gh-113993: Allow interned strings to be mortal, and fix related issues (GH-120520)

* Add an InternalDocs file describing how interning should work and how to use it.

* Add internal functions to *explicitly* request what kind of interning is done:
  - `_PyUnicode_InternMortal`
  - `_PyUnicode_InternImmortal`
  - `_PyUnicode_InternStatic`

* Switch uses of `PyUnicode_InternInPlace` to those.

* Disallow using `_Py_SetImmortal` on strings directly.
  You should use `_PyUnicode_InternImmortal` instead:
  - Strings should be interned before immortalization, otherwise you're possibly
    interning a immortalizing copy.
  - `_Py_SetImmortal` doesn't handle the `SSTATE_INTERNED_MORTAL` to
    `SSTATE_INTERNED_IMMORTAL` update, and those flags can't be changed in
    backports, as they are now part of public API and version-specific ABI.

* Add private `_only_immortal` argument for `sys.getunicodeinternedsize`, used in refleak test machinery.

* Make sure the statically allocated string singletons are unique. This means these sets are now disjoint:
  - `_Py_ID`
  - `_Py_STR` (including the empty string)
  - one-character latin-1 singletons

  Now, when you intern a singleton, that exact singleton will be interned.

* Add a `_Py_LATIN1_CHR` macro, use it instead of `_Py_ID`/`_Py_STR` for one-character latin-1 singletons everywhere (including Clinic).

* Intern `_Py_STR` singletons at startup.

* For free-threaded builds, intern `_Py_LATIN1_CHR` singletons at startup.

* Beef up the tests. Cover internal details (marked with `@cpython_only`).

* Add lots of assertions

Co-Authored-By: Eric Snow <ericsnowcurrently@gmail.com>

1 files changed, 7 insertions, 4 deletions

diff --git a/Modules/_operator.c b/Modules/_operator.c
index 5d3f883..793a2d0 100644
--- a/Modules/_operator.c
+++ b/Modules/_operator.c
@@ -2,6 +2,7 @@
 #include "pycore_modsupport.h"    // _PyArg_NoKwnames()
 #include "pycore_moduleobject.h"  // _PyModule_GetState()
 #include "pycore_runtime.h"       // _Py_ID()
+#include "pycore_pystate.h"       // _PyInterpreterState_GET()
 
 
 #include "clinic/_operator.c.h"
@@ -1236,6 +1237,7 @@ attrgetter_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
         return NULL;
 
     /* prepare attr while checking args */
+    PyInterpreterState *interp = _PyInterpreterState_GET();
     for (idx = 0; idx < nattrs; ++idx) {
         PyObject *item = PyTuple_GET_ITEM(args, idx);
         int dot_count;
@@ -1259,7 +1261,7 @@ attrgetter_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
 
         if (dot_count == 0) {
             Py_INCREF(item);
-            PyUnicode_InternInPlace(&item);
+            _PyUnicode_InternMortal(interp, &item);
             PyTuple_SET_ITEM(attr, idx, item);
         } else { /* make it a tuple of non-dotted attrnames */
             PyObject *attr_chain = PyTuple_New(dot_count + 1);
@@ -1285,7 +1287,7 @@ attrgetter_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
                     Py_DECREF(attr);
                     return NULL;
                 }
-                PyUnicode_InternInPlace(&attr_chain_item);
+                _PyUnicode_InternMortal(interp, &attr_chain_item);
                 PyTuple_SET_ITEM(attr_chain, attr_chain_idx, attr_chain_item);
                 ++attr_chain_idx;
                 unibuff_till = unibuff_from = unibuff_till + 1;
@@ -1299,7 +1301,7 @@ attrgetter_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
                 Py_DECREF(attr);
                 return NULL;
             }
-            PyUnicode_InternInPlace(&attr_chain_item);
+            _PyUnicode_InternMortal(interp, &attr_chain_item);
             PyTuple_SET_ITEM(attr_chain, attr_chain_idx, attr_chain_item);
 
             PyTuple_SET_ITEM(attr, idx, attr_chain);
@@ -1662,7 +1664,8 @@ methodcaller_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
     }
 
     Py_INCREF(name);
-    PyUnicode_InternInPlace(&name);
+    PyInterpreterState *interp = _PyInterpreterState_GET();
+    _PyUnicode_InternMortal(interp, &name);
     mc->name = name;
 
     mc->xargs = Py_XNewRef(args); // allows us to use borrowed references