Re: [PATCH] rtmutex: ensure we wake up the top waiter

[Wander Lairson Costa]

On Thu, Feb 2, 2023 at 5:07 AM Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:
>
> On Tue, Jan 31 2023 at 14:53, Wander Lairson Costa wrote:
> > On Tue, Jan 31, 2023 at 02:46:19PM -0300, Wander Lairson Costa wrote:
> >> > If you have traces which show the sequence of lock events leading to
> >> > this problem, then you should be able to decode the scenario. If you
> >> > fail to extract the information, then please provide the traces so we
> >> > can stare at them.
> >> >
> >>
> >> Here we go:
> >>
> >> Let L1 and L2 be two spinlocks.
> >>
> >> Let T1 be a task holding L1 and blocked on L2. T1, currently, is the top
> >> waiter of L2.
> >>
> >> Let T2 be the task holding L2.
> >>
> >> Let T3 be a task trying to acquire L1.
> >>
> >> The following events will lead to a state in which the wait queue of L2
> >> isn't empty but nobody holds it.
>
> That explains it nicely. Care to resend with proper explanations in the
> changelog?
>

Sure thing, thanks.