runtime: implement async scheduler preemption

This adds signal-based preemption to preemptone.

Since STW and forEachP ultimately use preemptone, this also makes
these work with async preemption.

This also makes freezetheworld more robust so tracebacks from fatal
panics should be far less likely to report "goroutine running on other
thread; stack unavailable".

For #10958, #24543. (This doesn't fix it yet because asynchronous
preemption only works on POSIX platforms on 386 and amd64 right now.)

Change-Id: If776181dd5a9b3026a7b89a1b5266521b95a5f61
Reviewed-on: https://go-review.googlesource.com/c/go/+/201762
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

src/runtime/preempt.go

@@ -282,7 +282,11 @@ func asyncPreempt()
 func asyncPreempt2() {
 	gp := getg()
 	gp.asyncSafePoint = true
+	if gp.preemptStop {
 		mcall(preemptPark)
+	} else {
+		mcall(gopreempt_m)
+	}
 	gp.asyncSafePoint = false
 }
 
@@ -316,7 +320,8 @@ func init() {
 // wantAsyncPreempt returns whether an asynchronous preemption is
 // queued for gp.
 func wantAsyncPreempt(gp *g) bool {
-	return gp.preemptStop && readgstatus(gp)&^_Gscan == _Grunning
+	// Check both the G and the P.
+	return (gp.preempt || gp.m.p != 0 && gp.m.p.ptr().preempt) && readgstatus(gp)&^_Gscan == _Grunning
 }
 
 // isAsyncSafePoint reports whether gp at instruction PC is an

src/runtime/proc.go

@@ -2487,11 +2487,13 @@ func schedule() {
 	}
 
 top:
+	pp := _g_.m.p.ptr()
+	pp.preempt = false
+
 	if sched.gcwaiting != 0 {
 		gcstopm()
 		goto top
 	}
-	pp := _g_.m.p.ptr()
 	if pp.runSafePointFn != 0 {
 		runSafePointFn()
 	}
@@ -4654,6 +4656,13 @@ func preemptone(_p_ *p) bool {
 	// Setting gp->stackguard0 to StackPreempt folds
 	// preemption into the normal stack overflow check.
 	gp.stackguard0 = stackPreempt
+
+	// Request an async preemption of this P.
+	if preemptMSupported && debug.asyncpreemptoff == 0 {
+		_p_.preempt = true
+		preemptM(mp)
+	}
+
 	return true
 }
 

src/runtime/runtime2.go

@@ -642,6 +642,10 @@ type p struct {
 	// Race context used while executing timer functions.
 	timerRaceCtx uintptr
 
+	// preempt is set to indicate that this P should be enter the
+	// scheduler ASAP (regardless of what G is running on it).
+	preempt bool
+
 	pad cpu.CacheLinePad
 }