Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main git pull for the drm,

  I pretty much froze major pulls at -rc5/6 time, and haven't had much
  fallout, so will probably continue doing that.

  Lots of changes all over, big internal header cleanup to make it clear
  drm features are legacy things and what are things that modern KMS
  drivers should be using.  Also big move to use the new generic fences
  in all the TTM drivers.

  core:
        atomic prep work,
        vblank rework changes, allows immediate vblank disables
        major header reworking and cleanups to better delinate legacy
        interfaces from what KMS drivers should be using.
        cursor planes locking fixes

  ttm:
        move to generic fences (affects all TTM drivers)
        ppc64 caching fixes

  radeon:
        userptr support,
        uvd for old asics,
        reset rework for fence changes
        better buffer placement changes,
        dpm feature enablement
        hdmi audio support fixes

  intel:
        Cherryview work,
        180 degree rotation,
        skylake prep work,
        execlist command submission
        full ppgtt prep work
        cursor improvements
        edid caching,
        vdd handling improvements

  nouveau:
        fence reworking
        kepler memory clock work
        gt21x clock work
        fan control improvements
        hdmi infoframe fixes
        DP audio

  ast:
        ppc64 fixes
        caching fix

  rcar:
        rcar-du DT support

  ipuv3:
        prep work for capture support

  msm:
        LVDS support for mdp4, new panel, gpu refactoring

  exynos:
        exynos3250 SoC support, drop bad mmap interface,
        mipi dsi changes, and component match support"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (640 commits)
  drm/mst: rework payload table allocation to conform better.
  drm/ast: Fix HW cursor image
  drm/radeon/kv: add uvd/vce info to dpm debugfs output
  drm/radeon/ci: add uvd/vce info to dpm debugfs output
  drm/radeon: export reservation_object from dmabuf to ttm
  drm/radeon: cope with foreign fences inside the reservation object
  drm/radeon: cope with foreign fences inside display
  drm/core: use helper to check driver features
  drm/radeon/cik: write gfx ucode version to ucode addr reg
  drm/radeon/si: print full CS when we hit a packet 0
  drm/radeon: remove unecessary includes
  drm/radeon/combios: declare legacy_connector_convert as static
  drm/radeon/atombios: declare connector convert tables as static
  drm/radeon: drop btc_get_max_clock_from_voltage_dependency_table
  drm/radeon/dpm: drop clk/voltage dependency filters for BTC
  drm/radeon/dpm: drop clk/voltage dependency filters for CI
  drm/radeon/dpm: drop clk/voltage dependency filters for SI
  drm/radeon/dpm: drop clk/voltage dependency filters for NI
  drm/radeon: disable audio when we disable hdmi (v2)
  drm/radeon: split audio enable between eg and r600 (v2)
  ...

1 files changed, 622 insertions, 196 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 40c12295c0bd..c27b6140bfd1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -309,6 +309,9 @@ static void gen7_enable_fbc(struct drm_crtc *crtc)
 
 	dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
 
+	if (dev_priv->fbc.false_color)
+		dpfc_ctl |= FBC_CTL_FALSE_COLOR;
+
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
 	if (IS_IVYBRIDGE(dev)) {
@@ -342,6 +345,16 @@ bool intel_fbc_enabled(struct drm_device *dev)
 	return dev_priv->display.fbc_enabled(dev);
 }
 
+void gen8_fbc_sw_flush(struct drm_device *dev, u32 value)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_GEN8(dev))
+		return;
+
+	I915_WRITE(MSG_FBC_REND_STATE, value);
+}
+
 static void intel_fbc_work_fn(struct work_struct *__work)
 {
 	struct intel_fbc_work *work =
@@ -578,6 +591,12 @@ void intel_update_fbc(struct drm_device *dev)
 			DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
 		goto out_disable;
 	}
+	if (INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
+	    to_intel_plane(crtc->primary)->rotation != BIT(DRM_ROTATE_0)) {
+		if (set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED_MODE))
+			DRM_DEBUG_KMS("Rotation unsupported, disabling\n");
+		goto out_disable;
+	}
 
 	/* If the kernel debugger is active, always disable compression */
 	if (in_dbg_master())
@@ -853,7 +872,7 @@ void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable)
  * A value of 5us seems to be a good balance; safe for very low end
  * platforms but not overly aggressive on lower latency configs.
  */
-static const int latency_ns = 5000;
+static const int pessimal_latency_ns = 5000;
 
 static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
 {
@@ -982,13 +1001,20 @@ static const struct intel_watermark_params i915_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params i830_wm_info = {
+static const struct intel_watermark_params i830_a_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
 	.default_wm = 1,
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+static const struct intel_watermark_params i830_bc_wm_info = {
+	.fifo_size = I855GM_FIFO_SIZE,
+	.max_wm = I915_MAX_WM/2,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I830_FIFO_LINE_SIZE,
+};
 static const struct intel_watermark_params i845_wm_info = {
 	.fifo_size = I830_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -1044,6 +1070,17 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz,
 		wm_size = wm->max_wm;
 	if (wm_size <= 0)
 		wm_size = wm->default_wm;
+
+	/*
+	 * Bspec seems to indicate that the value shouldn't be lower than
+	 * 'burst size + 1'. Certainly 830 is quite unhappy with low values.
+	 * Lets go for 8 which is the burst size since certain platforms
+	 * already use a hardcoded 8 (which is what the spec says should be
+	 * done).
+	 */
+	if (wm_size <= 8)
+		wm_size = 8;
+
 	return wm_size;
 }
 
