drm/amd/display: Remove FPU operations from dcn201 resources

We have some FPU operations on the resource part of the DCN201. This
commit drops FPU flags and moves any required FPU code to the DML
folder.

Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 100 insertions, 25 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/Makefile b/drivers/gpu/drm/amd/display/dc/dcn201/Makefile
index 96cbd4ccd344..5c9ce2cebb0f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn201/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn201/Makefile
@@ -6,30 +6,6 @@ DCN201 = dcn201_init.o dcn201_resource.o dcn201_hwseq.o \
 	dcn201_mpc.o dcn201_hubp.o dcn201_opp.o dcn201_optc.o dcn201_dpp.o \
 	dcn201_dccg.o dcn201_link_encoder.o
 
-ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn201/dcn201_resource.o := -mhard-float -msse
-endif
-
-ifdef CONFIG_PPC64
-CFLAGS_$(AMDDALPATH)/dc/dcn201/dcn201_resource.o := -mhard-float -maltivec
-endif
-
-ifdef CONFIG_CC_IS_GCC
-ifeq ($(call cc-ifversion, -lt, 0701, y), y)
-IS_OLD_GCC = 1
-endif
-endif
-
-ifdef CONFIG_X86
-ifdef IS_OLD_GCC
-# Stack alignment mismatch, proceed with caution.
-# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
-# (8B stack alignment).
-CFLAGS_$(AMDDALPATH)/dc/dcn201/dcn201_resource.o += -mpreferred-stack-boundary=4
-else
-CFLAGS_$(AMDDALPATH)/dc/dcn201/dcn201_resource.o += -msse2
-endif
-endif
 AMD_DAL_DCN201 = $(addprefix $(AMDDALPATH)/dc/dcn201/,$(DCN201))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_DCN201)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c
index 0bb7d3dd53fa..e549a79f3fe1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c
@@ -1036,6 +1036,14 @@ static bool dcn201_get_dcc_compression_cap(const struct dc *dc,
 			output);
 }
 
+static void dcn201_populate_dml_writeback_from_context(struct dc *dc,
+						       struct resource_context *res_ctx,
+						       display_e2e_pipe_params_st *pipes)
+{
+	DC_FP_START();
+	dcn201_populate_dml_writeback_from_context_fpu(dc, res_ctx, pipes);
+	DC_FP_END();
+}
 
