UefiCpuPkg/MpInitLib: Remove StartCount and volatile definition.

The patch includes below changes:
(1) It removes "volatile" from RunningCount, because only the BSP modifies it.
(2) When we detect a timeout in CheckAllAPs(), and collect the list of failed CPUs, the size of the list is derived from the following difference, before the patch:
  StartCount - FinishedCount
where "StartCount" is set by the BSP at startup, and FinishedCount is incremented by the APs themselves.
Here the patch replaces this difference with
  StartCount - RunningCount
that is, the difference is no more calculated from the BSP's startup counter and the AP's shared finish counter, but from the RunningCount measurement that the BSP does itself, in CheckAllAPs().
(3) Finally, the patch changes the meaning of RunningCount. Before the patch, we have:
- StartCount: the number of APs the BSP stars up,
- RunningCount: the number of finished APs that the BSP collected
After the patch, StartCount is removed, and RunningCount is *redefined* as the following difference:
  OLD_StartCount - OLD_RunningCount
Giving the number of APs that the BSP started up but hasn't collected yet.

Cc: Laszlo Ersek <[email protected]>
Cc: Ruiyu Ni <[email protected]>
Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Eric Dong <[email protected]>
Reviewed-by: Ruiyu Ni <[email protected]>
Reviewed-by: Laszlo Ersek <[email protected]>
Tested-by: Laszlo Ersek <[email protected]>

UefiCpuPkg/Library/MpInitLib/MpLib.c

@@ -1424,7 +1424,7 @@ CheckAllAPs (
     // value of state after setting the it to CpuStateIdle, so BSP can safely make use of its value.
     //
     if (GetApState(CpuData) == CpuStateIdle) {
-      CpuMpData->RunningCount ++;
+      CpuMpData->RunningCount --;
       CpuMpData->CpuData[ProcessorNumber].Waiting = FALSE;
 
       //
@@ -1449,7 +1449,7 @@ CheckAllAPs (
   //
   // If all APs finish, return EFI_SUCCESS.
   //
-  if (CpuMpData->RunningCount == CpuMpData->StartCount) {
+  if (CpuMpData->RunningCount == 0) {
     return EFI_SUCCESS;
   }
 
@@ -1466,7 +1466,7 @@ CheckAllAPs (
     //
     if (CpuMpData->FailedCpuList != NULL) {
       *CpuMpData->FailedCpuList =
-         AllocatePool ((CpuMpData->StartCount - CpuMpData->FinishedCount + 1) * sizeof (UINTN));
+         AllocatePool ((CpuMpData->RunningCount + 1) * sizeof (UINTN));
       ASSERT (*CpuMpData->FailedCpuList != NULL);
     }
     ListIndex = 0;
@@ -2212,7 +2212,7 @@ StartupAllAPsWorker (
     return EFI_NOT_STARTED;
   }
 
-  CpuMpData->StartCount = 0;
+  CpuMpData->RunningCount = 0;
   for (ProcessorNumber = 0; ProcessorNumber < ProcessorCount; ProcessorNumber++) {
     CpuData = &CpuMpData->CpuData[ProcessorNumber];
     CpuData->Waiting = FALSE;
@@ -2222,7 +2222,7 @@ StartupAllAPsWorker (
         // Mark this processor as responsible for current calling.
         //
         CpuData->Waiting = TRUE;
-        CpuMpData->StartCount++;
+        CpuMpData->RunningCount++;
       }
     }
   }
@@ -2231,7 +2231,6 @@ StartupAllAPsWorker (
   CpuMpData->ProcArguments = ProcedureArgument;
   CpuMpData->SingleThread  = SingleThread;
   CpuMpData->FinishedCount = 0;
-  CpuMpData->RunningCount  = 0;
   CpuMpData->FailedCpuList = FailedCpuList;
   CpuMpData->ExpectedTime  = CalculateTimeout (
                                TimeoutInMicroseconds,

UefiCpuPkg/Library/MpInitLib/MpLib.h

@@ -215,9 +215,8 @@ struct _CPU_MP_DATA {
   UINTN                          BackupBuffer;
   UINTN                          BackupBufferSize;
 
-  volatile UINT32                StartCount;
   volatile UINT32                FinishedCount;
-  volatile UINT32                RunningCount;
+  UINT32                         RunningCount;
   BOOLEAN                        SingleThread;
   EFI_AP_PROCEDURE               Procedure;
   VOID                           *ProcArguments;