malloc_hook

• 打堆的一个关键的方法就是劫持堆相关函数中的hook函数。即在堆中的三大hook函数，malloc_hook、realloc_hook、free_hook

• 之前看hook利用的时候，感觉不是特别理解，所以就没有看了，今天感觉有点开窍了，就来学习一下，感觉这个学期都没怎么学pwn，学的pwn没有上学期多。参考博客：malloc_hook以及free_hook劫持原理 | S3cana’s Blog、malloc_hook&&free_hook hijack原理

hook介绍

• hook的就是劫持函数指针，控制程序的执行，让函数执行我们所指定的函数。

  • hook翻译过来是钩子。假设a函数中有这样一个执行过程：判断b函数指针是否为空，如果不为空就先b函数指针所指向的函数。这样当我们使用b钩子的时候，我们在执行a函数，执行流就会被b钩子给钩过来，这样就达到了执行b函数指针所指向的函数地址。

• 为了方便调试程序，在glibc中有四个比较重要的函数指针，分别是malloc_hook、free_hook、realloc_hook、exit_hook。

• 我们可以通过一些堆漏洞或者其他漏洞就可以将原本指向NULL的这些函数指针，修改为one_gadget，这样我们在满足一定的条件后就可以getshell，这样就是pwn中的劫持hook函数最常见的用法。

• 之后由于hook的存在着比较严重的漏洞利用，在glibc2.34版本及以上就被删除了，所以glibc2.34版本及以上的pwn就不能往劫持这些hook函数去想了。

前置知识

• 这里可以先去了解一下函数指针。不了解其实也没关系，也就把他当做指针就行。
• 这里我是在已经有读一些glibc源码的基础上才学的malloc_hook技术，前置知识可能不太基础。

malloc函数流程

• 通过阅读malloc函数的源码，大致总结出了malloc函数的执行流程，流程图如下

malloc函数相关源码

• 还是以glibc2.23的malloc相关源码

__libc_malloc

/*------------------------ Public wrappers. --------------------------------*/

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

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

  arena_get (ar_ptr, bytes);

  victim = _int_malloc (ar_ptr, bytes);
  /* Retry with another arena only if we were able to find a usable arena
     before.  */
  if (!victim && ar_ptr != NULL)
    {
      LIBC_PROBE (memory_malloc_retry, 1, bytes);
      ar_ptr = arena_get_retry (ar_ptr, bytes);
      victim = _int_malloc (ar_ptr, bytes);
    }

  if (ar_ptr != NULL)
    (void) mutex_unlock (&ar_ptr->mutex);

  assert (!victim || chunk_is_mmapped (mem2chunk (victim)) ||
          ar_ptr == arena_for_chunk (mem2chunk (victim)));
  return victim;
}
libc_hidden_def (__libc_malloc)

_int_malloc

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

static void *
_int_malloc (mstate av, size_t bytes)
{
  INTERNAL_SIZE_T nb;               /* normalized request size */
  unsigned int idx;                 /* associated bin index */
  mbinptr bin;                      /* associated bin */

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

  mchunkptr remainder;              /* remainder from a split */
  unsigned long 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 */

  const char *errstr = NULL;

  /*
     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);

  /* There are no usable arenas.  Fall back to sysmalloc to get a chunk from
     mmap.  */
  if (__glibc_unlikely (av == NULL))
    {
      void *p = sysmalloc (nb, av);
      if (p != NULL)
	alloc_perturb (p, bytes);
      return p;
    }

  /*
     If the size qualifies as a fastbin, first check corresponding bin.
     This code is safe to execute even if av is not yet initialized, so we
     can try it without checking, which saves some time on this fast path.
   */

  if ((unsigned long) (nb) <= (unsigned long) (get_max_fast ()))
    {
      idx = fastbin_index (nb);
      mfastbinptr *fb = &fastbin (av, idx);
      mchunkptr pp = *fb;
      do
        {
          victim = pp;
          if (victim == NULL)
            break;
        }
      while ((pp = catomic_compare_and_exchange_val_acq (fb, victim->fd, victim))
             != victim);
      if (victim != 0)
        {
          if (__builtin_expect (fastbin_index (chunksize (victim)) != idx, 0))
            {
              errstr = "malloc(): memory corruption (fast)";
            errout:
              malloc_printerr (check_action, errstr, chunk2mem (victim), av);
              return NULL;
            }
          check_remalloced_chunk (av, victim, nb);
          void *p = chunk2mem (victim);
          alloc_perturb (p, bytes);
          return p;
        }
    }

  /*
     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)
        {
          if (victim == 0) /* initialization check */
            malloc_consolidate (av);
          else
            {
              bck = victim->bk;
	if (__glibc_unlikely (bck->fd != victim))
                {
                  errstr = "malloc(): smallbin double linked list corrupted";
                  goto errout;
                }
              set_inuse_bit_at_offset (victim, nb);
              bin->bk = bck;
              bck->fd = bin;

              if (av != &main_arena)
                victim->size |= NON_MAIN_ARENA;
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }
        }
    }

  /*
     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.

     The outer loop here is needed because we might not realize until
     near the end of malloc that we should have consolidated, so must
     do so and retry. This happens at most once, and only when we would
     otherwise need to expand memory to service a "small" request.
   */

  for (;; )
    {
      int iters = 0;
      while ((victim = unsorted_chunks (av)->bk) != unsorted_chunks (av))
        {
          bck = victim->bk;
          if (__builtin_expect (victim->size <= 2 * SIZE_SZ, 0)
              || __builtin_expect (victim->size > av->system_mem, 0))
            malloc_printerr (check_action, "malloc(): memory corruption",
                             chunk2mem (victim), av);
          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 &&
              (unsigned long) (size) > (unsigned long) (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);
              if (!in_smallbin_range (remainder_size))
                {
                  remainder->fd_nextsize = NULL;
                  remainder->bk_nextsize = NULL;
                }

              set_head (victim, nb | PREV_INUSE |
                        (av != &main_arena ? NON_MAIN_ARENA : 0));
              set_head (remainder, remainder_size | PREV_INUSE);
              set_foot (remainder, remainder_size);

              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }

          /* 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);
              if (av != &main_arena)
                victim->size |= NON_MAIN_ARENA;
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }

          /* 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;

              /* maintain large bins in sorted order */
              if (fwd != bck)
                {
                  /* Or with inuse bit to speed comparisons */
                  size |= PREV_INUSE;
                  /* if smaller than smallest, bypass loop below */
                  assert ((bck->bk->size & NON_MAIN_ARENA) == 0);
                  if ((unsigned long) (size) < (unsigned long) (bck->bk->size))
                    {
                      fwd = bck;
                      bck = bck->bk;

                      victim->fd_nextsize = fwd->fd;
                      victim->bk_nextsize = fwd->fd->bk_nextsize;
                      fwd->fd->bk_nextsize = victim->bk_nextsize->fd_nextsize = victim;
                    }
                  else
                    {
                      assert ((fwd->size & NON_MAIN_ARENA) == 0);
                      while ((unsigned long) size < fwd->size)
                        {
                          fwd = fwd->fd_nextsize;
                          assert ((fwd->size & NON_MAIN_ARENA) == 0);
                        }

                      if ((unsigned long) size == (unsigned long) fwd->size)
                        /* Always insert in the second position.  */
                        fwd = fwd->fd;
                      else
                        {
                          victim->fd_nextsize = fwd;
                          victim->bk_nextsize = fwd->bk_nextsize;
                          fwd->bk_nextsize = victim;
                          victim->bk_nextsize->fd_nextsize = victim;
                        }
                      bck = fwd->bk;
                    }
                }
              else
                victim->fd_nextsize = victim->bk_nextsize = victim;
            }

          mark_bin (av, victim_index);
          victim->bk = bck;
          victim->fd = fwd;
          fwd->bk = victim;
          bck->fd = victim;

#define MAX_ITERS       10000
          if (++iters >= MAX_ITERS)
            break;
        }

      /*
         If a large request, scan through the chunks of current bin in
         sorted order to find smallest that fits.  Use the skip list for this.
       */

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

          /* skip scan if empty or largest chunk is too small */
          if ((victim = first (bin)) != bin &&
              (unsigned long) (victim->size) >= (unsigned long) (nb))
            {
              victim = victim->bk_nextsize;
              while (((unsigned long) (size = chunksize (victim)) <
                      (unsigned long) (nb)))
                victim = victim->bk_nextsize;

              /* Avoid removing the first entry for a size so that the skip
                 list does not have to be rerouted.  */
              if (victim != last (bin) && victim->size == victim->fd->size)
                victim = victim->fd;

              remainder_size = size - nb;
              unlink (av, victim, bck, fwd);

              /* Exhaust */
              if (remainder_size < MINSIZE)
                {
                  set_inuse_bit_at_offset (victim, size);
                  if (av != &main_arena)
                    victim->size |= NON_MAIN_ARENA;
                }
              /* Split */
              else
                {
                  remainder = chunk_at_offset (victim, nb);
                  /* We cannot assume the unsorted list is empty and therefore
                     have to perform a complete insert here.  */
                  bck = unsorted_chunks (av);
                  fwd = bck->fd;
	  if (__glibc_unlikely (fwd->bk != bck))
                    {
                      errstr = "malloc(): corrupted unsorted chunks";
                      goto errout;
                    }
                  remainder->bk = bck;
                  remainder->fd = fwd;
                  bck->fd = remainder;
                  fwd->bk = remainder;
                  if (!in_smallbin_range (remainder_size))
                    {
                      remainder->fd_nextsize = NULL;
                      remainder->bk_nextsize = NULL;
                    }
                  set_head (victim, nb | PREV_INUSE |
                            (av != &main_arena ? NON_MAIN_ARENA : 0));
                  set_head (remainder, remainder_size | PREV_INUSE);
                  set_foot (remainder, remainder_size);
                }
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }
        }

