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.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@204917 138bc75d-0d04-0410-961f-82ee72b054a4

8 files changed, 860 insertions, 350 deletions

diff --git a/libffi/ChangeLog b/libffi/ChangeLog
index 6846f51cd03..ce3a6c5797e 100644
--- a/libffi/ChangeLog
+++ b/libffi/ChangeLog
@@ -1,3 +1,13 @@
+2013-11-18  Alan Modra  <amodra@gmail.com>
+
+	* 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.
+
 2013-09-20  Alan Modra  <amodra@gmail.com>
 
 	* configure: Regenerate.
@@ -88,10 +98,10 @@
 2012-10-30  James Greenhalgh  <james.greenhalgh at arm.com>
             Marcus Shawcroft  <marcus.shawcroft at arm.com>
 
-        * README: Add details of aarch64 port.
-        * src/aarch64/ffi.c: New.
-        * src/aarch64/ffitarget.h: Likewise.
-        * src/aarch64/sysv.S: Likewise.
+	* README: Add details of aarch64 port.
+	* src/aarch64/ffi.c: New.
+	* src/aarch64/ffitarget.h: Likewise.
+	* src/aarch64/sysv.S: Likewise.
 	* Makefile.am: Support aarch64.
 	* configure.ac: Support aarch64.
 	* Makefile.in, configure: Rebuilt.
@@ -99,30 +109,30 @@
 2012-10-30  James Greenhalgh  <james.greenhalgh at arm.com>
             Marcus Shawcroft  <marcus.shawcroft at arm.com>
 
-        * testsuite/lib/libffi.exp: Add support for aarch64.
-        * testsuite/libffi.call/cls_struct_va1.c: New.
-        * testsuite/libffi.call/cls_uchar_va.c: Likewise.
-        * testsuite/libffi.call/cls_uint_va.c: Likewise.
-        * testsuite/libffi.call/cls_ulong_va.c: Likewise.
-        * testsuite/libffi.call/cls_ushort_va.c: Likewise.
-        * testsuite/libffi.call/nested_struct11.c: Likewise.
-        * testsuite/libffi.call/uninitialized.c: Likewise.
-        * testsuite/libffi.call/va_1.c: Likewise.
-        * testsuite/libffi.call/va_struct1.c: Likewise.
-        * testsuite/libffi.call/va_struct2.c: Likewise.
-        * testsuite/libffi.call/va_struct3.c: Likewise.
+	* testsuite/lib/libffi.exp: Add support for aarch64.
+	* testsuite/libffi.call/cls_struct_va1.c: New.
+	* testsuite/libffi.call/cls_uchar_va.c: Likewise.
+	* testsuite/libffi.call/cls_uint_va.c: Likewise.
+	* testsuite/libffi.call/cls_ulong_va.c: Likewise.
+	* testsuite/libffi.call/cls_ushort_va.c: Likewise.
+	* testsuite/libffi.call/nested_struct11.c: Likewise.
+	* testsuite/libffi.call/uninitialized.c: Likewise.
+	* testsuite/libffi.call/va_1.c: Likewise.
+	* testsuite/libffi.call/va_struct1.c: Likewise.
+	* testsuite/libffi.call/va_struct2.c: Likewise.
+	* testsuite/libffi.call/va_struct3.c: Likewise.
 
 2012-10-12  Walter Lee  <walt@tilera.com>
 
-        * Makefile.am: Add TILE-Gx/TILEPro support.
-        * configure.ac: Likewise.
-        * Makefile.in: Regenerate.
-        * configure: Likewise.
-        * src/prep_cif.c (ffi_prep_cif_core): Handle TILE-Gx/TILEPro.
-        * src/tile: New directory.
-        * src/tile/ffi.c: New file.
-        * src/tile/ffitarget.h: Ditto.
-        * src/tile/tile.S: Ditto.
+	* Makefile.am: Add TILE-Gx/TILEPro support.
+	* configure.ac: Likewise.
+	* Makefile.in: Regenerate.
+	* configure: Likewise.
+	* src/prep_cif.c (ffi_prep_cif_core): Handle TILE-Gx/TILEPro.
+	* src/tile: New directory.
+	* src/tile/ffi.c: New file.
+	* src/tile/ffitarget.h: Ditto.
+	* src/tile/tile.S: Ditto.
 
 2012-10-12  Matthias Klose  <doko@ubuntu.com>
 
@@ -623,7 +633,7 @@
 
 2011-07-11  Andrew Haley  <aph@redhat.com>
 
-        * src/arm/ffi.c (FFI_INIT_TRAMPOLINE): Clear icache.
+	* src/arm/ffi.c (FFI_INIT_TRAMPOLINE): Clear icache.
 
 2011-06-29  Rainer Orth  <ro@CeBiTec.Uni-Bielefeld.DE>
 
@@ -923,10 +933,10 @@
 
 2010-08-05  Dan Witte  <dwitte@mozilla.com>
 
-        * Makefile.am: Pass FFI_DEBUG define to msvcc.sh for linking to the
-        debug CRT when --enable-debug is given.
-        * configure.ac: Define it.
-        * msvcc.sh: Translate -g and -DFFI_DEBUG appropriately.
+	* Makefile.am: Pass FFI_DEBUG define to msvcc.sh for linking to the
+	debug CRT when --enable-debug is given.
+	* configure.ac: Define it.
+	* msvcc.sh: Translate -g and -DFFI_DEBUG appropriately.
 
 2010-08-04  Dan Witte  <dwitte@mozilla.com>
 
@@ -944,7 +954,7 @@
 
 	* src/*/ffitarget.h: Make FFI_LAST_ABI one past the last valid ABI.
 	* src/prep_cif.c: Fix ABI assertion.
-        * src/cris/ffi.c: Ditto.
+	* src/cris/ffi.c: Ditto.
 
