Skip to content

[3.12] gh-101006: Improve error handling when read marshal data (GH-101007) #106226

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 29, 2023
+72 −61
Merged

[3.12] gh-101006: Improve error handling when read marshal data (GH-101007) #106226

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Core and Builtins/2023-01-13-11-37-41.gh-issue-101006.fuLvn2.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Improve error handling when read :mod:`marshal` data.
132 changes: 71 additions & 61 deletions Python/marshal.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -751,23 +751,28 @@ r_string(Py_ssize_t n, RFILE *p)
static int
r_byte(RFILE *p)
{
int c = EOF;

if (p->ptr != NULL) {
if (p->ptr < p->end)
c = (unsigned char) *p->ptr++;
return c;
if (p->ptr < p->end) {
return (unsigned char) *p->ptr++;
}
}
if (!p->readable) {
else if (!p->readable) {
assert(p->fp);
c = getc(p->fp);
int c = getc(p->fp);
if (c != EOF) {
return c;
}
}
else {
const char *ptr = r_string(1, p);
if (ptr != NULL)
c = *(const unsigned char *) ptr;
if (ptr != NULL) {
return *(const unsigned char *) ptr;
}
return EOF;
}
return c;
PyErr_SetString(PyExc_EOFError,
"EOF read where not expected");
return EOF;
}

static int
Expand Down Expand Up @@ -828,10 +833,11 @@ r_PyLong(RFILE *p)
digit d;

n = r_long(p);
if (PyErr_Occurred())
return NULL;
if (n == 0)
return (PyObject *)_PyLong_New(0);
if (n == -1 && PyErr_Occurred()) {
return NULL;
}
if (n < -SIZE32_MAX || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (long size out of range)");
Expand All @@ -850,10 +856,6 @@ r_PyLong(RFILE *p)
d = 0;
for (j=0; j < PyLong_MARSHAL_RATIO; j++) {
md = r_short(p);
if (PyErr_Occurred()) {
Py_DECREF(ob);
return NULL;
}
if (md < 0 || md > PyLong_MARSHAL_BASE)
goto bad_digit;
d += (digit)md << j*PyLong_MARSHAL_SHIFT;
Expand All @@ -864,10 +866,6 @@ r_PyLong(RFILE *p)
d = 0;
for (j=0; j < shorts_in_top_digit; j++) {
md = r_short(p);
if (PyErr_Occurred()) {
Py_DECREF(ob);
return NULL;
}
if (md < 0 || md > PyLong_MARSHAL_BASE)
goto bad_digit;
/* topmost marshal digit should be nonzero */
Expand All @@ -879,18 +877,17 @@ r_PyLong(RFILE *p)
}
d += (digit)md << j*PyLong_MARSHAL_SHIFT;
}
if (PyErr_Occurred()) {
Py_DECREF(ob);
return NULL;
}
assert(!PyErr_Occurred());
/* top digit should be nonzero, else the resulting PyLong won't be
normalized */
ob->long_value.ob_digit[size-1] = d;
return (PyObject *)ob;
bad_digit:
Py_DECREF(ob);
PyErr_SetString(PyExc_ValueError,
"bad marshal data (digit out of range in long)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (digit out of range in long)");
}
return NULL;
}

Expand All @@ -913,8 +910,6 @@ r_float_str(RFILE *p)
const char *ptr;
n = r_byte(p);
if (n == EOF) {
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
return -1;
}
ptr = r_string(n, p);
Expand Down Expand Up @@ -992,8 +987,10 @@ r_object(RFILE *p)
PyObject *retval = NULL;

if (code == EOF) {
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
if (PyErr_ExceptionMatches(PyExc_EOFError)) {
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
}
return NULL;
}

Expand Down Expand Up @@ -1040,7 +1037,10 @@ r_object(RFILE *p)

case TYPE_INT:
n = r_long(p);
retval = PyErr_Occurred() ? NULL : PyLong_FromLong(n);
if (n == -1 && PyErr_Occurred()) {
break;
}
retval = PyLong_FromLong(n);
R_REF(retval);
break;

