From 448db2155fc81d2aa84f37dc58683251cba8772e Mon Sep 17 00:00:00 2001 From: Thomas Wouters Date: Wed, 16 Sep 2009 20:06:36 +0000 Subject: Merged revisions 74841 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r74841 | thomas.wouters | 2009-09-16 12:55:54 -0700 (Wed, 16 Sep 2009) | 23 lines Fix issue #1590864, multiple threads and fork() can cause deadlocks, by acquiring the import lock around fork() calls. This prevents other threads from having that lock while the fork happens, and is the recommended way of dealing with such issues. There are two other locks we care about, the GIL and the Thread Local Storage lock. The GIL is obviously held when calling Python functions like os.fork(), and the TLS lock is explicitly reallocated instead, while also deleting now-orphaned TLS data. This only fixes calls to os.fork(), not extension modules or embedding programs calling C's fork() directly. Solving that requires a new set of API functions, and possibly a rewrite of the Python/thread_*.c mess. Add a warning explaining the problem to the documentation in the mean time. This also changes behaviour a little on AIX. Before, AIX (but only AIX) was getting the import lock reallocated, seemingly to avoid this very same problem. This is not the right approach, because the import lock is a re-entrant one, and reallocating would do the wrong thing when forking while holding the import lock. Will backport to 2.6, minus the tiny AIX behaviour change. ........ --- Doc/c-api/init.rst | 16 ++++++++++++++++ Include/import.h | 8 ++++++++ Lib/test/test_fork1.py | 41 +++++++++++++++++++++++++++++++++++++++++ Modules/posixmodule.c | 34 +++++++++++++++++++++++++++++++--- Python/import.c | 21 ++++++++------------- 5 files changed, 104 insertions(+), 16 deletions(-) diff --git a/Doc/c-api/init.rst b/Doc/c-api/init.rst index 7beb211..ae93a36 100644 --- a/Doc/c-api/init.rst +++ b/Doc/c-api/init.rst @@ -523,6 +523,22 @@ supports the creation of additional interpreters (using :cfunc:`Py_NewInterpreter`), but mixing multiple interpreters and the :cfunc:`PyGILState_\*` API is unsupported. +Another important thing to note about threads is their behaviour in the face +of the C :cfunc:`fork` call. On most systems with :cfunc:`fork`, after a +process forks only the thread that issued the fork will exist. That also +means any locks held by other threads will never be released. Python solves +this for :func:`os.fork` by acquiring the locks it uses internally before +the fork, and releasing them afterwards. In addition, it resets any +:ref:`lock-objects` in the child. When extending or embedding Python, there +is no way to inform Python of additional (non-Python) locks that need to be +acquired before or reset after a fork. OS facilities such as +:cfunc:`posix_atfork` would need to be used to accomplish the same thing. +Additionally, when extending or embedding Python, calling :cfunc:`fork` +directly rather than through :func:`os.fork` (and returning to or calling +into Python) may result in a deadlock by one of Python's internal locks +being held by a thread that is defunct after the fork. +:cfunc:`PyOS_AfterFork` tries to reset the necessary locks, but is not +always able to. .. ctype:: PyInterpreterState diff --git a/Include/import.h b/Include/import.h index 05ad7f0..76aecdd 100644 --- a/Include/import.h +++ b/Include/import.h @@ -27,6 +27,14 @@ PyAPI_FUNC(PyObject *) PyImport_ReloadModule(PyObject *m); PyAPI_FUNC(void) PyImport_Cleanup(void); PyAPI_FUNC(int) PyImport_ImportFrozenModule(char *); +#ifdef WITH_THREAD +PyAPI_FUNC(void) _PyImport_AcquireLock(void); +PyAPI_FUNC(int) _PyImport_ReleaseLock(void); +#else +#define _PyImport_AcquireLock() +#define _PyImport_ReleaseLock() 1 +#endif + PyAPI_FUNC(struct filedescr *) _PyImport_FindModule( const char *, PyObject *, char *, size_t, FILE **, PyObject **); PyAPI_FUNC(int) _PyImport_IsScript(struct filedescr *); diff --git a/Lib/test/test_fork1.py b/Lib/test/test_fork1.py index e64e398..31b4dd8 100644 --- a/Lib/test/test_fork1.py +++ b/Lib/test/test_fork1.py @@ -1,8 +1,14 @@ """This test checks for correct fork() behavior. """ +import errno +import imp import os +import signal +import sys import time +import threading + from test.fork_wait import ForkWait from test.test_support import TestSkipped, run_unittest, reap_children @@ -24,6 +30,41 @@ class ForkTest(ForkWait): self.assertEqual(spid, cpid) self.assertEqual(status, 0, "cause = %d, exit = %d" % (status&0xff, status>>8)) + def