gh-128137: Split out interned field from state

Author: corona10

Include/cpython/unicodeobject.h

@@ -99,17 +99,17 @@ typedef struct {
     PyObject_HEAD
     Py_ssize_t length;          /* Number of code points in the string */
     Py_hash_t hash;             /* Hash value; -1 if not set */
+    /* If interned is non-zero, the two references from the
+    dictionary to this object are *not* counted in ob_refcnt.
+    The possible values here are:
+        0: Not Interned
+        1: Interned
+        2: Interned and Immortal
+        3: Interned, Immortal, and Static
+    This categorization allows the runtime to determine the right
+    cleanup mechanism at runtime shutdown. */
+    uint16_t interned;
     struct {
-        /* If interned is non-zero, the two references from the
-           dictionary to this object are *not* counted in ob_refcnt.
-           The possible values here are:
-               0: Not Interned
-               1: Interned
-               2: Interned and Immortal
-               3: Interned, Immortal, and Static
-           This categorization allows the runtime to determine the right
-           cleanup mechanism at runtime shutdown. */
-        unsigned int interned:2;
         /* Character size:
 
            - PyUnicode_1BYTE_KIND (1):
@@ -132,21 +132,21 @@ typedef struct {
              * all characters are in the range U+0000-U+10FFFF
              * at least one character is in the range U+10000-U+10FFFF
          */
-        unsigned int kind:3;
+        uint16_t kind:3;
         /* Compact is with respect to the allocation scheme. Compact unicode
            objects only require one memory block while non-compact objects use
            one block for the PyUnicodeObject struct and another for its data
            buffer. */
-        unsigned int compact:1;
+        uint16_t compact:1;
         /* The string only contains characters in the range U+0000-U+007F (ASCII)
            and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
            set, use the PyASCIIObject structure. */
-        unsigned int ascii:1;
+        uint16_t ascii:1;
         /* The object is statically allocated. */
-        unsigned int statically_allocated:1;
+        uint16_t statically_allocated:1;
         /* Padding to ensure that PyUnicode_DATA() is always aligned to
            4 bytes (see issue #19537 on m68k). */
-        unsigned int :24;
+        uint16_t :10;
     } state;
 } PyASCIIObject;
 
@@ -195,7 +195,11 @@ typedef struct {
 
 /* Use only if you know it's a string */
 static inline unsigned int PyUnicode_CHECK_INTERNED(PyObject *op) {
-    return _PyASCIIObject_CAST(op)->state.interned;
+#ifdef Py_GIL_DISABLED
+    return _Py_atomic_load_uint16_relaxed(&(_PyASCIIObject_CAST(op)->interned));
+#else
+    return _PyASCIIObject_CAST(op)->interned;
+#endif
 }
 #define PyUnicode_CHECK_INTERNED(op) PyUnicode_CHECK_INTERNED(_PyObject_CAST(op))
 

Objects/unicodeobject.c

@@ -1409,7 +1409,7 @@ PyUnicode_New(Py_ssize_t size, Py_UCS4 maxchar)
         data = unicode + 1;
     _PyUnicode_LENGTH(unicode) = size;
     _PyUnicode_HASH(unicode) = -1;
-    _PyUnicode_STATE(unicode).interned = 0;
+    _PyASCIIObject_CAST(unicode)->interned = 0;
     _PyUnicode_STATE(unicode).kind = kind;
     _PyUnicode_STATE(unicode).compact = 1;
     _PyUnicode_STATE(unicode).ascii = is_ascii;
@@ -1711,7 +1711,7 @@ unicode_dealloc(PyObject *unicode)
         _Py_SetImmortal(unicode);
         return;
     }
-    switch (_PyUnicode_STATE(unicode).interned) {
+    switch (_PyASCIIObject_CAST(unicode)->interned) {
         case SSTATE_NOT_INTERNED:
             break;
         case SSTATE_INTERNED_MORTAL:
@@ -1739,7 +1739,7 @@ unicode_dealloc(PyObject *unicode)
                 //   so it can't cause trouble (except wasted memory)
                 // - if it wasn't popped, it'll remain interned
                 _Py_SetImmortal(unicode);
-                _PyUnicode_STATE(unicode).interned = SSTATE_INTERNED_IMMORTAL;
+                _PyASCIIObject_CAST(unicode)->interned = SSTATE_INTERNED_IMMORTAL;
                 return;
             }
             if (r == 0) {
@@ -15470,7 +15470,7 @@ unicode_subtype_new(PyTypeObject *type, PyObject *unicode)
 #else
     _PyUnicode_HASH(self) = _PyUnicode_HASH(unicode);
 #endif
-    _PyUnicode_STATE(self).interned = 0;
+    _PyASCIIObject_CAST(self)->interned = 0;
     _PyUnicode_STATE(self).kind = kind;
     _PyUnicode_STATE(self).compact = 0;
     _PyUnicode_STATE(self).ascii = _PyUnicode_STATE(unicode).ascii;
@@ -15689,7 +15689,7 @@ intern_static(PyInterpreterState *interp, PyObject *s /* stolen */)
     assert(r == NULL);
     /* but just in case (for the non-debug build), handle this */
     if (r != NULL && r != s) {
-        assert(_PyUnicode_STATE(r).interned == SSTATE_INTERNED_IMMORTAL_STATIC);
+        assert(_PyASCIIObject_CAST(r)->interned == SSTATE_INTERNED_IMMORTAL_STATIC);
         assert(_PyUnicode_CHECK(r));
         Py_DECREF(s);
         return Py_NewRef(r);
@@ -15699,7 +15699,7 @@ intern_static(PyInterpreterState *interp, PyObject *s /* stolen */)
         Py_FatalError("failed to intern static string");
     }
 
-    _PyUnicode_STATE(s).interned = SSTATE_INTERNED_IMMORTAL_STATIC;
+    _PyASCIIObject_CAST(s)->interned = SSTATE_INTERNED_IMMORTAL_STATIC;
     return s;
 }
 
@@ -15726,7 +15726,7 @@ immortalize_interned(PyObject *s)
         _Py_DecRefTotal(_PyThreadState_GET());
     }
 #endif
-    _PyUnicode_STATE(s).interned = SSTATE_INTERNED_IMMORTAL;
+    FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_IMMORTAL);
     _Py_SetImmortal(s);
 }
 
@@ -15833,7 +15833,7 @@ intern_common(PyInterpreterState *interp, PyObject *s /* stolen */,
 
     /* NOT_INTERNED -> INTERNED_MORTAL */
 
-    assert(_PyUnicode_STATE(s).interned == SSTATE_NOT_INTERNED);
+    assert(_PyASCIIObject_CAST(s)->interned == SSTATE_NOT_INTERNED);
 
     if (!_Py_IsImmortal(s)) {
         /* The two references in interned dict (key and value) are not counted.
@@ -15845,7 +15845,7 @@ intern_common(PyInterpreterState *interp, PyObject *s /* stolen */,
         _Py_DecRefTotal(_PyThreadState_GET());
 #endif
     }
-    _PyUnicode_STATE(s).interned = SSTATE_INTERNED_MORTAL;
+    FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_MORTAL);
 
     /* INTERNED_MORTAL -> INTERNED_IMMORTAL (if needed) */
 
@@ -15981,7 +15981,7 @@ _PyUnicode_ClearInterned(PyInterpreterState *interp)
             Py_UNREACHABLE();
         }
         if (!shared) {
-            _PyUnicode_STATE(s).interned = SSTATE_NOT_INTERNED;
+            FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_NOT_INTERNED);
         }
     }
 #ifdef INTERNED_STATS