[PATCH] FSP_TEMP_RAM_INIT API call must follow X64 Calling Convention

[PATCH] FSP_TEMP_RAM_INIT API call must follow X64 Calling Convention

[cbduggap]

This API accept one parameter using RCX and this is consumed
in mutiple sub functions.
Signed-off-by: cbduggap <chinni.b.duggapu@intel.com>
---
 IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm | 23 +++---
 .../Include/SaveRestoreSseAvxNasm.inc         | 82 +++++++++++++++++++
 2 files changed, 95 insertions(+), 10 deletions(-)

diff --git a/IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm b/IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm
index a9f5f28ed7..4add0ef3fd 100644
--- a/IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm
+++ b/IntelFsp2Pkg/FspSecCore/X64/FspApiEntryT.nasm
@@ -130,10 +130,9 @@ ASM_PFX(LoadMicrocodeDefault):
 
    cmp    rsp, 0
    jz     ParamError
-   mov    eax, dword [rsp + 8]    ; Parameter pointer
-   cmp    eax, 0
+   cmp    ecx, 0
    jz     ParamError
-   mov    esp, eax
+   mov    esp, ecx
 
    ; skip loading Microcode if the MicrocodeCodeSize is zero
    ; and report error if size is less than 2k
@@ -321,8 +320,7 @@ ASM_PFX(EstablishStackFsp):
   ;
   ; Save parameter pointer in rdx
   ;
-  mov       rdx, qword [rsp + 8]
-
+  mov       rdx, rcx
   ;
   ; Enable FSP STACK
   ;
@@ -418,9 +416,12 @@ ASM_PFX(TempRamInitApi):
   ;
   ; Ensure both SSE and AVX are enabled
   ;
-  ENABLE_SSE
+  ENABLE_SSE_X64
   ENABLE_AVX
-
+  ;
+  ; Save Input Parameter in YMM10
+  ;
+  SAVE_RCX
   ;
   ; Save RBP, RBX, RSI, RDI and RSP in YMM7, YMM8 and YMM6
   ;
@@ -442,9 +443,8 @@ ASM_PFX(TempRamInitApi):
   ;
   ; Check Parameter
   ;
-  mov       rax, qword [rsp + 8]
-  cmp       rax, 0
-  mov       rax, 08000000000000002h
+  cmp       rcx, 0
+  mov       rcx, 08000000000000002h
   jz        TempRamInitExit
 
   ;
@@ -456,17 +456,20 @@ ASM_PFX(TempRamInitApi):
 
   ; 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
diff --git a/IntelFsp2Pkg/Include/SaveRestoreSseAvxNasm.inc b/IntelFsp2Pkg/Include/SaveRestoreSseAvxNasm.inc
index e8bd91669d..fb6df2a18b 100644
--- a/IntelFsp2Pkg/Include/SaveRestoreSseAvxNasm.inc
+++ b/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
@@ -258,6 +282,7 @@ NextAddress:
             %endmacro
 
 %macro ENABLE_AVX   0
+            mov     r10, rcx
             mov     eax, 1
             cpuid
             and     ecx, 10000000h
@@ -280,5 +305,62 @@ 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
 
+%macro ENABLE_SSE_X64   0
+            ;
+            ; Initialize floating point units
+            ;
+            jmp     NextAddress
+align 4
+            ;
+            ; Float control word initial value:
+            ; all exceptions masked, double-precision, round-to-nearest
+            ;
+FpuControlWord       DW      027Fh
+            ;
+            ; Multimedia-extensions control word:
+            ; all exceptions masked, round-to-nearest, flush to zero for masked underflow
+            ;
+MmxControlWord       DQ      01F80h
+SseError:
+            ;
+            ; Processor has to support SSE
+            ;
+            jmp     SseError
+NextAddress:
+            finit
+            mov rax, FpuControlWord
+            fldcw [rax]
+
+            ;
+            ; 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
+            jnc     SseError
+
+            ;
+            ; SSE 4.1 support
+            ;
+            bt      ecx, 19
+            jnc     SseError
+            mov     rcx,  r10
+            ;
+            ; Set OSFXSR bit (bit #9) & OSXMMEXCPT bit (bit #10)
+            ;
+            mov     rax, cr4
+            or      rax, 00000600h
+            mov     cr4, rax
+
+            ;
+            ; The processor should support SSE instruction and we can use
+            ; ldmxcsr instruction
+            ;
+            mov  rax, MmxControlWord
+            ldmxcsr [rax]
+            %endmacro
\ No newline at end of file
-- 
2.36.0.windows.1