[Xen-devel] [PATCH 1 of 3] xen: Fix schedule's grabbing of the schedule lock

[George Dunlap <george.dunlap@xxxxxxxxxxxxx>]

Because the location of the lock can change between the time you read
it and the time you grab it, the per-cpu schedule locks need to check
after lock acquisition that the lock location hasn't changed, and
release and re-try if so.  This change was effected throughout the
source code, but one very important place was apparently missed: in
schedule() itself.

Signed-off-by: George Dunlap <george.dunlap@xxxxxxxxxxxxx>

diff -r 197e09bf0322 -r fd0d2fd2824b xen/common/schedule.c
--- a/xen/common/schedule.c     Wed Apr 04 11:29:43 2012 +0100
+++ b/xen/common/schedule.c     Thu Apr 05 12:20:04 2012 +0100
@@ -1075,6 +1075,7 @@ static void schedule(void)
     bool_t                tasklet_work_scheduled = 0;
     struct schedule_data *sd;
     struct task_slice     next_slice;
+    int cpu = smp_processor_id();
 
     ASSERT(!in_atomic());
 
@@ -1099,7 +1100,7 @@ static void schedule(void)
         BUG();
     }
 
-    spin_lock_irq(sd->schedule_lock);
+    pcpu_schedule_lock_irq(cpu);
 
     stop_timer(&sd->s_timer);
     
@@ -1116,7 +1117,7 @@ static void schedule(void)
 
     if ( unlikely(prev == next) )
     {
-        spin_unlock_irq(sd->schedule_lock);
+        pcpu_schedule_unlock_irq(cpu);
         trace_continue_running(next);
         return continue_running(prev);
     }
@@ -1154,7 +1155,7 @@ static void schedule(void)
     ASSERT(!next->is_running);
     next->is_running = 1;
 
-    spin_unlock_irq(sd->schedule_lock);
+    pcpu_schedule_unlock_irq(cpu);
 
     perfc_incr(sched_ctx);
 

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel