Currently, we reset the timer after a pre-eemption event. This has the
side-effect that the timeslice runs into the second context after the
first is completed after a normal promotion event, causing the second
context to be swapped out early and switched for a third context. To be
more fair, we want to reset the clock after promotion as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200113214546.1990139-1-chris@chris-wilson.co.uk
{
const struct i915_request *rq = *engine->execlists.active;
- if (i915_request_completed(rq))
+ if (!rq || i915_request_completed(rq))
return 0;
if (engine->execlists.switch_priority_hint < effective_prio(rq))
/* Point active to the new ELSP; prevent overwriting */
WRITE_ONCE(execlists->active, execlists->pending);
- set_timeslice(engine);
if (!inject_preempt_hang(execlists))
ring_set_paused(engine, 0);
} while (head != tail);
execlists->csb_head = head;
+ set_timeslice(engine);
/*
* Gen11 has proven to fail wrt global observation point between