Index: src/x86/win32.S
===================================================================
--- src/x86/win32.S	(revision 147800)
+++ src/x86/win32.S	(working copy)
@@ -390,6 +390,70 @@
 
 #endif /* !FFI_NO_RAW_API */
 
+        # This assumes we are using gas.
+	.balign	16
+	.globl	_ffi_closure_STDCALL
+	.def	_ffi_closure_STDCALL;	.scl	2;	.type	32;	.endef
+_ffi_closure_STDCALL:
+.LFB5:
+	pushl	%ebp
+.LCFI9:
+	movl	%esp, %ebp
+.LCFI10:
+	subl	$40, %esp
+	leal	-24(%ebp), %edx
+	movl	%edx, -12(%ebp)	/* resp */
+	leal	12(%ebp), %edx  /* account for stub return address on stack */
+	movl	%edx, 4(%esp)	/* args */
+	leal	-12(%ebp), %edx
+	movl	%edx, (%esp)	/* &resp */
+	call	_ffi_closure_SYSV_inner
+	movl	-12(%ebp), %ecx
+	/* It would be nice to just share this code with the
+	   duplicate sequence in _ffi_closure_SYSV, if only
+	   there were some way to represent that in the EH info.  */
+	cmpl	$FFI_TYPE_INT, %eax
+	je	.Lscls_retint
+	cmpl	$FFI_TYPE_FLOAT, %eax
+	je	.Lscls_retfloat
+	cmpl	$FFI_TYPE_DOUBLE, %eax
+	je	.Lscls_retdouble
+	cmpl	$FFI_TYPE_LONGDOUBLE, %eax
+	je	.Lscls_retldouble
+	cmpl	$FFI_TYPE_SINT64, %eax
+	je	.Lscls_retllong
+	cmpl	$FFI_TYPE_SINT8, %eax	/* 1-byte struct */
+	je	.Lscls_retstruct1
+	cmpl	$FFI_TYPE_SINT16, %eax	/* 2-bytes struct */
+	je	.Lscls_retstruct2
+.Lscls_epilogue:
+	movl	%ebp, %esp
+	popl	%ebp
+	ret
+.Lscls_retint:
+	movl	(%ecx), %eax
+	jmp	.Lscls_epilogue
+.Lscls_retfloat:
+	flds	(%ecx)
+	jmp	.Lscls_epilogue
+.Lscls_retdouble:
+	fldl	(%ecx)
+	jmp	.Lscls_epilogue
+.Lscls_retldouble:
+	fldt	(%ecx)
+	jmp	.Lscls_epilogue
+.Lscls_retllong:
+	movl	(%ecx), %eax
+	movl	4(%ecx), %edx
+	jmp	.Lscls_epilogue
+.Lscls_retstruct1:
+	movsbl	(%ecx), %eax
+	jmp	.Lscls_epilogue
+.Lscls_retstruct2:
+	movswl	(%ecx), %eax
+	jmp	.Lscls_epilogue
+.ffi_closure_STDCALL_end:
+.LFE5:
 
 	.section	.eh_frame,"w"
 .Lframe1:
@@ -552,3 +616,34 @@
 .LEFDE4:
 
 #endif /* !FFI_NO_RAW_API */
+
+.LSFDE5:
+	.long	.LEFDE5-.LASFDE5	/* FDE Length */
+.LASFDE5:
+	.long	.LASFDE5-.Lframe1	/* FDE CIE offset */
+#if defined __PIC__ && defined HAVE_AS_X86_PCREL
+	.long	.LFB5-.	/* FDE initial location */
+#else
+	.long	.LFB5
+#endif
+	.long	.LFE5-.LFB5	/* 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	.LCFI9-.LFB5
+	.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	.LCFI10-.LCFI9
+	.byte	0xd	/* DW_CFA_def_cfa_register CFA = r5 = %ebp */
+	.byte	0x5	/* .uleb128 0x5 */
+
+	/* End of DW_CFA_xxx CFI instructions.  */
+	.align 4
+.LEFDE5: