[Patch V4 2/2] UefiCpuPkg: Update PT code to support enable collect performance

["duntan" <dun.tan@intel.com>]

Update ProcTrace feature code to support enable collect performance
data by generating CYC and TSC packets. Add a new dynamic
PCD to indicate if enable performance collecting. In ProcTrace.c
code, if this new PCD is true, after check cpuid, CYC and TSC
packets will be generated by setting the corresponding MSR bits
feilds if supported.

Bugzila: https://bugzilla.tianocore.org/show_bug.cgi?id=4423
Signed-off-by: Dun Tan <dun.tan@intel.com>
Cc: Eric Dong <eric.dong@intel.com>
Reviewed-by: Ray Ni <ray.ni@intel.com>
Cc: Rahul Kumar <rahul1.kumar@intel.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Xiao X Chen <xiao.x.chen@intel.com>
---
 UefiCpuPkg/Library/CpuCommonFeaturesLib/CpuCommonFeaturesLib.inf | 11 ++++++-----
 UefiCpuPkg/Library/CpuCommonFeaturesLib/ProcTrace.c              | 38 ++++++++++++++++++++++++++++++--------
 UefiCpuPkg/UefiCpuPkg.dec                                        |  8 ++++++++
 3 files changed, 44 insertions(+), 13 deletions(-)

diff --git a/UefiCpuPkg/Library/CpuCommonFeaturesLib/CpuCommonFeaturesLib.inf b/UefiCpuPkg/Library/CpuCommonFeaturesLib/CpuCommonFeaturesLib.inf
index d803012ce2..1b823155b1 100644
--- a/UefiCpuPkg/Library/CpuCommonFeaturesLib/CpuCommonFeaturesLib.inf
+++ b/UefiCpuPkg/Library/CpuCommonFeaturesLib/CpuCommonFeaturesLib.inf
@@ -58,8 +58,9 @@
   LocalApicLib
 
 [Pcd]
-  gUefiCpuPkgTokenSpaceGuid.PcdCpuClockModulationDutyCycle   ## SOMETIMES_CONSUMES
-  gUefiCpuPkgTokenSpaceGuid.PcdIsPowerOnReset                ## SOMETIMES_CONSUMES
-  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceOutputScheme      ## SOMETIMES_CONSUMES
-  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceMemSize           ## SOMETIMES_CONSUMES
-  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceBspOnly           ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuClockModulationDutyCycle       ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdIsPowerOnReset                    ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceOutputScheme          ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceMemSize               ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceBspOnly               ## SOMETIMES_CONSUMES
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTracePerformanceCollecting ## SOMETIMES_CONSUMES
diff --git a/UefiCpuPkg/Library/CpuCommonFeaturesLib/ProcTrace.c b/UefiCpuPkg/Library/CpuCommonFeaturesLib/ProcTrace.c
index 92d6f54b42..a4510eb802 100644
--- a/UefiCpuPkg/Library/CpuCommonFeaturesLib/ProcTrace.c
+++ b/UefiCpuPkg/Library/CpuCommonFeaturesLib/ProcTrace.c
@@ -33,6 +33,7 @@ typedef struct  {
   MSR_IA32_RTIT_CTL_REGISTER                 RtitCtrl;
   MSR_IA32_RTIT_OUTPUT_BASE_REGISTER         RtitOutputBase;
   MSR_IA32_RTIT_OUTPUT_MASK_PTRS_REGISTER    RtitOutputMaskPtrs;
+  BOOLEAN                                    CycPacketSupported;
 } PROC_TRACE_PROCESSOR_DATA;
 
 typedef struct  {
@@ -47,6 +48,7 @@ typedef struct  {
   UINTN                        *TopaMemArray;
 
   BOOLEAN                      EnableOnBspOnly;
+  BOOLEAN                      EnablePerformanceCollecting;
 
   PROC_TRACE_PROCESSOR_DATA    *ProcessorData;
 } PROC_TRACE_DATA;
@@ -76,10 +78,11 @@ ProcTraceGetConfigData (
   ASSERT (ConfigData != NULL);
   ConfigData->ProcessorData = (PROC_TRACE_PROCESSOR_DATA *)((UINT8 *)ConfigData + sizeof (PROC_TRACE_DATA));
 
-  ConfigData->NumberOfProcessors    = (UINT32)NumberOfProcessors;
-  ConfigData->ProcTraceMemSize      = PcdGet32 (PcdCpuProcTraceMemSize);
-  ConfigData->ProcTraceOutputScheme = PcdGet8 (PcdCpuProcTraceOutputScheme);
-  ConfigData->EnableOnBspOnly       = PcdGetBool (PcdCpuProcTraceBspOnly);
+  ConfigData->NumberOfProcessors          = (UINT32)NumberOfProcessors;
+  ConfigData->ProcTraceMemSize            = PcdGet32 (PcdCpuProcTraceMemSize);
+  ConfigData->ProcTraceOutputScheme       = PcdGet8 (PcdCpuProcTraceOutputScheme);
+  ConfigData->EnableOnBspOnly             = PcdGetBool (PcdCpuProcTraceBspOnly);
+  ConfigData->EnablePerformanceCollecting = PcdGetBool (PcdCpuProcTracePerformanceCollecting);
 
   return ConfigData;
 }
@@ -111,7 +114,8 @@ ProcTraceSupport (
 {
   PROC_TRACE_DATA                              *ProcTraceData;
   CPUID_STRUCTURED_EXTENDED_FEATURE_FLAGS_EBX  Ebx;
-  CPUID_INTEL_PROCESSOR_TRACE_MAIN_LEAF_ECX    Ecx;
+  CPUID_INTEL_PROCESSOR_TRACE_MAIN_LEAF_ECX    ProcTraceEcx;
+  CPUID_INTEL_PROCESSOR_TRACE_MAIN_LEAF_EBX    ProcTraceEbx;
 
