[PATCH v3 05/11] UefiCpuPkg/CpuExceptionHandlerLib: Add stack switch support

[Jian J Wang <jian.j.wang@intel.com>]

> v3:
>  a. Move more general definitions to BaseLib.h
>  b. Update code to use new data structure CPU_EXCEPTION_INIT_DATA_EX
>  c. Implement new API InitializeCpuExceptionHandlersEx for DxeException
>  d. Add dummy InitializeCpuExceptionHandlersEx for SEC, PEI and SMM

> v2:
>  a. Move common TSS structure and API definitions to BaseLib.h
>  b. Add EXCEPTION_STACK_SWITCH_DATA to convery data used to setup stack
>     switch. This can avoid allocating memory for it in this library.
>  c. Add globals to reserve memory for stack switch initialized in early
>     phase of DXE core.
>  d. Remove the filter code used to exclude boot modes which doesn't support
>     memory allocation because those memory can passed in by parameter now.
>  e. Remove the nasm macro to define exception handler one by one and add a
>     function to return the start address of each handler.

If Stack Guard is enabled and there's really a stack overflow happened during
boot, a Page Fault exception will be triggered. Because the stack is out of
usage, the exception handler, which shares the stack with normal UEFI driver,
cannot be executed and cannot dump the processor information.

Without those information, it's very difficult for the BIOS developers locate
the root cause of stack overflow. And without a workable stack, the developer
cannot event use single step to debug the UEFI driver with JTAG debugger.

In order to make sure the exception handler to execute normally after stack
overflow. We need separate stacks for exception handlers in case of unusable
stack.

IA processor allows to switch to a new stack during handling interrupt and
exception. But X64 and IA32 provides different ways to make it. X64 provides
interrupt stack table (IST) to allow maximum 7 different exceptions to have
new stack for its handler. IA32 doesn't have IST mechanism and can only use
task gate to do it since task switch allows to load a new stack through its
task-state segment (TSS).

The new API, InitializeCpuExceptionHandlersEx, is implemented to complete
extra initialization for stack switch of exception handler. Since setting
up stack switch needs allocating new memory for new stack, new GDT table
and task-state segment but the initialization method will be called in
different phases which have no consistent way to reserve those memory, this
new API is allowed to pass the reserved resources to complete the extra
works. This is cannot be done by original InitializeCpuExceptionHandlers.

Considering exception handler initialization for MP situation, this new API
is also necessary, because AP is not supposed to allocate memory. So the
memory needed for stack switch have to be reserved in BSP before waking up
AP and then pass them to InitializeCpuExceptionHandlersEx afterwards.

Since Stack Guard feature is available only for DXE phase at this time, the
new API is fully implemented for DXE only. Other phases implement a dummy
one which just calls InitializeCpuExceptionHandlers().

Cc: Jiewen Yao <jiewen.yao@intel.com>
Cc: Eric Dong <eric.dong@intel.com>
Cc: Laszlo Ersek <lersek@redhat.com>
Cc: Michael Kinney <michael.d.kinney@intel.com>
Suggested-by: Ayellet Wolman <ayellet.wolman@intel.com>
Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Jian J Wang <jian.j.wang@intel.com>
---
 .../CpuExceptionHandlerLib/CpuExceptionCommon.h    |  39 ++
 .../DxeCpuExceptionHandlerLib.inf                  |   6 +
 .../Library/CpuExceptionHandlerLib/DxeException.c  |  79 ++++
 .../Ia32/ArchExceptionHandler.c                    | 167 +++++++++
 .../Ia32/ArchInterruptDefs.h                       |   8 +
 .../Ia32/ExceptionTssEntryAsm.nasm                 | 398 +++++++++++++++++++++
 .../CpuExceptionHandlerLib/PeiCpuException.c       |  34 +-
 .../PeiCpuExceptionHandlerLib.inf                  |   1 +
 .../CpuExceptionHandlerLib/SecPeiCpuException.c    |  34 +-
 .../SecPeiCpuExceptionHandlerLib.inf               |   1 +
 .../SmmCpuExceptionHandlerLib.inf                  |   1 +
 .../Library/CpuExceptionHandlerLib/SmmException.c  |  34 +-
 .../X64/ArchExceptionHandler.c                     | 134 +++++++
 .../CpuExceptionHandlerLib/X64/ArchInterruptDefs.h |   3 +
 14 files changed, 936 insertions(+), 3 deletions(-)
 create mode 100644 UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ExceptionTssEntryAsm.nasm

diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/CpuExceptionCommon.h b/UefiCpuPkg/Library/CpuExceptionHandlerLib/CpuExceptionCommon.h
index 740a58828b..9ad6c5f54f 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/CpuExceptionCommon.h
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/CpuExceptionCommon.h
@@ -48,6 +48,17 @@
     0xb21d9148, 0x9211, 0x4d8f, { 0xad, 0xd3, 0x66, 0xb1, 0x89, 0xc9, 0x2c, 0x83 } \
   }
 
+#define CPU_STACK_SWITCH_EXCEPTION_NUMBER \
+  FixedPcdGetSize (PcdCpuStackSwitchExceptionList)
+
+#define CPU_STACK_SWITCH_EXCEPTION_LIST \
+  FixedPcdGetPtr (PcdCpuStackSwitchExceptionList)
+
+#define CPU_KNOWN_GOOD_STACK_SIZE \
+  FixedPcdGet32 (PcdCpuKnownGoodStackSize)
+
+#define CPU_TSS_GDT_SIZE (SIZE_2KB + CPU_TSS_DESC_SIZE + CPU_TSS_SIZE)
+
 //
 // Record exception handler information
 //
@@ -288,5 +299,33 @@ CommonExceptionHandlerWorker (
   IN EXCEPTION_HANDLER_DATA      *ExceptionHandlerData
   );
 
+/**
+  Setup separate stack for specific exceptions.
+
+  @param[in] StackSwitchData      Pointer to data required for setuping up
+                                  stack switch.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized with new stack.
+  @retval EFI_INVALID_PARAMETER   StackSwitchData contains invalid content.
+**/
+EFI_STATUS
+ArchSetupExcpetionStack (
+  IN CPU_EXCEPTION_INIT_DATA_EX       *StackSwitchData
+  );
+
+/**
+  Return address map of exception handler template so that C code can generate
+  exception tables. The template is only for exceptions using task gate instead
+  of interrupt gate.
+
+  @param AddressMap  Pointer to a buffer where the address map is returned.
+**/
+VOID
+EFIAPI
+AsmGetTssTemplateMap (
+  OUT EXCEPTION_HANDLER_TEMPLATE_MAP  *AddressMap
+  );
+
 #endif
 
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeCpuExceptionHandlerLib.inf b/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeCpuExceptionHandlerLib.inf
index f4a8d01c80..58e55a8a2e 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeCpuExceptionHandlerLib.inf
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeCpuExceptionHandlerLib.inf
@@ -30,6 +30,7 @@
 [Sources.Ia32]
   Ia32/ExceptionHandlerAsm.asm
   Ia32/ExceptionHandlerAsm.nasm
+  Ia32/ExceptionTssEntryAsm.nasm
   Ia32/ExceptionHandlerAsm.S
   Ia32/ArchExceptionHandler.c
   Ia32/ArchInterruptDefs.h
@@ -47,6 +48,11 @@
   PeiDxeSmmCpuException.c
   DxeException.c
 
+[Pcd]
+  gEfiMdeModulePkgTokenSpaceGuid.PcdCpuStackGuard
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuStackSwitchExceptionList
+  gUefiCpuPkgTokenSpaceGuid.PcdCpuKnownGoodStackSize
+
 [Packages]
   MdePkg/MdePkg.dec
   MdeModulePkg/MdeModulePkg.dec
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeException.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeException.c
index 31febec976..dcd8d9bb98 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeException.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/DxeException.c
@@ -25,6 +25,10 @@ UINTN                       mEnabledInterruptNum = 0;
 
 EXCEPTION_HANDLER_DATA      mExceptionHandlerData;
 
+UINT8                       mNewStack[CPU_STACK_SWITCH_EXCEPTION_NUMBER *
+                                      CPU_KNOWN_GOOD_STACK_SIZE];
+UINT8                       mNewGdt[CPU_TSS_GDT_SIZE];
+
 /**
   Common exception handler.
 
@@ -197,3 +201,78 @@ RegisterCpuInterruptHandler (
 {
   return RegisterCpuInterruptHandlerWorker (InterruptType, InterruptHandler, &mExceptionHandlerData);
 }
+
+/**
+  Initializes CPU exceptions entries and setup stack switch for given exceptions.
+
+  This method will call InitializeCpuExceptionHandlers() to setup default
+  exception handlers unless indicated not to do it explicitly.
+
+  If InitDataEx is passed with NULL, this method will use the resource reserved
+  by global variables to initialize it; Otherwise it will use data in InitDataEx
+  to setup stack switch. This is for the different use cases in DxeCore and
+  Cpu MP exception initialization.
+
+  @param[in]  VectorInfo    Pointer to reserved vector list.
+  @param[in]  InitDataEx    Pointer to data required to setup stack switch for
+                            given exceptions.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized.
+  @retval EFI_INVALID_PARAMETER   VectorInfo or InitDataEx contains invalid
+                                  content.
+
+**/
+EFI_STATUS
+EFIAPI
+InitializeCpuExceptionHandlersEx (
+  IN EFI_VECTOR_HANDOFF_INFO            *VectorInfo OPTIONAL,
+  IN CPU_EXCEPTION_INIT_DATA_EX         *InitDataEx OPTIONAL
+  )
+{
+  EFI_STATUS                        Status;
+  CPU_EXCEPTION_INIT_DATA_EX        EssData;
+  IA32_DESCRIPTOR                   Idtr;
+  IA32_DESCRIPTOR                   Gdtr;
+
+  //
+  // To avoid repeat initialization of default handlers, the caller should pass
+  // an extended init data with InitDefaultHandlers set to FALSE. There's no
+  // need to call this method to just initialize default handlers. Call non-ex
+  // version instead; or this method must be implemented as a simple wrapper of
+  // non-ex version of it, if this version has to be called.
+  //
+  if (InitDataEx == NULL || InitDataEx->Ia32.InitDefaultHandlers) {
+    Status = InitializeCpuExceptionHandlers (VectorInfo);
+  } else {
+    Status = EFI_SUCCESS;
+  }
+
+  if (!EFI_ERROR (Status)) {
+    //
+    // Initializing stack switch is only necessary for Stack Guard functionality.
+    //
+    if (PcdGetBool (PcdCpuStackGuard)) {
+      if (InitDataEx == NULL) {
+        SetMem (mNewGdt, sizeof (mNewGdt), 0);
+
+        AsmReadIdtr (&Idtr);
+        AsmReadGdtr (&Gdtr);
+
+        EssData.Ia32.KnownGoodStackTop = (UINTN)mNewStack;
+        EssData.Ia32.KnownGoodStackSize = CPU_KNOWN_GOOD_STACK_SIZE;
+        EssData.Ia32.StackSwitchExceptions = CPU_STACK_SWITCH_EXCEPTION_LIST;
+        EssData.Ia32.StackSwitchExceptionNumber = CPU_STACK_SWITCH_EXCEPTION_NUMBER;
+        EssData.Ia32.IdtTable = (VOID *)Idtr.Base;
+        EssData.Ia32.GdtTable = mNewGdt;
+        EssData.Ia32.GdtSize = sizeof (mNewGdt);
+        EssData.Ia32.TssDesc = mNewGdt + Gdtr.Limit + 1;
+        EssData.Ia32.Tss = mNewGdt + Gdtr.Limit + 1 + CPU_TSS_DESC_SIZE;
+        InitDataEx = &EssData;
+      }
+      Status = ArchSetupExcpetionStack (InitDataEx);
+    }
+  }
+
+  return  Status;
+}
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchExceptionHandler.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchExceptionHandler.c
index f2c39eb193..e656eed842 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchExceptionHandler.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchExceptionHandler.c
@@ -107,6 +107,173 @@ ArchRestoreExceptionContext (
   SystemContext.SystemContextIa32->ExceptionData = ReservedVectors[ExceptionType].ExceptionData;
 }
 