@@ -1268,33 +1305,27 @@ static bool g4x_compute_srwm(struct drm_device *dev,
 			      display, cursor);
 }
 
-static bool vlv_compute_drain_latency(struct drm_device *dev,
-				     int plane,
-				     int *plane_prec_mult,
-				     int *plane_dl,
-				     int *cursor_prec_mult,
-				     int *cursor_dl)
+static bool vlv_compute_drain_latency(struct drm_crtc *crtc,
+				      int pixel_size,
+				      int *prec_mult,
+				      int *drain_latency)
 {
-	struct drm_crtc *crtc;
-	int clock, pixel_size;
 	int entries;
+	int clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
 
-	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (!intel_crtc_active(crtc))
+	if (WARN(clock == 0, "Pixel clock is zero!\n"))
 		return false;
 
-	clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
-	pixel_size = crtc->primary->fb->bits_per_pixel / 8;	/* BPP */
+	if (WARN(pixel_size == 0, "Pixel size is zero!\n"))
+		return false;
 
-	entries = (clock / 1000) * pixel_size;
-	*plane_prec_mult = (entries > 128) ?
-		DRAIN_LATENCY_PRECISION_64 : DRAIN_LATENCY_PRECISION_32;
-	*plane_dl = (64 * (*plane_prec_mult) * 4) / entries;
+	entries = DIV_ROUND_UP(clock, 1000) * pixel_size;
+	*prec_mult = (entries > 128) ? DRAIN_LATENCY_PRECISION_64 :
+				       DRAIN_LATENCY_PRECISION_32;
+	*drain_latency = (64 * (*prec_mult) * 4) / entries;
 
-	entries = (clock / 1000) * 4;	/* BPP is always 4 for cursor */
-	*cursor_prec_mult = (entries > 128) ?
-		DRAIN_LATENCY_PRECISION_64 : DRAIN_LATENCY_PRECISION_32;
-	*cursor_dl = (64 * (*cursor_prec_mult) * 4) / entries;
+	if (*drain_latency > DRAIN_LATENCY_MASK)
+		*drain_latency = DRAIN_LATENCY_MASK;
 
 	return true;
 }
@@ -1307,39 +1338,48 @@ static bool vlv_compute_drain_latency(struct drm_device *dev,
  * latency value.
  */
 
-static void vlv_update_drain_latency(struct drm_device *dev)
+static void vlv_update_drain_latency(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int planea_prec, planea_dl, planeb_prec, planeb_dl;
-	int cursora_prec, cursora_dl, cursorb_prec, cursorb_dl;
-	int plane_prec_mult, cursor_prec_mult; /* Precision multiplier is
-							either 16 or 32 */
+	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pixel_size;
+	int drain_latency;
+	enum pipe pipe = intel_crtc->pipe;
+	int plane_prec, prec_mult, plane_dl;
+
+	plane_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_PLANE_PRECISION_64 |
+		   DRAIN_LATENCY_MASK | DDL_CURSOR_PRECISION_64 |
+		   (DRAIN_LATENCY_MASK << DDL_CURSOR_SHIFT));
 
-	/* For plane A, Cursor A */
-	if (vlv_compute_drain_latency(dev, 0, &plane_prec_mult, &planea_dl,
-				      &cursor_prec_mult, &cursora_dl)) {
-		cursora_prec = (cursor_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_CURSORA_PRECISION_32 : DDL_CURSORA_PRECISION_64;
-		planea_prec = (plane_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_PLANEA_PRECISION_32 : DDL_PLANEA_PRECISION_64;
+	if (!intel_crtc_active(crtc)) {
+		I915_WRITE(VLV_DDL(pipe), plane_dl);
+		return;
+	}
 
-		I915_WRITE(VLV_DDL1, cursora_prec |
-				(cursora_dl << DDL_CURSORA_SHIFT) |
-				planea_prec | planea_dl);
+	/* Primary plane Drain Latency */
+	pixel_size = crtc->primary->fb->bits_per_pixel / 8;	/* BPP */
+	if (vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_PLANE_PRECISION_64 :
+					   DDL_PLANE_PRECISION_32;
+		plane_dl |= plane_prec | drain_latency;
 	}
 