   //
   // Check if ProcTraceMemorySize option is enabled (0xFF means disable by user)
@@ -132,15 +136,17 @@ ProcTraceSupport (
     return FALSE;
   }
 
-  AsmCpuidEx (CPUID_INTEL_PROCESSOR_TRACE, CPUID_INTEL_PROCESSOR_TRACE_MAIN_LEAF, NULL, NULL, &Ecx.Uint32, NULL);
-  ProcTraceData->ProcessorData[ProcessorNumber].TopaSupported        = (BOOLEAN)(Ecx.Bits.RTIT == 1);
-  ProcTraceData->ProcessorData[ProcessorNumber].SingleRangeSupported = (BOOLEAN)(Ecx.Bits.SingleRangeOutput == 1);
+  AsmCpuidEx (CPUID_INTEL_PROCESSOR_TRACE, CPUID_INTEL_PROCESSOR_TRACE_MAIN_LEAF, NULL, &ProcTraceEbx.Uint32, &ProcTraceEcx.Uint32, NULL);
+  ProcTraceData->ProcessorData[ProcessorNumber].TopaSupported        = (BOOLEAN)(ProcTraceEcx.Bits.RTIT == 1);
+  ProcTraceData->ProcessorData[ProcessorNumber].SingleRangeSupported = (BOOLEAN)(ProcTraceEcx.Bits.SingleRangeOutput == 1);
   if ((ProcTraceData->ProcessorData[ProcessorNumber].TopaSupported && (ProcTraceData->ProcTraceOutputScheme == RtitOutputSchemeToPA)) ||
       (ProcTraceData->ProcessorData[ProcessorNumber].SingleRangeSupported && (ProcTraceData->ProcTraceOutputScheme == RtitOutputSchemeSingleRange)))
   {
     ProcTraceData->ProcessorData[ProcessorNumber].RtitCtrl.Uint64           = AsmReadMsr64 (MSR_IA32_RTIT_CTL);
     ProcTraceData->ProcessorData[ProcessorNumber].RtitOutputBase.Uint64     = AsmReadMsr64 (MSR_IA32_RTIT_OUTPUT_BASE);
     ProcTraceData->ProcessorData[ProcessorNumber].RtitOutputMaskPtrs.Uint64 = AsmReadMsr64 (MSR_IA32_RTIT_OUTPUT_MASK_PTRS);
+    ProcTraceData->ProcessorData[ProcessorNumber].CycPacketSupported        = (BOOLEAN)(ProcTraceEbx.Bits.ConfigurablePsb == 1);
+
     return TRUE;
   }
 
@@ -517,6 +523,22 @@ ProcTraceInitialize (
   CtrlReg.Bits.User     = 1;
   CtrlReg.Bits.BranchEn = 1;
   CtrlReg.Bits.TraceEn  = 1;
+
+  //
+  // Generate CYC/TSC timing packets to collect performance data.
+  //
+  if (ProcTraceData->EnablePerformanceCollecting) {
+    if (ProcTraceData->ProcessorData[ProcessorNumber].CycPacketSupported) {
+      CtrlReg.Bits.CYCEn     = 1;
+      CtrlReg.Bits.CYCThresh = 5;
+    }
+
+    //
+    // Write to TSCEn is always supported
+    //
+    CtrlReg.Bits.TSCEn = 1;
+  }
+
   CPU_REGISTER_TABLE_WRITE64 (
     ProcessorNumber,
     Msr,
diff --git a/UefiCpuPkg/UefiCpuPkg.dec b/UefiCpuPkg/UefiCpuPkg.dec
index 6845e80706..d31c3b127c 100644
--- a/UefiCpuPkg/UefiCpuPkg.dec
+++ b/UefiCpuPkg/UefiCpuPkg.dec
@@ -345,6 +345,14 @@
   # @Prompt Enable CPU processor trace only on BSP.
   gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTraceBspOnly|FALSE|BOOLEAN|0x60000019
 
+  ## This PCD indicates if enable performance collecting when CPU processor trace is enabled.<BR><BR>
+  #  CYC/TSC timing packets will be generated to collect performance data if this PCD is TRUE.
+  #  This PCD is ignored if CPU processor trace is disabled.<BR><BR>
+  #  TRUE  - Performance collecting will be enabled in processor trace.<BR>
+  #  FASLE - Performance collecting will be disabled in processor trace.<BR>
+  # @Prompt Enable performance collecting when processor trace is enabled.
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuProcTracePerformanceCollecting|FALSE|BOOLEAN|0x60000020
+
 [PcdsFixedAtBuild.X64, PcdsPatchableInModule.X64, PcdsDynamic.X64, PcdsDynamicEx.X64]
   ## Indicate access to non-SMRAM memory is restricted to reserved, runtime and ACPI NVS type after SmmReadyToLock.
   #  MMIO access is always allowed regardless of the value of this PCD.
-- 
2.39.1.windows.1