UefiCpuPkg/MpInitLib: Add AsmRelocateApLoop() assembly code

AsmRelocateApLoop() is used to place APs into MWAIT-loop if MonitorMwait
feature is supported before hand-off to OS, or place APs into HLT-loop if
MonitorMwait feature is not supported.

If the current mode is long mode, we will switch APs to protected mode
before placing APs in MWAIT-loop or HLT-loop. Thus, once APs wakeup from
loop, APs needn't the page table that may be crashed by OS.

v3:
  1. Rename AsmRellocateApLoop to AsmRelocateApLoop.
  2. Fix typo Proteced to Protected.
  3. Fix typo segement to segment
  4. Use word MONITOR instead of mwait-monitor.

Cc: Michael Kinney <michael.d.kinney@intel.com>
Cc: Feng Tian <feng.tian@intel.com>
Cc: Giri P Mudusuru <giri.p.mudusuru@intel.com>
Cc: Laszlo Ersek <lersek@redhat.com>
Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Jeff Fan <jeff.fan@intel.com>
Reviewed-by: Giri P Mudusuru <giri.p.mudusuru@intel.com>
Reviewed-by: Michael Kinney <michael.d.kinney@intel.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Tested-by: Michael Kinney <michael.d.kinney@intel.com>

UefiCpuPkg/Library/MpInitLib/X64/MpFuncs.nasm

@@ -176,6 +176,60 @@ CProcedureInvoke:
 
 RendezvousFunnelProcEnd:
 
+;-------------------------------------------------------------------------------------
+;  AsmRelocateApLoop (MwaitSupport, ApTargetCState, PmCodeSegment);
+;-------------------------------------------------------------------------------------
+global ASM_PFX(AsmRelocateApLoop)
+ASM_PFX(AsmRelocateApLoop):
+AsmRelocateApLoopStart:
+    push       rcx
+    push       rdx
+
+    lea        rsi, [PmEntry]    ; rsi <- The start address of transition code
+
+    push       r8
+    push       rsi
+    DB         0x48
+    retf
+BITS 32
+PmEntry:
+    mov        eax, cr0
+    btr        eax, 31           ; Clear CR0.PG
+    mov        cr0, eax          ; Disable paging and caches
+
+    mov        ebx, edx          ; Save EntryPoint to rbx, for rdmsr will overwrite rdx
+    mov        ecx, 0xc0000080
+    rdmsr
+    and        ah, ~ 1           ; Clear LME
+    wrmsr
+    mov        eax, cr4
+    and        al, ~ (1 << 5)    ; Clear PAE
+    mov        cr4, eax
+
+    pop        edx
+    add        esp, 4
+    pop        ecx,
+    add        esp, 4
+    cmp        cl, 1              ; Check mwait-monitor support
+    jnz        HltLoop
+    mov        ebx, edx           ; Save C-State to ebx
+MwaitLoop:
+    mov        eax, esp           ; Set Monitor Address
+    xor        ecx, ecx           ; ecx = 0
+    xor        edx, edx           ; edx = 0
+    monitor
+    shl        ebx, 4
+    mov        eax, ebx           ; Mwait Cx, Target C-State per eax[7:4]
+    mwait
+    jmp        MwaitLoop
+HltLoop:
+    cli
+    hlt
+    jmp        HltLoop
+    ret
+BITS 64
+AsmRelocateApLoopEnd:
+
 ;-------------------------------------------------------------------------------------
 ;  AsmGetAddressMap (&AddressMap);
 ;-------------------------------------------------------------------------------------