gh-95778: CVE-2020-10735: Prevent DoS by very large int() (#96499)

Integer to and from text conversions via CPython's bignum `int` type is not safe against denial of service attacks due to malicious input. Very large input strings with hundred thousands of digits can consume several CPU seconds.

This PR comes fresh from a pile of work done in our private PSRT security response team repo.

Signed-off-by: Christian Heimes [Red Hat] <christian@python.org>
Tons-of-polishing-up-by: Gregory P. Smith [Google] <greg@krypto.org>
Reviews via the private PSRT repo via many others (see the NEWS entry in the PR).

<!-- gh-issue-number: gh-95778 -->
* Issue: gh-95778
<!-- /gh-issue-number -->

I wrote up [a one pager for the release managers](https://docs.google.com/document/d/1KjuF_aXlzPUxTK4BMgezGJ2Pn7uevfX7g0_mvgHlL7Y/edit#). Much of that text wound up in the Issue. Backports PRs already exist. See the issue for links.

3 files changed, 186 insertions, 3 deletions

diff --git a/Python/clinic/sysmodule.c.h b/Python/clinic/sysmodule.c.h
index ddf01a7..6864b8b 100644
--- a/Python/clinic/sysmodule.c.h
+++ b/Python/clinic/sysmodule.c.h
@@ -745,6 +745,82 @@ exit:
 
 #endif /* defined(USE_MALLOPT) */
 
+PyDoc_STRVAR(sys_get_int_max_str_digits__doc__,
+"get_int_max_str_digits($module, /)\n"
+"--\n"
+"\n"
+"Set the maximum string digits limit for non-binary int<->str conversions.");
+
+#define SYS_GET_INT_MAX_STR_DIGITS_METHODDEF    \
+    {"get_int_max_str_digits", (PyCFunction)sys_get_int_max_str_digits, METH_NOARGS, sys_get_int_max_str_digits__doc__},
+
+static PyObject *
+sys_get_int_max_str_digits_impl(PyObject *module);
+
+static PyObject *
+sys_get_int_max_str_digits(PyObject *module, PyObject *Py_UNUSED(ignored))
+{
+    return sys_get_int_max_str_digits_impl(module);
+}
+
+PyDoc_STRVAR(sys_set_int_max_str_digits__doc__,
+"set_int_max_str_digits($module, /, maxdigits)\n"
+"--\n"
+"\n"
+"Set the maximum string digits limit for non-binary int<->str conversions.");
+
+#define SYS_SET_INT_MAX_STR_DIGITS_METHODDEF    \
+    {"set_int_max_str_digits", _PyCFunction_CAST(sys_set_int_max_str_digits), METH_FASTCALL|METH_KEYWORDS, sys_set_int_max_str_digits__doc__},
+
+static PyObject *
+sys_set_int_max_str_digits_impl(PyObject *module, int maxdigits);
+
+static PyObject *
+sys_set_int_max_str_digits(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
+{
+    PyObject *return_value = NULL;
+    #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
+
+    #define NUM_KEYWORDS 1
+    static struct {
+        PyGC_Head _this_is_not_used;
+        PyObject_VAR_HEAD
+        PyObject *ob_item[NUM_KEYWORDS];
+    } _kwtuple = {
+        .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
+        .ob_item = { &_Py_ID(maxdigits), },
+    };
+    #undef NUM_KEYWORDS
+    #define KWTUPLE (&_kwtuple.ob_base.ob_base)
+
+    #else  // !Py_BUILD_CORE
+    #  define KWTUPLE NULL
+    #endif  // !Py_BUILD_CORE
+
+    static const char * const _keywords[] = {"maxdigits", NULL};
+    static _PyArg_Parser _parser = {
+        .keywords = _keywords,
+        .fname = "set_int_max_str_digits",
+        .kwtuple = KWTUPLE,
+    };
+    #undef KWTUPLE
+    PyObject *argsbuf[1];
+    int maxdigits;
+
+    args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf);
+    if (!args) {
+        goto exit;
+    }
+    maxdigits = _PyLong_AsInt(args[0]);
+    if (maxdigits == -1 && PyErr_Occurred()) {
+        goto exit;
+    }
+    return_value = sys_set_int_max_str_digits_impl(module, maxdigits);
+
+exit:
+    return return_value;
+}
+
 PyDoc_STRVAR(sys_getrefcount__doc__,
 "getrefcount($module, object, /)\n"
 "--\n"
@@ -1267,4 +1343,4 @@ sys_is_stack_trampoline_active(PyObject *module, PyObject *Py_UNUSED(ignored))
 #ifndef SYS_GETANDROIDAPILEVEL_METHODDEF
     #define SYS_GETANDROIDAPILEVEL_METHODDEF
 #endif /* !defined(SYS_GETANDROIDAPILEVEL_METHODDEF) */
-/*[clinic end generated code: output=43b44240211afe95 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=15318cdd96b62b06 input=a9049054013a1b77]*/
diff --git a/Python/initconfig.c b/Python/initconfig.c
index 33a8f27..f18ec40 100644
--- a/Python/initconfig.c
+++ b/Python/initconfig.c
@@ -3,6 +3,7 @@
 #include "pycore_getopt.h"        // _PyOS_GetOpt()
 #include "pycore_initconfig.h"    // _PyStatus_OK()
 #include "pycore_interp.h"        // _PyInterpreterState.runtime
+#include "pycore_long.h"          // _PY_LONG_MAX_STR_DIGITS_THRESHOLD
 #include "pycore_pathconfig.h"    // _Py_path_config
 #include "pycore_pyerrors.h"      // _PyErr_Fetch()
 #include "pycore_pylifecycle.h"   // _Py_PreInitializeFromConfig()
@@ -124,7 +125,11 @@ The following implementation-specific options are available:\n\
     do nothing if is not supported on the current system. The default value is \"off\".\n\
 \n\
 -X frozen_modules=[on|off]: whether or not frozen modules should be used.\n\
-   The default is \"on\" (or \"off\" if you are running a local build).";
+   The default is \"on\" (or \"off\" if you are running a local build).\n\
+\n\
+-X int_max_str_digits=number: limit the size of int<->str conversions.\n\
+    This helps avoid denial of service attacks when parsing untrusted data.\n\
+    The default is sys.int_info.default_max_str_digits.  0 disables.";
 
