[how2heap] fastbin_dup

static void
_int_free (mstate av, mchunkptr p, int have_lock)
{
  INTERNAL_SIZE_T size;        /* its size */
  mfastbinptr *fb;             /* associated fastbin */

  size = chunksize (p);

  /* Little security check which won't hurt performance: the
     allocator never wraps around at the end of the address space.
     Therefore we can exclude some size values which might appear
     here by accident or by "design" from some intruder.  */
  if (__builtin_expect ((uintptr_t) p > (uintptr_t) -size, 0)
      || __builtin_expect (misaligned_chunk (p), 0))
    malloc_printerr ("free(): invalid pointer");
  /* We know that each chunk is at least MINSIZE bytes in size or a
     multiple of MALLOC_ALIGNMENT.  */
  if (__glibc_unlikely (size < MINSIZE || !aligned_OK (size)))
    malloc_printerr ("free(): invalid size");

  check_inuse_chunk(av, p);

#if USE_TCACHE
  {
    size_t tc_idx = csize2tidx (size);
    if (tcache != NULL && tc_idx < mp_.tcache_bins)
      {
	/* Check to see if it's already in the tcache.  */
	tcache_entry *e = (tcache_entry *) chunk2mem (p);

	/* This test succeeds on double free.  However, we don't 100%
	   trust it (it also matches random payload data at a 1 in
	   2^<size_t> chance), so verify it's not an unlikely
	   coincidence before aborting.  */
	if (__glibc_unlikely (e->key == tcache_key))
	  {
	    tcache_entry *tmp;
	    size_t cnt = 0;
	    LIBC_PROBE (memory_tcache_double_free, 2, e, tc_idx);
	    for (tmp = tcache->entries[tc_idx];
		 tmp;
		 tmp = REVEAL_PTR (tmp->next), ++cnt)
	      {
		if (cnt >= mp_.tcache_count)
		  malloc_printerr ("free(): too many chunks detected in tcache");
		if (__glibc_unlikely (!aligned_OK (tmp)))
		  malloc_printerr ("free(): unaligned chunk detected in tcache 2");
		if (tmp == e)
		  malloc_printerr ("free(): double free detected in tcache 2");
		/* If we get here, it was a coincidence.  We've wasted a
		   few cycles, but don't abort.  */
	      }
	  }

	if (tcache->counts[tc_idx] < mp_.tcache_count)
	  {
	    tcache_put (p, tc_idx);
	    return;
	  }
      }
  }
#endif

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

  if ((unsigned long)(size) <= (unsigned long)(get_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
      ) {

    if (__builtin_expect (chunksize_nomask (chunk_at_offset (p, size))
			  <= CHUNK_HDR_SZ, 0)
	|| __builtin_expect (chunksize (chunk_at_offset (p, size))
			     >= av->system_mem, 0))
      {
	bool fail = true;
	/* We might not have a lock at this point and concurrent modifications
	   of system_mem might result in a false positive.  Redo the test after
	   getting the lock.  */
	if (!have_lock)
	  {
	    __libc_lock_lock (av->mutex);
	    fail = (chunksize_nomask (chunk_at_offset (p, size)) <= CHUNK_HDR_SZ
		    || chunksize (chunk_at_offset (p, size)) >= av->system_mem);
	    __libc_lock_unlock (av->mutex);
	  }

	if (fail)
	  malloc_printerr ("free(): invalid next size (fast)");
      }

    free_perturb (chunk2mem(p), size - CHUNK_HDR_SZ);

    atomic_store_relaxed (&av->have_fastchunks, true);
    unsigned int idx = fastbin_index(size);
    fb = &fastbin (av, idx);

    /* Atomically link P to its fastbin: P->FD = *FB; *FB = P;  */
    mchunkptr old = *fb, old2;

    if (SINGLE_THREAD_P)
      {
	/* Check that the top of the bin is not the record we are going to
	   add (i.e., double free).  */
	if (__builtin_expect (old == p, 0))
	  malloc_printerr ("double free or corruption (fasttop)");
	p->fd = PROTECT_PTR (&p->fd, old);
	*fb = p;
      }
    else
      do
	{
	  /* Check that the top of the bin is not the record we are going to
	     add (i.e., double free).  */
	  if (__builtin_expect (old == p, 0))
	    malloc_printerr ("double free or corruption (fasttop)");
	  old2 = old;
	  p->fd = PROTECT_PTR (&p->fd, old);
	}
      while ((old = catomic_compare_and_exchange_val_rel (fb, p, old2))
	     != old2);

    /* Check that size of fastbin chunk at the top is the same as
       size of the chunk that we are adding.  We can dereference OLD
       only if we have the lock, otherwise it might have already been
       allocated again.  */
    if (have_lock && old != NULL
	&& __builtin_expect (fastbin_index (chunksize (old)) != idx, 0))
      malloc_printerr ("invalid fastbin entry (free)");
  }

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

  else if (!chunk_is_mmapped(p)) {

    /* If we're single-threaded, don't lock the arena.  */
    if (SINGLE_THREAD_P)
      have_lock = true;

    if (!have_lock)
      __libc_lock_lock (av->mutex);

    _int_free_merge_chunk (av, p, size);

    if (!have_lock)
      __libc_lock_unlock (av->mutex);
  }
  /*
    If the chunk was allocated via mmap, release via munmap().
  */

  else {
    munmap_chunk (p);
  }
}