[3.12] gh-113993: For string interning, do not rely on (or assert) _Py_IsImmortal (GH-121358) (GH-124938)

gh-113993: For string interning, do not rely on (or assert) _Py_IsImmortal (GH-121358)

Older stable ABI extensions are allowed to make immortal objects mortal.
Instead, use `_PyUnicode_STATE` (`interned` and `statically_allocated`).
(cherry picked from commit 956270d08d)

Co-authored-by: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>
This commit is contained in:
Petr Viktorin 2024-10-04 16:50:34 +02:00 committed by GitHub
parent 58f7763b88
commit b3e2c02915
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 12 additions and 6 deletions

View file

@ -257,7 +257,8 @@ _PyUnicode_InternedSize_Immortal(void)
// value, to help detect bugs in optimizations.
while (PyDict_Next(dict, &pos, &key, &value)) {
if (_Py_IsImmortal(key)) {
assert(PyUnicode_CHECK_INTERNED(key) != SSTATE_INTERNED_IMMORTAL_STATIC);
if (PyUnicode_CHECK_INTERNED(key) == SSTATE_INTERNED_IMMORTAL) {
count++;
}
}
@ -691,10 +692,14 @@ _PyUnicode_CheckConsistency(PyObject *op, int check_content)
/* Check interning state */
#ifdef Py_DEBUG
// Note that we do not check `_Py_IsImmortal(op)`, since stable ABI
// extensions can make immortal strings mortal (but with a high enough
// refcount).
// The other way is extremely unlikely (worth a potential failed assertion
// in a debug build), so we do check `!_Py_IsImmortal(op)`.
switch (PyUnicode_CHECK_INTERNED(op)) {
case SSTATE_NOT_INTERNED:
if (ascii->state.statically_allocated) {
CHECK(_Py_IsImmortal(op));
// This state is for two exceptions:
// - strings are currently checked before they're interned
// - the 256 one-latin1-character strings
@ -710,11 +715,9 @@ _PyUnicode_CheckConsistency(PyObject *op, int check_content)
break;
case SSTATE_INTERNED_IMMORTAL:
CHECK(!ascii->state.statically_allocated);
CHECK(_Py_IsImmortal(op));
break;
case SSTATE_INTERNED_IMMORTAL_STATIC:
CHECK(ascii->state.statically_allocated);
CHECK(_Py_IsImmortal(op));
break;
default:
Py_UNREACHABLE();
@ -1899,7 +1902,8 @@ unicode_write_cstr(PyObject *unicode, Py_ssize_t index,
static PyObject*
get_latin1_char(Py_UCS1 ch)
{
return Py_NewRef(LATIN1(ch));
PyObject *o = LATIN1(ch);
return o;
}
static PyObject*
@ -15015,7 +15019,7 @@ intern_common(PyInterpreterState *interp, PyObject *s /* stolen */,
{
PyObject *r = (PyObject *)_Py_hashtable_get(INTERNED_STRINGS, s);
if (r != NULL) {
assert(_Py_IsImmortal(r));
assert(_PyUnicode_STATE(r).statically_allocated);
assert(r != s); // r must be statically_allocated; s is not
Py_DECREF(s);
return Py_NewRef(r);