Merge tag 'v4.15-rc1' into next-seccomp

Linux 4.15-rc1

1 files changed, 872 insertions, 587 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 48ea0fca1f72..f4a4e9496893 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -58,6 +58,19 @@
 
 static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	if (HAS_LLC(dev_priv)) {
+		/*
+		 * WaCompressedResourceDisplayNewHashMode:skl,kbl
+		 * Display WA#0390: skl,kbl
+		 *
+		 * Must match Sampler, Pixel Back End, and Media. See
+		 * WaCompressedResourceSamplerPbeMediaNewHashMode.
+		 */
+		I915_WRITE(CHICKEN_PAR1_1,
+			   I915_READ(CHICKEN_PAR1_1) |
+			   SKL_DE_COMPRESSED_HASH_MODE);
+	}
+
 	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
 	I915_WRITE(CHICKEN_PAR1_1,
 		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
@@ -78,6 +91,12 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl,cfl */
 	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
 		   ILK_DPFC_DISABLE_DUMMY0);
+
+	if (IS_SKYLAKE(dev_priv)) {
+		/* WaDisableDopClockGating */
+		I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL)
+			   & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+	}
 }
 
 static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -105,6 +124,7 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	u32 val;
 	gen9_init_clock_gating(dev_priv);
 
 	/*
@@ -124,6 +144,11 @@ static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
 		I915_WRITE(CHICKEN_MISC_2, val);
 	}
 
+	/* Display WA #1133: WaFbcSkipSegments:glk */
+	val = I915_READ(ILK_DPFC_CHICKEN);
+	val &= ~GLK_SKIP_SEG_COUNT_MASK;
+	val |= GLK_SKIP_SEG_EN | GLK_SKIP_SEG_COUNT(1);
+	I915_WRITE(ILK_DPFC_CHICKEN, val);
 }
 
 static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
@@ -297,7 +322,7 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 {
 	u32 val;
 
-	mutex_lock(&dev_priv->rps.hw_lock);
+	mutex_lock(&dev_priv->pcu_lock);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
 	if (enable)
@@ -312,14 +337,14 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 		      FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
 		DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");
 
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
 {
 	u32 val;
 
-	mutex_lock(&dev_priv->rps.hw_lock);
+	mutex_lock(&dev_priv->pcu_lock);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
 	if (enable)
@@ -328,7 +353,7 @@ static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
 		val &= ~DSP_MAXFIFO_PM5_ENABLE;
 	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val);
 
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 #define FW_WM(value, plane) \
@@ -1302,21 +1327,21 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	int num_active_planes = hweight32(crtc_state->active_planes &
 					  ~BIT(PLANE_CURSOR));
 	const struct g4x_pipe_wm *raw;
-	struct intel_plane_state *plane_state;
+	const struct intel_plane_state *old_plane_state;
+	const struct intel_plane_state *new_plane_state;
 	struct intel_plane *plane;
 	enum plane_id plane_id;
 	int i, level;
 	unsigned int dirty = 0;
 
-	for_each_intel_plane_in_state(state, plane, plane_state, i) {
-		const struct intel_plane_state *old_plane_state =
-			to_intel_plane_state(plane->base.state);
-
-		if (plane_state->base.crtc != &crtc->base &&
+	for_each_oldnew_intel_plane_in_state(state, plane,
+					     old_plane_state,
+					     new_plane_state, i) {
+		if (new_plane_state->base.crtc != &crtc->base &&
 		    old_plane_state->base.crtc != &crtc->base)
 			continue;
 
-		if (g4x_raw_plane_wm_compute(crtc_state, plane_state))
+		if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
 			dirty |= BIT(plane->id);
 	}
 
@@ -1811,21 +1836,21 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	int num_active_planes = hweight32(crtc_state->active_planes &
 					  ~BIT(PLANE_CURSOR));
 	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
-	struct intel_plane_state *plane_state;
+	const struct intel_plane_state *old_plane_state;
+	const struct intel_plane_state *new_plane_state;
 	struct intel_plane *plane;
 	enum plane_id plane_id;
 	int level, ret, i;
 	unsigned int dirty = 0;
 
-	for_each_intel_plane_in_state(state, plane, plane_state, i) {
-		const struct intel_plane_state *old_plane_state =
-			to_intel_plane_state(plane->base.state);
-
-		if (plane_state->base.crtc != &crtc->base &&
+	for_each_oldnew_intel_plane_in_state(state, plane,
+					     old_plane_state,
+					     new_plane_state, i) {
+		if (new_plane_state->base.crtc != &crtc->base &&
 		    old_plane_state->base.crtc != &crtc->base)
 			continue;
 
-		if (vlv_raw_plane_wm_compute(crtc_state, plane_state))
+		if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
 			dirty |= BIT(plane->id);
 	}
 
@@ -1844,7 +1869,7 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	/* cursor changes don't warrant a FIFO recompute */
 	if (dirty & ~BIT(PLANE_CURSOR)) {
 		const struct intel_crtc_state *old_crtc_state =
-			to_intel_crtc_state(crtc->base.state);
+			intel_atomic_get_old_crtc_state(state, crtc);
 		const struct vlv_fifo_state *old_fifo_state =
 			&old_crtc_state->wm.vlv.fifo_state;
 
@@ -2696,9 +2721,9 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
 				 const struct intel_crtc *intel_crtc,
 				 int level,
 				 struct intel_crtc_state *cstate,
-				 struct intel_plane_state *pristate,
-				 struct intel_plane_state *sprstate,
-				 struct intel_plane_state *curstate,
+				 const struct intel_plane_state *pristate,
+				 const struct intel_plane_state *sprstate,
+				 const struct intel_plane_state *curstate,
 				 struct intel_wm_level *result)
 {
 	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
@@ -2758,18 +2783,18 @@ hsw_compute_linetime_wm(const struct intel_crtc_state *cstate)
 static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 				  uint16_t wm[8])
 {
-	if (IS_GEN9(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		uint32_t val;
 		int ret, i;
 		int level, max_level = ilk_wm_max_level(dev_priv);
 
 		/* read the first set of memory latencies[0:3] */
 		val = 0; /* data0 to be programmed to 0 for first set */
-		mutex_lock(&dev_priv->rps.hw_lock);
+		mutex_lock(&dev_priv->pcu_lock);
 		ret = sandybridge_pcode_read(dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val);
-		mutex_unlock(&dev_priv->rps.hw_lock);
+		mutex_unlock(&dev_priv->pcu_lock);
 
 		if (ret) {
 			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
@@ -2786,11 +2811,11 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 
 		/* read the second set of memory latencies[4:7] */
 		val = 1; /* data0 to be programmed to 1 for second set */
-		mutex_lock(&dev_priv->rps.hw_lock);
+		mutex_lock(&dev_priv->pcu_lock);
 		ret = sandybridge_pcode_read(dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val);
-		mutex_unlock(&dev_priv->rps.hw_lock);
+		mutex_unlock(&dev_priv->pcu_lock);
 		if (ret) {
 			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
 			return;
@@ -2818,7 +2843,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 		}
 
 		/*
-		 * WaWmMemoryReadLatency:skl,glk
+		 * WaWmMemoryReadLatency:skl+,glk
 		 *
 		 * punit doesn't take into account the read latency so we need
 		 * to add 2us to the various latency levels we retrieve from the
@@ -2857,6 +2882,8 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 		wm[0] = 7;
 		wm[1] = (mltr >> MLTR_WM1_SHIFT) & ILK_SRLT_MASK;
 		wm[2] = (mltr >> MLTR_WM2_SHIFT) & ILK_SRLT_MASK;
+	} else {
+		MISSING_CASE(INTEL_DEVID(dev_priv));
 	}
 }
 
@@ -2912,7 +2939,7 @@ static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 		 * - latencies are in us on gen9.
 		 * - before then, WM1+ latency values are in 0.5us units
 		 */
-		if (IS_GEN9(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 9)
 			latency *= 10;
 		else if (level > 0)
 			latency *= 5;
@@ -3016,28 +3043,24 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	struct intel_pipe_wm *pipe_wm;
 	struct drm_device *dev = state->dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_plane *intel_plane;
-	struct intel_plane_state *pristate = NULL;
-	struct intel_plane_state *sprstate = NULL;
-	struct intel_plane_state *curstate = NULL;
+	struct drm_plane *plane;
+	const struct drm_plane_state *plane_state;
+	const struct intel_plane_state *pristate = NULL;
+	const struct intel_plane_state *sprstate = NULL;
+	const struct intel_plane_state *curstate = NULL;
 	int level, max_level = ilk_wm_max_level(dev_priv), usable_level;
 	struct ilk_wm_maximums max;
 
 	pipe_wm = &cstate->wm.ilk.optimal;
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct intel_plane_state *ps;
+	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, &cstate->base) {
+		const struct intel_plane_state *ps = to_intel_plane_state(plane_state);
 
-		ps = intel_atomic_get_existing_plane_state(state,
-							   intel_plane);
-		if (!ps)
-			continue;
-
-		if (intel_plane->base.type == DRM_PLANE_TYPE_PRIMARY)
+		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			pristate = ps;
-		else if (intel_plane->base.type == DRM_PLANE_TYPE_OVERLAY)
+		else if (plane->type == DRM_PLANE_TYPE_OVERLAY)
 			sprstate = ps;
-		else if (intel_plane->base.type == DRM_PLANE_TYPE_CURSOR)
+		else if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			curstate = ps;
 	}
 
@@ -3059,11 +3082,9 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	if (pipe_wm->sprites_scaled)
 		usable_level = 0;
 
-	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
-			     pristate, sprstate, curstate, &pipe_wm->raw_wm[0]);
-
 	memset(&pipe_wm->wm, 0, sizeof(pipe_wm->wm));
-	pipe_wm->wm[0] = pipe_wm->raw_wm[0];
+	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
+			     pristate, sprstate, curstate, &pipe_wm->wm[0]);
 
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		pipe_wm->linetime = hsw_compute_linetime_wm(cstate);
@@ -3073,8 +3094,8 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 
 	ilk_compute_wm_reg_maximums(dev_priv, 1, &max);
 
-	for (level = 1; level <= max_level; level++) {
-		struct intel_wm_level *wm = &pipe_wm->raw_wm[level];
+	for (level = 1; level <= usable_level; level++) {
+		struct intel_wm_level *wm = &pipe_wm->wm[level];
 
 		ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate,
 				     pristate, sprstate, curstate, wm);
@@ -3084,13 +3105,10 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 		 * register maximums since such watermarks are
 		 * always invalid.
 		 */
-		if (level > usable_level)
-			continue;
-
-		if (ilk_validate_wm_level(level, &max, wm))
-			pipe_wm->wm[level] = *wm;
-		else
-			usable_level = level;
+		if (!ilk_validate_wm_level(level, &max, wm)) {
+			memset(wm, 0, sizeof(*wm));
+			break;
+		}
 	}
 
 	return 0;
@@ -3106,7 +3124,11 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev,
 				       struct intel_crtc_state *newstate)
 {
 	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
-	struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk;
+	struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(newstate->base.state);
+	const struct intel_crtc_state *oldstate =
+		intel_atomic_get_old_crtc_state(intel_state, intel_crtc);
+	const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal;
 	int level, max_level = ilk_wm_max_level(to_i915(dev));
 
 	/*
@@ -3115,6 +3137,9 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev,
 	 * and after the vblank.
 	 */
 	*a = newstate->wm.ilk.optimal;
+	if (!newstate->base.active || drm_atomic_crtc_needs_modeset(&newstate->base))
+		return 0;
+
 	a->pipe_enabled |= b->pipe_enabled;
 	a->sprites_enabled |= b->sprites_enabled;
 	a->sprites_scaled |= b->sprites_scaled;
@@ -3530,8 +3555,6 @@ bool ilk_disable_lp_wm(struct drm_device *dev)
 	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
 }
 