      /*
         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.
         The particular case of skipping all bins during warm-up phases
         when no chunks have been returned yet is faster than it might look.
       */

      ++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 ((unsigned long) (size) >= (unsigned long) (nb));

              remainder_size = size - nb;

              /* unlink */
              unlink (av, victim, bck, fwd);

              /* Exhaust */
              if (remainder_size < MINSIZE)
                {
                  set_inuse_bit_at_offset (victim, size);
                  if (av != &main_arena)
                    victim->size |= NON_MAIN_ARENA;
                }

              /* Split */
              else
                {
                  remainder = chunk_at_offset (victim, nb);

                  /* We cannot assume the unsorted list is empty and therefore
                     have to perform a complete insert here.  */
                  bck = unsorted_chunks (av);
                  fwd = bck->fd;
	  if (__glibc_unlikely (fwd->bk != bck))
                    {
                      errstr = "malloc(): corrupted unsorted chunks 2";
                      goto errout;
                    }
                  remainder->bk = bck;
                  remainder->fd = fwd;
                  bck->fd = remainder;
                  fwd->bk = remainder;

                  /* advertise as last remainder */
                  if (in_smallbin_range (nb))
                    av->last_remainder = remainder;
                  if (!in_smallbin_range (remainder_size))
                    {
                      remainder->fd_nextsize = NULL;
                      remainder->bk_nextsize = NULL;
                    }
                  set_head (victim, nb | PREV_INUSE |
                            (av != &main_arena ? NON_MAIN_ARENA : 0));
                  set_head (remainder, remainder_size | PREV_INUSE);
                  set_foot (remainder, remainder_size);
                }
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }
        }

    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
         exhausted 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 ((unsigned long) (size) >= (unsigned long) (nb + MINSIZE))
        {
          remainder_size = size - nb;
          remainder = chunk_at_offset (victim, nb);
          av->top = remainder;
          set_head (victim, nb | PREV_INUSE |
                    (av != &main_arena ? NON_MAIN_ARENA : 0));
          set_head (remainder, remainder_size | PREV_INUSE);

          check_malloced_chunk (av, victim, nb);
          void *p = chunk2mem (victim);
          alloc_perturb (p, bytes);
          return p;
        }

      /* When we are using atomic ops to free fast chunks we can get
         here for all block sizes.  */
      else if (have_fastchunks (av))
        {
          malloc_consolidate (av);
          /* restore original bin index */
          if (in_smallbin_range (nb))
            idx = smallbin_index (nb);
          else
            idx = largebin_index (nb);
        }

      /*
         Otherwise, relay to handle system-dependent cases
       */
      else
        {
          void *p = sysmalloc (nb, av);
          if (p != NULL)
            alloc_perturb (p, bytes);
          return p;
        }
    }
}

malloc相关宏定义

/*申请的堆块对齐的宏定义*/
#ifndef MALLOC_ALIGNMENT
# if !SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_16)
/* This is the correct definition when there is no past ABI to constrain it.

   Among configurations with a past ABI constraint, it differs from
   2*SIZE_SZ only on powerpc32.  For the time being, changing this is
   causing more compatibility problems due to malloc_get_state and
   malloc_set_state than will returning blocks not adequately aligned for
   long double objects under -mlong-double-128.  */

#  define MALLOC_ALIGNMENT       (2 *SIZE_SZ < __alignof__ (long double)      \
                                  ? __alignof__ (long double) : 2 *SIZE_SZ)
# else
#  define MALLOC_ALIGNMENT       (2 *SIZE_SZ)
# endif
#endif

/* The corresponding bit mask value */
#define MALLOC_ALIGN_MASK      (MALLOC_ALIGNMENT - 1)

malloc_hook的位置

实验

• 在how2heap这个仓库中并没有关于malloc_hook的，也有可能是结合在其他堆利用中，所以我就找了其他师傅的博客。

利用方式

• 这边malloc_hook的利用方式其实是需要和其他漏洞利用去打组合计。malloc_hook只是在最后一步getshell中才比较起作用。
• malloc_hook就是让我们直接修改这个malloc_hook函数指针的值，使得我们在执行malloc()函数的时候就可以被钩到我们指定的地址中，最后就会getshell
• 这边就先介绍一下一些组合计。

利用方式1

利用方式2

malloc_hook_level_1

malloc_hook_level_2

malloc_hook_level_3

malloc_hook_level_4

malloc_hook_level_5