Commit | Line | Data |
---|---|---|
00b3cd10 PG |
1 | #!/usr/bin/env python3 |
2 | ||
3 | """ | |
83f2d71e | 4 | Intra2net 2017 |
00b3cd10 PG |
5 | |
6 | =============================================================================== | |
704ceaa5 | 7 | crypto -- Encryption Layer for the Deltatar Backup |
00b3cd10 PG |
8 | =============================================================================== |
9 | ||
10 | Crypto stack: | |
11 | ||
12 | - AES-GCM for the symmetric encryption; | |
13 | - Scrypt as KDF. | |
14 | ||
15 | References: | |
16 | ||
17 | - NIST Recommendation for Block Cipher Modes of Operation: Galois/Counter | |
18 | Mode (GCM) and GMAC | |
19 | http://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-38d.pdf | |
20 | ||
21 | - AES-GCM v1: | |
22 | https://cryptome.org/2014/01/aes-gcm-v1.pdf | |
23 | ||
24 | - Authentication weaknesses in GCM | |
25 | http://csrc.nist.gov/groups/ST/toolkit/BCM/documents/comments/CWC-GCM/Ferguson2.pdf | |
26 | ||
6d08915c PG |
27 | Errors |
28 | ------------------------------------------------------------------------------- | |
29 | ||
30 | Errors fall into roughly three categories: | |
31 | ||
704ceaa5 | 32 | - Cryptographical errors or invalid data. |
6d08915c PG |
33 | |
34 | - ``InvalidGCMTag`` (decryption failed on account of an invalid GCM | |
35 | tag), | |
36 | - ``InvalidIVFixedPart`` (IV fixed part of object not found in list), | |
f6cd676f | 37 | - ``DuplicateIV`` (the IV of an encrypted object already occurred), |
704ceaa5 PG |
38 | - ``DecryptionError`` (used in CLI decryption for presenting error |
39 | conditions to the user). | |
6d08915c PG |
40 | |
41 | - Incorrect usage of the library. | |
42 | ||
43 | - ``InvalidParameter`` (non-conforming user supplied parameter), | |
44 | - ``InvalidHeader`` (data passed for reading not parsable into header), | |
45 | - ``FormatError`` (cannot handle header or parameter version), | |
46 | - ``RuntimeError``. | |
47 | ||
48 | - Bad internal state. If one of these is encountered it means that a state | |
49 | was reached that shouldn’t occur during normal processing. | |
50 | ||
51 | - ``InternalError``, | |
52 | - ``Unreachable``. | |
53 | ||
54 | Also, ``EndOfFile`` is used as a sentinel to communicate that a stream supplied | |
55 | for reading is exhausted. | |
56 | ||
f6cd676f PG |
57 | Initialization Vectors |
58 | ------------------------------------------------------------------------------- | |
59 | ||
817cfffa | 60 | Initialization vectors are checked for reuse during the lifetime of a decryptor. |
704ceaa5 PG |
61 | The fixed counters for metadata files cannot be reused and attempts to do so |
62 | will cause a DuplicateIV error. This means the length of objects encrypted with | |
63 | a metadata counter is capped at 63 GB. | |
64 | ||
65 | For ordinary, non-metadata payload, there is an optional mode with strict IV | |
66 | checking that causes a crypto context to fail if an IV encountered or created | |
67 | was already used for decrypting or encrypting, respectively, an earlier object. | |
68 | Note that this mode can trigger false positives when decrypting non-linearly, | |
69 | e. g. when traversing the same object multiple times. Since the crypto context | |
70 | has no notion of a position in a PDT encrypted archive, this condition must be | |
71 | sorted out downstream. | |
72 | ||
66b1c6f4 PG |
73 | When encrypting with more than one Encrypt context special care must be taken |
74 | to prevent accidental reuse of IVs. The builtin protection against reuse is | |
75 | only effective for objects encrypted with the same Encrypt handle. If multiple | |
76 | Encrypt handles are used to encrypt with the same combination of password and | |
77 | salt, the encryption becomes susceptible to birthday attacks (bound = 2^32 due | |
78 | to the 64-bit random iv). Thus the use of multiple handles is discouraged. | |
79 | ||
80 | ||
704ceaa5 PG |
81 | Command Line Utility |
82 | ------------------------------------------------------------------------------- | |
83 | ||
84 | ``crypto.py`` may be invoked as a script for decrypting, validating, and | |
85 | splitting PDT encrypted files. Consult the usage message for details. | |
86 | ||
87 | Usage examples: | |
88 | ||
89 | Decrypt from stdin using the password ‘foo’: :: | |
90 | ||
91 | $ crypto.py process foo -i - -o - <some-file.tar.gz.pdtcrypt >some-file.tar.gz | |
92 | ||
93 | Output verbose information about the encrypted objects in the archive: :: | |
94 | ||
95 | $ crypto.py process foo -v -i some-file.tar.gz.pdtcrypt -o /dev/null | |
96 | PDT: decrypt from some-file.tar.gz.pdtcrypt | |
97 | PDT: decrypt to /dev/null | |
98 | PDT: source: file some-file.tar.gz.pdtcrypt | |
99 | PDT: sink: file /dev/null | |
100 | PDT: 0 hdr | |
101 | PDT: · version = 1 : 0100 | |
102 | PDT: · paramversion = 1 : 0100 | |
103 | PDT: · nacl : d270 b031 00d1 87e2 c946 610d 7b7f 7e5f | |
104 | PDT: · iv : 02ee 3dd7 a963 1eb1 0100 0000 | |
105 | PDT: · ctsize = 591 : 4f02 0000 0000 0000 | |
106 | PDT: · tag : 5b2d 6d8b 8f82 4842 12fd 0b10 b6e3 369b | |
107 | PDT: 64 decrypt obj no. 1, 591 B | |
108 | PDT: · [64] 0% done, read block (591 B of 591 B remaining) | |
109 | PDT: · decrypt ciphertext 591 B | |
110 | PDT: · decrypt plaintext 591 B | |
111 | PDT: 655 finalize | |
112 | … | |
113 | ||
114 | Also, the mode *scrypt* allows deriving encryption keys. To calculate the | |
115 | encryption key from the password ‘foo’ and the salt of the first object in a | |
116 | PDT encrypted file: :: | |
117 | ||
118 | $ crypto.py scrypt foo -i some-file.pdtcrypt | |
4f6405d6 | 119 | {"paramversion": 1, "salt": "Cqzbk48e3peEjzWto8D0yA==", "key": "JH9EkMwaM4x9F5aim5gK/Q=="} |
704ceaa5 PG |
120 | |
121 | The computed 16 byte key is given in hexadecimal notation in the value to | |
122 | ``hash`` and can be fed into Python’s ``binascii.unhexlify()`` to obtain the | |
123 | corresponding binary representation. | |
124 | ||
125 | Note that in Scrypt hashing mode, no data integrity checks are being performed. | |
126 | If the wrong password is given, a wrong key will be derived. Whether the password | |
127 | was indeed correct can only be determined by decrypting. Note that since PDT | |
128 | archives essentially consist of a stream of independent objects, the salt and | |
129 | other parameters may change. Thus a key derived using above method from the | |
130 | first object doesn’t necessarily apply to any of the subsequent objects. | |
f6cd676f | 131 | |
00b3cd10 PG |
132 | """ |
133 | ||
7b3940e5 | 134 | import base64 |
00b3cd10 | 135 | import binascii |
50710d86 | 136 | import bisect |
00b3cd10 PG |
137 | import ctypes |
138 | import io | |
c46c8670 | 139 | from functools import reduce, partial |
f41973a6 | 140 | import mmap |
00b3cd10 PG |
141 | import os |
142 | import struct | |
a808459e | 143 | import stat |
00b3cd10 PG |
144 | import sys |
145 | import time | |
da82bc58 | 146 | import types |
2a307f41 | 147 | import errno |
00b3cd10 PG |
148 | try: |
149 | import enum34 | |
150 | except ImportError as exn: | |
151 | pass | |
152 | ||
6257d5b3 | 153 | if __name__ == "__main__": ## Work around the import mechanism lest Python’s |
00b3cd10 PG |
154 | pwd = os.getcwd() ## preference for local imports causes a cyclical |
155 | ## import (crypto → pylibscrypt → […] → ./tarfile → crypto). | |
156 | sys.path = [ p for p in sys.path if p.find ("deltatar") < 0 ] | |
157 | ||
158 | import pylibscrypt | |
159 | from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes | |
160 | from cryptography.hazmat.backends import default_backend | |
15d3eefd | 161 | import cryptography |
00b3cd10 PG |
162 | |
163 | ||
a64085a8 | 164 | __all__ = [ "hdr_make", "hdr_read", "hdr_fmt", "hdr_fmt_pretty" |
b360b772 | 165 | , "scrypt_hashfile" |
3031b7ae PG |
166 | , "PDTCRYPT_HDR_SIZE", "AES_GCM_IV_CNT_DATA" |
167 | , "AES_GCM_IV_CNT_INFOFILE", "AES_GCM_IV_CNT_INDEX" | |
2d6fd8c8 | 168 | ] |
00b3cd10 | 169 | |
a393d9cb PG |
170 | |
171 | ############################################################################### | |
15d3eefd PG |
172 | ## exceptions |
173 | ############################################################################### | |
174 | ||
175 | class EndOfFile (Exception): | |
176 | """Reached EOF.""" | |
ae3d0f2a PG |
177 | remainder = 0 |
178 | msg = 0 | |
8a8ac469 | 179 | def __init__ (self, n=None, msg=None): |
5d394c0d PG |
180 | if n is not None: |
181 | self.remainder = n | |
182 | self.msg = msg | |
15d3eefd | 183 | |
b0078f26 | 184 | |
b12110dd PG |
185 | class InvalidParameter (Exception): |
186 | """Inputs not valid for PDT encryption.""" | |
187 | pass | |
188 | ||
b0078f26 | 189 | |
15d3eefd PG |
190 | class InvalidHeader (Exception): |
191 | """Header not valid.""" | |
192 | pass | |
193 | ||
b0078f26 PG |
194 | |
195 | class InvalidGCMTag (Exception): | |
196 | """ | |
197 | The GCM tag calculated during decryption differs from that in the object | |
198 | header. | |
199 | """ | |
200 | pass | |
201 | ||
202 | ||
26b42ad4 | 203 | class InvalidIVFixedPart (Exception): |
89ec6e2f PG |
204 | """ |
205 | IV fixed part not in supplied list: either the backup is corrupt or the | |
206 | current object does not belong to it. | |
207 | """ | |
26b42ad4 PG |
208 | pass |
209 | ||
b0078f26 | 210 | |
be124bca | 211 | class IVFixedPartError (Exception): |
89ec6e2f PG |
212 | """ |
213 | Error creating a unique IV fixed part: repeated calls to system RNG yielded | |
214 | the same sequence of bytes as the last IV used. | |
215 | """ | |
be124bca PG |
216 | pass |
217 | ||
218 | ||
fac2cfe1 | 219 | class InvalidFileCounter (Exception): |
89ec6e2f PG |
220 | """ |
221 | When encrypting, an attempted reuse of a dedicated counter (info file, | |
222 | index file) was caught. | |
223 | """ | |
fac2cfe1 PG |
224 | pass |
225 | ||
226 | ||
ee6aa239 | 227 | class DuplicateIV (Exception): |
89ec6e2f PG |
228 | """ |
229 | During encryption, the current IV fixed part is identical to an already | |
230 | existing IV (same prefix and file counter). This indicates tampering or | |
231 | programmer error and cannot be recovered from. | |
232 | """ | |
ee6aa239 PG |
233 | pass |
234 | ||
235 | ||
236 | class NonConsecutiveIV (Exception): | |
89ec6e2f PG |
237 | """ |
238 | IVs not numbered consecutively. This is a hard error with strict IV | |
239 | checking. Precludes random access to the encrypted objects. | |
240 | """ | |
ee6aa239 PG |
241 | pass |
242 | ||
243 | ||
58ed14b8 PG |
244 | class CiphertextTooLong (Exception): |
245 | """ | |
246 | An attempt was made to decrypt more data than the ciphertext size declared | |
247 | in the object header. | |
248 | """ | |
249 | pass | |
250 | ||
251 | ||
b12110dd PG |
252 | class FormatError (Exception): |
253 | """Unusable parameters in header.""" | |
254 | pass | |
255 | ||
b0078f26 | 256 | |
15d3eefd | 257 | class DecryptionError (Exception): |
89ec6e2f | 258 | """Error during decryption with ``crypto.py`` on the command line.""" |
15d3eefd PG |
259 | pass |
260 | ||
b0078f26 | 261 | |
70ad9458 | 262 | class Unreachable (Exception): |
89ec6e2f PG |
263 | """ |
264 | Makeshift __builtin_unreachable(); always a programmer error if | |
265 | thrown. | |
266 | """ | |
70ad9458 PG |
267 | pass |
268 | ||
b0078f26 | 269 | |
b12110dd PG |
270 | class InternalError (Exception): |
271 | """Errors not ascribable to bad user inputs or cryptography.""" | |
272 | pass | |
273 | ||
15d3eefd PG |
274 | |
275 | ############################################################################### | |
a393d9cb PG |
276 | ## crypto layer version |
277 | ############################################################################### | |
278 | ||
279 | ENCRYPTION_PARAMETERS = \ | |
c46c8670 | 280 | { 0: \ |
dd23cbc9 PG |
281 | { "kdf": ("dummy", 16) |
282 | , "enc": "passthrough" } | |
c46c8670 | 283 | , 1: \ |
dd23cbc9 PG |
284 | { "kdf": ( "scrypt" |
285 | , { "dkLen" : 16 | |
286 | , "N" : 1 << 16 | |
287 | , "r" : 8 | |
288 | , "p" : 1 | |
289 | , "NaCl_LEN" : 16 }) | |
290 | , "enc": "aes-gcm" } } | |
a393d9cb | 291 | |
6110ef14 PG |
292 | # Mode zero is unencrypted and only provided for testing purposes. nless |
