ffi 1.0.11 → 1.0.12.pre

data/ext/ffi_c/libffi/src/x86/ffi64.c

@@ -1,7 +1,8 @@
 /* -----------------------------------------------------------------------
-   ffi64.c - Copyright (c) 2002, 2007  Bo Thorsen <bo@suse.de>
-             Copyright (c) 2008  Red Hat, Inc.
-   
+   ffi64.c - Copyright (c) 20011  Anthony Green
+             Copyright (c) 2008, 2010  Red Hat, Inc.
+             Copyright (c) 2002, 2007  Bo Thorsen <bo@suse.de>
+             
    x86-64 Foreign Function Interface 
 
    Permission is hereby granted, free of charge, to any person obtaining
@@ -50,9 +51,10 @@ extern void ffi_call_unix64 (void *args, unsigned long bytes, unsigned flags,
    gcc/config/i386/i386.c. Do *not* change one without the other.  */
 
 /* Register class used for passing given 64bit part of the argument.
-   These represent classes as documented by the PS ABI, with the exception
-   of SSESF, SSEDF classes, that are basically SSE class, just gcc will
-   use SF or DFmode move instead of DImode to avoid reformating penalties.
+   These represent classes as documented by the PS ABI, with the
+   exception of SSESF, SSEDF classes, that are basically SSE class,
+   just gcc will use SF or DFmode move instead of DImode to avoid
+   reformatting penalties.
 
    Similary we play games with INTEGERSI_CLASS to use cheaper SImode moves
    whenever possible (upper half does contain padding).  */
@@ -377,7 +379,7 @@ ffi_prep_cif_machdep (ffi_cif *cif)
 	  if (align < 8)
 	    align = 8;
 
-	  bytes = ALIGN(bytes, align);
+	  bytes = ALIGN (bytes, align);
 	  bytes += cif->arg_types[i]->size;
 	}
       else
@@ -389,7 +391,7 @@ ffi_prep_cif_machdep (ffi_cif *cif)
   if (ssecount)
     flags |= 1 << 11;
   cif->flags = flags;
-  cif->bytes = bytes;
+  cif->bytes = ALIGN (bytes, 8);
 
   return FFI_OK;
 }
@@ -497,6 +499,13 @@ ffi_prep_closure_loc (ffi_closure* closure,
 {
   volatile unsigned short *tramp;
 
+  /* Sanity check on the cif ABI.  */
+  {
+    int abi = cif->abi;
+    if (UNLIKELY (! (abi > FFI_FIRST_ABI && abi < FFI_LAST_ABI)))
+      return FFI_BAD_ABI;
+  }
+
   tramp = (volatile unsigned short *) &closure->tramp[0];
 
   tramp[0] = 0xbb49;		/* mov <code>, %r11	*/

data/ext/ffi_c/libffi/src/x86/ffitarget.h

@@ -1,5 +1,5 @@
 /* -----------------------------------------------------------------*-C-*-
-   ffitarget.h - Copyright (c) 1996-2003  Red Hat, Inc.
+   ffitarget.h - Copyright (c) 1996-2003, 2010  Red Hat, Inc.
    Copyright (C) 2008  Free Software Foundation, Inc.
 
    Target configuration macros for x86 and x86-64.
@@ -31,6 +31,9 @@
 
 /* ---- System specific configurations ----------------------------------- */
 
+/* For code common to all platforms on x86 and x86_64. */
+#define X86_ANY
+
 #if defined (X86_64) && defined (__i386__)
 #undef X86_64
 #define X86
@@ -38,7 +41,7 @@
 
 #ifdef X86_WIN64
 #define FFI_SIZEOF_ARG 8
-#define USE_BUILTIN_FFS 0 // not yet implemented in mingw-64 
+#define USE_BUILTIN_FFS 0 /* not yet implemented in mingw-64 */
 #endif
 
 /* ---- Generic type definitions ----------------------------------------- */
@@ -64,28 +67,26 @@ typedef enum ffi_abi {
 #ifdef X86_WIN32
   FFI_SYSV,
   FFI_STDCALL,
+  FFI_LAST_ABI,
   /* TODO: Add fastcall support for the sake of completeness */
-  FFI_DEFAULT_ABI = FFI_SYSV,
-#endif
+  FFI_DEFAULT_ABI = FFI_SYSV
 
-#ifdef X86_WIN64
+#elif defined(X86_WIN64)
   FFI_WIN64,
-  FFI_DEFAULT_ABI = FFI_WIN64,
-#else
+  FFI_LAST_ABI,
+  FFI_DEFAULT_ABI = FFI_WIN64
 
