On Tue, 13 May 2014, Lai Jiangshan wrote:
> Hi, Thomas,
>
> I think this patch is just a workaround, it is not the proper fix.
> you need a updated deadlock-check mechanism:
>
> - (old) skip the check when top_waiter != task_top_pi_waiter(task)
> + (new) skip the check when top_waiter->prio > task->prio
I don't think that helps.
> > /*
> > + * Deadlock check for the following scenario:
> > + *
> > + * T holds lock L and has waiters
> > + * T locks L again, but does not end up as it's own top waiter
>
> ABBA problem (TA TB TC TD are of the same priority)
>
> TA holds lock LA, and try to lock LB which TC already has waited on
> TB holds lock LB, and try to lock LA which TD already has waited on
>
> I think this check can't detect it IIUC.
Right it doesn't.
> /*
> * Drop out, when the task has no waiters. Note,
> * top_waiter can be NULL, when we are in the deboosting
> * mode!
> */
> if (top_waiter && (!task_has_pi_waiters(task) ||
> top_waiter != task_top_pi_waiter(task)))
> goto out_unlock_pi;
So the issue here is, that we break out of the chain walk even if
deadlock detection is enabled.
The break out is correct for the boost case w/o deadlock detection, so
we won't do any pointless work.
For the deadlock detection case, we need to continue. But we should
store, that we are not the top_waiter so we can avoid the requeue
business when walking the chain.
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
