// Do this check last because it is more expensive and rarely true.
	// If it is false the expense doesn't matter since we are crashing.
	if inPersistentAlloc(uintptr(unsafe.Pointer(dst))) {
		return
	}

	systemstack(func() {
		println("write of unpinned Go pointer", hex(uintptr(src)), "to non-Go memory", hex(uintptr(unsafe.Pointer(dst))))
		throw(cgoWriteBarrierFail)
	})
}

// It's important that any use of gcWork during the mark phase prevent
// the garbage collector from transitioning to mark termination since
// gcWork may locally hold GC work buffers. This can be done by
// disabling preemption (systemstack or acquirem).
type gcWork struct {
	// wbuf1 and wbuf2 are the primary and secondary work buffers.
	//
	// This can be thought of as a stack of both work buffers'
	// pointers concatenated. When we pop the last pointer, we

	w, _ = w.ensure(1 + traceBytesPerNumber /* traceEvFrequency + frequency */)

	// Write out the string.
	w.byte(byte(traceEvFrequency))
	w.varint(traceClockUnitsPerSecond())

	// Immediately flush the buffer.
	systemstack(func() {
		lock(&trace.lock)
		traceBufFlush(w.traceBuf, gen)
		unlock(&trace.lock)
	})

	}
}

func TestTracebackSystemstack(t *testing.T) {
	if GOARCH == "ppc64" || GOARCH == "ppc64le" {
		t.Skip("systemstack tail call not implemented on ppc64x")
	}

	// Test that profiles correctly jump over systemstack,
	// including nested systemstack calls.
	pcs := make([]uintptr, 20)
	pcs = pcs[:TracebackSystemstack(pcs, 5)]
	// Check that runtime.TracebackSystemstack appears five times

		// systemstack which clobbers g.sched.
		save(pc, sp, bp)
	}
	if gp.syscallsp < gp.stack.lo || gp.stack.hi < gp.syscallsp {
		systemstack(func() {
			print("entersyscall inconsistent ", hex(gp.syscallsp), " [", hex(gp.stack.lo), ",", hex(gp.stack.hi), "]\n")
			throw("entersyscall")
		})
	}

	if trace.ok() {
		systemstack(func() {
			trace.GoSysCall()

	// switch to g0
	MOVD R2, g

	// call fn
	Get CTXT
	I32WrapI64
	I64Load $0
	CALL

	Get SP
	I32Const $8
	I32Add
	Set SP

	JMP runtime·badmcall2(SB)

// func systemstack(fn func())
TEXT runtime·systemstack(SB), NOSPLIT, $0-8
	// R0 = fn
	MOVD fn+0(FP), R0
	// R1 = g.m
	MOVD g_m(g), R1
	// R2 = g0
	MOVD m_g0(R1), R2

	// if g == g0
	Get g
	Get R2

	size uintptr   // total size of stacks in list
}

// dummy mspan that contains no free objects.
var emptymspan mspan

func allocmcache() *mcache {
	var c *mcache
	systemstack(func() {
		lock(&mheap_.lock)
		c = (*mcache)(mheap_.cachealloc.alloc())
		c.flushGen.Store(mheap_.sweepgen)
		unlock(&mheap_.lock)
	})
	for i := range c.alloc {
		c.alloc[i] = &emptymspan
	}

	MOVV	(g_sched+gobuf_sp)(g), R29	// sp = m->g0->sched.sp
	ADDV	$-16, R29
	MOVV	R1, 8(R29)
	MOVV	R0, 0(R29)
	JAL	(R4)
	JMP	runtime·badmcall2(SB)

// systemstack_switch is a dummy routine that systemstack leaves at the bottom
// of the G stack. We need to distinguish the routine that
// lives at the bottom of the G stack from the one that lives
// at the top of the system stack because the one at the top of

		// If the status was traced, nothing else to do.
		if gp.trace.statusWasTraced(gen) {
			return
		}
		// Scribble down information about this goroutine.
		ug := untracedG{gp: gp, mid: -1}
		systemstack(func() {
			me := getg().m.curg
			// We don't have to handle this G status transition because we
			// already eliminated ourselves from consideration above.

	// RDCYCLE reads counter that is per HART(core) based
	// according to the riscv manual, see issue 46737
	RDTIME	A0
	MOV	A0, ret+0(FP)
	RET

// systemstack_switch is a dummy routine that systemstack leaves at the bottom
// of the G stack. We need to distinguish the routine that
// lives at the bottom of the G stack from the one that lives
// at the top of the system stack because the one at the top of