+#else
   /* ---- Intel x86 and AMD x86-64 - */
-#if !defined(X86_WIN32) && (defined(__i386__) || defined(__x86_64__))
   FFI_SYSV,
   FFI_UNIX64,   /* Unix variants all use the same ABI for x86-64  */
-#ifdef __i386__
-  FFI_DEFAULT_ABI = FFI_SYSV,
+  FFI_LAST_ABI,
+#if defined(__i386__) || defined(__i386)
+  FFI_DEFAULT_ABI = FFI_SYSV
 #else
-  FFI_DEFAULT_ABI = FFI_UNIX64,
+  FFI_DEFAULT_ABI = FFI_UNIX64
 #endif
 #endif
-#endif /* X86_WIN64 */
-
-  FFI_LAST_ABI = FFI_DEFAULT_ABI + 1
 } ffi_abi;
 #endif
 

data/ext/ffi_c/libffi/src/x86/sysv.S

@@ -1,5 +1,5 @@
 /* -----------------------------------------------------------------------
-   sysv.S - Copyright (c) 1996, 1998, 2001-2003, 2005, 2008  Red Hat, Inc.
+   sysv.S - Copyright (c) 1996, 1998, 2001-2003, 2005, 2008, 2010  Red Hat, Inc.
    
    X86 Foreign Function Interface 
 
@@ -48,6 +48,9 @@ ffi_call_SYSV:
 	movl  16(%ebp),%ecx
 	subl  %ecx,%esp
 
+        /* Align the stack pointer to 16-bytes */
+        andl  $0xfffffff0, %esp
+
 	movl  %esp,%eax
 
 	/* Place all of the ffi_prep_args in position  */
@@ -325,23 +328,52 @@ ffi_closure_raw_SYSV:
 	.size	ffi_closure_raw_SYSV, .-ffi_closure_raw_SYSV
 #endif
 
+#if defined __PIC__
+# if defined __sun__ && defined __svr4__
+/* 32-bit Solaris 2/x86 uses datarel encoding for PIC.  GNU ld before 2.22
+   doesn't correctly sort .eh_frame_hdr with mixed encodings, so match this.  */
+#  define FDE_ENCODING		0x30	/* datarel */
+#  define FDE_ENCODE(X)		X@GOTOFF
+# else
+#  define FDE_ENCODING		0x1b	/* pcrel sdata4 */
+#  if defined HAVE_AS_X86_PCREL
+#   define FDE_ENCODE(X)	X-.
+#  else
+#   define FDE_ENCODE(X)	X@rel
+#  endif
+# endif
+#else
+# define FDE_ENCODING		0	/* absolute */
+# define FDE_ENCODE(X)		X
+#endif
+
 	.section	.eh_frame,EH_FRAME_FLAGS,@progbits
 .Lframe1:
 	.long	.LECIE1-.LSCIE1	/* Length of Common Information Entry */
 .LSCIE1:
 	.long	0x0	/* CIE Identifier Tag */
 	.byte	0x1	/* CIE Version */
+#ifdef HAVE_AS_ASCII_PSEUDO_OP
 #ifdef __PIC__
 	.ascii "zR\0"	/* CIE Augmentation */
 #else
 	.ascii "\0"	/* CIE Augmentation */
+#endif
+#elif defined HAVE_AS_STRING_PSEUDO_OP
+#ifdef __PIC__
+	.string "zR"	/* CIE Augmentation */
+#else
+	.string ""	/* CIE Augmentation */
+#endif
+#else
+#error missing .ascii/.string
 #endif
 	.byte	0x1	/* .uleb128 0x1; CIE Code Alignment Factor */
 	.byte	0x7c	/* .sleb128 -4; CIE Data Alignment Factor */
 	.byte	0x8	/* CIE RA Column */
 #ifdef __PIC__
 	.byte	0x1	/* .uleb128 0x1; Augmentation size */
-	.byte	0x1b	/* FDE Encoding (pcrel sdata4) */
+	.byte	FDE_ENCODING
 #endif
 	.byte	0xc	/* DW_CFA_def_cfa */
 	.byte	0x4	/* .uleb128 0x4 */
@@ -354,14 +386,8 @@ ffi_closure_raw_SYSV:
 	.long	.LEFDE1-.LASFDE1	/* FDE Length */
 .LASFDE1:
 	.long	.LASFDE1-.Lframe1	/* FDE CIE offset */
-#if defined __PIC__ && defined HAVE_AS_X86_PCREL
-	.long	.LFB1-.	/* FDE initial location */
-#elif defined __PIC__
-	.long	.LFB1@rel
-#else
-	.long	.LFB1
-#endif
-	.long	.LFE1-.LFB1	/* FDE address range */
+	.long	FDE_ENCODE(.LFB1)	/* FDE initial location */
+	.long	.LFE1-.LFB1		/* FDE address range */
 #ifdef __PIC__
 	.byte	0x0	/* .uleb128 0x0; Augmentation size */
 #endif
@@ -381,14 +407,8 @@ ffi_closure_raw_SYSV:
 	.long	.LEFDE2-.LASFDE2	/* FDE Length */
 .LASFDE2:
 	.long	.LASFDE2-.Lframe1	/* FDE CIE offset */
-#if defined __PIC__ && defined HAVE_AS_X86_PCREL
-	.long	.LFB2-.	/* FDE initial location */
-#elif defined __PIC__
-	.long	.LFB2@rel
-#else
-	.long	.LFB2
-#endif
-	.long	.LFE2-.LFB2	/* FDE address range */
+	.long	FDE_ENCODE(.LFB2)	/* FDE initial location */
+	.long	.LFE2-.LFB2		/* FDE address range */
 #ifdef __PIC__
 	.byte	0x0	/* .uleb128 0x0; Augmentation size */
 #endif
@@ -417,14 +437,8 @@ ffi_closure_raw_SYSV:
 	.long	.LEFDE3-.LASFDE3	/* FDE Length */
 .LASFDE3:
 	.long	.LASFDE3-.Lframe1	/* FDE CIE offset */
-#if defined __PIC__ && defined HAVE_AS_X86_PCREL
-	.long	.LFB3-.	/* FDE initial location */
-#elif defined __PIC__
-	.long	.LFB3@rel
-#else
-	.long	.LFB3
-#endif
-	.long	.LFE3-.LFB3	/* FDE address range */
+	.long	FDE_ENCODE(.LFB3)	/* FDE initial location */
+	.long	.LFE3-.LFB3		/* FDE address range */
 #ifdef __PIC__
 	.byte	0x0	/* .uleb128 0x0; Augmentation size */
 #endif

