drm/amd/display: Increase linebuffer pixel depth to 36bpp.

Testing with the photometer shows that at least Raven Ridge DCN-1.0
does not achieve more than 10 bpc effective output precision with a
16 bpc unorm surface of type SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616,
unless linebuffer depth is increased from LB_PIXEL_DEPTH_30BPP to
LB_PIXEL_DEPTH_36BPP. Otherwise precision gets truncated somewhere
to 10 bpc effective depth.

Strangely this increase was not needed on Polaris11 DCE-11.2 during
testing to get 12 bpc effective precision. It also is not needed for
fp16 framebuffers.

Tested on DCN-1.0 and DCE-11.2.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/core/dc_resource.c

@@ -1039,9 +1039,12 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	/*
 	 * LB calculations depend on vp size, h/v_active and scaling ratios
 	 * Setting line buffer pixel depth to 24bpp yields banding
-	 * on certain displays, such as the Sharp 4k
+	 * on certain displays, such as the Sharp 4k. 36bpp is needed
+	 * to support SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 and
+	 * SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616 with actual > 10 bpc
+	 * precision on at least DCN display engines.
 	 */
-	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
+	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
 	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = plane_state->per_pixel_alpha;
 
 	if (pipe_ctx->plane_res.xfm != NULL)

drivers/gpu/drm/amd/display/dc/dce/dce_transform.c

@@ -1647,7 +1647,8 @@ void dce_transform_construct(
 	xfm_dce->lb_pixel_depth_supported =
 			LB_PIXEL_DEPTH_18BPP |
 			LB_PIXEL_DEPTH_24BPP |
-			LB_PIXEL_DEPTH_30BPP;
+			LB_PIXEL_DEPTH_30BPP |
+			LB_PIXEL_DEPTH_36BPP;
 
 	xfm_dce->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	xfm_dce->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x6B0*/
@@ -1675,7 +1676,8 @@ void dce60_transform_construct(
 	xfm_dce->lb_pixel_depth_supported =
 			LB_PIXEL_DEPTH_18BPP |
 			LB_PIXEL_DEPTH_24BPP |
-			LB_PIXEL_DEPTH_30BPP;
+			LB_PIXEL_DEPTH_30BPP |
+			LB_PIXEL_DEPTH_36BPP;
 
 	xfm_dce->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	xfm_dce->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x6B0*/

drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c

@@ -708,7 +708,8 @@ bool dce110_transform_v_construct(
 	xfm_dce->lb_pixel_depth_supported =
 			LB_PIXEL_DEPTH_18BPP |
 			LB_PIXEL_DEPTH_24BPP |
-			LB_PIXEL_DEPTH_30BPP;
+			LB_PIXEL_DEPTH_30BPP |
+			LB_PIXEL_DEPTH_36BPP;
 
 	xfm_dce->prescaler_on = true;
 	xfm_dce->lb_bits_per_entry = LB_BITS_PER_ENTRY;

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c

@@ -568,7 +568,8 @@ void dpp1_construct(
 	dpp->lb_pixel_depth_supported =
 		LB_PIXEL_DEPTH_18BPP |
 		LB_PIXEL_DEPTH_24BPP |
-		LB_PIXEL_DEPTH_30BPP;
+		LB_PIXEL_DEPTH_30BPP |
+		LB_PIXEL_DEPTH_36BPP;
 
 	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -2593,7 +2593,7 @@ static void update_scaler(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 
 	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = per_pixel_alpha;
-	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
+	pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
 	/* scaler configuration */
 	pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
 			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c

@@ -432,7 +432,8 @@ bool dpp2_construct(
 	dpp->lb_pixel_depth_supported =
 		LB_PIXEL_DEPTH_18BPP |
 		LB_PIXEL_DEPTH_24BPP |
-		LB_PIXEL_DEPTH_30BPP;
+		LB_PIXEL_DEPTH_30BPP |
+		LB_PIXEL_DEPTH_36BPP;
 
 	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/

drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c

@@ -1473,7 +1473,7 @@ static void dcn20_update_dchubp_dpp(
 			plane_state->update_flags.bits.per_pixel_alpha_change ||
 			pipe_ctx->stream->update_flags.bits.scaling) {
 		pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->plane_state->per_pixel_alpha;
-		ASSERT(pipe_ctx->plane_res.scl_data.lb_params.depth == LB_PIXEL_DEPTH_30BPP);
+		ASSERT(pipe_ctx->plane_res.scl_data.lb_params.depth == LB_PIXEL_DEPTH_36BPP);
 		/* scaler configuration */
 		pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
 				pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);

drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c

@@ -1443,7 +1443,8 @@ bool dpp3_construct(
 	dpp->lb_pixel_depth_supported =
 		LB_PIXEL_DEPTH_18BPP |
 		LB_PIXEL_DEPTH_24BPP |
-		LB_PIXEL_DEPTH_30BPP;
+		LB_PIXEL_DEPTH_30BPP |
+		LB_PIXEL_DEPTH_36BPP;
 
 	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
 	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/