cli: add cloud-init query subcommand to query instance metadata

Cloud-init caches any cloud metadata crawled during boot in the file
/run/cloud-init/instance-data.json. Cloud-init also standardizes some of
that metadata across all clouds. The command 'cloud-init query' surfaces a
simple CLI to query or format any cached instance metadata so that scripts
or end-users do not have to write tools to crawl metadata themselves.

Since 'cloud-init query' is runnable by non-root users, redact any
sensitive data from instance-data.json and provide a root-readable
unredacted instance-data-sensitive.json. Datasources can now define a
sensitive_metadata_keys tuple which will redact any matching keys
which could contain passwords or credentials from instance-data.json.

Also add the following standardized 'v1' instance-data.json keys:
  - user_data: The base64encoded user-data provided at instance launch
  - vendor_data: Any vendor_data provided to the instance at launch
  - underscore_delimited versions of existing hyphenated keys:
    instance_id, local_hostname, availability_zone, cloud_name

2 files changed, 171 insertions, 35 deletions

diff --git a/cloudinit/sources/__init__.py b/cloudinit/sources/__init__.py
index a775f1a8..730e8174 100644
--- a/cloudinit/sources/__init__.py
+++ b/cloudinit/sources/__init__.py
@@ -38,8 +38,12 @@ DEP_FILESYSTEM = "FILESYSTEM"
 DEP_NETWORK = "NETWORK"
 DS_PREFIX = 'DataSource'
 
-# File in which instance meta-data, user-data and vendor-data is written
+# File in which public available instance meta-data is written
+# security-sensitive key values are redacted from this world-readable file
 INSTANCE_JSON_FILE = 'instance-data.json'
+# security-sensitive key values are present in this root-readable file
+INSTANCE_JSON_SENSITIVE_FILE = 'instance-data-sensitive.json'
+REDACT_SENSITIVE_VALUE = 'redacted for non-root user'
 
 # Key which can be provide a cloud's official product name to cloud-init
 METADATA_CLOUD_NAME_KEY = 'cloud-name'
@@ -58,7 +62,7 @@ class InvalidMetaDataException(Exception):
     pass
 
 
-def process_instance_metadata(metadata, key_path=''):
+def process_instance_metadata(metadata, key_path='', sensitive_keys=()):
     """Process all instance metadata cleaning it up for persisting as json.
 
     Strip ci-b64 prefix and catalog any 'base64_encoded_keys' as a list
@@ -67,22 +71,46 @@ def process_instance_metadata(metadata, key_path=''):
     """
     md_copy = copy.deepcopy(metadata)
     md_copy['base64_encoded_keys'] = []
+    md_copy['sensitive_keys'] = []
     for key, val in metadata.items():
         if key_path:
             sub_key_path = key_path + '/' + key
         else:
             sub_key_path = key
+        if key in sensitive_keys or sub_key_path in sensitive_keys:
+            md_copy['sensitive_keys'].append(sub_key_path)
         if isinstance(val, str) and val.startswith('ci-b64:'):
             md_copy['base64_encoded_keys'].append(sub_key_path)
             md_copy[key] = val.replace('ci-b64:', '')
         if isinstance(val, dict):
-            return_val = process_instance_metadata(val, sub_key_path)
+            return_val = process_instance_metadata(
+                val, sub_key_path, sensitive_keys)
             md_copy['base64_encoded_keys'].extend(
                 return_val.pop('base64_encoded_keys'))
+            md_copy['sensitive_keys'].extend(
+                return_val.pop('sensitive_keys'))
             md_copy[key] = return_val
     return md_copy
 
 
+def redact_sensitive_keys(metadata, redact_value=REDACT_SENSITIVE_VALUE):
+    """Redact any sensitive keys from to provided metadata dictionary.
+
+    Replace any keys values listed in 'sensitive_keys' with redact_value.
+    """
+    if not metadata.get('sensitive_keys', []):
+        return metadata
+    md_copy = copy.deepcopy(metadata)
+    for key_path in metadata.get('sensitive_keys'):
+        path_parts = key_path.split('/')
+        obj = md_copy
+        for path in path_parts:
+            if isinstance(obj[path], dict) and path != path_parts[-1]:
+                obj = obj[path]
+        obj[path] = redact_value
+    return md_copy
+
+
 URLParams = namedtuple(
     'URLParms', ['max_wait_seconds', 'timeout_seconds', 'num_retries'])
 
@@ -127,6 +155,10 @@ class DataSource(object):
 
     _dirty_cache = False
 
+    # N-tuple of keypaths or keynames redact from instance-data.json for
+    # non-root users
+    sensitive_metadata_keys = ('security-credentials',)
+
     def __init__(self, sys_cfg, distro, paths, ud_proc=None):
         self.sys_cfg = sys_cfg
         self.distro = distro
@@ -152,12 +184,24 @@ class DataSource(object):
 
     def _get_standardized_metadata(self):
         """Return a dictionary of standardized metadata keys."""
-        return {'v1': {
-            'local-hostname': self.get_hostname(),
-            'instance-id': self.get_instance_id(),
-            'cloud-name': self.cloud_name,
-            'region': self.region,
-            'availability-zone': self.availability_zone}}
+        local_hostname = self.get_hostname()
+        instance_id = self.get_instance_id()
+        availability_zone = self.availability_zone
+        cloud_name = self.cloud_name
+        # When adding new standard keys prefer underscore-delimited instead
+        # of hyphen-delimted to support simple variable references in jinja
+        # templates.
+        return {
+            'v1': {
+                'availability-zone': availability_zone,
+                'availability_zone': availability_zone,
+                'cloud-name': cloud_name,
+                'cloud_name': cloud_name,
+                'instance-id': instance_id,
+                'instance_id': instance_id,
+                'local-hostname': local_hostname,
+                'local_hostname': local_hostname,
+                'region': self.region}}
 
     def clear_cached_attrs(self, attr_defaults=()):
         """Reset any cached metadata attributes to datasource defaults.
@@ -200,9 +244,7 @@ class DataSource(object):
         """
         instance_data = {
             'ds': {
-                'meta_data': self.metadata,
-                'user_data': self.get_userdata_raw(),
-                'vendor_data': self.get_vendordata_raw()}}
+                'meta_data': self.metadata}}
         if hasattr(self, 'network_json'):
             network_json = getattr(self, 'network_json')
             if network_json != UNSET:
@@ -217,7 +259,9 @@ class DataSource(object):
             # Process content base64encoding unserializable values
             content = util.json_dumps(instance_data)
             # Strip base64: prefix and set base64_encoded_keys list.
-            processed_data = process_instance_metadata(json.loads(content))
+            processed_data = process_instance_metadata(
+                json.loads(content),
+                sensitive_keys=self.sensitive_metadata_keys)
         except TypeError as e:
             LOG.warning('Error persisting instance-data.json: %s', str(e))
             return False
@@ -225,7 +269,11 @@ class DataSource(object):
             LOG.warning('Error persisting instance-data.json: %s', str(e))
             return False
         json_file = os.path.join(self.paths.run_dir, INSTANCE_JSON_FILE)
-        write_json(json_file, processed_data, mode=0o600)
+        write_json(json_file, processed_data)  # World readable
+        json_sensitive_file = os.path.join(self.paths.run_dir,
+                                           INSTANCE_JSON_SENSITIVE_FILE)
+        write_json(json_sensitive_file,
+                   redact_sensitive_keys(processed_data), mode=0o600)
         return True
 
     def _get_data(self):
diff --git a/cloudinit/sources/tests/test_init.py b/cloudinit/sources/tests/test_init.py
index 8299af23..6b965750 100644
--- a/cloudinit/sources/tests/test_init.py
+++ b/cloudinit/sources/tests/test_init.py
@@ -1,5 +1,6 @@
 # This file is part of cloud-init. See LICENSE file for license information.
 
