runtime: cache workbufs on Ms and add consistency checks

Add local workbufs to the m struct in order to reduce contention.
Add consistency checks for workbuf ownership.
Chain workbufs through call change to avoid swapping them
to and from the m struct.
Adjust the size of the workbuf so that the mutators can
more frequently pass modifications to the GC thus shifting
some work from the STW mark termination phase to the concurrent
mark phase.

Change-Id: I557b53af34ad9972265e0ed9f5996e52d548563d
Reviewed-on: https://go-review.googlesource.com/3972Reviewed-by: Austin Clements <austin@google.com>

src/runtime/malloc.go

@@ -312,6 +312,7 @@ func profilealloc(mp *m, x unsafe.Pointer, size uintptr) {
 
 // For now this must be bracketed with a stoptheworld and a starttheworld to ensure
 // all go routines see the new barrier.
+//go:nowritebarrier
 func gcinstallmarkwb() {
 	gcphase = _GCmark
 }
@@ -389,6 +390,7 @@ func gcwork(force int32) {
 		gctimer.cycle.installmarkwb = nanotime()
 		systemstack(stoptheworld)
 		systemstack(gcinstallmarkwb)
+		systemstack(harvestwbufs)
 		systemstack(starttheworld)
 		gctimer.cycle.mark = nanotime()
 		systemstack(gcmark_m)

src/runtime/runtime2.go

@@ -274,6 +274,7 @@ type m struct {
 	waitsemacount uint32
 	waitsemalock  uint32
 	gcstats       gcstats
+	currentwbuf   uintptr // use locks or atomic operations such as xchguinptr to access.
 	needextram    bool
 	traceback     uint8
 	waitunlockf   unsafe.Pointer // todo go func(*g, unsafe.pointer) bool