-	/* For plane B, Cursor B */
-	if (vlv_compute_drain_latency(dev, 1, &plane_prec_mult, &planeb_dl,
-				      &cursor_prec_mult, &cursorb_dl)) {
-		cursorb_prec = (cursor_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_CURSORB_PRECISION_32 : DDL_CURSORB_PRECISION_64;
-		planeb_prec = (plane_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_PLANEB_PRECISION_32 : DDL_PLANEB_PRECISION_64;
+	/* Cursor Drain Latency
+	 * BPP is always 4 for cursor
+	 */
+	pixel_size = 4;
 
-		I915_WRITE(VLV_DDL2, cursorb_prec |
-				(cursorb_dl << DDL_CURSORB_SHIFT) |
-				planeb_prec | planeb_dl);
+	/* Program cursor DL only if it is enabled */
+	if (intel_crtc->cursor_base &&
+	    vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_CURSOR_PRECISION_64 :
+					   DDL_CURSOR_PRECISION_32;
+		plane_dl |= plane_prec | (drain_latency << DDL_CURSOR_SHIFT);
 	}
+
+	I915_WRITE(VLV_DDL(pipe), plane_dl);
 }
 
 #define single_plane_enabled(mask) is_power_of_2(mask)
@@ -1355,20 +1395,92 @@ static void valleyview_update_wm(struct drm_crtc *crtc)
 	unsigned int enabled = 0;
 	bool cxsr_enabled;
 
-	vlv_update_drain_latency(dev);
+	vlv_update_drain_latency(crtc);
+
+	if (g4x_compute_wm0(dev, PIPE_A,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planea_wm, &cursora_wm))
+		enabled |= 1 << PIPE_A;
+
+	if (g4x_compute_wm0(dev, PIPE_B,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planeb_wm, &cursorb_wm))
+		enabled |= 1 << PIPE_B;
+
+	if (single_plane_enabled(enabled) &&
+	    g4x_compute_srwm(dev, ffs(enabled) - 1,
+			     sr_latency_ns,
+			     &valleyview_wm_info,
+			     &valleyview_cursor_wm_info,
+			     &plane_sr, &ignore_cursor_sr) &&
+	    g4x_compute_srwm(dev, ffs(enabled) - 1,
+			     2*sr_latency_ns,
+			     &valleyview_wm_info,
+			     &valleyview_cursor_wm_info,
+			     &ignore_plane_sr, &cursor_sr)) {
+		cxsr_enabled = true;
+	} else {
+		cxsr_enabled = false;
+		intel_set_memory_cxsr(dev_priv, false);
+		plane_sr = cursor_sr = 0;
+	}
+
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+		      planea_wm, cursora_wm,
+		      planeb_wm, cursorb_wm,
+		      plane_sr, cursor_sr);
+
+	I915_WRITE(DSPFW1,
+		   (plane_sr << DSPFW_SR_SHIFT) |
+		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
+		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
+	I915_WRITE(DSPFW2,
+		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
+		   (cursora_wm << DSPFW_CURSORA_SHIFT));
+	I915_WRITE(DSPFW3,
+		   (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) |
+		   (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
+
+	if (cxsr_enabled)
+		intel_set_memory_cxsr(dev_priv, true);
+}
+
+static void cherryview_update_wm(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	static const int sr_latency_ns = 12000;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int planea_wm, planeb_wm, planec_wm;
+	int cursora_wm, cursorb_wm, cursorc_wm;
+	int plane_sr, cursor_sr;
+	int ignore_plane_sr, ignore_cursor_sr;
+	unsigned int enabled = 0;
+	bool cxsr_enabled;
+
+	vlv_update_drain_latency(crtc);
 
 	if (g4x_compute_wm0(dev, PIPE_A,
-			    &valleyview_wm_info, latency_ns,
-			    &valleyview_cursor_wm_info, latency_ns,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
 			    &planea_wm, &cursora_wm))
 		enabled |= 1 << PIPE_A;
 
 	if (g4x_compute_wm0(dev, PIPE_B,
-			    &valleyview_wm_info, latency_ns,
-			    &valleyview_cursor_wm_info, latency_ns,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 1 << PIPE_B;
 
+	if (g4x_compute_wm0(dev, PIPE_C,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planec_wm, &cursorc_wm))
+		enabled |= 1 << PIPE_C;
+
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
 			     sr_latency_ns,
@@ -1387,27 +1499,66 @@ static void valleyview_update_wm(struct drm_crtc *crtc)
 		plane_sr = cursor_sr = 0;
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, C: plane=%d, cursor=%d, "
+		      "SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
 		      planeb_wm, cursorb_wm,
+		      planec_wm, cursorc_wm,
 		      plane_sr, cursor_sr);
 
