Quoting Chris Wilson (2018-02-08 15:29:29)
> Quoting Mika Kuoppala (2018-02-08 15:20:30)
> > Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes:
> >
> > > Since commit 4a118ecbe99c ("drm/i915: Filter out spurious execlists
> > > context-switch interrupts") we probe execlists->active, and no longer
> > > have to peek at the execlist interrupt to determine if the tasklet still
> > > needs to be run to drain the ELSP.
> > >
> > > References: 4a118ecbe99c ("drm/i915: Filter out spurious execlists context-switch interrupts")
> > > Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> > > Cc: Michal Winiarski <michal.winiarski@xxxxxxxxx>
> > > Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
> > > Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxx>
> > > ---
> > > drivers/gpu/drm/i915/intel_engine_cs.c | 4 ----
> > > 1 file changed, 4 deletions(-)
> > >
> > > diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
> > > index bf634432c9c6..0ad9184eba97 100644
> > > --- a/drivers/gpu/drm/i915/intel_engine_cs.c
> > > +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
> > > @@ -1503,10 +1503,6 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
> > > if (I915_SELFTEST_ONLY(engine->breadcrumbs.mock))
> > > return true;
> > >
> > > - /* Interrupt/tasklet pending? */
> > > - if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
> > > - return false;
> > > -
> >
> > We assert that active is set on preempt so there should
> > be no window of idleness during that either.
> >
> > Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
>
> The other thing that crossed my mind was that we should drain the
> tasklet during parking. But the above check already means the tasklet is
> exiting -- one hopes. Still probably worth checking how horrible that
> looks.
Well, look at that, we do!
intel_engines_park() {
for_each_engine tasklet_kill(&engine->execlists.tasklet);
}
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
