sched: Create special class for stop/migrate work

In order to separate the stop/migrate work thread from the SCHED_FIFO
implementation, create a special class for it that is of higher priority than
SCHED_FIFO itself.

This currently solves a problem where cpu-hotplug consumes so much cpu-time
that the SCHED_FIFO class gets throttled, but has the bandwidth replenishment
timer pending on the now dead cpu.

It is also required for when we add the planned deadline scheduling class above
SCHED_FIFO, as the stop/migrate thread still needs to transcent those tasks.

Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1285165776.2275.1022.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 45 insertions, 9 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 7f522832250c..5f64fed56a44 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -486,7 +486,7 @@ struct rq {
 	 */
 	unsigned long nr_uninterruptible;
 
-	struct task_struct *curr, *idle;
+	struct task_struct *curr, *idle, *stop;
 	unsigned long next_balance;
 	struct mm_struct *prev_mm;
 
@@ -1837,7 +1837,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 static const struct sched_class rt_sched_class;
 
-#define sched_class_highest (&rt_sched_class)
+#define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1917,10 +1917,41 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
 #endif
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+	if (stop) {
+		/*
+		 * Make it appear like a SCHED_FIFO task, its something
+		 * userspace knows about and won't get confused about.
+		 *
+		 * Also, it will make PI more or less work without too
+		 * much confusion -- but then, stop work should not
+		 * rely on PI working anyway.
+		 */
+		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+		stop->sched_class = &stop_sched_class;
+	}
+
+	cpu_rq(cpu)->stop = stop;
+
+	if (old_stop) {
+		/*
+		 * Reset it back to a normal scheduling class so that
+		 * it can die in pieces.
+		 */
+		old_stop->sched_class = &rt_sched_class;
+	}
+}
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -3720,17 +3751,13 @@ pick_next_task(struct rq *rq)
 			return p;
 	}
 
-	class = sched_class_highest;
-	for ( ; ; ) {
+	for_each_class(class) {
 		p = class->pick_next_task(rq);
 		if (p)
 			return p;
-		/*
-		 * Will never be NULL as the idle class always
-		 * returns a non-NULL p:
-		 */
-		class = class->next;
 	}
+
+	BUG(); /* the idle class will always have a runnable task */
 }
 
 /*
@@ -4659,6 +4686,15 @@ recheck:
 	 */
 	rq = __task_rq_lock(p);
 
+	/*
+	 * Changing the policy of the stop threads its a very bad idea
+	 */
+	if (p == rq->stop) {
+		__task_rq_unlock(rq);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		return -EINVAL;
+	}
+
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
 		/*