Skip to contentSkip to conversation

Revert "drm/i915/chv: Use timeout mode for RC6 on chv"

PATCH In review Rodrigo Vivi 4 participants 4 messages Jan 12, 2015 – Jan 21, 2015

Subsystems (2)
lore
Share & tools
lore

Rodrigo Vivi

author maintainer
#0 lore raw

PATCH 1/1 Revert "drm/i915/chv: Use timeout mode for RC6 on chv"

This reverts commit 5a0afd4b78ec23f27f5d486ac3d102c2e8d66bd7.

Although timeout mode allows higher residency it impact badly on performance. I believe while we don't have a way to balance between performance and power savings at runtime I believe we have to revert and prioritize performance that was impacted a lot.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88103

Cc Deepak S <[email protected]>
Cc Wendy Wang <[email protected]>
Cc Jani Nikula <[email protected]>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/intel_pm.c +2 -3
index 20a6dfa..03fc7f2 100644
@@ -4681,8 +4681,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
 		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
-	/* TO threshold set to 1750 us ( 0x557 * 1.28 us) */
-	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
+	I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
 
 	/* allows RC6 residency counter to work */
 	I915_WRITE(VLV_COUNTER_CONTROL,
@@ -4696,7 +4695,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
 	/* 3: Enable RC6 */
 	if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
 						(pcbr >> VLV_PCBR_ADDR_SHIFT))
-		rc6_mode = GEN7_RC_CTL_TO_MODE;
+		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
Signature · 6 lines
1.9.3

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw
Quoted 4 lines · Rodrigo Vivi

This reverts commit 5a0afd4b78ec23f27f5d486ac3d102c2e8d66bd7.

Although timeout mode allows higher residency it impact badly on performance. I believe while we don't have a way to balance between performance and

We do though. We already try to determine idle/low power/high power scenarios.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw
In reply to Rodrigo Vivi
Quoted 8 lines · Rodrigo Vivi

This reverts commit 5a0afd4b78ec23f27f5d486ac3d102c2e8d66bd7.

Although timeout mode allows higher residency it impact badly on performance. I believe while we don't have a way to balance between performance and power savings at runtime I believe we have to revert and prioritize performance that was impacted a lot.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88103

The bug points at [1] as a potential fix.

BR,
Jani.

[1] http://mid.gmane.org/[email protected]

Quoted 35 lines
Cc Deepak S <[email protected]>
Cc Wendy Wang <[email protected]>
Cc Jani Nikula <[email protected]>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/intel_pm.c +2 -3
index 20a6dfa..03fc7f2 100644
@@ -4681,8 +4681,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
 		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
-	/* TO threshold set to 1750 us ( 0x557 * 1.28 us) */
-	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
+	I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
 
 	/* allows RC6 residency counter to work */
 	I915_WRITE(VLV_COUNTER_CONTROL,
@@ -4696,7 +4695,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
 	/* 3: Enable RC6 */
 	if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
 						(pcbr >> VLV_PCBR_ADDR_SHIFT))
-		rc6_mode = GEN7_RC_CTL_TO_MODE;
+		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
Signature · 1 line
1.9.3
Signature · 5 lines
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw
Quoted 10 lines · Jani Nikula
Quoted 8 lines · Rodrigo Vivi

This reverts commit 5a0afd4b78ec23f27f5d486ac3d102c2e8d66bd7.

Although timeout mode allows higher residency it impact badly on performance. I believe while we don't have a way to balance between performance and power savings at runtime I believe we have to revert and prioritize performance that was impacted a lot.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88103

Quoted 7 lines

The bug points at [1] as a potential fix.

BR,
Jani.

[1] http://mid.gmane.org/[email protected]

I've merged both Rodrigo's revert and Ville's fix + revert of the revert already. But didn't send out mails because no smtp at lca. -Daniel

Signature · 7 lines
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx