MOVV	buf+0(FP), R4
	MOVV	gobuf_g(R4), R5
	MOVV	0(R5), R0	// make sure g != nil
	JMP	gogo<>(SB)

TEXT gogo<>(SB), NOSPLIT|NOFRAME, $0
	MOVV	R5, g
	JAL	runtime·save_g(SB)

	MOVV	gobuf_sp(R4), R3
	MOVV	gobuf_lr(R4), R1
	MOVV	gobuf_ret(R4), R19
	MOVV	gobuf_ctxt(R4), REGCTXT
	MOVV	R0, gobuf_sp(R4)
	MOVV	R0, gobuf_ret(R4)
	MOVV	R0, gobuf_lr(R4)
	MOVV	R0, gobuf_ctxt(R4)

	MOVW	buf+0(FP), R3
	MOVW	gobuf_g(R3), R4
	MOVW	0(R4), R5	// make sure g != nil
	JMP	gogo<>(SB)

TEXT gogo<>(SB),NOSPLIT|NOFRAME,$0
	MOVW	R4, g
	JAL	runtime·save_g(SB)
	MOVW	gobuf_sp(R3), R29
	MOVW	gobuf_lr(R3), R31
	MOVW	gobuf_ret(R3), R1
	MOVW	gobuf_ctxt(R3), REGCTXT
	MOVW	R0, gobuf_sp(R3)
	MOVW	R0, gobuf_ret(R3)
	MOVW	R0, gobuf_lr(R3)
	MOVW	R0, gobuf_ctxt(R3)
	MOVW	gobuf_pc(R3), R4

	BL	runtime·abort(SB)

	// Called from f.
	// Set m->morebuf to f's caller.
	MOVD	R5, (m_morebuf+gobuf_pc)(R7)	// f's caller's PC
	MOVD	R1, (m_morebuf+gobuf_sp)(R7)	// f's caller's SP
	MOVD	g, (m_morebuf+gobuf_g)(R7)

	// Call newstack on m->g0's stack.
	MOVD	m_g0(R7), g
	BL	runtime·save_g(SB)
	MOVD	(g_sched+gobuf_sp)(g), R1
	MOVDU   R0, -(FIXED_FRAME+0)(R1)	// create a call frame on g0
	BL	runtime·newstack(SB)

	MOVD	buf+0(FP), R5
	MOVD	gobuf_g(R5), R6
	MOVD	0(R6), R4	// make sure g != nil
	B	gogo<>(SB)

TEXT gogo<>(SB), NOSPLIT|NOFRAME, $0
	MOVD	R6, g
	BL	runtime·save_g(SB)

	MOVD	gobuf_sp(R5), R0
	MOVD	R0, RSP
	MOVD	gobuf_bp(R5), R29
	MOVD	gobuf_lr(R5), LR
	MOVD	gobuf_ret(R5), R0
	MOVD	gobuf_ctxt(R5), R26
	MOVD	$0, gobuf_sp(R5)
	MOVD	$0, gobuf_bp(R5)
	MOVD	$0, gobuf_ret(R5)

	MOVQ	(g_sched+gobuf_sp)(DX), SP

	// call target function
	MOVQ	DI, DX
	MOVQ	0(DI), DI
	CALL	DI

	// switch back to g
	get_tls(CX)
	MOVQ	g(CX), AX
	MOVQ	g_m(AX), BX
	MOVQ	m_curg(BX), AX
	MOVQ	AX, g(CX)
	MOVQ	(g_sched+gobuf_sp)(AX), SP
	MOVQ	(g_sched+gobuf_bp)(AX), BP
	MOVQ	$0, (g_sched+gobuf_sp)(AX)
	MOVQ	$0, (g_sched+gobuf_bp)(AX)
	RET

noswitch:

	MOVD	LR, R14
	MOVD	$ret-FIXED_FRAME(FP), R5 // caller's SP
	MOVD	R14, m_vdsoPC(R21)
	MOVD	R5, m_vdsoSP(R21)

	MOVD	m_curg(R21), R6
	CMP	g, R6
	BNE	noswitch

	MOVD	m_g0(R21), R7
	MOVD	(g_sched+gobuf_sp)(R7), R1	// Set SP to g0 stack

noswitch:
	SUB	$16, R1                 // Space for results
	RLDICR	$0, R1, $59, R1         // Align for C code
	MOVD	R12, CTR
	MOVD	R1, R4

	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