fdroidserver/makebuildserver

#!/usr/bin/env python3

import os
import re
import requests
import stat
import sys
import shutil
import subprocess
import vagrant
import hashlib
import yaml
import json
import logging
from clint.textui import progress
from optparse import OptionParser
import fdroidserver.tail
import fdroidserver.vmtools


parser = OptionParser()
parser.add_option('-v', '--verbose', action="count", dest='verbosity', default=1,
                  help="Spew out even more information than normal")
parser.add_option('-q', action='store_const', const=0, dest='verbosity')
parser.add_option("-c", "--clean", action="store_true", default=False,
                  help="Build from scratch, rather than attempting to update the existing server")
parser.add_option('--skip-box-verification', action="store_true", default=False,
                  help="""Skip verifying the downloaded base box.""")
parser.add_option('--skip-cache-update', action="store_true", default=False,
                  help="""Skip downloading and checking cache."""
                       """This assumes that the cache is already downloaded completely.""")
parser.add_option('--copy-caches-from-host', action="store_true", default=False,
                  help="""Copy gradle and pip caches into the buildserver VM""")
parser.add_option('--keep-box-file', action="store_true", default=False,
                  help="""Box file will not be deleted after adding it to box storage"""
                       """ (KVM-only).""")
options, args = parser.parse_args()


logformat = '%(levelname)s: %(message)s'
loglevel = logging.DEBUG
if options.verbosity == 1:
    loglevel = logging.INFO
elif options.verbosity <= 0:
    loglevel = logging.WARNING
logging.basicConfig(format=logformat, level=loglevel)

tail = None

BASEBOX_DEFAULT = 'debian/bookworm64'
BASEBOX_VERSION_DEFAULT = "12.20231211.1"
BASEBOX_CHECKSUMS = {
    "12.20231211.1": {
        "libvirt": {
            "box.img": "80b048312c423b7fbbbac934c348f9a29bdf2f98fae96dd13b3af70ddfe7f12a",
            "Vagrantfile": "f9c6fcbb47a4d0d33eb066859c8e87efd642287a638bd7da69a9e7a6f25fec47",
            "metadata.json": "9d717678c19bb81d077e4e7eeb3602c168b6568cc38fee8fd3aa9d8f3cfe639b",
        },
        "virtualbox": {
            "box.ovf": "8ad49ba600fbd1027e35c8fd41d37383c04bad30fdbafa860a29911d207a3e7b",
            "box.vmdk": "57602a776860805e82bd3f61cdca9711f39781011db0f8f1dee9b2a614b2c889",
            "Vagrantfile": "0bbc2ae97668d8da27ab97b766752dcd0bf9e41900e21057de15a58ee7fae47d",
            "metadata.json": "ffdaa989f2f6932cd8042e1102371f405cc7ad38e324210a1326192e4689e83a",
        }
    },
}

configfile = 'buildserver/Vagrantfile.yaml'
if not os.path.exists(configfile):
    logging.warning('%s does not exist, copying template file.' % configfile)
    shutil.copy('examples/Vagrantfile.yaml', configfile)
with open(configfile) as fp:
    config = yaml.safe_load(fp)
    if not isinstance(config, dict):
        logging.info("config is empty or not a dict, using default.")
        config = {}
with open('buildserver/Vagrantfile') as fp:
    m = re.search(r"""\.vm\.box\s*=\s*["'](.*)["']""", fp.read())
    if not m:
        logging.error('Cannot find box name in buildserver/Vagrantfile!')
        sys.exit(1)
    config['basebox'] = m.group(1)
config['basebox_version'] = BASEBOX_VERSION_DEFAULT
config['cachedir'] = os.path.join(os.getenv('HOME'), '.cache', 'fdroidserver')

show_config_deprecation = False
if os.path.exists('makebuildserver.config.py'):
    show_config_deprecation = True
    logging.error('makebuildserver.config.py exists!')
elif os.path.exists('makebs.config.py'):
    show_config_deprecation = True
    # this is the old name for the config file
    logging.error('makebs.config.py exists!')
if show_config_deprecation:
    logging.error('Config is via %s and command line flags.' % configfile)
    parser.print_help()
    sys.exit(1)

logging.debug("Vagrantfile.yaml parsed -> %s", json.dumps(config, indent=4, sort_keys=True))

