#!/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 self.isN64 = False 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)), 8) def read16(self): return (struct.unpack('><'[self.isLSB] + 'H', self.read(2))[0], 16) def read32(self): return (struct.unpack('><'[self.isLSB] + 'I', self.read(4))[0], 32) def read64(self): return (struct.unpack('><'[self.isLSB] + 'Q', self.read(8))[0], 64) def readWord(self): if self.is64Bit: return self.read64() else: return self.read32() 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[0]] 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[0] == 2: # SHT_SYMTAB print " ('_symbols', [" dumpSymtab(f, self, strtab) print " ])" elif self.sh_type[0] == 4 or self.sh_type[0] == 9: # SHT_RELA / SHT_REL print " ('_relocations', [" dumpRel(f, self, self.sh_type[0] == 4) print " ])" elif dumpdata: f.seek(self.sh_offset[0]) if self.sh_type != 8: # != SHT_NOBITS data = f.read(self.sh_size[0]) print " ('_section_data', '%s')" % common_dump.dataToHex(data) else: print " ('_section_data', '')" print " )," def dumpSymtab(f, section, strtab): entries = section.sh_size[0] // section.sh_entsize[0] for index in range(entries): f.seek(section.sh_offset[0] + index * section.sh_entsize[0]) print " # Symbol %s" % index name = f.read32() print " (('st_name', %s)" % common_dump.HexDump(name), "# %r" % strtab[name[0]] 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()[0] st_bind = (st_info >> 4, 4) st_type = (st_info & 0xf, 4) print " ('st_bind', %s)" % common_dump.HexDump(st_bind) print " ('st_type', %s)" % common_dump.HexDump(st_type) 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()) print " ('st_size', %s)" % common_dump.HexDump(f.read64()) print " )," def dumpRel(f, section, dumprela = False): entries = section.sh_size[0] // section.sh_entsize[0] for index in range(entries): f.seek(section.sh_offset[0] + index * section.sh_entsize[0]) print " # Relocation %s" % index print " (('r_offset', %s)" % common_dump.HexDump(f.readWord()) if f.isN64: r_sym = f.read32() r_ssym = f.read8() r_type3 = f.read8() r_type2 = f.read8() r_type = f.read8() print " ('r_sym', %s)" % common_dump.HexDump(r_sym) print " ('r_ssym', %s)" % common_dump.HexDump(r_ssym) print " ('r_type3', %s)" % common_dump.HexDump(r_type3) print " ('r_type2', %s)" % common_dump.HexDump(r_type2) print " ('r_type', %s)" % common_dump.HexDump(r_type) else: r_info = f.readWord()[0] if f.is64Bit: r_sym = (r_info >> 32, 32) r_type = (r_info & 0xffffffff, 32) else: r_sym = (r_info >> 8, 24) r_type = (r_info & 0xff, 8) print " ('r_sym', %s)" % common_dump.HexDump(r_sym) print " ('r_type', %s)" % common_dump.HexDump(r_type) if dumprela: print " ('r_addend', %s)" % common_dump.HexDump(f.readWord()) print " )," def dumpELF(path, opts): f = Reader(path) magic = f.read(4) assert magic == '\x7FELF' fileclass = f.read8() if fileclass[0] == 1: # ELFCLASS32 f.is64Bit = False elif fileclass[0] == 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[0] == 1: # ELFDATA2LSB f.isLSB = True elif byteordering[0] == 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()) # Does any other architecture use N64? e_machine = f.read16() if e_machine[0] == 0x0008 and f.is64Bit: # EM_MIPS && 64 bit f.isN64 = True print "('e_machine', %s)" % common_dump.HexDump(e_machine) 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[0]): f.seek(e_shoff[0] + index * e_shentsize[0]) s = Section(f) sections.append(s) # Read .shstrtab so we can resolve section names f.seek(sections[e_shstrndx[0]].sh_offset[0]) shstrtab = StringTable(f.read(sections[e_shstrndx[0]].sh_size[0])) # Get the symbol string table strtab = None for section in sections: if shstrtab[section.sh_name[0]] == ".strtab": f.seek(section.sh_offset[0]) strtab = StringTable(f.read(section.sh_size[0])) break print "('_sections', [" for index in range(e_shnum[0]): print " # Section %s" % 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)