293 | # the encryptor / decryptor are explicitly instructed to do so. | |
294 | MIN_SECURE_PARAMETERS = 1 | |
295 | ||
00b3cd10 PG |
296 | ############################################################################### |
297 | ## constants | |
298 | ############################################################################### | |
299 | ||
dd47d6a2 | 300 | PDTCRYPT_HDR_MAGIC = b"PDTCRYPT" |
00b3cd10 | 301 | |
dd47d6a2 PG |
302 | PDTCRYPT_HDR_SIZE_MAGIC = 8 # 8 |
303 | PDTCRYPT_HDR_SIZE_VERSION = 2 # 10 | |
304 | PDTCRYPT_HDR_SIZE_PARAMVERSION = 2 # 12 | |
305 | PDTCRYPT_HDR_SIZE_NACL = 16 # 28 | |
306 | PDTCRYPT_HDR_SIZE_IV = 12 # 40 | |
307 | PDTCRYPT_HDR_SIZE_CTSIZE = 8 # 48 | |
308 | PDTCRYPT_HDR_SIZE_TAG = 16 # 64 GCM auth tag | |
00b3cd10 | 309 | |
dd47d6a2 PG |
310 | PDTCRYPT_HDR_SIZE = PDTCRYPT_HDR_SIZE_MAGIC + PDTCRYPT_HDR_SIZE_VERSION \ |
311 | + PDTCRYPT_HDR_SIZE_PARAMVERSION + PDTCRYPT_HDR_SIZE_NACL \ | |
312 | + PDTCRYPT_HDR_SIZE_IV + PDTCRYPT_HDR_SIZE_CTSIZE \ | |
313 | + PDTCRYPT_HDR_SIZE_TAG # = 64 | |
00b3cd10 PG |
314 | |
315 | # precalculate offsets since Python can’t do constant folding over names | |
dd47d6a2 PG |
316 | HDR_OFF_VERSION = PDTCRYPT_HDR_SIZE_MAGIC |
317 | HDR_OFF_PARAMVERSION = HDR_OFF_VERSION + PDTCRYPT_HDR_SIZE_VERSION | |
318 | HDR_OFF_NACL = HDR_OFF_PARAMVERSION + PDTCRYPT_HDR_SIZE_PARAMVERSION | |
319 | HDR_OFF_IV = HDR_OFF_NACL + PDTCRYPT_HDR_SIZE_NACL | |
320 | HDR_OFF_CTSIZE = HDR_OFF_IV + PDTCRYPT_HDR_SIZE_IV | |
321 | HDR_OFF_TAG = HDR_OFF_CTSIZE + PDTCRYPT_HDR_SIZE_CTSIZE | |
00b3cd10 PG |
322 | |
323 | FMT_UINT16_LE = "<H" | |
324 | FMT_UINT64_LE = "<Q" | |
50710d86 | 325 | FMT_I2N_IV = "<8sL" # 8 random bytes ‖ 32 bit counter |
83f2d71e PG |
326 | FMT_I2N_HDR = ("<" # host byte order |
327 | "8s" # magic | |
328 | "H" # version | |
329 | "H" # paramversion | |
330 | "16s" # sodium chloride | |
331 | "12s" # iv | |
3b53fb98 PG |
332 | "Q" # size |
333 | "16s") # GCM tag | |
00b3cd10 PG |
334 | |
335 | # aes+gcm | |
addcec42 PG |
336 | AES_KEY_SIZE = 16 # b"0123456789abcdef" |
337 | AES_KEY_SIZE_B64 = 24 # b'MDEyMzQ1Njc4OWFiY2RlZg==' | |
c89d123c TJ |
338 | |
339 | AES_GCM_MAX_SIZE = (1 << 36) - (1 << 5) # 2^39 - 2^8 b ≅ 64 GB. | |
340 | # Source: NIST SP 800-38D section 5.2.1.1 | |
341 | # https://crypto.stackexchange.com/questions/31793/plain-text-size-limits-for-aes-gcm-mode-just-64gb | |
342 | ||
cb7a3911 PG |
343 | PDTCRYPT_MAX_OBJ_SIZE_DEFAULT = 63 * (1 << 30) # 63 GB |
344 | PDTCRYPT_MAX_OBJ_SIZE = PDTCRYPT_MAX_OBJ_SIZE_DEFAULT | |
00b3cd10 | 345 | |
3031b7ae | 346 | # index and info files are written on-the fly while encrypting so their |
817cfffa | 347 | # counters must be available in advance |
cb7a3911 PG |
348 | AES_GCM_IV_CNT_INFOFILE = 1 # constant |
349 | AES_GCM_IV_CNT_INDEX = AES_GCM_IV_CNT_INFOFILE + 1 | |
350 | AES_GCM_IV_CNT_DATA = AES_GCM_IV_CNT_INDEX + 1 # also for multivolume | |
351 | AES_GCM_IV_CNT_MAX_DEFAULT = 0xffFFffFF | |
352 | AES_GCM_IV_CNT_MAX = AES_GCM_IV_CNT_MAX_DEFAULT | |
2d6fd8c8 | 353 | |
be124bca PG |
354 | # IV structure and generation |
355 | PDTCRYPT_IV_GEN_MAX_RETRIES = 10 # × | |
356 | PDTCRYPT_IV_FIXEDPART_SIZE = 8 # B | |
357 | PDTCRYPT_IV_COUNTER_SIZE = 4 # B | |
39accaaa | 358 | |
addcec42 PG |
359 | # secret type: PW of string | KEY of char [16] |
360 | PDTCRYPT_SECRET_PW = 0 | |
361 | PDTCRYPT_SECRET_KEY = 1 | |
362 | ||
00b3cd10 | 363 | ############################################################################### |
39accaaa | 364 | ## header, trailer |
00b3cd10 PG |
365 | ############################################################################### |
366 | # | |
367 | # Interface: | |
368 | # | |
369 | # struct hdrinfo | |
370 | # { version : u16 | |
371 | # , paramversion : u16 | |
372 | # , nacl : [u8; 16] | |
373 | # , iv : [u8; 12] | |
704ceaa5 PG |
374 | # , ctsize : usize |
375 | # , tag : [u8; 16] } | |
83f2d71e | 376 | # |
00b3cd10 | 377 | # fn hdr_read (f : handle) -> hdrinfo; |
c2d1c3ec | 378 | # fn hdr_make (f : handle, h : hdrinfo) -> IOResult<usize>; |
00b3cd10 PG |
379 | # fn hdr_fmt (h : hdrinfo) -> String; |
380 | # | |
381 | ||
83f2d71e | 382 | def hdr_read (data): |
704ceaa5 PG |
383 | """ |
384 | Read bytes as header structure. | |
385 | ||
386 | If the input could not be interpreted as a header, fail with | |
387 | ``InvalidHeader``. | |
388 | """ | |
83f2d71e | 389 | |
00b3cd10 | 390 | try: |
3b53fb98 | 391 | mag, version, paramversion, nacl, iv, ctsize, tag = \ |
83f2d71e PG |
392 | struct.unpack (FMT_I2N_HDR, data) |
393 | except Exception as exn: | |
15d3eefd PG |
394 | raise InvalidHeader ("error unpacking header from [%r]: %s" |
395 | % (binascii.hexlify (data), str (exn))) | |
00b3cd10 | 396 | |
dd47d6a2 | 397 | if mag != PDTCRYPT_HDR_MAGIC: |
15d3eefd | 398 | raise InvalidHeader ("bad magic in header: expected [%s], got [%s]" |
dd47d6a2 | 399 | % (PDTCRYPT_HDR_MAGIC, mag)) |
00b3cd10 | 400 | |
15d3eefd | 401 | return \ |
00b3cd10 PG |
402 | { "version" : version |
403 | , "paramversion" : paramversion | |
404 | , "nacl" : nacl | |
405 | , "iv" : iv | |
406 | , "ctsize" : ctsize | |
3b53fb98 | 407 | , "tag" : tag |
00b3cd10 PG |
408 | } |
409 | ||
410 | ||
39accaaa | 411 | def hdr_read_stream (instr): |
704ceaa5 PG |
412 | """ |
413 | Read header from stream at the current position. | |
414 | ||
415 | Fail with ``InvalidHeader`` if insufficient bytes were read from the | |
416 | stream, or if the content could not be interpreted as a header. | |
417 | """ | |
dd47d6a2 | 418 | data = instr.read(PDTCRYPT_HDR_SIZE) |
ae3d0f2a | 419 | ldata = len (data) |
8a8ac469 PG |
420 | if ldata == 0: |
421 | raise EndOfFile | |
422 | elif ldata != PDTCRYPT_HDR_SIZE: | |
423 | raise InvalidHeader ("hdr_read_stream: expected %d B, received %d B" | |
424 | % (PDTCRYPT_HDR_SIZE, ldata)) | |
47e27926 | 425 | return hdr_read (data) |
39accaaa PG |
426 | |
427 | ||
3b53fb98 | 428 | def hdr_from_params (version, paramversion, nacl, iv, ctsize, tag): |
704ceaa5 PG |
429 | """ |
430 | Assemble the necessary values into a PDTCRYPT header. | |
431 | ||
432 | :type version: int to fit uint16_t | |
433 | :type paramversion: int to fit uint16_t | |
434 | :type nacl: bytes to fit uint8_t[16] | |
435 | :type iv: bytes to fit uint8_t[12] | |
436 | :type size: int to fit uint64_t | |
437 | :type tag: bytes to fit uint8_t[16] | |
438 | """ | |
dd47d6a2 | 439 | buf = bytearray (PDTCRYPT_HDR_SIZE) |
83f2d71e | 440 | bufv = memoryview (buf) |
00b3cd10 | 441 | |
00b3cd10 | 442 | try: |
83f2d71e | 443 | struct.pack_into (FMT_I2N_HDR, bufv, 0, |
dd47d6a2 | 444 | PDTCRYPT_HDR_MAGIC, |
3b53fb98 | 445 | version, paramversion, nacl, iv, ctsize, tag) |
83f2d71e | 446 | except Exception as exn: |
a83fa4ed | 447 | return False, "error assembling header: %s" % str (exn) |
00b3cd10 | 448 | |
83f2d71e | 449 | return True, bytes (buf) |
00b3cd10 | 450 | |
00b3cd10 | 451 | |
8a990744 PG |
452 | def hdr_make_dummy (s): |
453 | """ | |
454 | Create a header sized block of bytes initialized to a value derived from a | |
455 | string. Used to verify we’ve jumped back correctly to the actual position | |
456 | of the object header. | |
457 | """ | |
458 | c = reduce (lambda a, c: a + ord(c), s, 0) % 0xFF | |
dd47d6a2 | 459 | return bytes (bytearray (struct.pack ("B", c)) * PDTCRYPT_HDR_SIZE) |
8a990744 PG |
460 | |
461 | ||
a393d9cb | 462 | def hdr_make (hdr): |
704ceaa5 PG |
463 | """ |
464 | Assemble a header from the given header structure. | |
465 | """ | |
a393d9cb PG |
466 | return hdr_from_params (version=hdr.get("version"), |
467 | paramversion=hdr.get("paramversion"), | |
468 | nacl=hdr.get("nacl"), iv=hdr.get("iv"), | |
3b53fb98 | 469 | ctsize=hdr.get("ctsize"), tag=hdr.get("tag")) |
a393d9cb PG |
470 | |
471 | ||
83f2d71e | 472 | HDR_FMT = "I2n_header { version: %d, paramversion: %d, nacl: %s[%d]," \ |
89131745 | 473 | " iv: %s[%d], ctsize: %d, tag: %s[%d] }" |
00b3cd10 | 474 | |
83f2d71e | 475 | def hdr_fmt (h): |
704ceaa5 | 476 | """Format a header structure into readable output.""" |
83f2d71e PG |
477 | return HDR_FMT % (h["version"], h["paramversion"], |
478 | binascii.hexlify (h["nacl"]), len(h["nacl"]), | |
479 | binascii.hexlify (h["iv"]), len(h["iv"]), | |
db1f3ac7 PG |
480 | h["ctsize"], |
481 | binascii.hexlify (h["tag"]), len(h["tag"])) | |
00b3cd10 | 482 | |
00b3cd10 | 483 | |
83f2d71e | 484 | def hex_spaced_of_bytes (b): |
704ceaa5 | 485 | """Format bytes object, hexdump style.""" |
83f2d71e PG |
486 | return " ".join ([ "%.2x%.2x" % (c1, c2) |
487 | for c1, c2 in zip (b[0::2], b[1::2]) ]) \ | |
488 | + (len (b) | 1 == len (b) and " %.2x" % b[-1] or "") # odd lengths | |
00b3cd10 | 489 | |
591a722f | 490 | |
3031b7ae PG |
491 | def hdr_iv_counter (h): |
492 | """Extract the variable part of the IV of the given header.""" | |
493 | _fixed, cnt = struct.unpack (FMT_I2N_IV, h ["iv"]) | |
494 | return cnt | |
495 | ||
496 | ||
497 | def hdr_iv_fixed (h): | |
498 | """Extract the fixed part of the IV of the given header.""" | |
499 | fixed, _cnt = struct.unpack (FMT_I2N_IV, h ["iv"]) | |
500 | return fixed | |
501 | ||
502 | ||
83f2d71e | 503 | hdr_dump = hex_spaced_of_bytes |
00b3cd10 | 504 | |
00b3cd10 | 505 | |
15d3eefd PG |
506 | HDR_FMT_PRETTY = \ |
507 | """version = %-4d : %s | |
508 | paramversion = %-4d : %s | |
509 | nacl : %s | |
510 | iv : %s | |
511 | ctsize = %-20d : %s | |
512 | tag : %s | |
83f2d71e | 513 | """ |
00b3cd10 | 514 | |
83f2d71e | 515 | def hdr_fmt_pretty (h): |
704ceaa5 PG |
516 | """ |
517 | Format header structure into multi-line representation of its contents and | |
518 | their raw representation. (Omit the implicit “PDTCRYPT” magic bytes that | |
519 | precede every header.) | |
520 | """ | |
83f2d71e PG |
521 | return HDR_FMT_PRETTY \ |
522 | % (h["version"], | |
523 | hex_spaced_of_bytes (struct.pack (FMT_UINT16_LE, h["version"])), | |
524 | h["paramversion"], | |
525 | hex_spaced_of_bytes (struct.pack (FMT_UINT16_LE, h["paramversion"])), | |
526 | hex_spaced_of_bytes (h["nacl"]), | |
527 | hex_spaced_of_bytes (h["iv"]), | |
528 | h["ctsize"], | |
15d3eefd PG |
529 | hex_spaced_of_bytes (struct.pack (FMT_UINT64_LE, h["ctsize"])), |
530 | hex_spaced_of_bytes (h["tag"])) | |
00b3cd10 | 531 | |
f6cd676f PG |
532 | IV_FMT = "((f %s) (c %d))" |
533 | ||
534 | def iv_fmt (iv): | |
704ceaa5 | 535 | """Format the two components of an IV in a readable fashion.""" |
f6cd676f PG |
536 | fixed, cnt = struct.unpack (FMT_I2N_IV, iv) |
537 | return IV_FMT % (binascii.hexlify (fixed), cnt) | |
538 | ||
00b3cd10 | 539 | |
00b3cd10 | 540 | ############################################################################### |
f41973a6 PG |
541 | ## restoration |
542 | ############################################################################### | |
543 | ||
544 | class Location (object): | |
545 | n = 0 | |
546 | offset = 0 | |
547 | ||
548 | def restore_loc_fmt (loc): | |
549 | return "%d off:%d" \ | |
550 | % (loc.n, loc.offset) | |
551 | ||
552 | def locate_hdr_candidates (fd): | |
553 | """ | |
554 | Walk over instances of the magic string in the payload, collecting their | |
555 | positions. If the offset of the first found instance is not zero, the file | |
d52e2737 | 556 | begins with leading garbage. Used by desaster recovery. |
f41973a6 PG |
557 | |
558 | :return: The list of offsets in the file. | |
559 | """ | |
560 | cands = [] | |
561 | ||
562 | mm = mmap.mmap(fd, 0, mmap.MAP_SHARED, mmap.PROT_READ) | |
563 | pos = 0 | |
564 | while True: | |
565 | pos = mm.find (PDTCRYPT_HDR_MAGIC, pos) | |
566 | if pos == -1: | |
567 | break | |
568 | cands.append (pos) | |
569 | pos += 1 | |
570 | ||
571 | return cands | |
572 | ||
573 | ||
6c8073ab PG |
574 | HDR_CAND_GOOD = 0 # header marks begin of valid object |
575 | HDR_CAND_FISHY = 1 # inconclusive (tag mismatch, obj overlap etc.) | |
576 | HDR_CAND_JUNK = 2 # not a header / object unreadable | |
577 | ||
5ed4c57d PG |
578 | HDR_VERDICT_NAME = \ |
579 | { HDR_CAND_GOOD : "valid" | |
580 | , HDR_CAND_FISHY : "fishy" | |
581 | , HDR_CAND_JUNK : "junk" | |
582 | } | |
583 | ||
584 | ||
585 | def verdict_fmt (vdt): | |
586 | return HDR_VERDICT_NAME [vdt] | |
587 | ||
6c8073ab PG |
588 | |
589 | def inspect_hdr (fd, off): | |
