summaryrefslogtreecommitdiff
path: root/cloudinit/sources/DataSourceNoCloud.py
blob: a126aad3d98814be7a235bc7a21c09737a6e31d2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
# Copyright (C) 2009-2010 Canonical Ltd.
# Copyright (C) 2012, 2013 Hewlett-Packard Development Company, L.P.
# Copyright (C) 2012 Yahoo! Inc.
#
# Author: Scott Moser <scott.moser@canonical.com>
# Author: Juerg Hafliger <juerg.haefliger@hp.com>
# Author: Joshua Harlow <harlowja@yahoo-inc.com>
#
# This file is part of cloud-init. See LICENSE file for license information.

import errno
import os

from cloudinit import dmi
from cloudinit import log as logging
from cloudinit.net import eni
from cloudinit import sources
from cloudinit import util

LOG = logging.getLogger(__name__)


class DataSourceNoCloud(sources.DataSource):

    dsname = "NoCloud"

    def __init__(self, sys_cfg, distro, paths):
        sources.DataSource.__init__(self, sys_cfg, distro, paths)
        self.seed = None
        self.seed_dirs = [os.path.join(paths.seed_dir, 'nocloud'),
                          os.path.join(paths.seed_dir, 'nocloud-net')]
        self.seed_dir = None
        self.supported_seed_starts = ("/", "file://")

    def __str__(self):
        root = sources.DataSource.__str__(self)
        return "%s [seed=%s][dsmode=%s]" % (root, self.seed, self.dsmode)

    def _get_devices(self, label):
        fslist = util.find_devs_with("TYPE=vfat")
        fslist.extend(util.find_devs_with("TYPE=iso9660"))

        label_list = util.find_devs_with("LABEL=%s" % label.upper())
        label_list.extend(util.find_devs_with("LABEL=%s" % label.lower()))
        label_list.extend(util.find_devs_with("LABEL_FATBOOT=%s" % label))

        devlist = list(set(fslist) & set(label_list))
        devlist.sort(reverse=True)
        return devlist

    def _get_data(self):
        defaults = {
            "instance-id": "nocloud",
            "dsmode": self.dsmode,
        }

        found = []
        mydata = {'meta-data': {}, 'user-data': "", 'vendor-data': "",
                  'network-config': None}

        try:
            # Parse the system serial label from dmi. If not empty, try parsing
            # like the commandline
            md = {}
            serial = dmi.read_dmi_data('system-serial-number')
            if serial and load_cmdline_data(md, serial):
                found.append("dmi")
                mydata = _merge_new_seed(mydata, {'meta-data': md})
        except Exception:
            util.logexc(LOG, "Unable to parse dmi data")
            return False

        try:
            # Parse the kernel command line, getting data passed in
            md = {}
            if load_cmdline_data(md):
                found.append("cmdline")
                mydata = _merge_new_seed(mydata, {'meta-data': md})
        except Exception:
            util.logexc(LOG, "Unable to parse command line data")
            return False

        # Check to see if the seed dir has data.
        pp2d_kwargs = {'required': ['user-data', 'meta-data'],
                       'optional': ['vendor-data', 'network-config']}

        for path in self.seed_dirs:
            try:
                seeded = util.pathprefix2dict(path, **pp2d_kwargs)
                found.append(path)
                LOG.debug("Using seeded data from %s", path)
                mydata = _merge_new_seed(mydata, seeded)
                break
            except ValueError:
                pass

        # If the datasource config had a 'seedfrom' entry, then that takes
        # precedence over a 'seedfrom' that was found in a filesystem
        # but not over external media
        if self.ds_cfg.get('seedfrom'):
            found.append("ds_config_seedfrom")
            mydata['meta-data']["seedfrom"] = self.ds_cfg['seedfrom']

        # fields appropriately named can also just come from the datasource
        # config (ie, 'user-data', 'meta-data', 'vendor-data' there)
        if 'user-data' in self.ds_cfg and 'meta-data' in self.ds_cfg:
            mydata = _merge_new_seed(mydata, self.ds_cfg)
            found.append("ds_config")

        def _pp2d_callback(mp, data):
            return util.pathprefix2dict(mp, **data)

        label = self.ds_cfg.get('fs_label', "cidata")
        if label is not None:
            for dev in self._get_devices(label):
                try:
                    LOG.debug("Attempting to use data from %s", dev)

                    try:
                        seeded = util.mount_cb(dev, _pp2d_callback,
                                               pp2d_kwargs)
                    except ValueError:
                        LOG.warning("device %s with label=%s not a "
                                    "valid seed.", dev, label)
                        continue

                    mydata = _merge_new_seed(mydata, seeded)

