struct malloc_chunk {

  INTERNAL_SIZE_T      mchunk_prev_size;  /* Size of previous chunk (if free).  */
  INTERNAL_SIZE_T      mchunk_size;       /* Size in bytes, including overhead. */

  struct malloc_chunk* fd;         /* double links -- used only if free. */
  struct malloc_chunk* bk;

  /* Only used for large blocks: pointer to next larger size.  */
  struct malloc_chunk* fd_nextsize; /* double links -- used only if free. */
  struct malloc_chunk* bk_nextsize;
};

/* size field is or'ed with PREV_INUSE when previous adjacent chunk in use */
#define PREV_INUSE 0x1

/* extract inuse bit of previous chunk */
#define prev_inuse(p)       ((p)->mchunk_size & PREV_INUSE)


/* size field is or'ed with IS_MMAPPED if the chunk was obtained with mmap() */
#define IS_MMAPPED 0x2

/* check for mmap()'ed chunk */
#define chunk_is_mmapped(p) ((p)->mchunk_size & IS_MMAPPED)


/* size field is or'ed with NON_MAIN_ARENA if the chunk was obtained
   from a non-main arena.  This is only set immediately before handing
   the chunk to the user, if necessary.  */
#define NON_MAIN_ARENA 0x4

/*
   Bits to mask off when extracting size

   Note: IS_MMAPPED is intentionally not masked off from size field in
   macros for which mmapped chunks should never be seen. This should
   cause helpful core dumps to occur if it is tried by accident by
   people extending or adapting this malloc.
 */
#define SIZE_BITS (PREV_INUSE | IS_MMAPPED | NON_MAIN_ARENA)

/*
   malloc_chunk details:

    (The following includes lightly edited explanations by Colin Plumb.)

    Chunks of memory are maintained using a `boundary tag' method as
    described in e.g., Knuth or Standish.  (See the paper by Paul
    Wilson ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a
    survey of such techniques.)  Sizes of free chunks are stored both
    in the front of each chunk and at the end.  This makes
    consolidating fragmented chunks into bigger chunks very fast.  The
    size fields also hold bits representing whether chunks are free or
    in use.

    An allocated chunk looks like this:


    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of previous chunk, if unallocated (P clear)  |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of chunk, in bytes                     |A|M|P|
      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             User data starts here...                          .
	    .                                                               .
	    .             (malloc_usable_size() bytes)                      .
	    .                                                               |
nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             (size of chunk, but used for application data)    |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of next chunk, in bytes                |A|0|1|
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    Where "chunk" is the front of the chunk for the purpose of most of
    the malloc code, but "mem" is the pointer that is returned to the
    user.  "Nextchunk" is the beginning of the next contiguous chunk.

    Chunks always begin on even word boundaries, so the mem portion
    (which is returned to the user) is also on an even word boundary, and
    thus at least double-word aligned.

    Free chunks are stored in circular doubly-linked lists, and look like this:

    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of previous chunk, if unallocated (P clear)  |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    `head:' |             Size of chunk, in bytes                     |A|0|P|
      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Forward pointer to next chunk in list             |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Back pointer to previous chunk in list            |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Unused space (may be 0 bytes long)                .
	    .                                                               .
	    .                                                               |
nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    `foot:' |             Size of chunk, in bytes                           |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of next chunk, in bytes                |A|0|0|
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    The P (PREV_INUSE) bit, stored in the unused low-order bit of the
    chunk size (which is always a multiple of two words), is an in-use
    bit for the *previous* chunk.  If that bit is *clear*, then the
    word before the current chunk size contains the previous chunk
    size, and can be used to find the front of the previous chunk.
    The very first chunk allocated always has this bit set,
    preventing access to non-existent (or non-owned) memory. If
    prev_inuse is set for any given chunk, then you CANNOT determine
    the size of the previous chunk, and might even get a memory
    addressing fault when trying to do so.

    The A (NON_MAIN_ARENA) bit is cleared for chunks on the initial,
    main arena, described by the main_arena variable.  When additional
    threads are spawned, each thread receives its own arena (up to a
    configurable limit, after which arenas are reused for multiple
    threads), and the chunks in these arenas have the A bit set.  To
    find the arena for a chunk on such a non-main arena, heap_for_ptr
    performs a bit mask operation and indirection through the ar_ptr
    member of the per-heap header heap_info (see arena.c).

    Note that the `foot' of the current chunk is actually represented
    as the prev_size of the NEXT chunk. This makes it easier to
    deal with alignments etc but can be very confusing when trying
    to extend or adapt this code.

