PowerPC64 ELFv2 support

PowerPC64 ELFv2 support
	* src/powerpc/ffitarget.h: Import from upstream.
	* src/powerpc/ffi.c: Likewise.
	* src/powerpc/linux64.S: Likewise.
	* src/powerpc/linux64_closure.S: Likewise.
	* doc/libffi.texi: Likewise.
	* testsuite/libffi.call/cls_double_va.c: Likewise.
	* testsuite/libffi.call/cls_longdouble_va.c: Likewise.

From-SVN: r204917

libffi/doc/libffi.texi

@@ -184,11 +184,11 @@ This calls the function @var{fn} according to the description given in
 
 @var{rvalue} is a pointer to a chunk of memory that will hold the
 result of the function call.  This must be large enough to hold the
-result and must be suitably aligned; it is the caller's responsibility
+result, no smaller than the system register size (generally 32 or 64
+bits), and must be suitably aligned; it is the caller's responsibility
 to ensure this.  If @var{cif} declares that the function returns
 @code{void} (using @code{ffi_type_void}), then @var{rvalue} is
-ignored.  If @var{rvalue} is @samp{NULL}, then the return value is
-discarded.
+ignored.
 
 @var{avalues} is a vector of @code{void *} pointers that point to the
 memory locations holding the argument values for a call.  If @var{cif}
@@ -214,7 +214,7 @@ int main()
   ffi_type *args[1];
   void *values[1];
   char *s;
-  int rc;
+  ffi_arg rc;
   
   /* Initialize the argument info vectors */    
   args[0] = &ffi_type_pointer;
@@ -222,7 +222,7 @@ int main()
   
   /* Initialize the cif */
   if (ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 1, 
-		       &ffi_type_uint, args) == FFI_OK)
+		       &ffi_type_sint, args) == FFI_OK)
     @{
       s = "Hello World!";
       ffi_call(&cif, puts, &rc, values);
@@ -360,7 +360,7 @@ You must first describe the structure to @samp{libffi} by creating a
 new @code{ffi_type} object for it.
 
 @tindex ffi_type
-@deftp ffi_type
+@deftp {Data type} ffi_type
 The @code{ffi_type} has the following members:
 @table @code
 @item size_t size
@@ -414,6 +414,7 @@ Here is the corresponding code to describe this struct to
       int i;
 
       tm_type.size = tm_type.alignment = 0;
+      tm_type.type = FFI_TYPE_STRUCT;
       tm_type.elements = &tm_type_elements;
     
       for (i = 0; i < 9; i++)
@@ -540,21 +541,23 @@ A trivial example that creates a new @code{puts} by binding
 #include <ffi.h>
 
 /* Acts like puts with the file given at time of enclosure. */
-void puts_binding(ffi_cif *cif, unsigned int *ret, void* args[], 
-                  FILE *stream)
+void puts_binding(ffi_cif *cif, void *ret, void* args[],
+                  void *stream)
 @{
-  *ret = fputs(*(char **)args[0], stream);
+  *(ffi_arg *)ret = fputs(*(char **)args[0], (FILE *)stream);
 @}
 
+typedef int (*puts_t)(char *);
+
 int main()
 @{
   ffi_cif cif;
   ffi_type *args[1];
   ffi_closure *closure;
 
-  int (*bound_puts)(char *);
+  void *bound_puts;
   int rc;
-  
+
   /* Allocate closure and bound_puts */
   closure = ffi_closure_alloc(sizeof(ffi_closure), &bound_puts);
 
@@ -565,13 +568,13 @@ int main()
 
       /* Initialize the cif */
       if (ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 1,
-                       &ffi_type_uint, args) == FFI_OK)
+                       &ffi_type_sint, args) == FFI_OK)
         @{
           /* Initialize the closure, setting stream to stdout */
-          if (ffi_prep_closure_loc(closure, &cif, puts_binding, 
+          if (ffi_prep_closure_loc(closure, &cif, puts_binding,
                                    stdout, bound_puts) == FFI_OK)
             @{
-              rc = bound_puts("Hello World!");
+              rc = ((puts_t)bound_puts)("Hello World!");
               /* rc now holds the result of the call to fputs */
             @}
         @}

libffi/src/powerpc/ffitarget.h

@@ -106,6 +106,10 @@ typedef enum ffi_abi {
 
 #define FFI_CLOSURES 1
 #define FFI_NATIVE_RAW_API 0
+#if defined (POWERPC) || defined (POWERPC_FREEBSD)
+# define FFI_TARGET_SPECIFIC_VARIADIC 1
+# define FFI_EXTRA_CIF_FIELDS unsigned nfixedargs
+#endif
 