 2010-07-10  Evan Phoenix  <evan@fallingsnow.net>
 
@@ -1546,74 +1556,74 @@
 	testsuite/libffi.call/cls_2byte.c,
 	testsuite/libffi.call/cls_3_1byte.c,
 	testsuite/libffi.call/cls_3byte1.c,
- 	testsuite/libffi.call/cls_3byte2.c,
- 	testsuite/libffi.call/cls_4_1byte.c,
- 	testsuite/libffi.call/cls_4byte.c,
- 	testsuite/libffi.call/cls_5_1_byte.c,
- 	testsuite/libffi.call/cls_5byte.c,
- 	testsuite/libffi.call/cls_64byte.c,
- 	testsuite/libffi.call/cls_6_1_byte.c,
- 	testsuite/libffi.call/cls_6byte.c,
- 	testsuite/libffi.call/cls_7_1_byte.c,
- 	testsuite/libffi.call/cls_7byte.c,
- 	testsuite/libffi.call/cls_8byte.c,
- 	testsuite/libffi.call/cls_9byte1.c,
- 	testsuite/libffi.call/cls_9byte2.c,
- 	testsuite/libffi.call/cls_align_double.c,
- 	testsuite/libffi.call/cls_align_float.c,
- 	testsuite/libffi.call/cls_align_longdouble.c,
- 	testsuite/libffi.call/cls_align_longdouble_split.c,
- 	testsuite/libffi.call/cls_align_longdouble_split2.c,
- 	testsuite/libffi.call/cls_align_pointer.c,
- 	testsuite/libffi.call/cls_align_sint16.c,
- 	testsuite/libffi.call/cls_align_sint32.c,
- 	testsuite/libffi.call/cls_align_sint64.c,
- 	testsuite/libffi.call/cls_align_uint16.c,
- 	testsuite/libffi.call/cls_align_uint32.c,
- 	testsuite/libffi.call/cls_align_uint64.c,
- 	testsuite/libffi.call/cls_dbls_struct.c,
- 	testsuite/libffi.call/cls_double.c,
- 	testsuite/libffi.call/cls_double_va.c,
- 	testsuite/libffi.call/cls_float.c,
- 	testsuite/libffi.call/cls_longdouble.c,
- 	testsuite/libffi.call/cls_longdouble_va.c,
- 	testsuite/libffi.call/cls_multi_schar.c,
- 	testsuite/libffi.call/cls_multi_sshort.c,
- 	testsuite/libffi.call/cls_multi_sshortchar.c,
- 	testsuite/libffi.call/cls_multi_uchar.c,
- 	testsuite/libffi.call/cls_multi_ushort.c,
- 	testsuite/libffi.call/cls_multi_ushortchar.c,
- 	testsuite/libffi.call/cls_pointer.c,
- 	testsuite/libffi.call/cls_pointer_stack.c,
- 	testsuite/libffi.call/cls_schar.c,
- 	testsuite/libffi.call/cls_sint.c,
- 	testsuite/libffi.call/cls_sshort.c,
- 	testsuite/libffi.call/cls_uchar.c,
- 	testsuite/libffi.call/cls_uint.c,
- 	testsuite/libffi.call/cls_ulonglong.c,
- 	testsuite/libffi.call/cls_ushort.c,
- 	testsuite/libffi.call/err_bad_abi.c,
- 	testsuite/libffi.call/err_bad_typedef.c,
- 	testsuite/libffi.call/float2.c,
- 	testsuite/libffi.call/huge_struct.c,
- 	testsuite/libffi.call/nested_struct.c,
- 	testsuite/libffi.call/nested_struct1.c,
- 	testsuite/libffi.call/nested_struct10.c,
- 	testsuite/libffi.call/nested_struct2.c,
- 	testsuite/libffi.call/nested_struct3.c,
- 	testsuite/libffi.call/nested_struct4.c,
- 	testsuite/libffi.call/nested_struct5.c,
- 	testsuite/libffi.call/nested_struct6.c,
- 	testsuite/libffi.call/nested_struct7.c,
- 	testsuite/libffi.call/nested_struct8.c,
- 	testsuite/libffi.call/nested_struct9.c,
- 	testsuite/libffi.call/problem1.c,
- 	testsuite/libffi.call/return_ldl.c,
- 	testsuite/libffi.call/return_ll1.c,
- 	testsuite/libffi.call/stret_large.c,
- 	testsuite/libffi.call/stret_large2.c,
- 	testsuite/libffi.call/stret_medium.c,
- 	testsuite/libffi.call/stret_medium2.c,
+	testsuite/libffi.call/cls_3byte2.c,
+	testsuite/libffi.call/cls_4_1byte.c,
+	testsuite/libffi.call/cls_4byte.c,
+	testsuite/libffi.call/cls_5_1_byte.c,
+	testsuite/libffi.call/cls_5byte.c,
+	testsuite/libffi.call/cls_64byte.c,
+	testsuite/libffi.call/cls_6_1_byte.c,
+	testsuite/libffi.call/cls_6byte.c,
+	testsuite/libffi.call/cls_7_1_byte.c,
+	testsuite/libffi.call/cls_7byte.c,
+	testsuite/libffi.call/cls_8byte.c,
+	testsuite/libffi.call/cls_9byte1.c,
+	testsuite/libffi.call/cls_9byte2.c,
+	testsuite/libffi.call/cls_align_double.c,
+	testsuite/libffi.call/cls_align_float.c,
+	testsuite/libffi.call/cls_align_longdouble.c,
+	testsuite/libffi.call/cls_align_longdouble_split.c,
+	testsuite/libffi.call/cls_align_longdouble_split2.c,
+	testsuite/libffi.call/cls_align_pointer.c,
+	testsuite/libffi.call/cls_align_sint16.c,
+	testsuite/libffi.call/cls_align_sint32.c,
+	testsuite/libffi.call/cls_align_sint64.c,
+	testsuite/libffi.call/cls_align_uint16.c,
+	testsuite/libffi.call/cls_align_uint32.c,
+	testsuite/libffi.call/cls_align_uint64.c,
+	testsuite/libffi.call/cls_dbls_struct.c,
+	testsuite/libffi.call/cls_double.c,
+	testsuite/libffi.call/cls_double_va.c,
+	testsuite/libffi.call/cls_float.c,
+	testsuite/libffi.call/cls_longdouble.c,
+	testsuite/libffi.call/cls_longdouble_va.c,
+	testsuite/libffi.call/cls_multi_schar.c,
+	testsuite/libffi.call/cls_multi_sshort.c,
+	testsuite/libffi.call/cls_multi_sshortchar.c,
+	testsuite/libffi.call/cls_multi_uchar.c,
+	testsuite/libffi.call/cls_multi_ushort.c,
+	testsuite/libffi.call/cls_multi_ushortchar.c,
+	testsuite/libffi.call/cls_pointer.c,
+	testsuite/libffi.call/cls_pointer_stack.c,
+	testsuite/libffi.call/cls_schar.c,
+	testsuite/libffi.call/cls_sint.c,
+	testsuite/libffi.call/cls_sshort.c,
+	testsuite/libffi.call/cls_uchar.c,
+	testsuite/libffi.call/cls_uint.c,
+	testsuite/libffi.call/cls_ulonglong.c,
+	testsuite/libffi.call/cls_ushort.c,
+	testsuite/libffi.call/err_bad_abi.c,
+	testsuite/libffi.call/err_bad_typedef.c,
+	testsuite/libffi.call/float2.c,
+	testsuite/libffi.call/huge_struct.c,
+	testsuite/libffi.call/nested_struct.c,
+	testsuite/libffi.call/nested_struct1.c,
+	testsuite/libffi.call/nested_struct10.c,
+	testsuite/libffi.call/nested_struct2.c,
+	testsuite/libffi.call/nested_struct3.c,
+	testsuite/libffi.call/nested_struct4.c,
+	testsuite/libffi.call/nested_struct5.c,
+	testsuite/libffi.call/nested_struct6.c,
+	testsuite/libffi.call/nested_struct7.c,
+	testsuite/libffi.call/nested_struct8.c,
+	testsuite/libffi.call/nested_struct9.c,
+	testsuite/libffi.call/problem1.c,
+	testsuite/libffi.call/return_ldl.c,
+	testsuite/libffi.call/return_ll1.c,
+	testsuite/libffi.call/stret_large.c,
+	testsuite/libffi.call/stret_large2.c,
+	testsuite/libffi.call/stret_medium.c,
+	testsuite/libffi.call/stret_medium2.c,
 	testsuite/libffi.special/unwindtest.cc: use ffi_closure_alloc instead
 	of checking for MMAP.  Use intptr_t instead of long casts.
 
diff --git a/libffi/doc/libffi.texi b/libffi/doc/libffi.texi
index f0e6517de16..57dae0b84cd 100644
--- a/libffi/doc/libffi.texi
+++ b/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 */
             @}
         @}
diff --git a/libffi/src/powerpc/ffi.c b/libffi/src/powerpc/ffi.c
index 26f7cf19b06..feb21447b64 100644
--- a/libffi/src/powerpc/ffi.c
+++ b/libffi/src/powerpc/ffi.c
@@ -49,6 +49,7 @@ enum {
   FLAG_RETURNS_128BITS  = 1 << (31-27), /* cr6  */
 
   FLAG_ARG_NEEDS_COPY   = 1 << (31- 7),
+  FLAG_ARG_NEEDS_PSAVE  = FLAG_ARG_NEEDS_COPY, /* Used by ELFv2 */
 #ifndef __NO_FPRS__
   FLAG_FP_ARGUMENTS     = 1 << (31- 6), /* cr1.eq; specified by ABI */
 #endif
@@ -369,7 +370,13 @@ ffi_prep_args_SYSV (extended_cif *ecif, unsigned *const stack)
   /* Check that we didn't overrun the stack...  */
   FFI_ASSERT (copy_space.c >= next_arg.c);
   FFI_ASSERT (gpr_base.u <= stacktop.u - ASM_NEEDS_REGISTERS);
+  /* The assert below is testing that the number of integer arguments agrees
+     with the number found in ffi_prep_cif_machdep().  However, intarg_count
+     is incremented whenever we place an FP arg on the stack, so account for
+     that before our assert test.  */
 #ifndef __NO_FPRS__
+  if (fparg_count > NUM_FPR_ARG_REGISTERS)
+    intarg_count -= fparg_count - NUM_FPR_ARG_REGISTERS;
   FFI_ASSERT (fpr_base.u
 	      <= stacktop.u - ASM_NEEDS_REGISTERS - NUM_GPR_ARG_REGISTERS);
 #endif
@@ -383,6 +390,45 @@ enum {
 };
 enum { ASM_NEEDS_REGISTERS64 = 4 };
 
+#if _CALL_ELF == 2
+static unsigned int
+discover_homogeneous_aggregate (const ffi_type *t, unsigned int *elnum)
+{
+  switch (t->type)
+    {
+    case FFI_TYPE_FLOAT:
+    case FFI_TYPE_DOUBLE:
+      *elnum = 1;
+      return (int) t->type;
+
+    case FFI_TYPE_STRUCT:;
+      {
+	unsigned int base_elt = 0, total_elnum = 0;
+	ffi_type **el = t->elements;
+	while (*el)
+	  {
+	    unsigned int el_elt, el_elnum = 0;
+	    el_elt = discover_homogeneous_aggregate (*el, &el_elnum);
+	    if (el_elt == 0
+		|| (base_elt && base_elt != el_elt))
+	      return 0;
+	    base_elt = el_elt;
+	    total_elnum += el_elnum;
+	    if (total_elnum > 8)
+	      return 0;
+	    el++;
+	  }
+	*elnum = total_elnum;
+	return base_elt;
+      }
+
+    default:
+      return 0;
+    }
+}
+#endif
+
+
 /* ffi_prep_args64 is called by the assembly routine once stack space
    has been allocated for the function's arguments.
 
@@ -428,6 +474,7 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
     unsigned long *ul;
     float *f;
     double *d;
+    size_t p;
   } valp;
 
   /* 'stacktop' points at the previous backchain pointer.  */
@@ -443,9 +490,9 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
   /* 'fpr_base' points at the space for fpr3, and grows upwards as
      we use FPR registers.  */
   valp fpr_base;
-  int fparg_count;
+  unsigned int fparg_count;
 
-  int i, words;
+  unsigned int i, words, nargs, nfixedargs;
   ffi_type **ptr;
   double double_tmp;
   union {
@@ -462,11 +509,18 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
     double **d;
   } p_argv;
   unsigned long gprvalue;
+#ifdef __STRUCT_PARM_ALIGN__
+  unsigned long align;
+#endif
 
   stacktop.c = (char *) stack + bytes;
   gpr_base.ul = stacktop.ul - ASM_NEEDS_REGISTERS64 - NUM_GPR_ARG_REGISTERS64;
   gpr_end.ul = gpr_base.ul + NUM_GPR_ARG_REGISTERS64;
+#if _CALL_ELF == 2
+  rest.ul = stack + 4 + NUM_GPR_ARG_REGISTERS64;
+#else
   rest.ul = stack + 6 + NUM_GPR_ARG_REGISTERS64;
+#endif
   fpr_base.d = gpr_base.d - NUM_FPR_ARG_REGISTERS64;
   fparg_count = 0;
   next_arg.ul = gpr_base.ul;
@@ -482,30 +536,36 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
 
   /* Now for the arguments.  */
   p_argv.v = ecif->avalue;
-  for (ptr = ecif->cif->arg_types, i = ecif->cif->nargs;
-       i > 0;
-       i--, ptr++, p_argv.v++)
+  nargs = ecif->cif->nargs;
+  nfixedargs = ecif->cif->nfixedargs;
+  for (ptr = ecif->cif->arg_types, i = 0;
+       i < nargs;
+       i++, ptr++, p_argv.v++)
     {
+      unsigned int elt, elnum;
+
       switch ((*ptr)->type)
 	{
 	case FFI_TYPE_FLOAT:
 	  double_tmp = **p_argv.f;
-	  *next_arg.f = (float) double_tmp;
+	  if (fparg_count < NUM_FPR_ARG_REGISTERS64 && i < nfixedargs)
+	    *fpr_base.d++ = double_tmp;
+	  else
+	    *next_arg.f = (float) double_tmp;
 	  if (++next_arg.ul == gpr_end.ul)
 	    next_arg.ul = rest.ul;
-	  if (fparg_count < NUM_FPR_ARG_REGISTERS64)
-	    *fpr_base.d++ = double_tmp;
 	  fparg_count++;
 	  FFI_ASSERT (flags & FLAG_FP_ARGUMENTS);
 	  break;
 
 	case FFI_TYPE_DOUBLE:
 	  double_tmp = **p_argv.d;
-	  *next_arg.d = double_tmp;
+	  if (fparg_count < NUM_FPR_ARG_REGISTERS64 && i < nfixedargs)
+	    *fpr_base.d++ = double_tmp;
+	  else
+	    *next_arg.d = double_tmp;
 	  if (++next_arg.ul == gpr_end.ul)
 	    next_arg.ul = rest.ul;
-	  if (fparg_count < NUM_FPR_ARG_REGISTERS64)
-	    *fpr_base.d++ = double_tmp;
 	  fparg_count++;
 	  FFI_ASSERT (flags & FLAG_FP_ARGUMENTS);
 	  break;
@@ -513,18 +573,20 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
 #if FFI_TYPE_LONGDOUBLE != FFI_TYPE_DOUBLE
 	case FFI_TYPE_LONGDOUBLE:
 	  double_tmp = (*p_argv.d)[0];
-	  *next_arg.d = double_tmp;
+	  if (fparg_count < NUM_FPR_ARG_REGISTERS64 && i < nfixedargs)
+	    *fpr_base.d++ = double_tmp;
+	  else
+	    *next_arg.d = double_tmp;
 	  if (++next_arg.ul == gpr_end.ul)
 	    next_arg.ul = rest.ul;
-	  if (fparg_count < NUM_FPR_ARG_REGISTERS64)
-	    *fpr_base.d++ = double_tmp;
 	  fparg_count++;
 	  double_tmp = (*p_argv.d)[1];
-	  *next_arg.d = double_tmp;
+	  if (fparg_count < NUM_FPR_ARG_REGISTERS64 && i < nfixedargs)
+	    *fpr_base.d++ = double_tmp;
+	  else
+	    *next_arg.d = double_tmp;
 	  if (++next_arg.ul == gpr_end.ul)
 	    next_arg.ul = rest.ul;
-	  if (fparg_count < NUM_FPR_ARG_REGISTERS64)
-	    *fpr_base.d++ = double_tmp;
 	  fparg_count++;
 	  FFI_ASSERT (__LDBL_MANT_DIG__ == 106);
 	  FFI_ASSERT (flags & FLAG_FP_ARGUMENTS);
@@ -532,28 +594,86 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
 #endif
 
 	case FFI_TYPE_STRUCT:
-	  words = ((*ptr)->size + 7) / 8;
-	  if (next_arg.ul >= gpr_base.ul && next_arg.ul + words > gpr_end.ul)
+#ifdef __STRUCT_PARM_ALIGN__
+	  align = (*ptr)->alignment;
+	  if (align > __STRUCT_PARM_ALIGN__)
+	    align = __STRUCT_PARM_ALIGN__;
+	  if (align > 1)
+	    next_arg.p = ALIGN (next_arg.p, align);
+#endif
+	  elt = 0;
+#if _CALL_ELF == 2
+	  elt = discover_homogeneous_aggregate (*ptr, &elnum);
+#endif
+	  if (elt)
 	    {
-	      size_t first = gpr_end.c - next_arg.c;
-	      memcpy (next_arg.c, *p_argv.c, first);
-	      memcpy (rest.c, *p_argv.c + first, (*ptr)->size - first);
-	      next_arg.c = rest.c + words * 8 - first;
+	      union {
+		void *v;
+		float *f;
+		double *d;
+	      } arg;
+
+	      arg.v = *p_argv.v;
+	      if (elt == FFI_TYPE_FLOAT)
+		{
+		  do
+		    {
+		      double_tmp = *arg.f++;
+		      if (fparg_count < NUM_FPR_ARG_REGISTERS64
+			  && i < nfixedargs)
+			*fpr_base.d++ = double_tmp;
+		      else
+			*next_arg.f = (float) double_tmp;
+		      if (++next_arg.f == gpr_end.f)
+			next_arg.f = rest.f;
+		      fparg_count++;
+		    }
+		  while (--elnum != 0);
+		  if ((next_arg.p & 3) != 0)
+		    {
+		      if (++next_arg.f == gpr_end.f)
+			next_arg.f = rest.f;
+		    }
+		}
+	      else
+		do
+		  {
+		    double_tmp = *arg.d++;
+		    if (fparg_count < NUM_FPR_ARG_REGISTERS64 && i < nfixedargs)
+		      *fpr_base.d++ = double_tmp;
+		    else
+		      *next_arg.d = double_tmp;
+		    if (++next_arg.d == gpr_end.d)
+		      next_arg.d = rest.d;
+		    fparg_count++;
+		  }
+		while (--elnum != 0);
 	    }
 	  else
 	    {
-	      char *where = next_arg.c;
+	      words = ((*ptr)->size + 7) / 8;
+	      if (next_arg.ul >= gpr_base.ul && next_arg.ul + words > gpr_end.ul)
+		{
+		  size_t first = gpr_end.c - next_arg.c;
+		  memcpy (next_arg.c, *p_argv.c, first);
+		  memcpy (rest.c, *p_argv.c + first, (*ptr)->size - first);
+		  next_arg.c = rest.c + words * 8 - first;
+		}
+	      else
+		{
+		  char *where = next_arg.c;
 
