1 files changed, 211 insertions, 242 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0f042d133..e59a28cb3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2119,32 +2119,34 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 				GEN9_MEM_LATENCY_LEVEL_MASK;
 
 		/*
+		 * If a level n (n > 1) has a 0us latency, all levels m (m >= n)
+		 * need to be disabled. We make sure to sanitize the values out
+		 * of the punit to satisfy this requirement.
+		 */
+		for (level = 1; level <= max_level; level++) {
+			if (wm[level] == 0) {
+				for (i = level + 1; i <= max_level; i++)
+					wm[i] = 0;
+				break;
+			}
+		}
+
+		/*
 		 * WaWmMemoryReadLatency:skl
 		 *
 		 * punit doesn't take into account the read latency so we need
-		 * to add 2us to the various latency levels we retrieve from
-		 * the punit.
-		 *   - W0 is a bit special in that it's the only level that
-		 *   can't be disabled if we want to have display working, so
-		 *   we always add 2us there.
-		 *   - For levels >=1, punit returns 0us latency when they are
-		 *   disabled, so we respect that and don't add 2us then
-		 *
-		 * Additionally, if a level n (n > 1) has a 0us latency, all
-		 * levels m (m >= n) need to be disabled. We make sure to
-		 * sanitize the values out of the punit to satisfy this
-		 * requirement.
+		 * to add 2us to the various latency levels we retrieve from the
+		 * punit when level 0 response data us 0us.
 		 */
-		wm[0] += 2;
-		for (level = 1; level <= max_level; level++)
-			if (wm[level] != 0)
+		if (wm[0] == 0) {
+			wm[0] += 2;
+			for (level = 1; level <= max_level; level++) {
+				if (wm[level] == 0)
+					break;
 				wm[level] += 2;
-			else {
-				for (i = level + 1; i <= max_level; i++)
-					wm[i] = 0;
-
-				break;
 			}
+		}
+
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		uint64_t sskpd = I915_READ64(MCH_SSKPD);
 
@@ -2876,6 +2878,19 @@ skl_wm_plane_id(const struct intel_plane *plane)
 	}
 }
 
+static bool
+intel_has_sagv(struct drm_i915_private *dev_priv)
+{
+	if (IS_KABYLAKE(dev_priv))
+		return true;
+
+	if (IS_SKYLAKE(dev_priv) &&
+	    dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED)
+		return true;
+
+	return false;
+}
+
 /*
  * SAGV dynamically adjusts the system agent voltage and clock frequencies
  * depending on power and performance requirements. The display engine access
@@ -2888,12 +2903,14 @@ skl_wm_plane_id(const struct intel_plane *plane)
  *  - We're not using an interlaced display configuration
  */
 int
-skl_enable_sagv(struct drm_i915_private *dev_priv)
+intel_enable_sagv(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
-	    dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED)
+	if (!intel_has_sagv(dev_priv))
+		return 0;
+
+	if (dev_priv->sagv_status == I915_SAGV_ENABLED)
 		return 0;
 
 	DRM_DEBUG_KMS("Enabling the SAGV\n");
@@ -2909,21 +2926,21 @@ skl_enable_sagv(struct drm_i915_private *dev_priv)
 	 * Some skl systems, pre-release machines in particular,
 	 * don't actually have an SAGV.
 	 */
-	if (ret == -ENXIO) {
+	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
 		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
-		dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (ret < 0) {
 		DRM_ERROR("Failed to enable the SAGV\n");
 		return ret;
 	}
 
-	dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED;
+	dev_priv->sagv_status = I915_SAGV_ENABLED;
 	return 0;
 }
 
 static int
-skl_do_sagv_disable(struct drm_i915_private *dev_priv)
+intel_do_sagv_disable(struct drm_i915_private *dev_priv)
 {
 	int ret;
 	uint32_t temp = GEN9_SAGV_DISABLE;
@@ -2937,19 +2954,21 @@ skl_do_sagv_disable(struct drm_i915_private *dev_priv)
 }
 
 int
-skl_disable_sagv(struct drm_i915_private *dev_priv)
+intel_disable_sagv(struct drm_i915_private *dev_priv)
 {
 	int ret, result;
 
-	if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
-	    dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED)
+	if (!intel_has_sagv(dev_priv))
+		return 0;
+
+	if (dev_priv->sagv_status == I915_SAGV_DISABLED)
 		return 0;
 