Expand Down Expand Up @@ -1106,10 +1106,11 @@ r_object(RFILE *p)
{
const char *ptr;
n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (bytes object size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (bytes object size out of range)");
}
break;
}
v = PyBytes_FromStringAndSize((char *)NULL, n);
Expand All @@ -1131,10 +1132,11 @@ r_object(RFILE *p)
/* fall through */
case TYPE_ASCII:
n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (string size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (string size out of range)");
}
break;
}
goto _read_ascii;
Expand All @@ -1145,8 +1147,6 @@ r_object(RFILE *p)
case TYPE_SHORT_ASCII:
n = r_byte(p);
if (n == EOF) {
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
break;
}
_read_ascii:
Expand All @@ -1173,10 +1173,11 @@ r_object(RFILE *p)
const char *buffer;

n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (string size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (string size out of range)");
}
break;
}
if (n != 0) {
Expand All @@ -1198,16 +1199,18 @@ r_object(RFILE *p)
}

case TYPE_SMALL_TUPLE:
n = (unsigned char) r_byte(p);
if (PyErr_Occurred())
n = r_byte(p);
if (n == EOF) {
break;
}
goto _read_tuple;
case TYPE_TUPLE:
n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (tuple size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (tuple size out of range)");
}
break;
}
_read_tuple:
Expand All @@ -1232,10 +1235,11 @@ r_object(RFILE *p)

case TYPE_LIST:
n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (list size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (list size out of range)");
}
break;
}
v = PyList_New(n);
Expand Down Expand Up @@ -1288,10 +1292,11 @@ r_object(RFILE *p)
case TYPE_SET:
case TYPE_FROZENSET:
n = r_long(p);
if (PyErr_Occurred())
break;
if (n < 0 || n > SIZE32_MAX) {
PyErr_SetString(PyExc_ValueError, "bad marshal data (set size out of range)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (set size out of range)");
}
break;
}

Expand Down Expand Up @@ -1368,20 +1373,20 @@ r_object(RFILE *p)

/* XXX ignore long->int overflows for now */
argcount = (int)r_long(p);
if (PyErr_Occurred())
if (argcount == -1 && PyErr_Occurred())
goto code_error;
posonlyargcount = (int)r_long(p);
if (PyErr_Occurred()) {
if (posonlyargcount == -1 && PyErr_Occurred()) {
goto code_error;
}
kwonlyargcount = (int)r_long(p);
if (PyErr_Occurred())
if (kwonlyargcount == -1 && PyErr_Occurred())
goto code_error;
stacksize = (int)r_long(p);
if (PyErr_Occurred())
if (stacksize == -1 && PyErr_Occurred())
goto code_error;
flags = (int)r_long(p);
if (PyErr_Occurred())
if (flags == -1 && PyErr_Occurred())
goto code_error;
code = r_object(p);
if (code == NULL)
Expand Down Expand Up @@ -1454,6 +1459,10 @@ r_object(RFILE *p)
v = r_ref_insert(v, idx, flag, p);

code_error:
if (v == NULL && !PyErr_Occurred()) {
PyErr_SetString(PyExc_TypeError,
"NULL object in marshal data for code object");
}
Py_XDECREF(code);
Py_XDECREF(consts);
Py_XDECREF(names);
Expand All @@ -1471,9 +1480,10 @@ r_object(RFILE *p)
case TYPE_REF:
n = r_long(p);
if (n < 0 || n >= PyList_GET_SIZE(p->refs)) {
if (n == -1 && PyErr_Occurred())
break;
PyErr_SetString(PyExc_ValueError, "bad marshal data (invalid reference)");
if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ValueError,
"bad marshal data (invalid reference)");
}
break;
}
v = PyList_GET_ITEM(p->refs, n);
Expand Down