Quoting Mika Kuoppala (2018-08-01 10:38:55)
> Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes:
>
> > We used to reset last_adj to 0 on crossing a power domain boundary, to
> > slow down our rate of change. However, commit 60548c554be2 ("drm/i915:
> > Interactive RPS mode") accidentally caused it to be reset on every
> > frequency update, nerfing the fast response granted by the slow start
> > algorithm.
> >
> > Fixes: 60548c554be2 ("drm/i915: Interactive RPS mode")
> > Testcase: igt/pm_rps/mix-max-config-loaded
> > Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> > Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
> > ---
> > drivers/gpu/drm/i915/intel_pm.c | 1 -
> > 1 file changed, 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> > index 2531eb75bdce..f90a3c7f1c40 100644
> > --- a/drivers/gpu/drm/i915/intel_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_pm.c
> > @@ -6371,7 +6371,6 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
> > new_power = HIGH_POWER;
> > rps_set_power(dev_priv, new_power);
> > mutex_unlock(&rps->power.mutex);
> > - rps->last_adj = 0;
>
> To follow the old logic, you should zero it in rps_set_power ?
Also note I didn't do that originally because we now have an alternative
path that would then modify last_adj outside of the rps worker,
conflicting with the previous logic as well.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
