GO closures for powerpc linux

Plus .cfi async unwind info, rearrangement of ffi_call_linux64 and
ffi_call_SYSV function params to avoid register copies, tweaks to
trampolines.

	* src/powerpc/ffitarget.h (FFI_GO_CLOSURES): Define.
	* src/powerpc/ffi.c (ffi_call_int): New function with extra
	closure param, and args rearranged on ffi_call_linux64 and
	ffi_call_SYSV calls, extracted from ..
	(ffi_call): ..here.
	(ffi_call_go, ffi_prep_go_closure): New functions.
	* src/powerpc/ffi_linux64.c (ffi_prep_closure_loc_linux64): Make
	hidden.  Only flush insn part of ELFv2 trampoline.  Don't shuffle
	ELFv1 trampoline.
	(ffi_closure_helper_LINUX64): Replace closure param with cif, fun,
	user_data params.
	* src/powerpc/ffi_powerpc.h (ffi_go_closure_sysv): Declare.
	(ffi_go_closure_linux64): Declare.
	(ffi_call_SYSV, fi_call_LINUX64): Update.
	(ffi_prep_closure_loc_sysv, ffi_prep_closure_loc_linux64): Declare.
	(ffi_closure_helper_SYSV, ffi_closure_helper_LINUX64): Update.
	* src/powerpc/ffi_sysv.c (ASM_NEEDS_REGISTERS): Increase to 6.
	(ffi_prep_closure_loc_sysv): Use bcl in trampoline, put data words
	last, flush just the insn part.
	(ffi_closure_helper_SYSV): Replace closure param with cif, fun and
	user_data params.
	* src/powerpc/linux64.S (ffi_call_LINUX64): Replace hand-written
	.eh_frame with .cfi directives.  Adjust for changed param order.
	Pass extra "closure" param to user function in static chain.  Add
	.cfi directives to describe epilogue.  Don't provide traceback
	table for ELFv2 or _CALL_LINUX.
	* src/powerpc/linux64_closure.S (ffi_closure_LINUX64): Replace
	hand-written .eh_frame with .cfi directives.  Adjust for changed
	ffi_closure_helper_LINUX64 params.  Add .cfi directives to
	describe epilogue.  Don't provide traceback table for ELFv2 or
	_CALL_LINUX.
	(ffi_go_closure_linux64): New function.
	* src/powerpc/sysv.S: Remove redundant .globl ffi_prep_args_SYSV.
	(ffi_call_SYSV): Make hidden.  Replace hand-written .eh_frame with
	.cfi directives.  Adjust for changed params.  Pass extra "closure"
	param to user function in static chain.  Add .cfi directives to
	describe epilogue.
	* src/powerpc/ppc_closure.S (ffi_closure_SYSV): Make hidden.
	Replace hand-written .eh_frame with .cfi directives.  Adjust for
	changed ffi_closure_helper_SYSV params.  Add .cfi directives to
	describe epilogue.  Don't just use nops in the dead __NO_FPRS__
	epilogues.
	(ffi_go_closure_sysv): New function.

src/powerpc/ppc_closure.S

@@ -33,13 +33,14 @@
 
 #ifndef POWERPC64
 
+FFI_HIDDEN(ffi_closure_SYSV)
 ENTRY(ffi_closure_SYSV)
-.LFB1:
+	.cfi_startproc
 	stwu %r1,-144(%r1)
-.LCFI0:
+	.cfi_def_cfa_offset 144
 	mflr %r0
-.LCFI1:
 	stw %r0,148(%r1)
+	.cfi_offset 65, 4
 
 # we want to build up an areas for the parameters passed
 # in registers (both floating point and integer)
@@ -48,6 +49,17 @@ ENTRY(ffi_closure_SYSV)
 	stw   %r3, 16(%r1)
 	stw   %r4, 20(%r1)
 	stw   %r5, 24(%r1)
+
+	# set up registers for the routine that does the work
+
+	# closure->cif
+	lwz %r3,FFI_TRAMPOLINE_SIZE(%r11)
+	# closure->fun
+	lwz %r4,FFI_TRAMPOLINE_SIZE+4(%r11)
+	# closure->user_data
+	lwz %r5,FFI_TRAMPOLINE_SIZE+8(%r11)
+
+.Ldoclosure:
 	stw   %r6, 28(%r1)
 	stw   %r7, 32(%r1)
 	stw   %r8, 36(%r1)
@@ -66,23 +78,18 @@ ENTRY(ffi_closure_SYSV)
 	stfd  %f8, 104(%r1)
 #endif
 
-	# set up registers for the routine that actually does the work
-	# get the context pointer from the trampoline
-	mr %r3,%r11
+	# pointer to the result storage
+	addi %r6,%r1,112
 
-	# now load up the pointer to the result storage
-	addi %r4,%r1,112
+	# pointer to the saved gpr registers
+	addi %r7,%r1,16
 
-	# now load up the pointer to the saved gpr registers
-	addi %r5,%r1,16
+	# pointer to the saved fpr registers
+	addi %r8,%r1,48
 
-	# now load up the pointer to the saved fpr registers */
-	addi %r6,%r1,48
-
-	# now load up the pointer to the outgoing parameter
-	# stack in the previous frame
+	# pointer to the outgoing parameter save area in the previous frame
 	# i.e. the previous frame pointer + 8
-	addi %r7,%r1,152
+	addi %r9,%r1,152
 
 	# make the call
 	bl ffi_closure_helper_SYSV@local
@@ -101,7 +108,6 @@ ENTRY(ffi_closure_SYSV)
 	add %r3,%r3,%r4		# add contents of table to table address
 	mtctr %r3
 	bctr			# jump to it
-.LFE1:
 
 # Each of the ret_typeX code fragments has to be exactly 16 bytes long
 # (4 instructions). For cache effectiveness we align to a 16 byte boundary
@@ -111,7 +117,9 @@ ENTRY(ffi_closure_SYSV)
 .Lret_type0:
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 	nop
 
 # case FFI_TYPE_INT
@@ -119,31 +127,33 @@ ENTRY(ffi_closure_SYSV)
 	mtlr %r0
 .Lfinish:
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_FLOAT
 #ifndef __NO_FPRS__
 	lfs %f1,112+0(%r1)
-	mtlr %r0
-	addi %r1,%r1,144
 #else
 	nop
-	nop
-	nop
 #endif
+	mtlr %r0
+	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_DOUBLE
 #ifndef __NO_FPRS__
 	lfd %f1,112+0(%r1)
-	mtlr %r0
-	addi %r1,%r1,144
 #else
 	nop
-	nop
-	nop
 #endif
+	mtlr %r0
+	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_LONGDOUBLE
 #ifndef __NO_FPRS__
@@ -152,10 +162,12 @@ ENTRY(ffi_closure_SYSV)
 	mtlr %r0
 	b .Lfinish
 #else
-	nop
-	nop
-	nop
+	mtlr %r0
+	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
+	nop
 #endif
 
 # case FFI_TYPE_UINT8
@@ -166,7 +178,9 @@ ENTRY(ffi_closure_SYSV)
 #endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT8
 #ifdef __LITTLE_ENDIAN__
@@ -186,7 +200,9 @@ ENTRY(ffi_closure_SYSV)
 #endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT16
 #ifdef __LITTLE_ENDIAN__
@@ -196,19 +212,25 @@ ENTRY(ffi_closure_SYSV)
 #endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT32
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT32
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT64
 	lwz %r3,112+0(%r1)
@@ -225,14 +247,18 @@ ENTRY(ffi_closure_SYSV)
 # case FFI_TYPE_STRUCT
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 	nop
 
