Re: [Bug] Race condition between CPU hotplug off flow and __sched_setscheduler()

[Peter Zijlstra]

On Thu, May 19, 2022 at 08:53:15PM +0800, Jing-Ting Wu wrote:
> Hi all
> 
> 
> There is a race condition between CPU hotplug off flow and
> __sched_setscheduler(), which will cause hang-up in CPU hotplug off
> flow.

How easy can you reproduce; does the below hack make it better?

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95bac3b094b3..f18ee22b29bc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4763,20 +4763,30 @@ struct callback_head balance_push_callback = {
 	.func = (void (*)(struct callback_head *))balance_push,
 };
 
-static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+static inline struct callback_head *
+__splice_balance_callbacks(struct rq *rq, bool foo)
 {
 	struct callback_head *head = rq->balance_callback;
 
 	lockdep_assert_rq_held(rq);
-	if (head)
-		rq->balance_callback = NULL;
+	if (head) {
+		if (foo && head == &balance_push_callback)
+			head = NULL;
+		else
+			rq->balance_callback = NULL;
+	}
 
 	return head;
 }
 
+static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+{
+	return __splice_balance_callbacks(rq, true);
+}
+
 static void __balance_callbacks(struct rq *rq)
 {
-	do_balance_callbacks(rq, splice_balance_callbacks(rq));
+	do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
 }
 
 static inline void balance_callbacks(struct rq *rq, struct callback_head *head)