 /* For additional types like the below, take care about the order in
    ppc_closures.S. They must follow after the FFI_TYPE_LAST.  */
@@ -118,14 +122,23 @@ typedef enum ffi_abi {
    defined in ffi.c, to determine the exact return type and its size.  */
 #define FFI_SYSV_TYPE_SMALL_STRUCT (FFI_TYPE_LAST + 2)
 
-#if defined(POWERPC64) || defined(POWERPC_AIX)
+/* Used by ELFv2 for homogenous structure returns.  */
+#define FFI_V2_TYPE_FLOAT_HOMOG		(FFI_TYPE_LAST + 1)
+#define FFI_V2_TYPE_DOUBLE_HOMOG	(FFI_TYPE_LAST + 2)
+#define FFI_V2_TYPE_SMALL_STRUCT	(FFI_TYPE_LAST + 3)
+
+#if _CALL_ELF == 2
+# define FFI_TRAMPOLINE_SIZE 32
+#else
+# if defined(POWERPC64) || defined(POWERPC_AIX)
 #  if defined(POWERPC_DARWIN64)
 #    define FFI_TRAMPOLINE_SIZE 48
 #  else
 #    define FFI_TRAMPOLINE_SIZE 24
 #  endif
-#else /* POWERPC || POWERPC_AIX */
+# else /* POWERPC || POWERPC_AIX */
 #  define FFI_TRAMPOLINE_SIZE 40
+# endif
 #endif
 
 #ifndef LIBFFI_ASM

libffi/src/powerpc/linux64.S

@@ -32,15 +32,22 @@
 #ifdef __powerpc64__
 	.hidden	ffi_call_LINUX64
 	.globl	ffi_call_LINUX64
+# if _CALL_ELF == 2
+	.text
+ffi_call_LINUX64:
+	addis	%r2, %r12, .TOC.-ffi_call_LINUX64@ha
+	addi	%r2, %r2, .TOC.-ffi_call_LINUX64@l
+	.localentry ffi_call_LINUX64, . - ffi_call_LINUX64
+# else
 	.section	".opd","aw"
 	.align	3
 ffi_call_LINUX64:
-#ifdef _CALL_LINUX
+#  ifdef _CALL_LINUX
 	.quad	.L.ffi_call_LINUX64,.TOC.@tocbase,0
 	.type	ffi_call_LINUX64,@function
 	.text
 .L.ffi_call_LINUX64:
-#else
+#  else
 	.hidden	.ffi_call_LINUX64
 	.globl	.ffi_call_LINUX64
 	.quad	.ffi_call_LINUX64,.TOC.@tocbase,0
@@ -48,7 +55,8 @@ ffi_call_LINUX64:
 	.type	.ffi_call_LINUX64,@function
 	.text
 .ffi_call_LINUX64:
-#endif
+#  endif
+# endif
 .LFB1:
 	mflr	%r0
 	std	%r28, -32(%r1)
@@ -63,26 +71,35 @@ ffi_call_LINUX64:
 	mr	%r31, %r5	/* flags, */
 	mr	%r30, %r6	/* rvalue, */
 	mr	%r29, %r7	/* function address.  */
+/* Save toc pointer, not for the ffi_prep_args64 call, but for the later
+   bctrl function call.  */
+# if _CALL_ELF == 2
+	std	%r2, 24(%r1)
+# else
 	std	%r2, 40(%r1)
+# endif
 
 	/* Call ffi_prep_args64.  */
 	mr	%r4, %r1
-#ifdef _CALL_LINUX
+# if defined _CALL_LINUX || _CALL_ELF == 2
 	bl	ffi_prep_args64
-#else
+# else
 	bl	.ffi_prep_args64
-#endif
+# endif
 
-	ld	%r0, 0(%r29)
+# if _CALL_ELF == 2
+	mr	%r12, %r29
+# else
+	ld	%r12, 0(%r29)
 	ld	%r2, 8(%r29)
 	ld	%r11, 16(%r29)
-
+# endif
 	/* Now do the call.  */
 	/* Set up cr1 with bits 4-7 of the flags.  */
 	mtcrf	0x40, %r31
 
