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
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
|
# vi: ts=4 expandtab
#
# Copyright (C) 2012 Canonical Ltd.
# Copyright (C) 2012 Hewlett-Packard Development Company, L.P.
# Copyright (C) 2012 Yahoo! Inc.
#
# Author: Scott Moser <scott.moser@canonical.com>
# Author: Juerg Haefliger <juerg.haefliger@hp.com>
# Author: Joshua Harlow <harlowja@yahoo-inc.com>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 3, as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
# pylint: disable=C0302
from StringIO import StringIO
import contextlib
import copy as obj_copy
import errno
import glob
import grp
import gzip
import hashlib
import os
import platform
import pwd
import random
import shutil
import socket
import stat
import string # pylint: disable=W0402
import subprocess
import sys
import tempfile
import time
import types
import urlparse
import yaml
from cloudinit import importer
from cloudinit import log as logging
from cloudinit import safeyaml
from cloudinit import url_helper as uhelp
from cloudinit import version
from cloudinit.settings import (CFG_BUILTIN)
_DNS_REDIRECT_IP = None
LOG = logging.getLogger(__name__)
# Helps cleanup filenames to ensure they aren't FS incompatible
FN_REPLACEMENTS = {
os.sep: '_',
}
FN_ALLOWED = ('_-.()' + string.digits + string.ascii_letters)
# Helper utils to see if running in a container
CONTAINER_TESTS = ['running-in-container', 'lxc-is-container']
class ProcessExecutionError(IOError):
MESSAGE_TMPL = ('%(description)s\n'
'Command: %(cmd)s\n'
'Exit code: %(exit_code)s\n'
'Reason: %(reason)s\n'
'Stdout: %(stdout)r\n'
'Stderr: %(stderr)r')
def __init__(self, stdout=None, stderr=None,
exit_code=None, cmd=None,
description=None, reason=None):
if not cmd:
self.cmd = '-'
else:
self.cmd = cmd
if not description:
self.description = 'Unexpected error while running command.'
else:
self.description = description
if not isinstance(exit_code, (long, int)):
self.exit_code = '-'
else:
self.exit_code = exit_code
if not stderr:
self.stderr = ''
else:
self.stderr = stderr
if not stdout:
self.stdout = ''
else:
self.stdout = stdout
if reason:
self.reason = reason
else:
self.reason = '-'
message = self.MESSAGE_TMPL % {
'description': self.description,
'cmd': self.cmd,
'exit_code': self.exit_code,
'stdout': self.stdout,
'stderr': self.stderr,
'reason': self.reason,
}
IOError.__init__(self, message)
class SeLinuxGuard(object):
def __init__(self, path, recursive=False):
# Late import since it might not always
# be possible to use this
try:
self.selinux = importer.import_module('selinux')
except ImportError:
self.selinux = None
self.path = path
self.recursive = recursive
def __enter__(self):
if self.selinux:
return True
else:
return False
def __exit__(self, excp_type, excp_value, excp_traceback):
if self.selinux:
path = os.path.realpath(os.path.expanduser(self.path))
do_restore = False
try:
# See if even worth restoring??
stats = os.lstat(path)
if stat.ST_MODE in stats:
self.selinux.matchpathcon(path, stats[stat.ST_MODE])
do_restore = True
except OSError:
pass
if do_restore:
LOG.debug("Restoring selinux mode for %s (recursive=%s)",
path, self.recursive)
self.selinux.restorecon(path, recursive=self.recursive)
class MountFailedError(Exception):
pass
class DecompressionError(Exception):
pass
def ExtendedTemporaryFile(**kwargs):
fh = tempfile.NamedTemporaryFile(**kwargs)
# Replace its unlink with a quiet version
# that does not raise errors when the
# file to unlink has been unlinked elsewhere..
LOG.debug("Created temporary file %s", fh.name)
fh.unlink = del_file
# Add a new method that will unlink
# right 'now' but still lets the exit
# method attempt to remove it (which will
# not throw due to our del file being quiet
# about files that are not there)
def unlink_now():
fh.unlink(fh.name)
setattr(fh, 'unlink_now', unlink_now)
return fh
def fork_cb(child_cb, *args):
fid = os.fork()
if fid == 0:
try:
child_cb(*args)
os._exit(0) # pylint: disable=W0212
except:
logexc(LOG, ("Failed forking and"
" calling callback %s"), obj_name(child_cb))
os._exit(1) # pylint: disable=W0212
else:
LOG.debug("Forked child %s who will run callback %s",
fid, obj_name(child_cb))
def is_true(val, addons=None):
if isinstance(val, (bool)):
return val is True
check_set = ['true', '1', 'on', 'yes']
if addons:
check_set = check_set + addons
if str(val).lower().strip() in check_set:
return True
return False
def is_false(val, addons=None):
if isinstance(val, (bool)):
return val is False
check_set = ['off', '0', 'no', 'false']
if addons:
check_set = check_set + addons
if str(val).lower().strip() in check_set:
return True
return False
def translate_bool(val, addons=None):
if not val:
# This handles empty lists and false and
# other things that python believes are false
return False
# If its already a boolean skip
if isinstance(val, (bool)):
return val
return is_true(val, addons)
def rand_str(strlen=32, select_from=None):
if not select_from:
select_from = string.letters + string.digits
return "".join([random.choice(select_from) for _x in range(0, strlen)])
def read_conf(fname):
try:
return load_yaml(load_file(fname), default={})
except IOError as e:
if e.errno == errno.ENOENT:
return {}
else:
raise
# Merges X lists, and then keeps the
# unique ones, but orders by sort order
# instead of by the original order
def uniq_merge_sorted(*lists):
return sorted(uniq_merge(*lists))
