examples/dwarf_decode_address.py

#-------------------------------------------------------------------------------
# elftools example: dwarf_decode_address.py
#
# Decode an address in an ELF file to find out which function it belongs to
# and from which filename/line it comes in the original source file.
#
# Eli Bendersky (eliben@gmail.com)
# This code is in the public domain
#-------------------------------------------------------------------------------
from __future__ import print_function
import sys

# If pyelftools is not installed, the example can also run from the root or
# examples/ dir of the source distribution.
sys.path[0:0] = ['.', '..']

from elftools.common.py3compat import maxint, bytes2str
from elftools.elf.elffile import ELFFile


def process_file(filename, address):
    print('Processing file:', filename)
    with open(filename, 'rb') as f:
        elffile = ELFFile(f)

        if not elffile.has_dwarf_info():
            print('  file has no DWARF info')
            return

        # get_dwarf_info returns a DWARFInfo context object, which is the
        # starting point for all DWARF-based processing in pyelftools.
        dwarfinfo = elffile.get_dwarf_info()

        funcname = decode_funcname(dwarfinfo, address)
        file, line = decode_file_line(dwarfinfo, address)

        print('Function:', bytes2str(funcname))
        print('File:', bytes2str(file))
        print('Line:', line)


def decode_funcname(dwarfinfo, address):
    # Go over all DIEs in the DWARF information, looking for a subprogram
    # entry with an address range that includes the given address. Note that
    # this simplifies things by disregarding subprograms that may have
    # split address ranges.
    for CU in dwarfinfo.iter_CUs():
        for DIE in CU.iter_DIEs():
            try:
                if DIE.tag == 'DW_TAG_subprogram':
                    lowpc = DIE.attributes['DW_AT_low_pc'].value
                    highpc = DIE.attributes['DW_AT_high_pc'].value
                    if lowpc <= address <= highpc:
                        return DIE.attributes['DW_AT_name'].value
            except KeyError:
                continue
    return None


def decode_file_line(dwarfinfo, address):
    # Go over all the line programs in the DWARF information, looking for
    # one that describes the given address.
    for CU in dwarfinfo.iter_CUs():
        # First, look at line programs to find the file/line for the address
        lineprog = dwarfinfo.line_program_for_CU(CU)
        prevstate = None
        for entry in lineprog.get_entries():
            # We're interested in those entries where a new state is assigned
            if entry.state is None or entry.state.end_sequence:
                continue
            # Looking for a range of addresses in two consecutive states that
            # contain the required address.
            if prevstate and prevstate.address <= address < entry.state.address:
                filename = lineprog['file_entry'][prevstate.file - 1].name
                line = prevstate.line
                return filename, line
            prevstate = entry.state
    return None, None


if __name__ == '__main__':
    for filename in sys.argv[1:]:
        # For testing we use a hardcoded address.
        process_file(filename, 0x400503)