data/ext/ffi_c/libffi/src/x86/unix64.S

@@ -324,7 +324,11 @@ ffi_closure_unix64:
 .LUW9:
 	.size	ffi_closure_unix64,.-ffi_closure_unix64
 
+#ifdef HAVE_AS_X86_64_UNWIND_SECTION_TYPE
+	.section	.eh_frame,"a",@unwind
+#else
 	.section	.eh_frame,"a",@progbits
+#endif
 .Lframe1:
 	.long	.LECIE1-.LSCIE1		/* CIE Length */
 .LSCIE1:

data/ext/ffi_c/libffi/src/x86/win32.S

@@ -2,6 +2,7 @@
    win32.S - Copyright (c) 1996, 1998, 2001, 2002, 2009  Red Hat, Inc.
 	     Copyright (c) 2001  John Beniton
 	     Copyright (c) 2002  Ranjit Mathew
+	     Copyright (c) 2009  Daniel Witte
 			
  
    X86 Foreign Function Interface
@@ -31,14 +32,373 @@
 #define LIBFFI_ASM
 #include <fficonfig.h>
 #include <ffi.h>
- 
+
+#ifdef _MSC_VER
+
+.386
+.MODEL FLAT, C
+
+EXTRN ffi_closure_SYSV_inner:NEAR
+
+_TEXT SEGMENT
+
+ffi_call_win32 PROC NEAR,
+    ffi_prep_args : NEAR PTR DWORD,
+    ecif          : NEAR PTR DWORD,
+    cif_bytes     : DWORD,
+    cif_flags     : DWORD,
+    rvalue        : NEAR PTR DWORD,
+    fn            : NEAR PTR DWORD
+
+        ;; Make room for all of the new args.
+        mov  ecx, cif_bytes
+        sub  esp, ecx
+
+        mov  eax, esp
+
+        ;; Place all of the ffi_prep_args in position
+        push ecif
+        push eax
+        call ffi_prep_args
+
+        ;; Return stack to previous state and call the function
+        add  esp, 8
+
+        call fn
+
+        ;; cdecl:   we restore esp in the epilogue, so there's no need to
+        ;;          remove the space we pushed for the args.
+        ;; stdcall: the callee has already cleaned the stack.
+
+        ;; Load ecx with the return type code
+        mov  ecx, cif_flags
+
+        ;; If the return value pointer is NULL, assume no return value.
+        cmp  rvalue, 0
+        jne  ca_jumptable
+
+        ;; Even if there is no space for the return value, we are
+        ;; obliged to handle floating-point values.
+        cmp  ecx, FFI_TYPE_FLOAT
+        jne  ca_epilogue
+        fstp st(0)
+
+        jmp  ca_epilogue
+
+ca_jumptable:
+        jmp  [ca_jumpdata + 4 * ecx]
+ca_jumpdata:
+        ;; Do not insert anything here between label and jump table.
+        dd offset ca_epilogue       ;; FFI_TYPE_VOID
+        dd offset ca_retint         ;; FFI_TYPE_INT
+        dd offset ca_retfloat       ;; FFI_TYPE_FLOAT
+        dd offset ca_retdouble      ;; FFI_TYPE_DOUBLE
+        dd offset ca_retlongdouble  ;; FFI_TYPE_LONGDOUBLE
+        dd offset ca_retint8        ;; FFI_TYPE_UINT8
+        dd offset ca_retint8        ;; FFI_TYPE_SINT8
+        dd offset ca_retint16       ;; FFI_TYPE_UINT16
+        dd offset ca_retint16       ;; FFI_TYPE_SINT16
+        dd offset ca_retint         ;; FFI_TYPE_UINT32
+        dd offset ca_retint         ;; FFI_TYPE_SINT32
+        dd offset ca_retint64       ;; FFI_TYPE_UINT64
+        dd offset ca_retint64       ;; FFI_TYPE_SINT64
+        dd offset ca_epilogue       ;; FFI_TYPE_STRUCT
+        dd offset ca_retint         ;; FFI_TYPE_POINTER
+        dd offset ca_retint8        ;; FFI_TYPE_SMALL_STRUCT_1B
+        dd offset ca_retint16       ;; FFI_TYPE_SMALL_STRUCT_2B
+        dd offset ca_retint         ;; FFI_TYPE_SMALL_STRUCT_4B
+
+ca_retint8:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        mov   [ecx + 0], al
+        jmp   ca_epilogue
+
+ca_retint16:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        mov   [ecx + 0], ax
+        jmp   ca_epilogue
+
+ca_retint:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        mov   [ecx + 0], eax
+        jmp   ca_epilogue
+
+ca_retint64:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        mov   [ecx + 0], eax
+        mov   [ecx + 4], edx
+        jmp   ca_epilogue
+
+ca_retfloat:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        fstp  DWORD PTR [ecx]
+        jmp   ca_epilogue
+
+ca_retdouble:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        fstp  QWORD PTR [ecx]
+        jmp   ca_epilogue
+
