Quoting Joonas Lahtinen (2018-03-05 14:25:07)
> As a pre-existing condition it's bit surprising that intel_breadcrumbs_busy()
> kicks the signaler as a side-effect.
Since we explicitly cancel the signaling on retire now (to prevent the
accumulation of references), we can actually say that we don't
Quoting Chris Wilson (2018-02-22 11:25:44)
> The goal here is to try and reduce the latency of signaling additional
> requests following the wakeup from interrupt by reducing the list of
> to-be-signaled requests from an rbtree to a sorted linked list. The
> original choice of using an rbtree was t
The goal here is to try and reduce the latency of signaling additional
requests following the wakeup from interrupt by reducing the list of
to-be-signaled requests from an rbtree to a sorted linked list. The
original choice of using an rbtree was to facilitate random insertions
of request into the