# Update cached files.
if not os.path.exists(config['cachedir']):
    os.makedirs(config['cachedir'], 0o755)
    logging.debug('created cachedir {} because it did not exists.'.format(config['cachedir']))

if config['vm_provider'] == 'libvirt':
    tmp = config['cachedir']
    while tmp != '/':
        mode = os.stat(tmp).st_mode
        if not (stat.S_IXUSR & mode and stat.S_IXGRP & mode and stat.S_IXOTH & mode):
            logging.critical('ERROR: %s will not be accessible to the VM!  To fix, run:', tmp)
            logging.critical('  chmod a+X %s', tmp)
            sys.exit(1)
        tmp = os.path.dirname(tmp)
    logging.debug('cache dir %s is accessible for libvirt vm.', config['cachedir'])

CACHE_FILES = [
    ('https://services.gradle.org/distributions/gradle-6.8.3-bin.zip',
     '7faa7198769f872826c8ef4f1450f839ec27f0b4d5d1e51bade63667cbccd205'),
    ('https://services.gradle.org/distributions/gradle-7.0.2-bin.zip',
     '0e46229820205440b48a5501122002842b82886e76af35f0f3a069243dca4b3c'),
]


def sha256_for_file(path):
    with open(path, 'rb') as f:
        s = hashlib.sha256()
        while True:
            data = f.read(4096)
            if not data:
                break
            s.update(data)
        return s.hexdigest()


def verify_file_sha256(path, sha256):
    if sha256_for_file(path) != sha256:
        logging.critical("File verification for '{path}' failed! "
                         "expected sha256 checksum: {checksum}"
                         .format(path=path, checksum=sha256))
        sys.exit(1)
    else:
        logging.debug("sucessfully verifyed file '{path}' "
                      "('{checksum}')".format(path=path,
                                              checksum=sha256))


def get_vagrant_home():
    return os.environ.get('VAGRANT_HOME',
                          os.path.join(os.path.expanduser('~'),
                                       '.vagrant.d'))


def run_via_vagrant_ssh(v, cmdlist):
    if (isinstance(cmdlist, str) or isinstance(cmdlist, bytes)):
        cmd = cmdlist
    else:
        cmd = ' '.join(cmdlist)
    v._run_vagrant_command(['ssh', '-c', cmd])


def update_cache(cachedir):
    count_files = 0
    for srcurl, shasum in CACHE_FILES:
        filename = os.path.basename(srcurl)
        local_filename = os.path.join(cachedir, filename)
        count_files = count_files + 1
        if os.path.exists(local_filename):
            if sha256_for_file(local_filename) == shasum:
                logging.info("\t...shasum verified for '{filename}'\t({filecounter} of {filesum} files)".format(filename=local_filename, filecounter=count_files, filesum=len(CACHE_FILES)))
                continue
            local_length = os.path.getsize(local_filename)
        else:
            local_length = -1

        resume_header = {}
        download = True

        try:
            r = requests.head(srcurl, allow_redirects=True, timeout=60)
            if r.status_code == 200:
                content_length = int(r.headers.get('content-length'))
            else:
                content_length = local_length  # skip the download
        except requests.exceptions.RequestException as e:
            content_length = local_length  # skip the download
            logging.warn('%s', e)

        if local_length == content_length:
            download = False
        elif local_length > content_length:
            logging.info('deleting corrupt file from cache: %s', local_filename)
            os.remove(local_filename)
            logging.info("Downloading %s to cache", filename)
        elif local_length > -1 and local_length < content_length:
            logging.info("Resuming download of %s", local_filename)
            resume_header = {'Range': 'bytes=%d-%d' % (local_length, content_length)}
        else:
            logging.info("Downloading %s to cache", filename)

        if download:
            r = requests.get(srcurl, headers=resume_header, stream=True,
                             allow_redirects=True, timeout=60)
            content_length = int(r.headers.get('content-length'))
            with open(local_filename, 'ab') as f:
                for chunk in progress.bar(r.iter_content(chunk_size=65536),
                                          expected_size=(content_length / 65536) + 1):
                    if chunk:  # filter out keep-alive new chunks
                        f.write(chunk)

        v = sha256_for_file(local_filename)
        if v == shasum:
            logging.info("\t...shasum verified for '{filename}'\t({filecounter} of {filesum} files)".format(filename=local_filename, filecounter=count_files, filesum=len(CACHE_FILES)))
        else:
            logging.critical("Invalid shasum of '%s' detected for %s", v, local_filename)
            os.remove(local_filename)
            sys.exit(1)