+ca_retlongdouble:
+        ;; Load %ecx with the pointer to storage for the return value
+        mov   ecx, rvalue
+        fstp  TBYTE PTR [ecx]
+        jmp   ca_epilogue
+
+ca_epilogue:
+        ;; Epilogue code is autogenerated.
+        ret
+ffi_call_win32 ENDP
+
+ffi_closure_SYSV PROC NEAR FORCEFRAME
+    ;; the ffi_closure ctx is passed in eax by the trampoline.
+
+        sub  esp, 40
+        lea  edx, [ebp - 24]
+        mov  [ebp - 12], edx         ;; resp
+        lea  edx, [ebp + 8]
+        mov  [esp + 8], edx          ;; args
+        lea  edx, [ebp - 12]
+        mov  [esp + 4], edx          ;; &resp
+        mov  [esp], eax              ;; closure
+        call ffi_closure_SYSV_inner
+        mov  ecx, [ebp - 12]
+
+cs_jumptable:
+        jmp  [cs_jumpdata + 4 * eax]
+cs_jumpdata:
+        ;; Do not insert anything here between the label and jump table.
+        dd offset cs_epilogue       ;; FFI_TYPE_VOID
+        dd offset cs_retint         ;; FFI_TYPE_INT
+        dd offset cs_retfloat       ;; FFI_TYPE_FLOAT
+        dd offset cs_retdouble      ;; FFI_TYPE_DOUBLE
+        dd offset cs_retlongdouble  ;; FFI_TYPE_LONGDOUBLE
+        dd offset cs_retint8        ;; FFI_TYPE_UINT8
+        dd offset cs_retint8        ;; FFI_TYPE_SINT8
+        dd offset cs_retint16       ;; FFI_TYPE_UINT16
+        dd offset cs_retint16       ;; FFI_TYPE_SINT16
+        dd offset cs_retint         ;; FFI_TYPE_UINT32
+        dd offset cs_retint         ;; FFI_TYPE_SINT32
+        dd offset cs_retint64       ;; FFI_TYPE_UINT64
+        dd offset cs_retint64       ;; FFI_TYPE_SINT64
+        dd offset cs_retstruct      ;; FFI_TYPE_STRUCT
+        dd offset cs_retint         ;; FFI_TYPE_POINTER
+        dd offset cs_retint8        ;; FFI_TYPE_SMALL_STRUCT_1B
+        dd offset cs_retint16       ;; FFI_TYPE_SMALL_STRUCT_2B
+        dd offset cs_retint         ;; FFI_TYPE_SMALL_STRUCT_4B
+
+cs_retint8:
+        mov   al, [ecx]
+        jmp   cs_epilogue
+
+cs_retint16:
+        mov   ax, [ecx]
+        jmp   cs_epilogue
+
+cs_retint:
+        mov   eax, [ecx]
+        jmp   cs_epilogue
+
+cs_retint64:
+        mov   eax, [ecx + 0]
+        mov   edx, [ecx + 4]
+        jmp   cs_epilogue
+
+cs_retfloat:
+        fld   DWORD PTR [ecx]
+        jmp   cs_epilogue
+
+cs_retdouble:
+        fld   QWORD PTR [ecx]
+        jmp   cs_epilogue
+
+cs_retlongdouble:
+        fld   TBYTE PTR [ecx]
+        jmp   cs_epilogue
+
+cs_retstruct:
+        ;; Caller expects us to pop struct return value pointer hidden arg.
+        ;; Epilogue code is autogenerated.
+        ret	4
+
+cs_epilogue:
+        ;; Epilogue code is autogenerated.
+        ret
+ffi_closure_SYSV ENDP
+
+#if !FFI_NO_RAW_API
+
+#define RAW_CLOSURE_CIF_OFFSET ((FFI_TRAMPOLINE_SIZE + 3) AND NOT 3)
+#define RAW_CLOSURE_FUN_OFFSET (RAW_CLOSURE_CIF_OFFSET + 4)
+#define RAW_CLOSURE_USER_DATA_OFFSET (RAW_CLOSURE_FUN_OFFSET + 4)
+#define CIF_FLAGS_OFFSET 20
+
+ffi_closure_raw_SYSV PROC NEAR USES esi
+    ;; the ffi_closure ctx is passed in eax by the trampoline.
+
+        sub  esp, 40
+        mov  esi, [eax + RAW_CLOSURE_CIF_OFFSET]        ;; closure->cif
+        mov  edx, [eax + RAW_CLOSURE_USER_DATA_OFFSET]  ;; closure->user_data
+        mov  [esp + 12], edx                            ;; user_data
+        lea  edx, [ebp + 8]
+        mov  [esp + 8], edx                             ;; raw_args
+        lea  edx, [ebp - 24]
+        mov  [esp + 4], edx                             ;; &res
+        mov  [esp], esi                                 ;; cif
+        call DWORD PTR [eax + RAW_CLOSURE_FUN_OFFSET]   ;; closure->fun
+        mov  eax, [esi + CIF_FLAGS_OFFSET]              ;; cif->flags
+        lea  ecx, [ebp - 24]
+
+cr_jumptable:
+        jmp  [cr_jumpdata + 4 * eax]
+cr_jumpdata:
+        ;; Do not insert anything here between the label and jump table.
+        dd offset cr_epilogue       ;; FFI_TYPE_VOID
+        dd offset cr_retint         ;; FFI_TYPE_INT