# Merges X lists and then iterates over those
# and only keeps the unique items (order preserving)
# and returns that merged and uniqued list as the
# final result.
#
# Note: if any entry is a string it will be
# split on commas and empty entries will be
# evicted and merged in accordingly.
def uniq_merge(*lists):
combined_list = []
for a_list in lists:
if isinstance(a_list, (str, basestring)):
a_list = a_list.strip().split(",")
# Kickout the empty ones
a_list = [a for a in a_list if len(a)]
combined_list.extend(a_list)
return uniq_list(combined_list)
def clean_filename(fn):
for (k, v) in FN_REPLACEMENTS.iteritems():
fn = fn.replace(k, v)
removals = []
for k in fn:
if k not in FN_ALLOWED:
removals.append(k)
for k in removals:
fn = fn.replace(k, '')
fn = fn.strip()
return fn
def decomp_gzip(data, quiet=True):
try:
buf = StringIO(str(data))
with contextlib.closing(gzip.GzipFile(None, "rb", 1, buf)) as gh:
return gh.read()
except Exception as e:
if quiet:
return data
else:
raise DecompressionError(str(e))
def extract_usergroup(ug_pair):
if not ug_pair:
return (None, None)
ug_parted = ug_pair.split(':', 1)
u = ug_parted[0].strip()
if len(ug_parted) == 2:
g = ug_parted[1].strip()
else:
g = None
if not u or u == "-1" or u.lower() == "none":
u = None
if not g or g == "-1" or g.lower() == "none":
g = None
return (u, g)
def find_modules(root_dir):
entries = dict()
for fname in glob.glob(os.path.join(root_dir, "*.py")):
if not os.path.isfile(fname):
continue
modname = os.path.basename(fname)[0:-3]
modname = modname.strip()
if modname and modname.find(".") == -1:
entries[fname] = modname
return entries
def multi_log(text, console=True, stderr=True,
log=None, log_level=logging.DEBUG):
if stderr:
sys.stderr.write(text)
if console:
# Don't use the write_file since
# this might be 'sensitive' info (not debug worthy?)
with open('/dev/console', 'wb') as wfh:
wfh.write(text)
wfh.flush()
if log:
if text[-1] == "\n":
log.log(log_level, text[:-1])
else:
log.log(log_level, text)
def is_ipv4(instr):
"""determine if input string is a ipv4 address. return boolean."""
toks = instr.split('.')
if len(toks) != 4:
return False
try:
toks = [x for x in toks if (int(x) < 256 and int(x) > 0)]
except:
return False
return (len(toks) == 4)
def get_cfg_option_bool(yobj, key, default=False):
if key not in yobj:
return default
return translate_bool(yobj[key])
def get_cfg_option_str(yobj, key, default=None):
if key not in yobj:
return default
val = yobj[key]
if not isinstance(val, (str, basestring)):
val = str(val)
return val
def system_info():
return {
'platform': platform.platform(),
'release': platform.release(),
'python': platform.python_version(),
'uname': platform.uname(),
}
def get_cfg_option_list(yobj, key, default=None):
"""
Gets the C{key} config option from C{yobj} as a list of strings. If the
key is present as a single string it will be returned as a list with one
string arg.
@param yobj: The configuration object.
@param key: The configuration key to get.
@param default: The default to return if key is not found.
@return: The configuration option as a list of strings or default if key
is not found.
"""
if not key in yobj:
return default
if yobj[key] is None:
return []
val = yobj[key]
if isinstance(val, (list)):
# Should we ensure they are all strings??
cval = [str(v) for v in val]
return cval
if not isinstance(val, (str, basestring)):
val = str(val)
return [val]
# get a cfg entry by its path array
# for f['a']['b']: get_cfg_by_path(mycfg,('a','b'))
def get_cfg_by_path(yobj, keyp, default=None):
cur = yobj
for tok in keyp:
if tok not in cur:
return default
cur = cur[tok]
return cur
def fixup_output(cfg, mode):
(outfmt, errfmt) = get_output_cfg(cfg, mode)
redirect_output(outfmt, errfmt)
return (outfmt, errfmt)
