((unsigned long)(sz) >= (unsigned long)trim_threshold)
      malloc_trim(top_pad);
    return;
  }

  set_head(next, nextsz);                    /* clear inuse bit */

  islr = 0;

  if (!(hd & PREV_INUSE))                    /* consolidate backward */
  {
    prevsz = p->prev_size;
    p = chunk_at_offset(p, -((long) prevsz));
    sz += prevsz;

    if (p->fd == last_remainder)             /* keep as last_remainder */
      islr = 1;
    else
      unlink(p, bck, fwd);
  }

  if (!(inuse_bit_at_offset(next, nextsz)))   /* consolidate forward */
  {
    sz += nextsz;

    if (!islr && next->fd == last_remainder)  /* re-insert last_remainder */
    {
      islr = 1;
      link_last_remainder(p);
    }
    else
      unlink(next, bck, fwd);
  }


  set_head(p, sz | PREV_INUSE);
  set_foot(p, sz);
  if (!islr)
    frontlink(p, sz, idx, bck, fwd);
}





/*

  Realloc algorithm:

    Chunks that were obtained via mmap cannot be extended or shrunk
    unless HAVE_MREMAP is defined, in which case mremap is used.
    Otherwise, if their reallocation is for additional space, they are
    copied.  If for less, they are just left alone.

    Otherwise, if the reallocation is for additional space, and the
    chunk can be extended, it is, else a malloc-copy-free sequence is
    taken.  There are several different ways that a chunk could be
    extended. All are tried:

       * Extending forward into following adjacent free chunk.
       * Shifting backwards, joining preceding adjacent space
       * Both shifting backwards and extending forward.
       * Extending into newly sbrked space

    Unless the #define REALLOC_ZERO_BYTES_FREES is set, realloc with a
    size argument of zero (re)allocates a minimum-sized chunk.

    If the reallocation is for less space, and the new request is for
    a `small' (<512 bytes) size, then the newly unused space is lopped
    off and freed.

    The old unix realloc convention of allowing the last-free'd chunk
    to be used as an argument to realloc is no longer supported.
    I don't know of any programs still relying on this feature,
    and allowing it would also allow too many other incorrect
    usages of realloc to be sensible.


*/


#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
{
  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 */
  INTERNAL_SIZE_T  nextsize;  /* its size */

  mchunkptr prev;             /* previous contiguous chunk before oldp */
  INTERNAL_SIZE_T  prevsize;  /* its size */

  mchunkptr remainder;        /* holds split off extra space from newp */
  INTERNAL_SIZE_T  remainder_size;   /* its size */

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

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

  if ((long)bytes < 0) return NULL;

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

#if CONFIG_VAL(SYS_MALLOC_F_LEN)
	if (!(gd->flags & GD_FLG_FULL_MALLOC_INIT)) {
		/* This is harder to support and should not be needed */
		panic("pre-reloc realloc() is not supported");
	}
#endif

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


  nb = request2size(bytes);

#if HAVE_MMAP
  if (chunk_is_mmapped(oldp))
  {
#if HAVE_MREMAP
    newp = mremap_chunk(oldp, nb);
    if(newp) return chunk2mem(newp);
#endif
    /* Note the extra SIZE_SZ overhead. */
    if(oldsize - SIZE_SZ >= nb) return oldmem; /* do nothing */
    /* Must alloc, copy, free. */
    newmem = mALLOc(bytes);
    if (newmem == 0) return 0; /* propagate failure */
    MALLOC_COPY(newmem, oldmem, oldsize - 2*SIZE_SZ);
    munmap_chunk(oldp);
    return newmem;
  }
#endif

  check_inuse_chunk(oldp);

  if ((long)(oldsize) < (long)(nb))
  {

    /* Try expanding forward */

    next = chunk_at_offset(oldp, oldsize);
    if (next == top || !inuse(next))
    {
      nextsize = chunksize(next);

      /* Forward into top only if a remainder */
      if (next == top)
      {
	if ((long)(nextsize + newsize) >= (long)(nb + MINSIZE))
	{
	  newsize += nextsize;
	  top = chunk_at_offset(oldp, nb);
	  set_head(top, (newsize - nb) | PREV_INUSE);
	  set_head_size(oldp, nb);
	  return chunk2mem(oldp);
	}
      }

      /* Forward into next chunk */
      else if (((long)(nextsize + newsize) >= (long)(nb)))
      {
	unlink(next, bck, fwd);
	newsize  += nextsize;
	goto split;
      }
    }
    else
    {
      next = NULL;
      nextsize = 0;
    }

    /* Try shifting backwards. */

    if (!prev_inuse(oldp))
    {
      prev = prev_chunk(oldp);
      prevsize = chunksize(prev);

      /* try forward + backward first to save a later consolidation */

      if (next != NULL)
      {
	/* into top */
	if (next == top)
	{
	  if ((long)(nextsize + prevsize + newsize) >= (long)(nb + MINSIZE))
	  {
	    unlink(prev, bck, fwd);
	    newp = prev;
	    newsize += prevsize + nextsize;
	    newmem = chunk2mem(newp);
	    MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
	    top = chunk_at_offset(newp, nb);
	    set_head(top, (newsize - nb) | PREV_INUSE);
	    set_head_size(newp, nb);
	    return newmem;
	  }
	}

	/* into next chunk */
	else if (((long)(nextsize + prevsize + newsize) >= (long)(nb)))
	{
	  unlink(next, bck, fwd);
	  unlink(prev, bck, fwd);
	  newp = prev;
	  newsize += nextsize + prevsize;
	  newmem = chunk2mem(newp);
	  MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
	  goto split;
	}
      }

      /* backward only */
      if (prev != NULL && (long)(prevsize + newsize) >= (long)nb)
      {
	unlink(prev, bck, fwd);
	newp = prev;
	newsize += prevsize;
	newmem = chunk2mem(newp);
	MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
	goto split;
      }
    }

    /* Must allocate */

    newmem = mALLOc (bytes);

    if (newmem == NULL)  /* propagate failure */
      return NULL;

    /* Avoid copy if newp is next chunk after oldp. */
    /* (This can only happen when new chunk is sbrk'ed.) */

    if ( (newp = mem2chunk(newmem)) == next_chunk(oldp))
    {
      newsize += chunksize(newp);
      newp = oldp;
      goto split;
    }

    /* Otherwise copy, free, and exit */
    MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
    fREe(oldmem);
    return newmem;
  }


 split:  /* split off extra room in old or expanded chunk */

  if (newsize - nb >= MINSIZE) /* split off remainder */
  {
    remainder = chunk_at_offset(newp, nb);
    remainder_size = newsize - nb;
    set_head_size(newp, nb);
    set_head(remainder, remainder_size | PREV_INUSE);
    set_inuse_bit_at_offset(remainder, remainder_size);
    fREe(chunk2mem(remainder)); /* let free() deal with it */
  }
  else
  {
    set_head_size(newp, newsize);
    set_inuse_bit_at_offset(newp, newsize);
  }

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




/*

  memalign algorithm:

    memalign requests more than enough space from malloc, finds a spot
    within that chunk that meets the alignment request, and then
    possibly frees the leading and trailing space.

    The alignment argument must be a power of two. This property is not
    checked by memalign, so misuse may result in random runtime errors.

    8-byte alignment is guaranteed by normal malloc calls, so don't
    bother calling memalign with an argument of 8 or less.

    Overreliance on memalign is a sure way to fragment space.

*/


#if __STD_C
Void_t* 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 befor alignment point */
  mchunkptr remainder;        /* spare room at end to split off */
  long      remainder_size;   /* its size */

  if ((long)bytes < 0) return NULL;

  /* 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;

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

  nb = request2size(bytes);
  m  = (char*)(mALLOc(nb + alignment + MINSIZE));

  /*
  * The attempt to over-allocate (with a size large enough to guarantee the
  * ability to find an aligned region within allocated memory) failed.
  *
  * Try again, this time only allocating exactly the size the user wants. If
  * the allocation now succeeds and just happens to be aligned, we can still
  * fulfill the user's request.
  */
  if (m == NULL) {
    size_t extra, extra2;
    /*
     * Use bytes not nb, since mALLOc internally calls request2size too, and
     * each call increases the size to allocate, to account for the header.
     */
    m  = (char*)(mALLOc(bytes));
    /* Aligned -> return it */
    if ((((unsigned long)(m)) % alignment) == 0)
      return m;
    /*
     * Otherwise, try again, requesting enough extra space to be able to
     * acquire alignment.
     */
    fREe(m);
    /* Add in extra bytes to match misalignment of unexpanded allocation */
    extra = alignment - (((unsigned long)(m)) % alignment);
    m  = (char*)(mALLOc(bytes + extra));
    /*
     * m might not be the same as before. Validate that the previous value of
     * extra still works for the current value of m.
     * If (!m), extra2=alignment so 
     */
    if (m) {
      extra2 = alignment - (((unsigned long)(m)) % alignment);
      if (extra2 > extra) {
        fREe(m);
        m = NULL;
      }
    }
    /* Fall through to original NULL check and chunk splitting logic */
  }

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

  p = mem2chunk(m);

  if ((((unsigned long)(m)) % alignment) == 0) /* aligned */
  {
#if HAVE_MMAP
    if(chunk_is_mmapped(p))
      return chunk2mem(p); /* nothing more to do */
#endif
  }
  else /* 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(((unsigned long)(m + alignment - 1)) & -((signed) alignment));
    if ((long)(brk - (char*)(p)) < MINSIZE) brk = brk + alignment;

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

#if HAVE_MMAP
    if(chunk_is_mmapped(p))
    {
      newp->prev_size = p->prev_size + leadsize;
      set_head(newp, newsize|IS_MMAPPED);
      return chunk2mem(newp);
    }
#endif

    /* 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 && (((unsigned long)(chunk2mem(p))) % alignment) == 0);
  }

  /* Also give back spare room at the end */

  remainder_size = chunksize(p) - nb;

  if (remainder_size >= (long)MINSIZE)
  {
    remainder = chunk_at_offset(p, nb);
    set_head(remainder, remainder_size | PREV_INUSE);