merge 2.6 with hash randomization fix

Doc/library/sys.rst

@@ -286,6 +286,7 @@ always available.
    :const:`verbose`              :option:`-v`
    :const:`unicode`              :option:`-U`
    :const:`bytes_warning`        :option:`-b`
+   :const:`hash_randomization`   :option:`-R`
    ============================= ===================================
 
    .. versionadded:: 2.6

Doc/reference/datamodel.rst

@@ -1282,6 +1282,8 @@ Basic customization
       modules are still available at the time when the :meth:`__del__` method is
       called.
 
+   See also the :option:`-R` command-line option.
+
 
 .. method:: object.__repr__(self)
 

Doc/using/cmdline.rst

@@ -24,7 +24,7 @@ Command line
 
 When invoking Python, you may specify any of these options::
 
-    python [-BdEiOQsStuUvVWxX3?] [-c command | -m module-name | script | - ] [args]
+    python [-BdEiOQsRStuUvVWxX3?] [-c command | -m module-name | script | - ] [args]
 
 The most common use case is, of course, a simple invocation of a script::
 
@@ -253,6 +253,29 @@ Miscellaneous options
       :pep:`238` -- Changing the division operator
 
 
+.. 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:: 2.6.8
+
+
 .. cmdoption:: -s
 
    Don't add the :data:`user site-packages directory <site.USER_SITE>` to
@@ -522,6 +545,27 @@ These environment variables influence Python's behavior.
 
    .. versionadded:: 2.6
 
+.. 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:: 2.6.8
+
+
 .. envvar:: PYTHONIOENCODING
 
    Overrides the encoding used for stdin/stdout/stderr, in the syntax

Include/object.h

@@ -517,6 +517,12 @@ PyAPI_FUNC(void) Py_ReprLeave(PyObject *);
 PyAPI_FUNC(long) _Py_HashDouble(double);
 PyAPI_FUNC(long) _Py_HashPointer(void*);
 
+typedef struct {
+    long prefix;
+    long suffix;
+} _Py_HashSecret_t;
+PyAPI_DATA(_Py_HashSecret_t) _Py_HashSecret;
+
 /* Helper for passing objects to printf and the like */
 #define PyObject_REPR(obj) PyString_AS_STRING(PyObject_Repr(obj))
 

Include/pydebug.h

@@ -26,6 +26,7 @@ PyAPI_DATA(int) Py_NoUserSiteDirectory;
 PyAPI_DATA(int) _Py_QnewFlag;
 /* Warn about 3.x issues */
 PyAPI_DATA(int) Py_Py3kWarningFlag;
+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

Include/pythonrun.h

@@ -171,6 +171,8 @@ typedef void (*PyOS_sighandler_t)(int);
 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
 }

Lib/os.py

@@ -738,22 +738,3 @@ try:
                      _make_statvfs_result)
 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")
-        try:
-            bs = b""
-            while n > len(bs):
-                bs += read(_urandomfd, n - len(bs))
-        finally:
-            close(_urandomfd)
-        return bs

Lib/test/test_cmd_line.py

@@ -86,6 +86,20 @@ class CmdLineTest(unittest.TestCase):
             self.exit_code('-c', 'pass'),
             0)
 
+    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"))'
+            data = self.start_python('-R', '-c', code)
+            hashes.append(data)
+        self.assertNotEqual(hashes[0], hashes[1])
+
+        # Verify that sys.flags contains hash_randomization
+        code = 'import sys; print sys.flags'
+        data = self.start_python('-R', '-c', code)
+        self.assertTrue('hash_randomization=1' in data)
 
 def test_main():
     test.test_support.run_unittest(CmdLineTest)

Lib/test/test_hash.py

@@ -3,10 +3,18 @@
 #
 # Also test that hash implementations are inherited as expected
 
+import os
+import sys
+import struct
+import datetime
 import unittest
+import subprocess
+
 from test import test_support
 from collections import Hashable
 
+IS_64BIT = (struct.calcsize('l') == 8)
+
 
 class HashEqualityTestCase(unittest.TestCase):
 