+/**
+  Setup separate stack for given exceptions.
+
+  @param[in] StackSwitchData      Pointer to data required for setuping up
+                                  stack switch.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized with new stack.
+  @retval EFI_INVALID_PARAMETER   StackSwitchData contains invalid content.
+
+**/
+EFI_STATUS
+ArchSetupExcpetionStack (
+  IN CPU_EXCEPTION_INIT_DATA_EX     *StackSwitchData
+  )
+{
+  IA32_DESCRIPTOR                   Gdtr;
+  IA32_DESCRIPTOR                   Idtr;
+  IA32_IDT_GATE_DESCRIPTOR          *IdtTable;
+  IA32_TSS_DESCRIPTOR               *TssDesc;
+  IA32_TASK_STATE_SEGMENT           *Tss;
+  UINTN                             StackTop;
+  UINTN                             Index;
+  UINTN                             Vector;
+  UINTN                             TssBase;
+  UINTN                             GdtSize;
+  EXCEPTION_HANDLER_TEMPLATE_MAP    TemplateMap;
+
+  if (StackSwitchData == NULL ||
+      StackSwitchData->Ia32.KnownGoodStackTop == 0 ||
+      StackSwitchData->Ia32.KnownGoodStackSize == 0 ||
+      StackSwitchData->Ia32.StackSwitchExceptions == NULL ||
+      StackSwitchData->Ia32.StackSwitchExceptionNumber == 0 ||
+      StackSwitchData->Ia32.GdtTable == NULL ||
+      StackSwitchData->Ia32.IdtTable == NULL ||
+      StackSwitchData->Ia32.TssDesc == NULL ||
+      StackSwitchData->Ia32.Tss == NULL) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  //
+  // The caller is responsible for that the GDT table, no matter the existing
+  // one or newly allocated, has enough space to hold descriptors for exception
+  // task-state segments.
+  //
+  if (((UINTN)StackSwitchData->Ia32.GdtTable & (IA32_GDT_ALIGNMENT - 1)) != 0) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.TssDesc < (UINTN)(StackSwitchData->Ia32.GdtTable)) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.TssDesc >=
+      ((UINTN)(StackSwitchData->Ia32.GdtTable) + StackSwitchData->Ia32.GdtSize)) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  GdtSize = (UINTN)StackSwitchData->Ia32.TssDesc -
+            (UINTN)(StackSwitchData->Ia32.GdtTable) +
+            sizeof (IA32_TSS_DESCRIPTOR) *
+            (StackSwitchData->Ia32.StackSwitchExceptionNumber + 1);
+  if (GdtSize > StackSwitchData->Ia32.GdtSize) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  //
+  // Initialize new GDT table and/or IDT table, if any
+  //
+  AsmReadIdtr (&Idtr);
+  AsmReadGdtr (&Gdtr);
+  if ((UINTN)StackSwitchData->Ia32.GdtTable != Gdtr.Base) {
+    CopyMem (StackSwitchData->Ia32.GdtTable, (VOID *)Gdtr.Base, Gdtr.Limit + 1);
+    Gdtr.Base = (UINTN)StackSwitchData->Ia32.GdtTable;
+    Gdtr.Limit = (UINT16)GdtSize - 1;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.IdtTable != Idtr.Base) {
+    Idtr.Base = (UINTN)StackSwitchData->Ia32.IdtTable;
+  }
+
+  //
+  // Fixup current task descriptor. Task-state segment for current task will
+  // be filled by processor during task switching.
+  //
+  TssDesc = StackSwitchData->Ia32.TssDesc;
+  Tss     = StackSwitchData->Ia32.Tss;
+
+  TssBase = (UINTN)Tss;
+  TssDesc->Bits.LimitLow   = sizeof(IA32_TASK_STATE_SEGMENT) - 1;
+  TssDesc->Bits.BaseLow    = (UINT16)TssBase;
+  TssDesc->Bits.BaseMid    = (UINT8)(TssBase >> 16);
+  TssDesc->Bits.Type       = IA32_GDT_TYPE_TSS;
+  TssDesc->Bits.P          = 1;
+  TssDesc->Bits.LimitHigh  = 0;
+  TssDesc->Bits.BaseHigh   = (UINT8)(TssBase >> 24);
+
+  //
+  // Fixup exception task descriptor and task-state segment
+  //
+  AsmGetTssTemplateMap (&TemplateMap);
+  StackTop = StackSwitchData->Ia32.KnownGoodStackTop - CPU_STACK_ALIGNMENT;
+  StackTop = (UINTN)ALIGN_POINTER (StackTop, CPU_STACK_ALIGNMENT);
+  IdtTable = StackSwitchData->Ia32.IdtTable;
+  for (Index = 0; Index < StackSwitchData->Ia32.StackSwitchExceptionNumber; ++Index) {
+    TssDesc += 1;
+    Tss     += 1;
+
+    //
+    // Fixup TSS descriptor
+    //
+    TssBase = (UINTN)Tss;
+
+    TssDesc->Bits.LimitLow  = sizeof(IA32_TASK_STATE_SEGMENT) - 1;
+    TssDesc->Bits.BaseLow   = (UINT16)TssBase;
+    TssDesc->Bits.BaseMid   = (UINT8)(TssBase >> 16);
+    TssDesc->Bits.Type      = IA32_GDT_TYPE_TSS;
+    TssDesc->Bits.P         = 1;
+    TssDesc->Bits.LimitHigh = 0;
+    TssDesc->Bits.BaseHigh  = (UINT8)(TssBase >> 24);
+
+    //
+    // Fixup TSS
+    //
+    Vector = StackSwitchData->Ia32.StackSwitchExceptions[Index];
+    Tss->EIP    = (UINT32)(TemplateMap.ExceptionStart
+                           + Vector * TemplateMap.ExceptionStubHeaderSize);
+    Tss->EFLAGS = 0x2;
+    Tss->ESP    = StackTop;
+    Tss->CR3    = AsmReadCr3 ();
+    Tss->ES     = AsmReadEs ();
+    Tss->CS     = AsmReadCs ();
+    Tss->SS     = AsmReadSs ();
+    Tss->DS     = AsmReadDs ();
+    Tss->FS     = AsmReadFs ();
+    Tss->GS     = AsmReadGs ();
+
+    StackTop   -= StackSwitchData->Ia32.KnownGoodStackSize;
+
+    //
+    // Update IDT to use Task Gate for given exception
+    //
+    IdtTable[Vector].Bits.OffsetLow  = 0;
+    IdtTable[Vector].Bits.Selector   = (UINT16)((UINTN)TssDesc - Gdtr.Base);
+    IdtTable[Vector].Bits.Reserved_0 = 0;
+    IdtTable[Vector].Bits.GateType   = IA32_IDT_GATE_TYPE_TASK;
+    IdtTable[Vector].Bits.OffsetHigh = 0;
+  }
+
+  //
+  // Publish GDT
+  //
+  AsmWriteGdtr (&Gdtr);
+
+  //
+  // Load current task
+  //
+  AsmWriteTr ((UINT16)((UINTN)StackSwitchData->Ia32.TssDesc - Gdtr.Base));
+
+  //
+  // Publish IDT
+  //
+  AsmWriteIdtr (&Idtr);
+
+  return EFI_SUCCESS;
+}
+
 /**
   Display processor context.
 