    The three exceptions to all this are:

     1. The special chunk `top' doesn't bother using the
	trailing size field since there is no next contiguous chunk
	that would have to index off it. After initialization, `top'
	is forced to always exist.  If it would become less than
	MINSIZE bytes long, it is replenished.

     2. Chunks allocated via mmap, which have the second-lowest-order
	bit M (IS_MMAPPED) set in their size fields.  Because they are
	allocated one-by-one, each must contain its own trailing size
	field.  If the M bit is set, the other bits are ignored
	(because mmapped chunks are neither in an arena, nor adjacent
	to a freed chunk).  The M bit is also used for chunks which
	originally came from a dumped heap via malloc_set_state in
	hooks.c.

     3. Chunks in fastbins are treated as allocated chunks from the
	point of view of the chunk allocator.  They are consolidated
	with their neighbors only in bulk, in malloc_consolidate.
*/

/*
  ---------- Size and alignment checks and conversions ----------
*/

/* Conversion from malloc headers to user pointers, and back.  When
   using memory tagging the user data and the malloc data structure
   headers have distinct tags.  Converting fully from one to the other
   involves extracting the tag at the other address and creating a
   suitable pointer using it.  That can be quite expensive.  There are
   cases when the pointers are not dereferenced (for example only used
   for alignment check) so the tags are not relevant, and there are
   cases when user data is not tagged distinctly from malloc headers
   (user data is untagged because tagging is done late in malloc and
   early in free).  User memory tagging across internal interfaces:

      sysmalloc: Returns untagged memory.
      _int_malloc: Returns untagged memory.
      _int_free: Takes untagged memory.
      _int_memalign: Returns untagged memory.
      _int_memalign: Returns untagged memory.
      _mid_memalign: Returns tagged memory.
      _int_realloc: Takes and returns tagged memory.
*/

typedef struct malloc_chunk *mfastbinptr;
typedef struct malloc_chunk* mchunkptr;

#define MAX_FAST_SIZE     (80 * SIZE_SZ / 4)

#define NFASTBINS  (fastbin_index (request2size (MAX_FAST_SIZE)) + 1)

#define NBINS             128

struct malloc_state
{
  /* Serialize access.  */
  __libc_lock_define (, mutex);

  /* Flags (formerly in max_fast).  */
  int flags;

  /* Set if the fastbin chunks contain recently inserted free blocks.  */
  /* Note this is a bool but not all targets support atomics on booleans.  */
  int have_fastchunks;

  /* Fastbins */
  mfastbinptr fastbinsY[NFASTBINS];

  /* Base of the topmost chunk -- not otherwise kept in a bin */
  mchunkptr top;

  /* The remainder from the most recent split of a small request */
  mchunkptr last_remainder;

  /* Normal bins packed as described above */
  mchunkptr bins[NBINS * 2 - 2];

  /* Bitmap of bins */
  unsigned int binmap[BINMAPSIZE];

  /* Linked list */
  struct malloc_state *next;

  /* Linked list for free arenas.  Access to this field is serialized
     by free_list_lock in arena.c.  */
  struct malloc_state *next_free;

  /* Number of threads attached to this arena.  0 if the arena is on
     the free list.  Access to this field is serialized by
     free_list_lock in arena.c.  */
  INTERNAL_SIZE_T attached_threads;

  /* Memory allocated from the system in this arena.  */
  INTERNAL_SIZE_T system_mem;
  INTERNAL_SIZE_T max_system_mem;
};

/*
   Indexing

    Bins for sizes < 512 bytes contain chunks of all the same size, spaced
    8 bytes apart. Larger bins are approximately logarithmically spaced:

    64 bins of size       8
    32 bins of size      64
    16 bins of size     512
     8 bins of size    4096
     4 bins of size   32768
     2 bins of size  262144
     1 bin  of size what's left

    There is actually a little bit of slop in the numbers in bin_index
    for the sake of speed. This makes no difference elsewhere.

    The bins top out around 1MB because we expect to service large
    requests via mmap.

    Bin 0 does not exist.  Bin 1 is the unordered list; if that would be
    a valid chunk size the small bins are bumped up one.
 */

#define NBINS             128
#define NSMALLBINS         64
#define SMALLBIN_WIDTH    MALLOC_ALIGNMENT
#define SMALLBIN_CORRECTION (MALLOC_ALIGNMENT > CHUNK_HDR_SZ)
#define MIN_LARGE_SIZE    ((NSMALLBINS - SMALLBIN_CORRECTION) * SMALLBIN_WIDTH)

#define in_smallbin_range(sz)  \
  ((unsigned long) (sz) < (unsigned long) MIN_LARGE_SIZE)