-#define SKL_SAGV_BLOCK_TIME	30 /* µs */
-
 /*
  * FIXME: We still don't have the proper code detect if we need to apply the WA,
  * so assume we'll always need it in order to avoid underruns.
@@ -3549,7 +3572,8 @@ static bool skl_needs_memory_bw_wa(struct intel_atomic_state *state)
 static bool
 intel_has_sagv(struct drm_i915_private *dev_priv)
 {
-	if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv))
+	if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
+	    IS_CANNONLAKE(dev_priv))
 		return true;
 
 	if (IS_SKYLAKE(dev_priv) &&
@@ -3582,13 +3606,13 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 		return 0;
 
 	DRM_DEBUG_KMS("Enabling the SAGV\n");
-	mutex_lock(&dev_priv->rps.hw_lock);
+	mutex_lock(&dev_priv->pcu_lock);
 
 	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				      GEN9_SAGV_ENABLE);
 
 	/* We don't need to wait for the SAGV when enabling */
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 
 	/*
 	 * Some skl systems, pre-release machines in particular,
@@ -3619,14 +3643,14 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 		return 0;
 
 	DRM_DEBUG_KMS("Disabling the SAGV\n");
-	mutex_lock(&dev_priv->rps.hw_lock);
+	mutex_lock(&dev_priv->pcu_lock);
 
 	/* bspec says to keep retrying for at least 1 ms */
 	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				GEN9_SAGV_DISABLE,
 				GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
 				1);
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 
 	/*
 	 * Some skl systems, pre-release machines in particular,
@@ -3655,12 +3679,13 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state)
 	struct intel_crtc_state *cstate;
 	enum pipe pipe;
 	int level, latency;
+	int sagv_block_time_us = IS_GEN9(dev_priv) ? 30 : 20;
 
 	if (!intel_has_sagv(dev_priv))
 		return false;
 
 	/*
-	 * SKL workaround: bspec recommends we disable the SAGV when we have
+	 * SKL+ workaround: bspec recommends we disable the SAGV when we have
 	 * more then one pipe enabled
 	 *
 	 * If there are no active CRTCs, no additional checks need be performed
@@ -3699,11 +3724,11 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state)
 			latency += 15;
 
 		/*
-		 * If any of the planes on this pipe don't enable wm levels
-		 * that incur memory latencies higher then 30µs we can't enable
-		 * the SAGV
+		 * If any of the planes on this pipe don't enable wm levels that
+		 * incur memory latencies higher than sagv_block_time_us we
+		 * can't enable the SAGV.
 		 */
-		if (latency < SKL_SAGV_BLOCK_TIME)
+		if (latency < sagv_block_time_us)
 			return false;
 	}
 
@@ -3837,7 +3862,7 @@ skl_plane_downscale_amount(const struct intel_crtc_state *cstate,
 	uint_fixed_16_16_t downscale_h, downscale_w;
 
 	if (WARN_ON(!intel_wm_plane_visible(cstate, pstate)))
-		return u32_to_fixed_16_16(0);
+		return u32_to_fixed16(0);
 
 	/* n.b., src is 16.16 fixed point, dst is whole integer */
 	if (plane->id == PLANE_CURSOR) {
@@ -3861,10 +3886,10 @@ skl_plane_downscale_amount(const struct intel_crtc_state *cstate,
 		dst_h = drm_rect_height(&pstate->base.dst);
 	}
 
-	fp_w_ratio = fixed_16_16_div(src_w, dst_w);
-	fp_h_ratio = fixed_16_16_div(src_h, dst_h);
-	downscale_w = max_fixed_16_16(fp_w_ratio, u32_to_fixed_16_16(1));
-	downscale_h = max_fixed_16_16(fp_h_ratio, u32_to_fixed_16_16(1));
+	fp_w_ratio = div_fixed16(src_w, dst_w);
+	fp_h_ratio = div_fixed16(src_h, dst_h);
+	downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
+	downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));
 
 	return mul_fixed16(downscale_w, downscale_h);
 }
@@ -3872,7 +3897,7 @@ skl_plane_downscale_amount(const struct intel_crtc_state *cstate,
 static uint_fixed_16_16_t
 skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state)
 {
-	uint_fixed_16_16_t pipe_downscale = u32_to_fixed_16_16(1);
+	uint_fixed_16_16_t pipe_downscale = u32_to_fixed16(1);
 
 	if (!crtc_state->base.enable)
 		return pipe_downscale;
@@ -3891,10 +3916,10 @@ skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state)
 		if (!dst_w || !dst_h)
 			return pipe_downscale;
 
-		fp_w_ratio = fixed_16_16_div(src_w, dst_w);
-		fp_h_ratio = fixed_16_16_div(src_h, dst_h);
-		downscale_w = max_fixed_16_16(fp_w_ratio, u32_to_fixed_16_16(1));
-		downscale_h = max_fixed_16_16(fp_h_ratio, u32_to_fixed_16_16(1));
+		fp_w_ratio = div_fixed16(src_w, dst_w);
+		fp_h_ratio = div_fixed16(src_h, dst_h);
+		downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
+		downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));
 
 		pipe_downscale = mul_fixed16(downscale_w, downscale_h);
 	}
@@ -3913,14 +3938,14 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 	int crtc_clock, dotclk;
 	uint32_t pipe_max_pixel_rate;
 	uint_fixed_16_16_t pipe_downscale;
-	uint_fixed_16_16_t max_downscale = u32_to_fixed_16_16(1);
+	uint_fixed_16_16_t max_downscale = u32_to_fixed16(1);
 
 	if (!cstate->base.enable)
 		return 0;
 
 	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
 		uint_fixed_16_16_t plane_downscale;
-		uint_fixed_16_16_t fp_9_div_8 = fixed_16_16_div(9, 8);
+		uint_fixed_16_16_t fp_9_div_8 = div_fixed16(9, 8);
 		int bpp;
 
 		if (!intel_wm_plane_visible(cstate,
@@ -3938,7 +3963,7 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 			plane_downscale = mul_fixed16(plane_downscale,
 						      fp_9_div_8);
 
-		max_downscale = max_fixed_16_16(plane_downscale, max_downscale);
+		max_downscale = max_fixed16(plane_downscale, max_downscale);
 	}
 	pipe_downscale = skl_pipe_downscale_amount(cstate);
 
@@ -4071,7 +4096,9 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 
 	/* For Non Y-tile return 8-blocks */
 	if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
-	    fb->modifier != I915_FORMAT_MOD_Yf_TILED)
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED &&
+	    fb->modifier != I915_FORMAT_MOD_Y_TILED_CCS &&
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED_CCS)
 		return 8;
 
 	/*
@@ -4266,8 +4293,9 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
  * should allow pixel_rate up to ~2 GHz which seems sufficient since max
  * 2xcdclk is 1350 MHz and the pixel rate should never exceed that.
 */
-static uint_fixed_16_16_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp,
-					 uint32_t latency)
+static uint_fixed_16_16_t
+skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
+	       uint8_t cpp, uint32_t latency)
 {
 	uint32_t wm_intermediate_val;
 	uint_fixed_16_16_t ret;
@@ -4276,7 +4304,11 @@ static uint_fixed_16_16_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp,
 		return FP_16_16_MAX;
 
 	wm_intermediate_val = latency * pixel_rate * cpp;
-	ret = fixed_16_16_div_u64(wm_intermediate_val, 1000 * 512);
+	ret = div_fixed16(wm_intermediate_val, 1000 * 512);
+
+	if (INTEL_GEN(dev_priv) >= 10)
+		ret = add_fixed16_u32(ret, 1);
+
 	return ret;
 }
 
@@ -4294,7 +4326,7 @@ static uint_fixed_16_16_t skl_wm_method2(uint32_t pixel_rate,
 	wm_intermediate_val = latency * pixel_rate;
 	wm_intermediate_val = DIV_ROUND_UP(wm_intermediate_val,
 					   pipe_htotal * 1000);
-	ret = mul_u32_fixed_16_16(wm_intermediate_val, plane_blocks_per_line);
+	ret = mul_u32_fixed16(wm_intermediate_val, plane_blocks_per_line);
 	return ret;
 }
 
@@ -4306,15 +4338,15 @@ intel_get_linetime_us(struct intel_crtc_state *cstate)
 	uint_fixed_16_16_t linetime_us;
 
 	if (!cstate->base.active)
-		return u32_to_fixed_16_16(0);
+		return u32_to_fixed16(0);
 
 	pixel_rate = cstate->pixel_rate;
 
 	if (WARN_ON(pixel_rate == 0))
-		return u32_to_fixed_16_16(0);
+		return u32_to_fixed16(0);
 
 	crtc_htotal = cstate->base.adjusted_mode.crtc_htotal;
-	linetime_us = fixed_16_16_div_u64(crtc_htotal * 1000, pixel_rate);
+	linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);
 
 	return linetime_us;
 }
@@ -4341,145 +4373,166 @@ skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate,
 					    downscale_amount);
 }
 
-static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
-				struct intel_crtc_state *cstate,
-				const struct intel_plane_state *intel_pstate,
-				uint16_t ddb_allocation,
-				int level,
-				uint16_t *out_blocks, /* out */
-				uint8_t *out_lines, /* out */
-				bool *enabled /* out */)
+static int
+skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
+			    struct intel_crtc_state *cstate,
+			    const struct intel_plane_state *intel_pstate,
+			    struct skl_wm_params *wp)
 {
 	struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane);
 	const struct drm_plane_state *pstate = &intel_pstate->base;
 	const struct drm_framebuffer *fb = pstate->fb;
-	uint32_t latency = dev_priv->wm.skl_latency[level];
-	uint_fixed_16_16_t method1, method2;
-	uint_fixed_16_16_t plane_blocks_per_line;
-	uint_fixed_16_16_t selected_result;
 	uint32_t interm_pbpl;
-	uint32_t plane_bytes_per_line;
-	uint32_t res_blocks, res_lines;
-	uint8_t cpp;
-	uint32_t width = 0, height = 0;
-	uint32_t plane_pixel_rate;
-	uint_fixed_16_16_t y_tile_minimum;
-	uint32_t y_min_scanlines;
 	struct intel_atomic_state *state =
 		to_intel_atomic_state(cstate->base.state);
 	bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
-	bool y_tiled, x_tiled;
 
-	if (latency == 0 ||
-	    !intel_wm_plane_visible(cstate, intel_pstate)) {
-		*enabled = false;
+	if (!intel_wm_plane_visible(cstate, intel_pstate))
 		return 0;
-	}
-
-	y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
-		  fb->modifier == I915_FORMAT_MOD_Yf_TILED;
-	x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;
 
-	/* Display WA #1141: kbl,cfl */
-	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) &&
-	    dev_priv->ipc_enabled)
-		latency += 4;
-
-	if (apply_memory_bw_wa && x_tiled)
-		latency += 15;
+	wp->y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
+		      fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
+		      fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+		      fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
+	wp->x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;
+	wp->rc_surface = fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+			 fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
 
 	if (plane->id == PLANE_CURSOR) {
-		width = intel_pstate->base.crtc_w;
-		height = intel_pstate->base.crtc_h;
+		wp->width = intel_pstate->base.crtc_w;
 	} else {
 		/*
 		 * Src coordinates are already rotated by 270 degrees for
 		 * the 90/270 degree plane rotation cases (to match the
 		 * GTT mapping), hence no need to account for rotation here.
 		 */
-		width = drm_rect_width(&intel_pstate->base.src) >> 16;
-		height = drm_rect_height(&intel_pstate->base.src) >> 16;
+		wp->width = drm_rect_width(&intel_pstate->base.src) >> 16;
 	}
 
-	cpp = fb->format->cpp[0];
-	plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate);
+	wp->cpp = (fb->format->format == DRM_FORMAT_NV12) ? fb->format->cpp[1] :
+							    fb->format->cpp[0];
+	wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate,
+							     intel_pstate);
 
 	if (drm_rotation_90_or_270(pstate->rotation)) {
-		int cpp = (fb->format->format == DRM_FORMAT_NV12) ?
-			fb->format->cpp[1] :
-			fb->format->cpp[0];
 