 	/* Get the address to call into CTR.  */
-	mtctr	%r0
+	mtctr	%r12
 	/* Load all those argument registers.  */
 	ld	%r3, -32-(8*8)(%r28)
 	ld	%r4, -32-(7*8)(%r28)
@@ -117,12 +134,17 @@ ffi_call_LINUX64:
 
 	/* This must follow the call immediately, the unwinder
 	   uses this to find out if r2 has been saved or not.  */
+# if _CALL_ELF == 2
+	ld	%r2, 24(%r1)
+# else
 	ld	%r2, 40(%r1)
+# endif
 
 	/* Now, deal with the return value.  */
 	mtcrf	0x01, %r31
-	bt-	30, .Ldone_return_value
-	bt-	29, .Lfp_return_value
+	bt	31, .Lstruct_return_value
+	bt	30, .Ldone_return_value
+	bt	29, .Lfp_return_value
 	std	%r3, 0(%r30)
 	/* Fall through...  */
 
@@ -130,7 +152,7 @@ ffi_call_LINUX64:
 	/* Restore the registers we used and return.  */
 	mr	%r1, %r28
 	ld	%r0, 16(%r28)
-	ld	%r28, -32(%r1)
+	ld	%r28, -32(%r28)
 	mtlr	%r0
 	ld	%r29, -24(%r1)
 	ld	%r30, -16(%r1)
@@ -147,14 +169,48 @@ ffi_call_LINUX64:
 .Lfloat_return_value:
 	stfs	%f1, 0(%r30)
 	b	.Ldone_return_value
+
+.Lstruct_return_value:
+	bf	29, .Lsmall_struct
+	bf	28, .Lfloat_homog_return_value
+	stfd	%f1, 0(%r30)
+	stfd	%f2, 8(%r30)
+	stfd	%f3, 16(%r30)
+	stfd	%f4, 24(%r30)
+	stfd	%f5, 32(%r30)
+	stfd	%f6, 40(%r30)
+	stfd	%f7, 48(%r30)
+	stfd	%f8, 56(%r30)
+	b	.Ldone_return_value
+
+.Lfloat_homog_return_value:
+	stfs	%f1, 0(%r30)
+	stfs	%f2, 4(%r30)
+	stfs	%f3, 8(%r30)
+	stfs	%f4, 12(%r30)
+	stfs	%f5, 16(%r30)
+	stfs	%f6, 20(%r30)
+	stfs	%f7, 24(%r30)
+	stfs	%f8, 28(%r30)
+	b	.Ldone_return_value
+
+.Lsmall_struct:
+	std	%r3, 0(%r30)
+	std	%r4, 8(%r30)
+	b	.Ldone_return_value
+
 .LFE1:
 	.long	0
 	.byte	0,12,0,1,128,4,0,0
-#ifdef _CALL_LINUX
+# if _CALL_ELF == 2
+	.size	ffi_call_LINUX64,.-ffi_call_LINUX64
+# else
+#  ifdef _CALL_LINUX
 	.size	ffi_call_LINUX64,.-.L.ffi_call_LINUX64
-#else
+#  else
 	.size	.ffi_call_LINUX64,.-.ffi_call_LINUX64
-#endif
+#  endif
+# endif
 
 	.section	.eh_frame,EH_FRAME_FLAGS,@progbits
 .Lframe1:
@@ -197,8 +253,8 @@ ffi_call_LINUX64:
 	.uleb128 0x4
 	.align 3
 .LEFDE1:
-#endif
 
-#if defined __ELF__ && defined __linux__
+# if (defined __ELF__ && defined __linux__) || _CALL_ELF == 2
 	.section	.note.GNU-stack,"",@progbits
+# endif
 #endif

