(original) (raw)

changeset: 75073:4a31f6b11e7a branch: 3.2 parent: 75062:a72e0e1d0292 parent: 75066:f4b7ecf8a5f8 user: Georg Brandl georg@python.org date: Mon Feb 20 21:31:46 2012 +0100 files: Doc/library/sys.rst Doc/reference/datamodel.rst Doc/using/cmdline.rst Include/object.h Include/pydebug.h Include/pythonrun.h Lib/os.py Lib/test/mapping_tests.py Lib/test/regrtest.py Lib/test/script_helper.py Lib/test/test_cmd_line.py Lib/test/test_descr.py Lib/test/test_gdb.py Lib/test/test_hash.py Lib/test/test_os.py Lib/test/test_set.py Lib/test/test_sys.py Lib/test/test_urllib.py Lib/test/test_urlparse.py Makefile.pre.in Misc/NEWS Misc/python.man Modules/_datetimemodule.c Modules/main.c Modules/posixmodule.c Objects/bytesobject.c Objects/object.c Objects/unicodeobject.c PCbuild/pythoncore.vcproj Python/pythonrun.c Python/sysmodule.c description: Merge from 3.1: Issue #13703: add a way to randomize the hash values of basic types (str, bytes, datetime) in order to make algorithmic complexity attacks on (e.g.) web apps much more complicated. The environment variable PYTHONHASHSEED and the new command line flag -R control this behavior. diff -r a72e0e1d0292 -r 4a31f6b11e7a Doc/library/sys.rst --- a/Doc/library/sys.rst Mon Feb 20 18:35:26 2012 +0000 +++ b/Doc/library/sys.rst Mon Feb 20 21:31:46 2012 +0100 @@ -253,11 +253,15 @@ :const:`verbose` :option:`-v` :const:`bytes_warning` :option:`-b` :const:`quiet` :option:`-q` + :const:`hash_randomization` :option:`-R` ============================= ============================= .. versionchanged:: 3.2 Added ``quiet`` attribute for the new :option:`-q` flag. + .. versionadded:: 3.2.3 + The ``hash_randomization`` attribute. + .. data:: float_info diff -r a72e0e1d0292 -r 4a31f6b11e7a Doc/reference/datamodel.rst --- a/Doc/reference/datamodel.rst Mon Feb 20 18:35:26 2012 +0000 +++ b/Doc/reference/datamodel.rst Mon Feb 20 21:31:46 2012 +0100 @@ -1272,6 +1272,8 @@ inheritance of :meth:`__hash__` will be blocked, just as if :attr:`__hash__` had been explicitly set to :const:`None`. + See also the :option:`-R` command-line option. + .. method:: object.__bool__(self) diff -r a72e0e1d0292 -r 4a31f6b11e7a Doc/using/cmdline.rst --- a/Doc/using/cmdline.rst Mon Feb 20 18:35:26 2012 +0000 +++ b/Doc/using/cmdline.rst Mon Feb 20 21:31:46 2012 +0100 @@ -24,7 +24,7 @@ When invoking Python, you may specify any of these options:: - python [-bBdEhiOsSuvVWx?] [-c command | -m module-name | script | - ] [args] + python [-bBdEhiORqsSuvVWx?] [-c command | -m module-name | script | - ] [args] The most common use case is, of course, a simple invocation of a script:: @@ -227,6 +227,29 @@ .. versionadded:: 3.2 +.. cmdoption:: -R + + Turn on hash randomization, so that the :meth:`__hash__` values of str, bytes + and datetime objects are "salted" with an unpredictable random value. + Although they remain constant within an individual Python process, they are + not predictable between repeated invocations of Python. + + This is intended to provide protection against a denial-of-service caused by + carefully-chosen inputs that exploit the worst case performance of a dict + insertion, O(n^2) complexity. See + http://www.ocert.org/advisories/ocert-2011-003.html for details. + + Changing hash values affects the order in which keys are retrieved from a + dict. Although Python has never made guarantees about this ordering (and it + typically varies between 32-bit and 64-bit builds), enough real-world code + implicitly relies on this non-guaranteed behavior that the randomization is + disabled by default. + + See also :envvar:`PYTHONHASHSEED`. + + .. versionadded:: 3.2.3 + + .. cmdoption:: -s Don't add the :data:`user site-packages directory ` to @@ -350,6 +373,7 @@ .. _Jython: http://jython.org + .. _using-on-envvars: Environment variables @@ -458,6 +482,27 @@ option. +.. envvar:: PYTHONHASHSEED + + If this variable is set to ``random``, the effect is the same as specifying + the :option:`-R` option: a random value is used to seed the hashes of str, + bytes and datetime objects. + + If :envvar:`PYTHONHASHSEED` is set to an integer value, it is used as a fixed + seed for generating the hash() of the types covered by the hash + randomization. + + Its purpose is to allow repeatable hashing, such as for selftests for the + interpreter itself, or to allow a cluster of python processes to share hash + values. + + The integer must be a decimal number in the range [0,4294967295]. Specifying + the value 0 will lead to the same hash values as when hash randomization is + disabled. + + .. versionadded:: 3.2.3 + + .. envvar:: PYTHONIOENCODING If this is set before running the interpreter, it overrides the encoding used diff -r a72e0e1d0292 -r 4a31f6b11e7a Include/object.h --- a/Include/object.h Mon Feb 20 18:35:26 2012 +0000 +++ b/Include/object.h Mon Feb 20 21:31:46 2012 +0100 @@ -517,6 +517,12 @@ PyAPI_FUNC(Py_hash_t) _Py_HashPointer(void*); #endif +typedef struct { + Py_hash_t prefix; + Py_hash_t suffix; +} _Py_HashSecret_t; +PyAPI_DATA(_Py_HashSecret_t) _Py_HashSecret; + /* Helper for passing objects to printf and the like */ #define PyObject_REPR(obj) _PyUnicode_AsString(PyObject_Repr(obj)) diff -r a72e0e1d0292 -r 4a31f6b11e7a Include/pydebug.h --- a/Include/pydebug.h Mon Feb 20 18:35:26 2012 +0000 +++ b/Include/pydebug.h Mon Feb 20 21:31:46 2012 +0100 @@ -20,6 +20,7 @@ PyAPI_DATA(int) Py_DontWriteBytecodeFlag; PyAPI_DATA(int) Py_NoUserSiteDirectory; PyAPI_DATA(int) Py_UnbufferedStdioFlag; +PyAPI_DATA(int) Py_HashRandomizationFlag; /* this is a wrapper around getenv() that pays attention to Py_IgnoreEnvironmentFlag. It should be used for getting variables like diff -r a72e0e1d0292 -r 4a31f6b11e7a Include/pythonrun.h --- a/Include/pythonrun.h Mon Feb 20 18:35:26 2012 +0000 +++ b/Include/pythonrun.h Mon Feb 20 21:31:46 2012 +0100 @@ -248,6 +248,8 @@ PyAPI_FUNC(PyOS_sighandler_t) PyOS_getsig(int); PyAPI_FUNC(PyOS_sighandler_t) PyOS_setsig(int, PyOS_sighandler_t); +/* Random */ +PyAPI_FUNC(int) _PyOS_URandom (void *buffer, Py_ssize_t size); #ifdef __cplusplus } diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/json/__init__.py --- a/Lib/json/__init__.