-		switch (cpp) {
+		switch (wp->cpp) {
 		case 1:
-			y_min_scanlines = 16;
+			wp->y_min_scanlines = 16;
 			break;
 		case 2:
-			y_min_scanlines = 8;
+			wp->y_min_scanlines = 8;
 			break;
 		case 4:
-			y_min_scanlines = 4;
+			wp->y_min_scanlines = 4;
 			break;
 		default:
-			MISSING_CASE(cpp);
+			MISSING_CASE(wp->cpp);
 			return -EINVAL;
 		}
 	} else {
-		y_min_scanlines = 4;
+		wp->y_min_scanlines = 4;
 	}
 
 	if (apply_memory_bw_wa)
-		y_min_scanlines *= 2;
-
-	plane_bytes_per_line = width * cpp;
-	if (y_tiled) {
-		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line *
-					   y_min_scanlines, 512);
-		plane_blocks_per_line = fixed_16_16_div(interm_pbpl,
-							y_min_scanlines);
-	} else if (x_tiled) {
-		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512);
-		plane_blocks_per_line = u32_to_fixed_16_16(interm_pbpl);
+		wp->y_min_scanlines *= 2;
+
+	wp->plane_bytes_per_line = wp->width * wp->cpp;
+	if (wp->y_tiled) {
+		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line *
+					   wp->y_min_scanlines, 512);
+
+		if (INTEL_GEN(dev_priv) >= 10)
+			interm_pbpl++;
+
+		wp->plane_blocks_per_line = div_fixed16(interm_pbpl,
+							wp->y_min_scanlines);
+	} else if (wp->x_tiled && IS_GEN9(dev_priv)) {
+		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, 512);
+		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	} else {
-		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
-		plane_blocks_per_line = u32_to_fixed_16_16(interm_pbpl);
+		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, 512) + 1;
+		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	}
 
-	method1 = skl_wm_method1(plane_pixel_rate, cpp, latency);
-	method2 = skl_wm_method2(plane_pixel_rate,
+	wp->y_tile_minimum = mul_u32_fixed16(wp->y_min_scanlines,
+					     wp->plane_blocks_per_line);
+	wp->linetime_us = fixed16_to_u32_round_up(
+					intel_get_linetime_us(cstate));
+
+	return 0;
+}
+
+static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
+				struct intel_crtc_state *cstate,
+				const struct intel_plane_state *intel_pstate,
+				uint16_t ddb_allocation,
+				int level,
+				const struct skl_wm_params *wp,
+				uint16_t *out_blocks, /* out */
+				uint8_t *out_lines, /* out */
+				bool *enabled /* out */)
+{
+	const struct drm_plane_state *pstate = &intel_pstate->base;
+	uint32_t latency = dev_priv->wm.skl_latency[level];
+	uint_fixed_16_16_t method1, method2;
+	uint_fixed_16_16_t selected_result;
+	uint32_t res_blocks, res_lines;
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(cstate->base.state);
+	bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
+
+	if (latency == 0 ||
+	    !intel_wm_plane_visible(cstate, intel_pstate)) {
+		*enabled = false;
+		return 0;
+	}
+
+	/* Display WA #1141: kbl,cfl */
+	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
+	    IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_B0)) &&
+	    dev_priv->ipc_enabled)
+		latency += 4;
+
+	if (apply_memory_bw_wa && wp->x_tiled)
+		latency += 15;
+
+	method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
+				 wp->cpp, latency);
+	method2 = skl_wm_method2(wp->plane_pixel_rate,
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 latency,
-				 plane_blocks_per_line);
-
-	y_tile_minimum = mul_u32_fixed_16_16(y_min_scanlines,
-					     plane_blocks_per_line);
+				 wp->plane_blocks_per_line);
 
-	if (y_tiled) {
-		selected_result = max_fixed_16_16(method2, y_tile_minimum);
+	if (wp->y_tiled) {
+		selected_result = max_fixed16(method2, wp->y_tile_minimum);
 	} else {
-		uint32_t linetime_us;
-
-		linetime_us = fixed_16_16_to_u32_round_up(
-				intel_get_linetime_us(cstate));
-		if ((cpp * cstate->base.adjusted_mode.crtc_htotal / 512 < 1) &&
-		    (plane_bytes_per_line / 512 < 1))
+		if ((wp->cpp * cstate->base.adjusted_mode.crtc_htotal /
+		     512 < 1) && (wp->plane_bytes_per_line / 512 < 1))
 			selected_result = method2;
-		else if ((ddb_allocation && ddb_allocation /
-			fixed_16_16_to_u32_round_up(plane_blocks_per_line)) >= 1)
-			selected_result = min_fixed_16_16(method1, method2);
-		else if (latency >= linetime_us)
-			selected_result = min_fixed_16_16(method1, method2);
+		else if (ddb_allocation >=
+			 fixed16_to_u32_round_up(wp->plane_blocks_per_line))
+			selected_result = min_fixed16(method1, method2);
+		else if (latency >= wp->linetime_us)
+			selected_result = min_fixed16(method1, method2);
 		else
 			selected_result = method1;
 	}
 
-	res_blocks = fixed_16_16_to_u32_round_up(selected_result) + 1;
+	res_blocks = fixed16_to_u32_round_up(selected_result) + 1;
 	res_lines = div_round_up_fixed16(selected_result,
-					 plane_blocks_per_line);
+					 wp->plane_blocks_per_line);
 
+	/* Display WA #1125: skl,bxt,kbl,glk */
+	if (level == 0 && wp->rc_surface)
+		res_blocks += fixed16_to_u32_round_up(wp->y_tile_minimum);
+
+	/* Display WA #1126: skl,bxt,kbl,glk */
 	if (level >= 1 && level <= 7) {
-		if (y_tiled) {
-			res_blocks += fixed_16_16_to_u32_round_up(y_tile_minimum);
-			res_lines += y_min_scanlines;
+		if (wp->y_tiled) {
+			res_blocks += fixed16_to_u32_round_up(
+							wp->y_tile_minimum);
+			res_lines += wp->y_min_scanlines;
 		} else {
 			res_blocks++;
 		}
@@ -4517,6 +4570,7 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 		      struct skl_ddb_allocation *ddb,
 		      struct intel_crtc_state *cstate,
 		      const struct intel_plane_state *intel_pstate,
+		      const struct skl_wm_params *wm_params,
 		      struct skl_plane_wm *wm)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
@@ -4540,6 +4594,7 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 					   intel_pstate,
 					   ddb_blocks,
 					   level,
+					   wm_params,
 					   &result->plane_res_b,
 					   &result->plane_res_l,
 					   &result->plane_en);
@@ -4563,23 +4618,67 @@ skl_compute_linetime_wm(struct intel_crtc_state *cstate)
 	if (is_fixed16_zero(linetime_us))
 		return 0;
 
-	linetime_wm = fixed_16_16_to_u32_round_up(mul_u32_fixed_16_16(8,
-				linetime_us));
+	linetime_wm = fixed16_to_u32_round_up(mul_u32_fixed16(8, linetime_us));
 
-	/* Display WA #1135: bxt. */
-	if (IS_BROXTON(dev_priv) && dev_priv->ipc_enabled)
-		linetime_wm = DIV_ROUND_UP(linetime_wm, 2);
+	/* Display WA #1135: bxt:ALL GLK:ALL */
+	if ((IS_BROXTON(dev_priv) || IS_GEMINILAKE(dev_priv)) &&
+	    dev_priv->ipc_enabled)
+		linetime_wm /= 2;
 
 	return linetime_wm;
 }
 
 static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
+				      struct skl_wm_params *wp,
+				      struct skl_wm_level *wm_l0,
+				      uint16_t ddb_allocation,
 				      struct skl_wm_level *trans_wm /* out */)
 {
+	struct drm_device *dev = cstate->base.crtc->dev;
+	const struct drm_i915_private *dev_priv = to_i915(dev);
+	uint16_t trans_min, trans_y_tile_min;
+	const uint16_t trans_amount = 10; /* This is configurable amount */
+	uint16_t trans_offset_b, res_blocks;
+
 	if (!cstate->base.active)
+		goto exit;
+
+	/* Transition WM are not recommended by HW team for GEN9 */
+	if (INTEL_GEN(dev_priv) <= 9)
+		goto exit;
+
+	/* Transition WM don't make any sense if ipc is disabled */
+	if (!dev_priv->ipc_enabled)
+		goto exit;
+
+	if (INTEL_GEN(dev_priv) >= 10)
+		trans_min = 4;
+
+	trans_offset_b = trans_min + trans_amount;
+
+	if (wp->y_tiled) {
+		trans_y_tile_min = (uint16_t) mul_round_up_u32_fixed16(2,
+							wp->y_tile_minimum);
+		res_blocks = max(wm_l0->plane_res_b, trans_y_tile_min) +
+				trans_offset_b;
+	} else {
+		res_blocks = wm_l0->plane_res_b + trans_offset_b;
+
+		/* WA BUG:1938466 add one block for non y-tile planes */
+		if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_A0))
+			res_blocks += 1;
+
+	}
+
+	res_blocks += 1;
+
+	if (res_blocks < ddb_allocation) {
+		trans_wm->plane_res_b = res_blocks;
+		trans_wm->plane_en = true;
 		return;
+	}
 
-	/* Until we know more, just disable transition WMs */
+exit:
 	trans_wm->plane_en = false;
 }
 
@@ -4605,14 +4704,25 @@ static int skl_build_pipe_wm(struct intel_crtc_state *cstate,
 		const struct intel_plane_state *intel_pstate =
 						to_intel_plane_state(pstate);
 		enum plane_id plane_id = to_intel_plane(plane)->id;
+		struct skl_wm_params wm_params;
+		enum pipe pipe = to_intel_crtc(cstate->base.crtc)->pipe;
+		uint16_t ddb_blocks;
 
 		wm = &pipe_wm->planes[plane_id];
+		ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][plane_id]);
+		memset(&wm_params, 0, sizeof(struct skl_wm_params));
+
+		ret = skl_compute_plane_wm_params(dev_priv, cstate,
+						  intel_pstate, &wm_params);
+		if (ret)
+			return ret;
 
 		ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
-					    intel_pstate, wm);
+					    intel_pstate, &wm_params, wm);
 		if (ret)
 			return ret;
-		skl_compute_transition_wm(cstate, &wm->trans_wm);
+		skl_compute_transition_wm(cstate, &wm_params, &wm->wm[0],
+					  ddb_blocks, &wm->trans_wm);
 	}
 	pipe_wm->linetime = skl_compute_linetime_wm(cstate);
 
@@ -4708,16 +4818,18 @@ static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
 	return a->start < b->end && b->start < a->end;
 }
 
-bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry **entries,
+bool skl_ddb_allocation_overlaps(struct drm_i915_private *dev_priv,
+				 const struct skl_ddb_entry **entries,
 				 const struct skl_ddb_entry *ddb,
 				 int ignore)
 {
-	int i;
+	enum pipe pipe;
 
-	for (i = 0; i < I915_MAX_PIPES; i++)
-		if (i != ignore && entries[i] &&
-		    skl_ddb_entries_overlap(ddb, entries[i]))
+	for_each_pipe(dev_priv, pipe) {
+		if (pipe != ignore && entries[pipe] &&
+		    skl_ddb_entries_overlap(ddb, entries[pipe]))
 			return true;
+	}
 
 	return false;
 }
@@ -5507,7 +5619,7 @@ void vlv_wm_get_hw_state(struct drm_device *dev)
 	wm->level = VLV_WM_LEVEL_PM2;
 
 	if (IS_CHERRYVIEW(dev_priv)) {
-		mutex_lock(&dev_priv->rps.hw_lock);
+		mutex_lock(&dev_priv->pcu_lock);
 
 		val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
 		if (val & DSP_MAXFIFO_PM5_ENABLE)
@@ -5537,7 +5649,7 @@ void vlv_wm_get_hw_state(struct drm_device *dev)
 				wm->level = VLV_WM_LEVEL_DDR_DVFS;
 		}
 
