Memory dump formatted like xxd from gdb

an adapted version of the solution of User FatalError

  • works with python 3
  • added a hex-col-header
  • length parameter optional
  • renamed to hd

examples

hd 0xbfffe4f1

hd 0xbfffe4f1 500

import gdb
from curses.ascii import isgraph

def groups_of(iterable, size, first=0):
    first = first if first != 0 else size
    chunk, iterable = iterable[:first], iterable[first:]
    while chunk:
        yield chunk
        chunk, iterable = iterable[:size], iterable[size:]

class HexDump(gdb.Command):
    def __init__(self):
        super (HexDump, self).__init__ ('hd', gdb.COMMAND_DATA)

    def invoke(self, arg, from_tty):
        argv = gdb.string_to_argv(arg)

        addr = gdb.parse_and_eval(argv[0]).cast(
            gdb.lookup_type('void').pointer())
        if len(argv) == 2:
             try:
                 bytes = int(gdb.parse_and_eval(argv[1]))
             except ValueError:
                 raise gdb.GdbError('Byte count numst be an integer value.')
        else:
             bytes = 500

        inferior = gdb.selected_inferior()

        align = gdb.parameter('hex-dump-align')
        width = gdb.parameter('hex-dump-width')
        if width == 0:
            width = 16

        mem = inferior.read_memory(addr, bytes)
        pr_addr = int(str(addr), 16)
        pr_offset = width

        if align:
            pr_offset = width - (pr_addr % width)
            pr_addr -= pr_addr % width
        start=(pr_addr) & 0xff;


        print ('            ' , end="")
        print ('  '.join(['%01X' % (i&0x0f,) for i in range(start,start+width)]) , end="")
        print ('  ' , end="")       
        print (' '.join(['%01X' % (i&0x0f,) for i in range(start,start+width)]) )

        for group in groups_of(mem, width, pr_offset):
            print ('0x%x: ' % (pr_addr,) + '   '*(width - pr_offset), end="")
            print (' '.join(['%02X' % (ord(g),) for g in group]) + \
                '   ' * (width - len(group) if pr_offset == width else 0) + ' ', end="")    
            print (' '*(width - pr_offset) +  ' '.join(
                [chr( int.from_bytes(g, byteorder='big')) if isgraph( int.from_bytes(g, byteorder='big')   ) or g == ' ' else '.' for g in group]))
            pr_addr += width
            pr_offset = width

class HexDumpAlign(gdb.Parameter):
    def __init__(self):
        super (HexDumpAlign, self).__init__('hex-dump-align',
                                            gdb.COMMAND_DATA,
                                            gdb.PARAM_BOOLEAN)

    set_doc = 'Determines if hex-dump always starts at an "aligned" address (see hex-dump-width'
    show_doc = 'Hex dump alignment is currently'

class HexDumpWidth(gdb.Parameter):
    def __init__(self):
        super (HexDumpWidth, self).__init__('hex-dump-width',
                                            gdb.COMMAND_DATA,
                                            gdb.PARAM_INTEGER)

    set_doc = 'Set the number of bytes per line of hex-dump'

    show_doc = 'The number of bytes per line in hex-dump is'

HexDump()
HexDumpAlign()
HexDumpWidth()

My own contribution, from Employed Russian solution and Roger Lipscombe comments:

  • use xxd,
  • preserve the address (xxd -o)
  • size argument is optional
  • small documentation included

The script (tested with gdb 7.8.1):

define xxd
  if $argc < 2
    set $size = sizeof(*$arg0)
  else
    set $size = $arg1
  end
  dump binary memory dump.bin $arg0 ((void *)$arg0)+$size
  eval "shell xxd -o %d dump.bin; rm dump.bin", ((void *)$arg0)
end
document xxd
  Dump memory with xxd command (keep the address as offset)

  xxd addr [size]
    addr -- expression resolvable as an address
    size -- size (in byte) of memory to dump
            sizeof(*addr) is used by default
end

Examples:

(gdb) p &m_data
$1 = (data_t *) 0x200130dc <m_data>

(gdb) p sizeof(m_data)
$2 = 32

(gdb) xxd &m_data 32
200130dc: 0300 0000 e87c 0400 0000 0000 0100 0000  .....|..........
200130ec: 0c01 0000 b831 0020 0100 0000 0100 0000  .....1. ........

(gdb) xxd &m_data
200130dc: 0300 0000 e87c 0400 0000 0000 0100 0000  .....|..........
200130ec: 0c01 0000 b831 0020 0100 0000 0100 0000  .....1. ........

(gdb) help xxd
  Dump memory with xxd command (keep the address as offset)

  xxd addr [size]
    addr -- expression resolvable as an address
    size -- size (in byte) of memory to dump
            sizeof(*addr) is used by default

(gdb) define xxd
>dump binary memory dump.bin $arg0 $arg0+$arg1
>shell xxd dump.bin
>end
(gdb) xxd &j 10 
0000000: 0000 0000 0000 0000 0000 0000 4d8c a7f7  ............M...
0000010: ff7f 0000 0000 0000 0000 0000 c8d7 ffff  ................
0000020: ff7f 0000 0000 0000

Seems easy enough ;-)

You could likely write a Python script (modern GDB versions have embedded Python interpreter) to do the same, and get rid of the need to "shell out".


So, I ended up playing around with the python interface and came up with this:

import gdb
from curses.ascii import isgraph

def groups_of(iterable, size, first=0):
    first = first if first != 0 else size
    chunk, iterable = iterable[:first], iterable[first:]
    while chunk:
        yield chunk
        chunk, iterable = iterable[:size], iterable[size:]

class HexDump(gdb.Command):
    def __init__(self):
        super (HexDump, self).__init__ ('hex-dump', gdb.COMMAND_DATA)

    def invoke(self, arg, from_tty):
        argv = gdb.string_to_argv(arg)
        if len(argv) != 2:
            raise gdb.GdbError('hex-dump takes exactly 2 arguments.')
        addr = gdb.parse_and_eval(argv[0]).cast(
            gdb.lookup_type('void').pointer())
        try:
            bytes = int(gdb.parse_and_eval(argv[1]))
        except ValueError:
            raise gdb.GdbError('Byte count numst be an integer value.')

        inferior = gdb.selected_inferior()

        align = gdb.parameter('hex-dump-align')
        width = gdb.parameter('hex-dump-width')
        if width == 0:
            width = 16

        mem = inferior.read_memory(addr, bytes)
        pr_addr = int(str(addr), 16)
        pr_offset = width

        if align:
            pr_offset = width - (pr_addr % width)
            pr_addr -= pr_addr % width

        for group in groups_of(mem, width, pr_offset):
            print '0x%x: ' % (pr_addr,) + '   '*(width - pr_offset),
            print ' '.join(['%02X' % (ord(g),) for g in group]) + \
                '   ' * (width - len(group) if pr_offset == width else 0) + ' ',
            print ' '*(width - pr_offset) +  ''.join(
                [g if isgraph(g) or g == ' ' else '.' for g in group])
            pr_addr += width
            pr_offset = width

class HexDumpAlign(gdb.Parameter):
    def __init__(self):
        super (HexDumpAlign, self).__init__('hex-dump-align',
                                            gdb.COMMAND_DATA,
                                            gdb.PARAM_BOOLEAN)

    set_doc = 'Determines if hex-dump always starts at an "aligned" address (see hex-dump-width'
    show_doc = 'Hex dump alignment is currently'

class HexDumpWidth(gdb.Parameter):
    def __init__(self):
        super (HexDumpWidth, self).__init__('hex-dump-width',
                                            gdb.COMMAND_DATA,
                                            gdb.PARAM_INTEGER)

    set_doc = 'Set the number of bytes per line of hex-dump'

    show_doc = 'The number of bytes per line in hex-dump is'

HexDump()
HexDumpAlign()
HexDumpWidth()

I realize it might not be the most beautiful and elegant solution, but it gets the job done and works as a first draft. It could be included in ~/.gdbinit like:

python
sys.path.insert(0, '/path/to/module/dir')
import hexdump
end

Then could be used with the program above like so:

(gdb) hex-dump buf 100
0x7fffffffdf00:  01 02 03 04 53 74 72 69 6E 67 20 44 61 74 61 AA  ....String Data.
0x7fffffffdf10:  BB CC 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf20:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf30:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf40:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf50:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf60:  00 00 00 00                                      ....

And a few other touches for good measure:

(gdb) set hex-dump-align on
Determines if hex-dump always starts at an "aligned" address (see hex-dump-width
(gdb) hex-dump &buf[5] 95
0x7fffffffdf00:                 74 72 69 6E 67 20 44 61 74 61 AA       tring Data.
0x7fffffffdf10:  BB CC 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf20:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf30:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf40:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf50:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
0x7fffffffdf60:  00 00 00 00                                      ....

(gdb) set hex-dump-width 8
Set the number of bytes per line of hex-dump
(gdb) hex-dump &buf[5] 95
0x7fffffffdf00:                 74 72 69       tri
0x7fffffffdf08:  6E 67 20 44 61 74 61 AA  ng Data.
0x7fffffffdf10:  BB CC 00 00 00 00 00 00  ........
0x7fffffffdf18:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf20:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf28:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf30:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf38:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf40:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf48:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf50:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf58:  00 00 00 00 00 00 00 00  ........
0x7fffffffdf60:  00 00 00 00              ....

No promises that there aren't bugs :). I might stick it up in github or something if people are interested.

I've only tested it with GDB 7.4.