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/json/__init__.py Mon Feb 20 21:31:46 2012 +0100 @@ -31,7 +31,9 @@ Compact encoding:: >>> import json - >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',', ':')) + >>> from collections import OrderedDict + >>> mydict = OrderedDict([('4', 5), ('6', 7)]) + >>> json.dumps([1,2,3,mydict], separators=(',', ':')) '[1,2,3,{"4":5,"6":7}]' Pretty printing:: diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/os.py --- a/Lib/os.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/os.py Mon Feb 20 21:31:46 2012 +0100 @@ -761,23 +761,6 @@ except NameError: # statvfs_result may not exist pass -if not _exists("urandom"): - def urandom(n): - """urandom(n) -> str - - Return a string of n random bytes suitable for cryptographic use. - - """ - try: - _urandomfd = open("/dev/urandom", O_RDONLY) - except (OSError, IOError): - raise NotImplementedError("/dev/urandom (or equivalent) not found") - bs = b"" - while len(bs) < n: - bs += read(_urandomfd, n - len(bs)) - close(_urandomfd) - return bs - # Supply os.popen() def popen(cmd, mode="r", buffering=-1): if not isinstance(cmd, str): diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/mapping_tests.py --- a/Lib/test/mapping_tests.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/mapping_tests.py Mon Feb 20 21:31:46 2012 +0100 @@ -14,7 +14,7 @@ def _reference(self): """Return a dictionary of values which are invariant by storage in the object under test.""" - return {1:2, "key1":"value1", "key2":(1,2,3)} + return {"1": "2", "key1":"value1", "key2":(1,2,3)} def _empty_mapping(self): """Return an empty mapping object""" return self.type2test() diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/regrtest.py --- a/Lib/test/regrtest.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/regrtest.py Mon Feb 20 21:31:46 2012 +0100 @@ -496,6 +496,11 @@ except ValueError: print("Couldn't find starting test (%s), using all tests" % start) if randomize: + hashseed = os.getenv('PYTHONHASHSEED') + if not hashseed: + os.environ['PYTHONHASHSEED'] = str(random_seed) + os.execv(sys.executable, [sys.executable] + sys.argv) + return random.seed(random_seed) print("Using random seed", random_seed) random.shuffle(selected) diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/script_helper.py --- a/Lib/test/script_helper.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/script_helper.py Mon Feb 20 21:31:46 2012 +0100 @@ -3,7 +3,6 @@ import sys import os -import re import os.path import tempfile import subprocess @@ -20,11 +19,15 @@ cmd_line = [sys.executable] if not env_vars: cmd_line.append('-E') - cmd_line.extend(args) # Need to preserve the original environment, for in-place testing of # shared library builds. env = os.environ.copy() + # But a special flag that can be set to override -- in this case, the + # caller is responsible to pass the full environment. + if env_vars.pop('__cleanenv', None): + env = {} env.update(env_vars) + cmd_line.extend(args) p = subprocess.Popen(cmd_line, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env) diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_cmd_line.py --- a/Lib/test/test_cmd_line.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_cmd_line.py Mon Feb 20 21:31:46 2012 +0100 @@ -330,6 +330,22 @@ def test_no_std_streams(self): self._test_no_stdio(['stdin', 'stdout', 'stderr']) + def test_hash_randomization(self): + # Verify that -R enables hash randomization: + self.verify_valid_flag('-R') + hashes = [] + for i in range(2): + code = 'print(hash("spam"))' + rc, out, err = assert_python_ok('-R', '-c', code) + self.assertEqual(rc, 0) + hashes.append(out) + self.assertNotEqual(hashes[0], hashes[1]) + + # Verify that sys.flags contains hash_randomization + code = 'import sys; print("random is", sys.flags.hash_randomization)' + rc, out, err = assert_python_ok('-R', '-c', code) + self.assertEqual(rc, 0) + self.assertIn(b'random is 1', out) def test_main(): test.support.run_unittest(CmdLineTest) diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_descr.py --- a/Lib/test/test_descr.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_descr.py Mon Feb 20 21:31:46 2012 +0100 @@ -4474,8 +4474,18 @@ def test_repr(self): # Testing dict_proxy.__repr__ + def sorted_dict_repr(repr_): + # Given the repr of a dict, sort the keys + assert repr_.startswith('{') + assert repr_.endswith('}') + kvs = repr_[1:-1].split(', ') + return '{' + ', '.join(sorted(kvs)) + '}' dict_ = {k: v for k, v in self.C.__dict__.items()} - self.assertEqual(repr(self.C.