-		mutex_unlock(&dev_priv->rps.hw_lock);
+		mutex_unlock(&dev_priv->pcu_lock);
 	}
 
 	for_each_intel_crtc(dev, crtc) {
@@ -5641,12 +5753,30 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
 
+/*
+ * FIXME should probably kill this and improve
+ * the real watermark readout/sanitation instead
+ */
+static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(WM3_LP_ILK, I915_READ(WM3_LP_ILK) & ~WM1_LP_SR_EN);
+	I915_WRITE(WM2_LP_ILK, I915_READ(WM2_LP_ILK) & ~WM1_LP_SR_EN);
+	I915_WRITE(WM1_LP_ILK, I915_READ(WM1_LP_ILK) & ~WM1_LP_SR_EN);
+
+	/*
+	 * Don't touch WM1S_LP_EN here.
+	 * Doing so could cause underruns.
+	 */
+}
+
 void ilk_wm_get_hw_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct drm_crtc *crtc;
 
+	ilk_init_lp_watermarks(dev_priv);
+
 	for_each_crtc(dev, crtc)
 		ilk_pipe_wm_get_hw_state(crtc);
 
@@ -5711,6 +5841,36 @@ void intel_update_watermarks(struct intel_crtc *crtc)
 		dev_priv->display.update_wm(crtc);
 }
 
+void intel_enable_ipc(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	/* Display WA #0477 WaDisableIPC: skl */
+	if (IS_SKYLAKE(dev_priv)) {
+		dev_priv->ipc_enabled = false;
+		return;
+	}
+
+	val = I915_READ(DISP_ARB_CTL2);
+
+	if (dev_priv->ipc_enabled)
+		val |= DISP_IPC_ENABLE;
+	else
+		val &= ~DISP_IPC_ENABLE;
+
+	I915_WRITE(DISP_ARB_CTL2, val);
+}
+
+void intel_init_ipc(struct drm_i915_private *dev_priv)
+{
+	dev_priv->ipc_enabled = false;
+	if (!HAS_IPC(dev_priv))
+		return;
+
+	dev_priv->ipc_enabled = true;
+	intel_enable_ipc(dev_priv);
+}
+
 /*
  * Lock protecting IPS related data structures
  */
@@ -5844,6 +6004,7 @@ static void ironlake_disable_drps(struct drm_i915_private *dev_priv)
  */
 static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 limits;
 
 	/* Only set the down limit when we've reached the lowest level to avoid
@@ -5852,14 +6013,14 @@ static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 	 * 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 (IS_GEN9(dev_priv)) {
-		limits = (dev_priv->rps.max_freq_softlimit) << 23;
-		if (val <= dev_priv->rps.min_freq_softlimit)
-			limits |= (dev_priv->rps.min_freq_softlimit) << 14;
+	if (INTEL_GEN(dev_priv) >= 9) {
+		limits = (rps->max_freq_softlimit) << 23;
+		if (val <= rps->min_freq_softlimit)
+			limits |= (rps->min_freq_softlimit) << 14;
 	} else {
-		limits = dev_priv->rps.max_freq_softlimit << 24;
-		if (val <= dev_priv->rps.min_freq_softlimit)
-			limits |= dev_priv->rps.min_freq_softlimit << 16;
+		limits = rps->max_freq_softlimit << 24;
+		if (val <= rps->min_freq_softlimit)
+			limits |= rps->min_freq_softlimit << 16;
 	}
 
 	return limits;
@@ -5867,39 +6028,40 @@ static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 
 static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int new_power;
 	u32 threshold_up = 0, threshold_down = 0; /* in % */
 	u32 ei_up = 0, ei_down = 0;
 
-	new_power = dev_priv->rps.power;
-	switch (dev_priv->rps.power) {
+	new_power = rps->power;
+	switch (rps->power) {
 	case LOW_POWER:
-		if (val > dev_priv->rps.efficient_freq + 1 &&
-		    val > dev_priv->rps.cur_freq)
+		if (val > rps->efficient_freq + 1 &&
+		    val > rps->cur_freq)
 			new_power = BETWEEN;
 		break;
 
 	case BETWEEN:
-		if (val <= dev_priv->rps.efficient_freq &&
-		    val < dev_priv->rps.cur_freq)
+		if (val <= rps->efficient_freq &&
+		    val < rps->cur_freq)
 			new_power = LOW_POWER;
-		else if (val >= dev_priv->rps.rp0_freq &&
-			 val > dev_priv->rps.cur_freq)
+		else if (val >= rps->rp0_freq &&
+			 val > rps->cur_freq)
 			new_power = HIGH_POWER;
 		break;
 
 	case HIGH_POWER:
-		if (val < (dev_priv->rps.rp1_freq + dev_priv->rps.rp0_freq) >> 1 &&
-		    val < dev_priv->rps.cur_freq)
+		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
+		    val < rps->cur_freq)
 			new_power = BETWEEN;
 		break;
 	}
 	/* Max/min bins are special */
-	if (val <= dev_priv->rps.min_freq_softlimit)
+	if (val <= rps->min_freq_softlimit)
 		new_power = LOW_POWER;
-	if (val >= dev_priv->rps.max_freq_softlimit)
+	if (val >= rps->max_freq_softlimit)
 		new_power = HIGH_POWER;
-	if (new_power == dev_priv->rps.power)
+	if (new_power == rps->power)
 		return;
 
 	/* Note the units here are not exactly 1us, but 1280ns. */
@@ -5962,20 +6124,21 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		   GEN6_RP_DOWN_IDLE_AVG);
 
 skip_hw_write:
-	dev_priv->rps.power = new_power;
-	dev_priv->rps.up_threshold = threshold_up;
-	dev_priv->rps.down_threshold = threshold_down;
-	dev_priv->rps.last_adj = 0;
+	rps->power = new_power;
+	rps->up_threshold = threshold_up;
+	rps->down_threshold = threshold_down;
+	rps->last_adj = 0;
 }
 
 static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 mask = 0;
 
 	/* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
-	if (val > dev_priv->rps.min_freq_softlimit)
+	if (val > rps->min_freq_softlimit)
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
-	if (val < dev_priv->rps.max_freq_softlimit)
+	if (val < rps->max_freq_softlimit)
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
 
 	mask &= dev_priv->pm_rps_events;
@@ -5988,13 +6151,15 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
  * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
 static int gen6_set_rps(struct drm_i915_private *dev_priv, u8 val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/* min/max delay may still have been modified so be sure to
 	 * write the limits value.
 	 */
-	if (val != dev_priv->rps.cur_freq) {
+	if (val != rps->cur_freq) {
 		gen6_set_rps_thresholds(dev_priv, val);
 
-		if (IS_GEN9(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 9)
 			I915_WRITE(GEN6_RPNSWREQ,
 				   GEN9_FREQUENCY(val));
 		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
@@ -6013,7 +6178,7 @@ static int gen6_set_rps(struct drm_i915_private *dev_priv, u8 val)
 	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, intel_rps_limits(dev_priv, val));
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
-	dev_priv->rps.cur_freq = val;
+	rps->cur_freq = val;
 	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
 
 	return 0;
@@ -6029,7 +6194,7 @@ static int valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
-	if (val != dev_priv->rps.cur_freq) {
+	if (val != dev_priv->gt_pm.rps.cur_freq) {
 		err = vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
 		if (err)
 			return err;
@@ -6037,7 +6202,7 @@ static int valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
 		gen6_set_rps_thresholds(dev_priv, val);
 	}
 
-	dev_priv->rps.cur_freq = val;
+	dev_priv->gt_pm.rps.cur_freq = val;
 	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
 
 	return 0;
@@ -6052,10 +6217,11 @@ static int valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
 */
 static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 {
-	u32 val = dev_priv->rps.idle_freq;
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	u32 val = rps->idle_freq;
 	int err;
 
-	if (dev_priv->rps.cur_freq <= val)
+	if (rps->cur_freq <= val)
 		return;
 
 	/* The punit delays the write of the frequency and voltage until it
@@ -6080,34 +6246,38 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 
 void gen6_rps_busy(struct drm_i915_private *dev_priv)
 {
-	mutex_lock(&dev_priv->rps.hw_lock);
-	if (dev_priv->rps.enabled) {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	mutex_lock(&dev_priv->pcu_lock);
+	if (rps->enabled) {
 		u8 freq;
 
 		if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
 			gen6_rps_reset_ei(dev_priv);
 		I915_WRITE(GEN6_PMINTRMSK,
-			   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
+			   gen6_rps_pm_mask(dev_priv, rps->cur_freq));
 
 		gen6_enable_rps_interrupts(dev_priv);
 
 		/* Use the user's desired frequency as a guide, but for better
 		 * performance, jump directly to RPe as our starting frequency.
 		 */
-		freq = max(dev_priv->rps.cur_freq,
-			   dev_priv->rps.efficient_freq);
+		freq = max(rps->cur_freq,
+			   rps->efficient_freq);
 
 		if (intel_set_rps(dev_priv,
 				  clamp(freq,
-					dev_priv->rps.min_freq_softlimit,
-					dev_priv->rps.max_freq_softlimit)))
+					rps->min_freq_softlimit,
+					rps->max_freq_softlimit)))
 			DRM_DEBUG_DRIVER("Failed to set idle frequency\n");
 	}
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/* Flush our bottom-half so that it does not race with us
 	 * setting the idle frequency and so that it is bounded by
 	 * our rpm wakeref. And then disable the interrupts to stop any
@@ -6115,70 +6285,60 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 	 */
 	gen6_disable_rps_interrupts(dev_priv);
 
-	mutex_lock(&dev_priv->rps.hw_lock);
-	if (dev_priv->rps.enabled) {
+	mutex_lock(&dev_priv->pcu_lock);
+	if (rps->enabled) {
 		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 			vlv_set_rps_idle(dev_priv);
 		else
-			gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
-		dev_priv->rps.last_adj = 0;
+			gen6_set_rps(dev_priv, rps->idle_freq);
+		rps->last_adj = 0;
 		I915_WRITE(GEN6_PMINTRMSK,
 			   gen6_sanitize_rps_pm_mask(dev_priv, ~0));
 	}
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-	spin_lock(&dev_priv->rps.client_lock);
-	while (!list_empty(&dev_priv->rps.clients))
-		list_del_init(dev_priv->rps.clients.next);
-	spin_unlock(&dev_priv->rps.client_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 }
 
-void gen6_rps_boost(struct drm_i915_private *dev_priv,
-		    struct intel_rps_client *rps,
-		    unsigned long submitted)
+void gen6_rps_boost(struct drm_i915_gem_request *rq,
+		    struct intel_rps_client *rps_client)
 {
+	struct intel_rps *rps = &rq->i915->gt_pm.rps;
+	unsigned long flags;
+	bool boost;
+
 	/* This is intentionally racy! We peek at the state here, then
 	 * validate inside the RPS worker.
 	 */
-	if (!(dev_priv->gt.awake &&
-	      dev_priv->rps.enabled &&
-	      dev_priv->rps.cur_freq < dev_priv->rps.boost_freq))
+	if (!rps->enabled)
 		return;
 
-	/* Force a RPS boost (and don't count it against the client) if
-	 * the GPU is severely congested.
-	 */
-	if (rps && time_after(jiffies, submitted + DRM_I915_THROTTLE_JIFFIES))
-		rps = NULL;
-
-	spin_lock(&dev_priv->rps.client_lock);
-	if (rps == NULL || list_empty(&rps->link)) {
-		spin_lock_irq(&dev_priv->irq_lock);
-		if (dev_priv->rps.interrupts_enabled) {
-			dev_priv->rps.client_boost = true;
-			schedule_work(&dev_priv->rps.work);
-		}
-		spin_unlock_irq(&dev_priv->irq_lock);
-
-		if (rps != NULL) {
-			list_add(&rps->link, &dev_priv->rps.clients);
-			rps->boosts++;
-		} else
-			dev_priv->rps.boosts++;
+	boost = false;
+	spin_lock_irqsave(&rq->lock, flags);
+	if (!rq->waitboost && !i915_gem_request_completed(rq)) {
+		atomic_inc(&rps->num_waiters);
+		rq->waitboost = true;
+		boost = true;
 	}
-	spin_unlock(&dev_priv->rps.client_lock);
+	spin_unlock_irqrestore(&rq->lock, flags);
+	if (!boost)
+		return;
+
+	if (READ_ONCE(rps->cur_freq) < rps->boost_freq)
+		schedule_work(&rps->work);
+
+	atomic_inc(rps_client ? &rps_client->boosts : &rps->boosts);
 }
 
 int intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int err;
 
