/usr/lib/python2.7/dist-packages/rekall/plugins/addrspaces/aff4.py is in python-rekall-core 1.6.0+dfsg-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 | # Rekall Memory Forensics
#
# Copyright 2015 Google Inc. All Rights Reserved.
#
# Authors:
# Copyright (C) 2015 Michael Cohen <scudette@google.com>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or (at
# your option) any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
"""This Address Space allows us to open aff4 images.
AFF4 images are produced by the Rekall memory acquisition tools (Pmem and
friends).
For this address space to work:
pip install pyaff4
"""
import logging
import re
import os
from pyaff4 import data_store
try:
from pyaff4 import aff4_cloud
except ImportError:
aff4_cloud = None
from pyaff4 import aff4_directory
from pyaff4 import zip
from pyaff4 import lexicon
from pyaff4 import rdfvalue
from pyaff4 import plugins # pylint: disable=unused-import
from rekall import addrspace
from rekall import cache
from rekall import yaml_utils
from rekall import utils
from rekall.plugins.addrspaces import standard
# Control the logging level for the pyaff4 library logger.
LOGGER = logging.getLogger("pyaff4")
LOGGER.setLevel(logging.ERROR)
class AFF4StreamWrapper(object):
def __init__(self, stream):
self.stream = stream
def read(self, offset, length):
self.stream.seek(offset)
return self.stream.read(length)
def end(self):
return self.stream.Size()
def __unicode__(self):
return utils.SmartUnicode(self.stream.urn)
class AFF4AddressSpace(addrspace.CachingAddressSpaceMixIn,
addrspace.RunBasedAddressSpace):
"""Handle AFF4Map or AFF4Image type streams.
Since AFF4 volumes may contain multiple streams, we allow the stream to be
specified inside the volume path. For example suppose the volume located at:
/home/mic/images/myimage.aff4
Contains a stream called PhysicalMemory, then we can specify the filename
as:
/home/mic/images/myimage.aff4/PhysicalMemory
If we just specified the path to the volume, then this address space will
pick the first AFF4 stream which has an aff4:category of
lexicon.AFF4_MEMORY_PHYSICAL.
So if you have more than one physical memory stream in the same volume, you
will need to specify the full path to the stream within the volume.
"""
__name = "aff4"
__image = True
# This AS can map files into itself.
__can_map_files = True
order = standard.FileAddressSpace.order - 10
def __init__(self, filename=None, **kwargs):
super(AFF4AddressSpace, self).__init__(**kwargs)
self.as_assert(self.base == None,
"Must stack on another address space")
path = filename or self.session.GetParameter("filename")
self.as_assert(path != None, "Filename must be specified")
self.image = None
self.resolver = data_store.MemoryDataStore()
# If we have a cache directory, configure AFF4 to use it.
try:
cache_dir = cache.GetCacheDir(self.session)
if cache_dir:
self.resolver.Set(lexicon.AFF4_CONFIG_CACHE_DIR,
lexicon.AFF4_FILE_NAME,
rdfvalue.XSDString(
os.path.join(cache_dir, "aff4_cache")))
except IOError:
pass
# A map between the filename and the offset it is mapped into the
# address space.
self.mapped_files = {}
try:
volume_path, stream_path = self._LocateAFF4Volume(path)
except IOError as e:
self.session.logging.debug("Unable to open AFF4 image %s", e)
raise addrspace.ASAssertionError("Unable to open AFF4 volume")
# filename is a volume, and there is no stream specified, just autoload
# the stream if possible.
if not stream_path:
try:
self._AutoLoadAFF4Volume(volume_path)
return
except IOError as e:
raise addrspace.ASAssertionError(
"Unable to open AFF4 volume: %s" % e)