 #ifndef __LITTLE_ENDIAN__
-	      /* Structures with size less than eight bytes are passed
-		 left-padded.  */
-	      if ((*ptr)->size < 8)
-		where += 8 - (*ptr)->size;
+		  /* Structures with size less than eight bytes are passed
+		     left-padded.  */
+		  if ((*ptr)->size < 8)
+		    where += 8 - (*ptr)->size;
 #endif
-	      memcpy (where, *p_argv.c, (*ptr)->size);
-	      next_arg.ul += words;
-	      if (next_arg.ul == gpr_end.ul)
-		next_arg.ul = rest.ul;
+		  memcpy (where, *p_argv.c, (*ptr)->size);
+		  next_arg.ul += words;
+		  if (next_arg.ul == gpr_end.ul)
+		    next_arg.ul = rest.ul;
+		}
 	    }
 	  break;
 
@@ -597,24 +717,22 @@ ffi_prep_args64 (extended_cif *ecif, unsigned long *const stack)
 
 
 /* Perform machine dependent cif processing */
-ffi_status
-ffi_prep_cif_machdep (ffi_cif *cif)
+static ffi_status
+ffi_prep_cif_machdep_core (ffi_cif *cif)
 {
   /* All this is for the SYSV and LINUX64 ABI.  */
-  int i;
   ffi_type **ptr;
   unsigned bytes;
-  int fparg_count = 0, intarg_count = 0;
-  unsigned flags = 0;
+  unsigned i, fparg_count = 0, intarg_count = 0;
+  unsigned flags = cif->flags;
   unsigned struct_copy_size = 0;
   unsigned type = cif->rtype->type;
   unsigned size = cif->rtype->size;
 
+  /* The machine-independent calculation of cif->bytes doesn't work
+     for us.  Redo the calculation.  */
   if (cif->abi != FFI_LINUX64)
     {
-      /* All the machine-independent calculation of cif->bytes will be wrong.
-	 Redo the calculation for SYSV.  */
-
       /* Space for the frame pointer, callee's LR, and the asm's temp regs.  */
       bytes = (2 + ASM_NEEDS_REGISTERS) * sizeof (int);
 
@@ -624,13 +742,20 @@ ffi_prep_cif_machdep (ffi_cif *cif)
   else
     {
       /* 64-bit ABI.  */
+#if _CALL_ELF == 2
+      /* Space for backchain, CR, LR, TOC and the asm's temp regs.  */
+      bytes = (4 + ASM_NEEDS_REGISTERS64) * sizeof (long);
 
+      /* Space for the general registers.  */
+      bytes += NUM_GPR_ARG_REGISTERS64 * sizeof (long);
+#else
       /* Space for backchain, CR, LR, cc/ld doubleword, TOC and the asm's temp
 	 regs.  */
       bytes = (6 + ASM_NEEDS_REGISTERS64) * sizeof (long);
 
       /* Space for the mandatory parm save area and general registers.  */
       bytes += 2 * NUM_GPR_ARG_REGISTERS64 * sizeof (long);
+#endif
     }
 
   /* Return value handling.  The rules for SYSV are as follows:
@@ -650,19 +775,23 @@ ffi_prep_cif_machdep (ffi_cif *cif)
      - soft-float float/doubles are treated as UINT32/UINT64 respectivley.
      - soft-float long doubles are returned in gpr3-gpr6.  */
   /* First translate for softfloat/nonlinux */
-  if (cif->abi == FFI_LINUX_SOFT_FLOAT) {
-	if (type == FFI_TYPE_FLOAT)
-		type = FFI_TYPE_UINT32;
-	if (type == FFI_TYPE_DOUBLE)
-		type = FFI_TYPE_UINT64;
-	if (type == FFI_TYPE_LONGDOUBLE)
-		type = FFI_TYPE_UINT128;
-  } else if (cif->abi != FFI_LINUX && cif->abi != FFI_LINUX64) {
+  if (cif->abi == FFI_LINUX_SOFT_FLOAT)
+    {
+      if (type == FFI_TYPE_FLOAT)
+	type = FFI_TYPE_UINT32;
+      if (type == FFI_TYPE_DOUBLE)
+	type = FFI_TYPE_UINT64;
+      if (type == FFI_TYPE_LONGDOUBLE)
+	type = FFI_TYPE_UINT128;
+    }
+  else if (cif->abi != FFI_LINUX
+	   && cif->abi != FFI_LINUX64)
+    {
 #if FFI_TYPE_LONGDOUBLE != FFI_TYPE_DOUBLE
-	if (type == FFI_TYPE_LONGDOUBLE)
-		type = FFI_TYPE_STRUCT;
+      if (type == FFI_TYPE_LONGDOUBLE)
+	type = FFI_TYPE_STRUCT;
 #endif
-  }
+    }
 