 /* Envvars that don't have equivalent command-line options are listed first */
 static const char usage_envvars[] =
@@ -144,6 +149,10 @@ static const char usage_envvars[] =
 "   to seed the hashes of str and bytes objects.  It can also be set to an\n"
 "   integer in the range [0,4294967295] to get hash values with a\n"
 "   predictable seed.\n"
+"PYTHONINTMAXSTRDIGITS: limits the maximum digit characters in an int value\n"
+"   when converting from a string and when converting an int back to a str.\n"
+"   A value of 0 disables the limit.  Conversions to or from bases 2, 4, 8,\n"
+"   16, and 32 are never limited.\n"
 "PYTHONMALLOC: set the Python memory allocators and/or install debug hooks\n"
 "   on Python memory allocators. Use PYTHONMALLOC=debug to install debug\n"
 "   hooks.\n"
@@ -784,6 +793,10 @@ _PyConfig_InitCompatConfig(PyConfig *config)
     config->code_debug_ranges = 1;
 }
 
+/* Excluded from public struct PyConfig for backporting reasons. */
+/* default to unconfigured, _PyLong_InitTypes() does the rest */
+int _Py_global_config_int_max_str_digits = -1;
+
 
 static void
 config_init_defaults(PyConfig *config)
@@ -1762,6 +1775,48 @@ config_init_tracemalloc(PyConfig *config)
     return _PyStatus_OK();
 }
 
+static PyStatus
+config_init_int_max_str_digits(PyConfig *config)
+{
+    int maxdigits;
+    int valid = 0;
+
+    const char *env = config_get_env(config, "PYTHONINTMAXSTRDIGITS");
+    if (env) {
+        if (!_Py_str_to_int(env, &maxdigits)) {
+            valid = ((maxdigits == 0) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD));
+        }
+        if (!valid) {
+#define STRINGIFY(VAL) _STRINGIFY(VAL)
+#define _STRINGIFY(VAL) #VAL
+            return _PyStatus_ERR(
+                    "PYTHONINTMAXSTRDIGITS: invalid limit; must be >= "
+                    STRINGIFY(_PY_LONG_MAX_STR_DIGITS_THRESHOLD)
+                    " or 0 for unlimited.");
+        }
+        _Py_global_config_int_max_str_digits = maxdigits;
+    }
+
+    const wchar_t *xoption = config_get_xoption(config, L"int_max_str_digits");
+    if (xoption) {
+        const wchar_t *sep = wcschr(xoption, L'=');
+        if (sep) {
+            if (!config_wstr_to_int(sep + 1, &maxdigits)) {
+                valid = ((maxdigits == 0) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD));
+            }
+        }
+        if (!valid) {
+            return _PyStatus_ERR(
+                    "-X int_max_str_digits: invalid limit; must be >= "
+                    STRINGIFY(_PY_LONG_MAX_STR_DIGITS_THRESHOLD)
+                    " or 0 for unlimited.");
+#undef _STRINGIFY
+#undef STRINGIFY
+        }
+        _Py_global_config_int_max_str_digits = maxdigits;
+    }
+    return _PyStatus_OK();
+}
 
 static PyStatus
 config_init_pycache_prefix(PyConfig *config)
@@ -1818,6 +1873,7 @@ config_read_complex_options(PyConfig *config)
             return status;
         }
     }
+
     if (config->perf_profiling < 0) {
         status = config_init_perf_profiling(config);
         if (_PyStatus_EXCEPTION(status)) {
@@ -1825,6 +1881,13 @@ config_read_complex_options(PyConfig *config)
         }
     }
 
