#include "tokenizer.h"
@@ -1131,6 +1132,28 @@ _PyPegen_number_token(Parser *p)
if (c == NULL) {
p->error_indicator = 1;
+ PyThreadState *tstate = _PyThreadState_GET();
+ // The only way a ValueError should happen in _this_ code is via
+ // PyLong_FromString hitting a length limit.
+ if (tstate->curexc_type == PyExc_ValueError &&
+ tstate->curexc_value != NULL) {
+ PyObject *type, *value, *tb;
+ // This acts as PyErr_Clear() as we're replacing curexc.
+ PyErr_Fetch(&type, &value, &tb);
+ Py_XDECREF(tb);
+ Py_DECREF(type);
+ /* Intentionally omitting columns to avoid a wall of 1000s of '^'s
+ * on the error message. Nobody is going to overlook their huge
+ * numeric literal once given the line. */
+ RAISE_ERROR_KNOWN_LOCATION(
+ p, PyExc_SyntaxError,
+ t->lineno, -1 /* col_offset */,
+ t->end_lineno, -1 /* end_col_offset */,
+ "%S - Consider hexadecimal for huge integer literals "
+ "to avoid decimal conversion limits.",
+ value);
+ Py_DECREF(value);
+ }
return NULL;
}
diff --git a/Python/clinic/sysmodule.c.h b/Python/clinic/sysmodule.c.h
index 04c84811498873..2a6ad89137b07c 100644
--- a/Python/clinic/sysmodule.c.h
+++ b/Python/clinic/sysmodule.c.h
@@ -647,6 +647,59 @@ sys_mdebug(PyObject *module, PyObject *arg)
#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)(void(*)(void))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;
+ static const char * const _keywords[] = {"maxdigits", NULL};
+ static _PyArg_Parser _parser = {NULL, _keywords, "set_int_max_str_digits", 0};
+ 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"
@@ -983,4 +1036,4 @@ sys__deactivate_opcache(PyObject *module, PyObject *Py_UNUSED(ignored))
#ifndef SYS_GETANDROIDAPILEVEL_METHODDEF
#define SYS_GETANDROIDAPILEVEL_METHODDEF
#endif /* !defined(SYS_GETANDROIDAPILEVEL_METHODDEF) */
-/*[clinic end generated code: output=68c62b9ca317a0c8 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=6230a1e3a4415744 input=a9049054013a1b77]*/
diff --git a/Python/initconfig.c b/Python/initconfig.c
index 0341e7baa210c9..0d2077a6573d36 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()
@@ -95,6 +96,10 @@ static const char usage_3[] = "\
-X pycache_prefix=PATH: enable writing .pyc files to a parallel tree rooted at the\n\
given directory instead of to the code tree\n\
-X warn_default_encoding: enable opt-in EncodingWarning for 'encoding=None'\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.\n\
+\n\
--check-hash-based-pycs always|default|never:\n\
control how Python invalidates hash-based .pyc files\n\
";
@@ -120,6 +125,10 @@ static const char usage_6[] =
" 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"
@@ -721,6 +730,10 @@ _PyConfig_InitCompatConfig(PyConfig *config)
#endif
}
+/* 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)
@@ -1757,6 +1770,48 @@ 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)
@@ -1808,6 +1863,12 @@ config_read_complex_options(PyConfig *config)
return status;
}
}
+ 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);
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index ac49f7867a5cb3..1d5a06a6b4787e 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -17,6 +17,7 @@ Data members:
#include "Python.h"
#include "pycore_ceval.h" // _Py_RecursionLimitLowerWaterMark()
#include "pycore_initconfig.h" // _PyStatus_EXCEPTION()
+#include "pycore_long.h" // _PY_LONG_MAX_STR_DIGITS_THRESHOLD
#include "pycore_object.h" // _PyObject_IS_GC()
#include "pycore_pathconfig.h" // _PyPathConfig_ComputeSysPath0()
#include "pycore_pyerrors.h" // _PyErr_Fetch()
@@ -1652,6 +1653,45 @@ 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)
{
@@ -2027,6 +2067,8 @@ static PyMethodDef sys_methods[] = {
SYS_GETANDROIDAPILEVEL_METHODDEF
SYS_UNRAISABLEHOOK_METHODDEF
SYS__DEACTIVATE_OPCACHE_METHODDEF
+ SYS_GET_INT_MAX_STR_DIGITS_METHODDEF
+ SYS_SET_INT_MAX_STR_DIGITS_METHODDEF
{NULL, NULL} /* sentinel */
};
@@ -2516,6 +2558,7 @@ static PyStructSequence_Field flags_fields[] = {
{"dev_mode", "-X dev"},
{"utf8_mode", "-X utf8"},
{"warn_default_encoding", "-X warn_default_encoding"},
+ {"int_max_str_digits", "-X int_max_str_digits"},
{0}
};
@@ -2523,7 +2566,7 @@ static PyStructSequence_Desc flags_desc = {
"sys.flags", /* name */
flags__doc__, /* doc */
flags_fields, /* fields */
- 16
+ 17
};
static int
@@ -2563,6 +2606,7 @@ set_flags_from_config(PyInterpreterState *interp, PyObject *flags)
SetFlagObj(PyBool_FromLong(config->dev_mode));
SetFlag(preconfig->utf8_mode);
SetFlag(config->warn_default_encoding);
+ SetFlag(_Py_global_config_int_max_str_digits);
#undef SetFlagObj
#undef SetFlag
return 0;
pFad - Phonifier reborn
Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.
Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.
Alternative Proxies:
Alternative Proxy
pFad Proxy
pFad v3 Proxy
pFad v4 Proxy