 static void dcn201_destroy_resource_pool(struct resource_pool **pool)
 {
@@ -1067,8 +1075,8 @@ static struct resource_funcs dcn201_res_pool_funcs = {
 	.add_dsc_to_stream_resource = NULL,
 	.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
 	.acquire_idle_pipe_for_layer = dcn201_acquire_idle_pipe_for_layer,
+	.populate_dml_writeback_from_context = dcn201_populate_dml_writeback_from_context,
 	.patch_unknown_plane_state = dcn20_patch_unknown_plane_state,
-	.populate_dml_writeback_from_context = dcn20_populate_dml_writeback_from_context,
 	.set_mcif_arb_params = dcn20_set_mcif_arb_params,
 	.find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index eeeae52fe6fc..39428488a052 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -2303,3 +2303,90 @@ void dcn21_clk_mgr_set_bw_params_wm_table(struct clk_bw_params *bw_params)
 	bw_params->wm_table.entries[WM_D].wm_type = WM_TYPE_RETRAINING;
 	bw_params->wm_table.entries[WM_D].valid = true;
 }
+
+void dcn201_populate_dml_writeback_from_context_fpu(struct dc *dc,
+						    struct resource_context *res_ctx,
+						    display_e2e_pipe_params_st *pipes)
+{
+	int pipe_cnt, i, j;
+	double max_calc_writeback_dispclk;
+	double writeback_dispclk;
+	struct writeback_st dout_wb;
+
+	dc_assert_fp_enabled();
+
+	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_stream_state *stream = res_ctx->pipe_ctx[i].stream;
+
+		if (!stream)
+			continue;
+		max_calc_writeback_dispclk = 0;
+
+		/* Set writeback information */
+		pipes[pipe_cnt].dout.wb_enable = 0;
+		pipes[pipe_cnt].dout.num_active_wb = 0;
+		for (j = 0; j < stream->num_wb_info; j++) {
+			struct dc_writeback_info *wb_info = &stream->writeback_info[j];
+
+			if (wb_info->wb_enabled && wb_info->writeback_source_plane &&
+					(wb_info->writeback_source_plane == res_ctx->pipe_ctx[i].plane_state)) {
+				pipes[pipe_cnt].dout.wb_enable = 1;
+				pipes[pipe_cnt].dout.num_active_wb++;
+				dout_wb.wb_src_height = wb_info->dwb_params.cnv_params.crop_en ?
+					wb_info->dwb_params.cnv_params.crop_height :
+					wb_info->dwb_params.cnv_params.src_height;
+				dout_wb.wb_src_width = wb_info->dwb_params.cnv_params.crop_en ?
+					wb_info->dwb_params.cnv_params.crop_width :
+					wb_info->dwb_params.cnv_params.src_width;
+				dout_wb.wb_dst_width = wb_info->dwb_params.dest_width;
+				dout_wb.wb_dst_height = wb_info->dwb_params.dest_height;
+				dout_wb.wb_htaps_luma = wb_info->dwb_params.scaler_taps.h_taps;
+				dout_wb.wb_vtaps_luma = wb_info->dwb_params.scaler_taps.v_taps;;
+				dout_wb.wb_htaps_chroma = wb_info->dwb_params.scaler_taps.h_taps_c;
+				dout_wb.wb_vtaps_chroma = wb_info->dwb_params.scaler_taps.v_taps_c;
+				dout_wb.wb_hratio = wb_info->dwb_params.cnv_params.crop_en ?
+					(double)wb_info->dwb_params.cnv_params.crop_width /
+						(double)wb_info->dwb_params.dest_width :
+					(double)wb_info->dwb_params.cnv_params.src_width /
+						(double)wb_info->dwb_params.dest_width;
+				dout_wb.wb_vratio = wb_info->dwb_params.cnv_params.crop_en ?
+					(double)wb_info->dwb_params.cnv_params.crop_height /
+						(double)wb_info->dwb_params.dest_height :
+					(double)wb_info->dwb_params.cnv_params.src_height /
+						(double)wb_info->dwb_params.dest_height;
+				if (wb_info->dwb_params.out_format == dwb_scaler_mode_yuv420) {
+					if (wb_info->dwb_params.output_depth == DWB_OUTPUT_PIXEL_DEPTH_8BPC)
+						dout_wb.wb_pixel_format = dm_420_8;
+					else
+						dout_wb.wb_pixel_format = dm_420_10;
+				} else
+					dout_wb.wb_pixel_format = dm_444_32;
+
+				/* Workaround for cases where multiple writebacks are connected to same plane
+				 * In which case, need to compute worst case and set the associated writeback parameters
+				 * This workaround is necessary due to DML computation assuming only 1 set of writeback
+				 * parameters per pipe */
+				writeback_dispclk = CalculateWriteBackDISPCLK(
+						dout_wb.wb_pixel_format,
+						pipes[pipe_cnt].pipe.dest.pixel_rate_mhz,
+						dout_wb.wb_hratio,
+						dout_wb.wb_vratio,
+						dout_wb.wb_htaps_luma,
+						dout_wb.wb_vtaps_luma,
+						dout_wb.wb_htaps_chroma,
+						dout_wb.wb_vtaps_chroma,
+						dout_wb.wb_dst_width,
+						pipes[pipe_cnt].pipe.dest.htotal,
+						2);
+
+				if (writeback_dispclk > max_calc_writeback_dispclk) {
+					max_calc_writeback_dispclk = writeback_dispclk;
+					pipes[pipe_cnt].dout.wb = dout_wb;
+				}
+			}
+		}
+
+		pipe_cnt++;
+	}
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h
index a6e1ad0f38e9..c51badf7b68a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h
@@ -84,4 +84,8 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 
 void dcn21_clk_mgr_set_bw_params_wm_table(struct clk_bw_params *bw_params);
 
+void dcn201_populate_dml_writeback_from_context_fpu(struct dc *dc,
+						struct resource_context *res_ctx,
+						display_e2e_pipe_params_st *pipes);
+
 #endif /* __DCN20_FPU_H__ */