[3.13] gh-113993: Allow interned strings to be mortal, and fix related issues (GH-120520) (GH-120945)

* 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>
This commit is contained in:
Petr Viktorin 2024-06-24 20:24:19 +02:00 committed by GitHub
parent 447e07ab3d
commit 9769b7ae06
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
42 changed files with 2460 additions and 1140 deletions

View file

@ -968,24 +968,64 @@ exit:
}
PyDoc_STRVAR(sys_getunicodeinternedsize__doc__,
"getunicodeinternedsize($module, /)\n"
"getunicodeinternedsize($module, /, *, _only_immortal=False)\n"
"--\n"
"\n"
"Return the number of elements of the unicode interned dictionary");
#define SYS_GETUNICODEINTERNEDSIZE_METHODDEF \
{"getunicodeinternedsize", (PyCFunction)sys_getunicodeinternedsize, METH_NOARGS, sys_getunicodeinternedsize__doc__},
{"getunicodeinternedsize", _PyCFunction_CAST(sys_getunicodeinternedsize), METH_FASTCALL|METH_KEYWORDS, sys_getunicodeinternedsize__doc__},
static Py_ssize_t
sys_getunicodeinternedsize_impl(PyObject *module);
sys_getunicodeinternedsize_impl(PyObject *module, int _only_immortal);
static PyObject *
sys_getunicodeinternedsize(PyObject *module, PyObject *Py_UNUSED(ignored))
sys_getunicodeinternedsize(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
{
PyObject *return_value = NULL;
#if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
#define NUM_KEYWORDS 1
static struct {
PyGC_Head _this_is_not_used;
PyObject_VAR_HEAD
PyObject *ob_item[NUM_KEYWORDS];
} _kwtuple = {
.ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
.ob_item = { &_Py_ID(_only_immortal), },
};
#undef NUM_KEYWORDS
#define KWTUPLE (&_kwtuple.ob_base.ob_base)
#else // !Py_BUILD_CORE
# define KWTUPLE NULL
#endif // !Py_BUILD_CORE
static const char * const _keywords[] = {"_only_immortal", NULL};
static _PyArg_Parser _parser = {
.keywords = _keywords,
.fname = "getunicodeinternedsize",
.kwtuple = KWTUPLE,
};
#undef KWTUPLE
PyObject *argsbuf[1];
Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0;
int _only_immortal = 0;
Py_ssize_t _return_value;
_return_value = sys_getunicodeinternedsize_impl(module);
args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 0, 0, argsbuf);
if (!args) {
goto exit;
}
if (!noptargs) {
goto skip_optional_kwonly;
}
_only_immortal = PyObject_IsTrue(args[0]);
if (_only_immortal < 0) {
goto exit;
}
skip_optional_kwonly:
_return_value = sys_getunicodeinternedsize_impl(module, _only_immortal);
if ((_return_value == -1) && PyErr_Occurred()) {
goto exit;
}
@ -1574,4 +1614,4 @@ exit:
#ifndef SYS_GETANDROIDAPILEVEL_METHODDEF
#define SYS_GETANDROIDAPILEVEL_METHODDEF
#endif /* !defined(SYS_GETANDROIDAPILEVEL_METHODDEF) */
/*[clinic end generated code: output=ef7c35945443d300 input=a9049054013a1b77]*/
/*[clinic end generated code: output=9cc9069aef1482bc input=a9049054013a1b77]*/