@@ -134,10 +142,100 @@ class HashBuiltinsTestCase(unittest.TestCase):
         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()
+        if seed is not None:
+            env['PYTHONHASHSEED'] = str(seed)
+        else:
+            env.pop('PYTHONHASHSEED', None)
+        cmd_line = [sys.executable, '-c', self.get_hash_command(repr_)]
+        p = subprocess.Popen(cmd_line, stdin=subprocess.PIPE,
+                             stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+                             env=env)
+        out, err = p.communicate()
+        out = test_support.strip_python_stderr(out)
+        return int(out.strip())
+
+    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 UnicodeHashRandomizationTests(StringlikeHashRandomizationTests):
+    repr_ = repr(u'abc')
+
+    def test_empty_string(self):
+        self.assertEqual(hash(u""), 0)
+
+class BufferHashRandomizationTests(StringlikeHashRandomizationTests):
+    repr_ = 'buffer("abc")'
+
+    def test_empty_string(self):
+        self.assertEqual(hash(buffer("")), 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():
     test_support.run_unittest(HashEqualityTestCase,
                               HashInheritanceTestCase,
-                              HashBuiltinsTestCase)
+                              HashBuiltinsTestCase,
+                              StrHashRandomizationTests,
+                              UnicodeHashRandomizationTests,
+                              BufferHashRandomizationTests,
+                              DatetimeDateTests,
+                              DatetimeDatetimeTests,
+                              DatetimeTimeTests)
+
 
 
 if __name__ == "__main__":

Lib/test/test_os.py

@@ -10,6 +10,7 @@ import sys
 import signal
 import subprocess
 import time
+
 from test import test_support
 import mmap
 import uuid
@@ -536,8 +537,41 @@ class URandomTests (unittest.TestCase):
             self.assertRaises(TypeError, os.urandom, 0.9)
             self.assertRaises(TypeError, os.urandom, 1.1)
             self.assertRaises(TypeError, os.urandom, 2.0)
-        except NotImplementedError:
-            pass
+            self.assertEqual(len(os.urandom(0.9)), 0)
+            self.assertEqual(len(os.urandom(1.1)), 1)
+            self.assertEqual(len(os.urandom(2.0)), 2)
+
+    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.write(data)',
+            'sys.stdout.flush()'))
+        cmd_line = [sys.executable, '-c', code]
+        p = subprocess.Popen(cmd_line, stdin=subprocess.PIPE,
+                             stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+        out, err = p.communicate()
+        out = test_support.strip_python_stderr(out)
+        self.assertEqual(len(out), count)
+        return out
+
+    def test_urandom_subprocess(self):
+        data1 = self.get_urandom_subprocess(16)
+        data2 = self.get_urandom_subprocess(16)
+        self.assertNotEqual(data1, data2)
+>>>>>>> other
 
     def test_execvpe_with_bad_arglist(self):
         self.assertRaises(ValueError, os.execvpe, 'notepad', [], None)

Lib/test/test_set.py

@@ -687,6 +687,17 @@ class TestBasicOps(unittest.TestCase):
         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):
         fo = open(test_support.TESTFN, "wb")
         try:
@@ -836,6 +847,46 @@ class TestBasicOpsTriple(TestBasicOps):
         self.length = 3
         self.repr   = None
 
+#------------------------------------------------------------------------------
+
+class TestBasicOpsString(TestBasicOps):
+    def setUp(self):
+        self.case   = "string set"
+        self.values = ["a", "b", "c"]
+        self.set    = set(self.values)
+        self.dup    = set(self.values)
+        self.length = 3
+
+    def test_repr(self):
+        self.check_repr_against_values()
+
+#------------------------------------------------------------------------------
+
+class TestBasicOpsUnicode(TestBasicOps):
+    def setUp(self):
+        self.case   = "unicode set"
+        self.values = [u"a", u"b", u"c"]
+        self.set    = set(self.values)
+        self.dup    = set(self.values)
+        self.length = 3
+
+    def test_repr(self):
+        self.check_repr_against_values()
+
+#------------------------------------------------------------------------------
+
+class TestBasicOpsMixedStringUnicode(TestBasicOps):
+    def setUp(self):
+        self.case   = "string and bytes set"
+        self.values = ["a", "b", u"a", u"b"]
+        self.set    = set(self.values)
+        self.dup    = set(self.values)
+        self.length = 4
+
+    def test_repr(self):
+        with test_support.check_warnings():
+            self.check_repr_against_values()
+
 #==============================================================================
 
 def baditer():