   switch (type)
     {
@@ -691,7 +820,7 @@ ffi_prep_cif_machdep (ffi_cif *cif)
     case FFI_TYPE_STRUCT:
       /*
        * The final SYSV ABI says that structures smaller or equal 8 bytes
-       * are returned in r3/r4. The FFI_GCC_SYSV ABI instead returns them
+       * are returned in r3/r4.  The FFI_GCC_SYSV ABI instead returns them
        * in memory.
        *
        * NOTE: The assembly code can safely assume that it just needs to
@@ -700,7 +829,29 @@ ffi_prep_cif_machdep (ffi_cif *cif)
        *       set.
        */
       if (cif->abi == FFI_SYSV && size <= 8)
-	flags |= FLAG_RETURNS_SMST;
+	{
+	  flags |= FLAG_RETURNS_SMST;
+	  break;
+	}
+#if _CALL_ELF == 2
+      if (cif->abi == FFI_LINUX64)
+	{
+	  unsigned int elt, elnum;
+	  elt = discover_homogeneous_aggregate (cif->rtype, &elnum);
+	  if (elt)
+	    {
+	      if (elt == FFI_TYPE_DOUBLE)
+		flags |= FLAG_RETURNS_64BITS;
+	      flags |= FLAG_RETURNS_FP | FLAG_RETURNS_SMST;
+	      break;
+	    }
+	  if (size <= 16)
+	    {
+	      flags |= FLAG_RETURNS_SMST;
+	      break;
+	    }
+	}
+#endif
       intarg_count++;
       flags |= FLAG_RETVAL_REFERENCE;
       /* Fall through.  */
@@ -816,27 +967,54 @@ ffi_prep_cif_machdep (ffi_cif *cif)
   else
     for (ptr = cif->arg_types, i = cif->nargs; i > 0; i--, ptr++)
       {
+	unsigned int elt, elnum;
+#ifdef __STRUCT_PARM_ALIGN__
+	unsigned int align;
+#endif
+
 	switch ((*ptr)->type)
 	  {
 #if FFI_TYPE_LONGDOUBLE != FFI_TYPE_DOUBLE
 	  case FFI_TYPE_LONGDOUBLE:
-	    if (cif->abi == FFI_LINUX_SOFT_FLOAT)
-	      intarg_count += 4;
-	    else
-	      {
-		fparg_count += 2;
-		intarg_count += 2;
-	      }
+	    fparg_count += 2;
+	    intarg_count += 2;
+	    if (fparg_count > NUM_FPR_ARG_REGISTERS)
+	      flags |= FLAG_ARG_NEEDS_PSAVE;
 	    break;
 #endif
 	  case FFI_TYPE_FLOAT:
 	  case FFI_TYPE_DOUBLE:
 	    fparg_count++;
 	    intarg_count++;
+	    if (fparg_count > NUM_FPR_ARG_REGISTERS)
+	      flags |= FLAG_ARG_NEEDS_PSAVE;
 	    break;
 
 	  case FFI_TYPE_STRUCT:
+#ifdef __STRUCT_PARM_ALIGN__
+	    align = (*ptr)->alignment;
+	    if (align > __STRUCT_PARM_ALIGN__)
+	      align = __STRUCT_PARM_ALIGN__;
+	    align = align / 8;
+	    if (align > 1)
+	      intarg_count = ALIGN (intarg_count, align);
+#endif
 	    intarg_count += ((*ptr)->size + 7) / 8;
+	    elt = 0;
+#if _CALL_ELF == 2
+	    elt = discover_homogeneous_aggregate (*ptr, &elnum);
+#endif
+	    if (elt)
+	      {
+		fparg_count += elnum;
+		if (fparg_count > NUM_FPR_ARG_REGISTERS)
+		  flags |= FLAG_ARG_NEEDS_PSAVE;
+	      }
+	    else
+	      {
+		if (intarg_count > NUM_GPR_ARG_REGISTERS)
+		  flags |= FLAG_ARG_NEEDS_PSAVE;
+	      }
 	    break;
 
 	  case FFI_TYPE_POINTER:
@@ -852,9 +1030,11 @@ ffi_prep_cif_machdep (ffi_cif *cif)
 	    /* Everything else is passed as a 8-byte word in a GPR, either
 	       the object itself or a pointer to it.  */
 	    intarg_count++;
+	    if (intarg_count > NUM_GPR_ARG_REGISTERS)
+	      flags |= FLAG_ARG_NEEDS_PSAVE;
 	    break;
 	  default:
-		FFI_ASSERT (0);
+	    FFI_ASSERT (0);
 	  }
       }
 
@@ -892,8 +1072,13 @@ ffi_prep_cif_machdep (ffi_cif *cif)
 #endif
 
       /* Stack space.  */
+#if _CALL_ELF == 2
+      if ((flags & FLAG_ARG_NEEDS_PSAVE) != 0)
+	bytes += intarg_count * sizeof (long);
+#else
       if (intarg_count > NUM_GPR_ARG_REGISTERS64)
 	bytes += (intarg_count - NUM_GPR_ARG_REGISTERS64) * sizeof (long);
+#endif
     }
 
   /* The stack space allocated needs to be a multiple of 16 bytes.  */
@@ -908,6 +1093,26 @@ ffi_prep_cif_machdep (ffi_cif *cif)
   return FFI_OK;
 }
 
+ffi_status
+ffi_prep_cif_machdep (ffi_cif *cif)
+{
+  cif->nfixedargs = cif->nargs;
+  return ffi_prep_cif_machdep_core (cif);
+}
+
+ffi_status
+ffi_prep_cif_machdep_var (ffi_cif *cif,
+			  unsigned int nfixedargs,
+			  unsigned int ntotalargs MAYBE_UNUSED)
+{
+  cif->nfixedargs = nfixedargs;
+#if _CALL_ELF == 2
+  if (cif->abi == FFI_LINUX64)
+    cif->flags |= FLAG_ARG_NEEDS_PSAVE;
+#endif
+  return ffi_prep_cif_machdep_core (cif);
+}
+
 extern void ffi_call_SYSV(extended_cif *, unsigned, unsigned, unsigned *,
 			  void (*fn)(void));
 extern void FFI_HIDDEN ffi_call_LINUX64(extended_cif *, unsigned long,
@@ -919,30 +1124,28 @@ ffi_call(ffi_cif *cif, void (*fn)(void), void *rvalue, void **avalue)
 {
   /*
    * The final SYSV ABI says that structures smaller or equal 8 bytes
-   * are returned in r3/r4. The FFI_GCC_SYSV ABI instead returns them
+   * are returned in r3/r4.  The FFI_GCC_SYSV ABI instead returns them
    * in memory.
    *
-   * Just to keep things simple for the assembly code, we will always
-   * bounce-buffer struct return values less than or equal to 8 bytes.
-   * This allows the ASM to handle SYSV small structures by directly
-   * writing r3 and r4 to memory without worrying about struct size.
+   * We bounce-buffer SYSV small struct return values so that sysv.S
+   * can write r3 and r4 to memory without worrying about struct size.
+   *
+   * For ELFv2 ABI, use a bounce buffer for homogeneous structs too,
+   * for similar reasons.
    */
-  unsigned int smst_buffer[2];
+  unsigned long smst_buffer[8];
   extended_cif ecif;
-  unsigned int rsize = 0;
 
   ecif.cif = cif;
   ecif.avalue = avalue;
 
