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.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