Lib/test/test_support.py

@@ -36,8 +36,8 @@ __all__ = ["Error", "TestFailed", "ResourceDenied", "import_module",
            "BasicTestRunner", "run_unittest", "run_doctest", "threading_setup",
            "threading_cleanup", "reap_children", "cpython_only",
            "check_impl_detail", "get_attribute", "py3k_bytes",
-           "import_fresh_module"]
-
+           "import_fresh_module", "threading_cleanup", "reap_children",
+           "strip_python_stderr"]
 
 class Error(Exception):
     """Base class for regression test exceptions."""

Lib/test/test_sys.py

@@ -438,7 +438,7 @@ class SysModuleTest(unittest.TestCase):
         attrs = ("debug", "py3k_warning", "division_warning", "division_new",
                  "inspect", "interactive", "optimize", "dont_write_bytecode",
                  "no_site", "ignore_environment", "tabcheck", "verbose",
-                 "unicode", "bytes_warning")
+                 "unicode", "bytes_warning", "hash_randomization")
         for attr in attrs:
             self.assertTrue(hasattr(sys.flags, attr), attr)
             self.assertEqual(type(getattr(sys.flags, attr)), int, attr)

Makefile.pre.in

@@ -290,6 +290,7 @@ PYTHON_OBJS=	\
 		Python/pymath.o \
 		Python/pystate.o \
 		Python/pythonrun.o \
+                Python/random.o \
 		Python/structmember.o \
 		Python/symtable.o \
 		Python/sysmodule.o \
@@ -739,7 +740,7 @@ buildbottest:	all platform
 		-@if which pybuildbot.identify >/dev/null 2>&1; then \
 			pybuildbot.identify "CC='$(CC)'" "CXX='$(CXX)'"; \
 		fi
-		$(TESTPYTHON) $(TESTPROG) -uall -rwW $(TESTOPTS)
+		$(TESTPYTHON) -R $(TESTPROG) -uall -rwW $(TESTOPTS)
 
 QUICKTESTOPTS=	$(TESTOPTS) -x test_subprocess test_io test_lib2to3 \
 		test_multibytecodec test_urllib2_localnet test_itertools \

Misc/NEWS

@@ -12,6 +12,11 @@ Core and Builtins
 - Issue #13020: Fix a reference leak when allocating a structsequence object
   fails.  Patch by Suman Saha.
 
+- Issue #13703: oCERT-2011-003: add -R command-line option and PYTHONHASHSEED
+  environment variable, 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 #11235: Fix OverflowError when trying to import a source file whose
   modification time doesn't fit in a 32-bit timestamp.
 

Misc/python.man

@@ -34,6 +34,9 @@ python \- an interpreted, interactive, object-oriented programming language
 .B \-OO
 ]
 [
+.B \-R
+]
+[
 .B -Q
 .I argument
 ]
@@ -151,6 +154,18 @@ to \fI.pyo\fP.  Given twice, causes docstrings to be discarded.
 .B \-OO
 Discard docstrings in addition to the \fB-O\fP optimizations.
 .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
@@ -423,6 +438,20 @@ specifying \fB\-v\fP multiple times.
 .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

Modules/main.c

@@ -40,7 +40,7 @@ static char **orig_argv;
 static int  orig_argc;
 
 /* command line options */
-#define BASE_OPTS "3bBc:dEhiJm:OQ:sStuUvVW:xX?"
+#define BASE_OPTS "3bBc:dEhiJm:OQ:RsStuUvVW:xX?"
 
