[Intel-gfx] [PATCH] drm/i915/gt: Prevent queuing retire workers on the virtual engine

[Tvrtko Ursulin]

On 06/02/2020 15:29, Chris Wilson wrote:
> Quoting Chris Wilson (2020-02-06 15:23:25)
>> Virtual engines are fleeting. They carry a reference count and may be freed
>> when their last request is retired. This makes them unsuitable for the
>> task of housing engine->retire.work so assert that it is not used.
>>
>> Tvrtko tracked down an instance where we did indeed violate this rule.
>> In virtal_submit_request, we flush a completed request directly with
>> __i915_request_submit and this causes us to queue that request on the
>> veng's breadcrumb list and signal it. Leading us down a path where we
>> should not attach the retire.
>>
>> Reported-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
>> Fixes: dc93c9b69315 ("drm/i915/gt: Schedule request retirement when signaler idles")
>> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
>> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> 
> Alternatively we could fixup the rq->engine before
> __i915_request_submit. That would stop the spread of
> intel_virtual_engine_get_sibling().
> 
> This is likely to be the cleaner fix, so I think I would prefer this and
> then remove the get_sibling().

Yes it makes more sense for rq->engine to be always physical at the 
point of __i915_request_submit.

Regards,

Tvrtko