aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c')
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c354
1 files changed, 70 insertions, 284 deletions
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index f47d82da115c..479e2c1a1301 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -396,64 +396,10 @@ static void CalculateUrgentBurstFactor(
static void UseMinimumDCFCLK(
struct display_mode_lib *mode_lib,
- int MaxInterDCNTileRepeaters,
+ struct vba_vars_st *v,
int MaxPrefetchMode,
- double FinalDRAMClockChangeLatency,
- double SREnterPlusExitTime,
- int ReturnBusWidth,
- int RoundTripPingLatencyCycles,
- int ReorderingBytes,
- int PixelChunkSizeInKByte,
- int MetaChunkSize,
- bool GPUVMEnable,
- int GPUVMMaxPageTableLevels,
- bool HostVMEnable,
- int NumberOfActivePlanes,
- double HostVMMinPageSize,
- int HostVMMaxNonCachedPageTableLevels,
- bool DynamicMetadataVMEnabled,
- enum immediate_flip_requirement ImmediateFlipRequirement,
- bool ProgressiveToInterlaceUnitInOPP,
- double MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly,
- int VTotal[],
- int VActive[],
- int DynamicMetadataTransmittedBytes[],
- int DynamicMetadataLinesBeforeActiveRequired[],
- bool Interlace[],
- double RequiredDPPCLK[][2][DC__NUM_DPP__MAX],
- double RequiredDISPCLK[][2],
- double UrgLatency[],
- unsigned int NoOfDPP[][2][DC__NUM_DPP__MAX],
- double ProjectedDCFCLKDeepSleep[][2],
- double MaximumVStartup[][2][DC__NUM_DPP__MAX],
- double TotalVActivePixelBandwidth[][2],
- double TotalVActiveCursorBandwidth[][2],
- double TotalMetaRowBandwidth[][2],
- double TotalDPTERowBandwidth[][2],
- unsigned int TotalNumberOfActiveDPP[][2],
- unsigned int TotalNumberOfDCCActiveDPP[][2],
- int dpte_group_bytes[],
- double PrefetchLinesY[][2][DC__NUM_DPP__MAX],
- double PrefetchLinesC[][2][DC__NUM_DPP__MAX],
- int swath_width_luma_ub_all_states[][2][DC__NUM_DPP__MAX],
- int swath_width_chroma_ub_all_states[][2][DC__NUM_DPP__MAX],
- int BytePerPixelY[],
- int BytePerPixelC[],
- int HTotal[],
- double PixelClock[],
- double PDEAndMetaPTEBytesPerFrame[][2][DC__NUM_DPP__MAX],
- double DPTEBytesPerRow[][2][DC__NUM_DPP__MAX],
- double MetaRowBytes[][2][DC__NUM_DPP__MAX],
- bool DynamicMetadataEnable[],
- double VActivePixelBandwidth[][2][DC__NUM_DPP__MAX],
- double VActiveCursorBandwidth[][2][DC__NUM_DPP__MAX],
- double ReadBandwidthLuma[],
- double ReadBandwidthChroma[],
- double DCFCLKPerState[],
- double DCFCLKState[][2]);
+ int ReorderingBytes);
+
static void CalculatePixelDeliveryTimes(
unsigned int NumberOfActivePlanes,
double VRatio[],
@@ -712,18 +658,6 @@ static double CalculateUrgentLatency(
double UrgentLatencyAdjustmentFabricClockReference,
double FabricClockSingle);
-static bool CalculateBytePerPixelAnd256BBlockSizes(
- enum source_format_class SourcePixelFormat,
- enum dm_swizzle_mode SurfaceTiling,
- unsigned int *BytePerPixelY,
- unsigned int *BytePerPixelC,
- double *BytePerPixelDETY,
- double *BytePerPixelDETC,
- unsigned int *BlockHeight256BytesY,
- unsigned int *BlockHeight256BytesC,
- unsigned int *BlockWidth256BytesY,
