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.

3 files changed, 24 insertions, 2 deletions

diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index a0d4cbd..d63fabc 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -878,11 +878,21 @@ bytes_hash(PyBytesObject *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 = (_PyHASH_MULTIPLIER*x) ^ *p++;
     x ^= Py_SIZE(a);
+    x ^= _Py_HashSecret.suffix;
     if (x == -1)
         x = -2;
     a->ob_shash = x;
diff --git a/Objects/object.c b/Objects/object.c
index 694e7e7..84ec2f3 100644
--- a/Objects/object.c
+++ b/Objects/object.c
@@ -754,6 +754,8 @@ PyObject_HashNotImplemented(PyObject *v)
     return -1;
 }
 
+_Py_HashSecret_t _Py_HashSecret;
+
 Py_hash_t
 PyObject_Hash(PyObject *v)
 {
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 70856f5..467f95c 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -7676,11 +7676,21 @@ unicode_hash(PyUnicodeObject *self)
     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;