vhost: Fix worker hangs due to missed wake up calls

We can race where we have added work to the work_list, but
vhost_task_fn has passed that check but not yet set us into
TASK_INTERRUPTIBLE. wake_up_process will see us in TASK_RUNNING and
just return.

This bug was intoduced in commit f9010dbd ("fork, vhost: Use
CLONE_THREAD to fix freezer/ps regression") when I moved the setting
of TASK_INTERRUPTIBLE to simplfy the code and avoid get_signal from
logging warnings about being in the wrong state. This moves the setting
of TASK_INTERRUPTIBLE back to before we test if we need to stop the
task to avoid a possible race there as well. We then have vhost_worker
set TASK_RUNNING if it finds work similar to before.

Fixes: f9010dbd ("fork, vhost: Use CLONE_THREAD to fix freezer/ps regression")
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Message-Id: <20230607192338.6041-3-michael.christie@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

drivers/vhost/vhost.c

@@ -341,6 +341,8 @@ static bool vhost_worker(void *data)
 
 	node = llist_del_all(&worker->work_list);
 	if (node) {
+		__set_current_state(TASK_RUNNING);
+
 		node = llist_reverse_order(node);
 		/* make sure flag is seen after deletion */
 		smp_wmb();

kernel/vhost_task.c

@@ -28,10 +28,6 @@ static int vhost_task_fn(void *data)
 	for (;;) {
 		bool did_work;
 
-		/* mb paired w/ vhost_task_stop */
-		if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags))
-			break;
-
 		if (!dead && signal_pending(current)) {
 			struct ksignal ksig;
 			/*
@@ -48,11 +44,17 @@ static int vhost_task_fn(void *data)
 				clear_thread_flag(TIF_SIGPENDING);
 		}
 
-		did_work = vtsk->fn(vtsk->data);
-		if (!did_work) {
+		/* mb paired w/ vhost_task_stop */
 		set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
+
+		if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) {
+			__set_current_state(TASK_RUNNING);
+			break;
 		}
+
+		did_work = vtsk->fn(vtsk->data);
+		if (!did_work)
+			schedule();
 	}
 
 	complete(&vtsk->exited);