590 | """ | |
591 | Attempt to parse a header in *fd* at position *off*. | |
592 | ||
593 | Returns a verdict about the quality of that header plus the parsed header | |
594 | when readable. | |
595 | """ | |
596 | ||
597 | _ = os.lseek (fd, off, os.SEEK_SET) | |
598 | ||
599 | if os.lseek (fd, 0, os.SEEK_CUR) != off: | |
600 | if PDTCRYPT_VERBOSE is True: | |
601 | noise ("PDT: %d → dismissed (lseek() past EOF)" % off) | |
602 | return HDR_CAND_JUNK, None | |
603 | ||
604 | raw = os.read (fd, PDTCRYPT_HDR_SIZE) | |
605 | if len (raw) != PDTCRYPT_HDR_SIZE: | |
606 | if PDTCRYPT_VERBOSE is True: | |
607 | noise ("PDT: %d → dismissed (EOF inside header)" % off) | |
608 | return HDR_CAND_JUNK, None | |
609 | ||
610 | try: | |
611 | hdr = hdr_read (raw) | |
612 | except InvalidHeader as exn: | |
613 | if PDTCRYPT_VERBOSE is True: | |
614 | noise ("PDT: %d → dismissed (invalid: [%s])" % (off, str (exn))) | |
615 | return HDR_CAND_JUNK, None | |
616 | ||
617 | obj0 = off + PDTCRYPT_HDR_SIZE | |
618 | objX = obj0 + hdr ["ctsize"] | |
619 | ||
620 | eof = os.lseek (fd, 0, os.SEEK_END) | |
621 | if eof < objX: | |
622 | if PDTCRYPT_VERBOSE is True: | |
623 | noise ("PDT: %d → EOF inside object (%d≤%d≤%d); adjusting size to " | |
624 | "%d" % (off, obj0, eof, objX, (eof - obj0))) | |
625 | # try reading up to the end | |
626 | hdr ["ctsize"] = eof - obj0 | |
627 | return HDR_CAND_FISHY, hdr | |
628 | ||
629 | return HDR_CAND_GOOD, hdr | |
630 | ||
631 | ||
a808459e | 632 | def try_decrypt (ifd, off, hdr, secret, ofd=-1): |
6c8073ab | 633 | """ |
a808459e PG |
634 | Attempt to decrypt the object in the (seekable) descriptor *ifd* starting |
635 | at *off* using the metadata in *hdr* and *secret*. An output fd can be | |
636 | specified with *ofd*; if it is *-1* – the default –, the decrypted payload | |
637 | will be discarded. | |
70a33834 PG |
638 | |
639 | Always creates a fresh decryptor, so validation steps across objects don’t | |
640 | apply. | |
202104ed | 641 | |
d52e2737 | 642 | Errors during GCM tag validation are ignored. Used by desaster recovery. |
6c8073ab | 643 | """ |
70a33834 PG |
644 | ctleft = hdr ["ctsize"] |
645 | pos = off | |
646 | ||
647 | ks = secret [0] | |
648 | if ks == PDTCRYPT_SECRET_PW: | |
649 | decr = Decrypt (password=secret [1]) | |
650 | elif ks == PDTCRYPT_SECRET_KEY: | |
6257d5b3 | 651 | key = secret [1] |
70a33834 PG |
652 | decr = Decrypt (key=key) |
653 | else: | |
654 | raise RuntimeError | |
655 | ||
70a33834 PG |
656 | decr.next (hdr) |
657 | ||
658 | try: | |
a808459e | 659 | os.lseek (ifd, pos, os.SEEK_SET) |
37ccf5bc | 660 | pt = b"" |
70a33834 PG |
661 | while ctleft > 0: |
662 | cnksiz = min (ctleft, PDTCRYPT_BLOCKSIZE) | |
a808459e | 663 | cnk = os.read (ifd, cnksiz) |
70a33834 PG |
664 | ctleft -= cnksiz |
665 | pos += cnksiz | |
a808459e PG |
666 | pt = decr.process (cnk) |
667 | if ofd != -1: | |
668 | os.write (ofd, pt) | |
202104ed PG |
669 | try: |
670 | pt = decr.done () | |
671 | except InvalidGCMTag: | |
672 | noise ("PDT: GCM tag mismatch for object %d–%d" | |
673 | % (off, off + hdr ["ctsize"])) | |
a808459e PG |
674 | if len (pt) > 0 and ofd != -1: |
675 | os.write (ofd, pt) | |
70a33834 | 676 | |
70a33834 PG |
677 | except Exception as exn: |
678 | noise ("PDT: error decrypting object %d–%d@%d, %d B remaining [%s]" | |
679 | % (off, off + hdr ["ctsize"], pos, ctleft, exn)) | |
680 | raise | |
6c8073ab | 681 | |
70a33834 | 682 | return pos - off |
6c8073ab PG |
683 | |
684 | ||
6690f5e0 PG |
685 | def readable_objects_offsets (ifd, secret, cands): |
686 | """ | |
687 | From a list of candidates, locate the ones that mark the start of actual | |
688 | readable PDTCRYPT objects. | |
689 | """ | |
690 | good = [] | |
24afaf18 PG |
691 | |
692 | for i, cand in enumerate (cands): | |
6690f5e0 PG |
693 | vdt, hdr = inspect_hdr (ifd, cand) |
694 | if vdt == HDR_CAND_JUNK: | |
695 | pass # ignore unreadable ones | |
696 | elif vdt in [HDR_CAND_GOOD, HDR_CAND_FISHY]: | |
24afaf18 | 697 | ctsize = hdr ["ctsize"] |
6690f5e0 | 698 | off0 = cand + PDTCRYPT_HDR_SIZE |
24afaf18 | 699 | ok = try_decrypt (ifd, off0, hdr, secret) == ctsize |
6690f5e0 | 700 | if ok is True: |
24afaf18 PG |
701 | good.append ((cand, off0 + ctsize)) |
702 | ||
703 | overlap = find_overlaps (good) | |
704 | ||
705 | return [ g [0] for g in good ] | |
6690f5e0 PG |
706 | |
707 | ||
708 | def reconstruct_offsets (fname, secret): | |
709 | ifd = os.open (fname, os.O_RDONLY) | |
710 | ||
711 | try: | |
712 | cands = locate_hdr_candidates (ifd) | |
713 | return readable_objects_offsets (ifd, secret, cands) | |
714 | finally: | |
715 | os.close (ifd) | |
716 | ||
717 | ||
f41973a6 | 718 | ############################################################################### |
addcec42 PG |
719 | ## helpers |
720 | ############################################################################### | |
721 | ||
722 | def make_secret (password=None, key=None): | |
723 | """ | |
724 | Safely create a “secret” value that consists either of a key or a password. | |
725 | Inputs are validated: the password is accepted as (UTF-8 encoded) bytes or | |
726 | string; for the key only a bytes object of the proper size or a base64 | |
727 | encoded string thereof is accepted. | |
728 | ||
729 | If both are provided, the key is preferred over the password; no checks are | |
730 | performed whether the key is derived from the password. | |
731 | ||
732 | :returns: secret value if inputs were acceptable | None otherwise. | |
733 | """ | |
734 | if key is not None: | |
735 | if isinstance (key, str) is True: | |
736 | key = key.encode ("utf-8") | |
737 | if isinstance (key, bytes) is True: | |
738 | if len (key) == AES_KEY_SIZE: | |
739 | return (PDTCRYPT_SECRET_KEY, key) | |
6257d5b3 PG |
740 | if len (key) == AES_KEY_SIZE * 2: |
741 | try: | |
742 | key = binascii.unhexlify (key) | |
743 | return (PDTCRYPT_SECRET_KEY, key) | |
744 | except binascii.Error: # garbage in string | |
745 | pass | |
addcec42 PG |
746 | if len (key) == AES_KEY_SIZE_B64: |
747 | try: | |
748 | key = base64.b64decode (key) | |
749 | # the base64 processor is very tolerant and allows for | |
6257d5b3 | 750 | # arbitrary trailing and leading data thus the data obtained |
addcec42 PG |
751 | # must be checked for the proper length |
752 | if len (key) == AES_KEY_SIZE: | |
753 | return (PDTCRYPT_SECRET_KEY, key) | |
754 | except binascii.Error: # “incorrect padding” | |
755 | pass | |
756 | elif password is not None: | |
757 | if isinstance (password, str) is True: | |
758 | return (PDTCRYPT_SECRET_PW, password) | |
759 | elif isinstance (password, bytes) is True: | |
760 | try: | |
761 | password = password.decode ("utf-8") | |
762 | return (PDTCRYPT_SECRET_PW, password) | |
763 | except UnicodeDecodeError: | |
764 | pass | |
765 | ||
766 | return None | |
767 | ||
768 | ||
769 | ############################################################################### | |
6178061e PG |
770 | ## passthrough / null encryption |
771 | ############################################################################### | |
772 | ||
773 | class PassthroughCipher (object): | |
774 | ||
775 | tag = struct.pack ("<QQ", 0, 0) | |
776 | ||
777 | def __init__ (self) : pass | |
778 | ||
779 | def update (self, b) : return b | |
780 | ||
50710d86 | 781 | def finalize (self) : return b"" |
6178061e PG |
782 | |
783 | def finalize_with_tag (self, _) : return b"" | |
784 | ||
785 | ############################################################################### | |
a393d9cb | 786 | ## convenience wrapper |
00b3cd10 PG |
787 | ############################################################################### |
788 | ||
c46c8670 PG |
789 | |
790 | def kdf_dummy (klen, password, _nacl): | |
704ceaa5 PG |
791 | """ |
792 | Fake KDF for testing purposes that is called when parameter version zero is | |
793 | encountered. | |
794 | """ | |
c46c8670 PG |
795 | q, r = divmod (klen, len (password)) |
796 | if isinstance (password, bytes) is False: | |
797 | password = password.encode () | |
798 | return password * q + password [:r], b"" | |
799 | ||
800 | ||
801 | SCRYPT_KEY_MEMO = { } # static because needed for both the info file and the archive | |
802 | ||
803 | ||
804 | def kdf_scrypt (params, password, nacl): | |
704ceaa5 PG |
805 | """ |
806 | Wrapper for the Scrypt KDF, corresponds to parameter version one. The | |
807 | computation result is memoized based on the inputs to facilitate spawning | |
808 | multiple encryption contexts. | |
809 | """ | |
c46c8670 PG |
810 | N = params["N"] |
811 | r = params["r"] | |
812 | p = params["p"] | |
813 | dkLen = params["dkLen"] | |
814 | ||
815 | if nacl is None: | |
816 | nacl = os.urandom (params["NaCl_LEN"]) | |
817 | ||
818 | key_parms = (password, nacl, N, r, p, dkLen) | |
819 | global SCRYPT_KEY_MEMO | |
820 | if key_parms not in SCRYPT_KEY_MEMO: | |
821 | SCRYPT_KEY_MEMO [key_parms] = \ | |
822 | pylibscrypt.scrypt (password, nacl, N, r, p, dkLen) | |
823 | return SCRYPT_KEY_MEMO [key_parms], nacl | |
a64085a8 PG |
824 | |
825 | ||
da82bc58 | 826 | def kdf_by_version (paramversion=None, defs=None): |
704ceaa5 PG |
827 | """ |
828 | Pick the KDF handler corresponding to the parameter version or the | |
829 | definition set. | |
830 | ||
831 | :rtype: function (password : str, nacl : str) -> str | |
832 | """ | |
da82bc58 PG |
833 | if paramversion is not None: |
834 | defs = ENCRYPTION_PARAMETERS.get(paramversion, None) | |
a64085a8 | 835 | if defs is None: |
1ed44e7b PG |
836 | raise InvalidParameter ("no encryption parameters for version %r" |
837 | % paramversion) | |
a64085a8 | 838 | (kdf, params) = defs["kdf"] |
c46c8670 PG |
839 | fn = None |
840 | if kdf == "scrypt" : fn = kdf_scrypt | |
a2dd68b9 | 841 | elif kdf == "dummy" : fn = kdf_dummy |
c46c8670 | 842 | if fn is None: |
a64085a8 | 843 | raise ValueError ("key derivation method %r unknown" % kdf) |
c46c8670 | 844 | return partial (fn, params) |
a64085a8 PG |
845 | |
846 | ||
b360b772 PG |
847 | ############################################################################### |
848 | ## SCRYPT hashing | |
849 | ############################################################################### | |
850 | ||
851 | def scrypt_hashsource (pw, ins): | |
852 | """ | |
853 | Calculate the SCRYPT hash from the password and the information contained | |
854 | in the first header found in ``ins``. | |
855 | ||
856 | This does not validate whether the first object is encrypted correctly. | |
857 | """ | |
c1ecc2e2 PG |
858 | if isinstance (pw, str) is True: |
859 | pw = str.encode (pw) | |
860 | elif isinstance (pw, bytes) is False: | |
861 | raise InvalidParameter ("password must be a string, not %s" | |
1ae49141 | 862 | % type (pw)) |
c1ecc2e2 PG |
863 | if isinstance (ins, io.BufferedReader) is False and \ |
864 | isinstance (ins, io.FileIO) is False: | |
865 | raise InvalidParameter ("file to hash must be opened in “binary” mode") | |
b360b772 PG |
866 | hdr = None |
867 | try: | |
868 | hdr = hdr_read_stream (ins) | |
869 | except EndOfFile as exn: | |
870 | noise ("PDT: malformed input: end of file reading first object header") | |
871 | noise ("PDT:") | |
872 | return 1 | |
873 | ||
874 | nacl = hdr ["nacl"] | |
875 | pver = hdr ["paramversion"] | |
876 | if PDTCRYPT_VERBOSE is True: | |
877 | noise ("PDT: salt of first object : %s" % binascii.hexlify (nacl)) | |
878 | noise ("PDT: parameter version of archive : %d" % pver) | |
879 | ||
880 | try: | |
881 | defs = ENCRYPTION_PARAMETERS.get(pver, None) | |
882 | kdfname, params = defs ["kdf"] | |
883 | if kdfname != "scrypt": | |
884 | noise ("PDT: input is not an SCRYPT archive") | |
885 | noise ("") | |
886 | return 1 | |
887 | kdf = kdf_by_version (None, defs) | |
888 | except ValueError as exn: | |
889 | noise ("PDT: object has unknown parameter version %d" % pver) | |
890 | ||
891 | hsh, _void = kdf (pw, nacl) | |
892 | ||
c1ecc2e2 | 893 | return hsh, nacl, hdr ["version"], pver |
b360b772 PG |
894 | |
895 | ||
896 | def scrypt_hashfile (pw, fname): | |
704ceaa5 PG |
897 | """ |
898 | Calculate the SCRYPT hash from the password and the information contained | |