+        dd offset cr_retfloat       ;; FFI_TYPE_FLOAT
+        dd offset cr_retdouble      ;; FFI_TYPE_DOUBLE
+        dd offset cr_retlongdouble  ;; FFI_TYPE_LONGDOUBLE
+        dd offset cr_retint8        ;; FFI_TYPE_UINT8
+        dd offset cr_retint8        ;; FFI_TYPE_SINT8
+        dd offset cr_retint16       ;; FFI_TYPE_UINT16
+        dd offset cr_retint16       ;; FFI_TYPE_SINT16
+        dd offset cr_retint         ;; FFI_TYPE_UINT32
+        dd offset cr_retint         ;; FFI_TYPE_SINT32
+        dd offset cr_retint64       ;; FFI_TYPE_UINT64
+        dd offset cr_retint64       ;; FFI_TYPE_SINT64
+        dd offset cr_epilogue       ;; FFI_TYPE_STRUCT
+        dd offset cr_retint         ;; FFI_TYPE_POINTER
+        dd offset cr_retint8        ;; FFI_TYPE_SMALL_STRUCT_1B
+        dd offset cr_retint16       ;; FFI_TYPE_SMALL_STRUCT_2B
+        dd offset cr_retint         ;; FFI_TYPE_SMALL_STRUCT_4B
+
+cr_retint8:
+        mov   al, [ecx]
+        jmp   cr_epilogue
+
+cr_retint16:
+        mov   ax, [ecx]
+        jmp   cr_epilogue
+
+cr_retint:
+        mov   eax, [ecx]
+        jmp   cr_epilogue
+
+cr_retint64:
+        mov   eax, [ecx + 0]
+        mov   edx, [ecx + 4]
+        jmp   cr_epilogue
+
+cr_retfloat:
+        fld   DWORD PTR [ecx]
+        jmp   cr_epilogue
+
+cr_retdouble:
+        fld   QWORD PTR [ecx]
+        jmp   cr_epilogue
+
+cr_retlongdouble:
+        fld   TBYTE PTR [ecx]
+        jmp   cr_epilogue
+
+cr_epilogue:
+        ;; Epilogue code is autogenerated.
+        ret
+ffi_closure_raw_SYSV ENDP
+
+#endif /* !FFI_NO_RAW_API */
+
+ffi_closure_STDCALL PROC NEAR FORCEFRAME
+    ;; the ffi_closure ctx is passed in eax by the trampoline.
+
+        sub  esp, 40
+        lea  edx, [ebp - 24]
+        mov  [ebp - 12], edx         ;; resp
+        lea  edx, [ebp + 12]         ;; account for stub return address on stack
+        mov  [esp + 8], edx          ;; args
+        lea  edx, [ebp - 12]
+        mov  [esp + 4], edx          ;; &resp
+        mov  [esp], eax              ;; closure
+        call ffi_closure_SYSV_inner
+        mov  ecx, [ebp - 12]
+
+cd_jumptable:
+        jmp  [cd_jumpdata + 4 * eax]
+cd_jumpdata:
+        ;; Do not insert anything here between the label and jump table.
+        dd offset cd_epilogue       ;; FFI_TYPE_VOID
+        dd offset cd_retint         ;; FFI_TYPE_INT
+        dd offset cd_retfloat       ;; FFI_TYPE_FLOAT
+        dd offset cd_retdouble      ;; FFI_TYPE_DOUBLE
+        dd offset cd_retlongdouble  ;; FFI_TYPE_LONGDOUBLE
+        dd offset cd_retint8        ;; FFI_TYPE_UINT8
+        dd offset cd_retint8        ;; FFI_TYPE_SINT8
+        dd offset cd_retint16       ;; FFI_TYPE_UINT16
+        dd offset cd_retint16       ;; FFI_TYPE_SINT16
+        dd offset cd_retint         ;; FFI_TYPE_UINT32
+        dd offset cd_retint         ;; FFI_TYPE_SINT32
+        dd offset cd_retint64       ;; FFI_TYPE_UINT64
+        dd offset cd_retint64       ;; FFI_TYPE_SINT64
+        dd offset cd_epilogue       ;; FFI_TYPE_STRUCT
+        dd offset cd_retint         ;; FFI_TYPE_POINTER
+        dd offset cd_retint8        ;; FFI_TYPE_SMALL_STRUCT_1B
+        dd offset cd_retint16       ;; FFI_TYPE_SMALL_STRUCT_2B
+        dd offset cd_retint         ;; FFI_TYPE_SMALL_STRUCT_4B
+
+cd_retint8:
+        mov   al, [ecx]
+        jmp   cd_epilogue
+
+cd_retint16:
+        mov   ax, [ecx]
+        jmp   cd_epilogue
+
+cd_retint:
+        mov   eax, [ecx]
+        jmp   cd_epilogue
+
+cd_retint64:
+        mov   eax, [ecx + 0]
+        mov   edx, [ecx + 4]
+        jmp   cd_epilogue
+
+cd_retfloat:
+        fld   DWORD PTR [ecx]
+        jmp   cd_epilogue
+
+cd_retdouble:
+        fld   QWORD PTR [ecx]
+        jmp   cd_epilogue
+
+cd_retlongdouble:
+        fld   TBYTE PTR [ecx]
+        jmp   cd_epilogue
+
+cd_epilogue:
+        ;; Epilogue code is autogenerated.
+        ret
+ffi_closure_STDCALL ENDP
+
+_TEXT ENDS
+END
+
+#else
+
 	.text
  