libffi/src/powerpc/linux64_closure.S

@@ -33,15 +33,22 @@
 #ifdef __powerpc64__
 	FFI_HIDDEN (ffi_closure_LINUX64)
 	.globl  ffi_closure_LINUX64
+# if _CALL_ELF == 2
+	.text
+ffi_closure_LINUX64:
+	addis	%r2, %r12, .TOC.-ffi_closure_LINUX64@ha
+	addi	%r2, %r2, .TOC.-ffi_closure_LINUX64@l
+	.localentry ffi_closure_LINUX64, . - ffi_closure_LINUX64
+# else
 	.section        ".opd","aw"
 	.align  3
 ffi_closure_LINUX64:
-#ifdef _CALL_LINUX
+#  ifdef _CALL_LINUX
 	.quad   .L.ffi_closure_LINUX64,.TOC.@tocbase,0
 	.type   ffi_closure_LINUX64,@function
 	.text
 .L.ffi_closure_LINUX64:
-#else
+#  else
 	FFI_HIDDEN (.ffi_closure_LINUX64)
 	.globl  .ffi_closure_LINUX64
 	.quad   .ffi_closure_LINUX64,.TOC.@tocbase,0
@@ -49,61 +56,103 @@ ffi_closure_LINUX64:
 	.type   .ffi_closure_LINUX64,@function
 	.text
 .ffi_closure_LINUX64:
-#endif
+#  endif
+# endif
+
+# if _CALL_ELF == 2
+#  32 byte special reg save area + 64 byte parm save area and retval
+#  + 13*8 fpr save area + round to 16
+#  define STACKFRAME 208
+#  define PARMSAVE 32
+#  No parameter save area is needed for the call to ffi_closure_helper_LINUX64,
+#  so return value can start there.
+#  define RETVAL PARMSAVE
+# else
+#  48 bytes special reg save area + 64 bytes parm save area
+#  + 16 bytes retval area + 13*8 bytes fpr save area + round to 16
+#  define STACKFRAME 240
+#  define PARMSAVE 48
+#  define RETVAL PARMSAVE+64
+# endif
+
 .LFB1:
-	# save general regs into parm save area
-	std	%r3, 48(%r1)
-	std	%r4, 56(%r1)
-	std	%r5, 64(%r1)
-	std	%r6, 72(%r1)
+# if _CALL_ELF == 2
+	ld	%r12, FFI_TRAMPOLINE_SIZE(%r11)		# closure->cif
 	mflr	%r0
+	lwz	%r12, 28(%r12)				# cif->flags
+	mtcrf	0x40, %r12
+	addi	%r12, %r1, PARMSAVE
+	bt	7, .Lparmsave
+	# Our caller has not allocated a parameter save area.
+	# We need to allocate one here and use it to pass gprs to
+	# ffi_closure_helper_LINUX64.  The return value area will do.
+	addi	%r12, %r1, -STACKFRAME+RETVAL
+.Lparmsave:
+	std	%r0, 16(%r1)
+	# Save general regs into parm save area
+	std	%r3, 0(%r12)
+	std	%r4, 8(%r12)
+	std	%r5, 16(%r12)
+	std	%r6, 24(%r12)
+	std	%r7, 32(%r12)
+	std	%r8, 40(%r12)
+	std	%r9, 48(%r12)
+	std	%r10, 56(%r12)
+
+	# load up the pointer to the parm save area
+	mr	%r5, %r12
+# else
+	mflr	%r0
+	# Save general regs into parm save area
+	# This is the parameter save area set up by our caller.
+	std	%r3, PARMSAVE+0(%r1)
+	std	%r4, PARMSAVE+8(%r1)
+	std	%r5, PARMSAVE+16(%r1)
+	std	%r6, PARMSAVE+24(%r1)
+	std	%r7, PARMSAVE+32(%r1)
+	std	%r8, PARMSAVE+40(%r1)
+	std	%r9, PARMSAVE+48(%r1)
+	std	%r10, PARMSAVE+56(%r1)
 
-	std	%r7, 80(%r1)
-	std	%r8, 88(%r1)
-	std	%r9, 96(%r1)
-	std	%r10, 104(%r1)
 	std	%r0, 16(%r1)
 
-	# mandatory 48 bytes special reg save area + 64 bytes parm save area
-	# + 16 bytes retval area + 13*8 bytes fpr save area + round to 16
-	stdu	%r1, -240(%r1)
-.LCFI0:
+	# load up the pointer to the parm save area
+	addi	%r5, %r1, PARMSAVE
+# endif
 