# redirect_output(outfmt, errfmt, orig_out, orig_err)
# replace orig_out and orig_err with filehandles specified in outfmt or errfmt
# fmt can be:
# > FILEPATH
# >> FILEPATH
# | program [ arg1 [ arg2 [ ... ] ] ]
#
# with a '|', arguments are passed to shell, so one level of
# shell escape is required.
#
# if _CLOUD_INIT_SAVE_STDOUT is set in environment to a non empty and true
# value then output input will not be closed (useful for debugging).
#
def redirect_output(outfmt, errfmt, o_out=None, o_err=None):
if is_true(os.environ.get("_CLOUD_INIT_SAVE_STDOUT")):
LOG.debug("Not redirecting output due to _CLOUD_INIT_SAVE_STDOUT")
return
if not o_out:
o_out = sys.stdout
if not o_err:
o_err = sys.stderr
if outfmt:
LOG.debug("Redirecting %s to %s", o_out, outfmt)
(mode, arg) = outfmt.split(" ", 1)
if mode == ">" or mode == ">>":
owith = "ab"
if mode == ">":
owith = "wb"
new_fp = open(arg, owith)
elif mode == "|":
proc = subprocess.Popen(arg, shell=True, stdin=subprocess.PIPE)
new_fp = proc.stdin
else:
raise TypeError("Invalid type for output format: %s" % outfmt)
if o_out:
os.dup2(new_fp.fileno(), o_out.fileno())
if errfmt == outfmt:
LOG.debug("Redirecting %s to %s", o_err, outfmt)
os.dup2(new_fp.fileno(), o_err.fileno())
return
if errfmt:
LOG.debug("Redirecting %s to %s", o_err, errfmt)
(mode, arg) = errfmt.split(" ", 1)
if mode == ">" or mode == ">>":
owith = "ab"
if mode == ">":
owith = "wb"
new_fp = open(arg, owith)
elif mode == "|":
proc = subprocess.Popen(arg, shell=True, stdin=subprocess.PIPE)
new_fp = proc.stdin
else:
raise TypeError("Invalid type for error format: %s" % errfmt)
if o_err:
os.dup2(new_fp.fileno(), o_err.fileno())
def make_url(scheme, host, port=None,
path='', params='', query='', fragment=''):
pieces = []
pieces.append(scheme or '')
netloc = ''
if host:
netloc = str(host)
if port is not None:
netloc += ":" + "%s" % (port)
pieces.append(netloc or '')
pieces.append(path or '')
pieces.append(params or '')
pieces.append(query or '')
pieces.append(fragment or '')
return urlparse.urlunparse(pieces)
def obj_name(obj):
if isinstance(obj, (types.TypeType,
types.ModuleType,
types.FunctionType,
types.LambdaType)):
return str(obj.__name__)
return obj_name(obj.__class__)
def mergemanydict(srcs, reverse=False):
if reverse:
srcs = reversed(srcs)
m_cfg = {}
for a_cfg in srcs:
if a_cfg:
m_cfg = mergedict(m_cfg, a_cfg)
return m_cfg
def mergedict(src, cand):
"""
Merge values from C{cand} into C{src}.
If C{src} has a key C{cand} will not override.
Nested dictionaries are merged recursively.
"""
if isinstance(src, dict) and isinstance(cand, dict):
for (k, v) in cand.iteritems():
if k not in src:
src[k] = v
else:
src[k] = mergedict(src[k], v)
return src
@contextlib.contextmanager
def chdir(ndir):
curr = os.getcwd()
try:
os.chdir(ndir)
yield ndir
finally:
os.chdir(curr)
@contextlib.contextmanager
def umask(n_msk):
old = os.umask(n_msk)
try:
yield old
finally:
os.umask(old)
@contextlib.contextmanager
def tempdir(**kwargs):
# This seems like it was only added in python 3.2
# Make it since its useful...
# See: http://bugs.python.org/file12970/tempdir.patch
tdir = tempfile.mkdtemp(**kwargs)
try:
yield tdir
finally:
del_dir(tdir)
def center(text, fill, max_len):
return '{0:{fill}{align}{size}}'.format(text, fill=fill,
align="^", size=max_len)
def del_dir(path):
LOG.debug("Recursively deleting %s", path)
shutil.rmtree(path)
def runparts(dirp, skip_no_exist=True):
if skip_no_exist and not os.path.isdir(dirp):
return
failed = []
attempted = []
for exe_name in sorted(os.listdir(dirp)):
exe_path = os.path.join(dirp, exe_name)
if os.path.isfile(exe_path) and os.access(exe_path, os.X_OK):
attempted.append(exe_path)
try:
subp([exe_path], capture=False)
except ProcessExecutionError as e:
logexc(LOG, "Failed running %s [%s]", exe_path, e.exit_code)
failed.append(e)
if failed and attempted:
raise RuntimeError('Runparts: %s failures in %s attempted commands'
% (len(failed), len(attempted)))
# read_optional_seed
# returns boolean indicating success or failure (presense of files)
# if files are present, populates 'fill' dictionary with 'user-data' and
# 'meta-data' entries
def read_optional_seed(fill, base="", ext="", timeout=5):
try:
(md, ud) = read_seeded(base, ext, timeout)
fill['user-data'] = ud
fill['meta-data'] = md
return True
except OSError as e:
if e.errno == errno.ENOENT:
return False
raise
def read_file_or_url(url, timeout=5, retries=10, file_retries=0):
if url.startswith("/"):
url = "file://%s" % url
if url.startswith("file://"):
retries = file_retries
return uhelp.readurl(url, timeout=timeout, retries=retries)
def load_yaml(blob, default=None, allowed=(dict,)):
loaded = default
try:
blob = str(blob)
LOG.debug(("Attempting to load yaml from string "
"of length %s with allowed root types %s"),
len(blob), allowed)
converted = safeyaml.load(blob)
if not isinstance(converted, allowed):
