MOVD	$-96(R15), R15

	// Save F8-F15 in our stack frame.
	FMOVD	F8, 32(R15)
	FMOVD	F9, 40(R15)
	FMOVD	F10, 48(R15)
	FMOVD	F11, 56(R15)
	FMOVD	F12, 64(R15)
	FMOVD	F13, 72(R15)
	FMOVD	F14, 80(R15)
	FMOVD	F15, 88(R15)

	// Initialize Go ABI environment.
	BL	runtime·load_g(SB)

	MOVD	R2, 8(R15)	// fn unsafe.Pointer
	MOVD	R3, 16(R15)	// a unsafe.Pointer
	// Skip R4 = n uint32

	std     %f13, 40(%r15)
	std     %f14, 48(%r15)
	std     %f15, 56(%r15)

	/* restore g pointer */
	lgr     %r13, %r3

	/* call fn */
	basr    %r14, %r2

	/* restore floating point registers */
	ld      %f8, 0(%r15)
	ld      %f9, 8(%r15)
	ld      %f10, 16(%r15)
	ld      %f11, 24(%r15)
	ld      %f12, 32(%r15)
	ld      %f13, 40(%r15)
	ld      %f14, 48(%r15)
	ld      %f15, 56(%r15)

	MOVD F4, 248(R3)
	MOVD F5, 256(R3)
	MOVD F6, 264(R3)
	MOVD F7, 272(R3)
	MOVD F8, 280(R3)
	MOVD F9, 288(R3)
	MOVD F10, 296(R3)
	MOVD F11, 304(R3)
	MOVD F12, 312(R3)
	MOVD F13, 320(R3)
	MOVD F14, 328(R3)
	MOVD F15, 336(R3)
	MOVD F16, 344(R3)
	MOVD F17, 352(R3)
	MOVD F18, 360(R3)
	MOVD F19, 368(R3)
	MOVD F20, 376(R3)
	MOVD F21, 384(R3)
	MOVD F22, 392(R3)
	MOVD F23, 400(R3)
	MOVD F24, 408(R3)

	CMP     $0, R11
	BNE     skipfpsave
	MOVD	F8, (13*4+8*1)(R13)
	MOVD	F9, (13*4+8*2)(R13)
	MOVD	F10, (13*4+8*3)(R13)
	MOVD	F11, (13*4+8*4)(R13)
	MOVD	F12, (13*4+8*5)(R13)
	MOVD	F13, (13*4+8*6)(R13)
	MOVD	F14, (13*4+8*7)(R13)
	MOVD	F15, (13*4+8*8)(R13)

skipfpsave:
	BL	runtime·load_g(SB)
	// We set up the arguments to cgocallback when saving registers above.
	BL	runtime·cgocallback(SB)

	MOVD F8, 124(R13)
	MOVD F9, 132(R13)
	MOVD F10, 140(R13)
	MOVD F11, 148(R13)
	MOVD F12, 156(R13)
	MOVD F13, 164(R13)
	MOVD F14, 172(R13)
	MOVD F15, 180(R13)
nofp:
	CALL ·asyncPreempt2(SB)
	MOVB ·goarmsoftfp(SB), R0
	CMP $0, R0
	BNE nofp2
	MOVD 180(R13), F15
	MOVD 172(R13), F14
	MOVD 164(R13), F13
	MOVD 156(R13), F12
	MOVD 148(R13), F11
	MOVD 140(R13), F10
	MOVD 132(R13), F9
	MOVD 124(R13), F8

	MOVD F4, 240(X2)
	MOVD F5, 248(X2)
	MOVD F6, 256(X2)
	MOVD F7, 264(X2)
	MOVD F8, 272(X2)
	MOVD F9, 280(X2)
	MOVD F10, 288(X2)
	MOVD F11, 296(X2)
	MOVD F12, 304(X2)
	MOVD F13, 312(X2)
	MOVD F14, 320(X2)
	MOVD F15, 328(X2)
	MOVD F16, 336(X2)
	MOVD F17, 344(X2)
	MOVD F18, 352(X2)
	MOVD F19, 360(X2)
	MOVD F20, 368(X2)
	MOVD F21, 376(X2)
	MOVD F22, 384(X2)
	MOVD F23, 392(X2)
	MOVD F24, 400(X2)

//
// On PPC64/ELFv2 targets, the following registers are callee
// saved when called from C. They must be preserved before
// calling into Go which does not preserve any of them.
//
//	R14-R31
//	CR2-4
//	VR20-31
//	F14-F31
//
// xcoff(aix) and ELFv1 are similar, but may only require a
// subset of these.
//
// These macros assume a 16 byte aligned stack pointer. This
// is required by ELFv1, ELFv2, and AIX PPC64.

	MOVD	R22, 112(R1)
	MOVD	R23, 120(R1)
	MOVD	R24, 128(R1)
	MOVD	R25, 136(R1)
	MOVD	R26, 144(R1)
	MOVD	R27, 152(R1)
	MOVD	R28, 160(R1)
	MOVD	R29, 168(R1)
	MOVD	g, 176(R1) // R30
	MOVD	R31, 184(R1)
	FMOVD	F14, 192(R1)
	FMOVD	F15, 200(R1)
	FMOVD	F16, 208(R1)
	FMOVD	F17, 216(R1)
	FMOVD	F18, 224(R1)
	FMOVD	F19, 232(R1)
	FMOVD	F20, 240(R1)
	FMOVD	F21, 248(R1)
	FMOVD	F22, 256(R1)
	FMOVD	F23, 264(R1)

.endif
.endm

/*
 * void crosscall_ppc64(void (*fn)(void), void *g)
 *
 * Calling into the gc tool chain, where all registers are caller save.
 * Called from standard ppc64 C ABI, where r2, r14-r31, f14-f31 are
 * callee-save, so they must be saved explicitly.
 */
.globl crosscall_ppc64
crosscall_ppc64:
	// Start with standard C stack frame layout and linkage
	mflr	%r0
	std	%r0, 16(%r1)	// Save LR in caller's frame

.file "gcc_aix_ppc64.S"

/*
 * void crosscall_ppc64(void (*fn)(void), void *g)
 *
 * Calling into the gc tool chain, where all registers are caller save.
 * Called from standard ppc64 C ABI, where r2, r14-r31, f14-f31 are
 * callee-save, so they must be saved explicitly.
 * AIX has a special assembly syntax and keywords that can be mixed with
 * Linux assembly.
 */
  .toc
  .csect .text[PR]
  .globl crosscall_ppc64