 	# next save fpr 1 to fpr 13
-	stfd  %f1, 128+(0*8)(%r1)
-	stfd  %f2, 128+(1*8)(%r1)
-	stfd  %f3, 128+(2*8)(%r1)
-	stfd  %f4, 128+(3*8)(%r1)
-	stfd  %f5, 128+(4*8)(%r1)
-	stfd  %f6, 128+(5*8)(%r1)
-	stfd  %f7, 128+(6*8)(%r1)
-	stfd  %f8, 128+(7*8)(%r1)
-	stfd  %f9, 128+(8*8)(%r1)
-	stfd  %f10, 128+(9*8)(%r1)
-	stfd  %f11, 128+(10*8)(%r1)
-	stfd  %f12, 128+(11*8)(%r1)
-	stfd  %f13, 128+(12*8)(%r1)
+	stfd	%f1, -104+(0*8)(%r1)
+	stfd	%f2, -104+(1*8)(%r1)
+	stfd	%f3, -104+(2*8)(%r1)
+	stfd	%f4, -104+(3*8)(%r1)
+	stfd	%f5, -104+(4*8)(%r1)
+	stfd	%f6, -104+(5*8)(%r1)
+	stfd	%f7, -104+(6*8)(%r1)
+	stfd	%f8, -104+(7*8)(%r1)
+	stfd	%f9, -104+(8*8)(%r1)
+	stfd	%f10, -104+(9*8)(%r1)
+	stfd	%f11, -104+(10*8)(%r1)
+	stfd	%f12, -104+(11*8)(%r1)
+	stfd	%f13, -104+(12*8)(%r1)
 
-	# set up registers for the routine that actually does the work
-	# get the context pointer from the trampoline
-	mr %r3, %r11
+	# load up the pointer to the saved fpr registers */
+	addi	%r6, %r1, -104
 
-	# now load up the pointer to the result storage
-	addi %r4, %r1, 112
+	# load up the pointer to the result storage
+	addi	%r4, %r1, -STACKFRAME+RETVAL
 
-	# now load up the pointer to the parameter save area
-	# in the previous frame
-	addi %r5, %r1, 240 + 48
+	stdu	%r1, -STACKFRAME(%r1)
+.LCFI0:
 
-	# now load up the pointer to the saved fpr registers */
-	addi %r6, %r1, 128
+	# get the context pointer from the trampoline
+	mr	%r3, %r11
 
 	# make the call
-#ifdef _CALL_LINUX
+# if defined _CALL_LINUX || _CALL_ELF == 2
 	bl ffi_closure_helper_LINUX64
-#else
+# else
 	bl .ffi_closure_helper_LINUX64
-#endif
+# endif
 .Lret:
 
