[PATCH v6] drm/i915/chv: Enable RPS (Turbo) for Cherryview

[deepak.s@linux.intel.com]

From: Deepak S <deepak.s@linux.intel.com>

v2: Disable media turbo and Add DOWN_IDLE_AVG support (Ville)

v3: Mass rename of the dev_priv->rps variables in upstream.

v4: Rebase against latest code. (Deepak)

v5: Rebase against latest nightly code. (Deepak)

v6: Rename the variables to match the spec (Mika)

Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h | 11 +++++
 drivers/gpu/drm/i915/intel_pm.c | 95 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 105 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c1f36a5..7e8968b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -529,6 +529,16 @@ enum punit_power_well {
 #define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
 #define PUNIT_FUSE_BUS1				0xf5 /* bits 55:48 */
 
+#define CHV_IOSF_PUNIT_FB_GFX_FREQ_REG		0xdb
+#define CHV_FB_GFX_MAX_FREQ_SHIFT		16
+#define CHV_FB_GFX_MAX_FREQ_MASK		0xff
+#define CHV_FB_GFX_MIN_FREQ_SHIFT		8
+#define CHV_FB_GFX_MIN_FREQ_MASK		0xff
+
+#define CHV_IOSF_PUNIT_FB_GFX_RPE_REG		0xdf
+#define CHV_FB_GFX_RPE_FREQ_SHIFT		8
+#define CHV_FB_GFX_RPE_FREQ_MASK		0xff
+
 #define IOSF_NC_FB_GFX_FREQ_FUSE		0x1c
 #define   FB_GFX_MAX_FREQ_FUSE_SHIFT		3
 #define   FB_GFX_MAX_FREQ_FUSE_MASK		0x000007f8
@@ -933,6 +943,7 @@ enum punit_power_well {
 #define   SANDYBRIDGE_FENCE_PITCH_SHIFT	32
 #define   GEN7_FENCE_MAX_PITCH_VAL	0x0800
 
+
 /* control register for cpu gtt access */
 #define TILECTL				0x101000
 #define   TILECTL_SWZCTL			(1 << 0)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1816c52..d4a84b3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3731,6 +3731,38 @@ void gen6_update_ring_freq(struct drm_device *dev)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
+int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rp0;
+
+	val = vlv_punit_read(dev_priv, CHV_IOSF_PUNIT_FB_GFX_FREQ_REG);
+
+	rp0 = (val >> CHV_FB_GFX_MAX_FREQ_SHIFT) &
+					CHV_FB_GFX_MAX_FREQ_MASK;
+
+	return rp0;
+}
+
+static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rpe;
+
+	val = vlv_punit_read(dev_priv, CHV_IOSF_PUNIT_FB_GFX_RPE_REG);
+	rpe = (val >> CHV_FB_GFX_RPE_FREQ_SHIFT) & CHV_FB_GFX_RPE_FREQ_MASK;
+
+	return rpe;
+}
+
+int cherryview_rps_min_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rpn;
+
+	val = vlv_punit_read(dev_priv, CHV_IOSF_PUNIT_FB_GFX_FREQ_REG);
+	rpn = (val >> CHV_FB_GFX_MIN_FREQ_SHIFT) & CHV_FB_GFX_MIN_FREQ_MASK;
+
+	return rpn;
+}
+
 int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
@@ -3890,7 +3922,36 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
 
 static void cherryview_init_gt_powersave(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	cherryview_setup_pctx(dev);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	dev_priv->rps.max_freq = cherryview_rps_max_freq(dev_priv);
+	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+			 dev_priv->rps.max_freq);
+
+	dev_priv->rps.efficient_freq = cherryview_rps_rpe_freq(dev_priv);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	dev_priv->rps.min_freq = cherryview_rps_min_freq(dev_priv);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
+			 dev_priv->rps.min_freq);
+
+	/* Preserve min/max settings in case of re-init */
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
@@ -3902,7 +3963,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
-	u32 gtfifodbg, rc6_mode = 0, pcbr;
+	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
 	int i;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -3949,6 +4010,38 @@ static void cherryview_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
+	/* 4 Program defaults and thresholds for RPS*/
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
+	I915_WRITE(GEN6_RP_UP_EI, 66000);
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
+
+	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	/* 5: Enable RPS */
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX |
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_AVG);
+
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+
+	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
+	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+
+	dev_priv->rps.cur_freq = (val >> 8) & 0xff;
+	DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+			 dev_priv->rps.cur_freq);
+
+	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	valleyview_set_rps(dev_priv->dev, dev_priv->rps.efficient_freq);
+
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-- 
1.9.1