llvm-project/llvm/test/Scripts/elf-dump

#!/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', %d) # %r" % (self.sh_name, shstrtab[self.sh_name])
        print "   ('sh_type', %d)" % self.sh_type
        print "   ('sh_flags', %d)" % self.sh_flags
        print "   ('sh_addr', %d)" % self.sh_addr
        print "   ('sh_offset', %d)" % self.sh_offset
        print "   ('sh_size', %d)" % self.sh_size
        print "   ('sh_link', %d)" % self.sh_link
        print "   ('sh_info', %d)" % self.sh_info
        print "   ('sh_addralign', %d)" % self.sh_addralign
        print "   ('sh_entsize', %d)" % 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)
            data = f.read(self.sh_size)
            print "   ('_section_data', '%s')" % common_dump.dataToHex(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 %d" % index
        name = f.read32()
        print "    (('st_name', %d) # %r" % (name, strtab[name])
        if not f.is64Bit:
            print "     ('st_value', %d)" % f.read32()
            print "     ('st_size', %d)" % f.read32()
        st_info = f.read8()
        print "     ('st_bind', %d)" % (st_info >> 4)
        print "     ('st_type', %d)" % (st_info & 0xf)
        print "     ('st_other', %d)" % f.read8()
        print "     ('st_shndx', %d)" % f.read16()
        if f.is64Bit:
            print "     ('st_value', %d)" % f.read64()
            print "     ('st_size', %d)" % f.read64()
        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 %d" % index
        print "    (('r_offset', %d)" % f.readWord()
        r_info = f.readWord()
        if f.is64Bit:
            print "     ('r_sym', %d)" % (r_info >> 32)
            print "     ('r_type', %d)" % (r_info & 0xffffffff)
        else:
            print "     ('r_sym', %d)" % (r_info >> 8)
            print "     ('r_type', %d)" % (r_info & 0xff)
        if dumprela:
            print "     ('r_addend', %d)" % 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 %d" % fileclass
    print "('e_indent[EI_CLASS]', %d)" % fileclass

    byteordering = f.read8()
    if byteordering == 1: # ELFDATA2LSB
        f.isLSB = True
    elif byteordering == 2: # ELFDATA2MSB
        f.isLSB = False
    else:
        raise ValueError, "Unknown byte ordering %d" % byteordering
    print "('e_indent[EI_DATA]', %d)" % byteordering

    print "('e_indent[EI_VERSION]', %d)" % f.read8()
    print "('e_indent[EI_OSABI]', %d)" % f.read8()
    print "('e_indent[EI_ABIVERSION]', %d)" % f.read8()

    f.seek(16) # Seek to end of e_ident.

    print "('e_type', %d)" % f.read16()
    print "('e_machine', %d)" % f.read16()
    print "('e_version', %d)" % f.read32()
    print "('e_entry', %d)" % f.readWord()
    print "('e_phoff', %d)" % f.readWord()
    e_shoff = f.readWord()
    print "('e_shoff', %d)" % e_shoff
    print "('e_flags', %d)" % f.read32()
    print "('e_ehsize', %d)" % f.read16()
    print "('e_phentsize', %d)" % f.read16()
    print "('e_phnum', %d)" % f.read16()
    e_shentsize = f.read16()
    print "('e_shentsize', %d)" % e_shentsize
    e_shnum = f.read16()
    print "('e_shnum', %d)" % e_shnum
    e_shstrndx = f.read16()
    print "('e_shstrndx', %d)" % 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 %d" % 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)