                    LOG.debug("Using data from %s", dev)
                    found.append(dev)
                    break
                except OSError as e:
                    if e.errno != errno.ENOENT:
                        raise
                except util.MountFailedError:
                    util.logexc(LOG, "Failed to mount %s when looking for "
                                "data", dev)

        # There was no indication on kernel cmdline or data
        # in the seeddir suggesting this handler should be used.
        if len(found) == 0:
            return False

        # The special argument "seedfrom" indicates we should
        # attempt to seed the userdata / metadata from its value
        # its primarily value is in allowing the user to type less
        # on the command line, ie: ds=nocloud;s=http://bit.ly/abcdefg
        if "seedfrom" in mydata['meta-data']:
            seedfrom = mydata['meta-data']["seedfrom"]
            seedfound = False
            for proto in self.supported_seed_starts:
                if seedfrom.startswith(proto):
                    seedfound = proto
                    break
            if not seedfound:
                LOG.debug("Seed from %s not supported by %s", seedfrom, self)
                return False

            # This could throw errors, but the user told us to do it
            # so if errors are raised, let them raise
            (md_seed, ud, vd) = util.read_seeded(seedfrom, timeout=None)
            LOG.debug("Using seeded cache data from %s", seedfrom)

            # Values in the command line override those from the seed
            mydata['meta-data'] = util.mergemanydict([mydata['meta-data'],
                                                      md_seed])
            mydata['user-data'] = ud
            mydata['vendor-data'] = vd
            found.append(seedfrom)

        # Now that we have exhausted any other places merge in the defaults
        mydata['meta-data'] = util.mergemanydict([mydata['meta-data'],
                                                  defaults])

        self.dsmode = self._determine_dsmode(
            [mydata['meta-data'].get('dsmode')])

        if self.dsmode == sources.DSMODE_DISABLED:
            LOG.debug("%s: not claiming datasource, dsmode=%s", self,
                      self.dsmode)
            return False

        self.seed = ",".join(found)
        self.metadata = mydata['meta-data']
        self.userdata_raw = mydata['user-data']
        self.vendordata_raw = mydata['vendor-data']
        self._network_config = mydata['network-config']
        self._network_eni = mydata['meta-data'].get('network-interfaces')
        return True

    @property
    def platform_type(self):
        # Handle upgrade path of pickled ds
        if not hasattr(self, '_platform_type'):
            self._platform_type = None
        if not self._platform_type:
            self._platform_type = 'lxd' if util.is_lxd() else 'nocloud'
        return self._platform_type

    def _get_cloud_name(self):
        """Return unknown when 'cloud-name' key is absent from metadata."""
        return sources.METADATA_UNKNOWN

    def _get_subplatform(self):
        """Return the subplatform metadata source details."""
        if self.seed.startswith('/dev'):
            subplatform_type = 'config-disk'
        else:
            subplatform_type = 'seed-dir'
        return '%s (%s)' % (subplatform_type, self.seed)

    def check_instance_id(self, sys_cfg):
        # quickly (local check only) if self.instance_id is still valid
        # we check kernel command line or files.
        current = self.get_instance_id()
        if not current:
            return None

        # LP: #1568150 need getattr in the case that an old class object
        # has been loaded from a pickled file and now executing new source.
        dirs = getattr(self, 'seed_dirs', [self.seed_dir])
        quick_id = _quick_read_instance_id(dirs=dirs)
        if not quick_id:
            return None
        return quick_id == current

