diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml new file mode 100644 index 0000000..e728712 --- /dev/null +++ b/.github/workflows/build.yml @@ -0,0 +1,15 @@ +name: pylint +on: [push, pull_request] + +jobs: + pylint: + name: Python Lint + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v2 + + - name: Install pylint + run: pip install pylint + + - name: Run pylint + run: pylint --reports=y --rcfile .pylintrc *.py ./kconfig diff --git a/.pylintrc b/.pylintrc new file mode 100644 index 0000000..bcb98c3 --- /dev/null +++ b/.pylintrc @@ -0,0 +1,566 @@ +[MASTER] + +# A comma-separated list of package or module names from where C extensions may +# be loaded. Extensions are loading into the active Python interpreter and may +# run arbitrary code. +extension-pkg-whitelist= + +# Add files or directories to the blacklist. They should be base names, not +# paths. +ignore=CVS + +# Add files or directories matching the regex patterns to the blacklist. The +# regex matches against base names, not paths. +ignore-patterns= + +# Python code to execute, usually for sys.path manipulation such as +# pygtk.require(). +#init-hook= + +# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the +# number of processors available to use. +jobs=1 + +# Control the amount of potential inferred values when inferring a single +# object. This can help the performance when dealing with large functions or +# complex, nested conditions. +limit-inference-results=120 + +# List of plugins (as comma separated values of python modules names) to load, +# usually to register additional checkers. +load-plugins= + +# Pickle collected data for later comparisons. +persistent=yes + +# Specify a configuration file. +#rcfile= + +# When enabled, pylint would attempt to guess common misconfiguration and emit +# user-friendly hints instead of false-positive error messages. +suggestion-mode=yes + +# Allow loading of arbitrary C extensions. Extensions are imported into the +# active Python interpreter and may run arbitrary code. +unsafe-load-any-extension=no + + +[MESSAGES CONTROL] + +# Only show warnings with the listed confidence levels. Leave empty to show +# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED. +confidence= + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once). You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use "--disable=all --enable=classes +# --disable=W". +disable=print-statement, + parameter-unpacking, + unpacking-in-except, + old-raise-syntax, + backtick, + long-suffix, + old-ne-operator, + old-octal-literal, + import-star-module-level, + non-ascii-bytes-literal, + raw-checker-failed, + bad-inline-option, + locally-disabled, + file-ignored, + suppressed-message, + useless-suppression, + deprecated-pragma, + use-symbolic-message-instead, + apply-builtin, + basestring-builtin, + buffer-builtin, + cmp-builtin, + coerce-builtin, + execfile-builtin, + file-builtin, + long-builtin, + raw_input-builtin, + reduce-builtin, + standarderror-builtin, + unicode-builtin, + xrange-builtin, + coerce-method, + delslice-method, + getslice-method, + setslice-method, + no-absolute-import, + old-division, + dict-iter-method, + dict-view-method, + next-method-called, + metaclass-assignment, + indexing-exception, + raising-string, + reload-builtin, + oct-method, + hex-method, + nonzero-method, + cmp-method, + input-builtin, + round-builtin, + intern-builtin, + unichr-builtin, + map-builtin-not-iterating, + zip-builtin-not-iterating, + range-builtin-not-iterating, + filter-builtin-not-iterating, + using-cmp-argument, + eq-without-hash, + div-method, + idiv-method, + rdiv-method, + exception-message-attribute, + invalid-str-codec, + sys-max-int, + bad-python3-import, + deprecated-string-function, + deprecated-str-translate-call, + deprecated-itertools-function, + deprecated-types-field, + next-method-defined, + dict-items-not-iterating, + dict-keys-not-iterating, + dict-values-not-iterating, + deprecated-operator-function, + deprecated-urllib-function, + xreadlines-attribute, + deprecated-sys-function, + exception-escape, + comprehension-escape, + invalid-name, + import-error, + fixme, + too-few-public-methods, + attribute-defined-outside-init, + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time (only on the command line, not in the configuration file where +# it should appear only once). See also the "--disable" option for examples. +enable=c-extension-no-member + + +[REPORTS] + +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) + +# Template used to display messages. This is a python new-style format string +# used to format the message information. See doc for all details. +#msg-template= + +# Set the output format. Available formats are text, parseable, colorized, json +# and msvs (visual studio). You can also give a reporter class, e.g. +# mypackage.mymodule.MyReporterClass. +output-format=text + +# Tells whether to display a full report or only the messages. +reports=no + +# Activate the evaluation score. +score=yes + + +[REFACTORING] + +# Maximum number of nested blocks for function / method body +max-nested-blocks=5 + +# Complete name of functions that never returns. When checking for +# inconsistent-return-statements if a never returning function is called then +# it will be considered as an explicit return statement and no message will be +# printed. +never-returning-functions=sys.exit + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME, + XXX, + TODO + + +[SPELLING] + +# Limits count of emitted suggestions for spelling mistakes. +max-spelling-suggestions=4 + +# Spelling dictionary name. Available dictionaries: none. To make it working +# install python-enchant package.. +spelling-dict= + +# List of comma separated words that should not be checked. +spelling-ignore-words= + +# A path to a file that contains private dictionary; one word per line. +spelling-private-dict-file= + +# Tells whether to store unknown words to indicated private dictionary in +# --spelling-private-dict-file option instead of raising a message. +spelling-store-unknown-words=no + + +[BASIC] + +# Naming style matching correct argument names. +argument-naming-style=snake_case + +# Regular expression matching correct argument names. Overrides argument- +# naming-style. +#argument-rgx= + +# Naming style matching correct attribute names. +attr-naming-style=snake_case + +# Regular expression matching correct attribute names. Overrides attr-naming- +# style. +#attr-rgx= + +# Bad variable names which should always be refused, separated by a comma. +bad-names=foo, + bar, + baz, + toto, + tutu, + tata + +# Naming style matching correct class attribute names. +class-attribute-naming-style=any + +# Regular expression matching correct class attribute names. Overrides class- +# attribute-naming-style. +#class-attribute-rgx= + +# Naming style matching correct class names. +class-naming-style=PascalCase + +# Regular expression matching correct class names. Overrides class-naming- +# style. +#class-rgx= + +# Naming style matching correct constant names. +const-naming-style=UPPER_CASE + +# Regular expression matching correct constant names. Overrides const-naming- +# style. +#const-rgx= + +# Minimum line length for functions/classes that require docstrings, shorter +# ones are exempt. +docstring-min-length=-1 + +# Naming style matching correct function names. +function-naming-style=snake_case + +# Regular expression matching correct function names. Overrides function- +# naming-style. +#function-rgx= + +# Good variable names which should always be accepted, separated by a comma. +good-names=i, + j, + k, + ex, + Run, + _ + +# Include a hint for the correct naming format with invalid-name. +include-naming-hint=no + +# Naming style matching correct inline iteration names. +inlinevar-naming-style=any + +# Regular expression matching correct inline iteration names. Overrides +# inlinevar-naming-style. +#inlinevar-rgx= + +# Naming style matching correct method names. +method-naming-style=snake_case + +# Regular expression matching correct method names. Overrides method-naming- +# style. +#method-rgx= + +# Naming style matching correct module names. +module-naming-style=snake_case + +# Regular expression matching correct module names. Overrides module-naming- +# style. +#module-rgx= + +# Colon-delimited sets of names that determine each other's naming style when +# the name regexes allow several styles. +name-group= + +# Regular