         # This assumes we are using gas.
         .balign 16
-	.globl	_ffi_call_SYSV
-	.def	_ffi_call_SYSV;	.scl	2;	.type	32;	.endef
-_ffi_call_SYSV:
+	.globl	_ffi_call_win32
+#ifndef __OS2__
+	.def	_ffi_call_win32;	.scl	2;	.type	32;	.endef
+#endif
+_ffi_call_win32:
 .LFB1:
         pushl %ebp
 .LCFI0:
@@ -61,8 +421,10 @@ _ffi_call_SYSV:
         # FIXME: Align the stack to a 128-bit boundary to avoid
         # potential performance hits.
 
-	call  *28(%ebp)
+        call  *28(%ebp)
  
+        # stdcall functions pop arguments off the stack themselves
+
         # Load %ecx with the return type code
         movl  20(%ebp),%ecx
  
@@ -181,166 +543,15 @@ _ffi_call_SYSV:
         movl %ebp,%esp
         popl %ebp
         ret
-.ffi_call_SYSV_end:
+.ffi_call_win32_end:
 .LFE1:
 
-        # This assumes we are using gas.
-        .balign 16
-	.globl	_ffi_call_STDCALL
-	.def	_ffi_call_STDCALL;	.scl	2;	.type	32;	.endef
-_ffi_call_STDCALL:
-.LFB2:
-        pushl %ebp
-.LCFI2:
-        movl  %esp,%ebp
-.LCFI3:
-        # Make room for all of the new args.
-        movl  16(%ebp),%ecx 
-        subl  %ecx,%esp
-
-        movl  %esp,%eax
-
-        # Place all of the ffi_prep_args in position
-        pushl 12(%ebp)
-        pushl %eax
-        call  *8(%ebp)
-
-        # Return stack to previous state and call the function
-        addl  $8,%esp
-
-        # FIXME: Align the stack to a 128-bit boundary to avoid
-        # potential performance hits.
-
-        call  *28(%ebp)
-
-        # stdcall functions pop arguments off the stack themselves
-
-        # Load %ecx with the return type code
-        movl  20(%ebp),%ecx
-
-        # If the return value pointer is NULL, assume no return value.
-        cmpl  $0,24(%ebp)
-        jne   0f
-
-        # Even if there is no space for the return value, we are
-        # obliged to handle floating-point values.
-        cmpl  $FFI_TYPE_FLOAT,%ecx
-        jne   .Lsc_noretval
-        fstp  %st(0)
-
-        jmp   .Lsc_epilogue
-
-0:
-	call	1f
-	# Do not insert anything here between the call and the jump table.
-.Lsc_store_table:
-	.long	.Lsc_noretval		/* FFI_TYPE_VOID */
-	.long	.Lsc_retint		/* FFI_TYPE_INT */
-	.long	.Lsc_retfloat		/* FFI_TYPE_FLOAT */
-	.long	.Lsc_retdouble		/* FFI_TYPE_DOUBLE */
-	.long	.Lsc_retlongdouble	/* FFI_TYPE_LONGDOUBLE */
-	.long	.Lsc_retuint8		/* FFI_TYPE_UINT8 */
-	.long	.Lsc_retsint8		/* FFI_TYPE_SINT8 */
-	.long	.Lsc_retuint16		/* FFI_TYPE_UINT16 */
-	.long	.Lsc_retsint16		/* FFI_TYPE_SINT16 */
-	.long	.Lsc_retint		/* FFI_TYPE_UINT32 */
-	.long	.Lsc_retint		/* FFI_TYPE_SINT32 */
-	.long	.Lsc_retint64		/* FFI_TYPE_UINT64 */
-	.long	.Lsc_retint64		/* FFI_TYPE_SINT64 */
