mercurial/policy.py

revlog: add a mechanism to verify expected file position before appending

If someone uses `hg debuglocks`, or some non-hg process writes to the .hg
directory without respecting the locks, or if the repo's on a networked
filesystem, it's possible for the revlog code to write out corrupted data.

The form of this corruption can vary depending on what data was written and how
that happened. We are in the "networked filesystem" case (though I've had users
also do this to themselves with the "`hg debuglocks`" scenario), and most often
see this with the changelog. What ends up happening is we produce two items
(let's call them rev1 and rev2) in the .i file that have the same linkrev,
baserev, and offset into the .d file, while the data in the .d file is appended
properly. rev2's compressed_size is accurate for rev2, but when we go to
decompress the data in the .d file, we use the offset that's recorded in the
index file, which is the same as rev1, and attempt to decompress
rev2.compressed_size bytes of rev1's data. This usually does not succeed. :)

When using inline data, this also fails, though I haven't investigated why too
closely. This shows up as a "patch decode" error. I believe what's happening
there is that we're basically ignoring the offset field, getting the data
properly, but since baserev != rev, it thinks this is a delta based on rev
(instead of a full text) and can't actually apply it as such.

For now, I'm going to make this an optional component and default it to entirely
off. I may increase the default severity of this in the future, once I've
enabled it for my users and we gain more experience with it. Luckily, most of my
users have a versioned filesystem and can roll back to before the corruption has
been written, it's just a hassle to do so and not everyone knows how (so it's a
support burden). Users on other filesystems will not have that luxury, and this
can cause them to have a corrupted repository that they are unlikely to know how
to resolve, and they'll see this as a data-loss event. Refusing to create the
corruption is a much better user experience.

This mechanism is not perfect. There may be false-negatives (racy writes that
are not detected). There should not be any false-positives (non-racy writes that
are detected as such). This is not a mechanism that makes putting a repo on a
networked filesystem "safe" or "supported", just *less* likely to cause
corruption.

Differential Revision: https://phab.mercurial-scm.org/D9952

# 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

from .pycompat import getattr

# Rules for how modules can be loaded. Values are:
#
#    c - require C extensions
#    rust+c - require Rust and C extensions
#    rust+c-allow - allow Rust and C extensions with fallback to pure Python
#                   for each
#    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': ('cext', None),
    b'allow': ('cext', 'pure'),
    b'cffi': ('cffi', None),
    b'cffi-allow': ('cffi', 'pure'),
    b'py': (None, 'pure'),
    # For now, rust policies impact importrust only
    b'rust+c': ('cext', None),
    b'rust+c-allow': ('cext', '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 '__pypy__' in sys.builtin_module_names:
    policy = b'cffi'

# Environment variable can always force settings.
if sys.version_info[0] >= 3:
    if 'HGMODULEPOLICY' in os.environ:
        policy = os.environ['HGMODULEPOLICY'].encode('utf-8')
else:
    policy = os.environ.get('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('cannot import name %s' % modname)
    # force import; fakelocals[modname] may be replaced with the real module
    getattr(mod, '__doc__', None)
    return fakelocals[modname]


# keep in sync with "version" in C modules
_cextversions = {
    ('cext', 'base85'): 1,
    ('cext', 'bdiff'): 3,
    ('cext', 'mpatch'): 1,
    ('cext', 'osutil'): 4,
    ('cext', 'parsers'): 17,
}

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


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


def _isrustpermissive():
    """Assuming the policy is a Rust one, tell if it's permissive."""
    return policy.endswith(b'-allow')


def importrust(modname, member=None, default=None):
    """Import Rust module according to policy and availability.

    If policy isn't a Rust one, this returns `default`.

    If either the module or its member is not available, this returns `default`
    if policy is permissive and raises `ImportError` if not.
    """
    if not policy.startswith(b'rust'):
        return default

    try:
        mod = _importfrom('rustext', modname)
    except ImportError:
        if _isrustpermissive():
            return default
        raise
    if member is None:
        return mod

    try:
        return getattr(mod, member)
    except AttributeError:
        if _isrustpermissive():
            return default
        raise ImportError("Cannot import name %s" % member)