sched: Fix cross-sched-class wakeup preemption

Instead of dealing with sched classes inside each check_preempt_curr()
implementation, pull out this logic into the generic wakeup preemption
path.

This fixes a hang in KVM (and others) where we are waiting for the
stop machine thread to run ...

Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Tested-by: Marcelo Tosatti <mtosatti@redhat.com>
Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1288891946.2039.31.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 27 insertions, 18 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 36a088018fe0..dc91a4d09ac3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -560,18 +560,8 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-	rq->curr->sched_class->check_preempt_curr(rq, p, 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.
-	 */
-	if (test_tsk_need_resched(p))
-		rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -2118,6 +2108,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+	const struct sched_class *class;
+
+	if (p->sched_class == rq->curr->sched_class) {
+		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+	} else {
+		for_each_class(class) {
+			if (class == rq->curr->sched_class)
+				break;
+			if (class == p->sched_class) {
+				resched_task(rq->curr);
+				break;
+			}
+		}
+	}
+
+	/*
+	 * A queue event has occurred, and we're going to schedule.  In
+	 * this case, we can save a useless back to back clock update.
+	 */
+	if (test_tsk_need_resched(rq->curr))
+		rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 034c4f410b36..52ab113d8bb9 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1654,12 +1654,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
-	if (unlikely(rt_prio(p->prio)))
-		goto preempt;
-
-	if (unlikely(p->sched_class != &fair_sched_class))
-		return;
-
 	if (unlikely(se == pse))
 		return;
 
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 755483b2a2ad..2bf6b47058c1 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,7 +19,7 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
 static void
 check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-	resched_task(rq->curr); /* we preempt everything */
+	/* we're never preempted */
 }
 
 static struct task_struct *pick_next_task_stop(struct rq *rq)