Re: sched_core_balance() releasing interrupts with pi_lock held

[Sebastian Andrzej Siewior]

On 2022-03-16 17:03:14 [+0100], To Steven Rostedt wrote:
…
> which looked right but RT still fall apart:
…
> | =====================================
> | WARNING: bad unlock balance detected!
> | 5.17.0-rc8-rt14+ #10 Not tainted
> | -------------------------------------
…
…
> It is always the local-lock that is breaks apart. Based on "locks held"
> and the lock it tries to release it looks like the lock was acquired on
> CPU-A and released on CPU-B.

with

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 33ce5cd113d8..f4675bd8f878 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5968,6 +5967,9 @@ static bool try_steal_cookie(int this, int that)
 		if (p == src->core_pick || p == src->curr)
 			goto next;
 
+		if (p->migration_disabled)
+			goto next;
+
 		if (!cpumask_test_cpu(this, &p->cpus_mask))
 			goto next;
 
on top my problems are gone. Let me do some testing and then I would
patch unless PeterZ does the yelling :)

> > Thanks,
> > 
> > -- Steve
> 
Sebastian