view mercurial/logexchange.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

# logexchange.py
#
# Copyright 2017 Augie Fackler <[e-mail]>
# Copyright 2017 Sean Farley <[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 .node import hex

from . import (
    util,
    vfs as vfsmod,
)

# directory name in .hg/ in which remotenames files will be present
remotenamedir = 'logexchange'

def readremotenamefile(repo, filename):
    """
    reads a file from .hg/logexchange/ directory and yields it's content
    filename: the file to be read
    yield a tuple (node, remotepath, name)
    """

    vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
    if not vfs.exists(filename):
        return
    f = vfs(filename)
    lineno = 0
    for line in f:
        line = line.strip()
        if not line:
            continue
        # contains the version number
        if lineno == 0:
            lineno += 1
        try:
            node, remote, rname = line.split('\0')
            yield node, remote, rname
        except ValueError:
            pass

    f.close()

def readremotenames(repo):
    """
    read the details about the remotenames stored in .hg/logexchange/ and
    yields a tuple (node, remotepath, name). It does not yields information
    about whether an entry yielded is branch or bookmark. To get that
    information, call the respective functions.
    """

    for bmentry in readremotenamefile(repo, 'bookmarks'):
        yield bmentry
    for branchentry in readremotenamefile(repo, 'branches'):
        yield branchentry

def writeremotenamefile(repo, remotepath, names, nametype):
    vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
    f = vfs(nametype, 'w', atomictemp=True)
    # write the storage version info on top of file
    # version '0' represents the very initial version of the storage format
    f.write('0\n\n')

    olddata = set(readremotenamefile(repo, nametype))
    # re-save the data from a different remote than this one.
    for node, oldpath, rname in sorted(olddata):
        if oldpath != remotepath:
            f.write('%s\0%s\0%s\n' % (node, oldpath, rname))

    for name, node in sorted(names.iteritems()):
        if nametype == "branches":
            for n in node:
                f.write('%s\0%s\0%s\n' % (n, remotepath, name))
        elif nametype == "bookmarks":
            if node:
                f.write('%s\0%s\0%s\n' % (node, remotepath, name))

    f.close()

def saveremotenames(repo, remotepath, branches=None, bookmarks=None):
    """
    save remotenames i.e. remotebookmarks and remotebranches in their
    respective files under ".hg/logexchange/" directory.
    """
    wlock = repo.wlock()
    try:
        if bookmarks:
            writeremotenamefile(repo, remotepath, bookmarks, 'bookmarks')
        if branches:
            writeremotenamefile(repo, remotepath, branches, 'branches')
    finally:
        wlock.release()

def activepath(repo, remote):
    """returns remote path"""
    local = None
    # is the remote a local peer
    local = remote.local()

    # determine the remote path from the repo, if possible; else just
    # use the string given to us
    rpath = remote
    if local:
        rpath = util.pconvert(remote._repo.root)
    elif not isinstance(remote, bytes):
        rpath = remote._url

    # represent the remotepath with user defined path name if exists
    for path, url in repo.ui.configitems('paths'):
        # remove auth info from user defined url
        noauthurl = util.removeauth(url)

        # Standardize on unix style paths, otherwise some {remotenames} end up
        # being an absolute path on Windows.
        url = util.pconvert(bytes(url))
        noauthurl = util.pconvert(noauthurl)
        if url == rpath or noauthurl == rpath:
            rpath = path
            break

    return rpath

def pullremotenames(localrepo, remoterepo):
    """
    pulls bookmarks and branches information of the remote repo during a
    pull or clone operation.
    localrepo is our local repository
    remoterepo is the peer instance
    """
    remotepath = activepath(localrepo, remoterepo)

    with remoterepo.commandexecutor() as e:
        bookmarks = e.callcommand('listkeys', {
            'namespace': 'bookmarks',
        }).result()

    # on a push, we don't want to keep obsolete heads since
    # they won't show up as heads on the next pull, so we
    # remove them here otherwise we would require the user
    # to issue a pull to refresh the storage
    bmap = {}
    repo = localrepo.unfiltered()

    with remoterepo.commandexecutor() as e:
        branchmap = e.callcommand('branchmap', {}).result()

    for branch, nodes in branchmap.iteritems():
        bmap[branch] = []
        for node in nodes:
            if node in repo and not repo[node].obsolete():
                bmap[branch].append(hex(node))

    saveremotenames(localrepo, remotepath, bmap, bookmarks)