[Intel-gfx] [PATCH] drm/i915/execlists: Prevent GPU death on ELSP[1] promotion to idle context

2020-03-27 Thread Chris Wilson
In what seems remarkably similar to the w/a required to not reload an idle context with HEAD==TAIL, it appears we must prevent the HW from switching to an idle context in ELSP[1], while simultaneously trying to preempt the HW to run another context and a continuation of the idle context (which is

[Intel-gfx] [PATCH] drm/i915/execlists: Prevent GPU death on ELSP[1] promotion to idle context

2020-03-27 Thread Chris Wilson
In what seems remarkably similar to the w/a required to not reload an idle context with HEAD==TAIL, it appears we must prevent the HW from switching to an idle context in ELSP[1], while simultaneously trying to preempt the HW to run another context and a continuation of the idle context (which is

[Intel-gfx] [PATCH] drm/i915/execlists: Prevent GPU death on ELSP[1] promotion to idle context

2020-03-26 Thread Chris Wilson
In what seems remarkably similar to the w/a required to not reload an idle context with HEAD==TAIL, it appears we must prevent the HW from switching to an idle context in ELSP[1], while simultaneously trying to preempt the HW to run another context and a continuation of the idle context (which is

[Intel-gfx] [PATCH] drm/i915/execlists: Prevent GPU death on ELSP[1] promotion to idle context

2020-03-26 Thread Chris Wilson
In what seems remarkably similar to the w/a required to not reload an idle context with HEAD==TAIL, it appears we must prevent the HW from switching to an idle context in ELSP[1], while simultaneously trying to preempt the HW to run another context and a continuation of the idle context (which is