 	I915_WRITE(DSPFW1,
 		   (plane_sr << DSPFW_SR_SHIFT) |
 		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
 		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
-		   planea_wm);
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
 	I915_WRITE(DSPFW2,
 		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
 		   (cursora_wm << DSPFW_CURSORA_SHIFT));
 	I915_WRITE(DSPFW3,
 		   (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) |
 		   (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
+	I915_WRITE(DSPFW9_CHV,
+		   (I915_READ(DSPFW9_CHV) & ~(DSPFW_PLANEC_MASK |
+					      DSPFW_CURSORC_MASK)) |
+		   (planec_wm << DSPFW_PLANEC_SHIFT) |
+		   (cursorc_wm << DSPFW_CURSORC_SHIFT));
 
 	if (cxsr_enabled)
 		intel_set_memory_cxsr(dev_priv, true);
 }
 
+static void valleyview_update_sprite_wm(struct drm_plane *plane,
+					struct drm_crtc *crtc,
+					uint32_t sprite_width,
+					uint32_t sprite_height,
+					int pixel_size,
+					bool enabled, bool scaled)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = to_intel_plane(plane)->pipe;
+	int sprite = to_intel_plane(plane)->plane;
+	int drain_latency;
+	int plane_prec;
+	int sprite_dl;
+	int prec_mult;
+
+	sprite_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_SPRITE_PRECISION_64(sprite) |
+		    (DRAIN_LATENCY_MASK << DDL_SPRITE_SHIFT(sprite)));
+
+	if (enabled && vlv_compute_drain_latency(crtc, pixel_size, &prec_mult,
+						 &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_SPRITE_PRECISION_64(sprite) :
+					   DDL_SPRITE_PRECISION_32(sprite);
+		sprite_dl |= plane_prec |
+			     (drain_latency << DDL_SPRITE_SHIFT(sprite));
+	}
+
+	I915_WRITE(VLV_DDL(pipe), sprite_dl);
+}
+
 static void g4x_update_wm(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -1419,14 +1570,14 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 	bool cxsr_enabled;
 
 	if (g4x_compute_wm0(dev, PIPE_A,
-			    &g4x_wm_info, latency_ns,
-			    &g4x_cursor_wm_info, latency_ns,
+			    &g4x_wm_info, pessimal_latency_ns,
+			    &g4x_cursor_wm_info, pessimal_latency_ns,
 			    &planea_wm, &cursora_wm))
 		enabled |= 1 << PIPE_A;
 
 	if (g4x_compute_wm0(dev, PIPE_B,
-			    &g4x_wm_info, latency_ns,
-			    &g4x_cursor_wm_info, latency_ns,
+			    &g4x_wm_info, pessimal_latency_ns,
+			    &g4x_cursor_wm_info, pessimal_latency_ns,
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 1 << PIPE_B;
 
@@ -1443,7 +1594,8 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 		plane_sr = cursor_sr = 0;
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
 		      planeb_wm, cursorb_wm,
 		      plane_sr, cursor_sr);
@@ -1452,7 +1604,7 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 		   (plane_sr << DSPFW_SR_SHIFT) |
 		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
 		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
-		   planea_wm);
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
 	I915_WRITE(DSPFW2,
 		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
 		   (cursora_wm << DSPFW_CURSORA_SHIFT));
@@ -1526,8 +1678,11 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 
 	/* 965 has limitations... */
 	I915_WRITE(DSPFW1, (srwm << DSPFW_SR_SHIFT) |
-		   (8 << 16) | (8 << 8) | (8 << 0));
-	I915_WRITE(DSPFW2, (8 << 8) | (8 << 0));
+		   (8 << DSPFW_CURSORB_SHIFT) |
+		   (8 << DSPFW_PLANEB_SHIFT) |
+		   (8 << DSPFW_PLANEA_SHIFT));
+	I915_WRITE(DSPFW2, (8 << DSPFW_CURSORA_SHIFT) |
+		   (8 << DSPFW_PLANEC_SHIFT_OLD));
 	/* update cursor SR watermark */
 	I915_WRITE(DSPFW3, (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
 
@@ -1552,7 +1707,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	else if (!IS_GEN2(dev))
 		wm_info = &i915_wm_info;
 	else
-		wm_info = &i830_wm_info;
+		wm_info = &i830_a_wm_info;
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 0);
 	crtc = intel_get_crtc_for_plane(dev, 0);
@@ -1565,10 +1720,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 		adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
 		planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
-					       latency_ns);
+					       pessimal_latency_ns);
 		enabled = crtc;
-	} else
+	} else {
 		planea_wm = fifo_size - wm_info->guard_size;
+		if (planea_wm > (long)wm_info->max_wm)
+			planea_wm = wm_info->max_wm;
+	}
+
+	if (IS_GEN2(dev))
+		wm_info = &i830_bc_wm_info;
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 1);
 	crtc = intel_get_crtc_for_plane(dev, 1);
@@ -1581,13 +1742,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 		adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
 		planeb_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
-					       latency_ns);
+					       pessimal_latency_ns);
 		if (enabled == NULL)
 			enabled = crtc;
 		else
 			enabled = NULL;
-	} else
+	} else {
 		planeb_wm = fifo_size - wm_info->guard_size;
+		if (planeb_wm > (long)wm_info->max_wm)
+			planeb_wm = wm_info->max_wm;
+	}
 