-	lockdep_assert_held(&dev_priv->rps.hw_lock);
-	GEM_BUG_ON(val > dev_priv->rps.max_freq);
-	GEM_BUG_ON(val < dev_priv->rps.min_freq);
+	lockdep_assert_held(&dev_priv->pcu_lock);
+	GEM_BUG_ON(val > rps->max_freq);
+	GEM_BUG_ON(val < rps->min_freq);
 
-	if (!dev_priv->rps.enabled) {
-		dev_priv->rps.cur_freq = val;
+	if (!rps->enabled) {
+		rps->cur_freq = val;
 		return 0;
 	}
 
@@ -6201,21 +6361,30 @@ static void gen9_disable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void gen6_disable_rps(struct drm_i915_private *dev_priv)
+static void gen6_disable_rc6(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RC_CONTROL, 0);
+}
+
+static void gen6_disable_rps(struct drm_i915_private *dev_priv)
+{
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
+static void cherryview_disable_rc6(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 }
 
-static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
+static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
 {
-	/* we're doing forcewake before Disabling RC6,
+	I915_WRITE(GEN6_RP_CONTROL, 0);
+}
+
+static void valleyview_disable_rc6(struct drm_i915_private *dev_priv)
+{
+	/* We're doing forcewake before Disabling RC6,
 	 * This what the BIOS expects when going into suspend */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
@@ -6224,6 +6393,11 @@ static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
+static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(GEN6_RP_CONTROL, 0);
+}
+
 static void intel_print_rc6_info(struct drm_i915_private *dev_priv, u32 mode)
 {
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
@@ -6346,58 +6520,61 @@ int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6)
 
 static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/* All of these values are in units of 50MHz */
 
 	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
 	if (IS_GEN9_LP(dev_priv)) {
 		u32 rp_state_cap = I915_READ(BXT_RP_STATE_CAP);
-		dev_priv->rps.rp0_freq = (rp_state_cap >> 16) & 0xff;
-		dev_priv->rps.rp1_freq = (rp_state_cap >>  8) & 0xff;
-		dev_priv->rps.min_freq = (rp_state_cap >>  0) & 0xff;
+		rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
+		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
+		rps->min_freq = (rp_state_cap >>  0) & 0xff;
 	} else {
 		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		dev_priv->rps.rp0_freq = (rp_state_cap >>  0) & 0xff;
-		dev_priv->rps.rp1_freq = (rp_state_cap >>  8) & 0xff;
-		dev_priv->rps.min_freq = (rp_state_cap >> 16) & 0xff;
+		rps->rp0_freq = (rp_state_cap >>  0) & 0xff;
+		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
+		rps->min_freq = (rp_state_cap >> 16) & 0xff;
 	}
 	/* hw_max = RP0 until we check for overclocking */
-	dev_priv->rps.max_freq = dev_priv->rps.rp0_freq;
+	rps->max_freq = rps->rp0_freq;
 
-	dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq;
+	rps->efficient_freq = rps->rp1_freq;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) ||
-	    IS_GEN9_BC(dev_priv)) {
+	    IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
 		u32 ddcc_status = 0;
 
 		if (sandybridge_pcode_read(dev_priv,
 					   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
 					   &ddcc_status) == 0)
-			dev_priv->rps.efficient_freq =
+			rps->efficient_freq =
 				clamp_t(u8,
 					((ddcc_status >> 8) & 0xff),
-					dev_priv->rps.min_freq,
-					dev_priv->rps.max_freq);
+					rps->min_freq,
+					rps->max_freq);
 	}
 
-	if (IS_GEN9_BC(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
 		/* Store the frequency values in 16.66 MHZ units, which is
 		 * the natural hardware unit for SKL
 		 */
-		dev_priv->rps.rp0_freq *= GEN9_FREQ_SCALER;
-		dev_priv->rps.rp1_freq *= GEN9_FREQ_SCALER;
-		dev_priv->rps.min_freq *= GEN9_FREQ_SCALER;
-		dev_priv->rps.max_freq *= GEN9_FREQ_SCALER;
-		dev_priv->rps.efficient_freq *= GEN9_FREQ_SCALER;
+		rps->rp0_freq *= GEN9_FREQ_SCALER;
+		rps->rp1_freq *= GEN9_FREQ_SCALER;
+		rps->min_freq *= GEN9_FREQ_SCALER;
+		rps->max_freq *= GEN9_FREQ_SCALER;
+		rps->efficient_freq *= GEN9_FREQ_SCALER;
 	}
 }
 
 static void reset_rps(struct drm_i915_private *dev_priv,
 		      int (*set)(struct drm_i915_private *, u8))
 {
-	u8 freq = dev_priv->rps.cur_freq;
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	u8 freq = rps->cur_freq;
 
 	/* force a reset */
-	dev_priv->rps.power = -1;
-	dev_priv->rps.cur_freq = -1;
+	rps->power = -1;
+	rps->cur_freq = -1;
 
 	if (set(dev_priv, freq))
 		DRM_ERROR("Failed to reset RPS to initial values\n");
@@ -6410,7 +6587,7 @@ static void gen9_enable_rps(struct drm_i915_private *dev_priv)
 
 	/* Program defaults and thresholds for RPS*/
 	I915_WRITE(GEN6_RC_VIDEO_FREQ,
-		GEN9_FREQUENCY(dev_priv->rps.rp1_freq));
+		GEN9_FREQUENCY(dev_priv->gt_pm.rps.rp1_freq));
 
 	/* 1 second timeout*/
 	I915_WRITE(GEN6_RP_DOWN_TIMEOUT,
@@ -6430,7 +6607,7 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	uint32_t rc6_mask = 0;
+	u32 rc6_mode, rc6_mask = 0;
 
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
@@ -6464,12 +6641,19 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 25);
 
 	/* 3a: Enable RC6 */
-	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
+	if (intel_rc6_enabled() & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
 	DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE));
 	I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
+
+	/* WaRsUseTimeoutMode:cnl (pre-prod) */
+	if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_C0))
+		rc6_mode = GEN7_RC_CTL_TO_MODE;
+	else
+		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
+
 	I915_WRITE(GEN6_RC_CONTROL,
-		   GEN6_RC_CTL_HW_ENABLE | GEN6_RC_CTL_EI_MODE(1) | rc6_mask);
+		   GEN6_RC_CTL_HW_ENABLE | rc6_mode | rc6_mask);
 
 	/*
 	 * 3b: Enable Coarse Power Gating only when RC6 is enabled.
@@ -6484,7 +6668,7 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void gen8_enable_rps(struct drm_i915_private *dev_priv)
+static void gen8_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -6493,7 +6677,7 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
 
-	/* 1c & 1d: Get forcewake during program sequence. Although the driver
+	/* 1b: Get forcewake during program sequence. Although the driver
 	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
@@ -6507,36 +6691,38 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 	for_each_engine(engine, dev_priv, id)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
-	if (IS_BROADWELL(dev_priv))
-		I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
-	else
-		I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+	I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
 
 	/* 3: Enable RC6 */
-	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
+	if (intel_rc6_enabled() & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
 	intel_print_rc6_info(dev_priv, rc6_mask);
-	if (IS_BROADWELL(dev_priv))
-		I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
-				GEN7_RC_CTL_TO_MODE |
-				rc6_mask);
-	else
-		I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
-				GEN6_RC_CTL_EI_MODE(1) |
-				rc6_mask);
 
-	/* 4 Program defaults and thresholds for RPS*/
+	I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
+			GEN7_RC_CTL_TO_MODE |
+			rc6_mask);
+
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+}
+
+static void gen8_enable_rps(struct drm_i915_private *dev_priv)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+	/* 1 Program defaults and thresholds for RPS*/
 	I915_WRITE(GEN6_RPNSWREQ,
-		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
+		   HSW_FREQUENCY(rps->rp1_freq));
 	I915_WRITE(GEN6_RC_VIDEO_FREQ,
-		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
+		   HSW_FREQUENCY(rps->rp1_freq));
 	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
 	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
 
 	/* Docs recommend 900MHz, and 300 MHz respectively */
 	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-		   dev_priv->rps.max_freq_softlimit << 24 |
-		   dev_priv->rps.min_freq_softlimit << 16);
+		   rps->max_freq_softlimit << 24 |
+		   rps->min_freq_softlimit << 16);
 
 	I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
@@ -6545,7 +6731,7 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
-	/* 5: Enable RPS */
+	/* 2: Enable RPS */
 	I915_WRITE(GEN6_RP_CONTROL,
 		   GEN6_RP_MEDIA_TURBO |
 		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
@@ -6554,14 +6740,12 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 		   GEN6_RP_UP_BUSY_AVG |
 		   GEN6_RP_DOWN_IDLE_AVG);
 
-	/* 6: Ring frequency + overclocking (our driver does this later */
-
 	reset_rps(dev_priv, gen6_set_rps);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void gen6_enable_rps(struct drm_i915_private *dev_priv)
+static void gen6_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -6570,14 +6754,6 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	int rc6_mode;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-
-	/* Here begins a magic sequence of register writes to enable
-	 * auto-downclocking.
-	 *
-	 * Perhaps there might be some value in exposing these to
-	 * userspace...
-	 */
 	I915_WRITE(GEN6_RC_STATE, 0);
 
 	/* Clear the DBG now so we don't confuse earlier errors */
@@ -6611,7 +6787,7 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
 	/* Check if we are enabling RC6 */
-	rc6_mode = intel_enable_rc6();
+	rc6_mode = intel_rc6_enabled();
 	if (rc6_mode & INTEL_RC6_ENABLE)
 		rc6_mask |= GEN6_RC_CTL_RC6_ENABLE;
 
@@ -6631,12 +6807,6 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 		   GEN6_RC_CTL_EI_MODE(1) |
 		   GEN6_RC_CTL_HW_ENABLE);
 
-	/* Power down if completely idle for over 50ms */
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 50000);
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
-	reset_rps(dev_priv, gen6_set_rps);
-
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
 	if (IS_GEN6(dev_priv) && ret) {
@@ -6654,8 +6824,28 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
+static void gen6_enable_rps(struct drm_i915_private *dev_priv)
+{
+	/* Here begins a magic sequence of register writes to enable
+	 * auto-downclocking.
+	 *
+	 * Perhaps there might be some value in exposing these to
+	 * userspace...
+	 */
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+	/* Power down if completely idle for over 50ms */
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 50000);
+	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	reset_rps(dev_priv, gen6_set_rps);
+
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+}
+
 static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int min_freq = 15;
 	unsigned int gpu_freq;
 	unsigned int max_ia_freq, min_ring_freq;
@@ -6663,7 +6853,7 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 	int scaling_factor = 180;
 	struct cpufreq_policy *policy;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
 
 	policy = cpufreq_cpu_get(0);
 	if (policy) {
@@ -6684,13 +6874,13 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 	/* convert DDR frequency from units of 266.6MHz to bandwidth */
 	min_ring_freq = mult_frac(min_ring_freq, 8, 3);
 
-	if (IS_GEN9_BC(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
 		/* Convert GT frequency to 50 HZ units */
-		min_gpu_freq = dev_priv->rps.min_freq / GEN9_FREQ_SCALER;
-		max_gpu_freq = dev_priv->rps.max_freq / GEN9_FREQ_SCALER;
+		min_gpu_freq = rps->min_freq / GEN9_FREQ_SCALER;
+		max_gpu_freq = rps->max_freq / GEN9_FREQ_SCALER;
 	} else {
-		min_gpu_freq = dev_priv->rps.min_freq;
-		max_gpu_freq = dev_priv->rps.max_freq;
+		min_gpu_freq = rps->min_freq;
+		max_gpu_freq = rps->max_freq;
 	}
 
 	/*
@@ -6702,7 +6892,7 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 		int diff = max_gpu_freq - gpu_freq;
 		unsigned int ia_freq = 0, ring_freq = 0;
 
-		if (IS_GEN9_BC(dev_priv)) {
+		if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
 			/*
 			 * ring_freq = 2 * GT. ring_freq is in 100MHz units
 			 * No floor required for ring frequency on SKL.
@@ -6941,17 +7131,18 @@ static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
 
 static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
 {
-	dev_priv->rps.gpll_ref_freq =
+	dev_priv->gt_pm.rps.gpll_ref_freq =
 		vlv_get_cck_clock(dev_priv, "GPLL ref",
 				  CCK_GPLL_CLOCK_CONTROL,
 				  dev_priv->czclk_freq);
 
 	DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n",
-			 dev_priv->rps.gpll_ref_freq);
+			 dev_priv->gt_pm.rps.gpll_ref_freq);
 }
 
 static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 val;
 
 	valleyview_setup_pctx(dev_priv);
@@ -6973,30 +7164,31 @@ static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
 	}
 	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", 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;
+	rps->max_freq = valleyview_rps_max_freq(dev_priv);
+	rps->rp0_freq = rps->max_freq;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.max_freq),
-			 dev_priv->rps.max_freq);
+			 intel_gpu_freq(dev_priv, rps->max_freq),
+			 rps->max_freq);
 
-	dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
+	rps->efficient_freq = valleyview_rps_rpe_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
-			 dev_priv->rps.efficient_freq);
+			 intel_gpu_freq(dev_priv, rps->efficient_freq),
+			 rps->efficient_freq);
 
-	dev_priv->rps.rp1_freq = valleyview_rps_guar_freq(dev_priv);
+	rps->rp1_freq = valleyview_rps_guar_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.rp1_freq),
-			 dev_priv->rps.rp1_freq);
+			 intel_gpu_freq(dev_priv, rps->rp1_freq),
+			 rps->rp1_freq);
 
-	dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv);
+	rps->min_freq = valleyview_rps_min_freq(dev_priv);
 	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.min_freq),
-			 dev_priv->rps.min_freq);
+			 intel_gpu_freq(dev_priv, rps->min_freq),
+			 rps->min_freq);
 }
 
 static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 val;
 
 	cherryview_setup_pctx(dev_priv);
@@ -7017,31 +7209,29 @@ static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
 	}
 	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", 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;
+	rps->max_freq = cherryview_rps_max_freq(dev_priv);
+	rps->rp0_freq = rps->max_freq;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.max_freq),
-			 dev_priv->rps.max_freq);
+			 intel_gpu_freq(dev_priv, rps->max_freq),
+			 rps->max_freq);
 
-	dev_priv->rps.efficient_freq = cherryview_rps_rpe_freq(dev_priv);
+	rps->efficient_freq = cherryview_rps_rpe_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
-			 dev_priv->rps.efficient_freq);
+			 intel_gpu_freq(dev_priv, rps->efficient_freq),
+			 rps->efficient_freq);
 
-	dev_priv->rps.rp1_freq = cherryview_rps_guar_freq(dev_priv);
+	rps->rp1_freq = cherryview_rps_guar_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.rp1_freq),
-			 dev_priv->rps.rp1_freq);
+			 intel_gpu_freq(dev_priv, rps->rp1_freq),
+			 rps->rp1_freq);
 
-	dev_priv->rps.min_freq = cherryview_rps_min_freq(dev_priv);
+	rps->min_freq = cherryview_rps_min_freq(dev_priv);
 	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, dev_priv->rps.min_freq),
-			 dev_priv->rps.min_freq);
+			 intel_gpu_freq(dev_priv, rps->min_freq),
+			 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,
+	WARN_ONCE((rps->max_freq | rps->efficient_freq | rps->rp1_freq |
+		   rps->min_freq) & 1,
 		  "Odd GPU freq values\n");
 }
 
@@ -7050,13 +7240,11 @@ static void valleyview_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 	valleyview_cleanup_pctx(dev_priv);
 }
 
-static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
+static void cherryview_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	u32 gtfifodbg, rc6_mode = 0, pcbr;
 
 	gtfifodbg = I915_READ(GTFIFODBG) & ~(GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV |
 					     GT_FIFO_FREE_ENTRIES_CHV);
@@ -7087,7 +7275,7 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 	/* TO threshold set to 500 us ( 0x186 * 1.28 us) */
 	I915_WRITE(GEN6_RC6_THRESHOLD, 0x186);
 
-	/* allows RC6 residency counter to work */
+	/* Allows RC6 residency counter to work */
 	I915_WRITE(VLV_COUNTER_CONTROL,
 		   _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
 				      VLV_MEDIA_RC6_COUNT_EN |
@@ -7097,13 +7285,22 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 	pcbr = I915_READ(VLV_PCBR);
 
 	/* 3: Enable RC6 */
-	if ((intel_enable_rc6() & INTEL_RC6_ENABLE) &&
+	if ((intel_rc6_enabled() & INTEL_RC6_ENABLE) &&
 	    (pcbr >> VLV_PCBR_ADDR_SHIFT))
 		rc6_mode = GEN7_RC_CTL_TO_MODE;
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
-	/* 4 Program defaults and thresholds for RPS*/
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+}
+
+static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+	/* 1: Program defaults and thresholds for RPS*/
 	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
 	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
@@ -7112,7 +7309,7 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
-	/* 5: Enable RPS */
+	/* 2: Enable RPS */
 	I915_WRITE(GEN6_RP_CONTROL,
 		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
 		   GEN6_RP_MEDIA_IS_GFX |
@@ -7139,13 +7336,11 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
+static void valleyview_enable_rc6(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	u32 gtfifodbg, val, rc6_mode = 0;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	u32 gtfifodbg, rc6_mode = 0;
 
 	valleyview_check_pctx(dev_priv);
 
@@ -7156,28 +7351,11 @@ static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 		I915_WRITE(GTFIFODBG, gtfifodbg);
 	}
 
-	/* If VLV, Forcewake all wells, else re-direct to regular path */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	/*  Disable RC states. */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
-	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);
-
-	I915_WRITE(GEN6_RP_CONTROL,
-		   GEN6_RP_MEDIA_TURBO |
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   GEN6_RP_DOWN_IDLE_CONT);
-
 	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
@@ -7187,7 +7365,7 @@ static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
 
-	/* allows RC6 residency counter to work */
+	/* Allows RC6 residency counter to work */
 	I915_WRITE(VLV_COUNTER_CONTROL,
 		   _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
 				      VLV_MEDIA_RC0_COUNT_EN |
@@ -7195,13 +7373,38 @@ static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 				      VLV_MEDIA_RC6_COUNT_EN |
 				      VLV_RENDER_RC6_COUNT_EN));
 
-	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
+	if (intel_rc6_enabled() & INTEL_RC6_ENABLE)
 		rc6_mode = GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
 
 	intel_print_rc6_info(dev_priv, rc6_mode);
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+}
+
+static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
+	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);
+
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_TURBO |
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX |
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_CONT);
+
 	/* Setting Fixed Bias */
 	val = VLV_OVERRIDE_EN |
 		  VLV_SOC_TDP_EN |
@@ -7409,7 +7612,7 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
 
 	lockdep_assert_held(&mchdev_lock);
 
-	pxvid = I915_READ(PXVFREQ(dev_priv->rps.cur_freq));
+	pxvid = I915_READ(PXVFREQ(dev_priv->gt_pm.rps.cur_freq));
 	pxvid = (pxvid >> 24) & 0x7f;
 	ext_v = pvid_to_extvid(dev_priv, pxvid);
 
@@ -7696,17 +7899,19 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
 
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/*
 	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
 	 * requirement.
 	 */
-	if (!i915.enable_rc6) {
+	if (!i915_modparams.enable_rc6) {
 		DRM_INFO("RC6 disabled, disabling runtime PM support\n");
 		intel_runtime_pm_get(dev_priv);
 	}
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	mutex_lock(&dev_priv->rps.hw_lock);
+	mutex_lock(&dev_priv->pcu_lock);
 
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
@@ -7717,16 +7922,16 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 		gen6_init_rps_frequencies(dev_priv);
 
 	/* Derive initial user preferences/limits from the hardware limits */
-	dev_priv->rps.idle_freq = dev_priv->rps.min_freq;
-	dev_priv->rps.cur_freq = dev_priv->rps.idle_freq;
+	rps->idle_freq = rps->min_freq;
+	rps->cur_freq = rps->idle_freq;
 
-	dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
-	dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+	rps->max_freq_softlimit = rps->max_freq;
+	rps->min_freq_softlimit = rps->min_freq;
 
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-		dev_priv->rps.min_freq_softlimit =
+		rps->min_freq_softlimit =
 			max_t(int,
-			      dev_priv->rps.efficient_freq,
+			      rps->efficient_freq,
 			      intel_freq_opcode(dev_priv, 450));
 
 	/* After setting max-softlimit, find the overclock max freq */
@@ -7737,16 +7942,16 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 		sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, &params);
 		if (params & BIT(31)) { /* OC supported */
 			DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n",
-					 (dev_priv->rps.max_freq & 0xff) * 50,
+					 (rps->max_freq & 0xff) * 50,
 					 (params & 0xff) * 50);
-			dev_priv->rps.max_freq = params & 0xff;
+			rps->max_freq = params & 0xff;
 		}
 	}
 
 	/* Finally allow us to boost to max by default */
-	dev_priv->rps.boost_freq = dev_priv->rps.max_freq;
+	rps->boost_freq = rps->max_freq;
 
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	intel_autoenable_gt_powersave(dev_priv);
@@ -7757,7 +7962,7 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 	if (IS_VALLEYVIEW(dev_priv))
 		valleyview_cleanup_gt_powersave(dev_priv);
 
-	if (!i915.enable_rc6)
+	if (!i915_modparams.enable_rc6)
 		intel_runtime_pm_put(dev_priv);
 }
 
@@ -7774,7 +7979,7 @@ void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) < 6)
 		return;
 
-	if (cancel_delayed_work_sync(&dev_priv->rps.autoenable_work))
+	if (cancel_delayed_work_sync(&dev_priv->gt_pm.autoenable_work))
 		intel_runtime_pm_put(dev_priv);
 
 	/* gen6_rps_idle() will be called later to disable interrupts */
@@ -7782,90 +7987,168 @@ void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv)
 
 void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	dev_priv->rps.enabled = true; /* force disabling */
+	dev_priv->gt_pm.rps.enabled = true; /* force RPS disabling */
+	dev_priv->gt_pm.rc6.enabled = true; /* force RC6 disabling */
 	intel_disable_gt_powersave(dev_priv);
 
 	gen6_reset_rps_interrupts(dev_priv);
 }
 
-void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
+static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 {
-	if (!READ_ONCE(dev_priv->rps.enabled))
+	lockdep_assert_held(&i915->pcu_lock);
+
+	if (!i915->gt_pm.llc_pstate.enabled)
 		return;
 
-	mutex_lock(&dev_priv->rps.hw_lock);
+	/* Currently there is no HW configuration to be done to disable. */
 