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchInterruptDefs.h b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchInterruptDefs.h
index a8d3556a80..d9ded5977f 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchInterruptDefs.h
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ArchInterruptDefs.h
@@ -41,4 +41,12 @@ typedef struct {
   UINT8       HookAfterStubHeaderCode[HOOKAFTER_STUB_SIZE];
 } RESERVED_VECTORS_DATA;
 
+#define CPU_TSS_DESC_SIZE \
+  (sizeof (IA32_TSS_DESCRIPTOR) * \
+   (PcdGetSize (PcdCpuStackSwitchExceptionList) + 1))
+
+#define CPU_TSS_SIZE \
+  (sizeof (IA32_TASK_STATE_SEGMENT) * \
+   (PcdGetSize (PcdCpuStackSwitchExceptionList) + 1))
+
 #endif
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ExceptionTssEntryAsm.nasm b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ExceptionTssEntryAsm.nasm
new file mode 100644
index 0000000000..62bcedea1a
--- /dev/null
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/Ia32/ExceptionTssEntryAsm.nasm
@@ -0,0 +1,398 @@
+;------------------------------------------------------------------------------ ;
+; Copyright (c) 2017, Intel Corporation. All rights reserved.<BR>
+; This program and the accompanying materials
+; are licensed and made available under the terms and conditions of the BSD License
+; which accompanies this distribution.  The full text of the license may be found at
+; http://opensource.org/licenses/bsd-license.php.
+;
+; THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
+; WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
+;
+; Module Name:
+;
+;   ExceptionTssEntryAsm.Asm
+;
+; Abstract:
+;
+;   IA32 CPU Exception Handler with Separate Stack
+;
+; Notes:
+;
+;------------------------------------------------------------------------------
+
+;
+; IA32 TSS Memory Layout Description
+;
+struc IA32_TSS
+                    resw 1
+                    resw 1
+  .ESP0:    resd 1
+  .SS0:     resw 1
+                    resw 1
+  .ESP1:    resd 1
+  .SS1:     resw 1
+                    resw 1
+  .ESP2:    resd 1
+  .SS2:     resw 1
+                    resw 1
+  ._CR3:    resd 1
+  .EIP:     resd 1
+  .EFLAGS:  resd 1
+  ._EAX:    resd 1
+  ._ECX:    resd 1
+  ._EDX:    resd 1
+  ._EBX:    resd 1
+  ._ESP:    resd 1
+  ._EBP:    resd 1
+  ._ESI:    resd 1
+  ._EDI:    resd 1
+  ._ES:     resw 1
+                    resw 1
+  ._CS:     resw 1
+                    resw 1
+  ._SS:     resw 1
+                    resw 1
+  ._DS:     resw 1
+                    resw 1
+  ._FS:     resw 1
+                    resw 1
+  ._GS:     resw 1
+                    resw 1
+  .LDT:     resw 1
+                    resw 1
+                    resw 1
+                    resw 1
+endstruc
+
+;
+; CommonExceptionHandler()
+;
+extern ASM_PFX(CommonExceptionHandler)
+
+SECTION .data
+
+SECTION .text
+
+ALIGN   8
+
+;
+; Exception handler stub table
+;
+AsmExceptionEntryBegin:
+%assign Vector 0
+%rep  32
+
+DoIret%[Vector]:
+    iretd
+ASM_PFX(ExceptionTaskSwtichEntry%[Vector]):
+    db      0x6a        ; push  #VectorNum
+    db      %[Vector]
+    mov     eax, ASM_PFX(CommonTaskSwtichEntryPoint)
+    call    eax
+    mov     esp, eax    ; Restore stack top
+    jmp     DoIret%[Vector]
+
+%assign Vector Vector+1
+%endrep
+AsmExceptionEntryEnd:
+
+;
+; Common part of exception handler
+;
+global ASM_PFX(CommonTaskSwtichEntryPoint)
+ASM_PFX(CommonTaskSwtichEntryPoint):
+    ;
+    ; Stack:
+    ; +---------------------+ <-- EBP - 8
+    ; +       TSS Base      +
+    ; +---------------------+ <-- EBP - 4
+    ; +      CPUID.EDX      +
+    ; +---------------------+ <-- EBP
+    ; +         EIP         +
+    ; +---------------------+ <-- EBP + 4
+    ; +    Vector Number    +
+    ; +---------------------+ <-- EBP + 8
+    ; +    Error Code       +
+    ; +---------------------+
+    ;
+
+    mov     ebp, esp                    ; Stack frame
+
+; Use CPUID to determine if FXSAVE/FXRESTOR and DE are supported
+    mov     eax, 1
+    cpuid
+    push    edx
+
+; Get TSS base of interrupted task through PreviousTaskLink field in
+; current TSS base
+    sub     esp, 8
+    sgdt    [esp + 2]
+    mov     eax, [esp + 4]              ; GDT base
+    add     esp, 8
+
+    xor     ebx, ebx
+    str     bx                          ; Current TR
+
+    mov     ecx, [eax + ebx + 2]
+    shl     ecx, 8
+    mov     cl, [eax + ebx + 7]
+    ror     ecx, 8                      ; ecx = Current TSS base
+    push    ecx                         ; keep it in stack for later use
+
+    movzx   ebx, word [ecx]             ; Previous Task Link
+    mov     ecx, [eax + ebx + 2]
+    shl     ecx, 8
+    mov     cl, [eax + ebx + 7]
+    ror     ecx, 8                      ; ecx = Previous TSS base
+
+;
+; Align stack to make sure that EFI_FX_SAVE_STATE_IA32 of EFI_SYSTEM_CONTEXT_IA32
