[issue24802] PyFloat_FromString Buffer Over-read
John Leitch
report at bugs.python.org
Thu Aug 6 05:15:21 CEST 2015
New submission from John Leitch:
Python suffers from a buffer over-read in PyFloat_FromString() that is caused by the incorrect assumption that buffers returned by PyObject_GetBuffer() are null-terminated. This could potentially result in the disclosure of adjacent memory.
PyObject *
PyFloat_FromString(PyObject *v)
{
const char *s, *last, *end;
double x;
PyObject *s_buffer = NULL;
Py_ssize_t len;
Py_buffer view = {NULL, NULL};
PyObject *result = NULL;
if (PyUnicode_Check(v)) {
s_buffer = _PyUnicode_TransformDecimalAndSpaceToASCII(v);
if (s_buffer == NULL)
return NULL;
s = PyUnicode_AsUTF8AndSize(s_buffer, &len);
if (s == NULL) {
Py_DECREF(s_buffer);
return NULL;
}
}
else if (PyObject_GetBuffer(v, &view, PyBUF_SIMPLE) == 0) {
s = (const char *)view.buf; <<<< The unterminated buffer is retrieved here.
len = view.len;
}
else {
PyErr_Format(PyExc_TypeError,
"float() argument must be a string or a number, not '%.200s'",
Py_TYPE(v)->tp_name);
return NULL;
}
last = s + len;
/* strip space */
while (s < last && Py_ISSPACE(*s))
s++;
while (s < last - 1 && Py_ISSPACE(last[-1]))
last--;
/* We don't care about overflow or underflow. If the platform
* supports them, infinities and signed zeroes (on underflow) are
* fine. */
x = PyOS_string_to_double(s, (char **)&end, NULL); <<<< The buffer is then passed
along here.
if (end != last) {
PyErr_Format(PyExc_ValueError,
"could not convert string to float: "
"%R", v);
result = NULL;
}
else if (x == -1.0 && PyErr_Occurred())
result = NULL;
else
result = PyFloat_FromDouble(x);
PyBuffer_Release(&view);
Py_XDECREF(s_buffer);
return result;
}
double
PyOS_string_to_double(const char *s,
char **endptr,
PyObject *overflow_exception)
{
double x, result=-1.0;
char *fail_pos;
errno = 0;
PyFPE_START_PROTECT("PyOS_string_to_double", return -1.0)
x = _PyOS_ascii_strtod(s, &fail_pos);
PyFPE_END_PROTECT(x)
if (errno == ENOMEM) {
PyErr_NoMemory();
fail_pos = (char *)s;
}
else if (!endptr && (fail_pos == s || *fail_pos != '\0'))
PyErr_Format(PyExc_ValueError, <<<< If any of these error paths are taken, the
unterminated buffer is passed along without
its length, ultimately resulting in a call
to unicode_fromformat_write_cstr().
"could not convert string to float: "
"%.200s", s);
else if (fail_pos == s)
PyErr_Format(PyExc_ValueError,
"could not convert string to float: "
"%.200s", s);
else if (errno == ERANGE && fabs(x) >= 1.0 && overflow_exception)
PyErr_Format(overflow_exception,
"value too large to convert to float: "
"%.200s", s);
else
result = x;
if (endptr != NULL)
*endptr = fail_pos;
return result;
}
static int
unicode_fromformat_write_cstr(_PyUnicodeWriter *writer, const char *str,
Py_ssize_t width, Py_ssize_t precision)
{
/* UTF-8 */
Py_ssize_t length;
PyObject *unicode;
int res;
length = strlen(str); <<<< str points to the unterminated buffer, which means
strlen() my read off the end, depending on the contents
of adjacent memory.
if (precision != -1)
length = Py_MIN(length, precision);
unicode = PyUnicode_DecodeUTF8Stateful(str, length, "replace", NULL); <<<< The new,
incorrect length is
passed along.
if (unicode == NULL)
return -1;
res = unicode_fromformat_write_str(writer, unicode, width, -1);
Py_DECREF(unicode);
return res;
}
A script that reproduces the issue is as follows:
import array
float(array.array("B",b"A"*0x10))
And it produces the following exception:
0:000> gu
eax=00000000 ebx=06116b00 ecx=00000000 edx=00000000 esi=06116b00 edi=00000000
eip=6516be1b esp=0080f440 ebp=0080f4f4 iopl=0 nv up ei pl zr na pe nc
cs=0023 ss=002b ds=002b es=002b fs=0053 gs=002b efl=00000246
python35!PyFloat_FromString+0xab:
6516be1b 8b4c2454 mov ecx,dword ptr [esp+54h] ss:002b:0080f494=090a2fe8
0:000> db @@(view.buf)
090a2fe8 41 41 41 41 41 41 41 41-41 41 41 41 41 41 41 41 AAAAAAAAAAAAAAAA
090a2ff8 c0 c0 c0 c0 d0 d0 d0 d0-?? ?? ?? ?? ?? ?? ?? ?? ........????????
