UefiCpuPkg/MpInitLib: support 64-bit AP stack addresses

The cached "CPU_INFO_IN_HOB.ApTopOfStack" field currently has type UINT32.
This is not ideal because the AP stacks are located within
"CpuMpData->Buffer", which is allocated with a plain AllocatePages() call
in MpInitLibInitialize():

  platform  CpuMpPei included  PEI RAM > 4GB  result
  --------  -----------------  -------------  ------
  Ia32      *                  n/a            good
  Ia32X64   no                 n/a            BAD
  Ia32X64   yes                n/a            good
  X64       no                 *              BAD
  X64       yes                no             good
  X64       yes                yes            BAD

- If we are on an Ia32X64 or X64 platform that does not include CpuMpPei,
  then CpuDxe cannot reuse the CPU_INFO_IN_HOB structures preallocated by
  CpuMpPei (through the CpuInitMpLib GUID HOB), and then AllocatePages()
  -- invoked first in 64-bit DXE -- could return an address outside of
  32-bit address space.

- If we are on an X64 platform where the permanent PEI RAM extends above
  the 32-bit address space, then the same issue can surface even if
  CpuMpPei is included: even the original allocation of the
  CPU_INFO_IN_HOB structures, by CpuMpPei, could be satisfied from above
  4GB.

The original "AP init" branch in "X64/MpFuncs.nasm" correctly considers a
64-bit stack start: the "MP_CPU_EXCHANGE_INFO.StackStart" field has type
UINTN, and the code uses QWORD addition and movement to set RSP from it.

Adapt the "GetApicId" branch of "X64/MpFuncs.nasm":

- change the type of "CPU_INFO_IN_HOB.ApTopOfStack" to UINT64,

- remove the explicit truncation to UINT32 in InitializeApData(),

- update the "GetNextProcNumber" iteration size to the new size of
  "CPU_INFO_IN_HOB",

- set RSP with a QWORD movement from "CPU_INFO_IN_HOB.ApTopOfStack".

Because the same CPU_INFO_IN_HOB structure is used by "Ia32/MpFuncs.nasm",
we have to update the "GetNextProcNumber" iteration size there as well.
The ESP setting can be preserved as a DWORD movement from the original
offset (decimal 12), since our integers are little endian.

Cc: Jeff Fan <jeff.fan@intel.com>
Fixes: 845c5be1fd
Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Jeff Fan <jeff.fan@intel.com>

UefiCpuPkg/Library/MpInitLib/Ia32/MpFuncs.nasm

@@ -181,7 +181,7 @@ GetProcessorNumber:
 GetNextProcNumber:
     cmp         [edi], edx                       ; APIC ID match?
     jz          ProgramStack
-    add         edi, 16
+    add         edi, 20
     inc         ebx
     jmp         GetNextProcNumber    
 

UefiCpuPkg/Library/MpInitLib/MpLib.c

@@ -433,7 +433,7 @@ InitializeApData (
   IN OUT CPU_MP_DATA      *CpuMpData,
   IN     UINTN            ProcessorNumber,
   IN     UINT32           BistData,
-  IN     UINTN            ApTopOfStack
+  IN     UINT64           ApTopOfStack
   )
 {
   CPU_INFO_IN_HOB          *CpuInfoInHob;
@@ -442,7 +442,7 @@ InitializeApData (
   CpuInfoInHob[ProcessorNumber].InitialApicId = GetInitialApicId ();
   CpuInfoInHob[ProcessorNumber].ApicId        = GetApicId ();
   CpuInfoInHob[ProcessorNumber].Health        = BistData;
-  CpuInfoInHob[ProcessorNumber].ApTopOfStack  = (UINT32) ApTopOfStack;
+  CpuInfoInHob[ProcessorNumber].ApTopOfStack  = ApTopOfStack;
 
   CpuMpData->CpuData[ProcessorNumber].Waiting    = FALSE;
   CpuMpData->CpuData[ProcessorNumber].CpuHealthy = (BistData == 0) ? TRUE : FALSE;
@@ -480,7 +480,7 @@ ApWakeupFunction (
   UINT32                     BistData;
   volatile UINT32            *ApStartupSignalBuffer;
   CPU_INFO_IN_HOB            *CpuInfoInHob;
-  UINTN                      ApTopOfStack;
+  UINT64                     ApTopOfStack;
 
   //
   // AP finished assembly code and begin to execute C code
@@ -500,7 +500,7 @@ ApWakeupFunction (
       // This is first time AP wakeup, get BIST information from AP stack
       //
       ApTopOfStack  = CpuMpData->Buffer + (ProcessorNumber + 1) * CpuMpData->CpuApStackSize;
-      BistData = *(UINT32 *) (ApTopOfStack - sizeof (UINTN));
+      BistData = *(UINT32 *) ((UINTN) ApTopOfStack - sizeof (UINTN));
       //
       // Do some AP initialize sync
       //

UefiCpuPkg/Library/MpInitLib/MpLib.h

@@ -129,12 +129,14 @@ typedef struct {
 // we need to make sure the each fields offset same in different
 // architecture.
 //
+#pragma pack (1)
 typedef struct {
   UINT32                         InitialApicId;
   UINT32                         ApicId;
   UINT32                         Health;
-  UINT32                         ApTopOfStack;
+  UINT64                         ApTopOfStack;
 } CPU_INFO_IN_HOB;
+#pragma pack ()
 
 //
 // AP reset code information including code address and size,

UefiCpuPkg/Library/MpInitLib/X64/MpFuncs.nasm

@@ -185,13 +185,12 @@ GetProcessorNumber:
 GetNextProcNumber:
     cmp         dword [edi], edx                      ; APIC ID match?
     jz          ProgramStack
-    add         edi, 16
+    add         edi, 20
     inc         ebx
     jmp         GetNextProcNumber    
 
 ProgramStack:
-    xor         rsp, rsp
-    mov         esp, dword [edi + 12]
+    mov         rsp, qword [edi + 12]
 
 CProcedureInvoke:
     push       rbp               ; Push BIST data at top of AP stack