[Intel-gfx] [PATCH] drm/i915: Skip engine serialisation for no-op seqno reset

Chris Wilson chris at chris-wilson.co.uk
Tue Nov 27 12:59:46 UTC 2018


Quoting Mika Kuoppala (2018-11-27 12:54:07)
> Chris Wilson <chris at chris-wilson.co.uk> writes:
> 
> > If the engine's seqno is already at our target seqno (most likely it
> > hasn't been used since the last reset), we can skip serialising the
> > engine and leave it as is.
> >
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> > ---
> >  drivers/gpu/drm/i915/i915_request.c | 3 +++
> >  1 file changed, 3 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
> > index 71107540581d..ca95ab2f4cfa 100644
> > --- a/drivers/gpu/drm/i915/i915_request.c
> > +++ b/drivers/gpu/drm/i915/i915_request.c
> > @@ -136,6 +136,9 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
> >                         intel_engine_get_seqno(engine),
> >                         seqno);
> >  
> > +             if (seqno == engine->timeline.seqno)
> > +                     continue;
> > +
> 
> Patch looks valid. Only concern is possibility of hiding
> the idle assertion deeper. But as that is for icl
> and debugfs stomping, I am in favour.

Ssh, what if that was its primary raison d'etre? ;)
Though given the failure, it's not going to completely hide them.
-Chris


More information about the Intel-gfx mailing list