drm/amd/display: update dml to rev.99 and smu clk_table w/a

[why]
1. update dml to rev.99
2. add smu clk table w/a: smu gives 1 dtm level with mismatch votage
   table which causes multiple issues.

Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Charlene Liu <Charlene.Liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

2 files changed, 28 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index 6feb23432f8d..e4b9fd31223c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -64,6 +64,8 @@ typedef struct {
 	double DCFCLKDeepSleep;
 	unsigned int DPPPerPlane;
 	bool ScalerEnabled;
+	double VRatio;
+	double VRatioChroma;
 	enum scan_direction_class SourceScan;
 	unsigned int BlockWidth256BytesY;
 	unsigned int BlockHeight256BytesY;
@@ -942,6 +944,7 @@ static bool CalculatePrefetchSchedule(
 	double dst_y_prefetch_equ;
 	double Tsw_oto;
 	double prefetch_bw_oto;
+	double prefetch_bw_pr;
 	double Tvm_oto;
 	double Tr0_oto;
 	double Tvm_oto_lines;
@@ -971,6 +974,7 @@ static bool CalculatePrefetchSchedule(
 	double min_Lsw;
 	double Tsw_est1 = 0;
 	double Tsw_est3 = 0;
+	double  max_Tsw = 0;
 
 	if (GPUVMEnable == true && HostVMEnable == true) {
 		HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
@@ -1111,11 +1115,14 @@ static bool CalculatePrefetchSchedule(
 		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC / 4;
 	else
 		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC;
-
+	/*rev 99*/
+	prefetch_bw_pr = dml_min(1, bytes_pp * myPipe->PixelClock / (double) myPipe->DPPPerPlane);
+    max_Tsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime;
 	prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC;
 	prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerPlane, prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime));
+    prefetch_bw_oto = dml_max(prefetch_bw_pr, prefetch_sw_bytes / max_Tsw);
 
-	min_Lsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre;
+	min_Lsw = dml_max(1, dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre);
 	Lsw_oto = dml_ceil(4 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1) / 4;
 	Tsw_oto = Lsw_oto * LineTime;
 
@@ -1389,7 +1396,7 @@ static bool CalculatePrefetchSchedule(
 			dml_print("DML::%s: SwathHeightC = %d\n", __func__, SwathHeightC);
 			dml_print("DML::%s: VInitPreFillC = %f\n", __func__, VInitPreFillC);
 #endif
-			if ((SwathHeightC > 4)) {
+			if ((SwathHeightC > 4) || VInitPreFillC > 3) {
 				if (LinesToRequestPrefetchPixelData > (VInitPreFillC - 3.0) / 2.0) {
 					*VRatioPrefetchC = dml_max(
 							*VRatioPrefetchC,
@@ -2663,6 +2670,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			myPipe.DCFCLKDeepSleep = v->DCFCLKDeepSleep;
 			myPipe.DPPPerPlane = v->DPPPerPlane[k];
 			myPipe.ScalerEnabled = v->ScalerEnabled[k];
+			myPipe.VRatio = v->VRatio[k];
+			myPipe.VRatioChroma = v->VRatioChroma[k];
 			myPipe.SourceScan = v->SourceScan[k];
 			myPipe.BlockWidth256BytesY = v->BlockWidth256BytesY[k];
 			myPipe.BlockHeight256BytesY = v->BlockHeight256BytesY[k];
@@ -3911,6 +3920,9 @@ static noinline void CalculatePrefetchSchedulePerPlane(
 	myPipe.DCFCLKDeepSleep = v->ProjectedDCFCLKDeepSleep[i][j];
 	myPipe.DPPPerPlane = v->NoOfDPP[i][j][k];
 	myPipe.ScalerEnabled = v->ScalerEnabled[k];
+	myPipe.VRatio = mode_lib->vba.VRatio[k];
+	myPipe.VRatioChroma = mode_lib->vba.VRatioChroma[k];
+
 	myPipe.SourceScan = v->SourceScan[k];
 	myPipe.BlockWidth256BytesY = v->Read256BlockWidthY[k];
 	myPipe.BlockHeight256BytesY = v->Read256BlockHeightY[k];
@@ -4987,6 +4999,17 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						&v->meta_row_bandwidth[i][j][k],
 						&v->dpte_row_bandwidth[i][j][k]);
 			}
+			/*DCCMetaBufferSizeSupport(i, j) = True
+			For k = 0 To NumberOfActivePlanes - 1
+			If MetaRowBytes(i, j, k) > 24064 Then
+			DCCMetaBufferSizeSupport(i, j) = False
+			End If
+			Next k*/
+			v->DCCMetaBufferSizeSupport[i][j] = true;
+			for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+				if (v->MetaRowBytes[i][j][k] > 24064)
+					v->DCCMetaBufferSizeSupport[i][j] = false;
+			}
 			v->UrgLatency[i] = CalculateUrgentLatency(
 					v->UrgentLatencyPixelDataOnly,
 					v->UrgentLatencyPixelMixedWithVMData,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 90e87961fe3e..8fe74a3b39a8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -544,6 +544,8 @@ struct vba_vars_st {
 	bool DTBCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES];
 	double UrgentRoundTripAndOutOfOrderLatencyPerState[DC__VOLTAGE_STATES];
 	bool ROBSupport[DC__VOLTAGE_STATES][2];
+	//based on rev 99: Dim DCCMetaBufferSizeSupport(NumberOfStates, 1) As Boolean
+	bool DCCMetaBufferSizeSupport[DC__VOLTAGE_STATES][2];
 	bool PTEBufferSizeNotExceeded[DC__VOLTAGE_STATES][2];
 	bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES][2];
 	double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES][2];