2. When mmu mapping for a shared segment is changed, procflushseg
is called to wait for other cpus to change their mapping.  The
loop contains a sched() call which could return on a different cpu,
and therefore cause some cpus in the list to be skipped

Reference: /n/sources/patch/proc-smp-fixes
Date: Tue Apr 19 13:42:06 CES 2016
Signed-off-by: miller@hamnavoe.com

--- /sys/src/9/port/proc.c	Tue Apr 19 13:28:33 2016
+++ /sys/src/9/port/proc.c	Tue Apr 19 13:42:26 2016
@@ -1299,7 +1297,7 @@
 
 /*
  *  wait till all processes have flushed their mmu
- *  state about segement s
+ *  state about segment s
  */
 void
 procflushseg(Segment *s)
@@ -1336,10 +1334,13 @@
 	 *  wait for all processors to take a clock interrupt
 	 *  and flush their mmu's
 	 */
-	for(nm = 0; nm < conf.nmach; nm++)
-		if(MACHP(nm) != m)
-			while(MACHP(nm)->flushmmu)
-				sched();
+again:
+	for(nm = 0; nm < conf.nmach; nm++){
+		if(nm != m->machno && MACHP(nm)->flushmmu){
+			sched();
+			goto again;
+		}
+	}
 }
 
 void