__dict__), 'dict_proxy({!r})'.format(dict_)) + repr_ = repr(self.C.__dict__) + self.assert_(repr_.startswith('dict_proxy(')) + self.assert_(repr_.endswith(')')) + self.assertEqual(sorted_dict_repr(repr_[len('dict_proxy('):-len(')')]), + sorted_dict_repr('{!r}'.format(dict_))) class PTypesLongInitTest(unittest.TestCase): diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_gdb.py --- a/Lib/test/test_gdb.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_gdb.py Mon Feb 20 21:31:46 2012 +0100 @@ -52,13 +52,18 @@ """Test that the debugger can debug Python.""" - def run_gdb(self, *args): + def run_gdb(self, *args, **env_vars): """Runs gdb with the command line given by *args. Returns its stdout, stderr """ + if env_vars: + env = os.environ.copy() + env.update(env_vars) + else: + env = None out, err = subprocess.Popen( - args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env, ).communicate() return out.decode('utf-8', 'replace'), err.decode('utf-8', 'replace') @@ -118,7 +123,7 @@ # print ' '.join(args) # Use "args" to invoke gdb, capturing stdout, stderr: - out, err = self.run_gdb(*args) + out, err = self.run_gdb(*args, PYTHONHASHSEED='0') # Ignore some noise on stderr due to the pending breakpoint: err = err.replace('Function "%s" not defined.\n' % breakpoint, '') @@ -207,7 +212,8 @@ 'Verify the pretty-printing of dictionaries' self.assertGdbRepr({}) self.assertGdbRepr({'foo': 'bar'}) - self.assertGdbRepr({'foo': 'bar', 'douglas':42}) + self.assertGdbRepr({'foo': 'bar', 'douglas': 42}, + "{'foo': 'bar', 'douglas': 42}") def test_lists(self): 'Verify the pretty-printing of lists' @@ -269,8 +275,8 @@ def test_sets(self): 'Verify the pretty-printing of sets' self.assertGdbRepr(set()) - self.assertGdbRepr(set(['a', 'b'])) - self.assertGdbRepr(set([4, 5, 6])) + self.assertGdbRepr(set(['a', 'b']), "{'a', 'b'}") + self.assertGdbRepr(set([4, 5, 6]), "{4, 5, 6}") # Ensure that we handle sets containing the "dummy" key value, # which happens on deletion: @@ -282,8 +288,8 @@ def test_frozensets(self): 'Verify the pretty-printing of frozensets' self.assertGdbRepr(frozenset()) - self.assertGdbRepr(frozenset(['a', 'b'])) - self.assertGdbRepr(frozenset([4, 5, 6])) + self.assertGdbRepr(frozenset(['a', 'b']), "frozenset({'a', 'b'})") + self.assertGdbRepr(frozenset([4, 5, 6]), "frozenset({4, 5, 6})") def test_exceptions(self): # Test a RuntimeError diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_hash.py --- a/Lib/test/test_hash.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_hash.py Mon Feb 20 21:31:46 2012 +0100 @@ -3,10 +3,16 @@ # # Also test that hash implementations are inherited as expected +import datetime +import os +import sys import unittest from test import support +from test.script_helper import assert_python_ok from collections import Hashable +IS_64BIT = sys.maxsize > 2**32 + class HashEqualityTestCase(unittest.TestCase): @@ -118,10 +124,92 @@ for obj in self.hashes_to_check: self.assertEqual(hash(obj), _default_hash(obj)) +class HashRandomizationTests(unittest.TestCase): + + # Each subclass should define a field "repr_", containing the repr() of + # an object to be tested + + def get_hash_command(self, repr_): + return 'print(hash(%s))' % repr_ + + def get_hash(self, repr_, seed=None): + env = os.environ.copy() + env['__cleanenv'] = True # signal to assert_python not to do a copy + # of os.environ on its own + if seed is not None: + env['PYTHONHASHSEED'] = str(seed) + else: + env.pop('PYTHONHASHSEED', None) + out = assert_python_ok( + '-c', self.get_hash_command(repr_), + **env) + stdout = out[1].strip() + return int(stdout) + + def test_randomized_hash(self): + # two runs should return different hashes + run1 = self.get_hash(self.repr_, seed='random') + run2 = self.get_hash(self.repr_, seed='random') + self.assertNotEqual(run1, run2) + +class StringlikeHashRandomizationTests(HashRandomizationTests): + def test_null_hash(self): + # PYTHONHASHSEED=0 disables the randomized hash + if IS_64BIT: + known_hash_of_obj = 1453079729188098211 + else: + known_hash_of_obj = -1600925533 + + # Randomization is disabled by default: + self.assertEqual(self.get_hash(self.repr_), known_hash_of_obj) + + # It can also be disabled by setting the seed to 0: + self.assertEqual(self.get_hash(self.repr_, seed=0), known_hash_of_obj) + + def test_fixed_hash(self): + # test a fixed seed for the randomized hash + # Note that all types share the same values: + if IS_64BIT: + h = -4410911502303878509 + else: + h = -206076799 + self.assertEqual(self.get_hash(self.repr_, seed=42), h) + +class StrHashRandomizationTests(StringlikeHashRandomizationTests): + repr_ = repr('abc') + + def test_empty_string(self): + self.assertEqual(hash(""), 0) + +class BytesHashRandomizationTests(StringlikeHashRandomizationTests): + repr_ = repr(b'abc') + + def test_empty_string(self): + self.assertEqual(hash(b""), 0) + +class DatetimeTests(HashRandomizationTests): + def get_hash_command(self, repr_): + return 'import datetime; print(hash(%s))' % repr_ + +class DatetimeDateTests(DatetimeTests): + repr_ = repr(datetime.date(1066, 10, 14)) + +class DatetimeDatetimeTests(DatetimeTests): + repr_ = repr(datetime.datetime(1, 2, 3, 4, 5, 6, 7)) + +class DatetimeTimeTests(DatetimeTests): + repr_ = repr(datetime.time(0)) + + def test_main(): support.run_unittest(HashEqualityTestCase, - HashInheritanceTestCase, - HashBuiltinsTestCase) + HashInheritanceTestCase, + HashBuiltinsTestCase, + StrHashRandomizationTests, + BytesHashRandomizationTests, + DatetimeDateTests, + DatetimeDatetimeTests, + DatetimeTimeTests) if __name__ == "__main__": diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_os.py --- a/Lib/test/test_os.