Workaround: do not set rq->skip_clock_update

Disabling the clock update seems to be causing problems even in normal
Linux, and causes major bugs under LITMUS^RT. As a workaround, just
disable this "optimization" for now.

Details: the idle load balancer causes tasks that suspsend to be
marked with set_tsk_need_resched(). When such a task resumes, it may
wrongly trigger the setting of skip_clock_update. However, a
corresponding rescheduling event may not happen immediately, such that
the currently-scheduled task is no longer charged for its execution
time.

1 files changed, 6 insertions, 0 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 60fbae0c747c..1b13c8e1cfc2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -578,8 +578,14 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
          * A queue event has occurred, and we're going to schedule.  In
          * this case, we can save a useless back to back clock update.
          */
+        /* LITMUS^RT: turning off the clock update is buggy in Linux 2.6.36;
+         * the scheduler can "forget" to renable the runqueue clock in some
+         * cases. LITMUS^RT amplifies the effects of this problem. Hence, we
+         * turn it off to avoid stalling clocks. */
+        /*
         if (test_tsk_need_resched(p))
                 rq->skip_clock_update = 1;
+        */
 }
 
 static inline int cpu_of(struct rq *rq)