Quoting Chris Wilson (2019-04-24 11:00:03)
> Quoting Tvrtko Ursulin (2019-04-16 15:50:27)
> >
> > On 16/04/2019 10:12, Chris Wilson wrote:
> > > + rq = ERR_PTR(-ENODEV);
> > > + with_intel_runtime_pm(engine->i915, wakeref)
> > > + rq = i915_request_alloc(engine, ctx);
> > > + if (IS_ERR(rq))
> > > + goto err_unpin;
> > > +
> > > + if (engine->emit_init_breadcrumb) { /* Be nice if we hang */
> > > + err = engine->emit_init_breadcrumb(rq);
> > > + if (err)
> > > + goto err_request;
> > > + }
> > > +
> > > + err = engine->emit_bb_start(rq, batch->node.start, 0, 0);
> >
> > Why is batch needed here when everything else is happy to run from the ring?
>
> Because we are playing with HW registers, I want reset to work safely.
> So long as we have init_breadcrumb, the payload scrubbing should work.
> Ok.
No, I am an idiot. The batch is so that we emulate userspace with
unprivileged execution
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