 	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
 
@@ -1674,7 +1838,7 @@ static void i845_update_wm(struct drm_crtc *unused_crtc)
 	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev, 0),
-				       4, latency_ns);
+				       4, pessimal_latency_ns);
 	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
 	fwater_lo |= (3<<8) | planea_wm;
 
@@ -2527,7 +2691,7 @@ static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev,
 #define WM_DIRTY_FBC (1 << 24)
 #define WM_DIRTY_DDB (1 << 25)
 
-static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
+static unsigned int ilk_compute_wm_dirty(struct drm_i915_private *dev_priv,
 					 const struct ilk_wm_values *old,
 					 const struct ilk_wm_values *new)
 {
@@ -2535,7 +2699,7 @@ static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
 	enum pipe pipe;
 	int wm_lp;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		if (old->wm_linetime[pipe] != new->wm_linetime[pipe]) {
 			dirty |= WM_DIRTY_LINETIME(pipe);
 			/* Must disable LP1+ watermarks too */
@@ -2621,7 +2785,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	unsigned int dirty;
 	uint32_t val;
 
-	dirty = ilk_compute_wm_dirty(dev, previous, results);
+	dirty = ilk_compute_wm_dirty(dev_priv, previous, results);
 	if (!dirty)
 		return;
 
@@ -3327,13 +3491,18 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
 	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
-	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
-			 dev_priv->rps.cur_freq,
-			 vlv_gpu_freq(dev_priv, val), val);
+	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
+		      "Odd GPU freq value\n"))
+		val &= ~1;
+
+	if (val != dev_priv->rps.cur_freq) {
+		DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
+				 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+				 dev_priv->rps.cur_freq,
+				 vlv_gpu_freq(dev_priv, val), val);
 
-	if (val != dev_priv->rps.cur_freq)
 		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+	}
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
@@ -3406,8 +3575,14 @@ static void valleyview_disable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* we're doing forcewake before Disabling RC6,
+	 * This what the BIOS expects when going into suspend */
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+
 	gen6_disable_rps_interrupts(dev);
 }
 
@@ -3598,7 +3773,6 @@ static void gen6_enable_rps(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
 	u32 rp_state_cap;
-	u32 gt_perf_status;
 	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
@@ -3623,7 +3797,6 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
 	parse_rp_state_cap(dev_priv, rp_state_cap);
 
@@ -3965,11 +4138,27 @@ static void valleyview_cleanup_pctx(struct drm_device *dev)
 static void valleyview_init_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val;
 
 	valleyview_setup_pctx(dev);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	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);
+
 	dev_priv->rps.max_freq = valleyview_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",
@@ -4004,11 +4193,38 @@ 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;
+	u32 val;
 
 	cherryview_setup_pctx(dev);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	val = vlv_punit_read(dev_priv, CCK_FUSE_REG);
+	switch ((val >> 2) & 0x7) {
+	case 0:
+	case 1:
+		dev_priv->rps.cz_freq = 200;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 2:
+		dev_priv->rps.cz_freq = 267;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 3:
+		dev_priv->rps.cz_freq = 333;
+		dev_priv->mem_freq = 2000;
+		break;
+	case 4:
+		dev_priv->rps.cz_freq = 320;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 5:
+		dev_priv->rps.cz_freq = 400;
+		dev_priv->mem_freq = 1600;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
+
 	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",
@@ -4030,6 +4246,12 @@ static void cherryview_init_gt_powersave(struct drm_device *dev)
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
 			 dev_priv->rps.min_freq);
 
+	WARN_ONCE((dev_priv->rps.max_freq |
+		   dev_priv->rps.efficient_freq |
+		   dev_priv->rps.rp1_freq |
+		   dev_priv->rps.min_freq) & 1,
+		  "Odd GPU freq values\n");
+
 	/* 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;
@@ -5088,7 +5310,7 @@ static void g4x_disable_trickle_feed(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(DSPCNTR(pipe),
 			   I915_READ(DSPCNTR(pipe)) |
 			   DISPPLANE_TRICKLE_FEED_DISABLE);
@@ -5203,7 +5425,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 	/* The below fixes the weird display corruption, a few pixels shifted
 	 * downward, on (only) LVDS of some HP laptops with IVY.
 	 */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		val = I915_READ(TRANS_CHICKEN2(pipe));
 		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
 		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
@@ -5215,7 +5437,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 		I915_WRITE(TRANS_CHICKEN2(pipe), val);
 	}
 	/* WADP0ClockGatingDisable */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(TRANS_CHICKEN1(pipe),
 			   TRANS_CHICKEN1_DP0UNIT_GC_DISABLE);
 	}
@@ -5383,7 +5605,7 @@ static void lpt_suspend_hw(struct drm_device *dev)
 	}
 }
 