+import copy
 import inspect
 import os
 import six
@@ -9,7 +10,8 @@ from cloudinit.event import EventType
 from cloudinit.helpers import Paths
 from cloudinit import importer
 from cloudinit.sources import (
-    INSTANCE_JSON_FILE, DataSource, UNSET)
+    INSTANCE_JSON_FILE, INSTANCE_JSON_SENSITIVE_FILE, REDACT_SENSITIVE_VALUE,
+    UNSET, DataSource, redact_sensitive_keys)
 from cloudinit.tests.helpers import CiTestCase, skipIf, mock
 from cloudinit.user_data import UserDataProcessor
 from cloudinit import util
@@ -20,20 +22,24 @@ class DataSourceTestSubclassNet(DataSource):
     dsname = 'MyTestSubclass'
     url_max_wait = 55
 
-    def __init__(self, sys_cfg, distro, paths, custom_userdata=None,
-                 get_data_retval=True):
+    def __init__(self, sys_cfg, distro, paths, custom_metadata=None,
+                 custom_userdata=None, get_data_retval=True):
         super(DataSourceTestSubclassNet, self).__init__(
             sys_cfg, distro, paths)
         self._custom_userdata = custom_userdata
+        self._custom_metadata = custom_metadata
         self._get_data_retval = get_data_retval
 
     def _get_cloud_name(self):
         return 'SubclassCloudName'
 
     def _get_data(self):
-        self.metadata = {'availability_zone': 'myaz',
-                         'local-hostname': 'test-subclass-hostname',
-                         'region': 'myregion'}
+        if self._custom_metadata:
+            self.metadata = self._custom_metadata
+        else:
+            self.metadata = {'availability_zone': 'myaz',
+                             'local-hostname': 'test-subclass-hostname',
+                             'region': 'myregion'}
         if self._custom_userdata:
             self.userdata_raw = self._custom_userdata
         else:
@@ -278,7 +284,7 @@ class TestDataSource(CiTestCase):
             os.path.exists(json_file), 'Found unexpected file %s' % json_file)
 
     def test_get_data_writes_json_instance_data_on_success(self):
-        """get_data writes INSTANCE_JSON_FILE to run_dir as readonly root."""
+        """get_data writes INSTANCE_JSON_FILE to run_dir as world readable."""
         tmp = self.tmp_dir()
         datasource = DataSourceTestSubclassNet(
             self.sys_cfg, self.distro, Paths({'run_dir': tmp}))
@@ -287,40 +293,90 @@ class TestDataSource(CiTestCase):
         content = util.load_file(json_file)
         expected = {
             'base64_encoded_keys': [],
+            'sensitive_keys': [],
             'v1': {
                 'availability-zone': 'myaz',
+                'availability_zone': 'myaz',
                 'cloud-name': 'subclasscloudname',
+                'cloud_name': 'subclasscloudname',
                 'instance-id': 'iid-datasource',
+                'instance_id': 'iid-datasource',
                 'local-hostname': 'test-subclass-hostname',
+                'local_hostname': 'test-subclass-hostname',
                 'region': 'myregion'},
             'ds': {
                 'meta_data': {'availability_zone': 'myaz',
                               'local-hostname': 'test-subclass-hostname',
-                              'region': 'myregion'},
-                'user_data': 'userdata_raw',
-                'vendor_data': 'vendordata_raw'}}
-        self.maxDiff = None
+                              'region': 'myregion'}}}
         self.assertEqual(expected, util.load_json(content))
         file_stat = os.stat(json_file)
+        self.assertEqual(0o644, stat.S_IMODE(file_stat.st_mode))
+        self.assertEqual(expected, util.load_json(content))
+
+    def test_get_data_writes_json_instance_data_sensitive(self):
+        """get_data writes INSTANCE_JSON_SENSITIVE_FILE as readonly root."""
+        tmp = self.tmp_dir()
+        datasource = DataSourceTestSubclassNet(
+            self.sys_cfg, self.distro, Paths({'run_dir': tmp}),
+            custom_metadata={
+                'availability_zone': 'myaz',
+                'local-hostname': 'test-subclass-hostname',
+                'region': 'myregion',
+                'some': {'security-credentials': {
+                    'cred1': 'sekret', 'cred2': 'othersekret'}}})
+        self.assertEqual(
+            ('security-credentials',), datasource.sensitive_metadata_keys)
+        datasource.get_data()
+        json_file = self.tmp_path(INSTANCE_JSON_FILE, tmp)
+        sensitive_json_file = self.tmp_path(INSTANCE_JSON_SENSITIVE_FILE, tmp)
+        redacted = util.load_json(util.load_file(json_file))
+        self.assertEqual(
+            {'cred1': 'sekret', 'cred2': 'othersekret'},
+            redacted['ds']['meta_data']['some']['security-credentials'])
+        content = util.load_file(sensitive_json_file)
+        expected = {
+            'base64_encoded_keys': [],
+            'sensitive_keys': ['ds/meta_data/some/security-credentials'],
+            'v1': {
+                'availability-zone': 'myaz',
+                'availability_zone': 'myaz',
+                'cloud-name': 'subclasscloudname',
+                'cloud_name': 'subclasscloudname',
+                'instance-id': 'iid-datasource',
+                'instance_id': 'iid-datasource',
+                'local-hostname': 'test-subclass-hostname',
+                'local_hostname': 'test-subclass-hostname',
+                'region': 'myregion'},
+            'ds': {
+                'meta_data': {
+                    'availability_zone': 'myaz',
+                    'local-hostname': 'test-subclass-hostname',
+                    'region': 'myregion',
+                    'some': {'security-credentials': REDACT_SENSITIVE_VALUE}}}
+        }
+        self.maxDiff = None
+        self.assertEqual(expected, util.load_json(content))
+        file_stat = os.stat(sensitive_json_file)
         self.assertEqual(0o600, stat.S_IMODE(file_stat.st_mode))
+        self.assertEqual(expected, util.load_json(content))
 
     def test_get_data_handles_redacted_unserializable_content(self):
         """get_data warns unserializable content in INSTANCE_JSON_FILE."""
         tmp = self.tmp_dir()
         datasource = DataSourceTestSubclassNet(
             self.sys_cfg, self.distro, Paths({'run_dir': tmp}),
-            custom_userdata={'key1': 'val1', 'key2': {'key2.1': self.paths}})
+            custom_metadata={'key1': 'val1', 'key2': {'key2.1': self.paths}})
         datasource.get_data()
         json_file = self.tmp_path(INSTANCE_JSON_FILE, tmp)
         content = util.load_file(json_file)
-        expected_userdata = {
+        expected_metadata = {
             'key1': 'val1',
             'key2': {
                 'key2.1': "Warning: redacted unserializable type <class"
                           " 'cloudinit.helpers.Paths'>"}}
         instance_json = util.load_json(content)
         self.assertEqual(
-            expected_userdata, instance_json['ds']['user_data'])
+            expected_metadata, instance_json['ds']['meta_data'])
 
     def test_persist_instance_data_writes_ec2_metadata_when_set(self):
         """When ec2_metadata class attribute is set, persist to json."""
@@ -361,17 +417,17 @@ class TestDataSource(CiTestCase):
         tmp = self.tmp_dir()
         datasource = DataSourceTestSubclassNet(
             self.sys_cfg, self.distro, Paths({'run_dir': tmp}),
-            custom_userdata={'key1': 'val1', 'key2': {'key2.1': b'\x123'}})
+            custom_metadata={'key1': 'val1', 'key2': {'key2.1': b'\x123'}})
         self.assertTrue(datasource.get_data())
         json_file = self.tmp_path(INSTANCE_JSON_FILE, tmp)
         content = util.load_file(json_file)
         instance_json = util.load_json(content)
-        self.assertEqual(
-            ['ds/user_data/key2/key2.1'],
+        self.assertItemsEqual(
+            ['ds/meta_data/key2/key2.1'],
             instance_json['base64_encoded_keys'])
         self.assertEqual(
             {'key1': 'val1', 'key2': {'key2.1': 'EjM='}},
-            instance_json['ds']['user_data'])
+            instance_json['ds']['meta_data'])
 
