BL	runtime·save_g(SB)		// Save g for callbacks.
	MOVD	R15, R7				// Save SP.
	MOVD	g_m(g), R8			// R8 = thread.
	MOVD	m_g0(R8), R8			// R8 = g0.
	CMPBEQ	R8, g, call			// Already on g0?
	MOVD	(g_sched+gobuf_sp)(R8), R15	// Switch SP to g0.
call:	SUB	$160, R15			// Allocate C frame.
	BL	R1				// Call C code.
	MOVD	R7, R15				// Restore SP.
	RET					// Return to Go.

	MOVQ	g_m(R14), R13
	// Switch to g0 stack.
	MOVQ	SP, R12		// callee-saved, preserved across the CALL
	MOVQ	m_g0(R13), R10
	CMPQ	R10, R14
	JE	call	// already on g0
	MOVQ	(g_sched+gobuf_sp)(R10), SP
call:
	ANDQ	$~15, SP	// alignment for gcc ABI
	CALL	AX
	MOVQ	R12, SP
	// Back to Go world, set special registers.
	// The g register (R14) is preserved in C.
	XORPS	X15, X15
	RET

	// Switch to g0 stack.
	MOVD	RSP, R19	// callee-saved, preserved across the CALL
	MOVD	R30, R20	// callee-saved, preserved across the CALL
	MOVD	m_g0(R10), R11
	CMP	R11, g
	BEQ	call	// already on g0
	MOVD	(g_sched+gobuf_sp)(R11), R12
	MOVD	R12, RSP
call:
	// Decrement SP past where the frame pointer is saved in the Go arm64
	// ABI (one word below the stack pointer) so the race detector library
	// code doesn't clobber it

	MOVD    0(R10), g
	MOVD	g_m(g), R7		// m for g
	MOVD	R1, R16			// callee-saved, preserved across C call
	MOVD	m_g0(R7), R10		// g0 for m
	CMP	R10, g			// same g0?
	BEQ	call			// already on g0
	MOVD	(g_sched+gobuf_sp)(R10), R1 // switch R1
call:
	// prepare frame for C ABI
	SUB	$32, R1			// create frame for callee saving LR, CR, R2 etc.
	RLDCR   $0, R1, $~15, R1	// align SP to 16 bytes
	MOVD	R8, CTR			// R8 = caller addr