 # case FFI_TYPE_POINTER
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT128
 	lwz %r3,112+0(%r1)
@@ -245,20 +271,26 @@ ENTRY(ffi_closure_SYSV)
 	lbz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 2. Two byte struct.
 	lhz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 3. Three byte struct.
 	lwz %r3,112+0(%r1)
 #ifdef __LITTLE_ENDIAN__
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 #else
 	srwi %r3,%r3,8
 	mtlr %r0
@@ -269,7 +301,9 @@ ENTRY(ffi_closure_SYSV)
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 5. Five byte struct.
 	lwz %r3,112+0(%r1)
@@ -319,64 +353,43 @@ ENTRY(ffi_closure_SYSV)
 	or %r4,%r6,%r4
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 #endif
 
 .Luint128:
 	lwz %r6,112+12(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
-	
+	.cfi_endproc
 END(ffi_closure_SYSV)
 
-	.section	".eh_frame",EH_FRAME_FLAGS,@progbits
-.Lframe1:
-	.4byte	.LECIE1-.LSCIE1	 # Length of Common Information Entry
-.LSCIE1:
-	.4byte	0x0	 # CIE Identifier Tag
-	.byte	0x1	 # CIE Version
-#if defined _RELOCATABLE || defined __PIC__
-	.ascii "zR\0"	 # CIE Augmentation
-#else
-	.ascii "\0"	 # CIE Augmentation
-#endif
-	.uleb128 0x1	 # CIE Code Alignment Factor
-	.sleb128 -4	 # CIE Data Alignment Factor
-	.byte	0x41	 # CIE RA Column
-#if defined _RELOCATABLE || defined __PIC__
-	.uleb128 0x1	 # Augmentation size
-	.byte	0x1b	 # FDE Encoding (pcrel sdata4)
-#endif
-	.byte	0xc	 # DW_CFA_def_cfa
-	.uleb128 0x1
-	.uleb128 0x0
-	.align 2
-.LECIE1:
-.LSFDE1:
-	.4byte	.LEFDE1-.LASFDE1	 # FDE Length
-.LASFDE1:
-	.4byte	.LASFDE1-.Lframe1	 # FDE CIE offset
-#if defined _RELOCATABLE || defined __PIC__
-	.4byte	.LFB1-.	 # FDE initial location
-#else
-	.4byte	.LFB1	 # FDE initial location
-#endif
-	.4byte	.LFE1-.LFB1	 # FDE address range
-#if defined _RELOCATABLE || defined __PIC__
-	.uleb128 0x0	 # Augmentation size
-#endif
-	.byte	0x4	 # DW_CFA_advance_loc4
-	.4byte	.LCFI0-.LFB1
-	.byte	0xe	 # DW_CFA_def_cfa_offset
-	.uleb128 144
-	.byte	0x4	 # DW_CFA_advance_loc4
-	.4byte	.LCFI1-.LCFI0
-	.byte	0x11	 # DW_CFA_offset_extended_sf
-	.uleb128 0x41
-	.sleb128 -1
-	.align 2
-.LEFDE1:
+
+FFI_HIDDEN(ffi_go_closure_sysv)
+ENTRY(ffi_go_closure_sysv)
+	.cfi_startproc
+	stwu %r1,-144(%r1)
+	.cfi_def_cfa_offset 144
+	mflr %r0
+	stw %r0,148(%r1)
+	.cfi_offset 65, 4
+
+	stw   %r3, 16(%r1)
+	stw   %r4, 20(%r1)
+	stw   %r5, 24(%r1)
+
+	# closure->cif
+	lwz %r3,4(%r11)
+	# closure->fun
+	lwz %r4,8(%r11)
+	# user_data
+	mr %r5,%r11
+	b .Ldoclosure
+	.cfi_endproc
+END(ffi_go_closure_sysv)
 
 #if defined __ELF__ && defined __linux__
 	.section	.note.GNU-stack,"",@progbits