1 files changed, 238 insertions, 160 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 347d4df49a9b..6a04761ddc0f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -487,20 +487,6 @@ static const struct intel_watermark_params g4x_cursor_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = G4X_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params valleyview_wm_info = {
-	.fifo_size = VALLEYVIEW_FIFO_SIZE,
-	.max_wm = VALLEYVIEW_MAX_WM,
-	.default_wm = VALLEYVIEW_MAX_WM,
-	.guard_size = 2,
-	.cacheline_size = G4X_FIFO_LINE_SIZE,
-};
-static const struct intel_watermark_params valleyview_cursor_wm_info = {
-	.fifo_size = I965_CURSOR_FIFO,
-	.max_wm = VALLEYVIEW_CURSOR_MAX_WM,
-	.default_wm = I965_CURSOR_DFT_WM,
-	.guard_size = 2,
-	.cacheline_size = G4X_FIFO_LINE_SIZE,
-};
 static const struct intel_watermark_params i965_cursor_wm_info = {
 	.fifo_size = I965_CURSOR_FIFO,
 	.max_wm = I965_CURSOR_MAX_WM,
@@ -2010,11 +1996,18 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
 		cur_latency *= 5;
 	}
 
-	result->pri_val = ilk_compute_pri_wm(cstate, pristate,
-					     pri_latency, level);
-	result->spr_val = ilk_compute_spr_wm(cstate, sprstate, spr_latency);
-	result->cur_val = ilk_compute_cur_wm(cstate, curstate, cur_latency);
-	result->fbc_val = ilk_compute_fbc_wm(cstate, pristate, result->pri_val);
+	if (pristate) {
+		result->pri_val = ilk_compute_pri_wm(cstate, pristate,
+						     pri_latency, level);
+		result->fbc_val = ilk_compute_fbc_wm(cstate, pristate, result->pri_val);
+	}
+
+	if (sprstate)
+		result->spr_val = ilk_compute_spr_wm(cstate, sprstate, spr_latency);
+
+	if (curstate)
+		result->cur_val = ilk_compute_cur_wm(cstate, curstate, cur_latency);
+
 	result->enable = true;
 }
 
@@ -2278,100 +2271,171 @@ static void skl_setup_wm_latency(struct drm_device *dev)
 	intel_print_wm_latency(dev, "Gen9 Plane", dev_priv->wm.skl_latency);
 }
 
+static bool ilk_validate_pipe_wm(struct drm_device *dev,
+				 struct intel_pipe_wm *pipe_wm)
+{
+	/* LP0 watermark maximums depend on this pipe alone */
+	const struct intel_wm_config config = {
+		.num_pipes_active = 1,
+		.sprites_enabled = pipe_wm->sprites_enabled,
+		.sprites_scaled = pipe_wm->sprites_scaled,
+	};
+	struct ilk_wm_maximums max;
+
+	/* LP0 watermarks always use 1/2 DDB partitioning */
+	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
+
+	/* At least LP0 must be valid */
+	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) {
+		DRM_DEBUG_KMS("LP0 watermark invalid\n");
+		return false;
+	}
+
+	return true;
+}
+
 /* Compute new watermarks for the pipe */
-static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc,
-			       struct drm_atomic_state *state)
+static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 {
+	struct drm_atomic_state *state = cstate->base.state;
+	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 	struct intel_pipe_wm *pipe_wm;
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_device *dev = state->dev;
 	const struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc_state *cstate = NULL;
 	struct intel_plane *intel_plane;
-	struct drm_plane_state *ps;
 	struct intel_plane_state *pristate = NULL;
 	struct intel_plane_state *sprstate = NULL;
 	struct intel_plane_state *curstate = NULL;
-	int level, max_level = ilk_wm_max_level(dev);
-	/* LP0 watermark maximums depend on this pipe alone */
-	struct intel_wm_config config = {
-		.num_pipes_active = 1,
-	};
+	int level, max_level = ilk_wm_max_level(dev), usable_level;
 	struct ilk_wm_maximums max;
 