# If the user asked for a specific stream just load that one. Note that
# you can still load the pagefile manually using the --pagefile
# parameter.
try:
image_urn = volume_path.Append(stream_path)
self._LoadMemoryImage(image_urn)
except IOError as e:
raise addrspace.ASAssertionError(
"Unable to open AFF4 stream %s: %s" % (
stream_path, e))
def _LocateAFF4Volume(self, filename):
stream_name = []
path_components = list(filename.split(os.sep))
while path_components:
volume_path = os.sep.join(path_components)
volume_urn = rdfvalue.URN.NewURNFromFilename(volume_path)
volume_urn_parts = volume_urn.Parse()
if volume_urn_parts.scheme == "file":
if os.path.isfile(volume_path):
with zip.ZipFile.NewZipFile(
self.resolver, volume_urn) as volume:
if stream_name:
return volume.urn, os.sep.join(stream_name)
return volume.urn, None
elif os.path.isdir(volume_path):
with aff4_directory.AFF4Directory.NewAFF4Directory(
self.resolver, volume_urn) as volume:
if stream_name:
return volume.urn, os.sep.join(stream_name)
return volume.urn, None
else:
# volume_path is not valid.
return None, None
elif volume_urn_parts.scheme == "gs" and aff4_cloud:
with aff4_cloud.AFF4GStore.NewAFF4GStore(
self.resolver, volume_urn) as volume:
if stream_name:
return volume.urn, os.sep.join(stream_name)
return volume.urn, None
# File does not exist - maybe the path stem points at a stream in
# the image.
else:
stream_name.insert(0, path_components.pop(-1))
raise IOError("Not found")
def _AutoLoadAFF4Volume(self, path):
with self.resolver.AFF4FactoryOpen(path) as volume:
self.volume_urn = volume.urn
# We are searching for images with the physical memory category.
for (subject, _, value) in self.resolver.QueryPredicate(
lexicon.AFF4_CATEGORY):
if value == lexicon.AFF4_MEMORY_PHYSICAL:
self._LoadMemoryImage(subject)
break
self.as_assert(self.image is not None,
"No physical memory categories found.")
self.filenames = {}
# Newer AFF4 images should have the AFF4_STREAM_ORIGINAL_FILENAME
# attribute set.
for (subject, _, value) in self.resolver.QueryPredicate(
lexicon.AFF4_STREAM_ORIGINAL_FILENAME):
# Normalize the filename for case insensitive filesysyems.
self.filenames[unicode(value).lower()] = subject
# TODO: Deprecate this guessing once all images have the
# AFF4_STREAM_ORIGINAL_FILENAME attribute.
for subject in self.resolver.QuerySubject(re.compile(".")):
relative_name = self.volume_urn.RelativePath(subject)
if relative_name:
filename = self._normalize_filename(relative_name)
self.filenames[filename] = subject
def _normalize_filename(self, filename):
"""Normalize the filename based on the source OS."""
m = re.match(r"/?([a-zA-Z]:[/\\].+)", filename)
if m:
# This is a windows filename.
filename = m.group(1).replace("/", "\\")
return filename.lower()
return filename
def _LoadMemoryImage(self, image_urn):
aff4_stream = self.resolver.AFF4FactoryOpen(image_urn)
self.image = AFF4StreamWrapper(aff4_stream)
# Add the ranges if this is a map.
try:
for map_range in aff4_stream.GetRanges():
self.add_run(map_range.map_offset,
map_range.map_offset,
map_range.length,
self.image)
except AttributeError:
self.add_run(0, 0, aff4_stream.Size(), self.image)
self.session.logging.info("Added %s as physical memory", image_urn)
def ConfigureSession(self, session):
self._parse_physical_memory_metadata(session, self.image.stream.urn)
def file_mapping_offset(self, filename):
"""Returns the offset where the filename should be mapped.
This function manages the session cache. By storing the file mappings in
the session cache we can guarantee repeatable mappings.
"""
mapped_files = self.session.GetParameter("file_mappings", {})
if filename in mapped_files:
return utils.CaseInsensitiveDictLookup(
filename, mapped_files)
# Give a bit of space for the mapping and page align it.
mapped_offset = (self.end() + 0x10000) & 0xFFFFFFFFFFFFF000
mapped_files[filename] = mapped_offset
self.session.SetCache("file_mappings", mapped_files)
return mapped_offset
def get_file_address_space(self, filename):
"""Return an address space for filename."""
subject = utils.CaseInsensitiveDictLookup(
filename, self.filenames)
if subject:
return AFF4StreamWrapper(self.resolver.AFF4FactoryOpen(subject))
return
def get_mapped_offset(self, filename, file_offset=0):
"""Map the filename into the address space.
