view mercurial/revlogutils/constants.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

# revlogdeltas.py - constant used for revlog logic
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
# Copyright 2018 Octobus <[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.
"""Helper class to compute deltas stored inside revlogs"""

from __future__ import absolute_import

from .. import (
    repository,
    util,
)

# revlog header flags
REVLOGV0 = 0
REVLOGV1 = 1
# Dummy value until file format is finalized.
# Reminder: change the bounds check in revlog.__init__ when this is changed.
REVLOGV2 = 0xDEAD
FLAG_INLINE_DATA = (1 << 16)
FLAG_GENERALDELTA = (1 << 17)
REVLOG_DEFAULT_FLAGS = FLAG_INLINE_DATA
REVLOG_DEFAULT_FORMAT = REVLOGV1
REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
REVLOGV1_FLAGS = FLAG_INLINE_DATA | FLAG_GENERALDELTA
REVLOGV2_FLAGS = REVLOGV1_FLAGS

# revlog index flags

# For historical reasons, revlog's internal flags were exposed via the
# wire protocol and are even exposed in parts of the storage APIs.

# revision has censor metadata, must be verified
REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED
# revision hash does not match data (narrowhg)
REVIDX_ELLIPSIS = repository.REVISION_FLAG_ELLIPSIS
# revision data is stored externally
REVIDX_EXTSTORED = repository.REVISION_FLAG_EXTSTORED
REVIDX_DEFAULT_FLAGS = 0
# stable order in which flags need to be processed and their processors applied
REVIDX_FLAGS_ORDER = [
    REVIDX_ISCENSORED,
    REVIDX_ELLIPSIS,
    REVIDX_EXTSTORED,
]
REVIDX_KNOWN_FLAGS = util.bitsfrom(REVIDX_FLAGS_ORDER)
# bitmark for flags that could cause rawdata content change
REVIDX_RAWTEXT_CHANGING_FLAGS = REVIDX_ISCENSORED | REVIDX_EXTSTORED

SPARSE_REVLOG_MAX_CHAIN_LENGTH = 1000