runtime: fix traceback from goexit1

We used to not call traceback from goexit1.
But now tracer does it and crashes on amd64p32:

runtime: unexpected return pc for runtime.getg called from 0x108a4240
goroutine 18 [runnable, locked to thread]:
runtime.traceGoEnd()
    src/runtime/trace.go:758 fp=0x10818fe0 sp=0x10818fdc
runtime.goexit1()
    src/runtime/proc1.go:1540 +0x20 fp=0x10818fe8 sp=0x10818fe0
runtime.getg(0x0)
    src/runtime/asm_386.s:2414 fp=0x10818fec sp=0x10818fe8
created by runtime/pprof_test.TestTraceStress
    src/runtime/pprof/trace_test.go:123 +0x500

Return PC from goexit1 points right after goexit (+0x6).
It happens to work most of the time somehow.

This change fixes traceback from goexit1 by adding an additional NOP to goexit.

Fixes #9931

Change-Id: Ied25240a181b0a2d7bc98127b3ed9068e9a1a13e
Reviewed-on: https://go-review.googlesource.com/5460Reviewed-by: Russ Cox <rsc@golang.org>

src/runtime/asm_386.s

@@ -2422,6 +2422,8 @@ TEXT _cgo_topofstack(SB),NOSPLIT,$0
 TEXT runtime·goexit(SB),NOSPLIT,$0-0
 	BYTE	$0x90	// NOP
 	CALL	runtime·goexit1(SB)	// does not return
+	// traceback from goexit1 must hit code range of goexit
+	BYTE	$0x90	// NOP
 
 TEXT runtime·getg(SB),NOSPLIT,$0-4
 	get_tls(CX)

src/runtime/asm_amd64.s

@@ -2457,6 +2457,8 @@ TEXT _cgo_topofstack(SB),NOSPLIT,$0
 TEXT runtime·goexit(SB),NOSPLIT,$0-0
 	BYTE	$0x90	// NOP
 	CALL	runtime·goexit1(SB)	// does not return
+	// traceback from goexit1 must hit code range of goexit
+	BYTE	$0x90	// NOP
 
 TEXT runtime·getg(SB),NOSPLIT,$0-8
 	get_tls(CX)

src/runtime/asm_amd64p32.s

@@ -1085,6 +1085,8 @@ TEXT runtime·return0(SB), NOSPLIT, $0
 TEXT runtime·goexit(SB),NOSPLIT,$0-0
 	BYTE	$0x90	// NOP
 	CALL	runtime·goexit1(SB)	// does not return
+	// traceback from goexit1 must hit code range of goexit
+	BYTE	$0x90	// NOP
 
 TEXT runtime·getg(SB),NOSPLIT,$0-4
 	get_tls(CX)

src/runtime/asm_arm.s

@@ -1338,6 +1338,8 @@ TEXT _cgo_topofstack(SB),NOSPLIT,$8
 TEXT runtime·goexit(SB),NOSPLIT,$-4-0
 	MOVW	R0, R0	// NOP
 	BL	runtime·goexit1(SB)	// does not return
+	// traceback from goexit1 must hit code range of goexit
+	MOVW	R0, R0	// NOP
 
 TEXT runtime·getg(SB),NOSPLIT,$-4-4
 	MOVW	g, ret+0(FP)

src/runtime/asm_ppc64x.s

@@ -1241,6 +1241,8 @@ TEXT _cgo_topofstack(SB),NOSPLIT,$-8
 TEXT runtime·goexit(SB),NOSPLIT,$-8-0
 	MOVD	R0, R0	// NOP
 	BL	runtime·goexit1(SB)	// does not return
+	// traceback from goexit1 must hit code range of goexit
+	MOVD	R0, R0	// NOP
 
 TEXT runtime·getg(SB),NOSPLIT,$-8-8
 	MOVD	g, ret+0(FP)

src/runtime/proc1.go

@@ -1553,8 +1553,6 @@ func gopreempt_m(gp *g) {
 }
 
 // Finishes execution of the current goroutine.
-// Must be NOSPLIT because it is called from Go. (TODO - probably not anymore)
-//go:nosplit
 func goexit1() {
 	if raceenabled {
 		racegoend()