def debug_log_vagrant_vm(vm_dir, config):
    if options.verbosity >= 3:
        _vagrant_dir = os.path.join(vm_dir, '.vagrant')
        logging.debug('check %s dir exists? -> %r', _vagrant_dir, os.path.isdir(_vagrant_dir))
        logging.debug('> vagrant status')
        subprocess.call(['vagrant', 'status'], cwd=vm_dir)
        logging.debug('> vagrant box list')
        subprocess.call(['vagrant', 'box', 'list'])
        if config['vm_provider'] == 'libvirt':
            logging.debug('> virsh -c qmeu:///system list --all')
            subprocess.call(['virsh', '-c', 'qemu:///system', 'list', '--all'])
            domain = 'buildserver_default'
            logging.debug('> virsh -c qemu:///system snapshot-list %s', domain)
            subprocess.call(['virsh', '-c', 'qemu:///system', 'snapshot-list', domain])


def main():
    global config, tail

    if options.skip_cache_update:
        logging.info('skipping cache update and verification...')
    else:
        update_cache(config['cachedir'])

    # use VirtualBox software virtualization if hardware is not available,
    # like if this is being run in kvm or some other VM platform, like
    # http://jenkins.debian.net, the values are 'on' or 'off'
    if config.get('hwvirtex') != 'off' and os.path.exists('/proc/cpuinfo'):
        with open('/proc/cpuinfo') as f:
            contents = f.read()
        if 'vmx' in contents or 'svm' in contents:
            logging.debug('found \'vmx\' or \'svm\' in /proc/cpuinfo -> hwvirtex = \'on\'')
        else:
            logging.error('hwvirtex = \'on\' and no \'vmx\' or \'svm\' found in /proc/cpuinfo!')
            sys.exit(1)

    serverdir = os.path.join(os.getcwd(), 'buildserver')
    logfilename = os.path.join(serverdir, 'up.log')
    if not os.path.exists(logfilename):
        open(logfilename, 'a').close()  # create blank file
    log_cm = vagrant.make_file_cm(logfilename)
    v = vagrant.Vagrant(root=serverdir, out_cm=log_cm, err_cm=log_cm)
    # https://phoenhex.re/2018-03-25/not-a-vagrant-bug
    os_env = os.environ.copy()
    os_env['VAGRANT_DISABLE_VBOXSYMLINKCREATE'] = '1'
    v.env = os_env

    if options.verbosity >= 2:
        tail = fdroidserver.tail.Tail(logfilename)
        tail.start()

    vm = fdroidserver.vmtools.get_build_vm(serverdir, provider=config['vm_provider'])
    if options.clean:
        vm.destroy()

    # Check if selected provider is supported
    if config['vm_provider'] not in ['libvirt', 'virtualbox']:
        logging.critical("Currently selected VM provider '{vm_provider}' "
                         "is not supported. (please choose from: "
                         "virtualbox, libvirt)"
                         .format(vm_provider=config['cm_provider']))
        sys.exit(1)

    # Download and verify pre-built Vagrant boxes
    if not options.skip_box_verification:
        buildserver_not_created = any([True for x in v.status() if x.state == 'not_created' and x.name == 'default'])
        if buildserver_not_created or options.clean:
            # make vagrant download and add basebox
            target_basebox_installed = any([x for x in v.box_list() if x.name == config['basebox'] and x.provider == config['vm_provider'] and x.version == config['basebox_version']])
            if not target_basebox_installed:
                cmd = [shutil.which('vagrant'), 'box', 'add', config['basebox'],
                       '--box-version=' + config['basebox_version'],
                       '--provider=' + config['vm_provider']]
                ret_val = subprocess.call(cmd)
                if ret_val != 0:
                    logging.critical("downloading basebox '{box}' "
                                     "({provider}, version {version}) failed."
                                     .format(box=config['basebox'],
                                             provider=config['vm_provider'],
                                             version=config['basebox_version']))
                    sys.exit(1)
            # verify box
            if config['basebox_version'] not in BASEBOX_CHECKSUMS:
                logging.critical("can not verify '{box}', "
                                 "unknown basebox version '{version}'"
                                 .format(box=config['basebox'],
                                         version=config['basebox_version']))
                sys.exit(1)
            for filename, sha256 in BASEBOX_CHECKSUMS[config['basebox_version']][config['vm_provider']].items():
                verify_file_sha256(os.path.join(get_vagrant_home(),
                                                'boxes',
                                                config['basebox'].replace('/', '-VAGRANTSLASH-'),
                                                config['basebox_version'],
                                                config['vm_provider'],
                                                filename),
                                   sha256)
            logging.info("successfully verified: '{box}' "
                         "({provider}, version {version})"
                         .format(box=config['basebox'],
                                 provider=config['vm_provider'],
                                 version=config['basebox_version']))
    else:
        logging.debug('using unverified basebox ...')