-	.long	.Lsc_retstruct		/* FFI_TYPE_STRUCT */
-	.long	.Lsc_retint		/* FFI_TYPE_POINTER */
-	.long	.Lsc_retstruct1b	/* FFI_TYPE_SMALL_STRUCT_1B */
-	.long	.Lsc_retstruct2b	/* FFI_TYPE_SMALL_STRUCT_2B */
-	.long	.Lsc_retstruct4b	/* FFI_TYPE_SMALL_STRUCT_4B */
-
-1:
-	add	%ecx, %ecx
-	add	%ecx, %ecx
-	add	(%esp),%ecx
-	add	$4, %esp
-	jmp	*(%ecx)
-
-	/* Sign/zero extend as appropriate.  */
-.Lsc_retsint8:
-	movsbl	%al, %eax
-	jmp	.Lsc_retint
-
-.Lsc_retsint16:
-	movswl	%ax, %eax
-	jmp	.Lsc_retint
-
-.Lsc_retuint8:
-	movzbl	%al, %eax
-	jmp	.Lsc_retint
-
-.Lsc_retuint16:
-	movzwl	%ax, %eax
-	jmp	.Lsc_retint
-
-.Lsc_retint:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        movl  %eax,0(%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retfloat:
-         # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        fstps (%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retdouble:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        fstpl (%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retlongdouble:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        fstpt (%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retint64:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        movl  %eax,0(%ecx)
-        movl  %edx,4(%ecx)
-	jmp   .Lsc_epilogue
-
-.Lsc_retstruct1b:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        movb  %al,0(%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retstruct2b:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        movw  %ax,0(%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retstruct4b:
-        # Load %ecx with the pointer to storage for the return value
-        movl  24(%ebp),%ecx
-        movl  %eax,0(%ecx)
-        jmp   .Lsc_epilogue
-
-.Lsc_retstruct:
-        # Nothing to do!
-
-.Lsc_noretval:
-.Lsc_epilogue:
-        movl %ebp,%esp
-        popl %ebp
-        ret
-.ffi_call_STDCALL_end:
-.LFE2:
-
         # This assumes we are using gas.
         .balign 16
 	.globl	_ffi_closure_SYSV
+#ifndef __OS2__
 	.def	_ffi_closure_SYSV;	.scl	2;	.type	32;	.endef
+#endif
 _ffi_closure_SYSV:
 .LFB3:
 	pushl	%ebp
@@ -461,7 +672,9 @@ _ffi_closure_SYSV:
         # This assumes we are using gas.
         .balign 16
 	.globl	_ffi_closure_raw_SYSV
+#ifndef __OS2__
 	.def	_ffi_closure_raw_SYSV;	.scl	2;	.type	32;	.endef
+#endif
 _ffi_closure_raw_SYSV:
 .LFB4:
 	pushl	%ebp
@@ -577,7 +790,9 @@ _ffi_closure_raw_SYSV:
         # This assumes we are using gas.
 	.balign	16
 	.globl	_ffi_closure_STDCALL
+#ifndef __OS2__
 	.def	_ffi_closure_STDCALL;	.scl	2;	.type	32;	.endef
+#endif
 _ffi_closure_STDCALL:
 .LFB5:
 	pushl	%ebp
@@ -683,7 +898,9 @@ _ffi_closure_STDCALL:
 .ffi_closure_STDCALL_end:
 .LFE5:
 