expression which should only match function or class names that do +# not require a docstring. +no-docstring-rgx=^_ + +# List of decorators that produce properties, such as abc.abstractproperty. Add +# to this list to register other decorators that produce valid properties. +# These decorators are taken in consideration only for invalid-name. +property-classes=abc.abstractproperty + +# Naming style matching correct variable names. +variable-naming-style=snake_case + +# Regular expression matching correct variable names. Overrides variable- +# naming-style. +#variable-rgx= + + +[LOGGING] + +# Format style used to check logging format string. `old` means using % +# formatting, while `new` is for `{}` formatting. +logging-format-style=old + +# Logging modules to check that the string format arguments are in logging +# function parameter format. +logging-modules=logging + + +[VARIABLES] + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid defining new builtins when possible. +additional-builtins= + +# Tells whether unused global variables should be treated as a violation. +allow-global-unused-variables=yes + +# List of strings which can identify a callback function by name. A callback +# name must start or end with one of those strings. +callbacks=cb_, + _cb + +# A regular expression matching the name of dummy variables (i.e. expected to +# not be used). +dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_ + +# Argument names that match this expression will be ignored. Default to name +# with leading underscore. +ignored-argument-names=_.*|^ignored_|^unused_ + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# List of qualified module names which can have objects that can redefine +# builtins. +redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io + + +[TYPECHECK] + +# List of decorators that produce context managers, such as +# contextlib.contextmanager. Add to this list to register other decorators that +# produce valid context managers. +contextmanager-decorators=contextlib.contextmanager + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E1101 when accessed. Python regular +# expressions are accepted. +generated-members= + +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes + +# Tells whether to warn about missing members when the owner of the attribute +# is inferred to be None. +ignore-none=yes + +# This flag controls whether pylint should warn about no-member and similar +# checks whenever an opaque object is returned when inferring. The inference +# can return multiple potential results while evaluating a Python object, but +# some branches might not be evaluated, which results in partial inference. In +# that case, it might be useful to still emit no-member and other checks for +# the rest of the inferred objects. +ignore-on-opaque-inference=yes + +# List of class names for which member attributes should not be checked (useful +# for classes with dynamically set attributes). This supports the use of +# qualified names. +ignored-classes=optparse.Values,thread._local,_thread._local + +# List of module names for which member attributes should not be checked +# (useful for modules/projects where namespaces are manipulated during runtime +# and thus existing member attributes cannot be deduced by static analysis. It +# supports qualified module names, as well as Unix pattern matching. +ignored-modules= + +# Show a hint with possible names when a member name was not found. The aspect +# of finding the hint is based on edit distance. +missing-member-hint=yes + +# The minimum edit distance a name should have in order to be considered a +# similar match for a missing member name. +missing-member-hint-distance=1 + +# The total number of similar names that should be taken in consideration when +# showing a hint for a missing member. +missing-member-max-choices=1 + + +[FORMAT] + +# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. +expected-line-ending-format= + +# Regexp for a line that is allowed to be longer than the limit. +ignore-long-lines=^\s*(# )??