drm/amd/display: Force enable 3DLUT DMA check for dcn401 in DML

[WHY]
Currently TR0 (trip 0) is not properly budgeting for urgent latency in
DML2.1. This results in overly aggressive prefetch schedules that are
vulnerable to request return jitter, resulting in severe underflow at
the start of the frame.

[HOW]
Forcing 3DLUT DMA check to enable causes urgent latency to be budgeted
properly into the prefetch schedule, avoiding the vulnerability.
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c

@@ -816,6 +816,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 
 	if (plane_state->mcm_luts.lut3d_data.lut3d_src == DC_CM2_TRANSFER_FUNC_SOURCE_VIDMEM) {
 		plane->tdlut.setup_for_tdlut = true;
+
 		switch (plane_state->mcm_luts.lut3d_data.gpu_mem_params.layout) {
 		case DC_CM2_GPU_MEM_LAYOUT_3D_SWIZZLE_LINEAR_RGB:
 		case DC_CM2_GPU_MEM_LAYOUT_3D_SWIZZLE_LINEAR_BGR:
@@ -825,6 +826,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 			plane->tdlut.tdlut_addressing_mode = dml2_tdlut_simple_linear;
 			break;
 		}
+
 		switch (plane_state->mcm_luts.lut3d_data.gpu_mem_params.size) {
 		case DC_CM2_GPU_MEM_SIZE_171717:
 			plane->tdlut.tdlut_width_mode = dml2_tdlut_width_17_cube;
@@ -833,8 +835,8 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 			//plane->tdlut.tdlut_width_mode = dml2_tdlut_width_flatten; // dml2_tdlut_width_flatten undefined
 			break;
 		}
-	} else
-		plane->tdlut.setup_for_tdlut = false;
+	}
+	plane->tdlut.setup_for_tdlut |= dml_ctx->config.force_tdlut_enable;
 
 	plane->dynamic_meta_data.enable = false;
 	plane->dynamic_meta_data.lines_before_active_required = 0;

drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h

@@ -236,6 +236,7 @@ struct dml2_configuration_options {
 
 	bool use_clock_dc_limits;
 	bool gpuvm_enable;
+	bool force_tdlut_enable;
 	struct dml2_soc_bb *bb_from_dmub;
 };
 

drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c

@@ -2099,6 +2099,7 @@ static bool dcn401_resource_construct(
 	dc->dml2_options.use_native_soc_bb_construction = true;
 	dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.map_dc_pipes_with_callbacks = true;
+	dc->dml2_options.force_tdlut_enable = true;
 
 	resource_init_common_dml2_callbacks(dc, &dc->dml2_options);
 	dc->dml2_options.callbacks.can_support_mclk_switch_using_fw_based_vblank_stretch = &dcn30_can_support_mclk_switch_using_fw_based_vblank_stretch;