From 826659dbab972f50f9d036b3fbb1284b822b57fc Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 13 Sep 2021 13:32:50 -0400
Subject: drm/amd/display: Reduce stack size for
dml21_ModeSupportAndSystemConfigurationFull
Git-commit: a62427ef9b55d4b5aec2b08dc9b2d9719572bf57
Patch-mainline: v5.16-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
[Why & How]
With Werror enabled in the kernel we were failing the clang build since
dml21_ModeSupportAndSystemConfigurationFull's stack frame is 1064 when
building with clang, and exceeding the default 1024 stack frame limit.
The culprit seems to be the Pipe struct, so pull the relevant block
out into its own sub-function.
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
.../dc/dml/dcn21/display_mode_vba_21.c | 236 +++++++++---------
1 file changed, 123 insertions(+), 113 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 4136eb8256cb..8a7485e21d53 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -3394,6 +3394,127 @@ static unsigned int TruncToValidBPP(
}
}
+
+static noinline void CalculatePrefetchSchedulePerPlane(
+ struct display_mode_lib *mode_lib,
+ int i,
+ unsigned j,
+ unsigned k)
+{
+ struct vba_vars_st *locals = &mode_lib->vba;
+ Pipe myPipe;
+ HostVM myHostVM;
+
+ if (mode_lib->vba.XFCEnabled[k] == true) {
+ mode_lib->vba.XFCRemoteSurfaceFlipDelay =
+ CalculateRemoteSurfaceFlipDelay(
+ mode_lib,
+ mode_lib->vba.VRatio[k],
+ locals->SwathWidthYThisState[k],
+ dml_ceil(locals->BytePerPixelInDETY[k], 1.0),
+ mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k],
+ mode_lib->vba.XFCTSlvVupdateOffset,
+ mode_lib->vba.XFCTSlvVupdateWidth,
+ mode_lib->vba.XFCTSlvVreadyOffset,
+ mode_lib->vba.XFCXBUFLatencyTolerance,
+ mode_lib->vba.XFCFillBWOverhead,
+ mode_lib->vba.XFCSlvChunkSize,
+ mode_lib->vba.XFCBusTransportTime,
+ mode_lib->vba.TimeCalc,
+ mode_lib->vba.TWait,
+ &mode_lib->vba.SrcActiveDrainRate,
+ &mode_lib->vba.TInitXFill,
+ &mode_lib->vba.TslvChk);
+ } else {
+ mode_lib->vba.XFCRemoteSurfaceFlipDelay = 0.0;
+ }
+
+ myPipe.DPPCLK = locals->RequiredDPPCLK[i][j][k];
+ myPipe.DISPCLK = locals->RequiredDISPCLK[i][j];
+ myPipe.PixelClock = mode_lib->vba.PixelClock[k];
+ myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
+ myPipe.DPPPerPlane = locals->NoOfDPP[i][j][k];
+ myPipe.ScalerEnabled = mode_lib->vba.ScalerEnabled[k];
+ myPipe.SourceScan = mode_lib->vba.SourceScan[k];
+ myPipe.BlockWidth256BytesY = locals->Read256BlockWidthY[k];
+ myPipe.BlockHeight256BytesY = locals->Read256BlockHeightY[k];
+ myPipe.BlockWidth256BytesC = locals->Read256BlockWidthC[k];
+ myPipe.BlockHeight256BytesC = locals->Read256BlockHeightC[k];
+ myPipe.InterlaceEnable = mode_lib->vba.Interlace[k];
+ myPipe.NumberOfCursors = mode_lib->vba.NumberOfCursors[k];
+ myPipe.VBlank = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k];
+ myPipe.HTotal = mode_lib->vba.HTotal[k];
+
+
+ myHostVM.Enable = mode_lib->vba.HostVMEnable;
+ myHostVM.MaxPageTableLevels = mode_lib->vba.HostVMMaxPageTableLevels;
+ myHostVM.CachedPageTableLevels = mode_lib->vba.HostVMCachedPageTableLevels;
+
+
+ mode_lib->vba.IsErrorResult[i][j][k] = CalculatePrefetchSchedule(
+ mode_lib,
+ mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
+ mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
+ &myPipe,
+ locals->DSCDelayPerState[i][k],
+ mode_lib->vba.DPPCLKDelaySubtotal,
+ mode_lib->vba.DPPCLKDelaySCL,
+ mode_lib->vba.DPPCLKDelaySCLLBOnly,