 	# now r3 contains the return type
@@ -112,10 +161,12 @@ ffi_closure_LINUX64:
 
 	# look up the proper starting point in table
 	# by using return type as offset
+	ld %r0, STACKFRAME+16(%r1)
+	cmpldi %r3, FFI_V2_TYPE_SMALL_STRUCT
+	bge .Lsmall
 	mflr %r4		# move address of .Lret to r4
 	sldi %r3, %r3, 4	# now multiply return type by 16
 	addi %r4, %r4, .Lret_type0 - .Lret
-	ld %r0, 240+16(%r1)
 	add %r3, %r3, %r4	# add contents of table to table address
 	mtctr %r3
 	bctr			# jump to it
@@ -128,117 +179,175 @@ ffi_closure_LINUX64:
 .Lret_type0:
 # case FFI_TYPE_VOID
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 	nop
 # case FFI_TYPE_INT
-#ifdef __LITTLE_ENDIAN__
-	lwa %r3, 112+0(%r1)
-#else
-	lwa %r3, 112+4(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lwa %r3, RETVAL+0(%r1)
+# else
+	lwa %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_FLOAT
-	lfs %f1, 112+0(%r1)
+	lfs %f1, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_DOUBLE
-	lfd %f1, 112+0(%r1)
+	lfd %f1, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_LONGDOUBLE
-	lfd %f1, 112+0(%r1)
+	lfd %f1, RETVAL+0(%r1)
 	mtlr %r0
-	lfd %f2, 112+8(%r1)
+	lfd %f2, RETVAL+8(%r1)
 	b .Lfinish
 # case FFI_TYPE_UINT8
-#ifdef __LITTLE_ENDIAN__
-	lbz %r3, 112+0(%r1)
-#else
-	lbz %r3, 112+7(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lbz %r3, RETVAL+0(%r1)
+# else
+	lbz %r3, RETVAL+7(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_SINT8
-#ifdef __LITTLE_ENDIAN__
-	lbz %r3, 112+0(%r1)
-#else
-	lbz %r3, 112+7(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lbz %r3, RETVAL+0(%r1)
+# else
+	lbz %r3, RETVAL+7(%r1)
+# endif
 	extsb %r3,%r3
 	mtlr %r0
 	b .Lfinish
 # case FFI_TYPE_UINT16
-#ifdef __LITTLE_ENDIAN__
-	lhz %r3, 112+0(%r1)
-#else
-	lhz %r3, 112+6(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lhz %r3, RETVAL+0(%r1)
+# else
+	lhz %r3, RETVAL+6(%r1)
+# endif
 	mtlr %r0
 .Lfinish:
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_SINT16
-#ifdef __LITTLE_ENDIAN__
-	lha %r3, 112+0(%r1)
-#else
-	lha %r3, 112+6(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lha %r3, RETVAL+0(%r1)
+# else
+	lha %r3, RETVAL+6(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_UINT32
-#ifdef __LITTLE_ENDIAN__
-	lwz %r3, 112+0(%r1)
-#else
-	lwz %r3, 112+4(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lwz %r3, RETVAL+0(%r1)
+# else
+	lwz %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_SINT32
-#ifdef __LITTLE_ENDIAN__
-	lwa %r3, 112+0(%r1)
-#else
-	lwa %r3, 112+4(%r1)
-#endif
+# ifdef __LITTLE_ENDIAN__
+	lwa %r3, RETVAL+0(%r1)
+# else
+	lwa %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_UINT64
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_SINT64
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 # case FFI_TYPE_STRUCT
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
 	blr
 	nop
 # case FFI_TYPE_POINTER
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
+	mtlr %r0
+	addi %r1, %r1, STACKFRAME
+	blr
+# case FFI_V2_TYPE_FLOAT_HOMOG
+	lfs %f1, RETVAL+0(%r1)
+	lfs %f2, RETVAL+4(%r1)
+	lfs %f3, RETVAL+8(%r1)
+	b .Lmorefloat
+# case FFI_V2_TYPE_DOUBLE_HOMOG
+	lfd %f1, RETVAL+0(%r1)
+	lfd %f2, RETVAL+8(%r1)
+	lfd %f3, RETVAL+16(%r1)
+	lfd %f4, RETVAL+24(%r1)
+	mtlr %r0
+	lfd %f5, RETVAL+32(%r1)
+	lfd %f6, RETVAL+40(%r1)
+	lfd %f7, RETVAL+48(%r1)
+	lfd %f8, RETVAL+56(%r1)
+	addi %r1, %r1, STACKFRAME
+	blr
+.Lmorefloat:
+	lfs %f4, RETVAL+12(%r1)
+	mtlr %r0
+	lfs %f5, RETVAL+16(%r1)
+	lfs %f6, RETVAL+20(%r1)
+	lfs %f7, RETVAL+24(%r1)
+	lfs %f8, RETVAL+28(%r1)
+	addi %r1, %r1, STACKFRAME
+	blr
+.Lsmall:
+# ifdef __LITTLE_ENDIAN__
+	ld %r3,RETVAL+0(%r1)
+	mtlr %r0
+	ld %r4,RETVAL+8(%r1)
+	addi %r1, %r1, STACKFRAME
+	blr
+# else
+	# A struct smaller than a dword is returned in the low bits of r3
+	# ie. right justified.  Larger structs are passed left justified
+	# in r3 and r4.  The return value area on the stack will have
+	# the structs as they are usually stored in memory.
+	cmpldi %r3, FFI_V2_TYPE_SMALL_STRUCT + 7 # size 8 bytes?
+	neg %r5, %r3
+	ld %r3,RETVAL+0(%r1)
+	blt .Lsmalldown
+	mtlr %r0
+	ld %r4,RETVAL+8(%r1)
+	addi %r1, %r1, STACKFRAME
+	blr
+.Lsmalldown:
+	addi %r5, %r5, FFI_V2_TYPE_SMALL_STRUCT + 7
 	mtlr %r0
-	addi %r1, %r1, 240
+	sldi %r5, %r5, 3
+	addi %r1, %r1, STACKFRAME
+	srd %r3, %r3, %r5
 	blr
-# esac
+# endif
+
 .LFE1:
 	.long	0
 	.byte	0,12,0,1,128,0,0,0
-#ifdef _CALL_LINUX
+# if _CALL_ELF == 2
+	.size	ffi_closure_LINUX64,.-ffi_closure_LINUX64
+# else
+#  ifdef _CALL_LINUX
 	.size	ffi_closure_LINUX64,.-.L.ffi_closure_LINUX64
-#else
+#  else
 	.size	.ffi_closure_LINUX64,.-.ffi_closure_LINUX64
-#endif
+#  endif
+# endif
 