# Yes this will just be caught, but thats ok for now...
raise TypeError(("Yaml load allows %s root types,"
" but got %s instead") %
(allowed, obj_name(converted)))
loaded = converted
except (yaml.YAMLError, TypeError, ValueError):
if len(blob) == 0:
LOG.debug("load_yaml given empty string, returning default")
else:
logexc(LOG, "Failed loading yaml blob")
return loaded
def read_seeded(base="", ext="", timeout=5, retries=10, file_retries=0):
if base.startswith("/"):
base = "file://%s" % base
# default retries for file is 0. for network is 10
if base.startswith("file://"):
retries = file_retries
if base.find("%s") >= 0:
ud_url = base % ("user-data" + ext)
md_url = base % ("meta-data" + ext)
else:
ud_url = "%s%s%s" % (base, "user-data", ext)
md_url = "%s%s%s" % (base, "meta-data", ext)
md_resp = read_file_or_url(md_url, timeout, retries, file_retries)
md = None
if md_resp.ok():
md_str = str(md_resp)
md = load_yaml(md_str, default={})
ud_resp = read_file_or_url(ud_url, timeout, retries, file_retries)
ud = None
if ud_resp.ok():
ud_str = str(ud_resp)
ud = ud_str
return (md, ud)
def read_conf_d(confd):
# Get reverse sorted list (later trumps newer)
confs = sorted(os.listdir(confd), reverse=True)
# Remove anything not ending in '.cfg'
confs = [f for f in confs if f.endswith(".cfg")]
# Remove anything not a file
confs = [f for f in confs
if os.path.isfile(os.path.join(confd, f))]
# Load them all so that they can be merged
cfgs = []
for fn in confs:
cfgs.append(read_conf(os.path.join(confd, fn)))
return mergemanydict(cfgs)
def read_conf_with_confd(cfgfile):
cfg = read_conf(cfgfile)
confd = False
if "conf_d" in cfg:
confd = cfg['conf_d']
if confd:
if not isinstance(confd, (str, basestring)):
raise TypeError(("Config file %s contains 'conf_d' "
"with non-string type %s") %
(cfgfile, obj_name(confd)))
else:
confd = str(confd).strip()
elif os.path.isdir("%s.d" % cfgfile):
confd = "%s.d" % cfgfile
if not confd or not os.path.isdir(confd):
return cfg
# Conf.d settings override input configuration
confd_cfg = read_conf_d(confd)
return mergedict(confd_cfg, cfg)
def read_cc_from_cmdline(cmdline=None):
# this should support reading cloud-config information from
# the kernel command line. It is intended to support content of the
# format:
# cc: <yaml content here> [end_cc]
# this would include:
# cc: ssh_import_id: [smoser, kirkland]\\n
# cc: ssh_import_id: [smoser, bob]\\nruncmd: [ [ ls, -l ], echo hi ] end_cc
# cc:ssh_import_id: [smoser] end_cc cc:runcmd: [ [ ls, -l ] ] end_cc
if cmdline is None:
cmdline = get_cmdline()
tag_begin = "cc:"
tag_end = "end_cc"
begin_l = len(tag_begin)
end_l = len(tag_end)
clen = len(cmdline)
tokens = []
begin = cmdline.find(tag_begin)
while begin >= 0:
end = cmdline.find(tag_end, begin + begin_l)
if end < 0:
end = clen
tokens.append(cmdline[begin + begin_l:end].lstrip().replace("\\n",
"\n"))
begin = cmdline.find(tag_begin, end + end_l)
return '\n'.join(tokens)
def dos2unix(contents):
# find first end of line
pos = contents.find('\n')
if pos <= 0 or contents[pos - 1] != '\r':
return contents
return contents.replace('\r\n', '\n')
def get_hostname_fqdn(cfg, cloud):
# return the hostname and fqdn from 'cfg'. If not found in cfg,
# then fall back to data from cloud
if "fqdn" in cfg:
# user specified a fqdn. Default hostname then is based off that
fqdn = cfg['fqdn']
hostname = get_cfg_option_str(cfg, "hostname", fqdn.split('.')[0])
else:
if "hostname" in cfg and cfg['hostname'].find('.') > 0:
# user specified hostname, and it had '.' in it
# be nice to them. set fqdn and hostname from that
fqdn = cfg['hostname']
hostname = cfg['hostname'][:fqdn.find('.')]
else:
# no fqdn set, get fqdn from cloud.
# get hostname from cfg if available otherwise cloud
fqdn = cloud.get_hostname(fqdn=True)
if "hostname" in cfg:
hostname = cfg['hostname']
else:
hostname = cloud.get_hostname()
return (hostname, fqdn)
def get_fqdn_from_hosts(hostname, filename="/etc/hosts"):
"""
For each host a single line should be present with
the following information:
IP_address canonical_hostname [aliases...]
Fields of the entry are separated by any number of blanks and/or tab
characters. Text from a "#" character until the end of the line is a
comment, and is ignored. Host names may contain only alphanumeric
characters, minus signs ("-"), and periods ("."). They must begin with
an alphabetic character and end with an alphanumeric character.
Optional aliases provide for name changes, alternate spellings, shorter
hostnames, or generic hostnames (for example, localhost).
"""
fqdn = None
try:
for line in load_file(filename).splitlines():
hashpos = line.find("#")
if hashpos >= 0:
line = line[0:hashpos]
line = line.strip()
if not line:
continue
# If there there is less than 3 entries
# (IP_address, canonical_hostname, alias)
# then ignore this line
toks = line.split()
if len(toks) < 3:
continue
if hostname in toks[2:]:
fqdn = toks[1]
break
except IOError:
pass
return fqdn
def get_cmdline_url(names=('cloud-config-url', 'url'),
starts="#cloud-config", cmdline=None):
if cmdline is None:
cmdline = get_cmdline()
data = keyval_str_to_dict(cmdline)
url = None
key = None
for key in names:
if key in data:
url = data[key]
break
if not url:
return (None, None, None)
resp = uhelp.readurl(url)
if resp.contents.startswith(starts) and resp.ok():
return (key, url, str(resp))
return (key, url, None)
def is_resolvable(name):
"""determine if a url is resolvable, return a boolean
This also attempts to be resilent against dns redirection.
Note, that normal nsswitch resolution is used here. So in order
to avoid any utilization of 'search' entries in /etc/resolv.conf
we have to append '.'.
The top level 'invalid' domain is invalid per RFC. And example.com
should also not exist. The random entry will be resolved inside
the search list.
"""
global _DNS_REDIRECT_IP # pylint: disable=W0603
if _DNS_REDIRECT_IP is None:
badips = set()
badnames = ("does-not-exist.example.com.", "example.invalid.",
rand_str())
badresults = {}
for iname in badnames:
try:
result = socket.getaddrinfo(iname, None, 0, 0,
socket.SOCK_STREAM, socket.AI_CANONNAME)
badresults[iname] = []
for (_fam, _stype, _proto, cname, sockaddr) in result:
badresults[iname].append("%s: %s" % (cname, sockaddr[0]))
badips.add(sockaddr[0])
except socket.gaierror:
pass
_DNS_REDIRECT_IP = badips
if badresults:
LOG.debug("detected dns redirection: %s" % badresults)
try:
result = socket.getaddrinfo(name, None)
# check first result's sockaddr field
addr = result[0][4][0]
if addr in _DNS_REDIRECT_IP:
return False
return True
except socket.gaierror:
return False
def get_hostname():
hostname = socket.gethostname()
return hostname
def is_resolvable_url(url):
"""determine if this url is resolvable (existing or ip)."""
return (is_resolvable(urlparse.urlparse(url).hostname))
def search_for_mirror(candidates):
"""
Search through a list of mirror urls for one that works
This needs to return quickly.
"""
for cand in candidates:
try:
if is_resolvable_url(cand):
return cand
except Exception:
pass
return None
def close_stdin():
"""
reopen stdin as /dev/null so even subprocesses or other os level things get
/dev/null as input.
if _CLOUD_INIT_SAVE_STDIN is set in environment to a non empty and true
value then input will not be closed (useful for debugging).
"""
if is_true(os.environ.get("_CLOUD_INIT_SAVE_STDIN")):
return
with open(os.devnull) as fp:
os.dup2(fp.fileno(), sys.stdin.fileno())
def find_devs_with(criteria=None, oformat='device',
tag=None, no_cache=False, path=None):
"""
find devices matching given criteria (via blkid)
criteria can be *one* of:
TYPE=<filesystem>
LABEL=<label>
UUID=<uuid>
"""
blk_id_cmd = ['blkid']
options = []
if criteria:
# Search for block devices with tokens named NAME that
# have the value 'value' and display any devices which are found.
# Common values for NAME include TYPE, LABEL, and UUID.
# If there are no devices specified on the command line,
# all block devices will be searched; otherwise,
# only search the devices specified by the user.
options.append("-t%s" % (criteria))
if tag:
# For each (specified) device, show only the tags that match tag.
options.append("-s%s" % (tag))
if no_cache:
# If you want to start with a clean cache
# (i.e. don't report devices previously scanned
# but not necessarily available at this time), specify /dev/null.
options.extend(["-c", "/dev/null"])
if oformat:
