IntelFsp2Pkg: FSP_TEMP_RAM_INIT call must follow X64 Calling Convention

REF:https://bugzilla.tianocore.org/show_bug.cgi?id=3926
This API accept one parameter using RCX and this is consumed
in mutiple sub functions.

Cc: Chasel Chiu <chasel.chiu@intel.com>
Cc: Nate DeSimone <nathaniel.l.desimone@intel.com>
Cc: Star Zeng <star.zeng@intel.com>
Cc: Ashraf Ali S <ashraf.ali.s@intel.com>
Signed-off-by: cbduggap <chinni.b.duggapu@intel.com>
Reviewed-by: Chasel Chiu <chasel.chiu@intel.com>

IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm

@@ -114,7 +114,7 @@ endstruc
 global ASM_PFX(LoadMicrocodeDefault)
 ASM_PFX(LoadMicrocodeDefault):
    ; Inputs:
-   ;   rsp -> LoadMicrocodeParams pointer
+   ;   rcx -> LoadMicrocodeParams pointer
    ; Register Usage:
    ;   rsp  Preserved
    ;   All others destroyed
@@ -130,10 +130,9 @@ ASM_PFX(LoadMicrocodeDefault):
 
    cmp    rsp, 0
    jz     ParamError
-   mov    eax, dword [rsp + 8]    ; Parameter pointer
+   cmp    rcx, 0
-   cmp    eax, 0
    jz     ParamError
-   mov    esp, eax
+   mov    rsp, rcx
 
    ; skip loading Microcode if the MicrocodeCodeSize is zero
    ; and report error if size is less than 2k
@@ -144,14 +143,14 @@ ASM_PFX(LoadMicrocodeDefault):
    jne    ParamError
 
    ; UPD structure is compliant with FSP spec 2.4
-   mov    eax, dword [rsp + LoadMicrocodeParamsFsp24.MicrocodeCodeSize]
+   mov    rax, qword [rsp + LoadMicrocodeParamsFsp24.MicrocodeCodeSize]
-   cmp    eax, 0
+   cmp    rax, 0
    jz     Exit2
-   cmp    eax, 0800h
+   cmp    rax, 0800h
    jl     ParamError
 
-   mov    esi, dword [rsp + LoadMicrocodeParamsFsp24.MicrocodeCodeAddr]
+   mov    rsi, qword [rsp + LoadMicrocodeParamsFsp24.MicrocodeCodeAddr]
-   cmp    esi, 0
+   cmp    rsi, 0
    jnz    CheckMainHeader
 
 ParamError:
@@ -256,7 +255,8 @@ CheckAddress:
    ; UPD structure is compliant with FSP spec 2.4
    ; Is automatic size detection ?
    mov   rax, qword [rsp + LoadMicrocodeParamsFsp24.MicrocodeCodeSize]
-   cmp   rax, 0ffffffffffffffffh
+   mov   rcx, 0ffffffffffffffffh
+   cmp   rax, rcx
    jz    LoadMicrocodeDefault4
 
    ; Address >= microcode region address + microcode region size?
@@ -321,8 +321,7 @@ ASM_PFX(EstablishStackFsp):
   ;
   ; Save parameter pointer in rdx
   ;
-  mov       rdx, qword [rsp + 8]
+  mov       rdx, rcx
-
   ;
   ; Enable FSP STACK
   ;
@@ -420,7 +419,10 @@ ASM_PFX(TempRamInitApi):
   ;
   ENABLE_SSE
   ENABLE_AVX
-
+  ;
+  ; Save Input Parameter in YMM10
+  ;
+  SAVE_RCX
   ;
   ; Save RBP, RBX, RSI, RDI and RSP in YMM7, YMM8 and YMM6
   ;
@@ -442,9 +444,8 @@ ASM_PFX(TempRamInitApi):
   ;
   ; Check Parameter
   ;
-  mov       rax, qword [rsp + 8]
+  cmp       rcx, 0
-  cmp       rax, 0
+  mov       rcx, 08000000000000002h
-  mov       rax, 08000000000000002h
   jz        TempRamInitExit
 
   ;
@@ -455,18 +456,18 @@ ASM_PFX(TempRamInitApi):
   jnz       TempRamInitExit
 
   ; Load microcode
-  LOAD_RSP
+  LOAD_RCX
   CALL_YMM  ASM_PFX(LoadMicrocodeDefault)
   SAVE_UCODE_STATUS rax             ; Save microcode return status in SLOT 0 in YMM9 (upper 128bits).
   ; @note If return value rax is not 0, microcode did not load, but continue and attempt to boot.
 
   ; Call Sec CAR Init
-  LOAD_RSP
+  LOAD_RCX
   CALL_YMM  ASM_PFX(SecCarInit)
   cmp       rax, 0
   jnz       TempRamInitExit
 
-  LOAD_RSP
+  LOAD_RCX
   CALL_YMM  ASM_PFX(EstablishStackFsp)
   cmp       rax, 0
   jnz       TempRamInitExit

IntelFsp2Pkg/Include/SaveRestoreSseAvxNasm.inc

@@ -177,6 +177,30 @@
             LXMMN   xmm5, %1, 1
             %endmacro
 
+;
+; Upper half of YMM10 to save/restore RCX
+;
+;
+; Save RCX to YMM10[128:191]
+; Modified: XMM5 and YMM10
+;
+
+%macro SAVE_RCX     0
+            LYMMN   ymm10, xmm5, 1
+            SXMMN   xmm5, 0, rcx
+            SYMMN   ymm10, 1, xmm5
+            %endmacro
+
+;
+; Restore RCX from YMM10[128:191]
+; Modified: XMM5 and RCX
+;
+
+%macro LOAD_RCX     0
+            LYMMN   ymm10, xmm5, 1
+            movq    rcx,  xmm5
+            %endmacro
+
 ;
 ; YMM7[128:191] for calling stack
 ; arg 1:Entry
@@ -231,6 +255,7 @@ NextAddress:
             ; Use CpuId instruction (CPUID.01H:EDX.SSE[bit 25] = 1) to test
             ; whether the processor supports SSE instruction.
             ;
+            mov     r10, rcx
             mov     rax, 1
             cpuid
             bt      rdx, 25
@@ -241,6 +266,7 @@ NextAddress:
             ;
             bt      ecx, 19
             jnc     SseError
+            mov     rcx,  r10
 
             ;
             ; Set OSFXSR bit (bit #9) & OSXMMEXCPT bit (bit #10)
@@ -258,6 +284,7 @@ NextAddress:
             %endmacro
 
 %macro ENABLE_AVX   0
+            mov     r10, rcx
             mov     eax, 1
             cpuid
             and     ecx, 10000000h
@@ -280,5 +307,6 @@ EnableAvx:
             xgetbv                 ; result in edx:eax
             or      eax, 00000006h ; Set XCR0 bit #1 and bit #2 to enable SSE state and AVX state
             xsetbv
+            mov     rcx, r10
             %endmacro