090a3008 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3018 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3028 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3038 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3048 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3058 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
0:000> g
(828.bec): Access violation - code c0000005 (first chance)
First chance exceptions are reported before any exception handling.
This exception may be expected and handled.
eax=0080f4d0 ebx=0080f3a0 ecx=0080f3a0 edx=090a2fe8 esi=090a3000 edi=090a2fe9
eip=651ac280 esp=0080f31c ebp=0080f328 iopl=0 nv up ei ng nz na po nc
cs=0023 ss=002b ds=002b es=002b fs=0053 gs=002b efl=00010282
python35!unicode_fromformat_write_cstr+0x10:
651ac280 8a06 mov al,byte ptr [esi] ds:002b:090a3000=??
0:000> db esi-0x10
090a2ff0 41 41 41 41 41 41 41 41-c0 c0 c0 c0 d0 d0 d0 d0 AAAAAAAA........
090a3000 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3010 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3020 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3030 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3040 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3050 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
090a3060 ?? ?? ?? ?? ?? ?? ?? ??-?? ?? ?? ?? ?? ?? ?? ?? ????????????????
0:000> !analyze -v -nodb
*******************************************************************************
* *
* Exception Analysis *
* *
*******************************************************************************
FAULTING_IP:
python35!unicode_fromformat_write_cstr+10 [c:\build\cpython\objects\unicodeobject.c @ 2368]
651ac280 8a06 mov al,byte ptr [esi]
EXCEPTION_RECORD: ffffffff -- (.exr 0xffffffffffffffff)
ExceptionAddress: 651ac280 (python35!unicode_fromformat_write_cstr+0x00000010)
ExceptionCode: c0000005 (Access violation)
ExceptionFlags: 00000000
NumberParameters: 2
Parameter[0]: 00000000
Parameter[1]: 090a3000
Attempt to read from address 090a3000
CONTEXT: 00000000 -- (.cxr 0x0;r)
eax=0080f4d0 ebx=0080f3a0 ecx=0080f3a0 edx=090a2fe8 esi=090a3000 edi=090a2fe9
eip=651ac280 esp=0080f31c ebp=0080f328 iopl=0 nv up ei ng nz na po nc
cs=0023 ss=002b ds=002b es=002b fs=0053 gs=002b efl=00010282
python35!unicode_fromformat_write_cstr+0x10:
651ac280 8a06 mov al,byte ptr [esi] ds:002b:090a3000=??
FAULTING_THREAD: 00000bec
DEFAULT_BUCKET_ID: INVALID_POINTER_READ
PROCESS_NAME: python.exe
ERROR_CODE: (NTSTATUS) 0xc0000005 - The instruction at 0x%p referenced memory at 0x%p. The memory could not be %s.
EXCEPTION_CODE: (NTSTATUS) 0xc0000005 - The instruction at 0x%p referenced memory at 0x%p. The memory could not be %s.