     @skipIf(not six.PY2, "json serialization on <= py2.7 handles bytes")
     def test_get_data_handles_bytes_values(self):
@@ -379,7 +435,7 @@ class TestDataSource(CiTestCase):
         tmp = self.tmp_dir()
         datasource = DataSourceTestSubclassNet(
             self.sys_cfg, self.distro, Paths({'run_dir': tmp}),
-            custom_userdata={'key1': 'val1', 'key2': {'key2.1': b'\x123'}})
+            custom_metadata={'key1': 'val1', 'key2': {'key2.1': b'\x123'}})
         self.assertTrue(datasource.get_data())
         json_file = self.tmp_path(INSTANCE_JSON_FILE, tmp)
         content = util.load_file(json_file)
@@ -387,7 +443,7 @@ class TestDataSource(CiTestCase):
         self.assertEqual([], instance_json['base64_encoded_keys'])
         self.assertEqual(
             {'key1': 'val1', 'key2': {'key2.1': '\x123'}},
-            instance_json['ds']['user_data'])
+            instance_json['ds']['meta_data'])
 
     @skipIf(not six.PY2, "Only python2 hits UnicodeDecodeErrors on non-utf8")
     def test_non_utf8_encoding_logs_warning(self):
@@ -395,7 +451,7 @@ class TestDataSource(CiTestCase):
         tmp = self.tmp_dir()
         datasource = DataSourceTestSubclassNet(
             self.sys_cfg, self.distro, Paths({'run_dir': tmp}),
-            custom_userdata={'key1': 'val1', 'key2': {'key2.1': b'ab\xaadef'}})
+            custom_metadata={'key1': 'val1', 'key2': {'key2.1': b'ab\xaadef'}})
         self.assertTrue(datasource.get_data())
         json_file = self.tmp_path(INSTANCE_JSON_FILE, tmp)
         self.assertFalse(os.path.exists(json_file))
@@ -509,4 +565,36 @@ class TestDataSource(CiTestCase):
             self.logs.getvalue())
 
 
+class TestRedactSensitiveData(CiTestCase):
+
+    def test_redact_sensitive_data_noop_when_no_sensitive_keys_present(self):
+        """When sensitive_keys is absent or empty from metadata do nothing."""
+        md = {'my': 'data'}
+        self.assertEqual(
+            md, redact_sensitive_keys(md, redact_value='redacted'))
+        md['sensitive_keys'] = []
+        self.assertEqual(
+            md, redact_sensitive_keys(md, redact_value='redacted'))
+
+    def test_redact_sensitive_data_redacts_exact_match_name(self):
+        """Only exact matched sensitive_keys are redacted from metadata."""
+        md = {'sensitive_keys': ['md/secure'],
+              'md': {'secure': 's3kr1t', 'insecure': 'publik'}}
+        secure_md = copy.deepcopy(md)
+        secure_md['md']['secure'] = 'redacted'
+        self.assertEqual(
+            secure_md,
+            redact_sensitive_keys(md, redact_value='redacted'))
+
+    def test_redact_sensitive_data_does_redacts_with_default_string(self):
+        """When redact_value is absent, REDACT_SENSITIVE_VALUE is used."""
+        md = {'sensitive_keys': ['md/secure'],
+              'md': {'secure': 's3kr1t', 'insecure': 'publik'}}
+        secure_md = copy.deepcopy(md)
+        secure_md['md']['secure'] = 'redacted for non-root user'
+        self.assertEqual(
+            secure_md,
+            redact_sensitive_keys(md))
+
+
 # vi: ts=4 expandtab