1 files changed, 49 insertions, 95 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 33a8dbe6403..172efa0bfb8 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3429,26 +3429,19 @@ static void ironlake_disable_drps(struct drm_device *dev)
  * ourselves, instead of doing a rmw cycle (which might result in us clearing
  * all limits and the gpu stuck at whatever frequency it is at atm).
  */
-static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 *val)
+static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 {
 	u32 limits;
 
-	limits = 0;
-
-	if (*val >= dev_priv->rps.max_delay)
-		*val = dev_priv->rps.max_delay;
-	limits |= dev_priv->rps.max_delay << 24;
-
 	/* Only set the down limit when we've reached the lowest level to avoid
 	 * getting more interrupts, otherwise leave this clear. This prevents a
 	 * race in the hw when coming out of rc6: There's a tiny window where
 	 * the hw runs at the minimal clock before selecting the desired
 	 * frequency, if the down threshold expires in that window we will not
 	 * receive a down interrupt. */
-	if (*val <= dev_priv->rps.min_delay) {
-		*val = dev_priv->rps.min_delay;
+	limits = dev_priv->rps.max_delay << 24;
+	if (val <= dev_priv->rps.min_delay)
 		limits |= dev_priv->rps.min_delay << 16;
-	}
 
 	return limits;
 }
@@ -3548,7 +3541,6 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 void gen6_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 limits = gen6_rps_limits(dev_priv, &val);
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 	WARN_ON(val > dev_priv->rps.max_delay);
@@ -3571,7 +3563,8 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	/* Make sure we continue to get interrupts
 	 * until we hit the minimum or maximum frequencies.
 	 */
-	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
+	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+		   gen6_rps_limits(dev_priv, val));
 
 	POSTING_READ(GEN6_RPNSWREQ);
 
@@ -3606,48 +3599,18 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-/*
- * Wait until the previous freq change has completed,
- * or the timeout elapsed, and then update our notion
- * of the current GPU frequency.
- */
-static void vlv_update_rps_cur_delay(struct drm_i915_private *dev_priv)
-{
-	u32 pval;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-
-	if (wait_for(((pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) & GENFREQSTATUS) == 0, 10))
-		DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
-
-	pval >>= 8;
-
-	if (pval != dev_priv->rps.cur_delay)
-		DRM_DEBUG_DRIVER("Punit overrode GPU freq: %d MHz (%u) requested, but got %d Mhz (%u)\n",
-				 vlv_gpu_freq(dev_priv->mem_freq, dev_priv->rps.cur_delay),
-				 dev_priv->rps.cur_delay,
-				 vlv_gpu_freq(dev_priv->mem_freq, pval), pval);
-
-	dev_priv->rps.cur_delay = pval;
-}
-
 void valleyview_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	gen6_rps_limits(dev_priv, &val);
-
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 	WARN_ON(val > dev_priv->rps.max_delay);
 	WARN_ON(val < dev_priv->rps.min_delay);
 
-	vlv_update_rps_cur_delay(dev_priv);
-
 	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.cur_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
 			 dev_priv->rps.cur_delay,
-			 vlv_gpu_freq(dev_priv->mem_freq, val), val);
+			 vlv_gpu_freq(dev_priv, val), val);
 
 	if (val == dev_priv->rps.cur_delay)
 		return;
@@ -3656,7 +3619,7 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 
 	dev_priv->rps.cur_delay = val;
 
-	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv->mem_freq, val));
+	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
 }
 
 static void gen6_disable_rps_interrupts(struct drm_device *dev)
@@ -4154,51 +4117,33 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-	switch ((val >> 6) & 3) {
-	case 0:
-	case 1:
-		dev_priv->mem_freq = 800;
-		break;
-	case 2:
-		dev_priv->mem_freq = 1066;
-		break;
-	case 3:
-		dev_priv->mem_freq = 1333;
-		break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
 	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
 
 	dev_priv->rps.cur_delay = (val >> 8) & 0xff;
 	DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.cur_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
 			 dev_priv->rps.cur_delay);
 
 	dev_priv->rps.max_delay = valleyview_rps_max_freq(dev_priv);
 	dev_priv->rps.hw_max = dev_priv->rps.max_delay;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.max_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay),
 			 dev_priv->rps.max_delay);
 
 	dev_priv->rps.rpe_delay = valleyview_rps_rpe_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.rpe_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
 	dev_priv->rps.min_delay = valleyview_rps_min_freq(dev_priv);
 	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.min_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay),
 			 dev_priv->rps.min_delay);
 
 	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.rpe_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
@@ -5462,6 +5407,26 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 static void valleyview_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	switch ((val >> 6) & 3) {
+	case 0:
+		dev_priv->mem_freq = 800;
+		break;
+	case 1:
+		dev_priv->mem_freq = 1066;
+		break;
+	case 2:
+		dev_priv->mem_freq = 1333;
+		break;
+	case 3:
+		dev_priv->mem_freq = 1333;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
@@ -6090,59 +6055,48 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val)
 	return 0;
 }
 
-int vlv_gpu_freq(int ddr_freq, int val)
+int vlv_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
-	int mult, base;
+	int div;
 
-	switch (ddr_freq) {
+	/* 4 x czclk */
+	switch (dev_priv->mem_freq) {
 	case 800:
-		mult = 20;
-		base = 120;
+		div = 10;
 		break;
 	case 1066:
-		mult = 22;
-		base = 133;
+		div = 12;
 		break;
 	case 1333:
-		mult = 21;
-		base = 125;
+		div = 16;
 		break;
 	default:
 		return -1;
 	}
 
-	return ((val - 0xbd) * mult) + base;
+	return DIV_ROUND_CLOSEST(dev_priv->mem_freq * (val + 6 - 0xbd), 4 * div);
 }
 
-int vlv_freq_opcode(int ddr_freq, int val)
+int vlv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
-	int mult, base;
+	int mul;
 
-	switch (ddr_freq) {
+	/* 4 x czclk */
+	switch (dev_priv->mem_freq) {
 	case 800:
-		mult = 20;
-		base = 120;
+		mul = 10;
 		break;
 	case 1066:
-		mult = 22;
-		base = 133;
+		mul = 12;
 		break;
 	case 1333:
-		mult = 21;
-		base = 125;
+		mul = 16;
 		break;
 	default:
 		return -1;
 	}
 
-	val /= mult;
-	val -= base / mult;
-	val += 0xbd;
-
-	if (val > 0xea)
-		val = 0xea;
-
-	return val;
+	return DIV_ROUND_CLOSEST(4 * mul * val, dev_priv->mem_freq) + 0xbd - 6;
 }
 
 void intel_pm_init(struct drm_device *dev)