899 | in the first header found in the given file. The header is read only at | |
900 | offset zero. | |
901 | """ | |
b360b772 | 902 | with deptdcrypt_mk_stream (PDTCRYPT_SOURCE, fname or "-") as ins: |
c1ecc2e2 | 903 | hsh, _void, _void, _void = scrypt_hashsource (pw, ins) |
b360b772 PG |
904 | return hsh |
905 | ||
906 | ||
907 | ############################################################################### | |
908 | ## AES-GCM context | |
909 | ############################################################################### | |
910 | ||
a393d9cb PG |
911 | class Crypto (object): |
912 | """ | |
913 | Encryption context to remain alive throughout an entire tarfile pass. | |
914 | """ | |
6178061e | 915 | enc = None |
a393d9cb PG |
916 | nacl = None |
917 | key = None | |
50710d86 PG |
918 | cnt = None # file counter (uint32_t != 0) |
919 | iv = None # current IV | |
30019abf PG |
920 | fixed = None # accu for 64 bit fixed parts of IV |
921 | used_ivs = None # tracks IVs | |
922 | strict_ivs = False # if True, panic on duplicate object IV | |
48db09ba PG |
923 | password = None |
924 | paramversion = None | |
6110ef14 | 925 | insecure = False # allow plaintext parameters |
633b18a9 PG |
926 | stats = { "in" : 0 |
927 | , "out" : 0 | |
928 | , "obj" : 0 } | |
fa47412e | 929 | |
fa47412e PG |
930 | ctsize = -1 |
931 | ptsize = -1 | |
3031b7ae PG |
932 | info_counter_used = False |
933 | index_counter_used = False | |
a393d9cb | 934 | |
a64085a8 | 935 | def __init__ (self, *al, **akv): |
30019abf | 936 | self.used_ivs = set () |
a64085a8 | 937 | self.set_parameters (*al, **akv) |
39accaaa PG |
938 | |
939 | ||
704ceaa5 | 940 | def next_fixed (self): |
be124bca | 941 | # NOP for decryption |
50710d86 PG |
942 | pass |
943 | ||
944 | ||
945 | def set_object_counter (self, cnt=None): | |
704ceaa5 PG |
946 | """ |
947 | Safely set the internal counter of encrypted objects. Numerous | |
948 | constraints apply: | |
949 | ||
950 | The same counter may not be reused in combination with one IV fixed | |
951 | part. This is validated elsewhere in the IV handling. | |
952 | ||
953 | Counter zero is invalid. The first two counters are reserved for | |
954 | metadata. The implementation does not allow for splitting metadata | |
955 | files over multiple encrypted objects. (This would be possible by | |
956 | assigning new fixed parts.) Thus in a Deltatar backup there is at most | |
957 | one object with a counter value of one and two. On creation of a | |
958 | context, the initial counter may be chosen. The globals | |
959 | ``AES_GCM_IV_CNT_INFOFILE`` and ``AES_GCM_IV_CNT_INDEX`` can be used to | |
960 | request one of the reserved values. If one of these values has been | |
961 | used, any further attempt of setting the counter to that value will | |
962 | be rejected with an ``InvalidFileCounter`` exception. | |
963 | ||
964 | Out of bounds values (i. e. below one and more than the maximum of 2³²) | |
965 | cause an ``InvalidParameter`` exception to be thrown. | |
966 | """ | |
50710d86 PG |
967 | if cnt is None: |
968 | self.cnt = AES_GCM_IV_CNT_DATA | |
969 | return | |
970 | if cnt == 0 or cnt > AES_GCM_IV_CNT_MAX + 1: | |
b12110dd PG |
971 | raise InvalidParameter ("invalid counter value %d requested: " |
972 | "acceptable values are from 1 to %d" | |
973 | % (cnt, AES_GCM_IV_CNT_MAX)) | |
50710d86 PG |
974 | if cnt == AES_GCM_IV_CNT_INFOFILE: |
975 | if self.info_counter_used is True: | |
fac2cfe1 PG |
976 | raise InvalidFileCounter ("attempted to reuse info file " |
977 | "counter %d: must be unique" % cnt) | |
50710d86 | 978 | self.info_counter_used = True |
3031b7ae PG |
979 | elif cnt == AES_GCM_IV_CNT_INDEX: |
980 | if self.index_counter_used is True: | |
fac2cfe1 | 981 | raise InvalidFileCounter ("attempted to reuse index file " |
66b1c6f4 | 982 | "counter %d: must be unique" % cnt) |
3031b7ae | 983 | self.index_counter_used = True |
50710d86 PG |
984 | if cnt <= AES_GCM_IV_CNT_MAX: |
985 | self.cnt = cnt | |
986 | return | |
987 | # cnt == AES_GCM_IV_CNT_MAX + 1 → wrap | |
988 | self.cnt = AES_GCM_IV_CNT_DATA | |
704ceaa5 | 989 | self.next_fixed () |
50710d86 PG |
990 | |
991 | ||
1f3fd7b0 | 992 | def set_parameters (self, password=None, key=None, paramversion=None, |
6110ef14 PG |
993 | nacl=None, counter=None, strict_ivs=False, |
994 | insecure=False): | |
704ceaa5 PG |
995 | """ |
996 | Configure the internal state of a crypto context. Not intended for | |
997 | external use. | |
6110ef14 PG |
998 | |
999 | A parameter version indicating passthrough (plaintext) mode is rejected | |
1000 | with an ``InvalidParameter`` unless ``insecure`` is set. | |
704ceaa5 | 1001 | """ |
be124bca | 1002 | self.next_fixed () |
50710d86 | 1003 | self.set_object_counter (counter) |
30019abf PG |
1004 | self.strict_ivs = strict_ivs |
1005 | ||
6110ef14 PG |
1006 | self.insecure = insecure |
1007 | ||
a83fa4ed | 1008 | if paramversion is not None: |
6110ef14 PG |
1009 | if self.insecure is False \ |
1010 | and paramversion < MIN_SECURE_PARAMETERS: | |
1011 | raise InvalidParameter \ | |
1012 | ("set_parameters: requested parameter version %d but " | |
1013 | "plaintext encryption disallowed in secure context!" | |
1014 | % paramversion) | |
a83fa4ed PG |
1015 | self.paramversion = paramversion |
1016 | ||
1f3fd7b0 PG |
1017 | if key is not None: |
1018 | self.key, self.nacl = key, nacl | |
1019 | return | |
1020 | ||
a83fa4ed PG |
1021 | if password is not None: |
1022 | if isinstance (password, bytes) is False: | |
1023 | password = str.encode (password) | |
1024 | self.password = password | |
1025 | if paramversion is None and nacl is None: | |
1026 | # postpone key setup until first header is available | |
1027 | return | |
1028 | kdf = kdf_by_version (paramversion) | |
1029 | if kdf is not None: | |
1030 | self.key, self.nacl = kdf (password, nacl) | |
fa47412e | 1031 | |
39accaaa | 1032 | |
39accaaa | 1033 | def process (self, buf): |
704ceaa5 PG |
1034 | """ |
1035 | Encrypt / decrypt a buffer. Invokes the ``.update()`` method on the | |
1036 | wrapped encryptor or decryptor, respectively. | |
1037 | ||
1038 | The Cryptography exception ``AlreadyFinalized`` is translated to an | |
1039 | ``InternalError`` at this point. It may occur in sound code when the GC | |
1040 | closes an encrypting stream after an error. Everywhere else it must be | |
1041 | treated as a bug. | |
1042 | """ | |
cb7a3911 PG |
1043 | if self.enc is None: |
1044 | raise RuntimeError ("process: context not initialized") | |
1045 | self.stats ["in"] += len (buf) | |
fac2cfe1 PG |
1046 | try: |
1047 | out = self.enc.update (buf) | |
1048 | except cryptography.exceptions.AlreadyFinalized as exn: | |
1049 | raise InternalError (exn) | |
cb7a3911 PG |
1050 | self.stats ["out"] += len (out) |
1051 | return out | |
39accaaa PG |
1052 | |
1053 | ||
30019abf | 1054 | def next (self, password, paramversion, nacl, iv): |
704ceaa5 PG |
1055 | """ |
1056 | Prepare for encrypting another object: Reset the data counters and | |
1057 | change the configuration in case one of the variable parameters differs | |
1058 | from the last object. Also check the IV for duplicates and error out | |
1059 | if strict checking was requested. | |
1060 | """ | |
fa47412e PG |
1061 | self.ctsize = 0 |
1062 | self.ptsize = 0 | |
1063 | self.stats ["obj"] += 1 | |
30019abf PG |
1064 | |
1065 | self.check_duplicate_iv (iv) | |
1066 | ||
6178061e PG |
1067 | if ( self.paramversion != paramversion |
1068 | or self.password != password | |
1069 | or self.nacl != nacl): | |
1f3fd7b0 | 1070 | self.set_parameters (password=password, paramversion=paramversion, |
6110ef14 PG |
1071 | nacl=nacl, strict_ivs=self.strict_ivs, |
1072 | insecure=self.insecure) | |
30019abf PG |
1073 | |
1074 | ||
1075 | def check_duplicate_iv (self, iv): | |
704ceaa5 PG |
1076 | """ |
1077 | Add an IV (the 12 byte representation as in the header) to the list. With | |
1078 | strict checking enabled, this will throw a ``DuplicateIV``. Depending on | |
1079 | the context, this may indicate a serious error (IV reuse). | |
1080 | """ | |
30019abf PG |
1081 | if self.strict_ivs is True and iv in self.used_ivs: |
1082 | raise DuplicateIV ("iv %s was reused" % iv_fmt (iv)) | |
1083 | # vi has not been used before; add to collection | |
1084 | self.used_ivs.add (iv) | |
fa47412e PG |
1085 | |
1086 | ||
633b18a9 | 1087 | def counters (self): |
704ceaa5 PG |
1088 | """ |
1089 | Access the data counters. | |
1090 | """ | |
633b18a9 PG |
1091 | return self.stats ["obj"], self.stats ["in"], self.stats ["out"] |
1092 | ||
1093 | ||
8de91f4f PG |
1094 | def drop (self): |
1095 | """ | |
1096 | Clear the current context regardless of its finalization state. The | |
1097 | next operation must be ``.next()``. | |
1098 | """ | |
1099 | self.enc = None | |
1100 | ||
1101 | ||
66b1c6f4 PG |
1102 | def get_used_ivs (self): |
1103 | """ | |
1104 | Get the set of IVs that were used so far during the lifetime of | |
1105 | this context. Useful to check for IV reuse if multiple encryption | |
1106 | contexts were used independently. | |
1107 | """ | |
1108 | return self.used_ivs | |
1109 | ||
1110 | ||
39accaaa PG |
1111 | class Encrypt (Crypto): |
1112 | ||
48db09ba PG |
1113 | lastinfo = None |
1114 | version = None | |
72a42219 | 1115 | paramenc = None |
50710d86 | 1116 | |
1f3fd7b0 | 1117 | def __init__ (self, version, paramversion, password=None, key=None, nacl=None, |
6110ef14 | 1118 | counter=AES_GCM_IV_CNT_DATA, strict_ivs=True, insecure=False): |
704ceaa5 PG |
1119 | """ |
1120 | The ctor will throw immediately if one of the parameters does not conform | |
1121 | to our expectations. | |
1122 | ||
704ceaa5 PG |
1123 | :type version: int to fit uint16_t |
1124 | :type paramversion: int to fit uint16_t | |
1125 | :param password: mutually exclusive with ``key`` | |
1126 | :type password: bytes | |
1127 | :param key: mutually exclusive with ``password`` | |
1128 | :type key: bytes | |
1129 | :type nacl: bytes | |
1130 | :type counter: initial object counter the values | |
1131 | ``AES_GCM_IV_CNT_INFOFILE`` and | |
1132 | ``AES_GCM_IV_CNT_INDEX`` are unique in each backup set | |
1133 | and cannot be reused even with different fixed parts. | |
1134 | :type strict_ivs: bool | |
6110ef14 | 1135 | :type insecure: bool, whether to permit passthrough mode |
66b1c6f4 PG |
1136 | |
1137 | *Security considerations*: The ``class Encrypt`` handle guarantees that | |
1138 | all random parts (first eight bytes) of the IVs used for encrypting | |
1139 | objects are unique. This guarantee does *not* apply across handles if | |
1140 | multiple handles are used with the same combination of password and | |
1141 | salt. Thus, use of multiple handles with the same combination of password | |
1142 | and salt is subject to birthday attacks with a bound of 2^32. To avoid | |
1143 | collisions, the application should keep the number of handles as low | |
1144 | as possible and check for reuse by comparing the set of IVs used of all | |
1145 | handles that were created (accessible using the ``get_used_ivs`` method). | |
704ceaa5 | 1146 | """ |
1f3fd7b0 PG |
1147 | if password is None and key is None \ |
1148 | or password is not None and key is not None : | |
1149 | raise InvalidParameter ("__init__: need either key or password") | |
1150 | ||
1151 | if key is not None: | |
1152 | if isinstance (key, bytes) is False: | |
1153 | raise InvalidParameter ("__init__: key must be provided as " | |
1154 | "bytes, not %s" % type (key)) | |
1155 | if nacl is None: | |
1156 | raise InvalidParameter ("__init__: salt must be provided along " | |
1157 | "with encryption key") | |
1158 | else: # password, no key | |
1159 | if isinstance (password, str) is False: | |
1160 | raise InvalidParameter ("__init__: password must be a string, not %s" | |
1161 | % type (password)) | |
1162 | if len (password) == 0: | |
1163 | raise InvalidParameter ("__init__: supplied empty password but not " | |
1164 | "permitted for PDT encrypted files") | |
36b9932a PG |
1165 | # version |
1166 | if isinstance (version, int) is False: | |
1167 | raise InvalidParameter ("__init__: version number must be an " | |
1168 | "integer, not %s" % type (version)) | |
1169 | if version < 0: | |
1170 | raise InvalidParameter ("__init__: version number must be a " | |
1171 | "nonnegative integer, not %d" % version) | |
1172 | # paramversion | |
1173 | if isinstance (paramversion, int) is False: | |
1174 | raise InvalidParameter ("__init__: crypto parameter version number " | |
1175 | "must be an integer, not %s" | |
1176 | % type (paramversion)) | |
1177 | if paramversion < 0: | |
1178 | raise InvalidParameter ("__init__: crypto parameter version number " | |
1179 | "must be a nonnegative integer, not %d" | |
1180 | % paramversion) | |
1181 | # salt | |
1182 | if nacl is not None: | |
1183 | if isinstance (nacl, bytes) is False: | |
1184 | raise InvalidParameter ("__init__: salt given, but of type %s " | |
1185 | "instead of bytes" % type (nacl)) | |
1186 | # salt length would depend on the actual encryption so it can’t be | |
1187 | # validated at this point | |
b12110dd | 1188 | self.fixed = [ ] |
48db09ba PG |
1189 | self.version = version |
1190 | self.paramenc = ENCRYPTION_PARAMETERS.get (paramversion) ["enc"] | |
72a42219 | 1191 | |
1f3fd7b0 | 1192 | super().__init__ (password, key, paramversion, nacl, counter=counter, |
6110ef14 | 1193 | strict_ivs=strict_ivs, insecure=insecure) |
a393d9cb PG |
1194 | |
1195 | ||
be124bca PG |
1196 | def next_fixed (self, retries=PDTCRYPT_IV_GEN_MAX_RETRIES): |
1197 | """ | |
1198 | Generate the next IV fixed part by reading eight bytes from | |
1199 | ``/dev/urandom``. The buffer so obtained is tested against the fixed | |
1200 | parts used so far to prevent accidental reuse of IVs. After a | |
1201 | configurable number of attempts to create a unique fixed part, it will | |
1202 | refuse to continue with an ``IVFixedPartError``. This is unlikely to | |
1203 | ever happen on a normal system but may detect an issue with the random | |
1204 | generator. | |
1205 | ||
1206 | The list of fixed parts that were used by the context at hand can be | |
1207 | accessed through the ``.fixed`` list. Its last element is the fixed | |
1208 | part currently in use. | |
1209 | """ | |
1210 | i = 0 | |
1211 | while i < retries: | |
1212 | fp = os.urandom (PDTCRYPT_IV_FIXEDPART_SIZE) | |
1213 | if fp not in self.fixed: | |
1214 | self.fixed.append (fp) | |
1215 | return | |
1216 | i += 1 | |
1217 | raise IVFixedPartError ("error obtaining a unique IV fixed part from " | |
1218 | "/dev/urandom; giving up after %d tries" % i) | |
1219 | ||
1220 | ||
a393d9cb | 1221 | def iv_make (self): |
704ceaa5 PG |
1222 | """ |
1223 | Construct a 12-bytes IV from the current fixed part and the object | |
1224 | counter. | |
1225 | """ | |
b12110dd | 1226 | return struct.pack(FMT_I2N_IV, self.fixed [-1], self.cnt) |
a393d9cb PG |
1227 | |
1228 | ||
cb7a3911 | 1229 | def next (self, filename=None, counter=None): |
704ceaa5 PG |
1230 | """ |
1231 | Prepare for encrypting the next incoming object. Update the counter | |
1232 | and put together the IV, possibly changing prefixes. Then create the | |
1233 | new encryptor. | |
1234 | ||
1235 | The argument ``counter`` can be used to specify a file counter for this | |
1236 | object. Unless it is one of the reserved values, the counter of | |
1237 | subsequent objects will be computed from this one. | |
1238 | ||
1239 | If this is the first object in a series, ``filename`` is required, | |
1240 | otherwise it is reused if not present. The value is used to derive a | |
1241 | header sized placeholder to use until after encryption when all the | |
1242 | inputs to construct the final header are available. This is then | |
1243 | matched in ``.done()`` against the value found at the position of the | |
1244 | header. The motivation for this extra check is primarily to assist | |
1245 | format debugging: It makes stray headers easy to spot in malformed | |
1246 | PDTCRYPT files. | |
1247 | """ | |
cb7a3911 PG |
1248 | if filename is None: |
1249 | if self.lastinfo is None: | |
1250 | raise InvalidParameter ("next: filename is mandatory for " | |
1251 | "first object") | |
1252 | filename, _dummy = self.lastinfo | |
1253 | else: | |
1254 | if isinstance (filename, str) is False: | |
1255 | raise InvalidParameter ("next: filename must be a string, no %s" | |
1256 | % type (filename)) | |
3031b7ae PG |
1257 | if counter is not None: |
1258 | if isinstance (counter, int) is False: | |
1259 | raise InvalidParameter ("next: the supplied counter is of " | |
1260 | "invalid type %s; please pass an " | |
1261 | "integer instead" % type (counter)) | |
1262 | self.set_object_counter (counter) | |
fac2cfe1 | 1263 | |
50710d86 | 1264 | self.iv = self.iv_make () |
72a42219 | 1265 | if self.paramenc == "aes-gcm": |
6178061e PG |
1266 | self.enc = Cipher \ |
1267 | ( algorithms.AES (self.key) | |
1268 | , modes.GCM (self.iv) | |
1269 | , backend = default_backend ()) \ | |
1270 | .encryptor () | |
72a42219 | 1271 | elif self.paramenc == "passthrough": |
6178061e PG |
1272 | self.enc = PassthroughCipher () |
1273 | else: | |
b12110dd PG |
1274 | raise InvalidParameter ("next: parameter version %d not known" |
1275 | % self.paramversion) | |
48db09ba PG |
1276 | hdrdum = hdr_make_dummy (filename) |
1277 | self.lastinfo = (filename, hdrdum) | |
30019abf | 1278 | super().next (self.password, self.paramversion, self.nacl, self.iv) |
72a42219 | 1279 | |
3031b7ae | 1280 | self.set_object_counter (self.cnt + 1) |
48db09ba | 1281 | return hdrdum |
a393d9cb | 1282 | |
a393d9cb | 1283 | |
cd77dadb | 1284 | def done (self, cmpdata): |
704ceaa5 PG |
1285 | """ |
1286 | Complete encryption of an object. After this has been called, attempts | |
1287 | of encrypting further data will cause an error until ``.next()`` is | |
1288 | invoked properly. | |
1289 | ||
1290 | Returns a 64 bytes buffer containing the object header including all | |
1291 | values including the “late” ones e. g. the ciphertext size and the | |
1292 | GCM tag. | |
1293 | """ | |
36b9932a PG |
1294 | if isinstance (cmpdata, bytes) is False: |
1295 | raise InvalidParameter ("done: comparison input expected as bytes, " | |
1296 | "not %s" % type (cmpdata)) | |
cb7a3911 PG |
1297 | if self.lastinfo is None: |
1298 | raise RuntimeError ("done: encryption context not initialized") | |
48db09ba PG |
1299 | filename, hdrdum = self.lastinfo |
1300 | if cmpdata != hdrdum: | |
b12110dd PG |
1301 | raise RuntimeError ("done: bad sync of header for object %d: " |
1302 | "preliminary data does not match; this likely " | |
1303 | "indicates a wrongly repositioned stream" | |
1304 | % self.cnt) | |
6178061e | 1305 | data = self.enc.finalize () |
633b18a9 | 1306 | self.stats ["out"] += len (data) |
cd77dadb | 1307 | self.ctsize += len (data) |
48db09ba PG |
1308 | ok, hdr = hdr_from_params (self.version, self.paramversion, self.nacl, |
1309 | self.iv, self.ctsize, self.enc.tag) | |
8a990744 | 1310 | if ok is False: |
b12110dd PG |
1311 | raise InternalError ("error constructing header: %r" % hdr) |
1312 | return data, hdr, self.fixed | |
a393d9cb | 1313 | |
a393d9cb | 1314 | |
cd77dadb | 1315 | def process (self, buf): |
704ceaa5 PG |
1316 | """ |
1317 | Encrypt a chunk of plaintext with the active encryptor. Returns the | |
1318 | size of the input consumed. This **must** be checked downstream. If the | |
1319 | maximum possible object size has been reached, the current context must | |
1320 | be finalized and a new one established before any further data can be | |
1321 | encrypted. The second argument is the remainder of the plaintext that | |
1322 | was not encrypted for the caller to use immediately after the new | |
1323 | context is ready. | |
1324 | """ | |
36b9932a PG |
1325 | if isinstance (buf, bytes) is False: |
1326 | raise InvalidParameter ("process: expected byte buffer, not %s" | |
1327 | % type (buf)) | |
cb7a3911 PG |
1328 | bsize = len (buf) |
1329 | newptsize = self.ptsize + bsize | |
1330 | diff = newptsize - PDTCRYPT_MAX_OBJ_SIZE | |
1331 | if diff > 0: | |
1332 | bsize -= diff | |
1333 | newptsize = PDTCRYPT_MAX_OBJ_SIZE | |
1334 | self.ptsize = newptsize | |
1335 | data = super().process (buf [:bsize]) | |
cd77dadb | 1336 | self.ctsize += len (data) |
cb7a3911 | 1337 | return bsize, data |
cd77dadb PG |
1338 | |
1339 | ||
39accaaa | 1340 | class Decrypt (Crypto): |
a393d9cb | 1341 | |
3031b7ae | 1342 | tag = None # GCM tag, part of header |
3031b7ae | 1343 | last_iv = None # check consecutive ivs in strict mode |
58ed14b8 | 1344 | hdr_ctsize = -1 |
39accaaa | 1345 | |
1f3fd7b0 | 1346 | def __init__ (self, password=None, key=None, counter=None, fixedparts=None, |
6110ef14 | 1347 | strict_ivs=False, insecure=False): |
704ceaa5 PG |
1348 | """ |
1349 | Sanitizing ctor for the decryption context. ``fixedparts`` specifies a | |
1350 | list of IV fixed parts accepted during decryption. If a fixed part is | |
1351 | encountered that is not in the list, decryption will fail. | |
1352 | ||
1353 | :param password: mutually exclusive with ``key`` | |
1354 | :type password: bytes | |
1355 | :param key: mutually exclusive with ``password`` | |
1356 | :type key: bytes | |
1357 | :type counter: initial object counter the values | |
1358 | ``AES_GCM_IV_CNT_INFOFILE`` and | |
1359 | ``AES_GCM_IV_CNT_INDEX`` are unique in each backup set | |
1360 | and cannot be reused even with different fixed parts. | |
1361 | :type fixedparts: bytes list | |
66b1c6f4 PG |
1362 | :type insecure: bool |
1363 | :param insecure: whether to process objects encrypted in | |
6110ef14 | 1364 | passthrough mode (*``paramversion`` < 1*) |
704ceaa5 | 1365 | """ |
1f3fd7b0 PG |
1366 | if password is None and key is None \ |
1367 | or password is not None and key is not None : | |
1368 | raise InvalidParameter ("__init__: need either key or password") | |
1369 | ||
1370 | if key is not None: | |
1371 | if isinstance (key, bytes) is False: | |
1372 | raise InvalidParameter ("__init__: key must be provided as " | |
1373 | "bytes, not %s" % type (key)) | |
1374 | else: # password, no key | |
1375 | if isinstance (password, str) is False: | |
1376 | raise InvalidParameter ("__init__: password must be a string, not %s" | |
1377 | % type (password)) | |
1378 | if len (password) == 0: | |
1379 | raise InvalidParameter ("__init__: supplied empty password but not " | |
1380 | "permitted for PDT encrypted files") | |
36b9932a | 1381 | # fixed parts |
50710d86 | 1382 | if fixedparts is not None: |
36b9932a PG |
1383 | if isinstance (fixedparts, list) is False: |
1384 | raise InvalidParameter ("__init__: IV fixed parts must be " | |
1385 | "supplied as list, not %s" | |
1386 | % type (fixedparts)) | |
b12110dd PG |
1387 | self.fixed = fixedparts |
1388 | self.fixed.sort () | |
ee6aa239 | 1389 | |
a83fa4ed | 1390 | super().__init__ (password=password, key=key, counter=counter, |
6110ef14 | 1391 | strict_ivs=strict_ivs, insecure=insecure) |
39accaaa PG |
1392 | |
1393 | ||
b12110dd | 1394 | def valid_fixed_part (self, iv): |
704ceaa5 PG |
1395 | """ |
1396 | Check if a fixed part was already seen. | |
1397 | """ | |
50710d86 | 1398 | # check if fixed part is known |
b12110dd PG |
1399 | fixed, _cnt = struct.unpack (FMT_I2N_IV, iv) |
1400 | i = bisect.bisect_left (self.fixed, fixed) | |
1401 | return i != len (self.fixed) and self.fixed [i] == fixed | |
50710d86 PG |
1402 | |
1403 | ||
ee6aa239 | 1404 | def check_consecutive_iv (self, iv): |
704ceaa5 PG |
1405 | """ |
1406 | Check whether the counter part of the given IV is indeed the successor | |
1407 | of the currently present counter. This should always be the case for | |
1408 | the objects in a well formed PDT archive but should not be enforced | |
1409 | when decrypting out-of-order. | |
1410 | """ | |
ee6aa239 | 1411 | fixed, cnt = struct.unpack (FMT_I2N_IV, iv) |
3031b7ae PG |
1412 | if self.strict_ivs is True \ |
1413 | and self.last_iv is not None \ | |
ee6aa239 PG |
1414 | and self.last_iv [0] == fixed \ |
1415 | and self.last_iv [1] != cnt - 1: | |
f6cd676f | 1416 | raise NonConsecutiveIV ("iv %s counter not successor of " |
ee6aa239 | 1417 | "last object (expected %d, found %d)" |
2f0b128c | 1418 | % (iv_fmt (iv), self.last_iv [1], cnt)) |
4c842b5d | 1419 | self.last_iv = (fixed, cnt) |
ee6aa239 PG |
1420 | |
1421 | ||
79782fa9 | 1422 | def next (self, hdr): |