-	cstate = intel_atomic_get_crtc_state(state, intel_crtc);
-	if (IS_ERR(cstate))
-		return PTR_ERR(cstate);
-
 	pipe_wm = &cstate->wm.optimal.ilk;
-	memset(pipe_wm, 0, sizeof(*pipe_wm));
 
 	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		ps = drm_atomic_get_plane_state(state,
-						&intel_plane->base);
-		if (IS_ERR(ps))
-			return PTR_ERR(ps);
+		struct intel_plane_state *ps;
+
+		ps = intel_atomic_get_existing_plane_state(state,
+							   intel_plane);
+		if (!ps)
+			continue;
 
 		if (intel_plane->base.type == DRM_PLANE_TYPE_PRIMARY)
-			pristate = to_intel_plane_state(ps);
+			pristate = ps;
 		else if (intel_plane->base.type == DRM_PLANE_TYPE_OVERLAY)
-			sprstate = to_intel_plane_state(ps);
+			sprstate = ps;
 		else if (intel_plane->base.type == DRM_PLANE_TYPE_CURSOR)
-			curstate = to_intel_plane_state(ps);
+			curstate = ps;
 	}
 
-	config.sprites_enabled = sprstate->visible;
-	config.sprites_scaled = sprstate->visible &&
-		(drm_rect_width(&sprstate->dst) != drm_rect_width(&sprstate->src) >> 16 ||
-		drm_rect_height(&sprstate->dst) != drm_rect_height(&sprstate->src) >> 16);
-
 	pipe_wm->pipe_enabled = cstate->base.active;
-	pipe_wm->sprites_enabled = config.sprites_enabled;
-	pipe_wm->sprites_scaled = config.sprites_scaled;
+	if (sprstate) {
+		pipe_wm->sprites_enabled = sprstate->visible;
+		pipe_wm->sprites_scaled = sprstate->visible &&
+			(drm_rect_width(&sprstate->dst) != drm_rect_width(&sprstate->src) >> 16 ||
+			 drm_rect_height(&sprstate->dst) != drm_rect_height(&sprstate->src) >> 16);
+	}
+
+	usable_level = max_level;
 
 	/* ILK/SNB: LP2+ watermarks only w/o sprites */
-	if (INTEL_INFO(dev)->gen <= 6 && sprstate->visible)
-		max_level = 1;
+	if (INTEL_INFO(dev)->gen <= 6 && pipe_wm->sprites_enabled)
+		usable_level = 1;
 
 	/* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */
-	if (config.sprites_scaled)
-		max_level = 0;
+	if (pipe_wm->sprites_scaled)
+		usable_level = 0;
 
 	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
-			     pristate, sprstate, curstate, &pipe_wm->wm[0]);
+			     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];
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate);
 
-	/* LP0 watermarks always use 1/2 DDB partitioning */
-	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
-
-	/* At least LP0 must be valid */
-	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]))
+	if (!ilk_validate_pipe_wm(dev, pipe_wm))
 		return -EINVAL;
 
 	ilk_compute_wm_reg_maximums(dev, 1, &max);
 
 	for (level = 1; level <= max_level; level++) {
-		struct intel_wm_level wm = {};
+		struct intel_wm_level *wm = &pipe_wm->raw_wm[level];
 
 		ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate,
-				     pristate, sprstate, curstate, &wm);
+				     pristate, sprstate, curstate, wm);
 
 		/*
 		 * Disable any watermark level that exceeds the
 		 * register maximums since such watermarks are
 		 * always invalid.
 		 */
-		if (!ilk_validate_wm_level(level, &max, &wm))
-			break;
+		if (level > usable_level)
+			continue;
 
-		pipe_wm->wm[level] = wm;
+		if (ilk_validate_wm_level(level, &max, wm))
+			pipe_wm->wm[level] = *wm;
+		else
+			usable_level = level;
 	}
 
