[Intel-gfx] [PATCH 5/7] drm/i915: Use cpu clock to calculate rc0 residency

[Mika Kuoppala]

Avoid more costly punit access and use the local cpu clock.
The time diff between separate processor units is irrelevant in
our rc0 residency granularity so we can ignore it.

Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h |  2 +-
 drivers/gpu/drm/i915/i915_irq.c | 10 ++++------
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0023e21..70e335c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1323,7 +1323,7 @@ struct vlv_s0ix_state {
 };
 
 struct intel_rps_ei {
-	u32 cz_clock;
+	u64 cpu_clock;
 	u32 render_c0;
 	u32 media_c0;
 };
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 31f0d7c..00e7875 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1076,7 +1076,7 @@ static void notify_ring(struct intel_engine_cs *engine)
 static void vlv_c0_read(struct drm_i915_private *dev_priv,
 			struct intel_rps_ei *ei)
 {
-	ei->cz_clock = vlv_punit_read(dev_priv, PUNIT_REG_CZ_TIMESTAMP);
+	ei->cpu_clock = local_clock();
 	ei->render_c0 = I915_READ(VLV_RENDER_C0_COUNT);
 	ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
 }
@@ -1096,19 +1096,17 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 		return 0;
 
 	vlv_c0_read(dev_priv, &now);
-	if (now.cz_clock == 0)
-		return 0;
 
-	if (prev->cz_clock) {
+	if (prev->cpu_clock) {
 		u64 time, c0;
 		u32 render, media;
 		unsigned int mul;
 
-		mul = VLV_CZ_CLOCK_TO_MILLI_SEC * 100; /* scale to threshold% */
+		mul = 1000 * 1000 * 100; /* scale to threshold% */
 		if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
 			mul <<= 8;
 
-		time = now.cz_clock - prev->cz_clock;
+		time = now.cpu_clock - prev->cpu_clock;
 		time *= dev_priv->czclk_freq;
 
 		/* Workload can be split between render + media,
-- 
2.7.4