Un-revert "bpo-40521: Per-interpreter interned strings (pythonGH-20085)".

This reverts commit 35d6540.

Author: ericsnowcurrently

Include/internal/pycore_unicodeobject.h

@@ -50,11 +50,21 @@ struct _Py_unicode_state {
     PyObject *latin1[256];
     struct _Py_unicode_fs_codec fs_codec;
 
+    /* This dictionary holds all interned unicode strings.  Note that references
+       to strings in this dictionary are *not* counted in the string's ob_refcnt.
+       When the interned string reaches a refcnt of 0 the string deallocation
+       function will delete the reference from this dictionary.
+
+       Another way to look at this is that to say that the actual reference
+       count of a string is:  s->ob_refcnt + (s->state ? 2 : 0)
+    */
+    PyObject *interned;
+
     // Unicode identifiers (_Py_Identifier): see _PyUnicode_FromId()
     struct _Py_unicode_ids ids;
 };
 
-extern void _PyUnicode_ClearInterned(PyInterpreterState *interp);
+extern void _PyUnicode_ClearInterned(PyInterpreterState *);
 
 
 #ifdef __cplusplus

Misc/NEWS.d/next/Core and Builtins/2022-01-05-17-13-47.bpo-46006.hdH5Vn.rst

@@ -54,11 +54,6 @@ typedef struct PySlot_Offset {
 } PySlot_Offset;
 
 
-/* bpo-40521: Interned strings are shared by all subinterpreters */
-#ifndef EXPERIMENTAL_ISOLATED_SUBINTERPRETERS
-#  define INTERN_NAME_STRINGS
-#endif
-
 /* alphabetical order */
 _Py_IDENTIFIER(__abstractmethods__);
 _Py_IDENTIFIER(__annotations__);
@@ -4033,7 +4028,6 @@ type_setattro(PyTypeObject *type, PyObject *name, PyObject *value)
             if (name == NULL)
                 return -1;
         }
-#ifdef INTERN_NAME_STRINGS
         if (!PyUnicode_CHECK_INTERNED(name)) {
             PyUnicode_InternInPlace(&name);
             if (!PyUnicode_CHECK_INTERNED(name)) {
@@ -4043,7 +4037,6 @@ type_setattro(PyTypeObject *type, PyObject *name, PyObject *value)
                 return -1;
             }
         }
-#endif
     }
     else {
         /* Will fail in _PyObject_GenericSetAttrWithDict. */
@@ -8431,17 +8424,10 @@ _PyTypes_InitSlotDefs(void)
     for (slotdef *p = slotdefs; p->name; p++) {
         /* Slots must be ordered by their offset in the PyHeapTypeObject. */
         assert(!p[1].name || p->offset <= p[1].offset);
-#ifdef INTERN_NAME_STRINGS
         p->name_strobj = PyUnicode_InternFromString(p->name);
         if (!p->name_strobj || !PyUnicode_CHECK_INTERNED(p->name_strobj)) {
             return _PyStatus_NO_MEMORY();
         }
-#else
-        p->name_strobj = PyUnicode_FromString(p->name);
-        if (!p->name_strobj) {
-            return _PyStatus_NO_MEMORY();
-        }
-#endif
     }
     slotdefs_initialized = 1;
     return _PyStatus_OK();
@@ -8466,24 +8452,16 @@ update_slot(PyTypeObject *type, PyObject *name)
     int offset;
 
     assert(PyUnicode_CheckExact(name));
-#ifdef INTERN_NAME_STRINGS
     assert(PyUnicode_CHECK_INTERNED(name));
-#endif
 
     assert(slotdefs_initialized);
     pp = ptrs;
     for (p = slotdefs; p->name; p++) {
         assert(PyUnicode_CheckExact(p->name_strobj));
         assert(PyUnicode_CheckExact(name));
-#ifdef INTERN_NAME_STRINGS
         if (p->name_strobj == name) {
             *pp++ = p;
         }
-#else
-        if (p->name_strobj == name || _PyUnicode_EQ(p->name_strobj, name)) {
-            *pp++ = p;
-        }
-#endif
     }
     *pp = NULL;
     for (pp = ptrs; *pp; pp++) {

Objects/typeobject.c

@@ -214,22 +214,6 @@ extern "C" {
 #  define OVERALLOCATE_FACTOR 4
 #endif
 
-/* bpo-40521: Interned strings are shared by all interpreters. */
-#ifndef EXPERIMENTAL_ISOLATED_SUBINTERPRETERS
-#  define INTERNED_STRINGS
-#endif
-
-/* This dictionary holds all interned unicode strings.  Note that references
-   to strings in this dictionary are *not* counted in the string's ob_refcnt.
-   When the interned string reaches a refcnt of 0 the string deallocation
-   function will delete the reference from this dictionary.
-
-   Another way to look at this is that to say that the actual reference
-   count of a string is:  s->ob_refcnt + (s->state ? 2 : 0)
-*/
-#ifdef INTERNED_STRINGS
-static PyObject *interned = NULL;
-#endif
 
 /* Forward declaration */
 static inline int
@@ -1966,21 +1950,20 @@ unicode_dealloc(PyObject *unicode)
 
     case SSTATE_INTERNED_MORTAL:
     {
-#ifdef INTERNED_STRINGS
+        struct _Py_unicode_state *state = get_unicode_state();
         /* Revive the dead object temporarily. PyDict_DelItem() removes two
            references (key and value) which were ignored by
            PyUnicode_InternInPlace(). Use refcnt=3 rather than refcnt=2
            to prevent calling unicode_dealloc() again. Adjust refcnt after
            PyDict_DelItem(). */
         assert(Py_REFCNT(unicode) == 0);
         Py_SET_REFCNT(unicode, 3);
-        if (PyDict_DelItem(interned, unicode) != 0) {
+        if (PyDict_DelItem(state->interned, unicode) != 0) {
             _PyErr_WriteUnraisableMsg("deletion of interned string failed",
                                       NULL);
         }
         assert(Py_REFCNT(unicode) == 1);
         Py_SET_REFCNT(unicode, 0);
-#endif
         break;
     }
 
@@ -11359,13 +11342,11 @@ _PyUnicode_EqualToASCIIId(PyObject *left, _Py_Identifier *right)
     if (PyUnicode_CHECK_INTERNED(left))
         return 0;
 
-#ifdef INTERNED_STRINGS
     assert(_PyUnicode_HASH(right_uni) != -1);
     Py_hash_t hash = _PyUnicode_HASH(left);
     if (hash != -1 && hash != _PyUnicode_HASH(right_uni)) {
         return 0;
     }
-#endif
 
     return unicode_compare_eq(left, right_uni);
 }
@@ -15610,21 +15591,21 @@ PyUnicode_InternInPlace(PyObject **p)
         return;
     }
 
-#ifdef INTERNED_STRINGS
     if (PyUnicode_READY(s) == -1) {
         PyErr_Clear();
         return;
     }
 
-    if (interned == NULL) {
-        interned = PyDict_New();
-        if (interned == NULL) {
+    struct _Py_unicode_state *state = get_unicode_state();
+    if (state->interned == NULL) {
+        state->interned = PyDict_New();
+        if (state->interned == NULL) {
             PyErr_Clear(); /* Don't leave an exception */
             return;
         }
     }
 
-    PyObject *t = PyDict_SetDefault(interned, s, s);
+    PyObject *t = PyDict_SetDefault(state->interned, s, s);
     if (t == NULL) {
         PyErr_Clear();
         return;
@@ -15641,13 +15622,9 @@ PyUnicode_InternInPlace(PyObject **p)
        this. */
     Py_SET_REFCNT(s, Py_REFCNT(s) - 2);
     _PyUnicode_STATE(s).interned = SSTATE_INTERNED_MORTAL;
-#else
-    // PyDict expects that interned strings have their hash
-    // (PyASCIIObject.hash) already computed.
-    (void)unicode_hash(s);
-#endif
 }
 
+
 void
 PyUnicode_InternImmortal(PyObject **p)
 {
@@ -15681,29 +15658,25 @@ PyUnicode_InternFromString(const char *cp)
 void
 _PyUnicode_ClearInterned(PyInterpreterState *interp)
 {
-    if (!_Py_IsMainInterpreter(interp)) {
-        // interned dict is shared by all interpreters
-        return;
-    }
-
-    if (interned == NULL) {
+    struct _Py_unicode_state *state = &interp->unicode;
+    if (state->interned == NULL) {
         return;
     }
-    assert(PyDict_CheckExact(interned));
+    assert(PyDict_CheckExact(state->interned));
 
     /* Interned unicode strings are not forcibly deallocated; rather, we give
        them their stolen references back, and then clear and DECREF the
        interned dict. */
 
 #ifdef INTERNED_STATS
     fprintf(stderr, "releasing %zd interned strings\n",
-            PyDict_GET_SIZE(interned));
+            PyDict_GET_SIZE(state->interned));
 
     Py_ssize_t immortal_size = 0, mortal_size = 0;
 #endif
     Py_ssize_t pos = 0;
     PyObject *s, *ignored_value;
-    while (PyDict_Next(interned, &pos, &s, &ignored_value)) {
+    while (PyDict_Next(state->interned, &pos, &s, &ignored_value)) {
         assert(PyUnicode_IS_READY(s));
 
         switch (PyUnicode_CHECK_INTERNED(s)) {
@@ -15734,8 +15707,8 @@ _PyUnicode_ClearInterned(PyInterpreterState *interp)
             mortal_size, immortal_size);
 #endif
 
-    PyDict_Clear(interned);
-    Py_CLEAR(interned);
+    PyDict_Clear(state->interned);
+    Py_CLEAR(state->interned);
 }
 
 
@@ -16106,7 +16079,8 @@ _PyUnicode_EnableLegacyWindowsFSEncoding(void)
 static inline int
 unicode_is_finalizing(void)
 {
-    return (interned == NULL);
+    struct _Py_unicode_state *state = get_unicode_state();
+    return (state->interned == NULL);
 }
 #endif
 
@@ -16116,10 +16090,8 @@ _PyUnicode_Fini(PyInterpreterState *interp)
 {
     struct _Py_unicode_state *state = &interp->unicode;
 
-    if (_Py_IsMainInterpreter(interp)) {
-        // _PyUnicode_ClearInterned() must be called before _PyUnicode_Fini()
-        assert(interned == NULL);
-    }
+    // _PyUnicode_ClearInterned() must be called before
+    assert(state->interned == NULL);
 
     _PyUnicode_FiniEncodings(&state->fs_codec);