 	return 0;
 }
 
 /*
+ * Build a set of 'intermediate' watermark values that satisfy both the old
+ * state and the new state.  These can be programmed to the hardware
+ * immediately.
+ */
+static int ilk_compute_intermediate_wm(struct drm_device *dev,
+				       struct intel_crtc *intel_crtc,
+				       struct intel_crtc_state *newstate)
+{
+	struct intel_pipe_wm *a = &newstate->wm.intermediate;
+	struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk;
+	int level, max_level = ilk_wm_max_level(dev);
+
+	/*
+	 * Start with the final, target watermarks, then combine with the
+	 * currently active watermarks to get values that are safe both before
+	 * and after the vblank.
+	 */
+	*a = newstate->wm.optimal.ilk;
+	a->pipe_enabled |= b->pipe_enabled;
+	a->sprites_enabled |= b->sprites_enabled;
+	a->sprites_scaled |= b->sprites_scaled;
+
+	for (level = 0; level <= max_level; level++) {
+		struct intel_wm_level *a_wm = &a->wm[level];
+		const struct intel_wm_level *b_wm = &b->wm[level];
+
+		a_wm->enable &= b_wm->enable;
+		a_wm->pri_val = max(a_wm->pri_val, b_wm->pri_val);
+		a_wm->spr_val = max(a_wm->spr_val, b_wm->spr_val);
+		a_wm->cur_val = max(a_wm->cur_val, b_wm->cur_val);
+		a_wm->fbc_val = max(a_wm->fbc_val, b_wm->fbc_val);
+	}
+
+	/*
+	 * We need to make sure that these merged watermark values are
+	 * actually a valid configuration themselves.  If they're not,
+	 * there's no safe way to transition from the old state to
+	 * the new state, so we need to fail the atomic transaction.
+	 */
+	if (!ilk_validate_pipe_wm(dev, a))
+		return -EINVAL;
+
+	/*
+	 * If our intermediate WM are identical to the final WM, then we can
+	 * omit the post-vblank programming; only update if it's different.
+	 */
+	if (memcmp(a, &newstate->wm.optimal.ilk, sizeof(*a)) == 0)
+		newstate->wm.need_postvbl_update = false;
+
+	return 0;
+}
+
+/*
  * Merge the watermarks from all active pipes for a specific level.
  */
 static void ilk_merge_wm_level(struct drm_device *dev,
@@ -2383,9 +2447,7 @@ static void ilk_merge_wm_level(struct drm_device *dev,
 	ret_wm->enable = true;
 
 	for_each_intel_crtc(dev, intel_crtc) {
-		const struct intel_crtc_state *cstate =
-			to_intel_crtc_state(intel_crtc->base.state);
-		const struct intel_pipe_wm *active = &cstate->wm.optimal.ilk;
+		const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk;
 		const struct intel_wm_level *wm = &active->wm[level];
 
 		if (!active->pipe_enabled)
@@ -2533,15 +2595,14 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 
 	/* LP0 register values */
 	for_each_intel_crtc(dev, intel_crtc) {
-		const struct intel_crtc_state *cstate =
-			to_intel_crtc_state(intel_crtc->base.state);
 		enum pipe pipe = intel_crtc->pipe;
-		const struct intel_wm_level *r = &cstate->wm.optimal.ilk.wm[0];
+		const struct intel_wm_level *r =
+			&intel_crtc->wm.active.ilk.wm[0];
 
 		if (WARN_ON(!r->enable))
 			continue;
 
-		results->wm_linetime[pipe] = cstate->wm.optimal.ilk.linetime;
+		results->wm_linetime[pipe] = intel_crtc->wm.active.ilk.linetime;
 
 		results->wm_pipe[pipe] =
 			(r->pri_val << WM0_PIPE_PLANE_SHIFT) |
@@ -2748,7 +2809,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	dev_priv->wm.hw = *results;
 }
 
-static bool ilk_disable_lp_wm(struct drm_device *dev)
+bool ilk_disable_lp_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -3643,11 +3704,9 @@ static void ilk_compute_wm_config(struct drm_device *dev,
 	}
 }
 
-static void ilk_program_watermarks(struct intel_crtc_state *cstate)
+static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
 {
-	struct drm_crtc *crtc = cstate->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_device *dev = dev_priv->dev;
 	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
 	struct ilk_wm_maximums max;
 	struct intel_wm_config config = {};
@@ -3678,28 +3737,28 @@ static void ilk_program_watermarks(struct intel_crtc_state *cstate)
 	ilk_write_wm_values(dev_priv, &results);
 }
 
-static void ilk_update_wm(struct drm_crtc *crtc)
+static void ilk_initial_watermarks(struct intel_crtc_state *cstate)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
-
-	WARN_ON(cstate->base.active != intel_crtc->active);
+	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 
-	/*
-	 * IVB workaround: must disable low power watermarks for at least
-	 * one frame before enabling scaling.  LP watermarks can be re-enabled
-	 * when scaling is disabled.
-	 *
-	 * WaCxSRDisabledForSpriteScaling:ivb
-	 */
-	if (cstate->disable_lp_wm) {
-		ilk_disable_lp_wm(crtc->dev);
-		intel_wait_for_vblank(crtc->dev, intel_crtc->pipe);
-	}
+	mutex_lock(&dev_priv->wm.wm_mutex);
+	intel_crtc->wm.active.ilk = cstate->wm.intermediate;
+	ilk_program_watermarks(dev_priv);
+	mutex_unlock(&dev_priv->wm.wm_mutex);
+}
 
-	intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk;
+static void ilk_optimize_watermarks(struct intel_crtc_state *cstate)
+{
+	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 
-	ilk_program_watermarks(cstate);
+	mutex_lock(&dev_priv->wm.wm_mutex);
+	if (cstate->wm.need_postvbl_update) {
+		intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk;
+		ilk_program_watermarks(dev_priv);
+	}
+	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
 
 static void skl_pipe_wm_active_state(uint32_t val,
@@ -4585,9 +4644,9 @@ static bool bxt_check_bios_rc6_setup(const struct drm_device *dev)
 	 * for this check.
 	 */
 	rc6_ctx_base = I915_READ(RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
-	if (!((rc6_ctx_base >= dev_priv->gtt.stolen_reserved_base) &&
-	      (rc6_ctx_base + PAGE_SIZE <= dev_priv->gtt.stolen_reserved_base +
-					dev_priv->gtt.stolen_reserved_size))) {
+	if (!((rc6_ctx_base >= dev_priv->ggtt.stolen_reserved_base) &&
+	      (rc6_ctx_base + PAGE_SIZE <= dev_priv->ggtt.stolen_reserved_base +
+					dev_priv->ggtt.stolen_reserved_size))) {
 		DRM_DEBUG_KMS("RC6 Base address not as expected.\n");
 		enable_rc6 = false;
 	}
@@ -4756,9 +4815,8 @@ static void gen9_enable_rps(struct drm_device *dev)
 static void gen9_enable_rc6(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	uint32_t rc6_mask = 0;
-	int unused;
 
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
@@ -4779,8 +4837,8 @@ static void gen9_enable_rc6(struct drm_device *dev)
 		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_ring(ring, dev_priv, unused)
-		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	for_each_engine(engine, dev_priv)
+		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	if (HAS_GUC_UCODE(dev))
 		I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
@@ -4826,9 +4884,8 @@ static void gen9_enable_rc6(struct drm_device *dev)
 static void gen8_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	uint32_t rc6_mask = 0;
-	int unused;
 
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
@@ -4847,8 +4904,8 @@ static void gen8_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_ring(ring, dev_priv, unused)
-		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	for_each_engine(engine, dev_priv)
+		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	if (IS_BROADWELL(dev))
 		I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
@@ -4908,11 +4965,11 @@ static void gen8_enable_rps(struct drm_device *dev)
 static void gen6_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
-	int i, ret;
+	int ret;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
@@ -4944,8 +5001,8 @@ static void gen6_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_ring(ring, dev_priv, i)
-		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	for_each_engine(engine, dev_priv)
+		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
@@ -5232,7 +5289,7 @@ static void cherryview_setup_pctx(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long pctx_paddr, paddr;
-	struct i915_gtt *gtt = &dev_priv->gtt;
+	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	u32 pcbr;
 	int pctx_size = 32*1024;
 