 	DRM_DEBUG_KMS("Disabling the SAGV\n");
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	/* bspec says to keep retrying for at least 1 ms */
-	ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1);
+	ret = wait_for(result = intel_do_sagv_disable(dev_priv), 1);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	if (ret == -ETIMEDOUT) {
@@ -2961,20 +2980,20 @@ skl_disable_sagv(struct drm_i915_private *dev_priv)
 	 * Some skl systems, pre-release machines in particular,
 	 * don't actually have an SAGV.
 	 */
-	if (result == -ENXIO) {
+	if (IS_SKYLAKE(dev_priv) && result == -ENXIO) {
 		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
-		dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (result < 0) {
 		DRM_ERROR("Failed to disable the SAGV\n");
 		return result;
 	}
 
-	dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED;
+	dev_priv->sagv_status = I915_SAGV_DISABLED;
 	return 0;
 }
 
-bool skl_can_enable_sagv(struct drm_atomic_state *state)
+bool intel_can_enable_sagv(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -2983,6 +3002,9 @@ bool skl_can_enable_sagv(struct drm_atomic_state *state)
 	enum pipe pipe;
 	int level, plane;
 
+	if (!intel_has_sagv(dev_priv))
+		return false;
+
 	/*
 	 * SKL workaround: bspec recommends we disable the SAGV when we have
 	 * more then one pipe enabled
@@ -3473,29 +3495,14 @@ static uint32_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latenc
 }
 
 static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
-			       uint32_t horiz_pixels, uint8_t cpp,
-			       uint64_t tiling, uint32_t latency)
+			       uint32_t latency, uint32_t plane_blocks_per_line)
 {
 	uint32_t ret;
-	uint32_t plane_bytes_per_line, plane_blocks_per_line;
 	uint32_t wm_intermediate_val;
 
 	if (latency == 0)
 		return UINT_MAX;
 
-	plane_bytes_per_line = horiz_pixels * cpp;
-
-	if (tiling == I915_FORMAT_MOD_Y_TILED ||
-	    tiling == I915_FORMAT_MOD_Yf_TILED) {
-		plane_bytes_per_line *= 4;
-		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
-		plane_blocks_per_line /= 4;
-	} else if (tiling == DRM_FORMAT_MOD_NONE) {
-		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
-	} else {
-		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
-	}
-
 	wm_intermediate_val = latency * pixel_rate;
 	ret = DIV_ROUND_UP(wm_intermediate_val, pipe_htotal * 1000) *
 				plane_blocks_per_line;
@@ -3546,6 +3553,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	uint8_t cpp;
 	uint32_t width = 0, height = 0;
 	uint32_t plane_pixel_rate;
+	uint32_t y_tile_minimum, y_min_scanlines;
 
 	if (latency == 0 || !cstate->base.active || !intel_pstate->visible) {
 		*enabled = false;
@@ -3561,38 +3569,51 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 	plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate);
 
+	if (intel_rotation_90_or_270(pstate->rotation)) {
+		int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
+			drm_format_plane_cpp(fb->pixel_format, 1) :
+			drm_format_plane_cpp(fb->pixel_format, 0);
+
+		switch (cpp) {
+		case 1:
+			y_min_scanlines = 16;
+			break;
+		case 2:
+			y_min_scanlines = 8;
+			break;
+		default:
+			WARN(1, "Unsupported pixel depth for rotation");
+		case 4:
+			y_min_scanlines = 4;
+			break;
+		}
+	} else {
+		y_min_scanlines = 4;
+	}
+
+	plane_bytes_per_line = width * cpp;
+	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
+	    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
+		plane_blocks_per_line =
+		      DIV_ROUND_UP(plane_bytes_per_line * y_min_scanlines, 512);
+		plane_blocks_per_line /= y_min_scanlines;
+	} else if (fb->modifier[0] == DRM_FORMAT_MOD_NONE) {
+		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512)
+					+ 1;
+	} else {
+		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
+	}
+
 	method1 = skl_wm_method1(plane_pixel_rate, cpp, latency);
 	method2 = skl_wm_method2(plane_pixel_rate,
 				 cstate->base.adjusted_mode.crtc_htotal,
-				 width,
-				 cpp,
-				 fb->modifier[0],
-				 latency);
+				 latency,
+				 plane_blocks_per_line);
 