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_os.py Mon Feb 20 21:31:46 2012 +0100 @@ -15,6 +15,7 @@ import contextlib import mmap import uuid +from test.script_helper import assert_python_ok # Detect whether we're on a Linux system that uses the (now outdated # and unmaintained) linuxthreads threading library. There's an issue @@ -611,14 +612,33 @@ self.assertEqual(f.read(), b'') class URandomTests(unittest.TestCase): - def test_urandom(self): - try: - self.assertEqual(len(os.urandom(1)), 1) - self.assertEqual(len(os.urandom(10)), 10) - self.assertEqual(len(os.urandom(100)), 100) - self.assertEqual(len(os.urandom(1000)), 1000) - except NotImplementedError: - pass + def test_urandom_length(self): + self.assertEqual(len(os.urandom(0)), 0) + self.assertEqual(len(os.urandom(1)), 1) + self.assertEqual(len(os.urandom(10)), 10) + self.assertEqual(len(os.urandom(100)), 100) + self.assertEqual(len(os.urandom(1000)), 1000) + + def test_urandom_value(self): + data1 = os.urandom(16) + data2 = os.urandom(16) + self.assertNotEqual(data1, data2) + + def get_urandom_subprocess(self, count): + code = '\n'.join(( + 'import os, sys', + 'data = os.urandom(%s)' % count, + 'sys.stdout.buffer.write(data)', + 'sys.stdout.buffer.flush()')) + out = assert_python_ok('-c', code) + stdout = out[1] + self.assertEqual(len(stdout), 16) + return stdout + + def test_urandom_subprocess(self): + data1 = self.get_urandom_subprocess(16) + data2 = self.get_urandom_subprocess(16) + self.assertNotEqual(data1, data2) @contextlib.contextmanager def _execvpe_mockup(defpath=None): diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_set.py --- a/Lib/test/test_set.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_set.py Mon Feb 20 21:31:46 2012 +0100 @@ -733,6 +733,17 @@ if self.repr is not None: self.assertEqual(repr(self.set), self.repr) + def check_repr_against_values(self): + text = repr(self.set) + self.assertTrue(text.startswith('{')) + self.assertTrue(text.endswith('}')) + + result = text[1:-1].split(', ') + result.sort() + sorted_repr_values = [repr(value) for value in self.values] + sorted_repr_values.sort() + self.assertEqual(result, sorted_repr_values) + def test_print(self): try: fo = open(support.TESTFN, "w") @@ -891,7 +902,9 @@ self.set = set(self.values) self.dup = set(self.values) self.length = 3 - self.repr = "{'a', 'c', 'b'}" + + def test_repr(self): + self.check_repr_against_values() #------------------------------------------------------------------------------ @@ -902,7 +915,9 @@ self.set = set(self.values) self.dup = set(self.values) self.length = 3 - self.repr = "{b'a', b'c', b'b'}" + + def test_repr(self): + self.check_repr_against_values() #------------------------------------------------------------------------------ @@ -916,11 +931,13 @@ self.set = set(self.values) self.dup = set(self.values) self.length = 4 - self.repr = "{'a', b'a', 'b', b'b'}" def tearDown(self): self._warning_filters.__exit__(None, None, None) + def test_repr(self): + self.check_repr_against_values() + #============================================================================== def baditer(): diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_sys.py --- a/Lib/test/test_sys.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_sys.py Mon Feb 20 21:31:46 2012 +0100 @@ -503,7 +503,7 @@ attrs = ("debug", "division_warning", "inspect", "interactive", "optimize", "dont_write_bytecode", "no_user_site", "no_site", "ignore_environment", "verbose", - "bytes_warning", "quiet") + "bytes_warning", "quiet", "hash_randomization") for attr in attrs: self.assertTrue(hasattr(sys.flags, attr), attr) self.assertEqual(type(getattr(sys.flags, attr)), int, attr) diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_urllib.py --- a/Lib/test/test_urllib.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_urllib.py Mon Feb 20 21:31:46 2012 +0100 @@ -13,6 +13,7 @@ import tempfile from base64 import b64encode +import collections def hexescape(char): """Escape char as RFC 2396 specifies""" @@ -953,8 +954,9 @@ self.assertEqual("a=1&a=2", urllib.parse.urlencode({"a": [1, 2]}, True)) self.assertEqual("a=None&a=a", urllib.parse.urlencode({"a": [None, "a"]}, True)) + data = collections.OrderedDict([("a", 1), ("b", 1)]) self.assertEqual("a=a&a=b", - urllib.parse.urlencode({"a": {"a": 1, "b": 1}}, True)) + urllib.parse.urlencode({"a": data}, True)) def test_urlencode_encoding(self): # ASCII encoding. Expect %3F with errors="replace' diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/test/test_urlparse.py --- a/Lib/test/test_urlparse.