runtime: fix writebarrier throw in lock_sema

The value in question is really a bit pattern
(a pointer with extra bits thrown in),
so treat it as a uintptr instead, avoiding the
generation of a write barrier when there
might not be a p.

Also add the obligatory //go:nowritebarrier.

Change-Id: I4ea097945dd7093a140f4740bcadca3ce7191971
Reviewed-on: https://go-review.googlesource.com/7667
Reviewed-by: Rick Hudson <rlh@golang.org>
Reviewed-by: Austin Clements <austin@google.com>

src/runtime/lock_sema.go

@@ -72,7 +72,7 @@ Loop:
 			// for this lock, chained through m->nextwaitm.
 			// Queue this M.
 			for {
-				gp.m.nextwaitm = (*m)((unsafe.Pointer)(v &^ locked))
+				gp.m.nextwaitm = v &^ locked
 				if casuintptr(&l.key, v, uintptr(unsafe.Pointer(gp.m))|locked) {
 					break
 				}
@@ -90,6 +90,8 @@ Loop:
 	}
 }
 
+//go:nowritebarrier
+// We might not be holding a p in this code.
 func unlock(l *mutex) {
 	gp := getg()
 	var mp *m
@@ -103,7 +105,7 @@ func unlock(l *mutex) {
 			// Other M's are waiting for the lock.
 			// Dequeue an M.
 			mp = (*m)((unsafe.Pointer)(v &^ locked))
-			if casuintptr(&l.key, v, uintptr(unsafe.Pointer(mp.nextwaitm))) {
+			if casuintptr(&l.key, v, mp.nextwaitm) {
 				// Dequeued an M.  Wake it.
 				semawakeup(mp)
 				break

src/runtime/runtime2.go

@@ -301,7 +301,7 @@ type m struct {
 	freghi        [16]uint32  // d[i] msb and f[i+16]
 	fflag         uint32      // floating point compare flags
 	locked        uint32      // tracking for lockosthread
-	nextwaitm     *m          // next m waiting for lock
+	nextwaitm     uintptr     // next m waiting for lock
 	waitsema      uintptr     // semaphore for parking on locks
 	waitsemacount uint32
 	waitsemalock  uint32