test_import_lock_fork(self): + import_started = threading.Event() + fake_module_name = "fake test module" + partial_module = "partial" + complete_module = "complete" + def importer(): + imp.acquire_lock() + sys.modules[fake_module_name] = partial_module + import_started.set() + time.sleep(0.01) # Give the other thread time to try and acquire. + sys.modules[fake_module_name] = complete_module + imp.release_lock() + t = threading.Thread(target=importer) + t.start() + import_started.wait() + pid = os.fork() + try: + if not pid: + m = __import__(fake_module_name) + if m == complete_module: + os._exit(0) + else: + os._exit(1) + else: + t.join() + # Exitcode 1 means the child got a partial module (bad.) No + # exitcode (but a hang, which manifests as 'got pid 0') + # means the child deadlocked (also bad.) + self.wait_impl(pid) + finally: + try: + os.kill(pid, signal.SIGKILL) + except OSError: + pass + def test_main(): run_unittest(ForkTest) reap_children() diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c index 3fd081d..ebdbc8d 100644 --- a/Modules/posixmodule.c +++ b/Modules/posixmodule.c @@ -3630,11 +3630,21 @@ Return 0 to child process and PID of child to parent process."); static PyObject * posix_fork1(PyObject *self, PyObject *noargs) { - pid_t pid = fork1(); + pid_t pid; + int result; + _PyImport_AcquireLock(); + pid = fork1(); + result = _PyImport_ReleaseLock(); if (pid == -1) return posix_error(); if (pid == 0) PyOS_AfterFork(); + if (result < 0) { + /* Don't clobber the OSError if the fork failed. */ + PyErr_SetString(PyExc_RuntimeError, + "not holding the import lock"); + return NULL; + } return PyLong_FromPid(pid); } #endif @@ -3649,11 +3659,21 @@ Return 0 to child process and PID of child to parent process."); static PyObject * posix_fork(PyObject *self, PyObject *noargs) { - pid_t pid = fork(); + pid_t pid; + int result; + _PyImport_AcquireLock(); + pid = fork(); + result = _PyImport_ReleaseLock(); if (pid == -1) return posix_error(); if (pid == 0) PyOS_AfterFork(); + if (result < 0) { + /* Don't clobber the OSError if the fork failed. */ + PyErr_SetString(PyExc_RuntimeError, + "not holding the import lock"); + return NULL; + } return PyLong_FromPid(pid); } #endif @@ -3756,14 +3776,22 @@ To both, return fd of newly opened pseudo-terminal.\n"); static PyObject * posix_forkpty(PyObject *self, PyObject *noargs) { - int master_fd = -1; + int master_fd = -1, result; pid_t pid; + _PyImport_AcquireLock(); pid = forkpty(&master_fd, NULL, NULL, NULL); + result = _PyImport_ReleaseLock(); if (pid == -1) return posix_error(); if (pid == 0) PyOS_AfterFork(); + if (result < 0) { + /* Don't clobber the OSError if the fork failed. */ + PyErr_SetString(PyExc_RuntimeError, + "not holding the import lock"); + return NULL; + } return Py_BuildValue("(Ni)", PyLong_FromPid(pid), master_fd); } #endif diff --git a/Python/import.c b/Python/import.c index 4846e10..cbfb761 100644 --- a/Python/import.c +++ b/Python/import.c @@ -256,8 +256,8 @@ static PyThread_type_lock import_lock = 0; static long import_lock_thread = -1; static int import_lock_level = 0; -static void -lock_import(void) +void +_PyImport_AcquireLock(void) { long me = PyThread_get_thread_ident(); if (me == -1) @@ -281,8 +281,8 @@ lock_import(void) import_lock_level = 1; } -static int -unlock_import(void) +int +_PyImport_ReleaseLock(void) { long me = PyThread_get_thread_ident(); if (me == -1 || import_lock == NULL) @@ -309,11 +309,6 @@ _PyImport_ReInitLock(void) #endif } -#else - -#define lock_import() -#define unlock_import() 0 - #endif static PyObject * @@ -330,7 +325,7 @@ static PyObject * imp_acquire_lock(PyObject *self, PyObject *noargs) { #ifdef WITH_THREAD - lock_import(); + _PyImport_AcquireLock(); #endif Py_INCREF(Py_None); return Py_None; @@ -340,7 +335,7 @@ static PyObject * imp_release_lock(PyObject *self, PyObject *noargs) { #ifdef WITH_THREAD - if (unlock_import() < 0) { + if (_PyImport_ReleaseLock() < 0) { PyErr_SetString(PyExc_RuntimeError, "not holding the import lock"); return NULL; @@ -2183,9 +2178,9 @@ PyImport_ImportModuleLevel(char *name, PyObject *globals, PyObject *locals, PyObject *fromlist, int level) { PyObject *result; - lock_import(); + _PyImport_AcquireLock(); result = import_module_level(name, globals, locals, fromlist, level); - if (unlock_import() < 0) { + if (_PyImport_ReleaseLock() < 0) { Py_XDECREF(result); PyErr_SetString(PyExc_RuntimeError, "not holding the import lock"); -- cgit v0.12