704ceaa5 PG |
1423 | """ |
1424 | Start decrypting the next object. The PDTCRYPT header for the object | |
1425 | can be given either as already parsed object or as bytes. | |
1426 | """ | |
dccfe104 PG |
1427 | if isinstance (hdr, bytes) is True: |
1428 | hdr = hdr_read (hdr) | |
36b9932a PG |
1429 | elif isinstance (hdr, dict) is False: |
1430 | # this won’t catch malformed specs though | |
1431 | raise InvalidParameter ("next: wrong type of parameter hdr: " | |
1432 | "expected bytes or spec, got %s" | |
fbfda3d4 | 1433 | % type (hdr)) |
36b9932a PG |
1434 | try: |
1435 | paramversion = hdr ["paramversion"] | |
1436 | nacl = hdr ["nacl"] | |
1437 | iv = hdr ["iv"] | |
1438 | tag = hdr ["tag"] | |
58ed14b8 | 1439 | ctsize = hdr ["ctsize"] |
36b9932a PG |
1440 | except KeyError: |
1441 | raise InvalidHeader ("next: not a header %r" % hdr) | |
1442 | ||
58ed14b8 PG |
1443 | if ctsize > PDTCRYPT_MAX_OBJ_SIZE: |
1444 | raise InvalidHeader ("next: ciphertext size %d exceeds maximum " | |
1445 | "object size (%d)" | |
1446 | % (ctsize, PDTCRYPT_MAX_OBJ_SIZE)) | |
1447 | ||
1448 | self.hdr_ctsize = ctsize | |
1449 | ||
30019abf | 1450 | super().next (self.password, paramversion, nacl, iv) |
b12110dd | 1451 | if self.fixed is not None and self.valid_fixed_part (iv) is False: |
f6cd676f PG |
1452 | raise InvalidIVFixedPart ("iv %s has invalid fixed part" |
1453 | % iv_fmt (iv)) | |
3031b7ae | 1454 | self.check_consecutive_iv (iv) |
ee6aa239 | 1455 | |
36b9932a | 1456 | self.tag = tag |
b12110dd PG |
1457 | defs = ENCRYPTION_PARAMETERS.get (paramversion, None) |
1458 | if defs is None: | |
1459 | raise FormatError ("header contains unknown parameter version %d; " | |
1460 | "maybe the file was created by a more recent " | |
1461 | "version of Deltatar" % paramversion) | |
50710d86 | 1462 | enc = defs ["enc"] |
6178061e PG |
1463 | if enc == "aes-gcm": |
1464 | self.enc = Cipher \ | |
1465 | ( algorithms.AES (self.key) | |
36b9932a | 1466 | , modes.GCM (iv, tag=self.tag) |
6178061e PG |
1467 | , backend = default_backend ()) \ |
1468 | . decryptor () | |
1469 | elif enc == "passthrough": | |
1470 | self.enc = PassthroughCipher () | |
1471 | else: | |
b12110dd PG |
1472 | raise InternalError ("encryption parameter set %d refers to unknown " |
1473 | "mode %r" % (paramversion, enc)) | |
f484f2d1 | 1474 | self.set_object_counter (self.cnt + 1) |
39accaaa PG |
1475 | |
1476 | ||
db1f3ac7 | 1477 | def done (self, tag=None): |
704ceaa5 PG |
1478 | """ |
1479 | Stop decryption of the current object and finalize it with the active | |
1480 | context. This will throw an *InvalidGCMTag* exception to indicate that | |
1481 | the authentication tag does not match the data. If the tag is correct, | |
1482 | the rest of the plaintext is returned. | |
1483 | """ | |
633b18a9 | 1484 | data = b"" |
db1f3ac7 PG |
1485 | try: |
1486 | if tag is None: | |
f484f2d1 | 1487 | data = self.enc.finalize () |
db1f3ac7 | 1488 | else: |
36b9932a PG |
1489 | if isinstance (tag, bytes) is False: |
1490 | raise InvalidParameter ("done: wrong type of parameter " | |
1491 | "tag: expected bytes, got %s" | |
1492 | % type (tag)) | |
f484f2d1 | 1493 | data = self.enc.finalize_with_tag (self.tag) |
b0078f26 | 1494 | except cryptography.exceptions.InvalidTag: |
f08c604b | 1495 | raise InvalidGCMTag ("done: tag mismatch of object %d: %s " |
b0078f26 | 1496 | "rejected by finalize ()" |
f08c604b | 1497 | % (self.cnt, binascii.hexlify (self.tag))) |
58ed14b8 | 1498 | self.ptsize += len (data) |
633b18a9 | 1499 | self.stats ["out"] += len (data) |
58ed14b8 PG |
1500 | |
1501 | assert self.ctsize == self.ptsize == self.hdr_ctsize | |
1502 | ||
b0078f26 | 1503 | return data |
00b3cd10 PG |
1504 | |
1505 | ||
47e27926 | 1506 | def process (self, buf): |
704ceaa5 PG |
1507 | """ |
1508 | Decrypt the bytes object *buf* with the active decryptor. | |
1509 | """ | |
36b9932a PG |
1510 | if isinstance (buf, bytes) is False: |
1511 | raise InvalidParameter ("process: expected byte buffer, not %s" | |
1512 | % type (buf)) | |
47e27926 | 1513 | self.ctsize += len (buf) |
58ed14b8 PG |
1514 | if self.ctsize > self.hdr_ctsize: |
1515 | raise CiphertextTooLong ("process: object length exceeded: got " | |
1516 | "%d B but header specfiies %d B" | |
1517 | % (self.ctsize, self.hdr_ctsize)) | |
1518 | ||
47e27926 PG |
1519 | data = super().process (buf) |
1520 | self.ptsize += len (data) | |
1521 | return data | |
1522 | ||
1523 | ||
00b3cd10 | 1524 | ############################################################################### |
770173c5 PG |
1525 | ## testing helpers |
1526 | ############################################################################### | |
1527 | ||
cb7a3911 | 1528 | def _patch_global (glob, vow, n=None): |
770173c5 PG |
1529 | """ |
1530 | Adapt upper file counter bound for testing IV logic. Completely unsafe. | |
1531 | """ | |
1532 | assert vow == "I am fully aware that this will void my warranty." | |
cb7a3911 PG |
1533 | r = globals () [glob] |
1534 | if n is None: | |
1535 | n = globals () [glob + "_DEFAULT"] | |
1536 | globals () [glob] = n | |
770173c5 PG |
1537 | return r |
1538 | ||
cb7a3911 PG |
1539 | _testing_set_AES_GCM_IV_CNT_MAX = \ |
1540 | partial (_patch_global, "AES_GCM_IV_CNT_MAX") | |
1541 | ||
1542 | _testing_set_PDTCRYPT_MAX_OBJ_SIZE = \ | |
1543 | partial (_patch_global, "PDTCRYPT_MAX_OBJ_SIZE") | |
1544 | ||
a808459e PG |
1545 | def open2_dump_file (fname, dir_fd, force=False): |
1546 | outfd = -1 | |
1547 | ||
1548 | oflags = os.O_CREAT | os.O_WRONLY | |
6690f5e0 | 1549 | if force is True: |
a808459e PG |
1550 | oflags |= os.O_TRUNC |
1551 | else: | |
1552 | oflags |= os.O_EXCL | |
1553 | ||
1554 | try: | |
1555 | outfd = os.open (fname, oflags, | |
1556 | stat.S_IRUSR | stat.S_IWUSR, dir_fd=dir_fd) | |
1557 | except FileExistsError as exn: | |
1558 | noise ("PDT: refusing to overwrite existing file %s" % fname) | |
1559 | noise ("") | |
1560 | raise RuntimeError ("destination file %s already exists" % fname) | |
1561 | if PDTCRYPT_VERBOSE is True: | |
1562 | noise ("PDT: new output file %s (fd=%d)" % (fname, outfd)) | |
1563 | ||
1564 | return outfd | |
1565 | ||
770173c5 | 1566 | ############################################################################### |
00b3cd10 PG |
1567 | ## freestanding invocation |
1568 | ############################################################################### | |
1569 | ||
da82bc58 PG |
1570 | PDTCRYPT_SUB_PROCESS = 0 |
1571 | PDTCRYPT_SUB_SCRYPT = 1 | |
f41973a6 | 1572 | PDTCRYPT_SUB_SCAN = 2 |
da82bc58 PG |
1573 | |
1574 | PDTCRYPT_SUB = \ | |
1575 | { "process" : PDTCRYPT_SUB_PROCESS | |
f41973a6 PG |
1576 | , "scrypt" : PDTCRYPT_SUB_SCRYPT |
1577 | , "scan" : PDTCRYPT_SUB_SCAN } | |
da82bc58 | 1578 | |
e3abcdf0 PG |
1579 | PDTCRYPT_DECRYPT = 1 << 0 # decrypt archive with password |
1580 | PDTCRYPT_SPLIT = 1 << 1 # split archive into individual objects | |
da82bc58 | 1581 | PDTCRYPT_HASH = 1 << 2 # output scrypt hash for file and given password |
e3abcdf0 | 1582 | |
a808459e PG |
1583 | PDTCRYPT_SPLITNAME = "pdtcrypt-object-%d.bin" |
1584 | PDTCRYPT_RESCUENAME = "pdtcrypt-rescue-object-%0.5d.bin" | |
e3abcdf0 | 1585 | |
70ad9458 | 1586 | PDTCRYPT_VERBOSE = False |
ee6aa239 | 1587 | PDTCRYPT_STRICTIVS = False |
b07633d3 | 1588 | PDTCRYPT_OVERWRITE = False |
15d3eefd | 1589 | PDTCRYPT_BLOCKSIZE = 1 << 12 |
70ad9458 PG |
1590 | PDTCRYPT_SINK = 0 |
1591 | PDTCRYPT_SOURCE = 1 | |
1592 | SELF = None | |
1593 | ||
77058bab PG |
1594 | PDTCRYPT_DEFAULT_VER = 1 |
1595 | PDTCRYPT_DEFAULT_PVER = 1 | |
1596 | ||
7b3940e5 PG |
1597 | # scrypt hashing output control |
1598 | PDTCRYPT_SCRYPT_INTRANATOR = 0 | |
1599 | PDTCRYPT_SCRYPT_PARAMETERS = 1 | |
4f6405d6 | 1600 | PDTCRYPT_SCRYPT_DEFAULT = PDTCRYPT_SCRYPT_INTRANATOR |
7b3940e5 PG |
1601 | |
1602 | PDTCRYPT_SCRYPT_FORMAT = \ | |
1603 | { "i2n" : PDTCRYPT_SCRYPT_INTRANATOR | |
1604 | , "params" : PDTCRYPT_SCRYPT_PARAMETERS } | |
1605 | ||
4c62ddc0 | 1606 | PDTCRYPT_TT_COLUMNS = 80 # assume standard terminal |
15d3eefd PG |
1607 | |
1608 | class PDTDecryptionError (Exception): | |
1609 | """Decryption failed.""" | |
1610 | ||
e3abcdf0 PG |
1611 | class PDTSplitError (Exception): |
1612 | """Decryption failed.""" | |
1613 | ||
15d3eefd PG |
1614 | |
1615 | def noise (*a, **b): | |
591a722f | 1616 | print (file=sys.stderr, *a, **b) |
15d3eefd PG |
1617 | |
1618 | ||
89e1073c PG |
1619 | class PassthroughDecryptor (object): |
1620 | ||
1621 | curhdr = None # write current header on first data write | |
1622 | ||
1623 | def __init__ (self): | |
1624 | if PDTCRYPT_VERBOSE is True: | |
1625 | noise ("PDT: no encryption; data passthrough") | |
1626 | ||
1627 | def next (self, hdr): | |
1628 | ok, curhdr = hdr_make (hdr) | |
1629 | if ok is False: | |
1630 | raise PDTDecryptionError ("bad header %r" % hdr) | |
1631 | self.curhdr = curhdr | |
1632 | ||
1633 | def done (self): | |
1634 | if self.curhdr is not None: | |
1635 | return self.curhdr | |
1636 | return b"" | |
1637 | ||
1638 | def process (self, d): | |
1639 | if self.curhdr is not None: | |
1640 | d = self.curhdr + d | |
1641 | self.curhdr = None | |
1642 | return d | |
1643 | ||
1644 | ||
a83fa4ed | 1645 | def depdtcrypt (mode, secret, ins, outs): |
15d3eefd | 1646 | """ |
a83fa4ed PG |
1647 | Remove PDTCRYPT layer from all objects encrypted with the secret. Used on a |
1648 | Deltatar backup this will yield a (possibly Gzip compressed) tarball. | |
15d3eefd PG |
1649 | """ |
1650 | ctleft = -1 # length of ciphertext to consume | |
1651 | ctcurrent = 0 # total ciphertext of current object | |
15d3eefd PG |
1652 | total_obj = 0 # total number of objects read |
1653 | total_pt = 0 # total plaintext bytes | |
1654 | total_ct = 0 # total ciphertext bytes | |
1655 | total_read = 0 # total bytes read | |
e3abcdf0 PG |
1656 | outfile = None # Python file object for output |
1657 | ||
89e1073c | 1658 | if mode & PDTCRYPT_DECRYPT: # decryptor |
a83fa4ed PG |
1659 | ks = secret [0] |
1660 | if ks == PDTCRYPT_SECRET_PW: | |
1661 | decr = Decrypt (password=secret [1], strict_ivs=PDTCRYPT_STRICTIVS) | |
1662 | elif ks == PDTCRYPT_SECRET_KEY: | |
6257d5b3 | 1663 | key = secret [1] |
a83fa4ed PG |
1664 | decr = Decrypt (key=key, strict_ivs=PDTCRYPT_STRICTIVS) |
1665 | else: | |
1666 | raise InternalError ("‘%d’ does not specify a valid kind of secret" | |
1667 | % ks) | |
89e1073c PG |
1668 | else: |
1669 | decr = PassthroughDecryptor () | |
1670 | ||
e3abcdf0 PG |
1671 | def nextout (_): |
1672 | """Dummy for non-split mode: output file does not vary.""" | |
1673 | return outs | |
1674 | ||
1675 | if mode & PDTCRYPT_SPLIT: | |
1676 | def nextout (outfile): | |
1677 | """ | |
1678 | We were passed an fd as outs for accessing the destination | |
1679 | directory where extracted archive components are supposed | |
1680 | to end up in. | |
1681 | """ | |
1682 | ||
1683 | if outfile is None: | |
1684 | if PDTCRYPT_VERBOSE is True: | |
1685 | noise ("PDT: no output file to close at this point") | |
375fb496 TJ |
1686 | else: |
1687 | if PDTCRYPT_VERBOSE is True: | |
1688 | noise ("PDT: release output file %r" % outfile) | |
1689 | # cleanup happens automatically by the GC; the next | |
1690 | # line will error out on account of an invalid fd | |
1691 | #outfile.close () | |
e3abcdf0 PG |
1692 | |
1693 | assert total_obj > 0 | |
1694 | fname = PDTCRYPT_SPLITNAME % total_obj | |
1695 | try: | |
a808459e PG |
1696 | outfd = open2_dump_file (fname, outs, force=PDTCRYPT_OVERWRITE) |
1697 | except RuntimeError as exn: | |
1698 | raise PDTSplitError (exn) | |
e3abcdf0 PG |
1699 | return os.fdopen (outfd, "wb", closefd=True) |
1700 | ||
15d3eefd | 1701 | |
47d22679 | 1702 | def tell (s): |
b09a99eb | 1703 | """ESPIPE is normal on non-seekable stdio stream.""" |
47d22679 PG |
1704 | try: |
1705 | return s.tell () | |
1706 | except OSError as exn: | |
2a307f41 | 1707 | if exn.errno == errno.ESPIPE: |
47d22679 PG |
1708 | return -1 |
1709 | ||
e3abcdf0 | 1710 | def out (pt, outfile): |
15d3eefd PG |
1711 | npt = len (pt) |
1712 | nonlocal total_pt | |
1713 | total_pt += npt | |
70ad9458 | 1714 | if PDTCRYPT_VERBOSE is True: |
15d3eefd PG |
1715 | noise ("PDT:\t· decrypt plaintext %d B" % (npt)) |