# Display blkid's output using the specified format.
# The format parameter may be:
# full, value, list, device, udev, export
options.append('-o%s' % (oformat))
if path:
options.append(path)
cmd = blk_id_cmd + options
# See man blkid for why 2 is added
(out, _err) = subp(cmd, rcs=[0, 2])
entries = []
for line in out.splitlines():
line = line.strip()
if line:
entries.append(line)
return entries
def peek_file(fname, max_bytes):
LOG.debug("Peeking at %s (max_bytes=%s)", fname, max_bytes)
with open(fname, 'rb') as ifh:
return ifh.read(max_bytes)
def uniq_list(in_list):
out_list = []
for i in in_list:
if i in out_list:
continue
else:
out_list.append(i)
return out_list
def load_file(fname, read_cb=None, quiet=False):
LOG.debug("Reading from %s (quiet=%s)", fname, quiet)
ofh = StringIO()
try:
with open(fname, 'rb') as ifh:
pipe_in_out(ifh, ofh, chunk_cb=read_cb)
except IOError as e:
if not quiet:
raise
if e.errno != errno.ENOENT:
raise
contents = ofh.getvalue()
LOG.debug("Read %s bytes from %s", len(contents), fname)
return contents
def get_cmdline():
if 'DEBUG_PROC_CMDLINE' in os.environ:
cmdline = os.environ["DEBUG_PROC_CMDLINE"]
else:
try:
cmdline = load_file("/proc/cmdline").strip()
except:
cmdline = ""
return cmdline
def pipe_in_out(in_fh, out_fh, chunk_size=1024, chunk_cb=None):
bytes_piped = 0
while True:
data = in_fh.read(chunk_size)
if data == '':
break
else:
out_fh.write(data)
bytes_piped += len(data)
if chunk_cb:
chunk_cb(bytes_piped)
out_fh.flush()
return bytes_piped
def chownbyid(fname, uid=None, gid=None):
if uid in [None, -1] and gid in [None, -1]:
# Nothing to do
return
LOG.debug("Changing the ownership of %s to %s:%s", fname, uid, gid)
os.chown(fname, uid, gid)
def chownbyname(fname, user=None, group=None):
uid = -1
gid = -1
try:
if user:
uid = pwd.getpwnam(user).pw_uid
if group:
gid = grp.getgrnam(group).gr_gid
except KeyError as e:
raise OSError("Unknown user or group: %s" % (e))
chownbyid(fname, uid, gid)
# Always returns well formated values
# cfg is expected to have an entry 'output' in it, which is a dictionary
# that includes entries for 'init', 'config', 'final' or 'all'
# init: /var/log/cloud.out
# config: [ ">> /var/log/cloud-config.out", /var/log/cloud-config.err ]
# final:
# output: "| logger -p"
# error: "> /dev/null"
# this returns the specific 'mode' entry, cleanly formatted, with value
def get_output_cfg(cfg, mode):
ret = [None, None]
if not cfg or not 'output' in cfg:
return ret
outcfg = cfg['output']
if mode in outcfg:
modecfg = outcfg[mode]
else:
if 'all' not in outcfg:
return ret
# if there is a 'all' item in the output list
# then it applies to all users of this (init, config, final)
modecfg = outcfg['all']
# if value is a string, it specifies stdout and stderr
if isinstance(modecfg, str):
ret = [modecfg, modecfg]
# if its a list, then we expect (stdout, stderr)
if isinstance(modecfg, list):
if len(modecfg) > 0:
ret[0] = modecfg[0]
if len(modecfg) > 1:
ret[1] = modecfg[1]
# if it is a dictionary, expect 'out' and 'error'
# items, which indicate out and error
if isinstance(modecfg, dict):
if 'output' in modecfg:
ret[0] = modecfg['output']
if 'error' in modecfg:
ret[1] = modecfg['error']
# if err's entry == "&1", then make it same as stdout
# as in shell syntax of "echo foo >/dev/null 2>&1"
if ret[1] == "&1":
ret[1] = ret[0]
swlist = [">>", ">", "|"]
for i in range(len(ret)):
if not ret[i]:
continue
val = ret[i].lstrip()
found = False
for s in swlist:
if val.startswith(s):
val = "%s %s" % (s, val[len(s):].strip())
found = True
break
if not found:
# default behavior is append
val = "%s %s" % (">>", val.strip())
ret[i] = val
return ret
def logexc(log, msg, *args):
# Setting this here allows this to change
# levels easily (not always error level)
# or even desirable to have that much junk
# coming out to a non-debug stream
if msg:
log.warn(msg, *args)
# Debug gets the full trace
log.debug(msg, exc_info=1, *args)
def hash_blob(blob, routine, mlen=None):
hasher = hashlib.new(routine)
hasher.update(blob)
digest = hasher.hexdigest()
# Don't get to long now
if mlen is not None:
return digest[0:mlen]
else:
return digest
def is_user(name):
try:
if pwd.getpwnam(name):
return True
except KeyError:
return False
def is_group(name):
try:
if grp.getgrnam(name):
return True
except KeyError:
return False
def rename(src, dest):
LOG.debug("Renaming %s to %s", src, dest)