#define smallbin_index(sz) \
  ((SMALLBIN_WIDTH == 16 ? (((unsigned) (sz)) >> 4) : (((unsigned) (sz)) >> 3))\
   + SMALLBIN_CORRECTION)

#define largebin_index_32(sz)                                                \
  (((((unsigned long) (sz)) >> 6) <= 38) ?  56 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

#define largebin_index_32_big(sz)                                            \
  (((((unsigned long) (sz)) >> 6) <= 45) ?  49 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

// XXX It remains to be seen whether it is good to keep the widths of
// XXX the buckets the same or whether it should be scaled by a factor
// XXX of two as well.
#define largebin_index_64(sz)                                                \
  (((((unsigned long) (sz)) >> 6) <= 48) ?  48 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

#define largebin_index(sz) \
  (SIZE_SZ == 8 ? largebin_index_64 (sz)                                     \
   : MALLOC_ALIGNMENT == 16 ? largebin_index_32_big (sz)                     \
   : largebin_index_32 (sz))

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

typedef struct _heap_info
{
  mstate ar_ptr; /* Arena for this heap. */
  struct _heap_info *prev; /* Previous heap. */
  size_t size;   /* Current size in bytes. */
  size_t mprotect_size; /* Size in bytes that has been mprotected
                           PROT_READ|PROT_WRITE.  */
  size_t pagesize; /* Page size used when allocating the arena.  */
  /* Make sure the following data is properly aligned, particularly
     that sizeof (heap_info) + 2 * SIZE_SZ is a multiple of
     MALLOC_ALIGNMENT. */
  char pad[-3 * SIZE_SZ & MALLOC_ALIGN_MASK];
} heap_info;

void *
__libc_malloc (size_t bytes)
{
  mstate ar_ptr;
  void *victim;

  _Static_assert (PTRDIFF_MAX <= SIZE_MAX / 2,
                  "PTRDIFF_MAX is not more than half of SIZE_MAX");

  void *(*hook) (size_t, const void *)
    = atomic_forced_read (__malloc_hook);
  if (__builtin_expect (hook != NULL, 0))
    return (*hook)(bytes, RETURN_ADDRESS (0));
}

if (__builtin_expect (hook != NULL, 0))
    return (*hook)(bytes, RETURN_ADDRESS (0));

static void *
malloc_hook_ini (size_t sz, const void *caller)
{
  __malloc_hook = NULL;
  ptmalloc_init ();
  return __libc_malloc (sz);
}

#if USE_TCACHE
  /* int_free also calls request2size, be careful to not pad twice.  */
  size_t tbytes;
  if (!checked_request2size (bytes, &tbytes))
    {
      __set_errno (ENOMEM);
      return NULL;
    }
  size_t tc_idx = csize2tidx (tbytes);

  MAYBE_INIT_TCACHE ();

  DIAG_PUSH_NEEDS_COMMENT;
  if (tc_idx < mp_.tcache_bins
      && tcache
      && tcache->counts[tc_idx] > 0)
    {
      victim = tcache_get (tc_idx);
      return TAG_NEW_USABLE (victim);
    }
  DIAG_POP_NEEDS_COMMENT;
#endif

static __thread tcache_perthread_struct *tcache = NULL;

# define TCACHE_MAX_BINS		64
# define MAX_TCACHE_SIZE	tidx2usize (TCACHE_MAX_BINS-1)

typedef struct tcache_perthread_struct
{
  uint16_t counts[TCACHE_MAX_BINS];
  tcache_entry *entries[TCACHE_MAX_BINS];
} tcache_perthread_struct;

typedef struct tcache_entry
{
  struct tcache_entry *next;
  /* This field exists to detect double frees.  */
  struct tcache_perthread_struct *key;
} tcache_entry;

static void
tcache_init(void)
{
  mstate ar_ptr;
  void *victim = 0;
  const size_t bytes = sizeof (tcache_perthread_struct);

  if (tcache_shutting_down)
    return;

  arena_get (ar_ptr, bytes);
  victim = _int_malloc (ar_ptr, bytes);
  if (!victim && ar_ptr != NULL)
    {
      ar_ptr = arena_get_retry (ar_ptr, bytes);
      victim = _int_malloc (ar_ptr, bytes);
    }


  if (ar_ptr != NULL)
    __libc_lock_unlock (ar_ptr->mutex);

  /* In a low memory situation, we may not be able to allocate memory
     - in which case, we just keep trying later.  However, we
     typically do this very early, so either there is sufficient
     memory, or there isn't enough memory to do non-trivial
     allocations anyway.  */
  if (victim)
    {
      tcache = (tcache_perthread_struct *) victim;
      memset (tcache, 0, sizeof (tcache_perthread_struct));
    }
}