Fix stale idle flag when IO workers exit.

macdice · macdice · commit 20b8b5dab983 · 2025-07-12T13:14:22.000+12:00
Otherwise we could choose a worker that has exited and crash while trying to wake it up. Back-patch to 18. Reported-by: Tomas Vondra <tomas@vondra.me> Reported-by: Andres Freund <andres@anarazel.de> Discussion: https://postgr.es/m/t5aqjhkj6xdkido535pds7fk5z4finoxra4zypefjqnlieevbg%40357aaf6u525j
diff --git a/src/backend/storage/aio/method_worker.c b/src/backend/storage/aio/method_worker.c
@@ -172,6 +172,7 @@ pgaio_choose_idle_worker(void)
 	/* Find the lowest bit position, and clear it. */
 	worker = pg_rightmost_one_pos64(io_worker_control->idle_worker_mask);
 	io_worker_control->idle_worker_mask &= ~(UINT64_C(1) << worker);
+	Assert(io_worker_control->workers[worker].in_use);
 
 	return worker;
 }
@@ -316,6 +317,7 @@ pgaio_worker_die(int code, Datum arg)
 	Assert(io_worker_control->workers[MyIoWorkerId].in_use);
 	Assert(io_worker_control->workers[MyIoWorkerId].latch == MyLatch);
 
+	io_worker_control->idle_worker_mask &= ~(UINT64_C(1) << MyIoWorkerId);
 	io_worker_control->workers[MyIoWorkerId].in_use = false;
 	io_worker_control->workers[MyIoWorkerId].latch = NULL;
 	LWLockRelease(AioWorkerSubmissionQueueLock);