- unsigned int *BlockWidth256BytesC);
-
void dml30_recalculate(struct display_mode_lib *mode_lib)
{
ModeSupportAndSystemConfiguration(mode_lib);
@@ -2095,7 +2029,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
DTRACE(" return_bus_bw = %f", v->ReturnBW);
for (k = 0; k < v->NumberOfActivePlanes; ++k) {
- CalculateBytePerPixelAnd256BBlockSizes(
+ dml30_CalculateBytePerPixelAnd256BBlockSizes(
v->SourcePixelFormat[k],
v->SurfaceTiling[k],
&v->BytePerPixelY[k],
@@ -3049,40 +2983,12 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
{
//Maximum Bandwidth Used
- double TotalWRBandwidth = 0;
- double MaxPerPlaneVActiveWRBandwidth = 0;
- double WRBandwidth = 0;
- double MaxUsedBW = 0;
- for (k = 0; k < v->NumberOfActivePlanes; ++k) {
- if (v->WritebackEnable[k] == true
- && v->WritebackPixelFormat[k] == dm_444_32) {
- WRBandwidth = v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k]
- / (v->HTotal[k] * v->WritebackSourceHeight[k] / v->PixelClock[k]) * 4;
- } else if (v->WritebackEnable[k] == true) {
- WRBandwidth = v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k]
- / (v->HTotal[k] * v->WritebackSourceHeight[k] / v->PixelClock[k]) * 8;
- }
- TotalWRBandwidth = TotalWRBandwidth + WRBandwidth;
- MaxPerPlaneVActiveWRBandwidth = dml_max(MaxPerPlaneVActiveWRBandwidth, WRBandwidth);
- }
-
v->TotalDataReadBandwidth = 0;
for (k = 0; k < v->NumberOfActivePlanes; ++k) {
v->TotalDataReadBandwidth = v->TotalDataReadBandwidth
+ v->ReadBandwidthPlaneLuma[k]
+ v->ReadBandwidthPlaneChroma[k];
}
-
- {
- double MaxPerPlaneVActiveRDBandwidth = 0;
- for (k = 0; k < v->NumberOfActivePlanes; ++k) {
- MaxPerPlaneVActiveRDBandwidth = dml_max(MaxPerPlaneVActiveRDBandwidth,
- v->ReadBandwidthPlaneLuma[k] + v->ReadBandwidthPlaneChroma[k]);
-
- }
- }
-
- MaxUsedBW = MaxTotalRDBandwidth + TotalWRBandwidth;
}
// VStartup Margin
@@ -3165,7 +3071,7 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
- CalculateBytePerPixelAnd256BBlockSizes(
+ dml30_CalculateBytePerPixelAnd256BBlockSizes(
mode_lib->vba.SourcePixelFormat[k],
mode_lib->vba.SurfaceTiling[k],
&BytePerPixY[k],
@@ -3218,7 +3124,7 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
&dummysinglestring);
}
-static bool CalculateBytePerPixelAnd256BBlockSizes(
+void dml30_CalculateBytePerPixelAnd256BBlockSizes(
enum source_format_class SourcePixelFormat,
enum dm_swizzle_mode SurfaceTiling,
unsigned int *BytePerPixelY,
@@ -3305,7 +3211,6 @@ static bool CalculateBytePerPixelAnd256BBlockSizes(
*BlockWidth256BytesY = 256U / *BytePerPixelY / *BlockHeight256BytesY;
*BlockWidth256BytesC = 256U / *BytePerPixelC / *BlockHeight256BytesC;
}
- return true;
}
static double CalculateTWait(
@@ -3709,7 +3614,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
/*Bandwidth Support Check*/
for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) {
- CalculateBytePerPixelAnd256BBlockSizes(
+ dml30_CalculateBytePerPixelAnd256BBlockSizes(
v->SourcePixelFormat[k],
v->SurfaceTiling[k],
&v->BytePerPixelY[k],
@@ -4733,66 +4638,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
}
if (v->UseMinimumRequiredDCFCLK == true) {
- UseMinimumDCFCLK(
- mode_lib,
- v->MaxInterDCNTileRepeaters,
- MaxPrefetchMode,
- v->FinalDRAMClockChangeLatency,
- v->SREnterPlusExitTime,
- v->ReturnBusWidth,
- v->RoundTripPingLatencyCycles,
- ReorderingBytes,
- v->PixelChunkSizeInKByte,
- v->MetaChunkSize,
- v->GPUVMEnable,
- v->GPUVMMaxPageTableLevels,
- v->HostVMEnable,
- v->NumberOfActivePlanes,
- v->HostVMMinPageSize,
- v->HostVMMaxNonCachedPageTableLevels,
- v->DynamicMetadataVMEnabled,
- v->ImmediateFlipRequirement[0],
- v->ProgressiveToInterlaceUnitInOPP,
- v->MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation,
- v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
- v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
- v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly,
- v->VTotal,
- v->VActive,
- v->DynamicMetadataTransmittedBytes,
- v->DynamicMetadataLinesBeforeActiveRequired,
- v->Interlace,
- v->RequiredDPPCLK,
- v->RequiredDISPCLK,
- v->UrgLatency,
- v->NoOfDPP,
- v->ProjectedDCFCLKDeepSleep,
- v->MaximumVStartup,
- v->TotalVActivePixelBandwidth,
- v->TotalVActiveCursorBandwidth,
- v->TotalMetaRowBandwidth,
- v->TotalDPTERowBandwidth,
- v->TotalNumberOfActiveDPP,
- v->TotalNumberOfDCCActiveDPP,
- v->dpte_group_bytes,
- v->PrefetchLinesY,
- v->PrefetchLinesC,
- v->swath_width_luma_ub_all_states,
- v->swath_width_chroma_ub_all_states,
- v->BytePerPixelY,
- v->BytePerPixelC,
- v->HTotal,
- v->PixelClock,
- v->PDEAndMetaPTEBytesPerFrame,
- v->DPTEBytesPerRow,
- v->MetaRowBytes,
- v->DynamicMetadataEnable,
- v->VActivePixelBandwidth,
- v->VActiveCursorBandwidth,
- v->ReadBandwidthLuma,
- v->ReadBandwidthChroma,
- v->DCFCLKPerState,
- v->DCFCLKState);
+ UseMinimumDCFCLK(mode_lib, v, MaxPrefetchMode, ReorderingBytes);
if (v->ClampMinDCFCLK) {
/* Clamp calculated values to actual minimum */
@@ -6476,10 +6322,6 @@ static void CalculateSwathWidth(
for (k = 0; k < NumberOfActivePlanes; ++k) {
enum odm_combine_mode MainPlaneODMCombine = 0;
- surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]);
- surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]);
- surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]);
- surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]);
if (SourceScan[k] != dm_vert) {
SwathWidthSingleDPPY[k] = ViewportWidth[k];
@@ -6519,8 +6361,6 @@ static void CalculateSwathWidth(
surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]);
surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]);
- surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]);
- surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]);
if (SourceScan[k] != dm_vert) {
MaximumSwathHeightY[k] = Read256BytesBlockHeightY[k];
@@ -6528,6 +6368,7 @@ static void CalculateSwathWidth(
swath_width_luma_ub[k] = dml_min(surface_width_ub_l, (long) dml_ceil(SwathWidthY[k] - 1,
Read256BytesBlockWidthY[k]) + Read256BytesBlockWidthY[k]);
if (BytePerPixC[k] > 0) {
+ surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]);
swath_width_chroma_ub[k] = dml_min(surface_width_ub_c, (long) dml_ceil(SwathWidthC[k] - 1,
Read256BytesBlockWidthC[k]) + Read256BytesBlockWidthC[k]);
} else {
@@ -6539,6 +6380,7 @@ static void CalculateSwathWidth(
swath_width_luma_ub[k] = dml_min(surface_height_ub_l, (long) dml_ceil(SwathWidthY[k] - 1,
Read256BytesBlockHeightY[k]) + Read256BytesBlockHeightY[k]);
if (BytePerPixC[k] > 0) {
+ surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]);
swath_width_chroma_ub[k] = dml_min(surface_height_ub_c, (long) dml_ceil(SwathWidthC[k] - 1,
Read256BytesBlockHeightC[k]) + Read256BytesBlockHeightC[k]);
} else {
@@ -6651,77 +6493,21 @@ static double CalculateUrgentLatency(
return ret;
}
-
-static void UseMinimumDCFCLK(
+static noinline_for_stack void UseMinimumDCFCLK(
struct display_mode_lib *mode_lib,
- int MaxInterDCNTileRepeaters,
+ struct vba_vars_st *v,
int MaxPrefetchMode,
- double FinalDRAMClockChangeLatency,
- double SREnterPlusExitTime,
- int ReturnBusWidth,
- int RoundTripPingLatencyCycles,
- int ReorderingBytes,
- int PixelChunkSizeInKByte,
- int MetaChunkSize,
- bool GPUVMEnable,
- int GPUVMMaxPageTableLevels,
- bool HostVMEnable,
- int NumberOfActivePlanes,
- double HostVMMinPageSize,
- int HostVMMaxNonCachedPageTableLevels,
- bool DynamicMetadataVMEnabled,
- enum immediate_flip_requirement ImmediateFlipRequirement,
- bool ProgressiveToInterlaceUnitInOPP,
- double MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
- double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly,
- int VTotal[],
- int VActive[],
- int DynamicMetadataTransmittedBytes[],
- int DynamicMetadataLinesBeforeActiveRequired[],
- bool Interlace[],
- double RequiredDPPCLK[][2][DC__NUM_DPP__MAX],
- double RequiredDISPCLK[][2],
- double UrgLatency[],
- unsigned int NoOfDPP[][2][DC__NUM_DPP__MAX],
- double ProjectedDCFCLKDeepSleep[][2],
- double MaximumVStartup[][2][DC__NUM_DPP__MAX],
- double TotalVActivePixelBandwidth[][2],
- double TotalVActiveCursorBandwidth[][2],
- double TotalMetaRowBandwidth[][2],
- double TotalDPTERowBandwidth[][2],
- unsigned int TotalNumberOfActiveDPP[][2],
- unsigned int TotalNumberOfDCCActiveDPP[][2],
- int dpte_group_bytes[],
- double PrefetchLinesY[][2][DC__NUM_DPP__MAX],
- double PrefetchLinesC[][2][DC__NUM_DPP__MAX],
- int swath_width_luma_ub_all_states[][2][DC__NUM_DPP__MAX],
- int swath_width_chroma_ub_all_states[][2][DC__NUM_DPP__MAX],
- int BytePerPixelY[],
- int BytePerPixelC[],
- int HTotal[],
- double PixelClock[],
- double PDEAndMetaPTEBytesPerFrame[][2][DC__NUM_DPP__MAX],
- double DPTEBytesPerRow[][2][DC__NUM_DPP__MAX],
- double MetaRowBytes[][2][DC__NUM_DPP__MAX],
- bool DynamicMetadataEnable[],
- double VActivePixelBandwidth[][2][DC__NUM_DPP__MAX],
- double VActiveCursorBandwidth[][2][DC__NUM_DPP__MAX],
- double ReadBandwidthLuma[],
- double ReadBandwidthChroma[],
- double DCFCLKPerState[],
- double DCFCLKState[][2])
+ int ReorderingBytes)
{
double NormalEfficiency = 0;
double PTEEfficiency = 0;
double TotalMaxPrefetchFlipDPTERowBandwidth[DC__VOLTAGE_STATES][2] = { { 0 } };
unsigned int i, j, k;
- NormalEfficiency = (HostVMEnable == true ? PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData
- : PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly) / 100.0;
- PTEEfficiency = (HostVMEnable == true ? PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly
- / PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData : 1.0);
+ NormalEfficiency = (v->HostVMEnable == true ? v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData
+ : v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly) / 100.0;
+ PTEEfficiency = (v->HostVMEnable == true ? v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly
+ / v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData : 1.0);
for (i = 0; i < mode_lib->soc.num_states; ++i) {
for (j = 0; j <= 1; ++j) {
double PixelDCFCLKCyclesRequiredInPrefetch[DC__NUM_DPP__MAX] = { 0 };
@@ -6739,58 +6525,58 @@ static void UseMinimumDCFCLK(
double MinimumTvmPlus2Tr0 = 0;
TotalMaxPrefetchFlipDPTERowBandwidth[i][j] = 0;
- for (k = 0; k < NumberOfActivePlanes; ++k) {
+ for (k = 0; k < v->NumberOfActivePlanes; ++k) {
TotalMaxPrefetchFlipDPTERowBandwidth[i][j] = TotalMaxPrefetchFlipDPTERowBandwidth[i][j]
- + NoOfDPP[i][j][k] * DPTEBytesPerRow[i][j][k] / (15.75 * HTotal[k] / PixelClock[k]);
+ + v->NoOfDPP[i][j][k] * v->DPTEBytesPerRow[i][j][k] / (15.75 * v->HTotal[k] / v->PixelClock[k]);
}
- for (k = 0; k <= NumberOfActivePlanes - 1; ++k) {
- NoOfDPPState[k] = NoOfDPP[i][j][k];
+ for (k = 0; k <= v->NumberOfActivePlanes - 1; ++k) {
+ NoOfDPPState[k] = v->NoOfDPP[i][j][k];
}
- MinimumTWait = CalculateTWait(MaxPrefetchMode, FinalDRAMClockChangeLatency, UrgLatency[i], SREnterPlusExitTime);
- NonDPTEBandwidth = TotalVActivePixelBandwidth[i][j] + TotalVActiveCursorBandwidth[i][j] + TotalMetaRowBandwidth[i][j];
- DPTEBandwidth = (HostVMEnable == true || ImmediateFlipRequirement == dm_immediate_flip_required) ?
- TotalMaxPrefetchFlipDPTERowBandwidth[i][j] : TotalDPTERowBandwidth[i][j];
- DCFCLKRequiredForAverageBandwidth = dml_max3(ProjectedDCFCLKDeepSleep[i][j],
- (NonDPTEBandwidth + TotalDPTERowBandwidth[i][j]) / ReturnBusWidth / (MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation / 100),
- (NonDPTEBandwidth + DPTEBandwidth / PTEEfficiency) / NormalEfficiency / ReturnBusWidth);
-
- ExtraLatencyBytes = CalculateExtraLatencyBytes(ReorderingBytes, TotalNumberOfActiveDPP[i][j], PixelChunkSizeInKByte, TotalNumberOfDCCActiveDPP[i][j],
- MetaChunkSize, GPUVMEnable, HostVMEnable, NumberOfActivePlanes, NoOfDPPState, dpte_group_bytes,
- PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
- HostVMMinPageSize, HostVMMaxNonCachedPageTableLevels);
- ExtraLatencyCycles = RoundTripPingLatencyCycles + 32 + ExtraLatencyBytes / NormalEfficiency / ReturnBusWidth;
- for (k = 0; k < NumberOfActivePlanes; ++k) {
+ MinimumTWait = CalculateTWait(MaxPrefetchMode, v->FinalDRAMClockChangeLatency, v->UrgLatency[i], v->SREnterPlusExitTime);
+ NonDPTEBandwidth = v->TotalVActivePixelBandwidth[i][j] + v->TotalVActiveCursorBandwidth[i][j] + v->TotalMetaRowBandwidth[i][j];
+ DPTEBandwidth = (v->HostVMEnable == true || v->ImmediateFlipRequirement[0] == dm_immediate_flip_required) ?
+ TotalMaxPrefetchFlipDPTERowBandwidth[i][j] : v->TotalDPTERowBandwidth[i][j];
+ DCFCLKRequiredForAverageBandwidth = dml_max3(v->ProjectedDCFCLKDeepSleep[i][j],
+ (NonDPTEBandwidth + v->TotalDPTERowBandwidth[i][j]) / v->ReturnBusWidth / (v->MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation / 100),
+ (NonDPTEBandwidth + DPTEBandwidth / PTEEfficiency) / NormalEfficiency / v->ReturnBusWidth);
+
+ ExtraLatencyBytes = CalculateExtraLatencyBytes(ReorderingBytes, v->TotalNumberOfActiveDPP[i][j], v->PixelChunkSizeInKByte, v->TotalNumberOfDCCActiveDPP[i][j],
+ v->MetaChunkSize, v->GPUVMEnable, v->HostVMEnable, v->NumberOfActivePlanes, NoOfDPPState, v->dpte_group_bytes,
+ v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
+ v->HostVMMinPageSize, v->HostVMMaxNonCachedPageTableLevels);
+ ExtraLatencyCycles = v->RoundTripPingLatencyCycles + 32 + ExtraLatencyBytes / NormalEfficiency / v->ReturnBusWidth;
+ for (k = 0; k < v->NumberOfActivePlanes; ++k) {
double DCFCLKCyclesRequiredInPrefetch = { 0 };
double ExpectedPrefetchBWAcceleration = { 0 };
double PrefetchTime = { 0 };
- PixelDCFCLKCyclesRequiredInPrefetch[k] = (PrefetchLinesY[i][j][k] * swath_width_luma_ub_all_states[i][j][k] * BytePerPixelY[k]
- + PrefetchLinesC[i][j][k] * swath_width_chroma_ub_all_states[i][j][k] * BytePerPixelC[k]) / NormalEfficiency / ReturnBusWidth;
- DCFCLKCyclesRequiredInPrefetch = 2 * ExtraLatencyCycles / NoOfDPPState[k] + PDEAndMetaPTEBytesPerFrame[i][j][k] / PTEEfficiency
- / NormalEfficiency / ReturnBusWidth * (GPUVMMaxPageTableLevels > 2 ? 1 : 0) + 2 * DPTEBytesPerRow[i][j][k] / PTEEfficiency
- / NormalEfficiency / ReturnBusWidth + 2 * MetaRowBytes[i][j][k] / NormalEfficiency / ReturnBusWidth + PixelDCFCLKCyclesRequiredInPrefetch[k];
- PrefetchPixelLinesTime[k] = dml_max(PrefetchLinesY[i][j][k], PrefetchLinesC[i][j][k]) * HTotal[k] / PixelClock[k];
- ExpectedPrefetchBWAcceleration = (VActivePixelBandwidth[i][j][k] + VActiveCursorBandwidth[i][j][k]) / (ReadBandwidthLuma[k] + ReadBandwidthChroma[k]);
- DynamicMetadataVMExtraLatency[k] = (GPUVMEnable == true && DynamicMetadataEnable[k] == true && DynamicMetadataVMEnabled == true) ?
- UrgLatency[i] * GPUVMMaxPageTableLevels * (HostVMEnable == true ? HostVMMaxNonCachedPageTableLevels + 1 : 1) : 0;
- PrefetchTime = (MaximumVStartup[i][j][k] - 1) * HTotal[k] / PixelClock[k] - MinimumTWait - UrgLatency[i] * ((GPUVMMaxPageTableLevels <= 2 ? GPUVMMaxPageTableLevels
- : GPUVMMaxPageTableLevels - 2) * (HostVMEnable == true ? HostVMMaxNonCachedPageTableLevels + 1 : 1) - 1) - DynamicMetadataVMExtraLatency[k];
+ PixelDCFCLKCyclesRequiredInPrefetch[k] = (v->PrefetchLinesY[i][j][k] * v->swath_width_luma_ub_all_states[i][j][k] * v->BytePerPixelY[k]
+ + v->PrefetchLinesC[i][j][k] * v->swath_width_chroma_ub_all_states[i][j][k] * v->BytePerPixelC[k]) / NormalEfficiency / v->ReturnBusWidth;
+ DCFCLKCyclesRequiredInPrefetch = 2 * ExtraLatencyCycles / NoOfDPPState[k] + v->PDEAndMetaPTEBytesPerFrame[i][j][k] / PTEEfficiency
+ / NormalEfficiency / v->ReturnBusWidth * (v->GPUVMMaxPageTableLevels > 2 ? 1 : 0) + 2 * v->DPTEBytesPerRow[i][j][k] / PTEEfficiency
+ / NormalEfficiency / v->ReturnBusWidth + 2 * v->MetaRowBytes[i][j][k] / NormalEfficiency / v->ReturnBusWidth + PixelDCFCLKCyclesRequiredInPrefetch[k];
+ PrefetchPixelLinesTime[k] = dml_max(v->PrefetchLinesY[i][j][k], v->PrefetchLinesC[i][j][k]) * v->HTotal[k] / v->PixelClock[k];
+ ExpectedPrefetchBWAcceleration = (v->VActivePixelBandwidth[i][j][k] + v->VActiveCursorBandwidth[i][j][k]) / (v->ReadBandwidthLuma[k] + v->ReadBandwidthChroma[k]);
+ DynamicMetadataVMExtraLatency[k] = (v->GPUVMEnable == true && v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true) ?
+ v->UrgLatency[i] * v->GPUVMMaxPageTableLevels * (v->HostVMEnable == true ? v->HostVMMaxNonCachedPageTableLevels + 1 : 1) : 0;
+ PrefetchTime = (v->MaximumVStartup[i][j][k] - 1) * v->HTotal[k] / v->PixelClock[k] - MinimumTWait - v->UrgLatency[i] * ((v->GPUVMMaxPageTableLevels <= 2 ? v->GPUVMMaxPageTableLevels
+ : v->GPUVMMaxPageTableLevels - 2) * (v->HostVMEnable == true ? v->HostVMMaxNonCachedPageTableLevels + 1 : 1) - 1) - DynamicMetadataVMExtraLatency[k];
if (PrefetchTime > 0) {
double ExpectedVRatioPrefetch = { 0 };
ExpectedVRatioPrefetch = PrefetchPixelLinesTime[k] / (PrefetchTime * PixelDCFCLKCyclesRequiredInPrefetch[k] / DCFCLKCyclesRequiredInPrefetch);
DCFCLKRequiredForPeakBandwidthPerPlane[k] = NoOfDPPState[k] * PixelDCFCLKCyclesRequiredInPrefetch[k] / PrefetchPixelLinesTime[k]
* dml_max(1.0, ExpectedVRatioPrefetch) * dml_max(1.0, ExpectedVRatioPrefetch / 4) * ExpectedPrefetchBWAcceleration;
- if (HostVMEnable == true || ImmediateFlipRequirement == dm_immediate_flip_required) {
+ if (v->HostVMEnable == true || v->ImmediateFlipRequirement[0] == dm_immediate_flip_required) {
DCFCLKRequiredForPeakBandwidthPerPlane[k] = DCFCLKRequiredForPeakBandwidthPerPlane[k]
- + NoOfDPPState[k] * DPTEBandwidth / PTEEfficiency / NormalEfficiency / ReturnBusWidth;
+ + NoOfDPPState[k] * DPTEBandwidth / PTEEfficiency / NormalEfficiency / v->ReturnBusWidth;
}
} else {
- DCFCLKRequiredForPeakBandwidthPerPlane[k] = DCFCLKPerState[i];
+ DCFCLKRequiredForPeakBandwidthPerPlane[k] = v->DCFCLKPerState[i];
}
- if (DynamicMetadataEnable[k] == true) {
+ if (v->DynamicMetadataEnable[k] == true) {
double TsetupPipe = { 0 };
double TdmbfPipe = { 0 };
double TdmsksPipe = { 0 };
@@ -6798,49 +6584,49 @@ static void UseMinimumDCFCLK(
double AllowedTimeForUrgentExtraLatency = { 0 };
CalculateDynamicMetadataParameters(
- MaxInterDCNTileRepeaters,
- RequiredDPPCLK[i][j][k],
- RequiredDISPCLK[i][j],
- ProjectedDCFCLKDeepSleep[i][j],
- PixelClock[k],
- HTotal[k],
- VTotal[k] - VActive[k],
- DynamicMetadataTransmittedBytes[k],
- DynamicMetadataLinesBeforeActiveRequired[k],
- Interlace[k],
- ProgressiveToInterlaceUnitInOPP,
+ v->MaxInterDCNTileRepeaters,
+ v->RequiredDPPCLK[i][j][k],
+ v->RequiredDISPCLK[i][j],
+ v->ProjectedDCFCLKDeepSleep[i][j],
+ v->PixelClock[k],
+ v->HTotal[k],
+ v->VTotal[k] - v->VActive[k],
+ v->DynamicMetadataTransmittedBytes[k],
+ v->DynamicMetadataLinesBeforeActiveRequired[k],
+ v->Interlace[k],
+ v->ProgressiveToInterlaceUnitInOPP,
&TsetupPipe,
&TdmbfPipe,
&TdmecPipe,
&TdmsksPipe);
- AllowedTimeForUrgentExtraLatency = MaximumVStartup[i][j][k] * HTotal[k] / PixelClock[k] - MinimumTWait - TsetupPipe
+ AllowedTimeForUrgentExtraLatency = v->MaximumVStartup[i][j][k] * v->HTotal[k] / v->PixelClock[k] - MinimumTWait - TsetupPipe
- TdmbfPipe - TdmecPipe - TdmsksPipe - DynamicMetadataVMExtraLatency[k];
if (AllowedTimeForUrgentExtraLatency > 0) {
DCFCLKRequiredForPeakBandwidthPerPlane[k] = dml_max(DCFCLKRequiredForPeakBandwidthPerPlane[k],
ExtraLatencyCycles / AllowedTimeForUrgentExtraLatency);
} else {
- DCFCLKRequiredForPeakBandwidthPerPlane[k] = DCFCLKPerState[i];
+ DCFCLKRequiredForPeakBandwidthPerPlane[k] = v->DCFCLKPerState[i];
}
}
}
DCFCLKRequiredForPeakBandwidth = 0;
- for (k = 0; k <= NumberOfActivePlanes - 1; ++k) {
+ for (k = 0; k <= v->NumberOfActivePlanes - 1; ++k) {
DCFCLKRequiredForPeakBandwidth = DCFCLKRequiredForPeakBandwidth + DCFCLKRequiredForPeakBandwidthPerPlane[k];
}
- MinimumTvmPlus2Tr0 = UrgLatency[i] * (GPUVMEnable == true ? (HostVMEnable == true ?
- (GPUVMMaxPageTableLevels + 2) * (HostVMMaxNonCachedPageTableLevels + 1) - 1 : GPUVMMaxPageTableLevels + 1) : 0);
- for (k = 0; k < NumberOfActivePlanes; ++k) {
+ MinimumTvmPlus2Tr0 = v->UrgLatency[i] * (v->GPUVMEnable == true ? (v->HostVMEnable == true ?
+ (v->GPUVMMaxPageTableLevels + 2) * (v->HostVMMaxNonCachedPageTableLevels + 1) - 1 : v->GPUVMMaxPageTableLevels + 1) : 0);
+ for (k = 0; k < v->NumberOfActivePlanes; ++k) {
double MaximumTvmPlus2Tr0PlusTsw = { 0 };
- MaximumTvmPlus2Tr0PlusTsw = (MaximumVStartup[i][j][k] - 2) * HTotal[k] / PixelClock[k] - MinimumTWait - DynamicMetadataVMExtraLatency[k];
+ MaximumTvmPlus2Tr0PlusTsw = (v->MaximumVStartup[i][j][k] - 2) * v->HTotal[k] / v->PixelClock[k] - MinimumTWait - DynamicMetadataVMExtraLatency[k];
if (MaximumTvmPlus2Tr0PlusTsw <= MinimumTvmPlus2Tr0 + PrefetchPixelLinesTime[k] / 4) {
- DCFCLKRequiredForPeakBandwidth = DCFCLKPerState[i];
+ DCFCLKRequiredForPeakBandwidth = v->DCFCLKPerState[i];
} else {
DCFCLKRequiredForPeakBandwidth = dml_max3(DCFCLKRequiredForPeakBandwidth, 2 * ExtraLatencyCycles
/ (MaximumTvmPlus2Tr0PlusTsw - MinimumTvmPlus2Tr0 - PrefetchPixelLinesTime[k] / 4),
(2 * ExtraLatencyCycles + PixelDCFCLKCyclesRequiredInPrefetch[k]) / (MaximumTvmPlus2Tr0PlusTsw - MinimumTvmPlus2Tr0));
}
}
- DCFCLKState[i][j] = dml_min(DCFCLKPerState[i], 1.05 * (1 + mode_lib->vba.PercentMarginOverMinimumRequiredDCFCLK / 100)
+ v->DCFCLKState[i][j] = dml_min(v->DCFCLKPerState[i], 1.05 * (1 + mode_lib->vba.PercentMarginOverMinimumRequiredDCFCLK / 100)
* dml_max(DCFCLKRequiredForAverageBandwidth, DCFCLKRequiredForPeakBandwidth));
}
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.