EXCEPTION_PARAMETER1: 00000000
EXCEPTION_PARAMETER2: 090a3000
READ_ADDRESS: 090a3000
FOLLOWUP_IP:
python35!unicode_fromformat_write_cstr+10 [c:\build\cpython\objects\unicodeobject.c @ 2368]
651ac280 8a06 mov al,byte ptr [esi]
NTGLOBALFLAG: 2000000
APPLICATION_VERIFIER_FLAGS: 0
FAULTING_LOCAL_VARIABLE_NAME: length
APP: python.exe
ANALYSIS_VERSION: 6.3.9600.17029 (debuggers(dbg).140219-1702) x86fre
PRIMARY_PROBLEM_CLASS: INVALID_POINTER_READ
BUGCHECK_STR: APPLICATION_FAULT_INVALID_POINTER_READ
LAST_CONTROL_TRANSFER: from 651ac6e9 to 651ac280
STACK_TEXT:
0080f328 651ac6e9 ffffffff 000000c8 00000000 python35!unicode_fromformat_write_cstr+0x10
0080f384 651ac955 0080f39c 090a2fe8 65321778 python35!unicode_fromformat_arg+0x409
0080f3d8 651f1a1a 65321778 0080f404 090a2fe8 python35!PyUnicode_FromFormatV+0x65
0080f3f4 652070a9 6536bd38 65321778 090a2fe8 python35!PyErr_Format+0x1a
0080f42c 6516be70 090a2fe8 0080f484 00000000 python35!PyOS_string_to_double+0xa9
0080f4f4 6514808b 06116b00 6536d658 6536d658 python35!PyFloat_FromString+0x100
0080f554 6516e6e2 06116b00 06116b00 06116b00 python35!PyNumber_Float+0xcb
0080f568 65194e08 6536d658 0610e630 00000000 python35!float_new+0x72
0080f588 6514947d 6536d658 0610e630 00000000 python35!type_call+0x38
0080f5a4 651e49cc 6536d658 0610e630 00000000 python35!PyObject_Call+0x6d
0080f5d0 651e449c 00000001 0610e630 00000083 python35!do_call+0x11c
0080f600 651e18d8 060ceab0 00000000 00000040 python35!call_function+0x36c
0080f678 651e339f 060ceab0 00000000 08c73ff0 python35!PyEval_EvalFrameEx+0x2318
0080f6c4 6521a142 060eff58 00000000 00000000 python35!_PyEval_EvalCodeWithName+0x82f
0080f700 65219fd5 060eff58 060eff58 0080f7cc python35!run_mod+0x42
0080f72c 6521904a 06d40fc8 061571d0 00000101 python35!PyRun_FileExFlags+0x85
0080f770 650ef037 06d40fc8 061571d0 00000001 python35!PyRun_SimpleFileExFlags+0x20a
0080f79c 650ef973 0080f7cc 65492100 65492108 python35!run_file+0xe7
0080f840 1c4b143f 00000002 05e06f10 05e0cf48 python35!Py_Main+0x913
0080f88c 76323744 7ee8e000 76323720 ddf3f75b python!__scrt_common_main_seh+0xff
0080f8a0 7789a064 7ee8e000 16227053 00000000 KERNEL32!BaseThreadInitThunk+0x24
0080f8e8 7789a02f ffffffff 778bd7c3 00000000 ntdll!__RtlUserThreadStart+0x2f
0080f8f8 00000000 1c4b14f7 7ee8e000 00000000 ntdll!_RtlUserThreadStart+0x1b
STACK_COMMAND: .cxr 0x0 ; kb
FAULTING_SOURCE_LINE: c:\build\cpython\objects\unicodeobject.c
FAULTING_SOURCE_FILE: c:\build\cpython\objects\unicodeobject.c
FAULTING_SOURCE_LINE_NUMBER: 2368
FAULTING_SOURCE_CODE:
2364: Py_ssize_t length;
2365: PyObject *unicode;
2366: int res;
2367:
> 2368: length = strlen(str);
2369: if (precision != -1)
2370: length = Py_MIN(length, precision);
2371: unicode = PyUnicode_DecodeUTF8Stateful(str, length, "replace", NULL);
2372: if (unicode == NULL)
2373: return -1;
SYMBOL_STACK_INDEX: 0
SYMBOL_NAME: python35!unicode_fromformat_write_cstr+10
FOLLOWUP_NAME: MachineOwner
MODULE_NAME: python35
IMAGE_NAME: python35.dll
DEBUG_FLR_IMAGE_TIMESTAMP: 5598ccc2
FAILURE_BUCKET_ID: INVALID_POINTER_READ_c0000005_python35.dll!unicode_fromformat_write_cstr
BUCKET_ID: APPLICATION_FAULT_INVALID_POINTER_READ_python35!unicode_fromformat_write_cstr+10
ANALYSIS_SOURCE: UM
FAILURE_ID_HASH_STRING: um:invalid_pointer_read_c0000005_python35.dll!unicode_fromformat_write_cstr
FAILURE_ID_HASH: {1d85cbc9-3259-9a7e-3da2-8540573292b2}
Followup: MachineOwner
---------
To fix the issue, it is recommended that PyFloat_FromString() check the type of argument v after a successful PyObject_GetBuffer() call to determine if the buffer is null-terminated or otherwise. A proposed patch is attached.
----------
files: PyFloat_FromString_Buffer_Over-read.patch
keywords: patch
messages: 248099
nosy: JohnLeitch
priority: normal
severity: normal
status: open
title: PyFloat_FromString Buffer Over-read
type: security
versions: Python 3.5
Added file: http://bugs.python.org/file40132/PyFloat_FromString_Buffer_Over-read.patch
_______________________________________
Python tracker <report at bugs.python.org>
<http://bugs.python.org/issue24802>
_______________________________________
More information about the Python-bugs-list
mailing list