+#ifndef __OS2__
 	.section	.eh_frame,"w"
+#endif
 .Lframe1:
 .LSCIE1:
 	.long	.LECIE1-.LASCIE1  /* Length of Common Information Entry */
@@ -742,38 +959,6 @@ _ffi_closure_STDCALL:
 .LEFDE1:
 
 
-.LSFDE2:
-	.long	.LEFDE2-.LASFDE2	/* FDE Length */
-.LASFDE2:
-	.long	.LASFDE2-.Lframe1	/* FDE CIE offset */
-#if defined __PIC__ && defined HAVE_AS_X86_PCREL
-	.long	.LFB2-.	/* FDE initial location */
-#else
-	.long	.LFB2
-#endif
-	.long	.LFE2-.LFB2	/* FDE address range */
-#ifdef __PIC__
-	.byte	0x0	/* .uleb128 0x0; Augmentation size */
-#endif
-	/* DW_CFA_xxx CFI instructions go here.  */
-
-	.byte	0x4	/* DW_CFA_advance_loc4 */
-	.long	.LCFI2-.LFB2
-	.byte	0xe	/* DW_CFA_def_cfa_offset CFA = r4 + 8 = 8(%esp) */
-	.byte	0x8	/* .uleb128 0x8 */
-	.byte	0x85	/* DW_CFA_offset, column 0x5 %ebp at CFA + 2 * -4 */
-	.byte	0x2	/* .uleb128 0x2 */
-
-	.byte	0x4	/* DW_CFA_advance_loc4 */
-	.long	.LCFI3-.LCFI2
-	.byte	0xd	/* DW_CFA_def_cfa_register CFA = r5 = %ebp */
-	.byte	0x5	/* .uleb128 0x5 */
-
-	/* End of DW_CFA_xxx CFI instructions.  */
-	.align 4
-.LEFDE2:
-
-
 .LSFDE3:
 	.long	.LEFDE3-.LASFDE3	/* FDE Length */
 .LASFDE3:
@@ -875,3 +1060,6 @@ _ffi_closure_STDCALL:
 	/* End of DW_CFA_xxx CFI instructions.  */
 	.align 4
 .LEFDE5:
+
+#endif /* !_MSC_VER */
+