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/test/test_urlparse.py Mon Feb 20 21:31:46 2012 +0100 @@ -769,7 +769,8 @@ # Other tests incidentally urlencode things; test non-covered cases: # Sequence and object values. result = urllib.parse.urlencode({'a': [1, 2], 'b': (3, 4, 5)}, True) - self.assertEqual(result, 'a=1&a=2&b=3&b=4&b=5') + # we cannot rely on ordering here + assert set(result.split('&')) == {'a=1', 'a=2', 'b=3', 'b=4', 'b=5'} class Trivial: def __str__(self): diff -r a72e0e1d0292 -r 4a31f6b11e7a Lib/tkinter/test/test_ttk/test_functions.py --- a/Lib/tkinter/test/test_ttk/test_functions.py Mon Feb 20 18:35:26 2012 +0000 +++ b/Lib/tkinter/test/test_ttk/test_functions.py Mon Feb 20 21:31:46 2012 +0100 @@ -143,7 +143,7 @@ ('a', 'b', 'c')), ("test {a b} c", ())) # state spec and options self.assertEqual(ttk._format_elemcreate('image', False, 'test', - ('a', 'b'), a='x', b='y'), ("test a b", ("-a", "x", "-b", "y"))) + ('a', 'b'), a='x'), ("test a b", ("-a", "x"))) # format returned values as a tcl script # state spec with multiple states and an option with a multivalue self.assertEqual(ttk._format_elemcreate('image', True, 'test', diff -r a72e0e1d0292 -r 4a31f6b11e7a Makefile.pre.in --- a/Makefile.pre.in Mon Feb 20 18:35:26 2012 +0000 +++ b/Makefile.pre.in Mon Feb 20 21:31:46 2012 +0100 @@ -322,6 +322,7 @@ Python/pystate.o \ Python/pythonrun.o \ Python/pytime.o \ + Python/random.o \ Python/structmember.o \ Python/symtable.o \ Python/sysmodule.o \ diff -r a72e0e1d0292 -r 4a31f6b11e7a Misc/NEWS --- a/Misc/NEWS Mon Feb 20 18:35:26 2012 +0000 +++ b/Misc/NEWS Mon Feb 20 21:31:46 2012 +0100 @@ -10,6 +10,11 @@ Core and Builtins ----------------- +- Issue #13703: oCERT-2011-003: add -R command-line option and PYTHONHASHSEED + environment variables, to provide an opt-in way to protect against denial of + service attacks due to hash collisions within the dict and set types. Patch + by David Malcolm, based on work by Victor Stinner. + - Issue #13020: Fix a reference leak when allocating a structsequence object fails. Patch by Suman Saha. diff -r a72e0e1d0292 -r 4a31f6b11e7a Misc/python.man --- a/Misc/python.man Mon Feb 20 18:35:26 2012 +0000 +++ b/Misc/python.man Mon Feb 20 21:31:46 2012 +0100 @@ -37,6 +37,9 @@ .B \-OO ] [ +.B \-R +] +[ .B -Q .I argument ] @@ -152,6 +155,18 @@ Do not print the version and copyright messages. These messages are also suppressed in non-interactive mode. .TP +.B \-R +Turn on "hash randomization", so that the hash() values of str, bytes and +datetime objects are "salted" with an unpredictable pseudo-random value. +Although they remain constant within an individual Python process, they are +not predictable between repeated invocations of Python. +.IP +This is intended to provide protection against a denial of service +caused by carefully-chosen inputs that exploit the worst case performance +of a dict insertion, O(n^2) complexity. See +http://www.ocert.org/advisories/ocert-2011-003.html +for details. +.TP .BI "\-Q " argument Division control; see PEP 238. The argument must be one of "old" (the default, int/int and long/long return an int or long), "new" (new @@ -413,6 +428,20 @@ .IP PYTHONWARNINGS If this is set to a comma-separated string it is equivalent to specifying the \fB\-W\fP option for each separate value. +.IP PYTHONHASHSEED +If this variable is set to "random", the effect is the same as specifying +the \fB-R\fP option: a random value is used to seed the hashes of str, +bytes and datetime objects. + +If PYTHONHASHSEED is set to an integer value, it is used as a fixed seed for +generating the hash() of the types covered by the hash randomization. Its +purpose is to allow repeatable hashing, such as for selftests for the +interpreter itself, or to allow a cluster of python processes to share hash +values. + +The integer must be a decimal number in the range [0,4294967295]. Specifying +the value 0 will lead to the same hash values as when hash randomization is +disabled. .SH AUTHOR The Python Software Foundation: http://www.python.org/psf .SH INTERNET RESOURCES diff -r a72e0e1d0292 -r 4a31f6b11e7a Modules/_datetimemodule.c --- a/Modules/_datetimemodule.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Modules/_datetimemodule.c Mon Feb 20 21:31:46 2012 +0100 @@ -2785,10 +2785,12 @@ register Py_hash_t x; p = (unsigned char *) data; - x = *p << 7; + x = _Py_HashSecret.prefix; + x ^= *p << 7; while (--len >= 0) x = (1000003*x) ^ *p++; x ^= len; + x ^= _Py_HashSecret.suffix; if (x == -1) x = -2; diff -r a72e0e1d0292 -r 4a31f6b11e7a Modules/main.c --- a/Modules/main.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Modules/main.c Mon Feb 20 21:31:46 2012 +0100 @@ -46,7 +46,7 @@ static int orig_argc; /* command line options */ -#define BASE_OPTS L"bBc:dEhiJm:OqsStuvVW:xX:?" +#define BASE_OPTS L"bBc:dEhiJm:OqRsStuvVW:xX:?" #define PROGRAM_OPTS BASE_OPTS @@ -72,6 +72,9 @@ -O : optimize generated bytecode slightly; also PYTHONOPTIMIZE=x\n\ -OO : remove doc-strings in addition to the -O optimizations\n\ -q : don't print version and copyright messages on interactive startup\n\ +-R : use a pseudo-random salt to make hash() values of various types be\n\ + unpredictable between separate invocations of the interpreter, as\n\ + a defence against denial-of-service attacks\n\ -s : don't add user site directory to sys.path; also PYTHONNOUSERSITE\n\ -S : don't imply 'import site' on initialization\n\ "; @@ -99,8 +102,14 @@ "PYTHONHOME : alternate directory (or %c).\n" " The default module search path uses %s.\n" "PYTHONCASEOK : ignore case in 'import' statements (Windows).\n" -"PYTHONIOENCODING: Encoding[:errors] used for stdin/stdout/stderr.\n" -; +"PYTHONIOENCODING: Encoding[:errors] used for stdin/stdout/stderr.