Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> writes:
> Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes:
>
>> If we stop filling the ELSP due to an incompatible virtual engine
>> request, check if we should enable the timeslice on behalf of the queue.
>>
>
> Leaves me pondering more of the why.
>
> So that on these boundaries also, the last rq gets subdued to
> a timeslice and not get a free run?
I got some confirmations on irc. Yes this for that.
The commit message could be augmented on the why emphasis!
>
>> Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
>> ---
>> drivers/gpu/drm/i915/gt/intel_lrc.c | 21 ++++++++++++++++-----
>> 1 file changed, 16 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
>> index 5da86a40434c..954bd4797482 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
>> @@ -1802,6 +1802,20 @@ static void set_timeslice(struct intel_engine_cs *engine)
>> set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
>> }
>>
>> +static void start_timeslice(struct intel_engine_cs *engine,
>> + struct i915_request *last)
>> +{
>> + struct intel_engine_execlists *execlists = &engine->execlists;
>> +
>> + /* As we are returning early, update the hint from the queue */
>> + execlists->switch_priority_hint =
>> + max(execlists->queue_priority_hint,
>> + execlists->switch_priority_hint);
Still not completely unclear how the all hints play together
but the comment holds true, we bail out early.
>> +
>> + if (!execlists->timer.expires && need_timeslice(engine, last))
>> + set_timer_ms(&execlists->timer, timeslice(engine));
>> +}
>> +
>> static void record_preemption(struct intel_engine_execlists *execlists)
>> {
>> (void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++);
>> @@ -1965,11 +1979,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
>> * Even if ELSP[1] is occupied and not worthy
>> * of timeslices, our queue might be.
>> */
>> - if (!execlists->timer.expires &&
>> - need_timeslice(engine, last))
>> - set_timer_ms(&execlists->timer,
>> - timeslice(engine));
>> -
>> + start_timeslice(engine, last);
>> return;
>> }
>> }
>> @@ -2004,6 +2014,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
>>
>> if (last && !can_merge_rq(last, rq)) {
>> spin_unlock(&ve->base.active.lock);
>> + start_timeslice(engine, last);
>> return; /* leave this for another */
>
> for another interrupt?
For another veng. The comment might have already been augmented.
Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
> -Mika
>
>> }
>>
>> --
>> 2.25.1
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
>> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