@@ -5240,7 +5297,7 @@ static void cherryview_setup_pctx(struct drm_device *dev)
 	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
 		DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
 		paddr = (dev_priv->mm.stolen_base +
-			 (gtt->stolen_size - pctx_size));
+			 (ggtt->stolen_size - pctx_size));
 
 		pctx_paddr = (paddr & (~4095));
 		I915_WRITE(VLV_PCBR, pctx_paddr);
@@ -5436,9 +5493,8 @@ static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
 static void cherryview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
-	int i;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
@@ -5463,8 +5519,8 @@ static void cherryview_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 
-	for_each_ring(ring, dev_priv, i)
-		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	for_each_engine(engine, dev_priv)
+		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
 	/* TO threshold set to 500 us ( 0x186 * 1.28 us) */
@@ -5534,9 +5590,8 @@ static void cherryview_enable_rps(struct drm_device *dev)
 static void valleyview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	u32 gtfifodbg, val, rc6_mode = 0;
-	int i;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
@@ -5574,8 +5629,8 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
 	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_ring(ring, dev_priv, i)
-		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	for_each_engine(engine, dev_priv)
+		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
 	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
 
@@ -5951,17 +6006,16 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower);
 bool i915_gpu_busy(void)
 {
 	struct drm_i915_private *dev_priv;
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	bool ret = false;
-	int i;
 
 	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev)
 		goto out_unlock;
 	dev_priv = i915_mch_dev;
 
-	for_each_ring(ring, dev_priv, i)
-		ret |= !list_empty(&ring->request_list);
+	for_each_engine(engine, dev_priv)
+		ret |= !list_empty(&engine->request_list);
 
 out_unlock:
 	spin_unlock_irq(&mchdev_lock);
@@ -7038,8 +7092,7 @@ void intel_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->display.init_clock_gating)
-		dev_priv->display.init_clock_gating(dev);
+	dev_priv->display.init_clock_gating(dev);
 }
 
 void intel_suspend_hw(struct drm_device *dev)
@@ -7048,6 +7101,60 @@ void intel_suspend_hw(struct drm_device *dev)
 		lpt_suspend_hw(dev);
 }
 