    logging.info("Configuring build server VM")
    debug_log_vagrant_vm(serverdir, config)
    try:
        v.up(provision=True)
    except subprocess.CalledProcessError:
        debug_log_vagrant_vm(serverdir, config)
        logging.error("'vagrant up' failed. Consult %s", logfilename)
        sys.exit(1)

    if options.copy_caches_from_host:
        ssh_config = v.ssh_config()
        user = re.search(r'User ([^ \n]+)', ssh_config).group(1)
        hostname = re.search(r'HostName ([^ \n]+)', ssh_config).group(1)
        port = re.search(r'Port ([0-9]+)', ssh_config).group(1)
        key = re.search(r'IdentityFile ([^ \n]+)', ssh_config).group(1)

        for d in ('.m2', '.gradle/caches', '.gradle/wrapper', '.pip_download_cache'):
            fullpath = os.path.join(os.getenv('HOME'), d)
            os.system('date')
            print('rsyncing', fullpath, 'into VM')
            if os.path.isdir(fullpath):
                ssh_command = ' '.join(('ssh -i {0} -p {1}'.format(key, port),
                                        '-o StrictHostKeyChecking=no',
                                        '-o UserKnownHostsFile=/dev/null',
                                        '-o LogLevel=FATAL',
                                        '-o IdentitiesOnly=yes',
                                        '-o PasswordAuthentication=no'))
                # TODO vagrant 1.5+ provides `vagrant rsync`
                run_via_vagrant_ssh(v, ['cd ~ && test -d', d, '|| mkdir -p', d])
                subprocess.call(['rsync', '-ax', '--delete', '-e',
                                 ssh_command,
                                 fullpath + '/',
                                 user + '@' + hostname + ':~/' + d + '/'])

        # this file changes every time but should not be cached
        run_via_vagrant_ssh(v, ['rm', '-f', '~/.gradle/caches/modules-2/modules-2.lock'])
        run_via_vagrant_ssh(v, ['rm', '-fr', '~/.gradle/caches/*/plugin-resolution/'])

    logging.info("Stopping build server VM")
    v.halt()

    logging.info("Packaging")
    boxfile = os.path.join(os.getcwd(), 'buildserver.box')
    if os.path.exists(boxfile):
        os.remove(boxfile)

    v.package(output=boxfile)

    logging.info("Adding box")
    vm.box_add('buildserver', boxfile, force=True)

    if 'buildserver' not in subprocess.check_output(['vagrant', 'box', 'list']).decode('utf-8'):
        logging.critical('could not add box \'%s\' as \'buildserver\', terminating', boxfile)
        sys.exit(1)

    # Boxes are stored in two places when using vagrant-libvirt:
    #
    #  1. `vagrant box add` -> ~/.vagrant.d/boxes/buildserver/0/libvirt/
    #  2. `vagrant up` -> /var/lib/libvirt/images/buildserver_vagrant_box_image_0_box.img
    #
    # If the second box is not cleaned up, then `fdroid build` will
    # continue to use that one from the second location, thereby
    # ignoring the updated one at the first location.  This process
    # keeps the second one around until the new box is ready in case
    # `fdroid build` is using it while this script is running.
    img = 'buildserver_vagrant_box_image_0_box.img'
    if os.path.exists(os.path.join('/var/lib/libvirt/images', img)):
        subprocess.call(
            ['virsh', '-c', 'qemu:///system', 'vol-delete', '--pool', 'default', '--vol', img]
        )

    if not options.keep_box_file:
        logging.debug("""box added to vagrant, removing generated box file '%s'""",
                      boxfile)
        os.remove(boxfile)

        # This was needed just to create the box, after that, it is unused.
        vm.destroy()


if __name__ == '__main__':

    if not os.path.exists('makebuildserver') and not os.path.exists('buildserver'):
        logging.critical('This must be run as ./makebuildserver in fdroidserver.git!')
        sys.exit(1)

    if os.path.isfile('/usr/bin/systemd-detect-virt'):
        try:
            virt = subprocess.check_output('/usr/bin/systemd-detect-virt').strip().decode('utf-8')
        except subprocess.CalledProcessError:
            virt = 'none'
        if virt in ('qemu', 'kvm', 'bochs'):
            logging.info('Running in a VM guest, defaulting to QEMU/KVM via libvirt')
            config['vm_provider'] = 'libvirt'
        elif virt != 'none':
            logging.info('Running in an unsupported VM guest (%s)!', virt)
        logging.debug('detected virt: %s', virt)

    try:
        main()
    finally:
        if tail is not None:
            tail.stop()