 #ifndef RISCOS
 #define PROGRAM_OPTS BASE_OPTS
@@ -71,6 +71,9 @@ static char *usage_2 = "\
 -m mod : run library module as a script (terminates option list)\n\
 -O     : optimize generated bytecode slightly; also PYTHONOPTIMIZE=x\n\
 -OO    : remove doc-strings in addition to the -O optimizations\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 defense against denial-of-service attacks\n\
 -Q arg : division options: -Qold (default), -Qwarn, -Qwarnall, -Qnew\n\
 -s     : don't add user site directory to sys.path; also PYTHONNOUSERSITE\n\
 -S     : don't imply 'import site' on initialization\n\
@@ -102,6 +105,12 @@ PYTHONHOME   : alternate <prefix> directory (or <prefix>%c<exec_prefix>).\n\
 PYTHONCASEOK : ignore case in 'import' statements (Windows).\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
@@ -118,6 +127,7 @@ usage(int exitcode, char* program)
         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) {
@@ -389,6 +399,10 @@ Py_Main(int argc, char **argv)
             PySys_AddWarnOption(_PyOS_optarg);
             break;
 
+        case 'R':
+            Py_HashRandomizationFlag++;
+            break;
+
         /* This space reserved for other options */
 
         default:

Modules/posixmodule.c

@@ -8538,117 +8538,35 @@ posix_getloadavg(PyObject *self, PyObject *noargs)
 }
 #endif
 
-#ifdef MS_WINDOWS
-
-PyDoc_STRVAR(win32_urandom__doc__,
+PyDoc_STRVAR(posix_urandom__doc__,
 "urandom(n) -> str\n\n\
-Return a string of n random bytes suitable for cryptographic use.");
+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)
+static PyObject *
+posix_urandom(PyObject *self, PyObject *args)
 {
-    int howMany;
-    PyObject* result;
+    Py_ssize_t size;
+    PyObject *result;
+    int ret;
 
-    /* Read arguments */
-    if (! PyArg_ParseTuple(args, "i:urandom", &howMany))
+     /* Read arguments */
+    if (!PyArg_ParseTuple(args, "n:urandom", &size))
         return NULL;
-    if (howMany < 0)
+    if (size < 0)
         return PyErr_Format(PyExc_ValueError,
                             "negative argument not allowed");
+    result = PyBytes_FromStringAndSize(NULL, size);
+    if (result == NULL)
+        return NULL;
 
-    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 = PyString_FromStringAndSize(NULL, howMany);
-    if (result != NULL) {
-        /* Get random data */
-        memset(PyString_AS_STRING(result), 0, howMany); /* zero seed */
-        if (! pCryptGenRandom(hCryptProv, howMany, (unsigned char*)
-                              PyString_AS_STRING(result))) {
-            Py_DECREF(result);
-            return win32_error("CryptGenRandom", NULL);
-        }
+    ret = _PyOS_URandom(PyBytes_AS_STRING(result),
+                        PyBytes_GET_SIZE(result));
+    if (ret == -1) {
+        Py_DECREF(result);
+        return NULL;
     }
     return result;
 }
-#endif
-
-#ifdef __VMS
-/* Use openssl random routine */
-#include <openssl/rand.h>
-PyDoc_STRVAR(vms_urandom__doc__,
-"urandom(n) -> str\n\n\
-Return a string of 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)
-        return PyErr_Format(PyExc_ValueError,
-                            "negative argument not allowed");
-
-    /* Allocate bytes */
-    result = PyString_FromStringAndSize(NULL, howMany);
-    if (result != NULL) {
-        /* Get random data */
-        if (RAND_pseudo_bytes((unsigned char*)
-                              PyString_AS_STRING(result),
-                              howMany) < 0) {
-            Py_DECREF(result);
-            return PyErr_Format(PyExc_ValueError,
-                                "RAND_pseudo_bytes");
-        }
-    }
-    return result;
-}
-#endif
 
 #ifdef HAVE_SETRESUID
 PyDoc_STRVAR(posix_setresuid__doc__,
@@ -9035,12 +8953,6 @@ static PyMethodDef posix_methods[] = {
 #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
 #ifdef HAVE_SETRESUID
     {"setresuid",       posix_setresuid, METH_VARARGS, posix_setresuid__doc__},
 #endif
@@ -9053,7 +8965,7 @@ static PyMethodDef posix_methods[] = {
 #ifdef HAVE_GETRESGID
     {"getresgid",       posix_getresgid, METH_NOARGS, posix_getresgid__doc__},
 #endif
-
+    {"urandom",         posix_urandom,   METH_VARARGS, posix_urandom__doc__},
     {NULL,              NULL}            /* Sentinel */
 };
 