-	if (INTEL_GEN(dev_priv) >= 9) {
+	i915->gt_pm.llc_pstate.enabled = false;
+}
+
+static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+{
+	lockdep_assert_held(&dev_priv->pcu_lock);
+
+	if (!dev_priv->gt_pm.rc6.enabled)
+		return;
+
+	if (INTEL_GEN(dev_priv) >= 9)
 		gen9_disable_rc6(dev_priv);
+	else if (IS_CHERRYVIEW(dev_priv))
+		cherryview_disable_rc6(dev_priv);
+	else if (IS_VALLEYVIEW(dev_priv))
+		valleyview_disable_rc6(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 6)
+		gen6_disable_rc6(dev_priv);
+
+	dev_priv->gt_pm.rc6.enabled = false;
+}
+
+static void intel_disable_rps(struct drm_i915_private *dev_priv)
+{
+	lockdep_assert_held(&dev_priv->pcu_lock);
+
+	if (!dev_priv->gt_pm.rps.enabled)
+		return;
+
+	if (INTEL_GEN(dev_priv) >= 9)
 		gen9_disable_rps(dev_priv);
-	} else if (IS_CHERRYVIEW(dev_priv)) {
+	else if (IS_CHERRYVIEW(dev_priv))
 		cherryview_disable_rps(dev_priv);
-	} else if (IS_VALLEYVIEW(dev_priv)) {
+	else if (IS_VALLEYVIEW(dev_priv))
 		valleyview_disable_rps(dev_priv);
-	} else if (INTEL_GEN(dev_priv) >= 6) {
+	else if (INTEL_GEN(dev_priv) >= 6)
 		gen6_disable_rps(dev_priv);
-	}  else if (IS_IRONLAKE_M(dev_priv)) {
+	else if (IS_IRONLAKE_M(dev_priv))
 		ironlake_disable_drps(dev_priv);
-	}
 
-	dev_priv->rps.enabled = false;
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	dev_priv->gt_pm.rps.enabled = false;
 }
 
-void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
+void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	/* We shouldn't be disabling as we submit, so this should be less
-	 * racy than it appears!
-	 */
-	if (READ_ONCE(dev_priv->rps.enabled))
+	mutex_lock(&dev_priv->pcu_lock);
+
+	intel_disable_rc6(dev_priv);
+	intel_disable_rps(dev_priv);
+	if (HAS_LLC(dev_priv))
+		intel_disable_llc_pstate(dev_priv);
+
+	mutex_unlock(&dev_priv->pcu_lock);
+}
+
+static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
+{
+	lockdep_assert_held(&i915->pcu_lock);
+
+	if (i915->gt_pm.llc_pstate.enabled)
 		return;
 
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(dev_priv))
+	gen6_update_ring_freq(i915);
+
+	i915->gt_pm.llc_pstate.enabled = true;
+}
+
+static void intel_enable_rc6(struct drm_i915_private *dev_priv)
+{
+	lockdep_assert_held(&dev_priv->pcu_lock);
+
+	if (dev_priv->gt_pm.rc6.enabled)
 		return;
 
-	mutex_lock(&dev_priv->rps.hw_lock);
+	if (IS_CHERRYVIEW(dev_priv))
+		cherryview_enable_rc6(dev_priv);
+	else if (IS_VALLEYVIEW(dev_priv))
+		valleyview_enable_rc6(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 9)
+		gen9_enable_rc6(dev_priv);
+	else if (IS_BROADWELL(dev_priv))
+		gen8_enable_rc6(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 6)
+		gen6_enable_rc6(dev_priv);
+
+	dev_priv->gt_pm.rc6.enabled = true;
+}
+
+static void intel_enable_rps(struct drm_i915_private *dev_priv)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	lockdep_assert_held(&dev_priv->pcu_lock);
+
+	if (rps->enabled)
+		return;
 
 	if (IS_CHERRYVIEW(dev_priv)) {
 		cherryview_enable_rps(dev_priv);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		valleyview_enable_rps(dev_priv);
 	} else if (INTEL_GEN(dev_priv) >= 9) {
-		gen9_enable_rc6(dev_priv);
 		gen9_enable_rps(dev_priv);
-		if (IS_GEN9_BC(dev_priv))
-			gen6_update_ring_freq(dev_priv);
 	} else if (IS_BROADWELL(dev_priv)) {
 		gen8_enable_rps(dev_priv);
-		gen6_update_ring_freq(dev_priv);
 	} else if (INTEL_GEN(dev_priv) >= 6) {
 		gen6_enable_rps(dev_priv);
-		gen6_update_ring_freq(dev_priv);
 	} else if (IS_IRONLAKE_M(dev_priv)) {
 		ironlake_enable_drps(dev_priv);
 		intel_init_emon(dev_priv);
 	}
 
-	WARN_ON(dev_priv->rps.max_freq < dev_priv->rps.min_freq);
-	WARN_ON(dev_priv->rps.idle_freq > dev_priv->rps.max_freq);
+	WARN_ON(rps->max_freq < rps->min_freq);
+	WARN_ON(rps->idle_freq > rps->max_freq);
+
+	WARN_ON(rps->efficient_freq < rps->min_freq);
+	WARN_ON(rps->efficient_freq > rps->max_freq);
+
+	rps->enabled = true;
+}
+
+void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
+{
+	/* Powersaving is controlled by the host when inside a VM */
+	if (intel_vgpu_active(dev_priv))
+		return;
+
+	mutex_lock(&dev_priv->pcu_lock);
 
-	WARN_ON(dev_priv->rps.efficient_freq < dev_priv->rps.min_freq);
-	WARN_ON(dev_priv->rps.efficient_freq > dev_priv->rps.max_freq);
+	intel_enable_rc6(dev_priv);
+	intel_enable_rps(dev_priv);
+	if (HAS_LLC(dev_priv))
+		intel_enable_llc_pstate(dev_priv);
 
-	dev_priv->rps.enabled = true;
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 static void __intel_autoenable_gt_powersave(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), rps.autoenable_work.work);
+		container_of(work,
+			     typeof(*dev_priv),
+			     gt_pm.autoenable_work.work);
 	struct intel_engine_cs *rcs;
 	struct drm_i915_gem_request *req;
 
-	if (READ_ONCE(dev_priv->rps.enabled))
-		goto out;
-
 	rcs = dev_priv->engine[RCS];
 	if (rcs->last_retired_context)
 		goto out;
@@ -7879,7 +8162,7 @@ static void __intel_autoenable_gt_powersave(struct work_struct *work)
 	if (IS_ERR(req))
 		goto unlock;
 
-	if (!i915.enable_execlists && i915_switch_context(req) == 0)
+	if (!i915_modparams.enable_execlists && i915_switch_context(req) == 0)
 		rcs->init_context(req);
 
 	/* Mark the device busy, calling intel_enable_gt_powersave() */
@@ -7893,9 +8176,6 @@ out:
 
 void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	if (READ_ONCE(dev_priv->rps.enabled))
-		return;
-
 	if (IS_IRONLAKE_M(dev_priv)) {
 		ironlake_enable_drps(dev_priv);
 		intel_init_emon(dev_priv);
@@ -7913,7 +8193,7 @@ void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv)
 		 * runtime resume it's necessary).
 		 */
 		if (queue_delayed_work(dev_priv->wq,
-				       &dev_priv->rps.autoenable_work,
+				       &dev_priv->gt_pm.autoenable_work,
 				       round_jiffies_up_relative(HZ)))
 			intel_runtime_pm_get_noresume(dev_priv);
 	}
@@ -7943,19 +8223,7 @@ static void g4x_disable_trickle_feed(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(WM3_LP_ILK, I915_READ(WM3_LP_ILK) & ~WM1_LP_SR_EN);
-	I915_WRITE(WM2_LP_ILK, I915_READ(WM2_LP_ILK) & ~WM1_LP_SR_EN);
-	I915_WRITE(WM1_LP_ILK, I915_READ(WM1_LP_ILK) & ~WM1_LP_SR_EN);
-
-	/*
-	 * Don't touch WM1S_LP_EN here.
-	 * Doing so could cause underruns.
-	 */
-}
-
-static void ironlake_init_clock_gating(struct drm_i915_private *dev_priv)
+static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
@@ -7988,8 +8256,6 @@ static void ironlake_init_clock_gating(struct drm_i915_private *dev_priv)
 		   (I915_READ(DISP_ARB_CTL) |
 		    DISP_FBC_WM_DIS));
 
-	ilk_init_lp_watermarks(dev_priv);
-
 	/*
 	 * Based on the document from hardware guys the following bits
 	 * should be set unconditionally in order to enable FBC.
@@ -8102,8 +8368,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_GT_MODE,
 		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
 
-	ilk_init_lp_watermarks(dev_priv);
-
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 
@@ -8220,14 +8484,17 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
 				   int high_prio_credits)
 {
 	u32 misccpctl;
+	u32 val;
 
 	/* WaTempDisableDOPClkGating:bdw */
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 
-	I915_WRITE(GEN8_L3SQCREG1,
-		   L3_GENERAL_PRIO_CREDITS(general_prio_credits) |
-		   L3_HIGH_PRIO_CREDITS(high_prio_credits));
+	val = I915_READ(GEN8_L3SQCREG1);
+	val &= ~L3_PRIO_CREDITS_MASK;
+	val |= L3_GENERAL_PRIO_CREDITS(general_prio_credits);
+	val |= L3_HIGH_PRIO_CREDITS(high_prio_credits);
+	I915_WRITE(GEN8_L3SQCREG1, val);
 
 	/*
 	 * Wait at least 100 clocks before re-enabling clock gating.
@@ -8238,7 +8505,57 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
 
-static void kabylake_init_clock_gating(struct drm_i915_private *dev_priv)
+static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	if (!HAS_PCH_CNP(dev_priv))
+		return;
+
+	/* Wa #1181 */
+	I915_WRITE(SOUTH_DSPCLK_GATE_D, I915_READ(SOUTH_DSPCLK_GATE_D) |
+		   CNP_PWM_CGE_GATING_DISABLE);
+}
+
+static void cnl_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+	cnp_init_clock_gating(dev_priv);
+
+	/* This is not an Wa. Enable for better image quality */
+	I915_WRITE(_3D_CHICKEN3,
+		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE));
+
+	/* WaEnableChickenDCPR:cnl */
+	I915_WRITE(GEN8_CHICKEN_DCPR_1,
+		   I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
+
+	/* WaFbcWakeMemOn:cnl */
+	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+		   DISP_FBC_MEMORY_WAKE);
+
+	/* WaSarbUnitClockGatingDisable:cnl (pre-prod) */
+	if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_B0))
+		I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE,
+			   I915_READ(SLICE_UNIT_LEVEL_CLKGATE) |
+			   SARBUNIT_CLKGATE_DIS);
+
+	/* Display WA #1133: WaFbcSkipSegments:cnl */
+	val = I915_READ(ILK_DPFC_CHICKEN);
+	val &= ~GLK_SKIP_SEG_COUNT_MASK;
+	val |= GLK_SKIP_SEG_EN | GLK_SKIP_SEG_COUNT(1);
+	I915_WRITE(ILK_DPFC_CHICKEN, val);
+}
+
+static void cfl_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	cnp_init_clock_gating(dev_priv);
+	gen9_init_clock_gating(dev_priv);
+
+	/* WaFbcNukeOnHostModify:cfl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+}
+
+static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	gen9_init_clock_gating(dev_priv);
 
@@ -8252,12 +8569,12 @@ static void kabylake_init_clock_gating(struct drm_i915_private *dev_priv)
 		I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaFbcNukeOnHostModify:kbl,cfl */
+	/* WaFbcNukeOnHostModify:kbl */
 	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
 		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
 }
 
-static void skylake_init_clock_gating(struct drm_i915_private *dev_priv)
+static void skl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	gen9_init_clock_gating(dev_priv);
 
@@ -8270,12 +8587,13 @@ static void skylake_init_clock_gating(struct drm_i915_private *dev_priv)
 		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
 }
 
-static void broadwell_init_clock_gating(struct drm_i915_private *dev_priv)
+static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	/* The GTT cache must be disabled if the system is using 2M pages. */
+	bool can_use_gtt_cache = !HAS_PAGE_SIZES(dev_priv,
+						 I915_GTT_PAGE_SIZE_2M);
 	enum pipe pipe;
 
-	ilk_init_lp_watermarks(dev_priv);
-
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -8306,12 +8624,8 @@ static void broadwell_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaProgramL3SqcReg1Default:bdw */
 	gen8_set_l3sqc_credits(dev_priv, 30, 2);
 
