Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

1 files changed, 87 insertions, 32 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7b4f4fbbb404..8c9ed9664840 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -3,12 +3,8 @@
  * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
  * policies)
  */
-#include "sched.h"
-
-#include "pelt.h"
 
 int sched_rr_timeslice = RR_TIMESLICE;
-int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
@@ -16,6 +12,57 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
 struct rt_bandwidth def_rt_bandwidth;
 
+/*
+ * period over which we measure -rt task CPU usage in us.
+ * default: 1s
+ */
+unsigned int sysctl_sched_rt_period = 1000000;
+
+/*
+ * part of the period that we allow rt tasks to run in us.
+ * default: 0.95s
+ */
+int sysctl_sched_rt_runtime = 950000;
+
+#ifdef CONFIG_SYSCTL
+static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+static struct ctl_table sched_rt_sysctls[] = {
+	{
+		.procname       = "sched_rt_period_us",
+		.data           = &sysctl_sched_rt_period,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{
+		.procname       = "sched_rt_runtime_us",
+		.data           = &sysctl_sched_rt_runtime,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{
+		.procname       = "sched_rr_timeslice_ms",
+		.data           = &sysctl_sched_rr_timeslice,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rr_handler,
+	},
+	{}
+};
+
+static int __init sched_rt_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_rt_sysctls);
+	return 0;
+}
+late_initcall(sched_rt_sysctl_init);
+#endif
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -271,8 +318,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
 #ifdef CONFIG_SMP
 
-static void pull_rt_task(struct rq *this_rq);
-
 static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
@@ -429,15 +474,6 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
-static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_rt_task(struct rq *this_rq)
-{
-}
-
 static inline void rt_queue_push_tasks(struct rq *rq)
 {
 }
@@ -885,6 +921,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+		struct rq_flags rf;
 		int skip;
 
 		/*
@@ -899,7 +936,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		if (skip)
 			continue;
 
-		raw_spin_rq_lock(rq);
+		rq_lock(rq, &rf);
 		update_rq_clock(rq);
 
 		if (rt_rq->rt_time) {
@@ -937,7 +974,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
-		raw_spin_rq_unlock(rq);
+		rq_unlock(rq, &rf);
 	}
 
 	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
@@ -1730,8 +1767,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
 	rt_queue_push_tasks(rq);
 }
 
-static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
-						   struct rt_rq *rt_rq)
+static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array = &rt_rq->active;
 	struct sched_rt_entity *next = NULL;
@@ -1753,7 +1789,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
-		rt_se = pick_next_rt_entity(rq, rt_rq);
+		rt_se = pick_next_rt_entity(rt_rq);
 		BUG_ON(!rt_se);
 		rt_rq = group_rt_rq(rt_se);
 	} while (rt_rq);
@@ -2026,6 +2062,16 @@ static int push_rt_task(struct rq *rq, bool pull)
 		return 0;
 
 retry:
+	/*
+	 * It's possible that the next_task slipped in of
+	 * higher priority than current. If that's the case
+	 * just reschedule current.
+	 */
+	if (unlikely(next_task->prio < rq->curr->prio)) {
+		resched_curr(rq);
+		return 0;
+	}
+
 	if (is_migration_disabled(next_task)) {
 		struct task_struct *push_task = NULL;
 		int cpu;
@@ -2033,6 +2079,18 @@ retry:
 		if (!pull || rq->push_busy)
 			return 0;
 
+		/*
+		 * Invoking find_lowest_rq() on anything but an RT task doesn't
+		 * make sense. Per the above priority check, curr has to
+		 * be of higher priority than next_task, so no need to
+		 * reschedule when bailing out.
+		 *
+		 * Note that the stoppers are masqueraded as SCHED_FIFO
+		 * (cf. sched_set_stop_task()), so we can't rely on rt_task().
+		 */
+		if (rq->curr->sched_class != &rt_sched_class)
+			return 0;
+
 		cpu = find_lowest_rq(rq->curr);
 		if (cpu == -1 || cpu == rq->cpu)
 			return 0;
@@ -2057,16 +2115,6 @@ retry:
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
-	/*
-	 * It's possible that the next_task slipped in of
-	 * higher priority than current. If that's the case
-	 * just reschedule current.
-	 */
-	if (unlikely(next_task->prio < rq->curr->prio)) {
-		resched_curr(rq);
-		return 0;
-	}
-
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
@@ -2864,6 +2912,7 @@ long sched_group_rt_period(struct task_group *tg)
 	return rt_period_us;
 }
 
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
 	int ret = 0;
@@ -2874,6 +2923,7 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+#endif /* CONFIG_SYSCTL */
 
 int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 {
@@ -2885,6 +2935,8 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 }
 
 #else /* !CONFIG_RT_GROUP_SCHED */
+
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
@@ -2902,8 +2954,10 @@ static int sched_rt_global_constraints(void)
 
 	return 0;
 }
+#endif /* CONFIG_SYSCTL */
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_validate(void)
 {
 	if (sysctl_sched_rt_period <= 0)
@@ -2928,7 +2982,7 @@ static void sched_rt_do_global(void)
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
@@ -2967,7 +3021,7 @@ undo:
 	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2988,6 +3042,7 @@ int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 
 	return ret;
 }
+#endif /* CONFIG_SYSCTL */
 
 #ifdef CONFIG_SCHED_DEBUG
 void print_rt_stats(struct seq_file *m, int cpu)