[PATCH v4 4/4] MdeModulePkg/EbcDxe AARCH64: simplify interpreter entry point thunks

[Ard Biesheuvel <ard.biesheuvel@linaro.org>]

The prototypes of EbcInterpret() and ExecuteEbcImageEntryPoint() are
private to the AARCH64 implementation of EbcDxe, so we can shuffle
the arguments around a bit and make the assembler thunking glue a lot
simpler.

For ExecuteEbcImageEntryPoint(), this involves passing the EntryPoint
argument as the third parameter, rather than the first, which allows
us to do a tail call. For EbcInterpret(), instead of copying each
argument beyond #8 from one native stack frame to the next (before
another copy is made into the VM stack), pass a pointer to the
argument stack.

Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org>
---
 MdeModulePkg/Universal/EbcDxe/AArch64/EbcLowLevel.S | 59 +++++--------------
 MdeModulePkg/Universal/EbcDxe/AArch64/EbcSupport.c  | 60 ++++++++------------
 2 files changed, 36 insertions(+), 83 deletions(-)

diff --git a/MdeModulePkg/Universal/EbcDxe/AArch64/EbcLowLevel.S b/MdeModulePkg/Universal/EbcDxe/AArch64/EbcLowLevel.S
index 34794c06a644..b1f09725ecf0 100644
--- a/MdeModulePkg/Universal/EbcDxe/AArch64/EbcLowLevel.S
+++ b/MdeModulePkg/Universal/EbcDxe/AArch64/EbcLowLevel.S
@@ -110,50 +110,23 @@ ASM_PFX(EbcLLCALLEXNative):
 //
 // This function is called by the thunk code to handle an Native to EBC call
 // This can handle up to 16 arguments (1-8 on in x0-x7, 9-16 are on the stack)
-// x16 contains the Entry point that will be the first argument when
+// x16 contains the Entry point that will be the first stacked argument when
 // EBCInterpret is called.
 //
 //****************************************************************************
 ASM_PFX(EbcLLEbcInterpret):
-    stp  x29, x30, [sp, #-16]!
-
-    // copy the current arguments 9-16 from old location and add arg 7 to stack
-    // keeping 16 byte stack alignment
-    sub sp, sp, #80
-    str x7, [sp]
-    ldr x11, [sp, #96]
-    str x11, [sp, #8]
-    ldr x11, [sp, #104]
-    str x11, [sp, #16]
-    ldr x11, [sp, #112]
-    str x11, [sp, #24]
-    ldr x11, [sp, #120]
-    str x11, [sp, #32]
-    ldr x11, [sp, #128]
-    str x11, [sp, #40]
-    ldr x11, [sp, #136]
-    str x11, [sp, #48]
-    ldr x11, [sp, #144]
-    str x11, [sp, #56]
-    ldr x11, [sp, #152]
-    str x11, [sp, #64]
-
-    // Shift arguments and add entry point and as argument 1
-    mov x7, x6
-    mov x6, x5
-    mov x5, x4
-    mov x4, x3
-    mov x3, x2
-    mov x2, x1
-    mov x1, x0
-    mov x0, x16
+    stp     x29, x30, [sp, #-16]!
+    mov     x29, sp
 
-    // call C-code
-    bl ASM_PFX(EbcInterpret)
-    add sp, sp, #80
+    // push the entry point and the address of args #9 - #16 onto the stack
+    add     x17, sp, #16
+    stp     x16, x17, [sp, #-16]!
 
-    ldp  x29, x30, [sp], #16
+    // call C-code
+    bl      ASM_PFX(EbcInterpret)
 
+    add     sp, sp, #16
+    ldp     x29, x30, [sp], #16
     ret
 
 //****************************************************************************
@@ -165,16 +138,10 @@ ASM_PFX(EbcLLEbcInterpret):
 //
 //****************************************************************************
 ASM_PFX(EbcLLExecuteEbcImageEntryPoint):
-    stp  x29, x30, [sp, #-16]!
-    // build new parameter calling convention
-    mov  x2, x1
-    mov  x1, x0
-    mov  x0, x16
+    mov     x2, x16
 
-    // call C-code
-    bl ASM_PFX(ExecuteEbcImageEntryPoint)
-    ldp  x29, x30, [sp], #16
-    ret
+    // tail call to C code
+    b       ASM_PFX(ExecuteEbcImageEntryPoint)
 
 //****************************************************************************
 // mEbcInstructionBufferTemplate
diff --git a/MdeModulePkg/Universal/EbcDxe/AArch64/EbcSupport.c b/MdeModulePkg/Universal/EbcDxe/AArch64/EbcSupport.c
index a5f21f400274..c5cc76d7bdcb 100644
--- a/MdeModulePkg/Universal/EbcDxe/AArch64/EbcSupport.c
+++ b/MdeModulePkg/Universal/EbcDxe/AArch64/EbcSupport.c
@@ -89,7 +89,6 @@ PushU64 (
 
   This is a thunk function.
 