+    if (_Py_global_config_int_max_str_digits < 0) {
+        status = config_init_int_max_str_digits(config);
+        if (_PyStatus_EXCEPTION(status)) {
+            return status;
+        }
+    }
+
     if (config->pycache_prefix == NULL) {
         status = config_init_pycache_prefix(config);
         if (_PyStatus_EXCEPTION(status)) {
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 75e6455..a33abb2 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -20,6 +20,7 @@ Data members:
 #include "pycore_code.h"          // _Py_QuickenedCount
 #include "pycore_frame.h"         // _PyInterpreterFrame
 #include "pycore_initconfig.h"    // _PyStatus_EXCEPTION()
+#include "pycore_long.h"          // _PY_LONG_MAX_STR_DIGITS_THRESHOLD
 #include "pycore_namespace.h"     // _PyNamespace_New()
 #include "pycore_object.h"        // _PyObject_IS_GC()
 #include "pycore_pathconfig.h"    // _PyPathConfig_ComputeSysPath0()
@@ -1671,6 +1672,45 @@ sys_mdebug_impl(PyObject *module, int flag)
 }
 #endif /* USE_MALLOPT */
 
+
+/*[clinic input]
+sys.get_int_max_str_digits
+
+Set the maximum string digits limit for non-binary int<->str conversions.
+[clinic start generated code]*/
+
+static PyObject *
+sys_get_int_max_str_digits_impl(PyObject *module)
+/*[clinic end generated code: output=0042f5e8ae0e8631 input=8dab13e2023e60d5]*/
+{
+    PyInterpreterState *interp = _PyInterpreterState_GET();
+    return PyLong_FromSsize_t(interp->int_max_str_digits);
+}
+
+/*[clinic input]
+sys.set_int_max_str_digits
+
+    maxdigits: int
+
+Set the maximum string digits limit for non-binary int<->str conversions.
+[clinic start generated code]*/
+
+static PyObject *
+sys_set_int_max_str_digits_impl(PyObject *module, int maxdigits)
+/*[clinic end generated code: output=734d4c2511f2a56d input=d7e3f325db6910c5]*/
+{
+    PyThreadState *tstate = _PyThreadState_GET();
+    if ((!maxdigits) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD)) {
+        tstate->interp->int_max_str_digits = maxdigits;
+        Py_RETURN_NONE;
+    } else {
+        PyErr_Format(
+            PyExc_ValueError, "maxdigits must be 0 or larger than %d",
+            _PY_LONG_MAX_STR_DIGITS_THRESHOLD);
+        return NULL;
+    }
+}
+
 size_t
 _PySys_GetSizeOf(PyObject *o)
 {
@@ -2186,6 +2226,8 @@ static PyMethodDef sys_methods[] = {
     SYS_DEACTIVATE_STACK_TRAMPOLINE_METHODDEF
     SYS_IS_STACK_TRAMPOLINE_ACTIVE_METHODDEF
     SYS_UNRAISABLEHOOK_METHODDEF
+    SYS_GET_INT_MAX_STR_DIGITS_METHODDEF
+    SYS_SET_INT_MAX_STR_DIGITS_METHODDEF
 #ifdef Py_STATS
     SYS__STATS_ON_METHODDEF
     SYS__STATS_OFF_METHODDEF
@@ -2686,6 +2728,7 @@ static PyStructSequence_Field flags_fields[] = {
     {"utf8_mode",               "-X utf8"},
     {"warn_default_encoding",   "-X warn_default_encoding"},
     {"safe_path", "-P"},
+    {"int_max_str_digits",      "-X int_max_str_digits"},
     {0}
 };
 
@@ -2693,7 +2736,7 @@ static PyStructSequence_Desc flags_desc = {
     "sys.flags",        /* name */
     flags__doc__,       /* doc */
     flags_fields,       /* fields */
-    17
+    18
 };
 
 static int
@@ -2734,6 +2777,7 @@ set_flags_from_config(PyInterpreterState *interp, PyObject *flags)
     SetFlag(preconfig->utf8_mode);
     SetFlag(config->warn_default_encoding);
     SetFlagObj(PyBool_FromLong(config->safe_path));
+    SetFlag(_Py_global_config_int_max_str_digits);
 #undef SetFlagObj
 #undef SetFlag
     return 0;