+; is 16-byte aligned
+;
+    and     esp, 0xfffffff0
+    sub     esp, 12
+
+;; UINT32  Edi, Esi, Ebp, Esp, Ebx, Edx, Ecx, Eax;
+    push    dword [ecx + IA32_TSS._EAX]
+    push    dword [ecx + IA32_TSS._ECX]
+    push    dword [ecx + IA32_TSS._EDX]
+    push    dword [ecx + IA32_TSS._EBX]
+    push    dword [ecx + IA32_TSS._ESP]
+    push    dword [ecx + IA32_TSS._EBP]
+    push    dword [ecx + IA32_TSS._ESI]
+    push    dword [ecx + IA32_TSS._EDI]
+
+;; UINT32  Gs, Fs, Es, Ds, Cs, Ss;
+    movzx   eax, word [ecx + IA32_TSS._SS]
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS._CS]
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS._DS]
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS._ES]
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS._FS]
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS._GS]
+    push    eax
+
+;; UINT32  Eip;
+    push    dword [ecx + IA32_TSS.EIP]
+
+;; UINT32  Gdtr[2], Idtr[2];
+    sub     esp, 8
+    sidt    [esp]
+    mov     eax, [esp + 2]
+    xchg    eax, [esp]
+    and     eax, 0xFFFF
+    mov     [esp+4], eax
+
+    sub     esp, 8
+    sgdt    [esp]
+    mov     eax, [esp + 2]
+    xchg    eax, [esp]
+    and     eax, 0xFFFF
+    mov     [esp+4], eax
+
+;; UINT32  Ldtr, Tr;
+    mov     eax, ebx    ; ebx still keeps selector of interrupted task
+    push    eax
+    movzx   eax, word [ecx + IA32_TSS.LDT]
+    push    eax
+
+;; UINT32  EFlags;
+    push    dword [ecx + IA32_TSS.EFLAGS]
+
+;; UINT32  Cr0, Cr1, Cr2, Cr3, Cr4;
+    mov     eax, cr4
+    push    eax             ; push cr4 firstly
+
+    mov     edx, [ebp - 4]  ; cpuid.edx
+    test    edx, BIT24      ; Test for FXSAVE/FXRESTOR support
+    jz      .1
+    or      eax, BIT9       ; Set CR4.OSFXSR
+.1:
+    test    edx, BIT2       ; Test for Debugging Extensions support
+    jz      .2
+    or      eax, BIT3       ; Set CR4.DE
+.2:
+    mov     cr4, eax
+
+    mov     eax, cr3
+    push    eax
+    mov     eax, cr2
+    push    eax
+    xor     eax, eax
+    push    eax
+    mov     eax, cr0
+    push    eax
+
+;; UINT32  Dr0, Dr1, Dr2, Dr3, Dr6, Dr7;
+    mov     eax, dr7
+    push    eax
+    mov     eax, dr6
+    push    eax
+    mov     eax, dr3
+    push    eax
+    mov     eax, dr2
+    push    eax
+    mov     eax, dr1
+    push    eax
+    mov     eax, dr0
+    push    eax
+
+;; FX_SAVE_STATE_IA32 FxSaveState;
+;; Clear TS bit in CR0 to avoid Device Not Available Exception (#NM)
+;; when executing fxsave/fxrstor instruction
+    test    edx, BIT24  ; Test for FXSAVE/FXRESTOR support.
+                        ; edx still contains result from CPUID above
+    jz      .3
+    clts
+    sub     esp, 512
+    mov     edi, esp
+    db      0xf, 0xae, 0x7 ;fxsave [edi]
+.3:
+
+;; UINT32  ExceptionData;
+    push    dword [ebp + 8]
+
+;; UEFI calling convention for IA32 requires that Direction flag in EFLAGs is clear
+    cld
+
+;; call into exception handler
+    mov     esi, ecx            ; Keep TSS base to avoid overwrite
+    mov     eax, ASM_PFX(CommonExceptionHandler)
+
+;; Prepare parameter and call
+    mov     edx, esp
+    push    edx                 ; EFI_SYSTEM_CONTEXT
+    push    dword [ebp + 4]     ; EFI_EXCEPTION_TYPE (vector number)
+
+    ;
+    ; Call External Exception Handler
+    ;
+    call    eax
+    add     esp, 8              ; Restore stack before calling
+    mov     ecx, esi            ; Restore TSS base
+
+;; UINT32  ExceptionData;
+    add     esp, 4
+
+;; FX_SAVE_STATE_IA32 FxSaveState;
+    mov     edx, [ebp - 4]  ; cpuid.edx
+    test    edx, BIT24      ; Test for FXSAVE/FXRESTOR support
+    jz      .4
+    mov     esi, esp
+    db      0xf, 0xae, 0xe  ; fxrstor [esi]
+.4:
+    add     esp, 512
+
+;; UINT32  Dr0, Dr1, Dr2, Dr3, Dr6, Dr7;
+;; Skip restoration of DRx registers to support debuggers
+;; that set breakpoints in interrupt/exception context
+    add     esp, 4 * 6
+
+;; UINT32  Cr0, Cr1, Cr2, Cr3, Cr4;
+    pop     eax
+    mov     cr0, eax
+    add     esp, 4    ; not for Cr1
+    pop     eax
+    mov     cr2, eax
+    pop     eax
+    mov     dword [ecx + IA32_TSS._CR3], eax
+    pop     eax
+    mov     cr4, eax
+
+;; UINT32  EFlags;
+    pop     dword [ecx + IA32_TSS.EFLAGS]
+    mov     ebx, dword [ecx + IA32_TSS.EFLAGS]
+    btr     ebx, 9      ; Do 'cli'
+    mov     dword [ecx + IA32_TSS.EFLAGS], ebx
+
+;; UINT32  Ldtr, Tr;
+;; UINT32  Gdtr[2], Idtr[2];
+;; Best not let anyone mess with these particular registers...
+    add     esp, 24
+
+;; UINT32  Eip;
+    pop     dword [ecx + IA32_TSS.EIP]
+
+;; UINT32  Gs, Fs, Es, Ds, Cs, Ss;
+;; NOTE - modified segment registers could hang the debugger...  We
+;;        could attempt to insulate ourselves against this possibility,
+;;        but that poses risks as well.
+;;
+    pop     eax
+o16 mov     [ecx + IA32_TSS._GS], ax
+    pop     eax
+o16 mov     [ecx + IA32_TSS._FS], ax
+    pop     eax
+o16 mov     [ecx + IA32_TSS._ES], ax
+    pop     eax
+o16 mov     [ecx + IA32_TSS._DS], ax
+    pop     eax
+o16 mov     [ecx + IA32_TSS._CS], ax
+    pop     eax
+o16 mov     [ecx + IA32_TSS._SS], ax
+
+;; UINT32  Edi, Esi, Ebp, Esp, Ebx, Edx, Ecx, Eax;
+    pop     dword [ecx + IA32_TSS._EDI]
+    pop     dword [ecx + IA32_TSS._ESI]
+    add     esp, 4   ; not for ebp
+    add     esp, 4   ; not for esp
+    pop     dword [ecx + IA32_TSS._EBX]
+    pop     dword [ecx + IA32_TSS._EDX]
+    pop     dword [ecx + IA32_TSS._ECX]
+    pop     dword [ecx + IA32_TSS._EAX]
+
+; Set single step DB# to allow debugger to able to go back to the EIP
+; where the exception is triggered.
+
+;; Create return context for iretd in stub function
+    mov    eax, dword [ecx + IA32_TSS._ESP]      ; Get old stack pointer
+    mov    ebx, dword [ecx + IA32_TSS.EIP]
+    mov    [eax - 0xc], ebx                      ; create EIP in old stack
+    movzx  ebx, word [ecx + IA32_TSS._CS]
+    mov    [eax - 0x8], ebx                      ; create CS in old stack
+    mov    ebx, dword [ecx + IA32_TSS.EFLAGS]
+    bts    ebx, 8
+    mov    [eax - 0x4], ebx                      ; create eflags in old stack
+    mov    dword [ecx + IA32_TSS.EFLAGS], ebx    ; update eflags in old TSS
+    mov    eax, dword [ecx + IA32_TSS._ESP]      ; Get old stack pointer
+    sub    eax, 0xc                              ; minus 12 byte
+    mov    dword [ecx + IA32_TSS._ESP], eax      ; Set new stack pointer
+
+;; Replace the EIP of interrupted task with stub function
+    mov    eax, ASM_PFX(SingleStepStubFunction)
+    mov    dword [ecx + IA32_TSS.EIP], eax
+
+    mov     ecx, [ebp - 8]                       ; Get current TSS base
+    mov     eax, dword [ecx + IA32_TSS._ESP]     ; Return current stack top
+    mov     esp, ebp
+
+    ret
+
+global ASM_PFX(SingleStepStubFunction)
+ASM_PFX(SingleStepStubFunction):
+;
+; we need clean TS bit in CR0 to execute
+; x87 FPU/MMX/SSE/SSE2/SSE3/SSSE3/SSE4 instructions.
+;
+    clts
+    iretd
+
+global ASM_PFX(AsmGetTssTemplateMap)
+ASM_PFX(AsmGetTssTemplateMap):
+    push    ebp                 ; C prolog
+    mov     ebp, esp
+    pushad
+
+    mov ebx, dword [ebp + 0x8]
+    mov dword [ebx],       ASM_PFX(ExceptionTaskSwtichEntry0)
+    mov dword [ebx + 0x4], (AsmExceptionEntryEnd - AsmExceptionEntryBegin) / 32
+    mov dword [ebx + 0x8], 0
+
+    popad
+    pop     ebp
+    ret
+
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuException.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuException.c
index 8d8d16ecbd..6dc0decbc5 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuException.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuException.c
@@ -177,4 +177,36 @@ RegisterCpuInterruptHandler (
   )
 {
   return EFI_UNSUPPORTED;
-}
\ No newline at end of file
+}
+
+/**
+  Initializes all CPU exceptions entries with optional extra initializations.
+
+  By default, this method should include all functionalities implemented by
+  InitializeCpuExceptionHandlers(), plus extra initialization works, if any.
+  This is could be done by calling InitializeCpuExceptionHandlers() directly
+  in this method besides the extra works.
+
+  InitDataEx is optional and its use and content are processor arch dependent.
+  The typical usage of it is to convey resources which have to be reserved
+  elsewhere and are necessary for the extra initializations of exception.
+
+  @param[in]  VectorInfo    Pointer to reserved vector list.
+  @param[in]  InitDataEx    Pointer to data optional for extra initializations
+                            of exception.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized.
+  @retval EFI_INVALID_PARAMETER   VectorInfo or InitDataEx contains invalid
+                                  content.
+
+**/
+EFI_STATUS
+EFIAPI
+InitializeCpuExceptionHandlersEx (
+  IN EFI_VECTOR_HANDOFF_INFO            *VectorInfo OPTIONAL,
+  IN CPU_EXCEPTION_INIT_DATA_EX         *InitDataEx OPTIONAL
+  )
+{
+  return InitializeCpuExceptionHandlers (VectorInfo);
+}
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuExceptionHandlerLib.inf b/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuExceptionHandlerLib.inf
index 75443288a9..4c0d435136 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuExceptionHandlerLib.inf
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/PeiCpuExceptionHandlerLib.inf
@@ -30,6 +30,7 @@
 [Sources.Ia32]
   Ia32/ExceptionHandlerAsm.asm
   Ia32/ExceptionHandlerAsm.nasm
+  Ia32/ExceptionTssEntryAsm.nasm
   Ia32/ExceptionHandlerAsm.S
   Ia32/ArchExceptionHandler.c
   Ia32/ArchInterruptDefs.h
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuException.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuException.c
index af608bffb6..56b87efdc7 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuException.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuException.c
@@ -176,4 +176,36 @@ RegisterCpuInterruptHandler (
   )
 {
   return EFI_UNSUPPORTED;
-}
\ No newline at end of file
+}
+
+/**
+  Initializes all CPU exceptions entries with optional extra initializations.
+
+  By default, this method should include all functionalities implemented by
+  InitializeCpuExceptionHandlers(), plus extra initialization works, if any.
+  This is could be done by calling InitializeCpuExceptionHandlers() directly
+  in this method besides the extra works.
+
+  InitDataEx is optional and its use and content are processor arch dependent.
+  The typical usage of it is to convey resources which have to be reserved
+  elsewhere and are necessary for the extra initializations of exception.
+
+  @param[in]  VectorInfo    Pointer to reserved vector list.
+  @param[in]  InitDataEx    Pointer to data optional for extra initializations
+                            of exception.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized.
+  @retval EFI_INVALID_PARAMETER   VectorInfo or InitDataEx contains invalid
+                                  content.
+
+**/
+EFI_STATUS
+EFIAPI
+InitializeCpuExceptionHandlersEx (
+  IN EFI_VECTOR_HANDOFF_INFO            *VectorInfo OPTIONAL,
+  IN CPU_EXCEPTION_INIT_DATA_EX         *InitDataEx OPTIONAL
+  )
+{
+  return InitializeCpuExceptionHandlers (VectorInfo);
+}
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuExceptionHandlerLib.inf b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuExceptionHandlerLib.inf
index d70a99c100..e5c03c16c9 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuExceptionHandlerLib.inf
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SecPeiCpuExceptionHandlerLib.inf
@@ -30,6 +30,7 @@
 [Sources.Ia32]
   Ia32/ExceptionHandlerAsm.asm
   Ia32/ExceptionHandlerAsm.nasm
+  Ia32/ExceptionTssEntryAsm.nasm
   Ia32/ExceptionHandlerAsm.S
   Ia32/ArchExceptionHandler.c
   Ia32/ArchInterruptDefs.h
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmCpuExceptionHandlerLib.inf b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmCpuExceptionHandlerLib.inf
index 634ffcb21d..56b875b7c8 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmCpuExceptionHandlerLib.inf
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmCpuExceptionHandlerLib.inf
@@ -30,6 +30,7 @@
 [Sources.Ia32]
   Ia32/ExceptionHandlerAsm.asm
   Ia32/ExceptionHandlerAsm.nasm
+  Ia32/ExceptionTssEntryAsm.nasm
   Ia32/ExceptionHandlerAsm.S
   Ia32/ArchExceptionHandler.c
   Ia32/ArchInterruptDefs.h
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmException.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmException.c
index 7414d3f773..0bdda6bcd0 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmException.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/SmmException.c
@@ -125,4 +125,36 @@ RegisterCpuInterruptHandler (
   )
 {
   return RegisterCpuInterruptHandlerWorker (InterruptType, InterruptHandler, &mExceptionHandlerData);
-}
\ No newline at end of file
+}
+
+/**
+  Initializes all CPU exceptions entries with optional extra initializations.
+
+  By default, this method should include all functionalities implemented by
+  InitializeCpuExceptionHandlers(), plus extra initialization works, if any.
+  This is could be done by calling InitializeCpuExceptionHandlers() directly
+  in this method besides the extra works.
+
+  InitDataEx is optional and its use and content are processor arch dependent.
+  The typical usage of it is to convey resources which have to be reserved
+  elsewhere and are necessary for the extra initializations of exception.
+
+  @param[in]  VectorInfo    Pointer to reserved vector list.
+  @param[in]  InitDataEx    Pointer to data optional for extra initializations
+                            of exception.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized.
+  @retval EFI_INVALID_PARAMETER   VectorInfo or InitDataEx contains invalid
+                                  content.
+
+**/
+EFI_STATUS
+EFIAPI
+InitializeCpuExceptionHandlersEx (
+  IN EFI_VECTOR_HANDOFF_INFO            *VectorInfo OPTIONAL,
+  IN CPU_EXCEPTION_INIT_DATA_EX         *InitDataEx OPTIONAL
+  )
+{
+  return InitializeCpuExceptionHandlers (VectorInfo);
+}
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchExceptionHandler.c b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchExceptionHandler.c
index 65f0cff680..5bc04656c7 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchExceptionHandler.c
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchExceptionHandler.c
@@ -112,6 +112,140 @@ ArchRestoreExceptionContext (
   SystemContext.SystemContextX64->ExceptionData = ReservedVectors[ExceptionType].ExceptionData;
 }
 