 	.section	.eh_frame,EH_FRAME_FLAGS,@progbits
 .Lframe1:
@@ -267,14 +376,14 @@ ffi_closure_LINUX64:
 	.byte	0x2	 # DW_CFA_advance_loc1
 	.byte	.LCFI0-.LFB1
 	.byte	0xe	 # DW_CFA_def_cfa_offset
-	.uleb128 240
+	.uleb128 STACKFRAME
 	.byte	0x11	 # DW_CFA_offset_extended_sf
 	.uleb128 0x41
 	.sleb128 -2
 	.align 3
 .LEFDE1:
-#endif
 
-#if defined __ELF__ && defined __linux__
+# if defined __ELF__ && defined __linux__
 	.section	.note.GNU-stack,"",@progbits
+# endif
 #endif

libffi/testsuite/libffi.call/cls_double_va.c

@@ -38,26 +38,24 @@ int main (void)
 
 	/* This printf call is variadic */
 	CHECK(ffi_prep_cif_var(&cif, FFI_DEFAULT_ABI, 1, 2, &ffi_type_sint,
-		arg_types) == FFI_OK);
+			       arg_types) == FFI_OK);
 
 	args[0] = &format;
 	args[1] = &doubleArg;
 	args[2] = NULL;
 
 	ffi_call(&cif, FFI_FN(printf), &res, args);
-	// { dg-output "7.0" }
+	/* { dg-output "7.0" } */
 	printf("res: %d\n", (int) res);
-	// { dg-output "\nres: 4" }
+	/* { dg-output "\nres: 4" } */
 
-	/* The call to cls_double_va_fn is static, so have to use a normal prep_cif */
-	CHECK(ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 2, &ffi_type_sint, arg_types) == FFI_OK);
+	CHECK(ffi_prep_closure_loc(pcl, &cif, cls_double_va_fn, NULL,
+				   code) == FFI_OK);
 
-	CHECK(ffi_prep_closure_loc(pcl, &cif, cls_double_va_fn, NULL, code) == FFI_OK);
-
-	res	= ((int(*)(char*, double))(code))(format, doubleArg);
-	// { dg-output "\n7.0" }
+	res = ((int(*)(char*, ...))(code))(format, doubleArg);
+	/* { dg-output "\n7.0" } */
 	printf("res: %d\n", (int) res);
-	// { dg-output "\nres: 4" }
+	/* { dg-output "\nres: 4" } */
 
 	exit(0);
 }

libffi/testsuite/libffi.call/cls_longdouble_va.c

@@ -38,27 +38,24 @@ int main (void)
 
 	/* This printf call is variadic */
 	CHECK(ffi_prep_cif_var(&cif, FFI_DEFAULT_ABI, 1, 2, &ffi_type_sint,
-		arg_types) == FFI_OK);
+			       arg_types) == FFI_OK);
 
 	args[0] = &format;
 	args[1] = &ldArg;
 	args[2] = NULL;
 
 	ffi_call(&cif, FFI_FN(printf), &res, args);
-	// { dg-output "7.0" }
+	/* { dg-output "7.0" } */
 	printf("res: %d\n", (int) res);
-	// { dg-output "\nres: 4" }
+	/* { dg-output "\nres: 4" } */
 
-	/* The call to cls_longdouble_va_fn is static, so have to use a normal prep_cif */
-	CHECK(ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 2, &ffi_type_sint,
-		arg_types) == FFI_OK);
+	CHECK(ffi_prep_closure_loc(pcl, &cif, cls_longdouble_va_fn, NULL,
+				   code) == FFI_OK);
 
-	CHECK(ffi_prep_closure_loc(pcl, &cif, cls_longdouble_va_fn, NULL, code) == FFI_OK);
-
-	res	= ((int(*)(char*, long double))(code))(format, ldArg);
-	// { dg-output "\n7.0" }
+	res = ((int(*)(char*, ...))(code))(format, ldArg);
+	/* { dg-output "\n7.0" } */
 	printf("res: %d\n", (int) res);
-	// { dg-output "\nres: 4" }
+	/* { dg-output "\nres: 4" } */
 
 	exit(0);
 }