homepage

Using a lock after fork() is unsafe and can crash.
Example of a crash in logging after a fork on AIX:
https://bugs.python.org/issue40068#msg365028
This problem is explained in length in bpo-6721: "Locks in the standard library should be sanitized on fork".
The threading module registers an "at fork" callback: Thread._reset_internal_locks() is called to reset self._started (threading.Event) and self._tstate_lock. The current implementation creates new Python lock objects and forgets about the old ones.
I propose to add a new _at_fork_reinit() method to Python lock objects which reinitializes the native lock internally without having to create a new Python object.
Currently, my implementation basically creates a new native lock object and forgets about the old new (don't call PyThread_free_lock()).
Tomorrow, we can imagine a more efficient impementation using platform specific function to handle this case without having to forget about the old lock.

_at_fork() has a bug: it creates a _DummyThread instead of a _MainThread. Example:
---
import os, _thread, threading, time
def fork_in_thread():
 pid = os.fork()
 if pid:
 # parent
 os._exit(0)
 # child process
 print(f"child process: {threading.current_thread()=}")
 print(f"child process: {threading._main_thread=}")
print(f"parent process: {threading.current_thread()=}")
print(f"parent process: {threading._main_thread=}")
_thread.start_new_thread(fork_in_thread, ())
# block the main thread: fork_in_thread() exit the process
time.sleep(60)
---
Output:
---
parent process: threading.current_thread()=<_MainThread(MainThread, started 139879200077632)>
parent process: threading._main_thread=<_MainThread(MainThread, started 139879200077632)>
child process: threading.current_thread()=<_DummyThread(Dummy-1, started daemon 139878980245248)>
child process: threading._main_thread=<_DummyThread(Dummy-1, started daemon 139878980245248)>
---
My PR 19191 fix the issue:
---
parent process: threading.current_thread()=<_MainThread(MainThread, started 140583665170240)>
parent process: threading._main_thread=<_MainThread(MainThread, started 140583665170240)>
child process: threading.current_thread()=<_MainThread(MainThread, started 140583445075712)>
child process: threading._main_thread=<_MainThread(MainThread, started 140583445075712)>
---

New changeset d8ff44ce4cd6f3ec0fab5fccda6bf14afcb25c30 by Victor Stinner in branch 'master':
bpo-40089: Fix threading._after_fork() (GH-19191)
https://github.com/python/cpython/commit/d8ff44ce4cd6f3ec0fab5fccda6bf14afcb25c30

See also bpo-40091 "Crash in logging._after_at_fork_child_reinit_locks()" that I just created.

See also bpo-40092: "Crash in _PyThreadState_DeleteExcept() at fork in the process child".

New changeset 87255be6964979b5abdc4b9dcf81cdcfdad6e753 by Victor Stinner in branch 'master':
bpo-40089: Add _at_fork_reinit() method to locks (GH-19195)
https://github.com/python/cpython/commit/87255be6964979b5abdc4b9dcf81cdcfdad6e753

New changeset 6318e45bda6c37d5497f33a6039cdb65aa494c93 by Miss Islington (bot) in branch '3.8':
bpo-40089: Fix threading._after_fork() (GH-19191) (GH-19194)
https://github.com/python/cpython/commit/6318e45bda6c37d5497f33a6039cdb65aa494c93

New changeset a514ccb3ea6f01fef850d9465b82a1670d5ace44 by Miss Islington (bot) in branch '3.7':
bpo-40089: Fix threading._after_fork() (GH-19191) (GH-19193)
https://github.com/python/cpython/commit/a514ccb3ea6f01fef850d9465b82a1670d5ace44