-	plane_bytes_per_line = width * cpp;
-	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
+	y_tile_minimum = plane_blocks_per_line * y_min_scanlines;
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
 	    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
-		uint32_t min_scanlines = 4;
-		uint32_t y_tile_minimum;
-		if (intel_rotation_90_or_270(pstate->rotation)) {
-			int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
-				drm_format_plane_cpp(fb->pixel_format, 1) :
-				drm_format_plane_cpp(fb->pixel_format, 0);
-
-			switch (cpp) {
-			case 1:
-				min_scanlines = 16;
-				break;
-			case 2:
-				min_scanlines = 8;
-				break;
-			case 8:
-				WARN(1, "Unsupported pixel depth for rotation");
-			}
-		}
-		y_tile_minimum = plane_blocks_per_line * min_scanlines;
 		selected_result = max(method2, y_tile_minimum);
 	} else {
 		if ((ddb_allocation / plane_blocks_per_line) >= 1)
@@ -3606,10 +3627,12 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 
 	if (level >= 1 && level <= 7) {
 		if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
-		    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED)
-			res_lines += 4;
-		else
+		    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
+			res_blocks += y_tile_minimum;
+			res_lines += y_min_scanlines;
+		} else {
 			res_blocks++;
+		}
 	}
 
 	if (res_blocks >= ddb_allocation || res_lines > 31) {
@@ -3828,182 +3851,82 @@ static void skl_ddb_entry_write(struct drm_i915_private *dev_priv,
 		I915_WRITE(reg, 0);
 }
 
-static void skl_write_wm_values(struct drm_i915_private *dev_priv,
-				const struct skl_wm_values *new)
+void skl_write_plane_wm(struct intel_crtc *intel_crtc,
+			const struct skl_wm_values *wm,
+			int plane)
 {
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_crtc *crtc;
-
-	for_each_intel_crtc(dev, crtc) {
-		int i, level, max_level = ilk_wm_max_level(dev);
-		enum pipe pipe = crtc->pipe;
-
-		if ((new->dirty_pipes & drm_crtc_mask(&crtc->base)) == 0)
-			continue;
-		if (!crtc->active)
-			continue;
-
-		I915_WRITE(PIPE_WM_LINETIME(pipe), new->wm_linetime[pipe]);
-
-		for (level = 0; level <= max_level; level++) {
-			for (i = 0; i < intel_num_planes(crtc); i++)
-				I915_WRITE(PLANE_WM(pipe, i, level),
-					   new->plane[pipe][i][level]);
-			I915_WRITE(CUR_WM(pipe, level),
-				   new->plane[pipe][PLANE_CURSOR][level]);
-		}
-		for (i = 0; i < intel_num_planes(crtc); i++)
-			I915_WRITE(PLANE_WM_TRANS(pipe, i),
-				   new->plane_trans[pipe][i]);
-		I915_WRITE(CUR_WM_TRANS(pipe),
-			   new->plane_trans[pipe][PLANE_CURSOR]);
-
-		for (i = 0; i < intel_num_planes(crtc); i++) {
-			skl_ddb_entry_write(dev_priv,
-					    PLANE_BUF_CFG(pipe, i),
-					    &new->ddb.plane[pipe][i]);
-			skl_ddb_entry_write(dev_priv,
-					    PLANE_NV12_BUF_CFG(pipe, i),
-					    &new->ddb.y_plane[pipe][i]);
-		}
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int level, max_level = ilk_wm_max_level(dev);
+	enum pipe pipe = intel_crtc->pipe;
 
-		skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
-				    &new->ddb.plane[pipe][PLANE_CURSOR]);
+	for (level = 0; level <= max_level; level++) {
+		I915_WRITE(PLANE_WM(pipe, plane, level),
+			   wm->plane[pipe][plane][level]);
 	}
-}
+	I915_WRITE(PLANE_WM_TRANS(pipe, plane), wm->plane_trans[pipe][plane]);
 
