[PATCH] sched: run SCHED_NORMAL tasks with real time tasks on SMT siblings

The hyperthread aware nice handling currently puts to sleep any non real
time task when a real time task is running on its sibling cpu.  This can
lead to prolonged starvation by having the non real time task pegged to the
cpu with load balancing not pulling that task away.

Currently we force lower priority hyperthread tasks to run a percentage of
time difference based on timeslice differences which is meaningless when
comparing real time tasks to SCHED_NORMAL tasks.  We can allow non real
time tasks to run with real time tasks on the sibling up to per_cpu_gain%
if we use jiffies as a counter.

Cleanups and micro-optimisations to the relevant code section should make
it more understandable as well.

Signed-off-by: Con Kolivas <kernel@kolivas.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

kernel/sched.c

@@ -2580,6 +2580,13 @@ out:
 }
 
 #ifdef CONFIG_SCHED_SMT
+static inline void wakeup_busy_runqueue(runqueue_t *rq)
+{
+	/* If an SMT runqueue is sleeping due to priority reasons wake it up */
+	if (rq->curr == rq->idle && rq->nr_running)
+		resched_task(rq->idle);
+}
+
 static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
 {
 	struct sched_domain *tmp, *sd = NULL;
@@ -2613,12 +2620,7 @@ static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
 	for_each_cpu_mask(i, sibling_map) {
 		runqueue_t *smt_rq = cpu_rq(i);
 
-		/*
+		wakeup_busy_runqueue(smt_rq);
-		 * If an SMT sibling task is sleeping due to priority
-		 * reasons wake it up now.
-		 */
-		if (smt_rq->curr == smt_rq->idle && smt_rq->nr_running)
-			resched_task(smt_rq->idle);
 	}
 
 	for_each_cpu_mask(i, sibling_map)
@@ -2672,6 +2674,10 @@ static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
 		runqueue_t *smt_rq = cpu_rq(i);
 		task_t *smt_curr = smt_rq->curr;
 
+		/* Kernel threads do not participate in dependent sleeping */
+		if (!p->mm || !smt_curr->mm || rt_task(p))
+			goto check_smt_task;
+
 		/*
 		 * If a user task with lower static priority than the
 		 * running task on the SMT sibling is trying to schedule,
@@ -2680,21 +2686,44 @@ static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
 		 * task from using an unfair proportion of the
 		 * physical cpu's resources. -ck
 		 */
-		if (((smt_curr->time_slice * (100 - sd->per_cpu_gain) / 100) >
+		if (rt_task(smt_curr)) {
-			task_timeslice(p) || rt_task(smt_curr)) &&
+			/*
-			p->mm && smt_curr->mm && !rt_task(p))
+			 * With real time tasks we run non-rt tasks only
+			 * per_cpu_gain% of the time.
+			 */
+			if ((jiffies % DEF_TIMESLICE) >
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
+					ret = 1;
+		} else
+			if (((smt_curr->time_slice * (100 - sd->per_cpu_gain) /
+				100) > task_timeslice(p)))
 					ret = 1;
 
+check_smt_task:
+		if ((!smt_curr->mm && smt_curr != smt_rq->idle) ||
+			rt_task(smt_curr))
+				continue;
+		if (!p->mm) {
+			wakeup_busy_runqueue(smt_rq);
+			continue;
+		}
+
 		/*
-		 * Reschedule a lower priority task on the SMT sibling,
+		 * Reschedule a lower priority task on the SMT sibling for
-		 * or wake it up if it has been put to sleep for priority
+		 * it to be put to sleep, or wake it up if it has been put to
-		 * reasons.
+		 * sleep for priority reasons to see if it should run now.
 		 */
-		if ((((p->time_slice * (100 - sd->per_cpu_gain) / 100) >
+		if (rt_task(p)) {
-			task_timeslice(smt_curr) || rt_task(p)) &&
+			if ((jiffies % DEF_TIMESLICE) >
-			smt_curr->mm && p->mm && !rt_task(smt_curr)) ||
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
-			(smt_curr == smt_rq->idle && smt_rq->nr_running))
 					resched_task(smt_curr);
+		} else {
+			if ((p->time_slice * (100 - sd->per_cpu_gain) / 100) >
+				task_timeslice(smt_curr))
+					resched_task(smt_curr);
+			else
+				wakeup_busy_runqueue(smt_rq);
+		}
 	}
 out_unlock:
 	for_each_cpu_mask(i, sibling_map)