$ + +# Number of spaces of indent required inside a hanging or continued line. +indent-after-paren=4 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + +# Maximum number of characters on a single line. +max-line-length=120 + +# Maximum number of lines in a module. +max-module-lines=1000 + +# List of optional constructs for which whitespace checking is disabled. `dict- +# separator` is used to allow tabulation in dicts, etc.: {1 : 1,\n222: 2}. +# `trailing-comma` allows a space between comma and closing bracket: (a, ). +# `empty-line` allows space-only lines. +no-space-check=trailing-comma, + dict-separator + +# Allow the body of a class to be on the same line as the declaration if body +# contains single statement. +single-line-class-stmt=no + +# Allow the body of an if to be on the same line as the test if there is no +# else. +single-line-if-stmt=no + + +[SIMILARITIES] + +# Ignore comments when computing similarities. +ignore-comments=yes + +# Ignore docstrings when computing similarities. +ignore-docstrings=yes + +# Ignore imports when computing similarities. +ignore-imports=no + +# Minimum lines number of a similarity. +min-similarity-lines=4 + + +[DESIGN] + +# Maximum number of arguments for function / method. +max-args=5 + +# Maximum number of attributes for a class (see R0902). +max-attributes=7 + +# Maximum number of boolean expressions in an if statement. +max-bool-expr=5 + +# Maximum number of branch for function / method body. +max-branches=12 + +# Maximum number of locals for function / method body. +max-locals=15 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=20 + +# Maximum number of return / yield for function / method body. +max-returns=6 + +# Maximum number of statements in function / method body. +max-statements=50 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + + +[IMPORTS] + +# Allow wildcard imports from modules that define __all__. +allow-wildcard-with-all=no + +# Analyse import fallback blocks. This can be used to support both Python 2 and +# 3 compatible code, which means that the block might have code that exists +# only in one or another interpreter, leading to false positives when analysed. +analyse-fallback-blocks=no + +# Deprecated modules which should not be used, separated by a comma. +deprecated-modules=optparse,tkinter.tix + +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled). +ext-import-graph= + +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled). +import-graph= + +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled). +int-import-graph= + +# Force import order to recognize a module as part of the standard +# compatibility libraries. +known-standard-library= + +# Force import order to recognize a module as part of a third party library. +known-third-party=enchant + + +[CLASSES] + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__, + __new__, + setUp + +# List of member names, which should be excluded from the protected access +# warning. +exclude-protected=_asdict, + _fields, + _replace, + _source, + _make + +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls + +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=cls + + +[EXCEPTIONS] + +# Exceptions that will emit a warning when being caught. Defaults to +# "Exception". +overgeneral-exceptions=Exception diff --git a/README.md b/README.md index d8a0022..8c03463 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# bn-kconfig-recover +# bn-kconfig-recover ![Python Lint](https://github.com/zznop/bn-kconfig-recover/workflows/pylint/badge.svg) ![demo bn-kconfig-recover](bn-kconfig-recover.gif) diff --git a/bn_kconfig_recover.py b/bn_kconfig_recover.py index 50699c4..078f674 100644 --- a/bn_kconfig_recover.py +++ b/bn_kconfig_recover.py @@ -39,14 +39,18 @@ def main(): else: logger.setLevel(logging.INFO) - logging.info(f'Opening "{args.bndb}" and getting view...') - bv = BinaryViewType.get_view_of_file(args.bndb) + logging.info('Opening "%s" and getting view...', args.bndb) + view = BinaryViewType.get_view_of_file(args.bndb) logging.info('Running BN analysis, this may take some time...') - #bv.reanalyze() - bv.update_analysis_and_wait() - recover = KConfigRecover(bv) - config = recover.do() + # This is needed to relocate strings, apparently update_analysis_and_wait isn't enough. I + # recommend commenting this line for dev (if you don't need to use get_string_at APIs + view.reanalyze() + + view.update_analysis_and_wait() + + kconfigr = KConfigRecover(view) + config = kconfigr.recover() save_kconfig(config, args.kconfig) diff --git a/kconfig/__init__.py b/kconfig/__init__.py index ef9a7c5..3be7e07 100644 --- a/kconfig/__init__.py +++ b/kconfig/__init__.py @@ -1 +1,4 @@ -from .recover import KConfigRecover, save_kconfig \ No newline at end of file +"""Exports for kconfig package +""" + +from .recover import KConfigRecover, save_kconfig diff --git a/kconfig/recover.py b/kconfig/recover.py index 7f9a27a..abc99af 100644 --- a/kconfig/recover.py +++ b/kconfig/recover.py @@ -1,9 +1,20 @@ -from binaryninja import BinaryView, HighLevelILOperation, BinaryReader +"""Contains classes and helper functions for using BN API to recover kernel configuration options +""" + from enum import Enum import logging +from binaryninja import BinaryView, HighLevelILOperation + +class AnalysisError(Exception): + """Excepton raised if there is an error or unexpected issue when analyzing code + """ class ConfigStatus(Enum): + """Enum that represent whether a boolean configuration option is set, unset, or there was an + error while trying to recover + """ + # Configuration is not set NOT_SET = 0 # Configuration is set @@ -20,24 +31,24 @@ def save_kconfig(config: dict, filepath: str): filepath: Path to output kconfig file. """ - with open(filepath, 'w') as f: + with open(filepath, 'w', encoding='utf-8') as _file: for subsystem, settings in config.items(): - f.write('#\n' f"# {subsystem}\n" '#\n') + _file.write('#\n' f"# {subsystem}\n" '#\n') for name, setting in settings.items(): if not setting: - f.write(f'# {name} needs user intervention\n') + _file.write(f'# {name} needs user intervention\n') elif isinstance(setting, str): - f.write(f'{name}="{setting}"\n') + _file.write(f'{name}="{setting}"\n') elif isinstance(setting, ConfigStatus): if setting == ConfigStatus.SET: - f.write(f'{name}=y\n') + _file.write(f'{name}=y\n') elif setting == ConfigStatus.NOT_SET: - f.write(f'# {name} is not set\n') + _file.write(f'# {name} is not set\n') elif setting == ConfigStatus.ERROR: - f.write(f'# {name} needs user intervention\n') - f.write('\n') + _file.write(f'# {name} needs user intervention\n') + _file.write('\n') - logging.info(f'Recovered kconfig saved to "{filepath}"') + logging.info('Recovered kconfig saved to "%s"', filepath) def to_ulong(i: int) -> int: @@ -56,9 +67,9 @@ def to_ulong(i: int) -> int: class KConfigRecover: """Class that uses BN API to attempt to recover kernel configurations. """ - def __init__(self, bv: BinaryView): - self.bv = bv - self.br = BinaryReader(self.bv) + + def __init__(self, view: BinaryView): + self.view = view self.helpers = { 'General Setup': { # General setup @@ -100,7 +111,8 @@ def __init__(self, bv: BinaryView): self._recover_config_generic_msi_irq_domain, 'CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR': self._recover_config_generic_irq_matrix_allocator, - # There is no way to determine whether or not this setting is set. It's used for PCI drivers (see drivers/pci/msi.c) + # There is no way to determine whether or not this setting is set. It's used for + # PCI drivers (see drivers/pci/msi.c) 'CONFIG_GENERIC_IRQ_RESERVATION_MODE': None, 'CONFIG_IRQ_FORCED_THREADING': @@ -113,8 +125,8 @@ def __init__(self, bv: BinaryView): self._recover_config_clocksource_watchdog, 'CONFIG_ARCH_CLOCKSOURCE_DATA': self._recover_config_arch_clocksource_data, - # TODO: I think we can get this one, but it will be a lot of work and won't make a difference for - # building drivers. See kernel/time/timekeeping_internal.h + # I think we can get this one, but it will be a lot of work and won't make a + # difference for building LKMs. See kernel/time/timekeeping_internal.h 'CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE': None, 'CONFIG_GENERIC_TIME_VSYSCALL': @@ -123,8 +135,9 @@ def __init__(self, bv: BinaryView): self._recover_config_generic_clockevents, 'CONFIG_GENERIC_CLOCKEVENTS_BROADCAST': self._recover_config_generic_clockevents_broadcast, - # TODO: Another one we might be able to get, but may not be worth the effort. Slightly changes - # clockevents_program_min_delta, a static function in kernel/time/clockevents.c + # Another one