view mercurial/dirstateguard.py @ 40670:87a872555e90

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

# dirstateguard.py - class to allow restoring dirstate after failure
#
# Copyright 2005-2007 Matt Mackall <[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

from .i18n import _

from . import (
    error,
    narrowspec,
    util,
)

class dirstateguard(util.transactional):
    '''Restore dirstate at unexpected failure.

    At the construction, this class does:

    - write current ``repo.dirstate`` out, and
    - save ``.hg/dirstate`` into the backup file

    This restores ``.hg/dirstate`` from backup file, if ``release()``
    is invoked before ``close()``.

    This just removes the backup file at ``close()`` before ``release()``.
    '''

    def __init__(self, repo, name):
        self._repo = repo
        self._active = False
        self._closed = False
        self._backupname = 'dirstate.backup.%s.%d' % (name, id(self))
        self._narrowspecbackupname = ('narrowspec.backup.%s.%d' %
                                      (name, id(self)))
        repo.dirstate.savebackup(repo.currenttransaction(), self._backupname)
        narrowspec.savebackup(repo, self._narrowspecbackupname)
        self._active = True

    def __del__(self):
        if self._active: # still active
            # this may occur, even if this class is used correctly:
            # for example, releasing other resources like transaction
            # may raise exception before ``dirstateguard.release`` in
            # ``release(tr, ....)``.
            self._abort()

    def close(self):
        if not self._active: # already inactivated
            msg = (_("can't close already inactivated backup: %s")
                   % self._backupname)
            raise error.Abort(msg)

        self._repo.dirstate.clearbackup(self._repo.currenttransaction(),
                                         self._backupname)
        narrowspec.clearbackup(self._repo, self._narrowspecbackupname)
        self._active = False
        self._closed = True

    def _abort(self):
        narrowspec.restorebackup(self._repo, self._narrowspecbackupname)
        self._repo.dirstate.restorebackup(self._repo.currenttransaction(),
                                           self._backupname)
        self._active = False

    def release(self):
        if not self._closed:
            if not self._active: # already inactivated
                msg = (_("can't release already inactivated backup: %s")
                       % self._backupname)
                raise error.Abort(msg)
            self._abort()