-  /* Ensure that we have a valid struct return value */
   ecif.rvalue = rvalue;
-  if (cif->rtype->type == FFI_TYPE_STRUCT) {
-    rsize = cif->rtype->size;
-    if (rsize <= 8)
-      ecif.rvalue = smst_buffer;
-    else if (!rvalue)
-      ecif.rvalue = alloca(rsize);
-  }
+  if ((cif->flags & FLAG_RETURNS_SMST) != 0)
+    ecif.rvalue = smst_buffer;
+  /* Ensure that we have a valid struct return value.
+     FIXME: Isn't this just papering over a user problem?  */
+  else if (!rvalue && cif->rtype->type == FFI_TYPE_STRUCT)
+    ecif.rvalue = alloca (cif->rtype->size);
 
   switch (cif->abi)
     {
@@ -967,11 +1170,26 @@ ffi_call(ffi_cif *cif, void (*fn)(void), void *rvalue, void **avalue)
 
   /* Check for a bounce-buffered return value */
   if (rvalue && ecif.rvalue == smst_buffer)
-    memcpy(rvalue, smst_buffer, rsize);
+    {
+      unsigned int rsize = cif->rtype->size;
+#ifndef __LITTLE_ENDIAN__
+      /* The SYSV ABI returns a structure of up to 4 bytes in size
+	 left-padded in r3.  */
+      if (cif->abi == FFI_SYSV && rsize <= 4)
+	memcpy (rvalue, (char *) smst_buffer + 4 - rsize, rsize);
+      /* The SYSV ABI returns a structure of up to 8 bytes in size
+	 left-padded in r3/r4, and the ELFv2 ABI similarly returns a
+	 structure of up to 8 bytes in size left-padded in r3.  */
+      else if (rsize <= 8)
+	memcpy (rvalue, (char *) smst_buffer + 8 - rsize, rsize);
+      else
+#endif
+	memcpy (rvalue, smst_buffer, rsize);
+    }
 }
 
 
-#ifndef POWERPC64
+#if !defined POWERPC64 || _CALL_ELF == 2
 #define MIN_CACHE_LINE_SIZE 8
 
 static void
@@ -995,6 +1213,22 @@ ffi_prep_closure_loc (ffi_closure *closure,
 		      void *codeloc)
 {
 #ifdef POWERPC64
+# if _CALL_ELF == 2
+  unsigned int *tramp = (unsigned int *) &closure->tramp[0];
+
+  if (cif->abi != FFI_LINUX64)
+    return FFI_BAD_ABI;
+
+  tramp[0] = 0xe96c0018;	/* 0:	ld	11,2f-0b(12)	*/
+  tramp[1] = 0xe98c0010;	/*	ld	12,1f-0b(12)	*/
+  tramp[2] = 0x7d8903a6;	/*	mtctr	12		*/
+  tramp[3] = 0x4e800420;	/*	bctr			*/
+				/* 1:	.quad	function_addr	*/
+				/* 2:	.quad	context		*/
+  *(void **) &tramp[4] = (void *) ffi_closure_LINUX64;
+  *(void **) &tramp[6] = codeloc;
+  flush_icache ((char *)tramp, (char *)codeloc, FFI_TRAMPOLINE_SIZE);
+# else
   void **tramp = (void **) &closure->tramp[0];
 
   if (cif->abi != FFI_LINUX64)
@@ -1002,6 +1236,7 @@ ffi_prep_closure_loc (ffi_closure *closure,
   /* Copy function address and TOC from ffi_closure_LINUX64.  */
   memcpy (tramp, (char *) ffi_closure_LINUX64, 16);
   tramp[2] = codeloc;
+# endif
 #else
   unsigned int *tramp;
 
@@ -1226,6 +1461,7 @@ ffi_closure_helper_SYSV (ffi_closure *closure, void *rvalue,
 	    }
 	  break;
 #endif
+
 	case FFI_TYPE_SINT16:
 	case FFI_TYPE_UINT16:
 #ifndef __LITTLE_ENDIAN__
@@ -1243,6 +1479,7 @@ ffi_closure_helper_SYSV (ffi_closure *closure, void *rvalue,
 	    }
 	  break;
 #endif
+
 	case FFI_TYPE_SINT32:
 	case FFI_TYPE_UINT32:
 	case FFI_TYPE_POINTER:
@@ -1346,16 +1583,20 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 
   void **avalue;
   ffi_type **arg_types;
-  long i, avn;
+  unsigned long i, avn, nfixedargs;
   ffi_cif *cif;
   ffi_dblfl *end_pfr = pfr + NUM_FPR_ARG_REGISTERS64;
+#ifdef __STRUCT_PARM_ALIGN__
+  unsigned long align;
+#endif
 
   cif = closure->cif;
   avalue = alloca (cif->nargs * sizeof (void *));
 
-  /* Copy the caller's structure return value address so that the closure
-     returns the data directly to the caller.  */
-  if (cif->rtype->type == FFI_TYPE_STRUCT)
+  /* Copy the caller's structure return value address so that the
+     closure returns the data directly to the caller.  */
+  if (cif->rtype->type == FFI_TYPE_STRUCT
+      && (cif->flags & FLAG_RETURNS_SMST) == 0)
     {
       rvalue = (void *) *pst;
       pst++;
@@ -1363,11 +1604,14 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 
   i = 0;
   avn = cif->nargs;
+  nfixedargs = cif->nfixedargs;
   arg_types = cif->arg_types;
 
