drm/amd/display: add plane shaper LUT support

Map DC shaper LUT to DM plane color management. Shaper LUT can be used
to delinearize and/or normalize the color space for computational
efficiency and achiving specific visual styles. If a plane degamma is
apply to linearize the color space, a custom shaper 1D LUT can be used
just before applying 3D LUT.

v2:
- use DPP color caps to verify plane 3D LUT support
- add debug message if shaper LUT programming fails

v4:
- remove helper to check 3D LUT color caps (Harry)
- update desc of lut3d-setup helper from MPC to DPP

v5:
- remove color_mgmt_changed check that prevents color updates (Joshua)

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -8269,6 +8269,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->surface_updates[planes_count].in_transfer_func = dc_plane->in_transfer_func;
 			bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix;
 			bundle->surface_updates[planes_count].hdr_mult = dc_plane->hdr_mult;
+			bundle->surface_updates[planes_count].func_shaper = dc_plane->in_shaper_func;
 		}
 
 		amdgpu_dm_plane_fill_dc_scaling_info(dm->adev, new_plane_state,

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h

@@ -908,6 +908,8 @@ void amdgpu_dm_trigger_timing_sync(struct drm_device *dev);
 /* 3D LUT max size is 17x17x17 (4913 entries) */
 #define MAX_COLOR_3DLUT_SIZE 17
 #define MAX_COLOR_3DLUT_BITDEPTH 12
+int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
+				struct drm_plane_state *plane_state);
 /* 1D LUT size */
 #define MAX_COLOR_LUT_ENTRIES 4096
 /* Legacy gamm LUT users such as X doesn't like large LUT sizes */

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c

@@ -623,6 +623,63 @@ amdgpu_tf_to_dc_tf(enum amdgpu_transfer_function tf)
 	}
 }
 
+static int amdgpu_dm_atomic_shaper_lut(const struct drm_color_lut *shaper_lut,
+				       uint32_t shaper_size,
+				       struct dc_transfer_func *func_shaper)
+{
+	int ret = 0;
+
+	if (shaper_size) {
+		/*
+		 * If user shaper LUT is set, we assume a linear color space
+		 * (linearized by degamma 1D LUT or not).
+		 */
+		func_shaper->type = TF_TYPE_DISTRIBUTED_POINTS;
+		func_shaper->tf = TRANSFER_FUNCTION_LINEAR;
+
+		ret = __set_output_tf(func_shaper, shaper_lut, shaper_size, false);
+	} else {
+		func_shaper->type = TF_TYPE_BYPASS;
+		func_shaper->tf = TRANSFER_FUNCTION_LINEAR;
+	}
+
+	return ret;
+}
+
+/**
+ * amdgpu_dm_verify_lut3d_size - verifies if 3D LUT is supported and if user
+ * shaper and 3D LUTs match the hw supported size
+ * @adev: amdgpu device
+ * @crtc_state: the DRM CRTC state
+ *
+ * Verifies if pre-blending (DPP) 3D LUT is supported by the HW (DCN 2.0 or
+ * newer) and if the user shaper and 3D LUTs match the supported size.
+ *
+ * Returns:
+ * 0 on success. -EINVAL if lut size are invalid.
+ */
+int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
+				struct drm_plane_state *plane_state)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	const struct drm_color_lut *shaper = NULL;
+	uint32_t exp_size, size;
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut;
+
+	/* shaper LUT is only available if 3D LUT color caps */
+	exp_size = has_3dlut ? MAX_COLOR_LUT_ENTRIES : 0;
+	shaper = __extract_blob_lut(dm_plane_state->shaper_lut, &size);
+
+	if (shaper && size != exp_size) {
+		drm_dbg(&adev->ddev,
+			"Invalid Shaper LUT size. Should be %u but got %u.\n",
+			exp_size, size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_verify_lut_sizes - verifies if DRM luts match the hw supported sizes
  * @crtc_state: the DRM CRTC state
@@ -910,6 +967,30 @@ __set_dm_plane_degamma(struct drm_plane_state *plane_state,
 	return 0;
 }
 
+static int
+amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state,
+				     struct dc_plane_state *dc_plane_state)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	const struct drm_color_lut *shaper_lut;
+	uint32_t shaper_size;
+	int ret;
+
+	dc_plane_state->hdr_mult = dc_fixpt_from_s3132(dm_plane_state->hdr_mult);
+
+	shaper_lut = __extract_blob_lut(dm_plane_state->shaper_lut, &shaper_size);
+	shaper_size = shaper_lut != NULL ? shaper_size : 0;
+
+	ret = amdgpu_dm_atomic_shaper_lut(shaper_lut, shaper_size,
+					  dc_plane_state->in_shaper_func);
+	if (ret)
+		drm_dbg_kms(plane_state->plane->dev,
+			    "setting plane %d shaper LUT failed.\n",
+			    plane_state->plane->index);
+
+	return ret;
+}
+
 /**
  * amdgpu_dm_update_plane_color_mgmt: Maps DRM color management to DC plane.
  * @crtc: amdgpu_dm crtc state
@@ -927,10 +1008,16 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 				      struct drm_plane_state *plane_state,
 				      struct dc_plane_state *dc_plane_state)
 {
-	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
 	bool has_crtc_cm_degamma;
 	int ret;
 
+	ret = amdgpu_dm_verify_lut3d_size(adev, plane_state);
+	if (ret) {
+		drm_dbg_driver(&adev->ddev, "amdgpu_dm_verify_lut3d_size() failed\n");
+		return ret;
+	}
+
 	/* Initially, we can just bypass the DGM block. */
 	dc_plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
 	dc_plane_state->in_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
@@ -938,8 +1025,6 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 	/* After, we start to update values according to color props */
 	has_crtc_cm_degamma = (crtc->cm_has_degamma || crtc->cm_is_degamma_srgb);
 
-	dc_plane_state->hdr_mult = dc_fixpt_from_s3132(dm_plane_state->hdr_mult);
-
 	ret = __set_dm_plane_degamma(plane_state, dc_plane_state);
 	if (ret == -ENOMEM)
 		return ret;
@@ -972,5 +1057,5 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 			return ret;
 	}
 
-	return 0;
+	return amdgpu_dm_plane_set_color_properties(plane_state, dc_plane_state);
 }