bpo-40521: Per-interpreter interned strings (GH-20085)

Make the Unicode dictionary of interned strings compatible with
subinterpreters.

Remove the INTERN_NAME_STRINGS macro in typeobject.c: names are
always now interned (even if EXPERIMENTAL_ISOLATED_SUBINTERPRETERS
macro is defined).

_PyUnicode_ClearInterned() now uses PyDict_Next() to no longer
allocate memory, to ensure that the interned dictionary is cleared.

1 files changed, 11 insertions, 0 deletions

diff --git a/Include/internal/pycore_interp.h b/Include/internal/pycore_interp.h
index 339c2c4c61..58b1126712 100644
--- a/Include/internal/pycore_interp.h
+++ b/Include/internal/pycore_interp.h
@@ -76,6 +76,17 @@ struct _Py_unicode_state {
        shared as well. */
     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;
 };