mirror of
https://github.com/python/cpython.git
synced 2025-08-19 00:00:48 +00:00
[3.12] gh-113993: Make interned strings mortal (GH-120520, GH-121364, GH-121903, GH-122303) (#123065)
This backports several PRs for gh-113993, making interned strings mortal so they can be garbage-collected when no longer needed. * 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. * Beef up the tests. Cover internal details (marked with `@cpython_only`). * Add lots of assertions * Don't immortalize in PyUnicode_InternInPlace; keep immortalizing in other API (GH-121364) * Switch PyUnicode_InternInPlace to _PyUnicode_InternMortal, clarify docs * Document immortality in some functions that take `const char *` This is PyUnicode_InternFromString; PyDict_SetItemString, PyObject_SetAttrString; PyObject_DelAttrString; PyUnicode_InternFromString; and the PyModule_Add convenience functions. Always point out a non-immortalizing alternative. * Don't immortalize user-provided attr names in _ctypes * Immortalize names in code objects to avoid crash (GH-121903) * Intern latin-1 one-byte strings at startup (GH-122303) There are some 3.12-specific changes, mainly to allow statically allocated strings in deepfreeze. (In 3.13, deepfreeze switched to the general `_Py_ID`/`_Py_STR`.) Co-authored-by: Eric Snow <ericsnowcurrently@gmail.com>
This commit is contained in:
parent
2fa9ca5070
commit
49f6beb56a
51 changed files with 26040 additions and 27615 deletions
|
@ -2,6 +2,9 @@
|
|||
#include "pycore_moduleobject.h" // _PyModule_GetState()
|
||||
#include "structmember.h" // PyMemberDef
|
||||
#include "pycore_runtime.h" // _Py_ID()
|
||||
#include "pycore_pystate.h" // _PyInterpreterState_GET()
|
||||
|
||||
|
||||
#include "clinic/_operator.c.h"
|
||||
|
||||
typedef struct {
|
||||
|
@ -1224,6 +1227,7 @@ 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;
|
||||
|
@ -1251,7 +1255,7 @@ 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);
|
||||
|
@ -1277,7 +1281,7 @@ 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;
|
||||
|
@ -1291,7 +1295,7 @@ 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);
|
||||
|
@ -1587,7 +1591,8 @@ methodcaller_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
|
|||
|
||||
name = PyTuple_GET_ITEM(args, 0);
|
||||
Py_INCREF(name);
|
||||
PyUnicode_InternInPlace(&name);
|
||||
PyInterpreterState *interp = _PyInterpreterState_GET();
|
||||
_PyUnicode_InternMortal(interp, &name);
|
||||
mc->name = name;
|
||||
|
||||
mc->kwds = Py_XNewRef(kwds);
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue