diff --git a/src/runtime/mgc.go b/src/runtime/mgc.go
index 8ed8c57362..bf916f841d 100644
--- a/src/runtime/mgc.go
+++ b/src/runtime/mgc.go
@@ -261,10 +261,22 @@ func startGC(mode int) {
 	if !bggc.started {
 		bggc.working = 1
 		bggc.started = true
+		// This puts the G on the end of the current run
+		// queue, so it may take a while to actually start.
+		// This is only a problem for the first GC cycle.
 		go backgroundgc()
 	} else if bggc.working == 0 {
 		bggc.working = 1
-		ready(bggc.g, 0)
+		if getg().m.lockedg != nil {
+			// We can't directly switch to GC on a locked
+			// M, so put it on the run queue and someone
+			// will get to it.
+			ready(bggc.g, 0)
+		} else {
+			unlock(&bggc.lock)
+			readyExecute(bggc.g, 0)
+			return
+		}
 	}
 	unlock(&bggc.lock)
 }
@@ -299,6 +311,13 @@ func gc(mode int) {
 	semacquire(&worldsema, false)
 
 	// Pick up the remaining unswept/not being swept spans concurrently
+	//
+	// TODO(austin): If the last GC cycle shrank the heap, our 1:1
+	// sweeping rule will undershoot and we'll wind up doing
+	// sweeping here, which will allow the mutator to do more
+	// allocation than we intended before we "really" start GC.
+	// Compute an allocation sweep ratio so we're done sweeping by
+	// the time we hit next_gc.
 	for gosweepone() != ^uintptr(0) {
 		sweep.nbgsweep++
 	}
diff --git a/src/runtime/proc1.go b/src/runtime/proc1.go
index 954d242b5f..65f83e2caa 100644
--- a/src/runtime/proc1.go
+++ b/src/runtime/proc1.go
@@ -155,6 +155,37 @@ func ready(gp *g, traceskip int) {
 	}
 }
 
+// readyExecute marks gp ready to run, preempt the current g, and execute gp.
+// This is used to start concurrent GC promptly when we reach its trigger.
+func readyExecute(gp *g, traceskip int) {
+	mcall(func(_g_ *g) {
+		if trace.enabled {
+			traceGoUnpark(gp, traceskip)
+			traceGoSched()
+		}
+
+		if _g_.m.locks != 0 {
+			throw("readyExecute: holding locks")
+		}
+		if _g_.m.lockedg != nil {
+			throw("cannot readyExecute from a locked g")
+		}
+		if readgstatus(gp)&^_Gscan != _Gwaiting {
+			dumpgstatus(gp)
+			throw("bad gp.status in readyExecute")
+		}
+
+		// Preempt the current g
+		casgstatus(_g_, _Grunning, _Grunnable)
+		runqput(_g_.m.p, _g_)
+		dropg()
+
+		// Ready gp and switch to it
+		casgstatus(gp, _Gwaiting, _Grunnable)
+		execute(gp)
+	})
+}
+
 func gcprocs() int32 {
 	// Figure out how many CPUs to use during GC.
 	// Limited by gomaxprocs, number of actual CPUs, and MaxGcproc.