view mercurial/policy.py @ 40626:87a872555e90

revlog: detect incomplete revlog reads

_readsegment() is supposed to return N bytes of revlog revision
data starting at a file offset. Surprisingly, its behavior before
this patch never verified that it actually read and returned N
bytes! Instead, it would perform the read(), then return whatever
data was available. And even more surprisingly, nothing in the
call chain appears to have been validating that it received all
the data it was expecting.

This behavior could lead to partial or incomplete revision chunks
being operated on. This could result in e.g. cached deltas being
applied against incomplete base revisions. The delta application
process would happily perform this operation. Only hash
verification would detect the corruption and save us.

This commit changes the behavior of raw revlog reading to validate
that we actually read() the number of bytes that were requested.
We will raise a more specific error faster, rather than possibly
have it go undetected or manifest later in the call stack, at
delta application or hash verification.

Differential Revision: https://phab.mercurial-scm.org/D5266

# policy.py - module policy logic for Mercurial.
#
# Copyright 2015 Gregory Szorc <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os
import sys

# Rules for how modules can be loaded. Values are:
#
#    c - require C extensions
#    allow - allow pure Python implementation when C loading fails
#    cffi - required cffi versions (implemented within pure module)
#    cffi-allow - allow pure Python implementation if cffi version is missing
#    py - only load pure Python modules
#
# By default, fall back to the pure modules so the in-place build can
# run without recompiling the C extensions. This will be overridden by
# __modulepolicy__ generated by setup.py.
policy = b'allow'
_packageprefs = {
    # policy: (versioned package, pure package)
    b'c': (r'cext', None),
    b'allow': (r'cext', r'pure'),
    b'cffi': (r'cffi', None),
    b'cffi-allow': (r'cffi', r'pure'),
    b'py': (None, r'pure'),
}

try:
    from . import __modulepolicy__
    policy = __modulepolicy__.modulepolicy
except ImportError:
    pass

# PyPy doesn't load C extensions.
#
# The canonical way to do this is to test platform.python_implementation().
# But we don't import platform and don't bloat for it here.
if r'__pypy__' in sys.builtin_module_names:
    policy = b'cffi'

# Environment variable can always force settings.
if sys.version_info[0] >= 3:
    if r'HGMODULEPOLICY' in os.environ:
        policy = os.environ[r'HGMODULEPOLICY'].encode(r'utf-8')
else:
    policy = os.environ.get(r'HGMODULEPOLICY', policy)

def _importfrom(pkgname, modname):
    # from .<pkgname> import <modname> (where . is looked through this module)
    fakelocals = {}
    pkg = __import__(pkgname, globals(), fakelocals, [modname], level=1)
    try:
        fakelocals[modname] = mod = getattr(pkg, modname)
    except AttributeError:
        raise ImportError(r'cannot import name %s' % modname)
    # force import; fakelocals[modname] may be replaced with the real module
    getattr(mod, r'__doc__', None)
    return fakelocals[modname]

# keep in sync with "version" in C modules
_cextversions = {
    (r'cext', r'base85'): 1,
    (r'cext', r'bdiff'): 3,
    (r'cext', r'mpatch'): 1,
    (r'cext', r'osutil'): 4,
    (r'cext', r'parsers'): 11,
}

# map import request to other package or module
_modredirects = {
    (r'cext', r'charencode'): (r'cext', r'parsers'),
    (r'cffi', r'base85'): (r'pure', r'base85'),
    (r'cffi', r'charencode'): (r'pure', r'charencode'),
    (r'cffi', r'parsers'): (r'pure', r'parsers'),
}

def _checkmod(pkgname, modname, mod):
    expected = _cextversions.get((pkgname, modname))
    actual = getattr(mod, r'version', None)
    if actual != expected:
        raise ImportError(r'cannot import module %s.%s '
                          r'(expected version: %d, actual: %r)'
                          % (pkgname, modname, expected, actual))

def importmod(modname):
    """Import module according to policy and check API version"""
    try:
        verpkg, purepkg = _packageprefs[policy]
    except KeyError:
        raise ImportError(r'invalid HGMODULEPOLICY %r' % policy)
    assert verpkg or purepkg
    if verpkg:
        pn, mn = _modredirects.get((verpkg, modname), (verpkg, modname))
        try:
            mod = _importfrom(pn, mn)
            if pn == verpkg:
                _checkmod(pn, mn, mod)
            return mod
        except ImportError:
            if not purepkg:
                raise
    pn, mn = _modredirects.get((purepkg, modname), (purepkg, modname))
    return _importfrom(pn, mn)