\n\ +"; +static char *usage_6 = "\ +PYTHONHASHSEED: if this variable is set to ``random``, the effect is the same \n\ + as specifying the :option:`-R` option: a random value is used to seed the\n\ + hashes of str, bytes and datetime objects. It can also be set to an integer\n\ + in the range [0,4294967295] to get hash values with a predictable seed.\n\ +"; static int usage(int exitcode, wchar_t* program) @@ -116,6 +125,7 @@ fputs(usage_3, f); fprintf(f, usage_4, DELIM); fprintf(f, usage_5, DELIM, PYTHONHOMEHELP); + fputs(usage_6, f); } #if defined(__VMS) if (exitcode == 0) { @@ -429,6 +439,10 @@ Py_QuietFlag++; break; + case 'R': + Py_HashRandomizationFlag++; + break; + /* This space reserved for other options */ default: diff -r a72e0e1d0292 -r 4a31f6b11e7a Modules/posixmodule.c --- a/Modules/posixmodule.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Modules/posixmodule.c Mon Feb 20 21:31:46 2012 +0100 @@ -7614,82 +7614,6 @@ } #endif -#ifdef MS_WINDOWS - -PyDoc_STRVAR(win32_urandom__doc__, -"urandom(n) -> str\n\n\ -Return n random bytes suitable for cryptographic use."); - -typedef BOOL (WINAPI *CRYPTACQUIRECONTEXTA)(HCRYPTPROV *phProv,\ - LPCSTR pszContainer, LPCSTR pszProvider, DWORD dwProvType,\ - DWORD dwFlags ); -typedef BOOL (WINAPI *CRYPTGENRANDOM)(HCRYPTPROV hProv, DWORD dwLen,\ - BYTE *pbBuffer ); - -static CRYPTGENRANDOM pCryptGenRandom = NULL; -/* This handle is never explicitly released. Instead, the operating - system will release it when the process terminates. */ -static HCRYPTPROV hCryptProv = 0; - -static PyObject* -win32_urandom(PyObject *self, PyObject *args) -{ - int howMany; - PyObject* result; - - /* Read arguments */ - if (! PyArg_ParseTuple(args, "i:urandom", &howMany)) - return NULL; - if (howMany < 0) - return PyErr_Format(PyExc_ValueError, - "negative argument not allowed"); - - if (hCryptProv == 0) { - HINSTANCE hAdvAPI32 = NULL; - CRYPTACQUIRECONTEXTA pCryptAcquireContext = NULL; - - /* Obtain handle to the DLL containing CryptoAPI - This should not fail */ - hAdvAPI32 = GetModuleHandle("advapi32.dll"); - if(hAdvAPI32 == NULL) - return win32_error("GetModuleHandle", NULL); - - /* Obtain pointers to the CryptoAPI functions - This will fail on some early versions of Win95 */ - pCryptAcquireContext = (CRYPTACQUIRECONTEXTA)GetProcAddress( - hAdvAPI32, - "CryptAcquireContextA"); - if (pCryptAcquireContext == NULL) - return PyErr_Format(PyExc_NotImplementedError, - "CryptAcquireContextA not found"); - - pCryptGenRandom = (CRYPTGENRANDOM)GetProcAddress( - hAdvAPI32, "CryptGenRandom"); - if (pCryptGenRandom == NULL) - return PyErr_Format(PyExc_NotImplementedError, - "CryptGenRandom not found"); - - /* Acquire context */ - if (! pCryptAcquireContext(&hCryptProv, NULL, NULL, - PROV_RSA_FULL, CRYPT_VERIFYCONTEXT)) - return win32_error("CryptAcquireContext", NULL); - } - - /* Allocate bytes */ - result = PyBytes_FromStringAndSize(NULL, howMany); - if (result != NULL) { - /* Get random data */ - memset(PyBytes_AS_STRING(result), 0, howMany); /* zero seed */ - if (! pCryptGenRandom(hCryptProv, howMany, (unsigned char*) - PyBytes_AS_STRING(result))) { - Py_DECREF(result); - return win32_error("CryptGenRandom", NULL); - } - } - return result; -} -#endif - PyDoc_STRVAR(device_encoding__doc__, "device_encoding(fd) -> str\n\n\ Return a string describing the encoding of the device\n\ @@ -7727,41 +7651,35 @@ return Py_None; } -#ifdef __VMS -/* Use openssl random routine */ -#include -PyDoc_STRVAR(vms_urandom__doc__, +PyDoc_STRVAR(posix_urandom__doc__, "urandom(n) -> str\n\n\ Return n random bytes suitable for cryptographic use."); -static PyObject* -vms_urandom(PyObject *self, PyObject *args) -{ - int howMany; - PyObject* result; - - /* Read arguments */ - if (! PyArg_ParseTuple(args, "i:urandom", &howMany)) - return NULL; - if (howMany < 0) +static PyObject * +posix_urandom(PyObject *self, PyObject *args) +{ + Py_ssize_t size; + PyObject *result; + int ret; + + /* Read arguments */ + if (!PyArg_ParseTuple(args, "n:urandom", &size)) + return NULL; + if (size < 0) return PyErr_Format(PyExc_ValueError, "negative argument not allowed"); - - /* Allocate bytes */ - result = PyBytes_FromStringAndSize(NULL, howMany); - if (result != NULL) { - /* Get random data */ - if (RAND_pseudo_bytes((unsigned char*) - PyBytes_AS_STRING(result), - howMany) < 0) { - Py_DECREF(result); - return PyErr_Format(PyExc_ValueError, - "RAND_pseudo_bytes"); - } + result = PyBytes_FromStringAndSize(NULL, size); + if (result == NULL) + return NULL; + + ret = _PyOS_URandom(PyBytes_AS_STRING(result), + PyBytes_GET_SIZE(result)); + if (ret == -1) { + Py_DECREF(result); + return NULL; } return result; } -#endif #ifdef HAVE_SETRESUID PyDoc_STRVAR(posix_setresuid__doc__, @@ -8137,12 +8055,7 @@ #ifdef HAVE_GETLOADAVG {"getloadavg", posix_getloadavg, METH_NOARGS, posix_getloadavg__doc__}, #endif - #ifdef MS_WINDOWS - {"urandom", win32_urandom, METH_VARARGS, win32_urandom__doc__}, - #endif - #ifdef __VMS - {"urandom", vms_urandom, METH_VARARGS, vms_urandom__doc__}, - #endif + {"urandom", posix_urandom, METH_VARARGS, posix_urandom__doc__}, #ifdef HAVE_SETRESUID {"setresuid", posix_setresuid, METH_VARARGS, posix_setresuid__doc__}, #endif @@ -8155,7 +8068,6 @@ #ifdef HAVE_GETRESGID {"getresgid", posix_getresgid, METH_NOARGS, posix_getresgid__doc__}, #endif - {NULL, NULL} /* Sentinel */ }; diff -r a72e0e1d0292 -r 4a31f6b11e7a Objects/bytesobject.c --- a/Objects/bytesobject.