-  @param  EntryPoint            The entrypoint of EBC code.
   @param  Arg1                  The 1st argument.
   @param  Arg2                  The 2nd argument.
   @param  Arg3                  The 3rd argument.
@@ -98,14 +97,8 @@ PushU64 (
   @param  Arg6                  The 6th argument.
   @param  Arg7                  The 7th argument.
   @param  Arg8                  The 8th argument.
-  @param  Arg9                  The 9th argument.
-  @param  Arg10                 The 10th argument.
-  @param  Arg11                 The 11th argument.
-  @param  Arg12                 The 12th argument.
-  @param  Arg13                 The 13th argument.
-  @param  Arg14                 The 14th argument.
-  @param  Arg15                 The 15th argument.
-  @param  Arg16                 The 16th argument.
+  @param  EntryPoint            The entrypoint of EBC code.
+  @param  Args9_16[]            Array containing arguments #9 to #16.
 
   @return The value returned by the EBC application we're going to run.
 
@@ -113,23 +106,16 @@ PushU64 (
 UINT64
 EFIAPI
 EbcInterpret (
-  IN UINTN      EntryPoint,
-  IN UINTN      Arg1,
-  IN UINTN      Arg2,
-  IN UINTN      Arg3,
-  IN UINTN      Arg4,
-  IN UINTN      Arg5,
-  IN UINTN      Arg6,
-  IN UINTN      Arg7,
-  IN UINTN      Arg8,
-  IN UINTN      Arg9,
-  IN UINTN      Arg10,
-  IN UINTN      Arg11,
-  IN UINTN      Arg12,
-  IN UINTN      Arg13,
-  IN UINTN      Arg14,
-  IN UINTN      Arg15,
-  IN UINTN      Arg16
+  IN UINTN        Arg1,
+  IN UINTN        Arg2,
+  IN UINTN        Arg3,
+  IN UINTN        Arg4,
+  IN UINTN        Arg5,
+  IN UINTN        Arg6,
+  IN UINTN        Arg7,
+  IN UINTN        Arg8,
+  IN UINTN        EntryPoint,
+  IN CONST UINTN  Args9_16[]
   )
 {
   //
@@ -193,14 +179,14 @@ EbcInterpret (
   // For the worst case, assume there are 4 arguments passed in registers, store
   // them to VM's stack.
   //
-  PushU64 (&VmContext, (UINT64) Arg16);
-  PushU64 (&VmContext, (UINT64) Arg15);
-  PushU64 (&VmContext, (UINT64) Arg14);
-  PushU64 (&VmContext, (UINT64) Arg13);
-  PushU64 (&VmContext, (UINT64) Arg12);
-  PushU64 (&VmContext, (UINT64) Arg11);
-  PushU64 (&VmContext, (UINT64) Arg10);
-  PushU64 (&VmContext, (UINT64) Arg9);
+  PushU64 (&VmContext, (UINT64) Args9_16[7]);
+  PushU64 (&VmContext, (UINT64) Args9_16[6]);
+  PushU64 (&VmContext, (UINT64) Args9_16[5]);
+  PushU64 (&VmContext, (UINT64) Args9_16[4]);
+  PushU64 (&VmContext, (UINT64) Args9_16[3]);
+  PushU64 (&VmContext, (UINT64) Args9_16[2]);
+  PushU64 (&VmContext, (UINT64) Args9_16[1]);
+  PushU64 (&VmContext, (UINT64) Args9_16[0]);
   PushU64 (&VmContext, (UINT64) Arg8);
   PushU64 (&VmContext, (UINT64) Arg7);
   PushU64 (&VmContext, (UINT64) Arg6);
@@ -252,10 +238,10 @@ EbcInterpret (
 /**
   Begin executing an EBC image.
 
-  @param  EntryPoint       The entrypoint of EBC code.
   @param  ImageHandle      image handle for the EBC application we're executing
   @param  SystemTable      standard system table passed into an driver's entry
                            point
+  @param  EntryPoint       The entrypoint of EBC code.
 
   @return The value returned by the EBC application we're going to run.
 
@@ -263,9 +249,9 @@ EbcInterpret (
 UINT64
 EFIAPI
 ExecuteEbcImageEntryPoint (
-  IN UINTN                EntryPoint,
   IN EFI_HANDLE           ImageHandle,
-  IN EFI_SYSTEM_TABLE     *SystemTable
+  IN EFI_SYSTEM_TABLE     *SystemTable,
+  IN UINTN                EntryPoint
   )
 {
   //
-- 
2.7.4