drm/i915/gt: Treat idling as a RPS downclock event

If we park/unpark faster than we can respond to RPS events, we never
will process a downclock event after expiring a waitboost, and thus we
will forever restart the GPU at max clocks even if the workload switches
and doesn't justify full power.

Closes: https://gitlab.freedesktop.org/drm/intel/issues/1500
Fixes: 3e7abf8 ("drm/i915: Extract GT render power state management")
Signed-off-by: Chris Wilson <[email protected]>
Cc: Andi Shyti <[email protected]>
Cc: Lyude Paul <[email protected]>
Reviewed-by: Andi Shyti <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Cc: <[email protected]> # v5.5+
(cherry picked from commit 21abf0b)
Signed-off-by: Rodrigo Vivi <[email protected]>

Author: ickle

drivers/gpu/drm/i915/gt/intel_rps.c

@@ -770,6 +770,19 @@ void intel_rps_park(struct intel_rps *rps)
 	intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
 	rps_set(rps, rps->idle_freq, false);
 	intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);
+
+	/*
+	 * Since we will try and restart from the previously requested
+	 * frequency on unparking, treat this idle point as a downclock
+	 * interrupt and reduce the frequency for resume. If we park/unpark
+	 * more frequently than the rps worker can run, we will not respond
+	 * to any EI and never see a change in frequency.
+	 *
+	 * (Note we accommodate Cherryview's limitation of only using an
+	 * even bin by applying it to all.)
+	 */
+	rps->cur_freq =
+		max_t(int, round_down(rps->cur_freq - 1, 2), rps->min_freq);
 }
 
 void intel_rps_boost(struct i915_request *rq)