// Prepare for entry to Go.
	BL	runtime·load_g(SB)

	// Call cgocallback, which will call callbackWrap(frame).
	MOVW	$0, R0
	MOVW	R0, 12(R13)	// context
	MOVW	$16(R13), R1	// R1 = &callbackArgs{...}
	MOVW	R1, 8(R13)	// frame (address of callbackArgs)
	MOVW	$·callbackWrap(SB), R1
	MOVW	R1, 4(R13)	// PC of function to call
	BL	runtime·cgocallback(SB)

	// Get callback result.

	I64Const $8
	Call	gcWriteBarrier<>(SB)
	Return
TEXT runtime·gcWriteBarrier2<ABIInternal>(SB),NOSPLIT,$0
	I64Const $16
	Call	gcWriteBarrier<>(SB)
	Return
TEXT runtime·gcWriteBarrier3<ABIInternal>(SB),NOSPLIT,$0
	I64Const $24
	Call	gcWriteBarrier<>(SB)
	Return
TEXT runtime·gcWriteBarrier4<ABIInternal>(SB),NOSPLIT,$0
	I64Const $32
	Call	gcWriteBarrier<>(SB)
	Return

		pcBuf[0] = uintptr(skip)
		if getg() == gp {
			nstk += fpTracebackPCs(unsafe.Pointer(getfp()), pcBuf[1:])
		} else if gp != nil {
			// Three cases:
			//
			// (1) We're called on the g0 stack through mcall(fn) or systemstack(fn). To
			// behave like gcallers above, we start unwinding from sched.bp, which
			// points to the caller frame of the leaf frame on g's stack. The return

	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

// C->Go callback thunk that allows to call runtime·racesymbolize from C code.

	MOVD	16(R1), R10		// LR was saved away, restore for return
	MOVD	R10, LR
	RET

// C->Go callback thunk that allows to call runtime·racesymbolize from C code.
// Direct Go->C race call has only switched SP, finish g->g0 switch by setting correct g.
// The overall effect of Go->C->Go call chain is similar to that of mcall.
// RARG0 contains command code. RARG1 contains command-specific context.
// See racecallback for command codes.

	SUB	$16, RSP
	BL	R9
	MOVD	R19, RSP
	JMP	(R20)

// C->Go callback thunk that allows to call runtime·racesymbolize from C code.
// Direct Go->C race call has only switched SP, finish g->g0 switch by setting correct g.
// The overall effect of Go->C->Go call chain is similar to that of mcall.
// R0 contains command code. R1 contains command-specific context.
// See racecallback for command codes.

(where to execute it), and a P (the rights and resources to execute
it). When an M stops executing user Go code, for example by entering a
system call, it returns its P to the idle P pool. In order to resume
executing user Go code, for example on return from a system call, it
must acquire a P from the idle pool.

All `g`, `m`, and `p` objects are heap allocated, but are never freed,

// so that we can set up g0.sched to return to the call of mstart1 above.
//
//go:noinline
func mstart1() {
	gp := getg()

	if gp != gp.m.g0 {
		throw("bad runtime·mstart")
	}

	// Set up m.g0.sched as a label returning to just
	// after the mstart1 call in mstart0 above, for use by goexit0 and mcall.
	// We're never coming back to mstart1 after we call schedule,

	JMP	(R4)

// void mcall(fn func(*g))
// Switch to m->g0's stack, call fn(g).
// Fn must never return. It should gogo(&g->sched)
// to keep running g.
TEXT runtime·mcall(SB), NOSPLIT|NOFRAME, $0-8
	// Save caller state in g->sched
	MOVV	R29, (g_sched+gobuf_sp)(g)
	MOVV	R31, (g_sched+gobuf_pc)(g)
	MOVV	R0, (g_sched+gobuf_lr)(g)

	// Switch to m->g0 & its stack, call fn.
	MOVV	g, R1
	MOVV	g_m(g), R3

	// save m0 to g0->m
	MOV	T0, g_m(g)

	CALL	runtime·check(SB)

	// args are already prepared
	CALL	runtime·args(SB)
	CALL	runtime·osinit(SB)
	CALL	runtime·schedinit(SB)

	// create a new goroutine to start program
	MOV	$runtime·mainPC(SB), T0		// entry
	SUB	$16, X2
	MOV	T0, 8(X2)
	MOV	ZERO, 0(X2)
	CALL	runtime·newproc(SB)
	ADD	$16, X2

	// start this M
	CALL	runtime·mstart(SB)

	WORD $0 // crash if reached