If the filename is found in the AFF4 image, we return the offset in this
address space corresponding to file_offset in the mapped file.
If the file is not mapped, return None.
"""
mapped_offset = None
filename = self._normalize_filename(filename)
mapped_offset = utils.CaseInsensitiveDictLookup(
filename, self.mapped_files)
if mapped_offset is None:
# Try to map the file.
subject = utils.CaseInsensitiveDictLookup(
filename, self.filenames)
# Fall back to looking up the sysnative path in case the
# image was acquired by a 32 bit imager.
if not subject:
# The 32 bit WinPmem imager access native files via
# SysNative but they are really located in System32.
subject = utils.CaseInsensitiveDictLookup(
filename.replace("SysNative", "System32"),
self.filenames)
if subject:
stream = self.resolver.AFF4FactoryOpen(subject)
mapped_offset = self.file_mapping_offset(filename)
self.add_run(mapped_offset, 0, stream.Size(),
AFF4StreamWrapper(stream))
self.session.logging.info(
"Mapped %s into address %#x", stream.urn, mapped_offset)
else:
# Cache failures too.
mapped_offset = -1
# Cache for next time.
self.mapped_files[filename] = mapped_offset
if mapped_offset > 0:
return mapped_offset + file_offset
_parameter = [
("dtb", "Registers.CR3"),
("kernel_base", "KernBase"),
("vm_kernel_slide", "kaslr_slide")
]
def _parse_physical_memory_metadata(self, session, image_urn):
try:
with self.resolver.AFF4FactoryOpen(
image_urn.Append("information.yaml")) as fd:
metadata = yaml_utils.decode(fd.read(10000000))
for session_param, info_para in self._parameter:
# Allow the user to override the AFF4 file.
if session.HasParameter(session_param):
continue
tmp = metadata
value = None
for key in info_para.split("."):
value = tmp.get(key)
if value is None:
break
tmp = value
if value is not None:
session.SetCache(session_param, value, volatile=False)
except IOError:
session.logging.info(
"AFF4 volume does not contain %s/information.yaml" % image_urn)
def describe(self, address):
start, _, run = self.runs.get_containing_range(address)
if start is None:
# For unmapped streams just say we have no idea.
return u"%#x (Unmapped)" % address
# For normal physical memory addresses just be concise.
if run.address_space == self.image:
return u"%#x" % address
# For other mapped streams, just say which ones they are.
return u"%#x @ %s (Mapped %#x)" % (
address - start, run.address_space, address)
# pylint: disable=unused-import, wrong-import-order
# Add these so that pyinstaller builds these dependencies in.
import rdflib.plugins.memory
import rdflib.plugins.parsers.hturtle
import rdflib.plugins.parsers.notation3
import rdflib.plugins.parsers.nquads
import rdflib.plugins.parsers.nt
import rdflib.plugins.parsers.rdfxml
import rdflib.plugins.parsers.structureddata
import rdflib.plugins.parsers.trig
import rdflib.plugins.parsers.trix
import rdflib.plugins.serializers.n3
import rdflib.plugins.serializers.nquads
import rdflib.plugins.serializers.nt
import rdflib.plugins.serializers.rdfxml
import rdflib.plugins.serializers.trig
import rdflib.plugins.serializers.trix
import rdflib.plugins.serializers.turtle
import rdflib.plugins.sleepycat
import rdflib.plugins.sparql.processor
import rdflib.plugins.sparql.results.csvresults
import rdflib.plugins.sparql.results.jsonresults
import rdflib.plugins.sparql.results.tsvresults
import rdflib.plugins.sparql.results.txtresults
import rdflib.plugins.sparql.results.xmlresults
import rdflib.plugins.stores.auditable
import rdflib.plugins.stores.concurrent
import rdflib.plugins.stores.sparqlstore
|