-static void gen8_init_clock_gating(struct drm_device *dev)
+static void broadwell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
@@ -5395,37 +5617,12 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	/* FIXME(BDW): Check all the w/a, some might only apply to
 	 * pre-production hw. */
 
-	/* WaDisablePartialInstShootdown:bdw */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
 
-	/* WaDisableThreadStallDopClockGating:bdw */
-	/* FIXME: Unclear whether we really need this on production bdw. */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS));
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 	I915_WRITE(GAMTARBMODE, _MASKED_BIT_ENABLE(ARB_MODE_BWGTLB_DISABLE));
 
 	I915_WRITE(_3D_CHICKEN3,
 		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(2)));
 
-	I915_WRITE(COMMON_SLICE_CHICKEN2,
-		   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
-
-	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	/* WaDisableDopClockGating:bdw May not be needed for production */
-	I915_WRITE(GEN7_ROW_CHICKEN2,
-		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -5435,37 +5632,18 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 		   I915_READ(CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
 	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(CHICKEN_PIPESL_1(pipe),
 			   I915_READ(CHICKEN_PIPESL_1(pipe)) |
 			   BDW_DPRS_MASK_VBLANK_SRD);
 	}
 
-	/* Use Force Non-Coherent whenever executing a 3D context. This is a
-	 * workaround for for a possible hang in the unlikely event a TLB
-	 * invalidation occurs during a PSD flush.
-	 */
-	I915_WRITE(HDC_CHICKEN0,
-		   I915_READ(HDC_CHICKEN0) |
-		   _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
-
 	/* WaVSRefCountFullforceMissDisable:bdw */
 	/* WaDSRefCountFullforceMissDisable:bdw */
 	I915_WRITE(GEN7_FF_THREAD_MODE,
 		   I915_READ(GEN7_FF_THREAD_MODE) &
 		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
 
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
-
 	I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
 		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
 
@@ -5473,9 +5651,7 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/* Wa4x4STCOptimizationDisable:bdw */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+	lpt_init_clock_gating(dev);
 }
 
 static void haswell_init_clock_gating(struct drm_device *dev)
@@ -5631,24 +5807,6 @@ 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:
-	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);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
@@ -5724,48 +5882,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 static void cherryview_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, CCK_FUSE_REG);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-	switch ((val >> 2) & 0x7) {
-	case 0:
-	case 1:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_200;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 2:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_267;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 3:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_333;
-			dev_priv->mem_freq = 2000;
-			break;
-	case 4:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_320;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 5:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_400;
-			dev_priv->mem_freq = 1600;
-			break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
 	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 
-	/* WaDisablePartialInstShootdown:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
-
-	/* WaDisableThreadStallDopClockGating:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
 	I915_WRITE(GEN7_FF_THREAD_MODE,
@@ -5784,10 +5905,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
-
 	/* WaDisableGunitClockGating:chv (pre-production hw) */
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) |
 		   GINT_DIS);
@@ -5797,8 +5914,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 		   _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE));
 
 	/* WaDisableDopClockGating:chv (pre-production hw) */
-	I915_WRITE(GEN7_ROW_CHICKEN2,
-		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 	I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 		   GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
 }
@@ -5883,6 +5998,9 @@ static void gen3_init_clock_gating(struct drm_device *dev)
 
 	/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
 	I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
+
+	I915_WRITE(MI_ARB_STATE,
+		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void i85x_init_clock_gating(struct drm_device *dev)
@@ -5894,6 +6012,9 @@ static void i85x_init_clock_gating(struct drm_device *dev)
 	/* interrupts should cause a wake up from C3 */
 	I915_WRITE(MI_STATE, _MASKED_BIT_ENABLE(MI_AGPBUSY_INT_EN) |
 		   _MASKED_BIT_DISABLE(MI_AGPBUSY_830_MODE));
+
+	I915_WRITE(MEM_MODE,
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void i830_init_clock_gating(struct drm_device *dev)
@@ -5901,6 +6022,10 @@ static void i830_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	I915_WRITE(DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
+
+	I915_WRITE(MEM_MODE,
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_A_TRICKLE_FEED_DISABLE) |
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_B_TRICKLE_FEED_DISABLE));
 }
 
 void intel_init_clock_gating(struct drm_device *dev)
@@ -6203,6 +6328,8 @@ static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	vlv_set_power_well(dev_priv, power_well, false);
+
+	vlv_power_sequencer_reset(dev_priv);
 }
 
 static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
@@ -6238,12 +6365,11 @@ static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
 static void vlv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
 					    struct i915_power_well *power_well)
 {
-	struct drm_device *dev = dev_priv->dev;
 	enum pipe pipe;
 