+ mode_lib->vba.DPPCLKDelayCNVCFormater,
+ mode_lib->vba.DPPCLKDelayCNVCCursor,
+ mode_lib->vba.DISPCLKDelaySubtotal,
+ locals->SwathWidthYThisState[k] / mode_lib->vba.HRatio[k],
+ mode_lib->vba.OutputFormat[k],
+ mode_lib->vba.MaxInterDCNTileRepeaters,
+ dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[0][0][k]),
+ locals->MaximumVStartup[0][0][k],
+ mode_lib->vba.GPUVMMaxPageTableLevels,
+ mode_lib->vba.GPUVMEnable,
+ &myHostVM,
+ mode_lib->vba.DynamicMetadataEnable[k],
+ mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k],
+ mode_lib->vba.DynamicMetadataTransmittedBytes[k],
+ mode_lib->vba.DCCEnable[k],
+ mode_lib->vba.UrgentLatency,
+ mode_lib->vba.ExtraLatency,
+ mode_lib->vba.TimeCalc,
+ locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
+ locals->MetaRowBytes[0][0][k],
+ locals->DPTEBytesPerRow[0][0][k],
+ locals->PrefetchLinesY[0][0][k],
+ locals->SwathWidthYThisState[k],
+ locals->BytePerPixelInDETY[k],
+ locals->PrefillY[k],
+ locals->MaxNumSwY[k],
+ locals->PrefetchLinesC[0][0][k],
+ locals->BytePerPixelInDETC[k],
+ locals->PrefillC[k],
+ locals->MaxNumSwC[k],
+ locals->SwathHeightYThisState[k],
+ locals->SwathHeightCThisState[k],
+ mode_lib->vba.TWait,
+ mode_lib->vba.XFCEnabled[k],
+ mode_lib->vba.XFCRemoteSurfaceFlipDelay,
+ mode_lib->vba.ProgressiveToInterlaceUnitInOPP,
+ &locals->dst_x_after_scaler,
+ &locals->dst_y_after_scaler,
+ &locals->LineTimesForPrefetch[k],
+ &locals->PrefetchBW[k],
+ &locals->LinesForMetaPTE[k],
+ &locals->LinesForMetaAndDPTERow[k],
+ &locals->VRatioPreY[i][j][k],
+ &locals->VRatioPreC[i][j][k],
+ &locals->RequiredPrefetchPixelDataBWLuma[i][j][k],
+ &locals->RequiredPrefetchPixelDataBWChroma[i][j][k],
+ &locals->VStartupRequiredWhenNotEnoughTimeForDynamicMetadata,
+ &locals->Tno_bw[k],
+ &locals->prefetch_vmrow_bw[k],
+ locals->swath_width_luma_ub,
+ locals->swath_width_chroma_ub,
+ &mode_lib->vba.VUpdateOffsetPix[k],
+ &mode_lib->vba.VUpdateWidthPix[k],
+ &mode_lib->vba.VReadyOffsetPix[k]);
+}
void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
{
struct vba_vars_st *locals = &mode_lib->vba;
@@ -4676,120 +4797,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
mode_lib->vba.DRAMClockChangeLatency,
mode_lib->vba.UrgentLatency,
mode_lib->vba.SREnterPlusExitTime);
- for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
- Pipe myPipe;
- HostVM myHostVM;
-
- if (mode_lib->vba.XFCEnabled[k] == true) {
- mode_lib->vba.XFCRemoteSurfaceFlipDelay =
- CalculateRemoteSurfaceFlipDelay(
- mode_lib,
- mode_lib->vba.VRatio[k],
- locals->SwathWidthYThisState[k],
- dml_ceil(locals->BytePerPixelInDETY[k], 1.0),
- mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k],
- mode_lib->vba.XFCTSlvVupdateOffset,
- mode_lib->vba.XFCTSlvVupdateWidth,
- mode_lib->vba.XFCTSlvVreadyOffset,
- mode_lib->vba.XFCXBUFLatencyTolerance,
- mode_lib->vba.XFCFillBWOverhead,
- mode_lib->vba.XFCSlvChunkSize,
- mode_lib->vba.XFCBusTransportTime,
- mode_lib->vba.TimeCalc,
- mode_lib->vba.TWait,
- &mode_lib->vba.SrcActiveDrainRate,
- &mode_lib->vba.TInitXFill,
- &mode_lib->vba.TslvChk);
- } else {
- mode_lib->vba.XFCRemoteSurfaceFlipDelay = 0.0;
- }
+ for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++)
+ CalculatePrefetchSchedulePerPlane(mode_lib, i, j, k);
- myPipe.DPPCLK = locals->RequiredDPPCLK[i][j][k];
- myPipe.DISPCLK = locals->RequiredDISPCLK[i][j];
- myPipe.PixelClock = mode_lib->vba.PixelClock[k];
- myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
- myPipe.DPPPerPlane = locals->NoOfDPP[i][j][k];
- myPipe.ScalerEnabled = mode_lib->vba.ScalerEnabled[k];
- myPipe.SourceScan = mode_lib->vba.SourceScan[k];
- myPipe.BlockWidth256BytesY = locals->Read256BlockWidthY[k];
- myPipe.BlockHeight256BytesY = locals->Read256BlockHeightY[k];
- myPipe.BlockWidth256BytesC = locals->Read256BlockWidthC[k];
- myPipe.BlockHeight256BytesC = locals->Read256BlockHeightC[k];
- myPipe.InterlaceEnable = mode_lib->vba.Interlace[k];
- myPipe.NumberOfCursors = mode_lib->vba.NumberOfCursors[k];
- myPipe.VBlank = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k];
- myPipe.HTotal = mode_lib->vba.HTotal[k];
-
-
- myHostVM.Enable = mode_lib->vba.HostVMEnable;
- myHostVM.MaxPageTableLevels = mode_lib->vba.HostVMMaxPageTableLevels;
- myHostVM.CachedPageTableLevels = mode_lib->vba.HostVMCachedPageTableLevels;
-
-
- mode_lib->vba.IsErrorResult[i][j][k] = CalculatePrefetchSchedule(
- mode_lib,
- mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
- mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
- &myPipe,
- locals->DSCDelayPerState[i][k],
- mode_lib->vba.DPPCLKDelaySubtotal,
- mode_lib->vba.DPPCLKDelaySCL,
- mode_lib->vba.DPPCLKDelaySCLLBOnly,
- mode_lib->vba.DPPCLKDelayCNVCFormater,
- mode_lib->vba.DPPCLKDelayCNVCCursor,
- mode_lib->vba.DISPCLKDelaySubtotal,
- locals->SwathWidthYThisState[k] / mode_lib->vba.HRatio[k],
- mode_lib->vba.OutputFormat[k],
- mode_lib->vba.MaxInterDCNTileRepeaters,
- dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[0][0][k]),
- locals->MaximumVStartup[0][0][k],
- mode_lib->vba.GPUVMMaxPageTableLevels,
- mode_lib->vba.GPUVMEnable,
- &myHostVM,
- mode_lib->vba.DynamicMetadataEnable[k],
- mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k],
- mode_lib->vba.DynamicMetadataTransmittedBytes[k],
- mode_lib->vba.DCCEnable[k],
- mode_lib->vba.UrgentLatency,
- mode_lib->vba.ExtraLatency,
- mode_lib->vba.TimeCalc,
- locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
- locals->MetaRowBytes[0][0][k],
- locals->DPTEBytesPerRow[0][0][k],
- locals->PrefetchLinesY[0][0][k],
- locals->SwathWidthYThisState[k],
- locals->BytePerPixelInDETY[k],
- locals->PrefillY[k],
- locals->MaxNumSwY[k],
- locals->PrefetchLinesC[0][0][k],
- locals->BytePerPixelInDETC[k],
- locals->PrefillC[k],
- locals->MaxNumSwC[k],
- locals->SwathHeightYThisState[k],
- locals->SwathHeightCThisState[k],
- mode_lib->vba.TWait,
- mode_lib->vba.XFCEnabled[k],
- mode_lib->vba.XFCRemoteSurfaceFlipDelay,
- mode_lib->vba.ProgressiveToInterlaceUnitInOPP,
- &locals->dst_x_after_scaler,
- &locals->dst_y_after_scaler,
- &locals->LineTimesForPrefetch[k],
- &locals->PrefetchBW[k],
- &locals->LinesForMetaPTE[k],
- &locals->LinesForMetaAndDPTERow[k],
- &locals->VRatioPreY[i][j][k],
- &locals->VRatioPreC[i][j][k],
- &locals->RequiredPrefetchPixelDataBWLuma[i][j][k],
- &locals->RequiredPrefetchPixelDataBWChroma[i][j][k],
- &locals->VStartupRequiredWhenNotEnoughTimeForDynamicMetadata,
- &locals->Tno_bw[k],
- &locals->prefetch_vmrow_bw[k],
- locals->swath_width_luma_ub,
- locals->swath_width_chroma_ub,
- &mode_lib->vba.VUpdateOffsetPix[k],
- &mode_lib->vba.VUpdateWidthPix[k],
- &mode_lib->vba.VReadyOffsetPix[k]);
- }
mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0;
mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0;
for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
--
2.38.1