scripts/libc_early_init_name.py

   1 #!/usr/bin/python3
   2 # Compute the hash-based name of the __libc_early_init function.
   3 # Copyright (C) 2022 Free Software Foundation, Inc.
   4 # This file is part of the GNU C Library.
   5 #
   6 # The GNU C Library is free software; you can redistribute it and/or
   7 # modify it under the terms of the GNU Lesser General Public
   8 # License as published by the Free Software Foundation; either
   9 # version 2.1 of the License, or (at your option) any later version.
  10 #
  11 # The GNU C Library is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14 # Lesser General Public License for more details.
  15 #
  16 # You should have received a copy of the GNU Lesser General Public
  17 # License along with the GNU C Library; if not, see
  18 # <https://www.gnu.org/licenses/>.
  19
  20 """Compute the name of the __libc_early_init function, which is used
  21 as a protocol version marker between ld.so and libc.so.
  22
  23 The name contains a hash suffix, and the hash changes if certain key
  24 files in the source tree change.  Distributions can also configure
  25 with --with-extra-version-id, to make the computed hash dependent on
  26 the package version.
  27
  28 """
  29
  30 import argparse
  31 import hashlib
  32 import os
  33 import string
  34 import sys
  35
  36 def gnu_hash(s):
  37     """Computes the GNU hash of the string."""
  38     h = 5381
  39     for ch in s:
  40         if type(ch) is not int:
  41             ch = ord(ch)
  42         h = (h * 33 + ch) & 0xffffffff
  43     return h
  44
  45 # Parse the command line.
  46 parser = argparse.ArgumentParser(description=__doc__)
  47 parser.add_argument('--output', metavar='PATH',
  48                     help='path to header file this tool generates')
  49 parser.add_argument('--extra-version-id', metavar='ID',
  50                     help='extra string to influence hash computation')
  51 parser.add_argument('inputs', metavar='PATH', nargs='*',
  52                     help='files whose contents influences the generated hash')
  53 opts = parser.parse_args()
  54
  55 # Obtain the blobs that affect the generated hash.
  56 blobs = [(opts.extra_version_id or '').encode('UTF-8')]
  57 for path in opts.inputs:
  58     with open(path, 'rb') as inp:
  59         blobs.append(inp.read())
  60
  61 # Hash the file boundaries.
  62 md = hashlib.sha256()
  63 md.update(repr([len(blob) for blob in blobs]).encode('UTF-8'))
  64
  65 # And then hash the file contents.  Do not hash the paths, to avoid
  66 # impacting reproducibility.
  67 for blob in blobs:
  68     md.update(blob)
  69
  70 # These are the bits used to compute the suffix.
  71 derived_bits = int.from_bytes(md.digest(), byteorder='big', signed=False)
  72
  73 # These digits are used in the suffix (should result in base-62 encoding).
  74 # They must be valid in C identifiers.
  75 digits = string.digits + string.ascii_letters
  76
  77 # Generate eight digits as a suffix.  They should provide enough
  78 # uniqueness (47.6 bits).
  79 name = '__libc_early_init_'
  80 for n in range(8):
  81     name += digits[derived_bits % len(digits)]
  82     derived_bits //= len(digits)
  83
  84 # Write the output file.
  85 with open(opts.output, 'w') if opts.output else sys.stdout as out:
  86     out.write('#define LIBC_EARLY_INIT_NAME {}\n'.format(name))
  87     out.write('#define LIBC_EARLY_INIT_NAME_STRING "{}"\n'.format(name))
  88     out.write('#define LIBC_EARLY_INIT_GNU_HASH {}\n'.format(
  89         gnu_hash(name)))