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, 9 insertions, 0 deletions

diff --git a/Include/object.h b/Include/object.h
index ef73a21..7848cf4 100644
--- a/Include/object.h
+++ b/Include/object.h
@@ -473,6 +473,12 @@ 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) _PyUnicode_AsString(PyObject_Repr(obj))
 
diff --git a/Include/pydebug.h b/Include/pydebug.h
index 0a31f5b..5969e44 100644
--- a/Include/pydebug.h
+++ b/Include/pydebug.h
@@ -19,6 +19,7 @@ PyAPI_DATA(int) Py_DivisionWarningFlag;
 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 --git a/Include/pythonrun.h b/Include/pythonrun.h
index 96a0e23..af4aa08 100644
--- a/Include/pythonrun.h
+++ b/Include/pythonrun.h
@@ -174,6 +174,8 @@ 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
 }