   /* Grab the addresses of the arguments from the stack frame.  */
   while (i < avn)
     {
+      unsigned int elt, elnum;
+
       switch (arg_types[i]->type)
 	{
 	case FFI_TYPE_SINT8:
@@ -1377,6 +1621,7 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 	  pst++;
 	  break;
 #endif
+
 	case FFI_TYPE_SINT16:
 	case FFI_TYPE_UINT16:
 #ifndef __LITTLE_ENDIAN__
@@ -1384,6 +1629,7 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 	  pst++;
 	  break;
 #endif
+
 	case FFI_TYPE_SINT32:
 	case FFI_TYPE_UINT32:
 #ifndef __LITTLE_ENDIAN__
@@ -1391,6 +1637,7 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 	  pst++;
 	  break;
 #endif
+
 	case FFI_TYPE_SINT64:
 	case FFI_TYPE_UINT64:
 	case FFI_TYPE_POINTER:
@@ -1399,14 +1646,82 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 	  break;
 
 	case FFI_TYPE_STRUCT:
-#ifndef __LITTLE_ENDIAN__
-	  /* Structures with size less than eight bytes are passed
-	     left-padded.  */
-	  if (arg_types[i]->size < 8)
-	    avalue[i] = (char *) pst + 8 - arg_types[i]->size;
+#ifdef __STRUCT_PARM_ALIGN__
+	  align = arg_types[i]->alignment;
+	  if (align > __STRUCT_PARM_ALIGN__)
+	    align = __STRUCT_PARM_ALIGN__;
+	  if (align > 1)
+	    pst = (unsigned long *) ALIGN ((size_t) pst, align);
+#endif
+	  elt = 0;
+#if _CALL_ELF == 2
+	  elt = discover_homogeneous_aggregate (arg_types[i], &elnum);
+#endif
+	  if (elt)
+	    {
+	      union {
+		void *v;
+		unsigned long *ul;
+		float *f;
+		double *d;
+		size_t p;
+	      } to, from;
+
+	      /* Repackage the aggregate from its parts.  The
+		 aggregate size is not greater than the space taken by
+		 the registers so store back to the register/parameter
+		 save arrays.  */
+	      if (pfr + elnum <= end_pfr)
+		to.v = pfr;
+	      else
+		to.v = pst;
+
+	      avalue[i] = to.v;
+	      from.ul = pst;
+	      if (elt == FFI_TYPE_FLOAT)
+		{
+		  do
+		    {
+		      if (pfr < end_pfr && i < nfixedargs)
+			{
+			  *to.f = (float) pfr->d;
+			  pfr++;
+			}
+		      else
+			*to.f = *from.f;
+		      to.f++;
+		      from.f++;
+		    }
+		  while (--elnum != 0);
+		}
+	      else
+		{
+		  do
+		    {
+		      if (pfr < end_pfr && i < nfixedargs)
+			{
+			  *to.d = pfr->d;
+			  pfr++;
+			}
+		      else
+			*to.d = *from.d;
+		      to.d++;
+		      from.d++;
+		    }
+		  while (--elnum != 0);
+		}
+	    }
 	  else
+	    {
+#ifndef __LITTLE_ENDIAN__
+	      /* Structures with size less than eight bytes are passed
+		 left-padded.  */
+	      if (arg_types[i]->size < 8)
+		avalue[i] = (char *) pst + 8 - arg_types[i]->size;
+	      else
 #endif
-	    avalue[i] = pst;
+		avalue[i] = pst;
+	    }
 	  pst += (arg_types[i]->size + 7) / 8;
 	  break;
 
@@ -1418,7 +1733,7 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 
 	  /* there are 13 64bit floating point registers */
 
-	  if (pfr < end_pfr)
+	  if (pfr < end_pfr && i < nfixedargs)
 	    {
 	      double temp = pfr->d;
 	      pfr->f = (float) temp;
@@ -1434,7 +1749,7 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 	  /* On the outgoing stack all values are aligned to 8 */
 	  /* there are 13 64bit floating point registers */
 
-	  if (pfr < end_pfr)
+	  if (pfr < end_pfr && i < nfixedargs)
 	    {
 	      avalue[i] = pfr;
 	      pfr++;
@@ -1446,14 +1761,14 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
 
 #if FFI_TYPE_LONGDOUBLE != FFI_TYPE_DOUBLE
 	case FFI_TYPE_LONGDOUBLE:
-	  if (pfr + 1 < end_pfr)
+	  if (pfr + 1 < end_pfr && i + 1 < nfixedargs)
 	    {
 	      avalue[i] = pfr;
 	      pfr += 2;
 	    }
 	  else
 	    {
-	      if (pfr < end_pfr)
+	      if (pfr < end_pfr && i < nfixedargs)
 		{
 		  /* Passed partly in f13 and partly on the stack.
 		     Move it all to the stack.  */
@@ -1477,5 +1792,14 @@ ffi_closure_helper_LINUX64 (ffi_closure *closure, void *rvalue,
   (closure->fun) (cif, rvalue, avalue, closure->user_data);
 
   /* Tell ffi_closure_LINUX64 how to perform return type promotions.  */
+  if ((cif->flags & FLAG_RETURNS_SMST) != 0)
+    {
+      if ((cif->flags & FLAG_RETURNS_FP) == 0)
+	return FFI_V2_TYPE_SMALL_STRUCT + cif->rtype->size - 1;
+      else if ((cif->flags & FLAG_RETURNS_64BITS) != 0)
+	return FFI_V2_TYPE_DOUBLE_HOMOG;
+      else
+	return FFI_V2_TYPE_FLOAT_HOMOG;
+    }
   return cif->rtype->type;
 }
diff --git a/libffi/src/powerpc/ffitarget.h b/libffi/src/powerpc/ffitarget.h
index 3c9db495f49..2be728e18f4 100644
--- a/libffi/src/powerpc/ffitarget.h
+++ b/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
diff --git a/libffi/src/powerpc/linux64.S b/libffi/src/powerpc/linux64.S
index f28da8120b7..85b8aaafd82 100644
--- a/libffi/src/powerpc/linux64.S
+++ b/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
diff --git a/libffi/src/powerpc/linux64_closure.S b/libffi/src/powerpc/linux64_closure.S
index ac4a226ac50..9b6b5f3d79e 100644
--- a/libffi/src/powerpc/linux64_closure.S
+++ b/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
diff --git a/libffi/testsuite/libffi.call/cls_double_va.c b/libffi/testsuite/libffi.call/cls_double_va.c
index dbf20002dfc..e077f92b863 100644
--- a/libffi/testsuite/libffi.call/cls_double_va.c
+++ b/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);
 }
diff --git a/libffi/testsuite/libffi.call/cls_longdouble_va.c b/libffi/testsuite/libffi.call/cls_longdouble_va.c
index 4fa1ea28ace..39b438b289a 100644
--- a/libffi/testsuite/libffi.call/cls_longdouble_va.c
+++ b/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);
 }