-/*
- * When setting up a new DDB allocation arrangement, we need to correctly
- * sequence the times at which the new allocations for the pipes are taken into
- * account or we'll have pipes fetching from space previously allocated to
- * another pipe.
- *
- * Roughly the sequence looks like:
- *  1. re-allocate the pipe(s) with the allocation being reduced and not
- *     overlapping with a previous light-up pipe (another way to put it is:
- *     pipes with their new allocation strickly included into their old ones).
- *  2. re-allocate the other pipes that get their allocation reduced
- *  3. allocate the pipes having their allocation increased
- *
- * Steps 1. and 2. are here to take care of the following case:
- * - Initially DDB looks like this:
- *     |   B    |   C    |
- * - enable pipe A.
- * - pipe B has a reduced DDB allocation that overlaps with the old pipe C
- *   allocation
- *     |  A  |  B  |  C  |
- *
- * We need to sequence the re-allocation: C, B, A (and not B, C, A).
- */
+	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane),
+			    &wm->ddb.plane[pipe][plane]);
+	skl_ddb_entry_write(dev_priv, PLANE_NV12_BUF_CFG(pipe, plane),
+			    &wm->ddb.y_plane[pipe][plane]);
+}
 
-static void
-skl_wm_flush_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, int pass)
+void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
+			 const struct skl_wm_values *wm)
 {
-	int plane;
-
-	DRM_DEBUG_KMS("flush pipe %c (pass %d)\n", pipe_name(pipe), pass);
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int level, max_level = ilk_wm_max_level(dev);
+	enum pipe pipe = intel_crtc->pipe;
 
-	for_each_plane(dev_priv, pipe, plane) {
-		I915_WRITE(PLANE_SURF(pipe, plane),
-			   I915_READ(PLANE_SURF(pipe, plane)));
+	for (level = 0; level <= max_level; level++) {
+		I915_WRITE(CUR_WM(pipe, level),
+			   wm->plane[pipe][PLANE_CURSOR][level]);
 	}
+	I915_WRITE(CUR_WM_TRANS(pipe), wm->plane_trans[pipe][PLANE_CURSOR]);
+
+	skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
+			    &wm->ddb.plane[pipe][PLANE_CURSOR]);
 }
 
-static bool
-skl_ddb_allocation_included(const struct skl_ddb_allocation *old,
-			    const struct skl_ddb_allocation *new,
-			    enum pipe pipe)
+bool skl_ddb_allocation_equals(const struct skl_ddb_allocation *old,
+			       const struct skl_ddb_allocation *new,
+			       enum pipe pipe)
 {
-	uint16_t old_size, new_size;
-
-	old_size = skl_ddb_entry_size(&old->pipe[pipe]);
-	new_size = skl_ddb_entry_size(&new->pipe[pipe]);
-
-	return old_size != new_size &&
-	       new->pipe[pipe].start >= old->pipe[pipe].start &&
-	       new->pipe[pipe].end <= old->pipe[pipe].end;
+	return new->pipe[pipe].start == old->pipe[pipe].start &&
+	       new->pipe[pipe].end == old->pipe[pipe].end;
 }
 
-static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
-				struct skl_wm_values *new_values)
+static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
+					   const struct skl_ddb_entry *b)
 {
-	struct drm_device *dev = &dev_priv->drm;
-	struct skl_ddb_allocation *cur_ddb, *new_ddb;
-	bool reallocated[I915_MAX_PIPES] = {};
-	struct intel_crtc *crtc;
-	enum pipe pipe;
-
-	new_ddb = &new_values->ddb;
-	cur_ddb = &dev_priv->wm.skl_hw.ddb;
-
-	/*
-	 * First pass: flush the pipes with the new allocation contained into
-	 * the old space.
-	 *
-	 * We'll wait for the vblank on those pipes to ensure we can safely
-	 * re-allocate the freed space without this pipe fetching from it.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
-
-		pipe = crtc->pipe;
-
-		if (!skl_ddb_allocation_included(cur_ddb, new_ddb, pipe))
-			continue;
-
-		skl_wm_flush_pipe(dev_priv, pipe, 1);
-		intel_wait_for_vblank(dev, pipe);
-
-		reallocated[pipe] = true;
-	}
-
+	return a->start < b->end && b->start < a->end;
+}
 
-	/*
-	 * Second pass: flush the pipes that are having their allocation
-	 * reduced, but overlapping with a previous allocation.
-	 *
-	 * Here as well we need to wait for the vblank to make sure the freed
-	 * space is not used anymore.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
+bool skl_ddb_allocation_overlaps(struct drm_atomic_state *state,
+				 const struct skl_ddb_allocation *old,
+				 const struct skl_ddb_allocation *new,
+				 enum pipe pipe)
+{
+	struct drm_device *dev = state->dev;
+	struct intel_crtc *intel_crtc;
+	enum pipe otherp;
 