 	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC);
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		assert_pll_disabled(dev_priv, pipe);
 
 	/* Assert common reset */
@@ -6252,6 +6378,153 @@ static void vlv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
 	vlv_set_power_well(dev_priv, power_well, false);
 }
 
+static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
+					   struct i915_power_well *power_well)
+{
+	enum dpio_phy phy;
+
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC &&
+		     power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D);
+
+	/*
+	 * Enable the CRI clock source so we can get at the
+	 * display and the reference clock for VGA
+	 * hotplug / manual detection.
+	 */
+	if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+		phy = DPIO_PHY0;
+		I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+			   DPLL_REFA_CLK_ENABLE_VLV);
+		I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+			   DPLL_REFA_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
+	} else {
+		phy = DPIO_PHY1;
+		I915_WRITE(DPLL(PIPE_C), I915_READ(DPLL(PIPE_C)) |
+			   DPLL_REFA_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
+	}
+	udelay(1); /* >10ns for cmnreset, >0ns for sidereset */
+	vlv_set_power_well(dev_priv, power_well, true);
+
+	/* Poll for phypwrgood signal */
+	if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & PHY_POWERGOOD(phy), 1))
+		DRM_ERROR("Display PHY %d is not power up\n", phy);
+
+	I915_WRITE(DISPLAY_PHY_CONTROL, I915_READ(DISPLAY_PHY_CONTROL) |
+		   PHY_COM_LANE_RESET_DEASSERT(phy));
+}
+
+static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
+					    struct i915_power_well *power_well)
+{
+	enum dpio_phy phy;
+
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC &&
+		     power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D);
+
+	if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+		phy = DPIO_PHY0;
+		assert_pll_disabled(dev_priv, PIPE_A);
+		assert_pll_disabled(dev_priv, PIPE_B);
+	} else {
+		phy = DPIO_PHY1;
+		assert_pll_disabled(dev_priv, PIPE_C);
+	}
+
+	I915_WRITE(DISPLAY_PHY_CONTROL, I915_READ(DISPLAY_PHY_CONTROL) &
+		   ~PHY_COM_LANE_RESET_DEASSERT(phy));
+
+	vlv_set_power_well(dev_priv, power_well, false);
+}
+
+static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	enum pipe pipe = power_well->data;
+	bool enabled;
+	u32 state, ctrl;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	state = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSS_MASK(pipe);
+	/*
+	 * We only ever set the power-on and power-gate states, anything
+	 * else is unexpected.
+	 */
+	WARN_ON(state != DP_SSS_PWR_ON(pipe) && state != DP_SSS_PWR_GATE(pipe));
+	enabled = state == DP_SSS_PWR_ON(pipe);
+
+	/*
+	 * A transient state at this point would mean some unexpected party
+	 * is poking at the power controls too.
+	 */
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSC_MASK(pipe);
+	WARN_ON(ctrl << 16 != state);
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	return enabled;
+}
+
+static void chv_set_pipe_power_well(struct drm_i915_private *dev_priv,
+				    struct i915_power_well *power_well,
+				    bool enable)
+{
+	enum pipe pipe = power_well->data;
+	u32 state;
+	u32 ctrl;
+
+	state = enable ? DP_SSS_PWR_ON(pipe) : DP_SSS_PWR_GATE(pipe);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+#define COND \
+	((vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSS_MASK(pipe)) == state)
+
+	if (COND)
+		goto out;
+
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+	ctrl &= ~DP_SSC_MASK(pipe);
+	ctrl |= enable ? DP_SSC_PWR_ON(pipe) : DP_SSC_PWR_GATE(pipe);
+	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, ctrl);
+
+	if (wait_for(COND, 100))
+		DRM_ERROR("timout setting power well state %08x (%08x)\n",
+			  state,
+			  vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ));
+
+#undef COND
+
+out:
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void chv_pipe_power_well_sync_hw(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	chv_set_pipe_power_well(dev_priv, power_well, power_well->count > 0);
+}
+
+static void chv_pipe_power_well_enable(struct drm_i915_private *dev_priv,
+				       struct i915_power_well *power_well)
+{
+	WARN_ON_ONCE(power_well->data != PIPE_A &&
+		     power_well->data != PIPE_B &&
+		     power_well->data != PIPE_C);
+
+	chv_set_pipe_power_well(dev_priv, power_well, true);
+}
+
+static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	WARN_ON_ONCE(power_well->data != PIPE_A &&
+		     power_well->data != PIPE_B &&
+		     power_well->data != PIPE_C);
+
+	chv_set_pipe_power_well(dev_priv, power_well, false);
+}
+
 static void check_power_well_state(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
@@ -6443,6 +6716,39 @@ EXPORT_SYMBOL_GPL(i915_get_cdclk_freq);
 	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
 	BIT(POWER_DOMAIN_INIT))
 
+#define CHV_PIPE_A_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_A) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_PIPE_B_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_B) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_PIPE_C_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_C) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_CMN_BC_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_CMN_D_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_always_on_power_well_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -6450,6 +6756,20 @@ static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.is_enabled = i9xx_always_on_power_well_enabled,
 };
 
+static const struct i915_power_well_ops chv_pipe_power_well_ops = {
+	.sync_hw = chv_pipe_power_well_sync_hw,
+	.enable = chv_pipe_power_well_enable,
+	.disable = chv_pipe_power_well_disable,
+	.is_enabled = chv_pipe_power_well_enabled,
+};
+
+static const struct i915_power_well_ops chv_dpio_cmn_power_well_ops = {
+	.sync_hw = vlv_power_well_sync_hw,
+	.enable = chv_dpio_cmn_power_well_enable,
+	.disable = chv_dpio_cmn_power_well_disable,
+	.is_enabled = vlv_power_well_enabled,
+};
+
 static struct i915_power_well i9xx_always_on_power_well[] = {
 	{
 		.name = "always-on",
@@ -6572,6 +6892,107 @@ static struct i915_power_well vlv_power_wells[] = {
 	},
 };
 
+static struct i915_power_well chv_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = VLV_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
+	},
+#if 0
+	{
+		.name = "display",
+		.domains = VLV_DISPLAY_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DISP2D,
+		.ops = &vlv_display_power_well_ops,
+	},
+	{
+		.name = "pipe-a",
+		.domains = CHV_PIPE_A_POWER_DOMAINS,
+		.data = PIPE_A,
+		.ops = &chv_pipe_power_well_ops,
+	},
+	{
+		.name = "pipe-b",
+		.domains = CHV_PIPE_B_POWER_DOMAINS,
+		.data = PIPE_B,
+		.ops = &chv_pipe_power_well_ops,
+	},
+	{
+		.name = "pipe-c",
+		.domains = CHV_PIPE_C_POWER_DOMAINS,
+		.data = PIPE_C,
+		.ops = &chv_pipe_power_well_ops,
+	},
+#endif
+	{
+		.name = "dpio-common-bc",
+		/*
+		 * XXX: cmnreset for one PHY seems to disturb the other.
+		 * As a workaround keep both powered on at the same
+		 * time for now.
+		 */
+		.domains = CHV_DPIO_CMN_BC_POWER_DOMAINS | CHV_DPIO_CMN_D_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_BC,
+		.ops = &chv_dpio_cmn_power_well_ops,
+	},
+	{
+		.name = "dpio-common-d",
+		/*
+		 * XXX: cmnreset for one PHY seems to disturb the other.
+		 * As a workaround keep both powered on at the same
+		 * time for now.
+		 */
+		.domains = CHV_DPIO_CMN_BC_POWER_DOMAINS | CHV_DPIO_CMN_D_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_D,
+		.ops = &chv_dpio_cmn_power_well_ops,
+	},
+#if 0
+	{
+		.name = "dpio-tx-b-01",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_01,
+	},
+	{
+		.name = "dpio-tx-b-23",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_23,
+	},
+	{
+		.name = "dpio-tx-c-01",
+		.domains = VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_01,
+	},
+	{
+		.name = "dpio-tx-c-23",
+		.domains = VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23,
+	},
+	{
+		.name = "dpio-tx-d-01",
+		.domains = CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS |
+			   CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_D_LANES_01,
+	},
+	{
+		.name = "dpio-tx-d-23",
+		.domains = CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS |
+			   CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_D_LANES_23,
+	},
+#endif
+};
+
 static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv,
 						 enum punit_power_well power_well_id)
 {
@@ -6608,6 +7029,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
 		hsw_pwr = power_domains;
+	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
+		set_power_wells(power_domains, chv_power_wells);
 	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
 		set_power_wells(power_domains, vlv_power_wells);
 	} else {
@@ -6833,13 +7256,15 @@ void intel_init_pm(struct drm_device *dev)
 		else if (IS_HASWELL(dev))
 			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
 		else if (INTEL_INFO(dev)->gen == 8)
-			dev_priv->display.init_clock_gating = gen8_init_clock_gating;
+			dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
 	} else if (IS_CHERRYVIEW(dev)) {
-		dev_priv->display.update_wm = valleyview_update_wm;
+		dev_priv->display.update_wm = cherryview_update_wm;
+		dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm;
 		dev_priv->display.init_clock_gating =
 			cherryview_init_clock_gating;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.update_wm = valleyview_update_wm;
+		dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm;
 		dev_priv->display.init_clock_gating =
 			valleyview_init_clock_gating;
 	} else if (IS_PINEVIEW(dev)) {
@@ -7025,6 +7450,7 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 		return -1;
 	}
 
+	/* CHV needs even values */
 	opcode = (DIV_ROUND_CLOSEST((val * 2 * mul), dev_priv->rps.cz_freq) * 2);
 
 	return opcode;