Objects/bufferobject.c

@@ -334,10 +334,20 @@ buffer_hash(PyBufferObject *self)
         return -1;
     p = (unsigned char *) ptr;
     len = size;
-    x = *p << 7;
+    /*
+      We make the hash of the empty buffer be 0, rather than using
+      (prefix ^ suffix), since this slightly obfuscates the hash secret
+    */
+    if (len == 0) {
+        self->b_hash = 0;
+        return 0;
+    }
+    x = _Py_HashSecret.prefix;
+    x ^= *p << 7;
     while (--len >= 0)
         x = (1000003*x) ^ *p++;
     x ^= size;
+    x ^= _Py_HashSecret.suffix;
     if (x == -1)
         x = -2;
     self->b_hash = x;

Objects/object.c

@@ -1094,6 +1094,8 @@ PyObject_HashNotImplemented(PyObject *self)
     return -1;
 }
 
+_Py_HashSecret_t _Py_HashSecret;
+
 long
 PyObject_Hash(PyObject *v)
 {

Objects/stringobject.c

@@ -1265,11 +1265,21 @@ string_hash(PyStringObject *a)
     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 = (1000003*x) ^ *p++;
     x ^= Py_SIZE(a);
+    x ^= _Py_HashSecret.suffix;
     if (x == -1)
         x = -2;
     a->ob_shash = x;

Objects/unicodeobject.c

@@ -6541,11 +6541,21 @@ unicode_hash(PyUnicodeObject *self)
     if (self->hash != -1)
         return self->hash;
     len = PyUnicode_GET_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 = PyUnicode_AS_UNICODE(self);
-    x = *p << 7;
+    x = _Py_HashSecret.prefix;
+    x ^= *p << 7;
     while (--len >= 0)
         x = (1000003*x) ^ *p++;
     x ^= PyUnicode_GET_SIZE(self);
+    x ^= _Py_HashSecret.suffix;
     if (x == -1)
         x = -2;
     self->hash = x;

Python/pythonrun.c

@@ -67,6 +67,7 @@ static void call_sys_exitfunc(void);
 static void call_ll_exitfuncs(void);
 extern void _PyUnicode_Init(void);
 extern void _PyUnicode_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 */
   true divisions (which they will be in 2.3). */
 int _Py_QnewFlag = 0;
 int Py_NoUserSiteDirectory = 0; /* for -s and site.py */
+int Py_HashRandomizationFlag = 0; /* for -R and PYTHONHASHSEED */
 
 /* PyModule_GetWarningsModule is no longer necessary as of 2.6
 since _warnings is builtin.  This API should not be used. */
@@ -166,6 +168,12 @@ Py_InitializeEx(int install_sigs)
         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)

Python/random.c

@@ -0,0 +1,302 @@
+#include "Python.h"
+#ifdef MS_WINDOWS
+#include <windows.h>
+#else
+#include <fcntl.h>
+#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 <openssl/rand.h>
+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
+    }
+}

Python/sysmodule.c

@@ -1209,6 +1209,7 @@ static PyStructSequence_Field flags_fields[] = {
     {"unicode",                 "-U"},
     /* {"skip_first",                   "-x"}, */
     {"bytes_warning", "-b"},
+    {"hash_randomization", "-R"},
     {0}
 };
 
@@ -1217,9 +1218,9 @@ static PyStructSequence_Desc flags_desc = {
     flags__doc__,       /* doc */
     flags_fields,       /* fields */
 #ifdef RISCOS
-    16
+    17
 #else
-    15
+    16
 #endif
 };
 
@@ -1256,6 +1257,7 @@ make_flags(void)
     SetFlag(Py_UnicodeFlag);
     /* SetFlag(skipfirstline); */
     SetFlag(Py_BytesWarningFlag);
+    SetFlag(Py_HashRandomizationFlag);
 #undef SetFlag
 
     if (PyErr_Occurred()) {