#!/usr/bin/env python
import struct
import sys
import StringIO
import common_dump
class Reader:
def __init__(self, path):
if path == "-":
# Snarf all the data so we can seek.
self.file = StringIO.StringIO(sys.stdin.read())
else:
self.file = open(path, "rb")
self.isLSB = None
self.is64Bit = None
def seek(self, pos):
self.file.seek(pos)
def read(self, N):
data = self.file.read(N)
if len(data) != N:
raise ValueError, "Out of data!"
return data
def read8(self):
return ord(self.read(1))
def read16(self):
return struct.unpack('><'[self.isLSB] + 'H', self.read(2))[0]
def read32(self):
return struct.unpack('><'[self.isLSB] + 'I', self.read(4))[0]
def read32S(self):
return struct.unpack('><'[self.isLSB] + 'i', self.read(4))[0]
def read64(self):
return struct.unpack('><'[self.isLSB] + 'Q', self.read(8))[0]
def read64S(self):
return struct.unpack('><'[self.isLSB] + 'q', self.read(8))[0]
def readWord(self):
if self.is64Bit:
return self.read64()
else:
return self.read32()
def readWordS(self):
if self.is64Bit:
return self.read64S()
else:
return self.read32S()
class StringTable:
def __init__(self, strings):
self.string_table = strings
def __getitem__(self, index):
end = self.string_table.index('\x00', index)
return self.string_table[index:end]
class Section:
def __init__(self, f):
self.sh_name = f.read32()
self.sh_type = f.read32()
self.sh_flags = f.readWord()
self.sh_addr = f.readWord()
self.sh_offset = f.readWord()
self.sh_size = f.readWord()
self.sh_link = f.read32()
self.sh_info = f.read32()
self.sh_addralign = f.readWord()
self.sh_entsize = f.readWord()
def dump(self, shstrtab, f, strtab, dumpdata):
print " (('sh_name', %s)" % common_dump.HexDump(self.sh_name), "# %r" % shstrtab[self.sh_name]
print " ('sh_type', %s)" % common_dump.HexDump(self.sh_type)
print " ('sh_flags', %s)" % common_dump.HexDump(self.sh_flags)
print " ('sh_addr', %s)" % common_dump.HexDump(self.sh_addr)
print " ('sh_offset', %s)" % common_dump.HexDump(self.sh_offset)
print " ('sh_size', %s)" % common_dump.HexDump(self.sh_size)
print " ('sh_link', %s)" % common_dump.HexDump(self.sh_link)
print " ('sh_info', %s)" % common_dump.HexDump(self.sh_info)
print " ('sh_addralign', %s)" % common_dump.HexDump(self.sh_addralign)
print " ('sh_entsize', %s)" % common_dump.HexDump(self.sh_entsize)
if self.sh_type == 2: # SHT_SYMTAB
print " ('_symbols', ["
dumpSymtab(f, self, strtab)
print " ])"
elif self.sh_type == 4 or self.sh_type == 9: # SHT_RELA / SHT_REL
print " ('_relocations', ["
dumpRel(f, self, self.sh_type == 4)
print " ])"
elif dumpdata:
f.seek(self.sh_offset)
if self.sh_type != 8: # != SHT_NOBITS
data = f.read(self.sh_size)
print " ('_section_data', '%s')" % common_dump.dataToHex(data)
else:
print " ('_section_data', '')"
print " ),"
def dumpSymtab(f, section, strtab):
entries = section.sh_size // section.sh_entsize
for index in range(entries):
f.seek(section.sh_offset + index * section.sh_entsize)
print " # Symbol %s" % common_dump.HexDump(index)
name = f.read32()
print " (('st_name', %s)" % common_dump.HexDump(name), "# %r" % strtab[name]
if not f.is64Bit:
print " ('st_value', %s)" % common_dump.HexDump(f.read32())
print " ('st_size', %s)" % common_dump.HexDump(f.read32())
st_info = f.read8()
print " ('st_bind', %s)" % common_dump.HexDump((st_info >> 4))
print " ('st_type', %s)" % common_dump.HexDump((st_info & 0xf))
print " ('st_other', %s)" % common_dump.HexDump(f.read8())
print " ('st_shndx', %s)" % common_dump.HexDump(f.read16())
if f.is64Bit:
print " ('st_value', %s)" % common_dump.HexDump(f.read64(), 64)
print " ('st_size', %s)" % common_dump.HexDump(f.read64(), 64)
print " ),"
def dumpRel(f, section, dumprela = False):
entries = section.sh_size // section.sh_entsize
for index in range(entries):
f.seek(section.sh_offset + index * section.sh_entsize)
print " # Relocation %s" % common_dump.HexDump(index)
print " (('r_offset', %s)" % common_dump.HexDump(f.readWord())
r_info = f.readWord()
if f.is64Bit:
print " ('r_sym', %s)" % common_dump.HexDump((r_info >> 32))
print " ('r_type', %s)" % common_dump.HexDump((r_info & 0xffffffff))
else:
print " ('r_sym', %s)" % common_dump.HexDump((r_info >> 8))
print " ('r_type', %s)" % common_dump.HexDump((r_info & 0xff))
if dumprela:
print " ('r_addend', %s)" % common_dump.HexDump(f.readWordS())
print " ),"
def dumpELF(path, opts):
f = Reader(path)
magic = f.read(4)
assert magic == '\x7FELF'
fileclass = f.read8()
if fileclass == 1: # ELFCLASS32
f.is64Bit = False
elif fileclass == 2: # ELFCLASS64
f.is64Bit = True
else:
raise ValueError, "Unknown file class %s" % common_dump.HexDump(fileclass)
print "('e_indent[EI_CLASS]', %s)" % common_dump.HexDump(fileclass)
byteordering = f.read8()
if byteordering == 1: # ELFDATA2LSB
f.isLSB = True
elif byteordering == 2: # ELFDATA2MSB
f.isLSB = False
else:
raise ValueError, "Unknown byte ordering %s" % common_dump.HexDump(byteordering)
print "('e_indent[EI_DATA]', %s)" % common_dump.HexDump(byteordering)
print "('e_indent[EI_VERSION]', %s)" % common_dump.HexDump(f.read8())
print "('e_indent[EI_OSABI]', %s)" % common_dump.HexDump(f.read8())
print "('e_indent[EI_ABIVERSION]', %s)" % common_dump.HexDump(f.read8())
f.seek(16) # Seek to end of e_ident.
print "('e_type', %s)" % common_dump.HexDump(f.read16())
print "('e_machine', %s)" % common_dump.HexDump(f.read16())
print "('e_version', %s)" % common_dump.HexDump(f.read32())
print "('e_entry', %s)" % common_dump.HexDump(f.readWord())
print "('e_phoff', %s)" % common_dump.HexDump(f.readWord())
e_shoff = f.readWord()
print "('e_shoff', %s)" % common_dump.HexDump(e_shoff)
print "('e_flags', %s)" % common_dump.HexDump(f.read32())
print "('e_ehsize', %s)" % common_dump.HexDump(f.read16())
print "('e_phentsize', %s)" % common_dump.HexDump(f.read16())
print "('e_phnum', %s)" % common_dump.HexDump(f.read16())
e_shentsize = f.read16()
print "('e_shentsize', %s)" % common_dump.HexDump(e_shentsize)
e_shnum = f.read16()
print "('e_shnum', %s)" % common_dump.HexDump(e_shnum)
e_shstrndx = f.read16()
print "('e_shstrndx', %s)" % common_dump.HexDump(e_shstrndx)
# Read all section headers
sections = []
for index in range(e_shnum):
f.seek(e_shoff + index * e_shentsize)
s = Section(f)
sections.append(s)
# Read .shstrtab so we can resolve section names
f.seek(sections[e_shstrndx].sh_offset)
shstrtab = StringTable(f.read(sections[e_shstrndx].sh_size))
# Get the symbol string table
strtab = None
for section in sections:
if shstrtab[section.sh_name] == ".strtab":
f.seek(section.sh_offset)
strtab = StringTable(f.read(section.sh_size))
break
print "('_sections', ["
for index in range(e_shnum):
print " # Section %s" % common_dump.HexDump(index)
sections[index].dump(shstrtab, f, strtab, opts.dumpSectionData)
print "])"
if __name__ == "__main__":
from optparse import OptionParser, OptionGroup
parser = OptionParser("usage: %prog [options] {files}")
parser.add_option("", "--dump-section-data", dest="dumpSectionData",
help="Dump the contents of sections",
action="store_true", default=False)
(opts, args) = parser.parse_args()
if not args:
args.append('-')
for arg in args:
dumpELF(arg, opts)