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Objects/bytesobject.c Mon Feb 20 21:31:46 2012 +0100 @@ -878,11 +878,21 @@ if (a->ob_shash != -1) return a->ob_shash; len = Py_SIZE(a); + /* + We make the hash of the empty string be 0, rather than using + (prefix ^ suffix), since this slightly obfuscates the hash secret + */ + if (len == 0) { + a->ob_shash = 0; + return 0; + } p = (unsigned char *) a->ob_sval; - x = *p << 7; + x = _Py_HashSecret.prefix; + x ^= *p << 7; while (--len >= 0) x = (_PyHASH_MULTIPLIER*x) ^ *p++; x ^= Py_SIZE(a); + x ^= _Py_HashSecret.suffix; if (x == -1) x = -2; a->ob_shash = x; diff -r a72e0e1d0292 -r 4a31f6b11e7a Objects/object.c --- a/Objects/object.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Objects/object.c Mon Feb 20 21:31:46 2012 +0100 @@ -754,6 +754,8 @@ return -1; } +_Py_HashSecret_t _Py_HashSecret; + Py_hash_t PyObject_Hash(PyObject *v) { diff -r a72e0e1d0292 -r 4a31f6b11e7a Objects/unicodeobject.c --- a/Objects/unicodeobject.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Objects/unicodeobject.c Mon Feb 20 21:31:46 2012 +0100 @@ -7676,11 +7676,21 @@ if (self->hash != -1) return self->hash; len = Py_SIZE(self); + /* + We make the hash of the empty string be 0, rather than using + (prefix ^ suffix), since this slightly obfuscates the hash secret + */ + if (len == 0) { + self->hash = 0; + return 0; + } p = self->str; - x = *p << 7; + x = _Py_HashSecret.prefix; + x ^= *p << 7; while (--len >= 0) x = (_PyHASH_MULTIPLIER*x) ^ *p++; x ^= Py_SIZE(self); + x ^= _Py_HashSecret.suffix; if (x == -1) x = -2; self->hash = x; diff -r a72e0e1d0292 -r 4a31f6b11e7a PCbuild/pythoncore.vcproj --- a/PCbuild/pythoncore.vcproj Mon Feb 20 18:35:26 2012 +0000 +++ b/PCbuild/pythoncore.vcproj Mon Feb 20 21:31:46 2012 +0100 @@ -1882,6 +1882,10 @@ RelativePath="..\Python\pythonrun.c" > + + diff -r a72e0e1d0292 -r 4a31f6b11e7a Python/pythonrun.c --- a/Python/pythonrun.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Python/pythonrun.c Mon Feb 20 21:31:46 2012 +0100 @@ -70,6 +70,7 @@ extern void _PyUnicode_Fini(void); extern int _PyLong_Init(void); extern void PyLong_Fini(void); +extern void _PyRandom_Init(void); #ifdef WITH_THREAD extern void _PyGILState_Init(PyInterpreterState *, PyThreadState *); @@ -89,6 +90,7 @@ int Py_IgnoreEnvironmentFlag; /* e.g. PYTHONPATH, PYTHONHOME */ int Py_NoUserSiteDirectory = 0; /* for -s and site.py */ int Py_UnbufferedStdioFlag = 0; /* Unbuffered binary std{in,out,err} */ +int Py_HashRandomizationFlag = 0; /* for -R and PYTHONHASHSEED */ PyThreadState *_Py_Finalizing = NULL; @@ -207,6 +209,12 @@ Py_OptimizeFlag = add_flag(Py_OptimizeFlag, p); if ((p = Py_GETENV("PYTHONDONTWRITEBYTECODE")) && *p != '\0') Py_DontWriteBytecodeFlag = add_flag(Py_DontWriteBytecodeFlag, p); + /* The variable is only tested for existence here; _PyRandom_Init will + check its value further. */ + if ((p = Py_GETENV("PYTHONHASHSEED")) && *p != '\0') + Py_HashRandomizationFlag = add_flag(Py_HashRandomizationFlag, p); + + _PyRandom_Init(); interp = PyInterpreterState_New(); if (interp == NULL) diff -r a72e0e1d0292 -r 4a31f6b11e7a Python/random.c --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Python/random.c Mon Feb 20 21:31:46 2012 +0100 @@ -0,0 +1,302 @@ +#include "Python.h" +#ifdef MS_WINDOWS +#include +#else +#include +#endif + +static int random_initialized = 0; + +#ifdef MS_WINDOWS +typedef BOOL (WINAPI *CRYPTACQUIRECONTEXTA)(HCRYPTPROV *phProv,\ + LPCSTR pszContainer, LPCSTR pszProvider, DWORD dwProvType,\ + DWORD dwFlags ); +typedef BOOL (WINAPI *CRYPTGENRANDOM)(HCRYPTPROV hProv, DWORD dwLen,\ + BYTE *pbBuffer ); + +static CRYPTGENRANDOM pCryptGenRandom = NULL; +/* This handle is never explicitly released. Instead, the operating + system will release it when the process terminates. */ +static HCRYPTPROV hCryptProv = 0; + +static int +win32_urandom_init(int raise) +{ + HINSTANCE hAdvAPI32 = NULL; + CRYPTACQUIRECONTEXTA pCryptAcquireContext = NULL; + + /* Obtain handle to the DLL containing CryptoAPI. This should not fail. */ + hAdvAPI32 = GetModuleHandle("advapi32.dll"); + if(hAdvAPI32 == NULL) + goto error; + + /* Obtain pointers to the CryptoAPI functions. This will fail on some early + versions of Win95. */ + pCryptAcquireContext = (CRYPTACQUIRECONTEXTA)GetProcAddress( + hAdvAPI32, "CryptAcquireContextA"); + if (pCryptAcquireContext == NULL) + goto error; + + pCryptGenRandom = (CRYPTGENRANDOM)GetProcAddress(hAdvAPI32, + "CryptGenRandom"); + if (pCryptGenRandom == NULL) + goto error; + + /* Acquire context */ + if (! pCryptAcquireContext(&hCryptProv, NULL, NULL, + PROV_RSA_FULL, CRYPT_VERIFYCONTEXT)) + goto error; + + return 0; + +error: + if (raise) + PyErr_SetFromWindowsErr(0); + else + Py_FatalError("Failed to initialize Windows random API (CryptoGen)"); + return -1; +} + +/* Fill buffer with size pseudo-random bytes generated by the Windows CryptoGen + API. Return 0 on success, or -1 on error. */ +static int +win32_urandom(unsigned char *buffer, Py_ssize_t size, int raise) +{ + Py_ssize_t chunk; + + if (hCryptProv == 0) + { + if (win32_urandom_init(raise) == -1) + return -1; + } + + while (size > 0) + { + chunk = size > INT_MAX ? INT_MAX : size; + if (!pCryptGenRandom(hCryptProv, chunk, buffer)) + { + /* CryptGenRandom() failed */ + if (raise) + PyErr_SetFromWindowsErr(0); + else + Py_FatalError("Failed to initialized the randomized hash " + "secret using CryptoGen)"); + return -1; + } + buffer += chunk; + size -= chunk; + } + return 0; +} +#endif /* MS_WINDOWS */ + + +#ifdef __VMS +/* Use openssl random routine */ +#include +static int +vms_urandom(unsigned char *buffer, Py_ssize_t size, int raise) +{ + if (RAND_pseudo_bytes(buffer, size) < 0) { + if (raise) { + PyErr_Format(PyExc_ValueError, + "RAND_pseudo_bytes"); + } else { + Py_FatalError("Failed to initialize the randomized hash " + "secret using RAND_pseudo_bytes"); + } + return -1; + } + return 0; +} +#endif /* __VMS */ + + +#if !defined(MS_WINDOWS) && !defined(__VMS) + +/* Read size bytes from /dev/urandom into buffer. + Call Py_FatalError() on error. */ +static void +dev_urandom_noraise(char *buffer, Py_ssize_t size) +{ + int fd; + Py_ssize_t n; + + assert (0 < size); + + fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) + Py_FatalError("Failed to open /dev/urandom"); + + while (0 < size) + { + do { + n = read(fd, buffer, (size_t)size); + } while (n < 0 && errno == EINTR); + if (n <= 0) + { + /* stop on error or if read(size) returned 0 */ + Py_FatalError("Failed to read bytes from /dev/urandom"); + break; + } + buffer += n; + size -= (Py_ssize_t)n; + } + close(fd); +} + +/* Read size bytes from /dev/urandom into buffer. + Return 0 on success, raise an exception and return -1 on error. */ +static int +dev_urandom_python(char *buffer, Py_ssize_t size) +{ + int fd; + Py_ssize_t n; + + if (size <= 0) + return 0; + + Py_BEGIN_ALLOW_THREADS + fd = open("/dev/urandom", O_RDONLY); + Py_END_ALLOW_THREADS + if (fd < 0) + { + PyErr_SetFromErrnoWithFilename(PyExc_OSError, "/dev/urandom"); + return -1; + } + + Py_BEGIN_ALLOW_THREADS + do { + do { + n = read(fd, buffer, (size_t)size); + } while (n < 0 && errno == EINTR); + if (n <= 0) + break; + buffer += n; + size -= (Py_ssize_t)n; + } while (0 < size); + Py_END_ALLOW_THREADS + + if (n <= 0) + { + /* stop on error or if read(size) returned 0 */ + if (n < 0) + PyErr_SetFromErrno(PyExc_OSError); + else + PyErr_Format(PyExc_RuntimeError, + "Failed to read %zi bytes from /dev/urandom", + size); + close(fd); + return -1; + } + close(fd); + return 0; +} +#endif /* !defined(MS_WINDOWS) && !defined(__VMS) */ + +/* Fill buffer with pseudo-random bytes generated by a linear congruent + generator (LCG): + + x(n+1) = (x(n) * 214013 + 2531011) % 2^32 + + Use bits 23..16 of x(n) to generate a byte. */ +static void +lcg_urandom(unsigned int x0, unsigned char *buffer, size_t size) +{ + size_t index; + unsigned int x; + + x = x0; + for (index=0; index < size; index++) { + x *= 214013; + x += 2531011; + /* modulo 2 ^ (8 * sizeof(int)) */ + buffer[index] = (x >> 16) & 0xff; + } +} + +/* Fill buffer with size pseudo-random bytes, not suitable for cryptographic + use, from the operating random number generator (RNG). + + Return 0 on success, raise an exception and return -1 on error. */ +int +_PyOS_URandom(void *buffer, Py_ssize_t size) +{ + if (size < 0) { + PyErr_Format(PyExc_ValueError, + "negative argument not allowed"); + return -1; + } + if (size == 0) + return 0; + +#ifdef MS_WINDOWS + return win32_urandom((unsigned char *)buffer, size, 1); +#else +# ifdef __VMS + return vms_urandom((unsigned char *)buffer, size, 1); +# else + return dev_urandom_python((char*)buffer, size); +# endif +#endif +} + +void +_PyRandom_Init(void) +{ + char *env; + void *secret = &_Py_HashSecret; + Py_ssize_t secret_size = sizeof(_Py_HashSecret); + + if (random_initialized) + return; + random_initialized = 1; + + /* + By default, hash randomization is disabled, and only + enabled if PYTHONHASHSEED is set to non-empty or if + "-R" is provided at the command line: + */ + if (!Py_HashRandomizationFlag) { + /* Disable the randomized hash: */ + memset(secret, 0, secret_size); + return; + } + + /* + Hash randomization is enabled. Generate a per-process secret, + using PYTHONHASHSEED if provided. + */ + + env = Py_GETENV("PYTHONHASHSEED"); + if (env && *env != '\0' & strcmp(env, "random") != 0) { + char *endptr = env; + unsigned long seed; + seed = strtoul(env, &endptr, 10); + if (*endptr != '\0' + || seed > 4294967295UL + || (errno == ERANGE && seed == ULONG_MAX)) + { + Py_FatalError("PYTHONHASHSEED must be \"random\" or an integer " + "in range [0; 4294967295]"); + } + if (seed == 0) { + /* disable the randomized hash */ + memset(secret, 0, secret_size); + } + else { + lcg_urandom(seed, (unsigned char*)secret, secret_size); + } + } + else { +#ifdef MS_WINDOWS + (void)win32_urandom((unsigned char *)secret, secret_size, 0); +#else /* #ifdef MS_WINDOWS */ +# ifdef __VMS + vms_urandom((unsigned char *)secret, secret_size, 0); +# else + dev_urandom_noraise((char*)secret, secret_size); +# endif +#endif + } +} diff -r a72e0e1d0292 -r 4a31f6b11e7a Python/sysmodule.c --- a/Python/sysmodule.c Mon Feb 20 18:35:26 2012 +0000 +++ b/Python/sysmodule.c Mon Feb 20 21:31:46 2012 +0100 @@ -1368,6 +1368,7 @@ /* {"skip_first", "-x"}, */ {"bytes_warning", "-b"}, {"quiet", "-q"}, + {"hash_randomization", "-R"}, {0} }; @@ -1376,9 +1377,9 @@ flags__doc__, /* doc */ flags_fields, /* fields */ #ifdef RISCOS - 13 + 14 #else - 12 + 13 #endif }; @@ -1412,6 +1413,7 @@ /* SetFlag(skipfirstline); */ SetFlag(Py_BytesWarningFlag); SetFlag(Py_QuietFlag); + SetFlag(Py_HashRandomizationFlag); #undef SetFlag if (PyErr_Occurred()) {/georg@python.org