drm/amd/display: Add DSC delay factor workaround

[Why]
Certain 4K high refresh rate modes requiring DSC are exhibiting top
of screen underflow corruption. Increasing the DSC delay by a factor
of 6 percent stops the underflow for most use cases.

[How]
Multiply DSC delay requirement in DML by a factor.
Add debug option to make this DSC delay factor configurable.
Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Shen <george.shen@amd.com>
Tested-by: Mark Broadworth <mark.broadworth@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -852,6 +852,7 @@ struct dc_debug_options {
 	bool enable_double_buffered_dsc_pg_support;
 	bool enable_dp_dig_pixel_rate_div_policy;
 	enum lttpr_mode lttpr_mode_override;
+	unsigned int dsc_delay_factor_wa_x1000;
 };
 
 struct gpu_info_soc_bounding_box_v1_0;

drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c

@@ -2359,9 +2359,11 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
 
 		if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes)
 			dcn3_2_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
-
 	}
 
+	/* DML DSC delay factor workaround */
+	dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
+
 	/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
 	dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c

@@ -367,7 +367,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 				mode_lib->vba.OutputBpp[k], mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k],
 				mode_lib->vba.NumberOfDSCSlices[k], mode_lib->vba.OutputFormat[k],
 				mode_lib->vba.Output[k], mode_lib->vba.PixelClock[k],
-				mode_lib->vba.PixelClockBackEnd[k]);
+				mode_lib->vba.PixelClockBackEnd[k], mode_lib->vba.ip.dsc_delay_factor_wa);
 	}
 
 	for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k)
@@ -2475,7 +2475,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.OutputBppPerState[i][k], mode_lib->vba.HActive[k],
 					mode_lib->vba.HTotal[k], mode_lib->vba.NumberOfDSCSlices[k],
 					mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k],
-					mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k]);
+					mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k],
+					mode_lib->vba.ip.dsc_delay_factor_wa);
 		}
 
 		for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) {

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c

@@ -1726,7 +1726,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
 		enum output_format_class  OutputFormat,
 		enum output_encoder_class Output,
 		double PixelClock,
-		double PixelClockBackEnd)
+		double PixelClockBackEnd,
+		double dsc_delay_factor_wa)
 {
 	unsigned int DSCDelayRequirement_val;
 
@@ -1764,7 +1765,7 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
 	dml_print("DML::%s: DSCDelayRequirement_val = %d\n", __func__, DSCDelayRequirement_val);
 #endif
 
-	return DSCDelayRequirement_val;
+	return dml_ceil(DSCDelayRequirement_val * dsc_delay_factor_wa, 1);
 }
 
 void dml32_CalculateSurfaceSizeInMall(

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h

@@ -327,7 +327,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
 		enum output_format_class  OutputFormat,
 		enum output_encoder_class Output,
 		double PixelClock,
-		double PixelClockBackEnd);
+		double PixelClockBackEnd,
+		double dsc_delay_factor_wa);
 
 void dml32_CalculateSurfaceSizeInMall(
 		unsigned int NumberOfActiveSurfaces,

drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c

@@ -29,6 +29,7 @@
 #include "dcn321_fpu.h"
 #include "dcn32/dcn32_resource.h"
 #include "dcn321/dcn321_resource.h"
+#include "dml/dcn32/display_mode_vba_util_32.h"
 
 #define DCN3_2_DEFAULT_DET_SIZE 256
 
@@ -538,9 +539,11 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 
 		if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes)
 			dcn3_21_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
-
 	}
 
+	/* DML DSC delay factor workaround */
+	dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
+
 	/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
 	dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;

drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h

@@ -364,6 +364,9 @@ struct _vcs_dpi_ip_params_st {
 	unsigned int max_num_dp2p0_outputs;
 	unsigned int max_num_dp2p0_streams;
 	unsigned int VBlankNomDefaultUS;
+
+	/* DM workarounds */
+	double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix
 };
 
 struct _vcs_dpi_display_xfc_params_st {