+/**
+  Setup separate stack for given exceptions.
+
+  @param[in] StackSwitchData      Pointer to data required for setuping up
+                                  stack switch.
+
+  @retval EFI_SUCCESS             The exceptions have been successfully
+                                  initialized with new stack.
+  @retval EFI_INVALID_PARAMETER   StackSwitchData contains invalid content.
+
+**/
+EFI_STATUS
+ArchSetupExcpetionStack (
+  IN CPU_EXCEPTION_INIT_DATA_EX         *StackSwitchData
+  )
+{
+  IA32_DESCRIPTOR                   Gdtr;
+  IA32_DESCRIPTOR                   Idtr;
+  IA32_IDT_GATE_DESCRIPTOR          *IdtTable;
+  IA32_TSS_DESCRIPTOR               *TssDesc;
+  IA32_TASK_STATE_SEGMENT           *Tss;
+  UINTN                             StackTop;
+  UINTN                             Index;
+  UINTN                             Vector;
+  UINTN                             TssBase;
+  UINTN                             GdtSize;
+
+  if (StackSwitchData == NULL ||
+      StackSwitchData->Ia32.KnownGoodStackTop == 0 ||
+      StackSwitchData->Ia32.KnownGoodStackSize == 0 ||
+      StackSwitchData->Ia32.StackSwitchExceptions == NULL ||
+      StackSwitchData->Ia32.StackSwitchExceptionNumber == 0 ||
+      StackSwitchData->Ia32.GdtTable == NULL ||
+      StackSwitchData->Ia32.IdtTable == NULL ||
+      StackSwitchData->Ia32.TssDesc == NULL ||
+      StackSwitchData->Ia32.Tss == NULL) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  //
+  // The caller is responsible for that the GDT table, no matter the existing
+  // one or newly allocated, has enough space to hold descriptors for exception
+  // task-state segments.
+  //
+  if (((UINTN)StackSwitchData->Ia32.GdtTable & (IA32_GDT_ALIGNMENT - 1)) != 0) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.TssDesc < (UINTN)(StackSwitchData->Ia32.GdtTable)) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.TssDesc >=
+      ((UINTN)(StackSwitchData->Ia32.GdtTable) + StackSwitchData->Ia32.GdtSize)) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  GdtSize = (UINTN)StackSwitchData->Ia32.TssDesc -
+            (UINTN)(StackSwitchData->Ia32.GdtTable) +
+            sizeof (IA32_TSS_DESCRIPTOR);
+  if (GdtSize > StackSwitchData->Ia32.GdtSize) {
+    return EFI_INVALID_PARAMETER;
+  }
+
+  //
+  // Initialize new GDT table and/or IDT table, if any
+  //
+  AsmReadIdtr (&Idtr);
+  AsmReadGdtr (&Gdtr);
+  if ((UINTN)StackSwitchData->Ia32.GdtTable != Gdtr.Base) {
+    CopyMem (StackSwitchData->Ia32.GdtTable, (VOID *)Gdtr.Base, Gdtr.Limit + 1);
+    Gdtr.Base = (UINTN)StackSwitchData->Ia32.GdtTable;
+    Gdtr.Limit = (UINT16)GdtSize - 1;
+  }
+
+  if ((UINTN)StackSwitchData->Ia32.IdtTable != Idtr.Base) {
+    Idtr.Base = (UINTN)StackSwitchData->Ia32.IdtTable;
+  }
+
+  //
+  // Fixup current task descriptor. Task-state segment for current task will
+  // be filled by processor during task switching.
+  //
+  TssDesc = StackSwitchData->Ia32.TssDesc;
+  Tss     = StackSwitchData->Ia32.Tss;
+
+  TssBase = (UINTN)Tss;
+  TssDesc->Bits.LimitLow   = sizeof(IA32_TASK_STATE_SEGMENT) - 1;
+  TssDesc->Bits.BaseLow    = (UINT16)TssBase;
+  TssDesc->Bits.BaseMidl   = (UINT8)(TssBase >> 16);
+  TssDesc->Bits.Type       = IA32_GDT_TYPE_TSS;
+  TssDesc->Bits.P          = 1;
+  TssDesc->Bits.LimitHigh  = 0;
+  TssDesc->Bits.BaseMidh   = (UINT8)(TssBase >> 24);
+  TssDesc->Bits.BaseHigh   = (UINT32)(TssBase >> 32);
+
+  //
+  // Fixup exception task descriptor and task-state segment
+  //
+  StackTop = StackSwitchData->Ia32.KnownGoodStackTop - CPU_STACK_ALIGNMENT;
+  StackTop = (UINTN)ALIGN_POINTER (StackTop, CPU_STACK_ALIGNMENT);
+  IdtTable = StackSwitchData->Ia32.IdtTable;
+  for (Index = 0; Index < StackSwitchData->Ia32.StackSwitchExceptionNumber; ++Index) {
+    //
+    // Fixup IST
+    //
+    Tss->IST[Index] = StackTop;
+    StackTop -= StackSwitchData->Ia32.KnownGoodStackSize;
+
+    //
+    // Set the IST field to enable corresponding IST
+    //
+    Vector = StackSwitchData->Ia32.StackSwitchExceptions[Index];
+    IdtTable[Vector].Bits.Reserved_0 = (UINT8)(Index + 1);
+  }
+
+  //
+  // Publish GDT
+  //
+  AsmWriteGdtr (&Gdtr);
+
+  //
+  // Load current task
+  //
+  AsmWriteTr ((UINT16)((UINTN)StackSwitchData->Ia32.TssDesc - Gdtr.Base));
+
+  //
+  // Publish IDT
+  //
+  AsmWriteIdtr (&Idtr);
+
+  return EFI_SUCCESS;
+}
+
 /**
   Display CPU information.
 
diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchInterruptDefs.h b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchInterruptDefs.h
index 906480134a..c88be46286 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchInterruptDefs.h
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ArchInterruptDefs.h
@@ -43,4 +43,7 @@ typedef struct {
   UINT8       HookAfterStubHeaderCode[HOOKAFTER_STUB_SIZE];
 } RESERVED_VECTORS_DATA;
 
+#define CPU_TSS_DESC_SIZE sizeof (IA32_TSS_DESCRIPTOR)
+#define CPU_TSS_SIZE      sizeof (IA32_TASK_STATE_SEGMENT)
+
 #endif
-- 
2.14.1.windows.1