1716 | try: | |
e3abcdf0 | 1717 | nn = outfile.write (pt) |
15d3eefd PG |
1718 | except OSError as exn: # probably ENOSPC |
1719 | raise DecryptionError ("error (%s)" % exn) | |
1720 | if nn != npt: | |
1721 | raise DecryptionError ("write aborted after %d of %d B" % (nn, npt)) | |
1722 | ||
1723 | while True: | |
1724 | if ctleft <= 0: | |
1725 | # current object completed; in a valid archive this marks either | |
1726 | # the start of a new header or the end of the input | |
1727 | if ctleft == 0: # current object requires finalization | |
70ad9458 | 1728 | if PDTCRYPT_VERBOSE is True: |
47d22679 | 1729 | noise ("PDT: %d finalize" % tell (ins)) |
5d394c0d PG |
1730 | try: |
1731 | pt = decr.done () | |
1732 | except InvalidGCMTag as exn: | |
f08c604b PG |
1733 | raise DecryptionError ("error finalizing object %d (%d B): " |
1734 | "%r" % (total_obj, len (pt), exn)) \ | |
1735 | from exn | |
e3abcdf0 | 1736 | out (pt, outfile) |
70ad9458 | 1737 | if PDTCRYPT_VERBOSE is True: |
15d3eefd PG |
1738 | noise ("PDT:\t· object validated") |
1739 | ||
70ad9458 | 1740 | if PDTCRYPT_VERBOSE is True: |
47d22679 | 1741 | noise ("PDT: %d hdr" % tell (ins)) |
15d3eefd PG |
1742 | try: |
1743 | hdr = hdr_read_stream (ins) | |
dd47d6a2 | 1744 | total_read += PDTCRYPT_HDR_SIZE |
ae3d0f2a PG |
1745 | except EndOfFile as exn: |
1746 | total_read += exn.remainder | |
dd47d6a2 | 1747 | if total_ct + total_obj * PDTCRYPT_HDR_SIZE != total_read: |
15d3eefd PG |
1748 | raise PDTDecryptionError ("ciphertext processed (%d B) plus " |
1749 | "overhead (%d × %d B) does not match " | |
1750 | "the number of bytes read (%d )" | |
dd47d6a2 | 1751 | % (total_ct, total_obj, PDTCRYPT_HDR_SIZE, |
15d3eefd PG |
1752 | total_read)) |
1753 | # the single good exit | |
1754 | return total_read, total_obj, total_ct, total_pt | |
1755 | except InvalidHeader as exn: | |
1756 | raise PDTDecryptionError ("invalid header at position %d in %r " | |
ee6aa239 | 1757 | "(%s)" % (tell (ins), exn, ins)) |
70ad9458 | 1758 | if PDTCRYPT_VERBOSE is True: |
15d3eefd PG |
1759 | pretty = hdr_fmt_pretty (hdr) |
1760 | noise (reduce (lambda a, e: (a + "\n" if a else "") + "PDT:\t· " + e, | |
1761 | pretty.splitlines (), "")) | |
1762 | ctcurrent = ctleft = hdr ["ctsize"] | |
89e1073c | 1763 | |
15d3eefd | 1764 | decr.next (hdr) |
e3abcdf0 PG |
1765 | |
1766 | total_obj += 1 # used in file counter with split mode | |
1767 | ||
1768 | # finalization complete or skipped in case of first object in | |
1769 | # stream; create a new output file if necessary | |
1770 | outfile = nextout (outfile) | |
15d3eefd | 1771 | |
70ad9458 | 1772 | if PDTCRYPT_VERBOSE is True: |
15d3eefd | 1773 | noise ("PDT: %d decrypt obj no. %d, %d B" |
47d22679 | 1774 | % (tell (ins), total_obj, ctleft)) |
15d3eefd PG |
1775 | |
1776 | # always allocate a new buffer since python-cryptography doesn’t allow | |
1777 | # passing a bytearray :/ | |
1778 | nexpect = min (ctleft, PDTCRYPT_BLOCKSIZE) | |
70ad9458 | 1779 | if PDTCRYPT_VERBOSE is True: |
15d3eefd | 1780 | noise ("PDT:\t· [%d] %d%% done, read block (%d B of %d B remaining)" |
47d22679 | 1781 | % (tell (ins), |
15d3eefd PG |
1782 | 100 - ctleft * 100 / (ctcurrent > 0 and ctcurrent or 1), |
1783 | nexpect, ctleft)) | |
1784 | ct = ins.read (nexpect) | |
1785 | nct = len (ct) | |
1786 | if nct < nexpect: | |
47d22679 | 1787 | off = tell (ins) |
ae3d0f2a PG |
1788 | raise EndOfFile (nct, |
1789 | "hit EOF after %d of %d B in block [%d:%d); " | |
15d3eefd PG |
1790 | "%d B ciphertext remaining for object no %d" |
1791 | % (nct, nexpect, off, off + nexpect, ctleft, | |
1792 | total_obj)) | |
1793 | ctleft -= nct | |
1794 | total_ct += nct | |
1795 | total_read += nct | |
1796 | ||
70ad9458 | 1797 | if PDTCRYPT_VERBOSE is True: |
15d3eefd PG |
1798 | noise ("PDT:\t· decrypt ciphertext %d B" % (nct)) |
1799 | pt = decr.process (ct) | |
e3abcdf0 | 1800 | out (pt, outfile) |
15d3eefd | 1801 | |
d6c15a52 | 1802 | |
70ad9458 | 1803 | def deptdcrypt_mk_stream (kind, path): |
d6c15a52 | 1804 | """Create stream from file or stdio descriptor.""" |
70ad9458 | 1805 | if kind == PDTCRYPT_SINK: |
d6c15a52 | 1806 | if path == "-": |
70ad9458 | 1807 | if PDTCRYPT_VERBOSE is True: noise ("PDT: sink: stdout") |
d6c15a52 PG |
1808 | return sys.stdout.buffer |
1809 | else: | |
70ad9458 | 1810 | if PDTCRYPT_VERBOSE is True: noise ("PDT: sink: file %s" % path) |
d6c15a52 | 1811 | return io.FileIO (path, "w") |
70ad9458 | 1812 | if kind == PDTCRYPT_SOURCE: |
d6c15a52 | 1813 | if path == "-": |
70ad9458 | 1814 | if PDTCRYPT_VERBOSE is True: noise ("PDT: source: stdin") |
d6c15a52 PG |
1815 | return sys.stdin.buffer |
1816 | else: | |
70ad9458 | 1817 | if PDTCRYPT_VERBOSE is True: noise ("PDT: source: file %s" % path) |
d6c15a52 PG |
1818 | return io.FileIO (path, "r") |
1819 | ||
1820 | raise ValueError ("bogus stream “%s” / %s" % (kind, path)) | |
1821 | ||
15d3eefd | 1822 | |
a83fa4ed | 1823 | def mode_depdtcrypt (mode, secret, ins, outs): |
da82bc58 PG |
1824 | try: |
1825 | total_read, total_obj, total_ct, total_pt = \ | |
a83fa4ed | 1826 | depdtcrypt (mode, secret, ins, outs) |
da82bc58 PG |
1827 | except DecryptionError as exn: |
1828 | noise ("PDT: Decryption failed:") | |
1829 | noise ("PDT:") | |
1830 | noise ("PDT: “%s”" % exn) | |
1831 | noise ("PDT:") | |
a83fa4ed | 1832 | noise ("PDT: Did you specify the correct key / password?") |
da82bc58 PG |
1833 | noise ("") |
1834 | return 1 | |
1835 | except PDTSplitError as exn: | |
1836 | noise ("PDT: Split operation failed:") | |
1837 | noise ("PDT:") | |
1838 | noise ("PDT: “%s”" % exn) | |
1839 | noise ("PDT:") | |
a83fa4ed | 1840 | noise ("PDT: Hint: target directory should be empty.") |
da82bc58 PG |
1841 | noise ("") |
1842 | return 1 | |
1843 | ||
1844 | if PDTCRYPT_VERBOSE is True: | |
1845 | noise ("PDT: decryption successful" ) | |
1846 | noise ("PDT: %.10d bytes read" % total_read) | |
1847 | noise ("PDT: %.10d objects decrypted" % total_obj ) | |
1848 | noise ("PDT: %.10d bytes ciphertext" % total_ct ) | |
1849 | noise ("PDT: %.10d bytes plaintext" % total_pt ) | |
1850 | noise ("" ) | |
1851 | ||
1852 | return 0 | |
1853 | ||
1854 | ||
7b3940e5 | 1855 | def mode_scrypt (pw, ins=None, nacl=None, fmt=PDTCRYPT_SCRYPT_INTRANATOR): |
77058bab | 1856 | hsh = None |
7b3940e5 | 1857 | paramversion = PDTCRYPT_DEFAULT_PVER |
77058bab PG |
1858 | if ins is not None: |
1859 | hsh, nacl, version, paramversion = scrypt_hashsource (pw, ins) | |
1860 | defs = ENCRYPTION_PARAMETERS.get(paramversion, None) | |
1861 | else: | |
1862 | nacl = binascii.unhexlify (nacl) | |
7b3940e5 | 1863 | defs = ENCRYPTION_PARAMETERS.get(paramversion, None) |
77058bab PG |
1864 | version = PDTCRYPT_DEFAULT_VER |
1865 | ||
1866 | kdfname, params = defs ["kdf"] | |
1867 | if hsh is None: | |
1868 | kdf = kdf_by_version (None, defs) | |
1869 | hsh, _void = kdf (pw, nacl) | |
da82bc58 PG |
1870 | |
1871 | import json | |
7b3940e5 PG |
1872 | |
1873 | if fmt == PDTCRYPT_SCRYPT_INTRANATOR: | |
1874 | out = json.dumps ({ "salt" : base64.b64encode (nacl).decode () | |
1875 | , "key" : base64.b64encode (hsh) .decode () | |
1876 | , "paramversion" : paramversion }) | |
1877 | elif fmt == PDTCRYPT_SCRYPT_PARAMETERS: | |
1878 | out = json.dumps ({ "salt" : binascii.hexlify (nacl).decode () | |
1879 | , "key" : binascii.hexlify (hsh) .decode () | |
1880 | , "version" : version | |
1881 | , "scrypt_params" : { "N" : params ["N"] | |
1882 | , "r" : params ["r"] | |
1883 | , "p" : params ["p"] | |
1884 | , "dkLen" : params ["dkLen"] } }) | |
1885 | else: | |
1886 | raise RuntimeError ("bad scrypt output scheme %r" % fmt) | |
1887 | ||
da82bc58 PG |
1888 | print (out) |
1889 | ||
1890 | ||
4c62ddc0 PG |
1891 | def noise_output_candidates (cands, indent=8, cols=PDTCRYPT_TT_COLUMNS): |
1892 | """ | |
1893 | Print a list of offsets without garbling the terminal too much. | |
1894 | ||
1895 | The indent is counted from column zero; if it is wide enough, the “PDT: ” | |
1896 | marker will be prepended, considered part of the indentation. | |
1897 | """ | |
1898 | wd = cols - 1 | |
1899 | nc = len (cands) | |
1900 | idt = " " * indent if indent < 5 else "PDT: " + " " * (indent - 5) | |
1901 | line = idt | |
1902 | lpos = indent | |
1903 | sep = "," | |
1904 | lsep = len (sep) | |
1905 | init = True # prevent leading separator | |
1906 | ||
1907 | if indent >= wd: | |
1908 | raise ValueError ("the requested indentation exceeds the line " | |
1909 | "width by %d" % (indent - wd)) | |
1910 | ||
1911 | for n in cands: | |
1912 | ns = "%d" % n | |
1913 | lns = len (ns) | |
1914 | if init is False: | |
1915 | line += sep | |
1916 | lpos += lsep | |
1917 | ||
1918 | lpos += lns | |
1919 | if lpos > wd: # line break | |
1920 | noise (line) | |
1921 | line = idt | |
1922 | lpos = indent + lns | |
1923 | elif init is True: | |
1924 | init = False | |
1925 | else: # space | |
1926 | line += ' ' | |
1927 | lpos += 1 | |
1928 | ||
1929 | line += ns | |
1930 | ||
1931 | if lpos != indent: | |
1932 | noise (line) | |
1933 | ||
1934 | ||
15047fe4 PG |
1935 | SLICE_START = 1 # ordering is important to have starts of intervals |
1936 | SLICE_END = 0 # sorted before equal ends | |
1937 | ||
1938 | def find_overlaps (slices): | |
1939 | """ | |
1940 | Find overlapping slices: iterate open/close points of intervals, tracking | |
1941 | the ones open at any time. | |
1942 | """ | |
1943 | bounds = [] | |
1944 | inside = set () # of indices into bounds | |
1945 | ovrlp = set () # of indices into bounds | |
1946 | ||
1947 | for i, s in enumerate (slices): | |
1948 | bounds.append ((s [0], SLICE_START, i)) | |
1949 | bounds.append ((s [1], SLICE_END , i)) | |
1950 | bounds = sorted (bounds) | |
1951 | ||
1952 | for val in bounds: | |
1953 | i = val [2] | |
1954 | if val [1] == SLICE_START: | |
1955 | inside.add (i) | |
1956 | else: | |
1957 | if len (inside) > 1: # closing one that overlapped | |
1958 | ovrlp |= inside | |
1959 | inside.remove (i) | |
1960 | ||
1961 | return [ slices [i] for i in ovrlp ] | |
1962 | ||
1963 | ||
a808459e | 1964 | def mode_scan (secret, fname, outs=None, nacl=None): |
f41973a6 PG |
1965 | """ |
1966 | Dissect a binary file, looking for PDTCRYPT headers and objects. | |
a808459e PG |
1967 | |
1968 | If *outs* is supplied, recoverable data will be dumped into the specified | |
1969 | directory. | |
f41973a6 PG |
1970 | """ |
1971 | try: | |
a808459e | 1972 | ifd = os.open (fname, os.O_RDONLY) |
f41973a6 PG |
1973 | except FileNotFoundError: |
1974 | noise ("PDT: failed to open %s readonly" % fname) | |
1975 | noise ("") | |
1976 | usage (err=True) | |
1977 | ||
1978 | try: | |
1979 | if PDTCRYPT_VERBOSE is True: | |
1980 | noise ("PDT: scan for potential sync points") | |
a808459e | 1981 | cands = locate_hdr_candidates (ifd) |
f41973a6 PG |
1982 | if len (cands) == 0: |
1983 | noise ("PDT: scan complete: input does not contain potential PDT " | |
1984 | "headers; giving up.") | |
1985 | return -1 | |
1986 | if PDTCRYPT_VERBOSE is True: | |
4c62ddc0 PG |
1987 | noise ("PDT: scan complete: found %d candidates:" % len (cands)) |
1988 | noise_output_candidates (cands) | |
6c8073ab | 1989 | except: |
a808459e | 1990 | os.close (ifd) |
6c8073ab | 1991 | raise |
f41973a6 | 1992 | |
15047fe4 | 1993 | junk, todo, slices = [], [], [] |
6c8073ab | 1994 | try: |
a808459e | 1995 | nobj = 0 |
6c8073ab | 1996 | for cand in cands: |
a808459e PG |
1997 | nobj += 1 |
1998 | vdt, hdr = inspect_hdr (ifd, cand) | |
15047fe4 | 1999 | |
5ed4c57d PG |
2000 | vdts = verdict_fmt (vdt) |
2001 | ||
6c8073ab | 2002 | if vdt == HDR_CAND_JUNK: |
5ed4c57d | 2003 | noise ("PDT: obj %d: %s object: bad header, skipping" % vdts) |
6c8073ab PG |
2004 | junk.append (cand) |
2005 | else: | |
2006 | off0 = cand + PDTCRYPT_HDR_SIZE | |
2007 | if PDTCRYPT_VERBOSE is True: | |
a808459e | 2008 | noise ("PDT: obj %d: read payload @%d" % (nobj, off0)) |
70a33834 PG |
2009 | pretty = hdr_fmt_pretty (hdr) |
2010 | noise (reduce (lambda a, e: (a + "\n" if a else "") + "PDT:\t· " + e, | |
2011 | pretty.splitlines (), "")) | |
6c8073ab | 2012 | |
a808459e PG |
2013 | ofd = -1 |
2014 | if outs is not None: | |