+static void nop_init_clock_gating(struct drm_device *dev)
+{
+	DRM_DEBUG_KMS("No clock gating settings or workarounds applied.\n");
+}
+
+/**
+ * intel_init_clock_gating_hooks - setup the clock gating hooks
+ * @dev_priv: device private
+ *
+ * Setup the hooks that configure which clocks of a given platform can be
+ * gated and also apply various GT and display specific workarounds for these
+ * platforms. Note that some GT specific workarounds are applied separately
+ * when GPU contexts or batchbuffers start their execution.
+ */
+void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
+{
+	if (IS_SKYLAKE(dev_priv))
+		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+	else if (IS_KABYLAKE(dev_priv))
+		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+	else if (IS_BROXTON(dev_priv))
+		dev_priv->display.init_clock_gating = bxt_init_clock_gating;
+	else if (IS_BROADWELL(dev_priv))
+		dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
+	else if (IS_CHERRYVIEW(dev_priv))
+		dev_priv->display.init_clock_gating = cherryview_init_clock_gating;
+	else if (IS_HASWELL(dev_priv))
+		dev_priv->display.init_clock_gating = haswell_init_clock_gating;
+	else if (IS_IVYBRIDGE(dev_priv))
+		dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
+	else if (IS_VALLEYVIEW(dev_priv))
+		dev_priv->display.init_clock_gating = valleyview_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;
+	else if (IS_G4X(dev_priv))
+		dev_priv->display.init_clock_gating = g4x_init_clock_gating;
+	else if (IS_CRESTLINE(dev_priv))
+		dev_priv->display.init_clock_gating = crestline_init_clock_gating;
+	else if (IS_BROADWATER(dev_priv))
+		dev_priv->display.init_clock_gating = broadwater_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))
+		dev_priv->display.init_clock_gating = i85x_init_clock_gating;
+	else if (IS_GEN2(dev_priv))
+		dev_priv->display.init_clock_gating = i830_init_clock_gating;
+	else {
+		MISSING_CASE(INTEL_DEVID(dev_priv));
+		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+	}
+}
+
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {
@@ -7064,10 +7171,6 @@ void intel_init_pm(struct drm_device *dev)
 	/* For FIFO watermark updates */
 	if (INTEL_INFO(dev)->gen >= 9) {
 		skl_setup_wm_latency(dev);
-
-		if (IS_BROXTON(dev))
-			dev_priv->display.init_clock_gating =
-				bxt_init_clock_gating;
 		dev_priv->display.update_wm = skl_update_wm;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		ilk_setup_wm_latency(dev);
@@ -7076,36 +7179,23 @@ void intel_init_pm(struct drm_device *dev)
 		     dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) ||
 		    (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] &&
 		     dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) {
-			dev_priv->display.update_wm = ilk_update_wm;
 			dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm;
-			dev_priv->display.program_watermarks = ilk_program_watermarks;
+			dev_priv->display.compute_intermediate_wm =
+				ilk_compute_intermediate_wm;
+			dev_priv->display.initial_watermarks =
+				ilk_initial_watermarks;
+			dev_priv->display.optimize_watermarks =
+				ilk_optimize_watermarks;
 		} else {
 			DRM_DEBUG_KMS("Failed to read display plane latency. "
 				      "Disable CxSR\n");
 		}
-
-		if (IS_GEN5(dev))
-			dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
-		else if (IS_GEN6(dev))
-			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
-		else if (IS_IVYBRIDGE(dev))
-			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
-		else if (IS_HASWELL(dev))
-			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
-		else if (INTEL_INFO(dev)->gen == 8)
-			dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
 	} else if (IS_CHERRYVIEW(dev)) {
 		vlv_setup_wm_latency(dev);
-
 		dev_priv->display.update_wm = vlv_update_wm;
-		dev_priv->display.init_clock_gating =
-			cherryview_init_clock_gating;
 	} else if (IS_VALLEYVIEW(dev)) {
 		vlv_setup_wm_latency(dev);
-
 		dev_priv->display.update_wm = vlv_update_wm;
-		dev_priv->display.init_clock_gating =
-			valleyview_init_clock_gating;
 	} else if (IS_PINEVIEW(dev)) {
 		if (!intel_get_cxsr_latency(IS_PINEVIEW_G(dev),
 					    dev_priv->is_ddr3,
@@ -7121,20 +7211,13 @@ void intel_init_pm(struct drm_device *dev)
 			dev_priv->display.update_wm = NULL;
 		} else
 			dev_priv->display.update_wm = pineview_update_wm;
-		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
 	} else if (IS_G4X(dev)) {
 		dev_priv->display.update_wm = g4x_update_wm;
-		dev_priv->display.init_clock_gating = g4x_init_clock_gating;
 	} else if (IS_GEN4(dev)) {
 		dev_priv->display.update_wm = i965_update_wm;
-		if (IS_CRESTLINE(dev))
-			dev_priv->display.init_clock_gating = crestline_init_clock_gating;
-		else if (IS_BROADWATER(dev))
-			dev_priv->display.init_clock_gating = broadwater_init_clock_gating;
 	} else if (IS_GEN3(dev)) {
 		dev_priv->display.update_wm = i9xx_update_wm;
 		dev_priv->display.get_fifo_size = i9xx_get_fifo_size;
-		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
 	} else if (IS_GEN2(dev)) {
 		if (INTEL_INFO(dev)->num_pipes == 1) {
 			dev_priv->display.update_wm = i845_update_wm;
@@ -7143,11 +7226,6 @@ void intel_init_pm(struct drm_device *dev)
 			dev_priv->display.update_wm = i9xx_update_wm;
 			dev_priv->display.get_fifo_size = i830_get_fifo_size;
 		}
-
-		if (IS_I85X(dev) || IS_I865G(dev))
-			dev_priv->display.init_clock_gating = i85x_init_clock_gating;
-		else
-			dev_priv->display.init_clock_gating = i830_init_clock_gating;
 	} else {
 		DRM_ERROR("unexpected fall-through in intel_init_pm\n");
 	}
@@ -7302,7 +7380,7 @@ static void __intel_rps_boost_work(struct work_struct *work)
 	struct drm_i915_gem_request *req = boost->req;
 
 	if (!i915_gem_request_completed(req, true))
-		gen6_rps_boost(to_i915(req->ring->dev), NULL,
+		gen6_rps_boost(to_i915(req->engine->dev), NULL,
 			       req->emitted_jiffies);
 
 	i915_gem_request_unreference__unlocked(req);