we might be able to get, but may not be worth the effort. + # Slightly changes clockevents_program_min_delta, a static function in + # kernel/time/clockevents.c 'CONFIG_GENERIC_CLOCKEVENTS_MIN_BROADCAST': None, 'CONFIG_GENERIC_CMOS_UPDATE': @@ -134,7 +147,8 @@ def __init__(self, bv: BinaryView): 'CONFIG_TICK_ONESHOT': self._recover_config_tick_oneshot, 'CONFIG_NO_HZ_COMMON': self._recover_config_no_hz_common, 'CONFIG_NO_HZ_FULL': self._recover_config_no_hz_full, - # CONFIG_NO_HZ_IDLE, CONFIG_NO_HZ_PERIODIC, and CONFIG_NO_HZ don't seem to be used in v4.18 kernel + # CONFIG_NO_HZ_IDLE, CONFIG_NO_HZ_PERIODIC, and CONFIG_NO_HZ don't seem to be used + # in v4.18 kernel 'CONFIG_NO_HZ_IDLE': None, 'CONFIG_HZ_PERIODIC': None, 'CONFIG_NO_HZ': None, @@ -163,29 +177,25 @@ def __init__(self, bv: BinaryView): def _recover_config_build_salt(self) -> str: """Recover CONFIG_BUILD_SALT configuration. - Analyze the first call to seq_printf in sched_debug_header and extract the pointer to the build salt from the - third parameter. + Analyze the first call to seq_printf in sched_debug_header and extract the pointer to the + build salt from the third parameter. Returns: Build salt string or None. """ - syms = self.bv.get_symbols_by_name('sched_debug_header') + syms = self.view.get_symbols_by_name('sched_debug_header') if not syms: - logging.error('Failed to lookup sched_debug_header') - return None + raise AnalysisError('Failed to lookup sched_debug_header') - sched_debug_header = self.bv.get_function_at(syms[0].address) + sched_debug_header = self.view.get_function_at(syms[0].address) if not sched_debug_header: - logging.error('Failed to get function sched_debug_header') - return None + raise AnalysisError('Failed to get function sched_debug_header') - syms = self.bv.get_symbols_by_name('seq_printf') + syms = self.view.get_symbols_by_name('seq_printf') if not syms: - logging.error('Failed to lookup seq_printf') - return None + raise AnalysisError('Failed to lookup seq_printf') - call_to_seq_printf = None for block in sched_debug_header.high_level_il: for instr in block: if instr.operation != HighLevelILOperation.HLIL_CALL: @@ -196,27 +206,26 @@ def _recover_config_build_salt(self) -> str: if to_ulong(instr.dest.constant) == syms[0].address: if len(instr.params) < 3: - logging.error( - 'First call in sched_debug header is not to seq_printf!?' - ) - return None + raise AnalysisError( + 'First call in sched_debug header is not to seq_printf!?') if instr.params[ 2].operation != HighLevelILOperation.HLIL_CONST_PTR: - logging.error( + raise AnalysisError( 'param3 of seq_printf call is not a pointer') - return None - s = self.bv.get_ascii_string_at( + _string = self.view.get_ascii_string_at( to_ulong(instr.params[2].constant)) - if not s: - logging.error('Failed to get build salt string') - return None + if not _string: + raise AnalysisError('Failed to get build salt string') + + return _string.value - return s.value + raise AnalysisError('No call instruction found in sched_debug_header!?') def _set_if_symbol_present(self, name: str) -> ConfigStatus: - """Helper for recovering configuration settings that can be determined based on the presence of a symbol + """Helper for recovering configuration settings that can be determined based on the + presence of a symbol Args: name: Symbol name. @@ -225,13 +234,14 @@ def _set_if_symbol_present(self, name: str) -> ConfigStatus: Configuration setting. """ - if self.bv.get_symbols_by_name(name): + if self.view.get_symbols_by_name(name): return ConfigStatus.SET return ConfigStatus.NOT_SET def _set_if_string_present(self, value: str) -> ConfigStatus: - """Helper for recovering configuration settings that can be determined based on the presence of a string + """Helper for recovering configuration settings that can be determined based on the + presence of a string Args: value: String value. @@ -239,9 +249,9 @@ def _set_if_string_present(self, value: str) -> ConfigStatus: Returns: Configuration setting. """ - strings = self.bv.get_strings() - for s in strings: - if s.value == value: + strings = self.view.get_strings() + for string in strings: + if string.value == value: return ConfigStatus.SET return ConfigStatus.NOT_SET @@ -280,22 +290,22 @@ def _recover_config_cross_memory_attach(self) -> ConfigStatus: """Set if any of the symbols in process_vm_access.c are present """ - if self.bv.platform.arch.name == 'x86_64': + if self.view.platform.arch.name == 'x86_64': return self._set_if_symbol_present('__x64_sys_process_vm_readv') logging.error( - f'Architecture is unsupported {self.bv.platform.arch.name}') + 'Architecture is unsupported %s', self.view.platform.arch.name) return ConfigStatus.ERROR def _recover_config_uselib(self) -> ConfigStatus: """Set if sys_uselib is present. """ - if self.bv.platform.arch.name == 'x86_64': + if self.view.platform.arch.name == 'x86_64': return self._set_if_symbol_present('__x64_sys_uselib') logging.error( - f'Architecture is unsupported {self.bv.platform.arch.name}') + 'Architecture is unsupported %s', self.view.platform.arch.name) return ConfigStatus.ERROR def _recover_config_audit(self) -> ConfigStatus: @@ -335,7 +345,9 @@ def _recover_config_generic_irq_show(self) -> ConfigStatus: return self._set_if_symbol_present('arch_show_interrupts') def _recover_config_generic_irq_effective_aff_mask(self) -> ConfigStatus: - """Set if effective_affinity_list string is present in the binary. See proc.c:register_irq_proc. + """Set if effective_affinity_list string is present in the binary. + + See proc.c:register_irq_proc. """ return self._set_if_string_present('effective_affinity_list') @@ -416,11 +428,11 @@ def _recover_config_arch_clocksource_data(self) -> ConfigStatus: """Set unconditionally for certain architectures. """ - if self.bv.platform.arch.name == 'x86_64': + if self.view.platform.arch.name == 'x86_64': return ConfigStatus.SET logging.error( - f'Architecture is unsupported {self.bv.platform.arch.name}') + 'Architecture is unsupported %s', self.view.platform.arch.name) return ConfigStatus.ERROR def _recover_config_generic_time_vsyscall(self) -> ConfigStatus: @@ -480,31 +492,32 @@ def _recover_config_preempt(self) -> ConfigStatus: def _recover_config_preempt_voluntary(self) -> ConfigStatus: """Set if mmiotrace_iounmap calls _cond_resched. - This starts with include/linux/kernel.h. If the configuration is set, then might_resched calls _cond_resched. - The might_sleep macro calls might_resched, and mmiotrace_iounmap calls might_sleep. + This starts with include/linux/kernel.h. If the configuration is set, then might_resched + calls _cond_resched. The might_sleep macro calls might_resched, and mmiotrace_iounmap + calls might_sleep. """ - syms = self.bv.get_symbols_by_name('_cond_resched') + syms = self.view.get_symbols_by_name('_cond_resched') if not syms: logging.error('Failed to lookup _cond_resched') return ConfigStatus.ERROR - xrefs = self.bv.get_code_refs(syms[0].address) + xrefs = self.view.get_code_refs(syms[0].address) for xref in xrefs: if xref.function.name == 'mmiotrace_iounmap': return ConfigStatus.SET - return ConfigStatus.NO_SET + return ConfigStatus.NOT_SET def _recover_config_tick_cpu_accounting(self) -> ConfigStatus: """Set if architecture is not PPC64. """ - if self.bv.platform.arch.name == 'x86_64': + if self.view.platform.arch.name == 'x86_64': return ConfigStatus.SET logging.error( - f'Architecture is unsupported {self.bv.platform.arch.name}') + 'Architecture is unsupported %s', self.view.platform.arch.name) return ConfigStatus.ERROR def _recover_config_virt_cpu_accounting_gen(self) -> ConfigStatus: @@ -543,20 +556,24 @@ def _recover_config_task_xacct(self) -> ConfigStatus: return self._set_if_symbol_present('xacct_add_tsk') - def do(self) -> dict: + def recover(self) -> dict: """Analyze binary and recover kernel configurations Returns: Dictionary of recovered configurations """ - results = dict() + results = {} for subsystem, settings in self.helpers.items(): - logging.info(f'Recovering "{subsystem}" configurations...') - results[subsystem] = dict() + logging.info('Recovering "%s" configurations...', subsystem) + results[subsystem] = {} for setting, helper in settings.items(): - if helper: - results[subsystem][setting] = helper() + if helper is not None: + try: + results[subsystem][setting] = helper() + except AnalysisError as ex: + logging.error(ex) + results[subsystem][setting] = None else: results[subsystem][setting] = None