2015 | ofname = PDTCRYPT_RESCUENAME % nobj | |
2016 | ofd = open2_dump_file (ofname, outs, force=PDTCRYPT_OVERWRITE) | |
2017 | ||
15047fe4 | 2018 | ctsize = hdr ["ctsize"] |
a808459e | 2019 | try: |
15047fe4 PG |
2020 | l = try_decrypt (ifd, off0, hdr, secret, ofd=ofd) |
2021 | ok = l == ctsize | |
2022 | slices.append ((off0, off0 + l)) | |
a808459e PG |
2023 | finally: |
2024 | if ofd != -1: | |
2025 | os.close (ofd) | |
70a33834 | 2026 | if vdt == HDR_CAND_GOOD and ok is True: |
5ed4c57d PG |
2027 | noise ("PDT: %d → ✓ %s object %d–%d" |
2028 | % (cand, vdts, off0, off0 + ctsize)) | |
70a33834 | 2029 | elif vdt == HDR_CAND_FISHY and ok is True: |
5ed4c57d PG |
2030 | noise ("PDT: %d → × %s object %d–%d, corrupt header" |
2031 | % (cand, vdts, off0, off0 + ctsize)) | |
70a33834 | 2032 | elif vdt == HDR_CAND_GOOD and ok is False: |
5ed4c57d PG |
2033 | noise ("PDT: %d → × %s object %d–%d, problematic payload" |
2034 | % (cand, vdts, off0, off0 + ctsize)) | |
70a33834 | 2035 | elif vdt == HDR_CAND_FISHY and ok is False: |
5ed4c57d PG |
2036 | noise ("PDT: %d → × %s object %d–%d, corrupt header, problematic " |
2037 | "ciphertext" % (cand, vdts, off0, off0 + ctsize)) | |
6c8073ab PG |
2038 | else: |
2039 | raise Unreachable | |
2040 | finally: | |
a808459e | 2041 | os.close (ifd) |
7b3940e5 | 2042 | |
70a33834 PG |
2043 | if len (junk) == 0: |
2044 | noise ("PDT: all headers ok") | |
2045 | else: | |
2046 | noise ("PDT: %d candidates not parseable as headers:" % len (junk)) | |
2047 | noise_output_candidates (junk) | |
2048 | ||
15047fe4 PG |
2049 | overlap = find_overlaps (slices) |
2050 | if len (overlap) > 0: | |
2051 | noise ("PDT: %d objects overlapping others" % len (overlap)) | |
2052 | for slice in overlap: | |
2053 | noise ("PDT: × %d→%d" % (slice [0], slice [1])) | |
2054 | ||
70ad9458 PG |
2055 | def usage (err=False): |
2056 | out = print | |
2057 | if err is True: | |
2058 | out = noise | |
5afcb45d | 2059 | indent = ' ' * len (SELF) |
da82bc58 | 2060 | out ("usage: %s SUBCOMMAND { --help" % SELF) |
5afcb45d | 2061 | out (" %s | [ -v ] { -p PASSWORD | -k KEY }" % indent) |
77058bab PG |
2062 | out (" %s [ { -i | --in } { - | SOURCE } ]" % indent) |
2063 | out (" %s [ { -n | --nacl } { SALT } ]" % indent) | |
2064 | out (" %s [ { -o | --out } { - | DESTINATION } ]" % indent) | |
2065 | out (" %s [ -D | --no-decrypt ] [ -S | --split ]" % indent) | |
7b3940e5 | 2066 | out (" %s [ -f | --format ]" % indent) |
70ad9458 PG |
2067 | out ("") |
2068 | out ("\twhere") | |
da82bc58 PG |
2069 | out ("\t\tSUBCOMMAND main mode: { process | scrypt }") |
2070 | out ("\t\t where:") | |
2071 | out ("\t\t process: extract objects from PDT archive") | |
2072 | out ("\t\t scrypt: calculate hash from password and first object") | |
a83fa4ed PG |
2073 | out ("\t\t-p PASSWORD password to derive the encryption key from") |
2074 | out ("\t\t-k KEY encryption key as 16 bytes in hexadecimal notation") | |
e3abcdf0 | 2075 | out ("\t\t-s enforce strict handling of initialization vectors") |
70ad9458 PG |
2076 | out ("\t\t-i SOURCE file name to read from") |
2077 | out ("\t\t-o DESTINATION file to write output to") | |
77058bab | 2078 | out ("\t\t-n SALT provide salt for scrypt mode in hex encoding") |
70ad9458 | 2079 | out ("\t\t-v print extra info") |
e3abcdf0 PG |
2080 | out ("\t\t-S split into files at object boundaries; this") |
2081 | out ("\t\t requires DESTINATION to refer to directory") | |
2082 | out ("\t\t-D PDT header and ciphertext passthrough") | |
7b3940e5 | 2083 | out ("\t\t-f format of SCRYPT hash output (“default” or “parameters”)") |
70ad9458 PG |
2084 | out ("") |
2085 | out ("\tinstead of filenames, “-” may used to specify stdin / stdout") | |
2086 | out ("") | |
2087 | sys.exit ((err is True) and 42 or 0) | |
2088 | ||
2089 | ||
a83fa4ed PG |
2090 | def bail (msg): |
2091 | noise (msg) | |
2092 | noise ("") | |
2093 | usage (err=True) | |
2094 | raise Unreachable | |
2095 | ||
2096 | ||
70ad9458 | 2097 | def parse_argv (argv): |
6690f5e0 | 2098 | global PDTCRYPT_OVERWRITE |
70ad9458 | 2099 | global SELF |
7b3940e5 PG |
2100 | mode = PDTCRYPT_DECRYPT |
2101 | secret = None | |
2102 | insspec = None | |
2103 | outsspec = None | |
a808459e | 2104 | outs = None |
7b3940e5 | 2105 | nacl = None |
4f6405d6 | 2106 | scrypt_format = PDTCRYPT_SCRYPT_DEFAULT |
70ad9458 PG |
2107 | |
2108 | argvi = iter (argv) | |
2109 | SELF = os.path.basename (next (argvi)) | |
2110 | ||
da82bc58 PG |
2111 | try: |
2112 | rawsubcmd = next (argvi) | |
2113 | subcommand = PDTCRYPT_SUB [rawsubcmd] | |
2114 | except StopIteration: | |
a83fa4ed | 2115 | bail ("ERROR: subcommand required") |
da82bc58 | 2116 | except KeyError: |
a83fa4ed | 2117 | bail ("ERROR: invalid subcommand “%s” specified" % rawsubcmd) |
da82bc58 | 2118 | |
59d74e2b PG |
2119 | def checked_arg (): |
2120 | nonlocal argvi | |
2121 | try: | |
2122 | return next (argvi) | |
2123 | except StopIteration: | |
2124 | bail ("ERROR: argument list incomplete") | |
2125 | ||
addcec42 | 2126 | def checked_secret (s): |
a83fa4ed PG |
2127 | nonlocal secret |
2128 | if secret is None: | |
addcec42 | 2129 | secret = s |
da82bc58 | 2130 | else: |
a83fa4ed | 2131 | bail ("ERROR: encountered “%s” but secret already given" % arg) |
da82bc58 | 2132 | |
70ad9458 PG |
2133 | for arg in argvi: |
2134 | if arg in [ "-h", "--help" ]: | |
2135 | usage () | |
2136 | raise Unreachable | |
2137 | elif arg in [ "-v", "--verbose", "--wtf" ]: | |
2138 | global PDTCRYPT_VERBOSE | |
2139 | PDTCRYPT_VERBOSE = True | |
2140 | elif arg in [ "-i", "--in", "--source" ]: | |
59d74e2b | 2141 | insspec = checked_arg () |
70ad9458 | 2142 | if PDTCRYPT_VERBOSE is True: noise ("PDT: decrypt from %s" % insspec) |
a83fa4ed | 2143 | elif arg in [ "-p", "--password" ]: |
59d74e2b | 2144 | arg = checked_arg () |
addcec42 | 2145 | checked_secret (make_secret (password=arg)) |
a83fa4ed | 2146 | if PDTCRYPT_VERBOSE is True: noise ("PDT: decrypting with password") |
70ad9458 | 2147 | else: |
da82bc58 PG |
2148 | if subcommand == PDTCRYPT_SUB_PROCESS: |
2149 | if arg in [ "-s", "--strict-ivs" ]: | |
2150 | global PDTCRYPT_STRICTIVS | |
2151 | PDTCRYPT_STRICTIVS = True | |
77058bab PG |
2152 | elif arg in [ "-o", "--out", "--dest", "--sink" ]: |
2153 | outsspec = checked_arg () | |
2154 | if PDTCRYPT_VERBOSE is True: noise ("PDT: decrypt to %s" % outsspec) | |
da82bc58 | 2155 | elif arg in [ "-f", "--force" ]: |
da82bc58 PG |
2156 | PDTCRYPT_OVERWRITE = True |
2157 | if PDTCRYPT_VERBOSE is True: noise ("PDT: overwrite existing files") | |
2158 | elif arg in [ "-S", "--split" ]: | |
2159 | mode |= PDTCRYPT_SPLIT | |
2160 | if PDTCRYPT_VERBOSE is True: noise ("PDT: split files") | |
2161 | elif arg in [ "-D", "--no-decrypt" ]: | |
2162 | mode &= ~PDTCRYPT_DECRYPT | |
2163 | if PDTCRYPT_VERBOSE is True: noise ("PDT: not decrypting") | |
a83fa4ed | 2164 | elif arg in [ "-k", "--key" ]: |
59d74e2b | 2165 | arg = checked_arg () |
addcec42 | 2166 | checked_secret (make_secret (key=arg)) |
a83fa4ed | 2167 | if PDTCRYPT_VERBOSE is True: noise ("PDT: decrypting with key") |
da82bc58 | 2168 | else: |
a83fa4ed | 2169 | bail ("ERROR: unexpected positional argument “%s”" % arg) |
da82bc58 | 2170 | elif subcommand == PDTCRYPT_SUB_SCRYPT: |
77058bab PG |
2171 | if arg in [ "-n", "--nacl", "--salt" ]: |
2172 | nacl = checked_arg () | |
2173 | if PDTCRYPT_VERBOSE is True: noise ("PDT: salt key with %s" % nacl) | |
7b3940e5 PG |
2174 | elif arg in [ "-f", "--format" ]: |
2175 | arg = checked_arg () | |
2176 | try: | |
2177 | scrypt_format = PDTCRYPT_SCRYPT_FORMAT [arg] | |
2178 | except KeyError: | |
2179 | bail ("ERROR: invalid scrypt output format %s" % arg) | |
2180 | if PDTCRYPT_VERBOSE is True: | |
2181 | noise ("PDT: scrypt output format “%s”" % scrypt_format) | |
77058bab PG |
2182 | else: |
2183 | bail ("ERROR: unexpected positional argument “%s”" % arg) | |
f41973a6 | 2184 | elif subcommand == PDTCRYPT_SUB_SCAN: |
a808459e PG |
2185 | if arg in [ "-o", "--out", "--dest", "--sink" ]: |
2186 | outsspec = checked_arg () | |
2187 | if PDTCRYPT_VERBOSE is True: noise ("PDT: decrypt to %s" % outsspec) | |
2188 | elif arg in [ "-f", "--force" ]: | |
a808459e PG |
2189 | PDTCRYPT_OVERWRITE = True |
2190 | if PDTCRYPT_VERBOSE is True: noise ("PDT: overwrite existing files") | |
2191 | else: | |
2192 | bail ("ERROR: unexpected positional argument “%s”" % arg) | |
70ad9458 | 2193 | |
a83fa4ed | 2194 | if secret is None: |
ecb9676d | 2195 | if PDTCRYPT_VERBOSE is True: |
a83fa4ed | 2196 | noise ("ERROR: no password or key specified, trying $PDTCRYPT_PASSWORD") |
ecb9676d PG |
2197 | epw = os.getenv ("PDTCRYPT_PASSWORD") |
2198 | if epw is not None: | |
addcec42 | 2199 | checked_secret (make_secret (password=epw.strip ())) |
a83fa4ed PG |
2200 | |
2201 | if secret is None: | |
2202 | if PDTCRYPT_VERBOSE is True: | |
2203 | noise ("ERROR: no password or key specified, trying $PDTCRYPT_KEY") | |
2204 | ek = os.getenv ("PDTCRYPT_KEY") | |
2205 | if ek is not None: | |
addcec42 | 2206 | checked_secret (make_secret (key=ek.strip ())) |
ecb9676d | 2207 | |
a83fa4ed | 2208 | if secret is None: |
da82bc58 | 2209 | if subcommand == PDTCRYPT_SUB_SCRYPT: |
a83fa4ed | 2210 | bail ("ERROR: scrypt hash mode requested but no password given") |
da82bc58 | 2211 | elif mode & PDTCRYPT_DECRYPT: |
6257d5b3 | 2212 | bail ("ERROR: decryption requested but no password given") |
a83fa4ed | 2213 | |
a808459e PG |
2214 | if mode & PDTCRYPT_SPLIT and outsspec is None: |
2215 | bail ("ERROR: split mode is incompatible with stdout sink " | |
2216 | "(the default)") | |
2217 | ||
2218 | if subcommand == PDTCRYPT_SUB_SCAN and outsspec is None: | |
2219 | pass # no output by default in scan mode | |
2220 | elif mode & PDTCRYPT_SPLIT or subcommand == PDTCRYPT_SUB_SCAN: | |
2221 | # destination must be directory | |
2222 | if outsspec == "-": | |
2223 | bail ("ERROR: mode is incompatible with stdout sink") | |
2224 | try: | |
2225 | try: | |
2226 | os.makedirs (outsspec, 0o700) | |
2227 | except FileExistsError: | |
2228 | # if it’s a directory with appropriate perms, everything is | |
2229 | # good; otherwise, below invocation of open(2) will fail | |
2230 | pass | |
2231 | outs = os.open (outsspec, os.O_DIRECTORY, 0o600) | |
2232 | except FileNotFoundError as exn: | |
2233 | bail ("ERROR: cannot create target directory “%s”" % outsspec) | |
2234 | except NotADirectoryError as exn: | |
2235 | bail ("ERROR: target path “%s” is not a directory" % outsspec) | |
2236 | else: | |
2237 | outs = deptdcrypt_mk_stream (PDTCRYPT_SINK, outsspec or "-") | |
2238 | ||
f41973a6 PG |
2239 | if subcommand == PDTCRYPT_SUB_SCAN: |
2240 | if insspec is None: | |
2241 | bail ("ERROR: please supply an input file for scanning") | |
2242 | if insspec == '-': | |
2243 | bail ("ERROR: input must be seekable; please specify a file") | |
a808459e | 2244 | return True, partial (mode_scan, secret, insspec, outs, nacl=nacl) |
f41973a6 | 2245 | |
77058bab PG |
2246 | if subcommand == PDTCRYPT_SUB_SCRYPT: |
2247 | if secret [0] == PDTCRYPT_SECRET_KEY: | |
2248 | bail ("ERROR: scrypt mode requires a password") | |
2249 | if insspec is not None and nacl is not None \ | |
2250 | or insspec is None and nacl is None : | |
2251 | bail ("ERROR: please supply either an input file or " | |
2252 | "the salt") | |
70ad9458 PG |
2253 | |
2254 | # default to stdout | |
77058bab PG |
2255 | ins = None |
2256 | if insspec is not None or subcommand != PDTCRYPT_SUB_SCRYPT: | |
2257 | ins = deptdcrypt_mk_stream (PDTCRYPT_SOURCE, insspec or "-") | |
da82bc58 PG |
2258 | |
2259 | if subcommand == PDTCRYPT_SUB_SCRYPT: | |
7b3940e5 PG |
2260 | return True, partial (mode_scrypt, secret [1].encode (), ins, nacl, |
2261 | fmt=scrypt_format) | |
da82bc58 | 2262 | |
a83fa4ed | 2263 | return True, partial (mode_depdtcrypt, mode, secret, ins, outs) |
15d3eefd PG |
2264 | |
2265 | ||
00b3cd10 | 2266 | def main (argv): |
da82bc58 | 2267 | ok, runner = parse_argv (argv) |
f08c604b | 2268 | |
da82bc58 | 2269 | if ok is True: return runner () |
15d3eefd | 2270 | |
da82bc58 | 2271 | return 1 |
f08c604b | 2272 | |
00b3cd10 PG |
2273 | |
2274 | if __name__ == "__main__": | |
2275 | sys.exit (main (sys.argv)) | |
2276 |