-		pipe = crtc->pipe;
+	for_each_intel_crtc(dev, intel_crtc) {
+		otherp = intel_crtc->pipe;
 
-		if (reallocated[pipe])
+		if (otherp == pipe)
 			continue;
 
-		if (skl_ddb_entry_size(&new_ddb->pipe[pipe]) <
-		    skl_ddb_entry_size(&cur_ddb->pipe[pipe])) {
-			skl_wm_flush_pipe(dev_priv, pipe, 2);
-			intel_wait_for_vblank(dev, pipe);
-			reallocated[pipe] = true;
-		}
+		if (skl_ddb_entries_overlap(&new->pipe[pipe],
+					    &old->pipe[otherp]))
+			return true;
 	}
 
-	/*
-	 * Third pass: flush the pipes that got more space allocated.
-	 *
-	 * We don't need to actively wait for the update here, next vblank
-	 * will just get more DDB space with the correct WM values.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
-
-		pipe = crtc->pipe;
-
-		/*
-		 * At this point, only the pipes more space than before are
-		 * left to re-allocate.
-		 */
-		if (reallocated[pipe])
-			continue;
-
-		skl_wm_flush_pipe(dev_priv, pipe, 3);
-	}
+	return false;
 }
 
 static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
@@ -4040,6 +3963,41 @@ pipes_modified(struct drm_atomic_state *state)
 	return ret;
 }
 
+int
+skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
+{
+	struct drm_atomic_state *state = cstate->base.state;
+	struct drm_device *dev = state->dev;
+	struct drm_crtc *crtc = cstate->base.crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
+	struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb;
+	struct drm_plane_state *plane_state;
+	struct drm_plane *plane;
+	enum pipe pipe = intel_crtc->pipe;
+	int id;
+
+	WARN_ON(!drm_atomic_get_existing_crtc_state(state, crtc));
+
+	drm_for_each_plane_mask(plane, dev, crtc->state->plane_mask) {
+		id = skl_wm_plane_id(to_intel_plane(plane));
+
+		if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][id],
+					&new_ddb->plane[pipe][id]) &&
+		    skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][id],
+					&new_ddb->y_plane[pipe][id]))
+			continue;
+
+		plane_state = drm_atomic_get_plane_state(state, plane);
+		if (IS_ERR(plane_state))
+			return PTR_ERR(plane_state);
+	}
+
+	return 0;
+}
+
 static int
 skl_compute_ddb(struct drm_atomic_state *state)
 {
@@ -4104,6 +4062,10 @@ skl_compute_ddb(struct drm_atomic_state *state)
 		if (ret)
 			return ret;
 
+		ret = skl_ddb_add_affected_planes(cstate);
+		if (ret)
+			return ret;
+
 		ret = drm_atomic_add_affected_planes(state, &intel_crtc->base);
 		if (ret)
 			return ret;
@@ -4205,7 +4167,7 @@ static void skl_update_wm(struct drm_crtc *crtc)
 	struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
 	struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
-	int pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
 		return;
@@ -4214,15 +4176,22 @@ static void skl_update_wm(struct drm_crtc *crtc)
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 
-	skl_write_wm_values(dev_priv, results);
-	skl_flush_wm_values(dev_priv, results);
-
 	/*
-	 * Store the new configuration (but only for the pipes that have
-	 * changed; the other values weren't recomputed).
+	 * If this pipe isn't active already, we're going to be enabling it
+	 * very soon. Since it's safe to update a pipe's ddb allocation while
+	 * the pipe's shut off, just do so here. Already active pipes will have
+	 * their watermarks updated once we update their planes.
 	 */
-	for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes)
-		skl_copy_wm_for_pipe(hw_vals, results, pipe);
+	if (crtc->state->active_changed) {
+		int plane;
+
+		for (plane = 0; plane < intel_num_planes(intel_crtc); plane++)
+			skl_write_plane_wm(intel_crtc, results, plane);
+
+		skl_write_cursor_wm(intel_crtc, results);
+	}
+
+	skl_copy_wm_for_pipe(hw_vals, results, pipe);
 
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }