Skip to content

bpo-1635741: Enable unicode_release_interned() without insure or valgrind. #21087

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 9 commits into from
Closed

bpo-1635741: Enable unicode_release_interned() without insure or valgrind. #21087

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
ed3cd98
Enable unicode_release_interned() without insure or valgrind.
shihai1991 Jun 23, 2020
3c8db50
resolve use after free
shihai1991 Jun 23, 2020
03f650d
Merge branch 'master' into bpo_1635741_interned_unicode
shihai1991 Jun 23, 2020
b2e578d
resolve confilicts
shihai1991 Jun 24, 2020
4618783
Use PyDict_Next() in unicode_release_interned()
shihai1991 Jun 25, 2020
8b47de1
resolve conflicts
shihai1991 Jun 25, 2020
33272ac
Merge remote-tracking branch 'origin/master' into bpo_1635741_interne…
shihai1991 Jun 25, 2020
ec1671b
update vars' name
shihai1991 Jun 25, 2020
b0da3bd
_PyUnicode_Fini() before _PyDict_Fini()
shihai1991 Jul 1, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 17 additions & 36 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15657,52 +15657,46 @@ PyUnicode_InternFromString(const char *cp)
}


#if defined(WITH_VALGRIND) || defined(__INSURE__)
static void
unicode_release_interned(void)
{
Py_ssize_t pos = 0;
PyObject *s, *ignored_value;

if (interned == NULL || !PyDict_Check(interned)) {
return;
}
PyObject *keys = PyDict_Keys(interned);
if (keys == NULL || !PyList_Check(keys)) {
PyErr_Clear();
return;
}

/* Since unicode_release_interned() is intended to help a leak
detector, interned unicode strings are not forcibly deallocated;
rather, we give them their stolen references back, and then clear
and DECREF the interned dict. */

Py_ssize_t n = PyList_GET_SIZE(keys);
#ifdef INTERNED_STATS
fprintf(stderr, "releasing %zd interned strings\n", n);
fprintf(stderr, "releasing %zd interned strings\n", PyDict_Size(interned));

Py_ssize_t immortal_size = 0, mortal_size = 0;
#endif
for (Py_ssize_t i = 0; i < n; i++) {
PyObject *s = PyList_GET_ITEM(keys, i);
while (PyDict_Next(interned, &pos, &s, &ignored_value)) {
if (PyUnicode_READY(s) == -1) {
Py_UNREACHABLE();
}
switch (PyUnicode_CHECK_INTERNED(s)) {
case SSTATE_INTERNED_IMMORTAL:
Py_SET_REFCNT(s, Py_REFCNT(s) + 1);
case SSTATE_INTERNED_IMMORTAL:
Py_SET_REFCNT(s, Py_REFCNT(s) + 1);
#ifdef INTERNED_STATS
immortal_size += PyUnicode_GET_LENGTH(s);
immortal_size += PyUnicode_GET_LENGTH(s);
#endif
break;
case SSTATE_INTERNED_MORTAL:
Py_SET_REFCNT(s, Py_REFCNT(s) + 2);
break;
case SSTATE_INTERNED_MORTAL:
Py_SET_REFCNT(s, Py_REFCNT(s) + 2);
#ifdef INTERNED_STATS
mortal_size += PyUnicode_GET_LENGTH(s);
mortal_size += PyUnicode_GET_LENGTH(s);
#endif
break;
case SSTATE_NOT_INTERNED:
/* fall through */
default:
Py_UNREACHABLE();
break;
case SSTATE_NOT_INTERNED:
/* fall through */
default:
Py_UNREACHABLE();
}
_PyUnicode_STATE(s).interned = SSTATE_NOT_INTERNED;
}
Expand All @@ -15711,11 +15705,9 @@ unicode_release_interned(void)
"total size of all interned strings: %zd/%zd mortal/immortal\n",
mortal_size, immortal_size);
#endif
Py_DECREF(keys);
PyDict_Clear(interned);
Py_CLEAR(interned);
}
#endif


/********************* Unicode Iterator **************************/
Expand Down Expand Up @@ -16209,18 +16201,7 @@ _PyUnicode_Fini(PyThreadState *tstate)

int is_main_interp = _Py_IsMainInterpreter(tstate);
if (is_main_interp) {
#if defined(WITH_VALGRIND) || defined(__INSURE__)
/* Insure++ is a memory analysis tool that aids in discovering
* memory leaks and other memory problems. On Python exit, the
* interned string dictionaries are flagged as being in use at exit
* (which it is). Under normal circumstances, this is fine because
* the memory will be automatically reclaimed by the system. Under
* memory debugging, it's a huge source of useless noise, so we
* trade off slower shutdown for less distraction in the memory
* reports. -baw
*/
unicode_release_interned();
#endif /* __INSURE__ */
}

Py_CLEAR(state->empty);
Expand Down
4 changes: 2 additions & 2 deletions Python/pylifecycle.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1259,14 +1259,14 @@ finalize_interp_types(PyThreadState *tstate, int is_main_interp)
_PyAsyncGen_Fini(tstate);
_PyContext_Fini(tstate);

_PyDict_Fini(tstate);
_PyList_Fini(tstate);
_PyUnicode_Fini(tstate);
_PyDict_Fini(tstate);
_PyTuple_Fini(tstate);

_PySlice_Fini(tstate);

_PyBytes_Fini(tstate);
_PyUnicode_Fini(tstate);
_PyFloat_Fini(tstate);
_PyLong_Fini(tstate);
}
Expand Down