    @property
    def network_config(self):
        if self._network_config is None:
            if self._network_eni is not None:
                self._network_config = eni.convert_eni_data(self._network_eni)
        return self._network_config


def _quick_read_instance_id(dirs=None):
    if dirs is None:
        dirs = []

    iid_key = 'instance-id'
    fill = {}
    if load_cmdline_data(fill) and iid_key in fill:
        return fill[iid_key]

    for d in dirs:
        if d is None:
            continue
        try:
            data = util.pathprefix2dict(d, required=['meta-data'])
            md = util.load_yaml(data['meta-data'])
            if iid_key in md:
                return md[iid_key]
        except ValueError:
            pass

    return None


def load_cmdline_data(fill, cmdline=None):
    pairs = [("ds=nocloud", sources.DSMODE_LOCAL),
             ("ds=nocloud-net", sources.DSMODE_NETWORK)]
    for idstr, dsmode in pairs:
        if parse_cmdline_data(idstr, fill, cmdline):
            # if dsmode was explicitly in the command line, then
            # prefer it to the dsmode based on the command line id
            if 'dsmode' not in fill:
                fill['dsmode'] = dsmode
            return True
    return False


# Returns true or false indicating if cmdline indicated
# that this module should be used.  Updates dictionary 'fill'
# with data that was found.
# Example cmdline:
#  root=LABEL=uec-rootfs ro ds=nocloud
def parse_cmdline_data(ds_id, fill, cmdline=None):
    if cmdline is None:
        cmdline = util.get_cmdline()
    cmdline = " %s " % cmdline

    if not (" %s " % ds_id in cmdline or " %s;" % ds_id in cmdline):
        return False

    argline = ""
    # cmdline can contain:
    # ds=nocloud[;key=val;key=val]
    for tok in cmdline.split():
        if tok.startswith(ds_id):
            argline = tok.split("=", 1)

    # argline array is now 'nocloud' followed optionally by
    # a ';' and then key=value pairs also terminated with ';'
    tmp = argline[1].split(";")
    if len(tmp) > 1:
        kvpairs = tmp[1:]
    else:
        kvpairs = ()

    # short2long mapping to save cmdline typing
    s2l = {"h": "local-hostname", "i": "instance-id", "s": "seedfrom"}
    for item in kvpairs:
        if item == "":
            continue
        try:
            (k, v) = item.split("=", 1)
        except Exception:
            k = item
            v = None
        if k in s2l:
            k = s2l[k]
        fill[k] = v

    return True


def _maybe_remove_top_network(cfg):
    """If network-config contains top level 'network' key, then remove it.

    Some providers of network configuration may provide a top level
    'network' key (LP: #1798117) even though it is not necessary.

    Be friendly and remove it if it really seems so.

    Return the original value if no change or the updated value if changed."""
    nullval = object()
    network_val = cfg.get('network', nullval)
    if network_val is nullval:
        return cfg
    bmsg = 'Top level network key in network-config %s: %s'
    if not isinstance(network_val, dict):
        LOG.debug(bmsg, "was not a dict", cfg)
        return cfg
    if len(list(cfg.keys())) != 1:
        LOG.debug(bmsg, "had multiple top level keys", cfg)
        return cfg
    if network_val.get('config') == "disabled":
        LOG.debug(bmsg, "was config/disabled", cfg)
    elif not all(('config' in network_val, 'version' in network_val)):
        LOG.debug(bmsg, "but missing 'config' or 'version'", cfg)
        return cfg
    LOG.debug(bmsg, "fixed by removing shifting network.", cfg)
    return network_val


def _merge_new_seed(cur, seeded):
    ret = cur.copy()

    newmd = seeded.get('meta-data', {})
    if not isinstance(seeded['meta-data'], dict):
        newmd = util.load_yaml(seeded['meta-data'])
    ret['meta-data'] = util.mergemanydict([cur['meta-data'], newmd])

    if seeded.get('network-config'):
        ret['network-config'] = _maybe_remove_top_network(
            util.load_yaml(seeded.get('network-config')))

    if 'user-data' in seeded:
        ret['user-data'] = seeded['user-data']
    if 'vendor-data' in seeded:
        ret['vendor-data'] = seeded['vendor-data']
    return ret


class DataSourceNoCloudNet(DataSourceNoCloud):
    def __init__(self, sys_cfg, distro, paths):
        DataSourceNoCloud.__init__(self, sys_cfg, distro, paths)
        self.supported_seed_starts = ("http://", "https://")


# Used to match classes to dependencies
datasources = [
    (DataSourceNoCloud, (sources.DEP_FILESYSTEM, )),
    (DataSourceNoCloudNet, (sources.DEP_FILESYSTEM, sources.DEP_NETWORK)),
]


# Return a list of data sources that match this set of dependencies
def get_datasource_list(depends):
    return sources.list_from_depends(depends, datasources)

# vi: ts=4 expandtab