-	/*
-	 * WaGttCachingOffByDefault:bdw
-	 * GTT cache may not work with big pages, so if those
-	 * are ever enabled GTT cache may need to be disabled.
-	 */
-	I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL);
+	/* WaGttCachingOffByDefault:bdw */
+	I915_WRITE(HSW_GTT_CACHE_EN, can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
 
 	/* WaKVMNotificationOnConfigChange:bdw */
 	I915_WRITE(CHICKEN_PAR2_1, I915_READ(CHICKEN_PAR2_1)
@@ -8328,10 +8642,8 @@ static void broadwell_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(GEN6_UCGCTL1) | GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
 }
 
-static void haswell_init_clock_gating(struct drm_i915_private *dev_priv)
+static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	ilk_init_lp_watermarks(dev_priv);
-
 	/* L3 caching of data atomics doesn't work -- disable it. */
 	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
 	I915_WRITE(HSW_ROW_CHICKEN3,
@@ -8375,19 +8687,13 @@ static void haswell_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
-	/* WaRsPkgCStateDisplayPMReq:hsw */
-	I915_WRITE(CHICKEN_PAR1_1,
-		   I915_READ(CHICKEN_PAR1_1) | FORCE_ARB_IDLE_PLANES);
-
 	lpt_init_clock_gating(dev_priv);
 }
 
-static void ivybridge_init_clock_gating(struct drm_i915_private *dev_priv)
+static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	uint32_t snpcr;
 
-	ilk_init_lp_watermarks(dev_priv);
-
 	I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableEarlyCull:ivb */
@@ -8479,7 +8785,7 @@ static void ivybridge_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen6_check_mch_setup(dev_priv);
 }
 
-static void valleyview_init_clock_gating(struct drm_i915_private *dev_priv)
+static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/* WaDisableEarlyCull:vlv */
 	I915_WRITE(_3D_CHICKEN3,
@@ -8559,7 +8865,7 @@ static void valleyview_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS);
 }
 
-static void cherryview_init_clock_gating(struct drm_i915_private *dev_priv)
+static void chv_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
@@ -8619,7 +8925,7 @@ static void g4x_init_clock_gating(struct drm_i915_private *dev_priv)
 	g4x_disable_trickle_feed(dev_priv);
 }
 
-static void crestline_init_clock_gating(struct drm_i915_private *dev_priv)
+static void i965gm_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
 	I915_WRITE(RENCLK_GATE_D2, 0);
@@ -8633,7 +8939,7 @@ static void crestline_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
-static void broadwater_init_clock_gating(struct drm_i915_private *dev_priv)
+static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(RENCLK_GATE_D1, I965_RCZ_CLOCK_GATE_DISABLE |
 		   I965_RCC_CLOCK_GATE_DISABLE |
@@ -8718,34 +9024,38 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
  */
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
-	if (IS_SKYLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = skylake_init_clock_gating;
-	else if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv))
-		dev_priv->display.init_clock_gating = kabylake_init_clock_gating;
+	if (IS_CANNONLAKE(dev_priv))
+		dev_priv->display.init_clock_gating = cnl_init_clock_gating;
+	else if (IS_COFFEELAKE(dev_priv))
+		dev_priv->display.init_clock_gating = cfl_init_clock_gating;
+	else if (IS_SKYLAKE(dev_priv))
+		dev_priv->display.init_clock_gating = skl_init_clock_gating;
+	else if (IS_KABYLAKE(dev_priv))
+		dev_priv->display.init_clock_gating = kbl_init_clock_gating;
 	else if (IS_BROXTON(dev_priv))
 		dev_priv->display.init_clock_gating = bxt_init_clock_gating;
 	else if (IS_GEMINILAKE(dev_priv))
 		dev_priv->display.init_clock_gating = glk_init_clock_gating;
 	else if (IS_BROADWELL(dev_priv))
-		dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
+		dev_priv->display.init_clock_gating = bdw_init_clock_gating;
 	else if (IS_CHERRYVIEW(dev_priv))
-		dev_priv->display.init_clock_gating = cherryview_init_clock_gating;
+		dev_priv->display.init_clock_gating = chv_init_clock_gating;
 	else if (IS_HASWELL(dev_priv))
-		dev_priv->display.init_clock_gating = haswell_init_clock_gating;
+		dev_priv->display.init_clock_gating = hsw_init_clock_gating;
 	else if (IS_IVYBRIDGE(dev_priv))
-		dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
+		dev_priv->display.init_clock_gating = ivb_init_clock_gating;
 	else if (IS_VALLEYVIEW(dev_priv))
-		dev_priv->display.init_clock_gating = valleyview_init_clock_gating;
+		dev_priv->display.init_clock_gating = vlv_init_clock_gating;
 	else if (IS_GEN6(dev_priv))
 		dev_priv->display.init_clock_gating = gen6_init_clock_gating;
 	else if (IS_GEN5(dev_priv))
-		dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
+		dev_priv->display.init_clock_gating = ilk_init_clock_gating;
 	else if (IS_G4X(dev_priv))
 		dev_priv->display.init_clock_gating = g4x_init_clock_gating;
 	else if (IS_I965GM(dev_priv))
-		dev_priv->display.init_clock_gating = crestline_init_clock_gating;
+		dev_priv->display.init_clock_gating = i965gm_init_clock_gating;
 	else if (IS_I965G(dev_priv))
-		dev_priv->display.init_clock_gating = broadwater_init_clock_gating;
+		dev_priv->display.init_clock_gating = i965g_init_clock_gating;
 	else if (IS_GEN3(dev_priv))
 		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
 	else if (IS_I85X(dev_priv) || IS_I865G(dev_priv))
@@ -8848,6 +9158,7 @@ static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv)
 	case GEN6_PCODE_SUCCESS:
 		return 0;
 	case GEN6_PCODE_UNIMPLEMENTED_CMD:
+		return -ENODEV;
 	case GEN6_PCODE_ILLEGAL_CMD:
 		return -ENXIO;
 	case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
@@ -8887,7 +9198,7 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 {
 	int status;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
 
 	/* GEN6_PCODE_* are outside of the forcewake domain, we can
 	 * use te fw I915_READ variants to reduce the amount of work
@@ -8895,7 +9206,8 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 	 */
 
 	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
-		DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed\n");
+		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps\n",
+				 mbox, __builtin_return_address(0));
 		return -EAGAIN;
 	}
 
@@ -8906,7 +9218,8 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 	if (__intel_wait_for_register_fw(dev_priv,
 					 GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
 					 500, 0, NULL)) {
-		DRM_ERROR("timeout waiting for pcode read (%d) to finish\n", mbox);
+		DRM_ERROR("timeout waiting for pcode read (from mbox %x) to finish for %ps\n",
+			  mbox, __builtin_return_address(0));
 		return -ETIMEDOUT;
 	}
 
@@ -8919,8 +9232,8 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 		status = gen6_check_mailbox_status(dev_priv);
 
 	if (status) {
-		DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n",
-				 status);
+		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
+				 mbox, __builtin_return_address(0), status);
 		return status;
 	}
 
@@ -8932,7 +9245,7 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 {
 	int status;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
 
 	/* GEN6_PCODE_* are outside of the forcewake domain, we can
 	 * use te fw I915_READ variants to reduce the amount of work
@@ -8940,7 +9253,8 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 	 */
 
 	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
-		DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed\n");
+		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps\n",
+				 val, mbox, __builtin_return_address(0));
 		return -EAGAIN;
 	}
 
@@ -8951,7 +9265,8 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 	if (__intel_wait_for_register_fw(dev_priv,
 					 GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
 					 500, 0, NULL)) {
-		DRM_ERROR("timeout waiting for pcode write (%d) to finish\n", mbox);
+		DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n",
+			  val, mbox, __builtin_return_address(0));
 		return -ETIMEDOUT;
 	}
 
@@ -8963,8 +9278,8 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 		status = gen6_check_mailbox_status(dev_priv);
 
 	if (status) {
-		DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n",
-				 status);
+		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
+				 val, mbox, __builtin_return_address(0), status);
 		return status;
 	}
 
@@ -9007,7 +9322,7 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 	u32 status;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
 
 #define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
 				   &status)
@@ -9049,36 +9364,44 @@ out:
 
 static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/*
 	 * N = val - 0xb7
 	 * Slow = Fast = GPLL ref * N
 	 */
-	return DIV_ROUND_CLOSEST(dev_priv->rps.gpll_ref_freq * (val - 0xb7), 1000);
+	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * (val - 0xb7), 1000);
 }
 
 static int byt_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
-	return DIV_ROUND_CLOSEST(1000 * val, dev_priv->rps.gpll_ref_freq) + 0xb7;
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	return DIV_ROUND_CLOSEST(1000 * val, rps->gpll_ref_freq) + 0xb7;
 }
 
 static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/*
 	 * N = val / 2
 	 * CU (slow) = CU2x (fast) / 2 = GPLL ref * N / 2
 	 */
-	return DIV_ROUND_CLOSEST(dev_priv->rps.gpll_ref_freq * val, 2 * 2 * 1000);
+	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * val, 2 * 2 * 1000);
 }
 
 static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
 	/* CHV needs even values */
-	return DIV_ROUND_CLOSEST(2 * 1000 * val, dev_priv->rps.gpll_ref_freq) * 2;
+	return DIV_ROUND_CLOSEST(2 * 1000 * val, rps->gpll_ref_freq) * 2;
 }
 
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
-	if (IS_GEN9(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 9)
 		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
 					 GEN9_FREQ_SCALER);
 	else if (IS_CHERRYVIEW(dev_priv))
@@ -9091,7 +9414,7 @@ int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
 
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
-	if (IS_GEN9(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 9)
 		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
 					 GT_FREQUENCY_MULTIPLIER);
 	else if (IS_CHERRYVIEW(dev_priv))
@@ -9102,54 +9425,16 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
 }
 
-struct request_boost {
-	struct work_struct work;
-	struct drm_i915_gem_request *req;
-};
-
-static void __intel_rps_boost_work(struct work_struct *work)
-{
-	struct request_boost *boost = container_of(work, struct request_boost, work);
-	struct drm_i915_gem_request *req = boost->req;
-
-	if (!i915_gem_request_completed(req))
-		gen6_rps_boost(req->i915, NULL, req->emitted_jiffies);
-
-	i915_gem_request_put(req);
-	kfree(boost);
-}
-
-void intel_queue_rps_boost_for_request(struct drm_i915_gem_request *req)
-{
-	struct request_boost *boost;
-
-	if (req == NULL || INTEL_GEN(req->i915) < 6)
-		return;
-
-	if (i915_gem_request_completed(req))
-		return;
-
-	boost = kmalloc(sizeof(*boost), GFP_ATOMIC);
-	if (boost == NULL)
-		return;
-
-	boost->req = i915_gem_request_get(req);
-
-	INIT_WORK(&boost->work, __intel_rps_boost_work);
-	queue_work(req->i915->wq, &boost->work);
-}
-
 void intel_pm_setup(struct drm_i915_private *dev_priv)
 {
-	mutex_init(&dev_priv->rps.hw_lock);
-	spin_lock_init(&dev_priv->rps.client_lock);
+	mutex_init(&dev_priv->pcu_lock);
 
-	INIT_DELAYED_WORK(&dev_priv->rps.autoenable_work,
+	INIT_DELAYED_WORK(&dev_priv->gt_pm.autoenable_work,
 			  __intel_autoenable_gt_powersave);
-	INIT_LIST_HEAD(&dev_priv->rps.clients);
+	atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
 
-	dev_priv->pm.suspended = false;
-	atomic_set(&dev_priv->pm.wakeref_count, 0);
+	dev_priv->runtime_pm.suspended = false;
+	atomic_set(&dev_priv->runtime_pm.wakeref_count, 0);
 }
 
 static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
@@ -9202,7 +9487,7 @@ u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
 {
 	u64 time_hw, units, div;
 
-	if (!intel_enable_rc6())
+	if (!intel_rc6_enabled())
 		return 0;
 
 	intel_runtime_pm_get(dev_priv);