runtime: abstract initializing and destroying Ps out of procresize

procresize is rather ungainly because it includes all of the code to
initialize new Ps and tear down unused Ps. Pull these out into their
own methods on the p type. This also tweaks the initialization loop in
procresize so we only initialize new Ps (and Ps we previously
destroyed) rather than asking each P "have you been initialized?"

This is for #10958 and #24543, but it's also just a nice cleanup.

Change-Id: Ic1242066f572c94a23cea8ea4dc47c918e31d559
Reviewed-on: https://go-review.googlesource.com/c/go/+/171762Reviewed-by: Michael Knyszek <mknyszek@google.com>

src/runtime/proc.go

@@ -3881,6 +3881,92 @@ func setcpuprofilerate(hz int32) {
 	_g_.m.locks--
 }
 
+// init initializes pp, which may be a freshly allocated p or a
+// previously destroyed p, and transitions it to status _Pgcstop.
+func (pp *p) init(id int32) {
+	pp.id = id
+	pp.status = _Pgcstop
+	pp.sudogcache = pp.sudogbuf[:0]
+	for i := range pp.deferpool {
+		pp.deferpool[i] = pp.deferpoolbuf[i][:0]
+	}
+	pp.wbBuf.reset()
+	if pp.mcache == nil {
+		if id == 0 {
+			if getg().m.mcache == nil {
+				throw("missing mcache?")
+			}
+			pp.mcache = getg().m.mcache // bootstrap
+		} else {
+			pp.mcache = allocmcache()
+		}
+	}
+	if raceenabled && pp.raceprocctx == 0 {
+		if id == 0 {
+			pp.raceprocctx = raceprocctx0
+			raceprocctx0 = 0 // bootstrap
+		} else {
+			pp.raceprocctx = raceproccreate()
+		}
+	}
+}
+
+// destroy releases all of the resources associated with pp and
+// transitions it to status _Pdead.
+//
+// sched.lock must be held and the world must be stopped.
+func (pp *p) destroy() {
+	// Move all runnable goroutines to the global queue
+	for pp.runqhead != pp.runqtail {
+		// Pop from tail of local queue
+		pp.runqtail--
+		gp := pp.runq[pp.runqtail%uint32(len(pp.runq))].ptr()
+		// Push onto head of global queue
+		globrunqputhead(gp)
+	}
+	if pp.runnext != 0 {
+		globrunqputhead(pp.runnext.ptr())
+		pp.runnext = 0
+	}
+	// If there's a background worker, make it runnable and put
+	// it on the global queue so it can clean itself up.
+	if gp := pp.gcBgMarkWorker.ptr(); gp != nil {
+		casgstatus(gp, _Gwaiting, _Grunnable)
+		if trace.enabled {
+			traceGoUnpark(gp, 0)
+		}
+		globrunqput(gp)
+		// This assignment doesn't race because the
+		// world is stopped.
+		pp.gcBgMarkWorker.set(nil)
+	}
+	// Flush p's write barrier buffer.
+	if gcphase != _GCoff {
+		wbBufFlush1(pp)
+		pp.gcw.dispose()
+	}
+	for i := range pp.sudogbuf {
+		pp.sudogbuf[i] = nil
+	}
+	pp.sudogcache = pp.sudogbuf[:0]
+	for i := range pp.deferpool {
+		for j := range pp.deferpoolbuf[i] {
+			pp.deferpoolbuf[i][j] = nil
+		}
+		pp.deferpool[i] = pp.deferpoolbuf[i][:0]
+	}
+	freemcache(pp.mcache)
+	pp.mcache = nil
+	gfpurge(pp)
+	traceProcFree(pp)
+	if raceenabled {
+		raceprocdestroy(pp.raceprocctx)
+		pp.raceprocctx = 0
+	}
+	pp.gcAssistTime = 0
+	pp.status = _Pdead
+}
+
 // Change number of processors. The world is stopped, sched is locked.
 // gcworkbufs are not being modified by either the GC or
 // the write barrier code.
@@ -3919,40 +4005,16 @@ func procresize(nprocs int32) *p {
 	}
 
 	// initialize new P's
-	for i := int32(0); i < nprocs; i++ {
+	for i := old; i < nprocs; i++ {
 		pp := allp[i]
 		if pp == nil {
 			pp = new(p)
-			pp.id = i
-			pp.status = _Pgcstop
-			pp.sudogcache = pp.sudogbuf[:0]
-			for i := range pp.deferpool {
-				pp.deferpool[i] = pp.deferpoolbuf[i][:0]
-			}
-			pp.wbBuf.reset()
-			atomicstorep(unsafe.Pointer(&allp[i]), unsafe.Pointer(pp))
-		}
-		if pp.mcache == nil {
-			if old == 0 && i == 0 {
-				if getg().m.mcache == nil {
-					throw("missing mcache?")
-				}
-				pp.mcache = getg().m.mcache // bootstrap
-			} else {
-				pp.mcache = allocmcache()
-			}
-		}
-		if raceenabled && pp.raceprocctx == 0 {
-			if old == 0 && i == 0 {
-				pp.raceprocctx = raceprocctx0
-				raceprocctx0 = 0 // bootstrap
-			} else {
-				pp.raceprocctx = raceproccreate()
-			}
 		}
+		pp.init(i)
+		atomicstorep(unsafe.Pointer(&allp[i]), unsafe.Pointer(pp))
 	}
 
-	// free unused P's
+	// release resources from unused P's
 	for i := nprocs; i < old; i++ {
 		p := allp[i]
 		if trace.enabled && p == getg().m.p.ptr() {
@@ -3961,55 +4023,7 @@ func procresize(nprocs int32) *p {
 			traceGoSched()
 			traceProcStop(p)
 		}
-		// move all runnable goroutines to the global queue
-		for p.runqhead != p.runqtail {
-			// pop from tail of local queue
-			p.runqtail--
-			gp := p.runq[p.runqtail%uint32(len(p.runq))].ptr()
-			// push onto head of global queue
-			globrunqputhead(gp)
-		}
-		if p.runnext != 0 {
-			globrunqputhead(p.runnext.ptr())
-			p.runnext = 0
-		}
-		// if there's a background worker, make it runnable and put
-		// it on the global queue so it can clean itself up
-		if gp := p.gcBgMarkWorker.ptr(); gp != nil {
-			casgstatus(gp, _Gwaiting, _Grunnable)
-			if trace.enabled {
-				traceGoUnpark(gp, 0)
-			}
-			globrunqput(gp)
-			// This assignment doesn't race because the
-			// world is stopped.
-			p.gcBgMarkWorker.set(nil)
-		}
-		// Flush p's write barrier buffer.
-		if gcphase != _GCoff {
-			wbBufFlush1(p)
-			p.gcw.dispose()
-		}
-		for i := range p.sudogbuf {
-			p.sudogbuf[i] = nil
-		}
-		p.sudogcache = p.sudogbuf[:0]
-		for i := range p.deferpool {
-			for j := range p.deferpoolbuf[i] {
-				p.deferpoolbuf[i][j] = nil
-			}
-			p.deferpool[i] = p.deferpoolbuf[i][:0]
-		}
-		freemcache(p.mcache)
-		p.mcache = nil
-		gfpurge(p)
-		traceProcFree(p)
-		if raceenabled {
-			raceprocdestroy(p.raceprocctx)
-			p.raceprocctx = 0
-		}
-		p.gcAssistTime = 0
-		p.status = _Pdead
+		p.destroy()
 		// can't free P itself because it can be referenced by an M in syscall
 	}