# TODO(harlowja) use a se guard here??
os.rename(src, dest)
def ensure_dirs(dirlist, mode=0755):
for d in dirlist:
ensure_dir(d, mode)
def read_write_cmdline_url(target_fn):
if not os.path.exists(target_fn):
try:
(key, url, content) = get_cmdline_url()
except:
logexc(LOG, "Failed fetching command line url")
return
try:
if key and content:
write_file(target_fn, content, mode=0600)
LOG.debug(("Wrote to %s with contents of command line"
" url %s (len=%s)"), target_fn, url, len(content))
elif key and not content:
LOG.debug(("Command line key %s with url"
" %s had no contents"), key, url)
except:
logexc(LOG, "Failed writing url content to %s", target_fn)
def yaml_dumps(obj):
formatted = yaml.dump(obj,
line_break="\n",
indent=4,
explicit_start=True,
explicit_end=True,
default_flow_style=False)
return formatted
def ensure_dir(path, mode=None):
if not os.path.isdir(path):
# Make the dir and adjust the mode
with SeLinuxGuard(os.path.dirname(path), recursive=True):
os.makedirs(path)
chmod(path, mode)
else:
# Just adjust the mode
chmod(path, mode)
@contextlib.contextmanager
def unmounter(umount):
try:
yield umount
finally:
if umount:
umount_cmd = ["umount", '-l', umount]
subp(umount_cmd)
def mounts():
mounted = {}
try:
# Go through mounts to see what is already mounted
mount_locs = load_file("/proc/mounts").splitlines()
for mpline in mount_locs:
# Format at: man fstab
try:
(dev, mp, fstype, opts, _freq, _passno) = mpline.split()
except:
continue
# If the name of the mount point contains spaces these
# can be escaped as '\040', so undo that..
mp = mp.replace("\\040", " ")
mounted[dev] = {
'fstype': fstype,
'mountpoint': mp,
'opts': opts,
}
LOG.debug("Fetched %s mounts from %s", mounted, "/proc/mounts")
except (IOError, OSError):
logexc(LOG, "Failed fetching mount points from /proc/mounts")
return mounted
def mount_cb(device, callback, data=None, rw=False, mtype=None, sync=True):
"""
Mount the device, call method 'callback' passing the directory
in which it was mounted, then unmount. Return whatever 'callback'
returned. If data != None, also pass data to callback.
"""
mounted = mounts()
with tempdir() as tmpd:
umount = False
if device in mounted:
mountpoint = mounted[device]['mountpoint']
else:
try:
mountcmd = ['mount']
mountopts = []
if rw:
mountopts.append('rw')
else:
mountopts.append('ro')
if sync:
# This seems like the safe approach to do
# (ie where this is on by default)
mountopts.append("sync")
if mountopts:
mountcmd.extend(["-o", ",".join(mountopts)])
if mtype:
mountcmd.extend(['-t', mtype])
mountcmd.append(device)
mountcmd.append(tmpd)
subp(mountcmd)
umount = tmpd # This forces it to be unmounted (when set)
mountpoint = tmpd
except (IOError, OSError) as exc:
raise MountFailedError(("Failed mounting %s "
"to %s due to: %s") %
(device, tmpd, exc))
# Be nice and ensure it ends with a slash
if not mountpoint.endswith("/"):
mountpoint += "/"
with unmounter(umount):
if data is None:
ret = callback(mountpoint)
else:
ret = callback(mountpoint, data)
return ret
def get_builtin_cfg():
# Deep copy so that others can't modify
return obj_copy.deepcopy(CFG_BUILTIN)
def sym_link(source, link):
LOG.debug("Creating symbolic link from %r => %r" % (link, source))
os.symlink(source, link)
def del_file(path):
LOG.debug("Attempting to remove %s", path)
try:
os.unlink(path)
except OSError as e:
if e.errno != errno.ENOENT:
raise e
def copy(src, dest):
LOG.debug("Copying %s to %s", src, dest)
shutil.copy(src, dest)
def time_rfc2822():
try:
ts = time.strftime("%a, %d %b %Y %H:%M:%S %z", time.gmtime())
except:
ts = "??"
return ts
def uptime():
uptime_str = '??'
try:
contents = load_file("/proc/uptime").strip()
if contents:
uptime_str = contents.split()[0]
except:
logexc(LOG, "Unable to read uptime from /proc/uptime")
return uptime_str
def append_file(path, content):
write_file(path, content, omode="ab", mode=None)
def ensure_file(path, mode=0644):
write_file(path, content='', omode="ab", mode=mode)
def safe_int(possible_int):
try:
return int(possible_int)
except (ValueError, TypeError):
return None
def chmod(path, mode):
real_mode = safe_int(mode)
if path and real_mode:
with SeLinuxGuard(path):
os.chmod(path, real_mode)
def write_file(filename, content, mode=0644, omode="wb"):
"""
Writes a file with the given content and sets the file mode as specified.
Resotres the SELinux context if possible.
@param filename: The full path of the file to write.
@param content: The content to write to the file.
@param mode: The filesystem mode to set on the file.
@param omode: The open mode used when opening the file (r, rb, a, etc.)
"""
ensure_dir(os.path.dirname(filename))
LOG.debug("Writing to %s - %s: [%s] %s bytes",
filename, omode, mode, len(content))
with SeLinuxGuard(path=filename):
with open(filename, omode) as fh:
fh.write(content)
fh.flush()
chmod(filename, mode)
def delete_dir_contents(dirname):
"""
Deletes all contents of a directory without deleting the directory itself.
@param dirname: The directory whose contents should be deleted.
"""
for node in os.listdir(dirname):
node_fullpath = os.path.join(dirname, node)
if os.path.isdir(node_fullpath):
del_dir(node_fullpath)
else:
del_file(node_fullpath)
def subp(args, data=None, rcs=None, env=None, capture=True, shell=False,
logstring=False):
if rcs is None:
rcs = [0]
try:
if not logstring:
LOG.debug(("Running command %s with allowed return codes %s"
" (shell=%s, capture=%s)"), args, rcs, shell, capture)
else:
LOG.debug(("Running hidden command to protect sensitive "
"input/output logstring: %s"), logstring)
if not capture:
stdout = None
stderr = None
else:
stdout = subprocess.PIPE
stderr = subprocess.PIPE
stdin = subprocess.PIPE
sp = subprocess.Popen(args, stdout=stdout,
stderr=stderr, stdin=stdin,
env=env, shell=shell)
(out, err) = sp.communicate(data)
except OSError as e:
raise ProcessExecutionError(cmd=args, reason=e)
rc = sp.returncode
if rc not in rcs:
raise ProcessExecutionError(stdout=out, stderr=err,
exit_code=rc,
cmd=args)
# Just ensure blank instead of none?? (iff capturing)
if not out and capture:
out = ''
if not err and capture:
err = ''
return (out, err)
def make_header(comment_char="#", base='created'):
ci_ver = version.version_string()
header = str(comment_char)
header += " %s by cloud-init v. %s" % (base.title(), ci_ver)
header += " on %s" % time_rfc2822()
return header
def abs_join(*paths):
return os.path.abspath(os.path.join(*paths))
# shellify, takes a list of commands
# for each entry in the list
# if it is an array, shell protect it (with single ticks)
# if it is a string, do nothing
def shellify(cmdlist, add_header=True):
content = ''
if add_header:
content += "#!/bin/sh\n"
escaped = "%s%s%s%s" % ("'", '\\', "'", "'")
cmds_made = 0
for args in cmdlist:
# If the item is a list, wrap all items in single tick.
# If its not, then just write it directly.
if isinstance(args, list):
fixed = []
for f in args:
fixed.append("'%s'" % (str(f).replace("'", escaped)))
content = "%s%s\n" % (content, ' '.join(fixed))
cmds_made += 1
elif isinstance(args, (str, basestring)):
content = "%s%s\n" % (content, args)
cmds_made += 1
else:
raise RuntimeError(("Unable to shellify type %s"
" which is not a list or string")
% (obj_name(args)))
LOG.debug("Shellified %s commands.", cmds_made)
return content
def is_container():
"""
Checks to see if this code running in a container of some sort
"""
for helper in CONTAINER_TESTS:
try:
# try to run a helper program. if it returns true/zero
# then we're inside a container. otherwise, no
subp([helper])
return True
except (IOError, OSError):
pass
# this code is largely from the logic in
# ubuntu's /etc/init/container-detect.conf
try:
# Detect old-style libvirt
# Detect OpenVZ containers
pid1env = get_proc_env(1)
if "container" in pid1env:
return True
if "LIBVIRT_LXC_UUID" in pid1env:
return True
except (IOError, OSError):
pass
# Detect OpenVZ containers
if os.path.isdir("/proc/vz") and not os.path.isdir("/proc/bc"):
return True
try:
# Detect Vserver containers
lines = load_file("/proc/self/status").splitlines()
for line in lines:
if line.startswith("VxID:"):
(_key, val) = line.strip().split(":", 1)
if val != "0":
return True
except (IOError, OSError):
pass
return False
def get_proc_env(pid):
"""
Return the environment in a dict that a given process id was started with.
"""
env = {}
fn = os.path.join("/proc/", str(pid), "environ")
try:
contents = load_file(fn)
toks = contents.split("\0")
for tok in toks:
if tok == "":
continue
(name, val) = tok.split("=", 1)
if name:
env[name] = val
except (IOError, OSError):
pass
return env
def keyval_str_to_dict(kvstring):
ret = {}
for tok in kvstring.split():
try:
(key, val) = tok.split("=", 1)
except ValueError:
key = tok
val = True
ret[key] = val
return ret
|