Merge tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Implement the SCHED_DEADLINE server infrastructure - Daniel Bristot
   de Oliveira's last major contribution to the kernel:

     "SCHED_DEADLINE servers can help fixing starvation issues of low
      priority tasks (e.g., SCHED_OTHER) when higher priority tasks
      monopolize CPU cycles. Today we have RT Throttling; DEADLINE
      servers should be able to replace and improve that."

   (Daniel Bristot de Oliveira, Peter Zijlstra, Joel Fernandes, Youssef
   Esmat, Huang Shijie)

 - Preparatory changes for sched_ext integration:
     - Use set_next_task(.first) where required
     - Fix up set_next_task() implementations
     - Clean up DL server vs. core sched
     - Split up put_prev_task_balance()
     - Rework pick_next_task()
     - Combine the last put_prev_task() and the first set_next_task()
     - Rework dl_server
     - Add put_prev_task(.next)

   (Peter Zijlstra, with a fix by Tejun Heo)

 - Complete the EEVDF transition and refine EEVDF scheduling:
     - Implement delayed dequeue
     - Allow shorter slices to wakeup-preempt
     - Use sched_attr::sched_runtime to set request/slice suggestion
     - Document the new feature flags
     - Remove unused and duplicate-functionality fields
     - Simplify & unify pick_next_task_fair()
     - Misc debuggability enhancements

   (Peter Zijlstra, with fixes/cleanups by Dietmar Eggemann, Valentin
   Schneider and Chuyi Zhou)

 - Initialize the vruntime of a new task when it is first enqueued,
   resulting in significant decrease in latency of newly woken tasks
   (Zhang Qiao)

 - Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
   (K Prateek Nayak, Peter Zijlstra)

 - Clean up and clarify the usage of Clean up usage of rt_task()
   (Qais Yousef)

 - Preempt SCHED_IDLE entities in strict cgroup hierarchies
   (Tianchen Ding)

 - Clarify the documentation of time units for deadline scheduler
   parameters (Christian Loehle)

 - Remove the HZ_BW chicken-bit feature flag introduced a year ago,
   the original change seems to be working fine (Phil Auld)

 - Misc fixes and cleanups (Chen Yu, Dan Carpenter, Huang Shijie,
   Peilin He, Qais Yousefm and Vincent Guittot)

* tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/cpufreq: Use NSEC_PER_MSEC for deadline task
  cpufreq/cppc: Use NSEC_PER_MSEC for deadline task
  sched/deadline: Clarify nanoseconds in uapi
  sched/deadline: Convert schedtool example to chrt
  sched/debug: Fix the runnable tasks output
  sched: Fix sched_delayed vs sched_core
  kernel/sched: Fix util_est accounting for DELAY_DEQUEUE
  kthread: Fix task state in kthread worker if being frozen
  sched/pelt: Use rq_clock_task() for hw_pressure
  sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
  sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
  sched: Add put_prev_task(.next)
  sched: Rework dl_server
  sched: Combine the last put_prev_task() and the first set_next_task()
  sched: Rework pick_next_task()
  sched: Split up put_prev_task_balance()
  sched: Clean up DL server vs core sched
  sched: Fixup set_next_task() implementations
  sched: Use set_next_task(.first) where required
  sched/fair: Properly deactivate sched_delayed task upon class change
  ...

1 files changed, 112 insertions, 149 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 310523c1b9e3..172c588de542 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -8,10 +8,6 @@ int sched_rr_timeslice = RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
-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
@@ -66,6 +62,40 @@ static int __init sched_rt_sysctl_init(void)
 late_initcall(sched_rt_sysctl_init);
 #endif
 
+void init_rt_rq(struct rt_rq *rt_rq)
+{
+	struct rt_prio_array *array;
+	int i;
+
+	array = &rt_rq->active;
+	for (i = 0; i < MAX_RT_PRIO; i++) {
+		INIT_LIST_HEAD(array->queue + i);
+		__clear_bit(i, array->bitmap);
+	}
+	/* delimiter for bitsearch: */
+	__set_bit(MAX_RT_PRIO, array->bitmap);
+
+#if defined CONFIG_SMP
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
+	rt_rq->overloaded = 0;
+	plist_head_init(&rt_rq->pushable_tasks);
+#endif /* CONFIG_SMP */
+	/* We start is dequeued state, because no RT tasks are queued */
+	rt_rq->rt_queued = 0;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq->rt_time = 0;
+	rt_rq->rt_throttled = 0;
+	rt_rq->rt_runtime = 0;
+	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
+#endif
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
+
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -130,35 +160,6 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	do_start_rt_bandwidth(rt_b);
 }
 
-void init_rt_rq(struct rt_rq *rt_rq)
-{
-	struct rt_prio_array *array;
-	int i;
-
-	array = &rt_rq->active;
-	for (i = 0; i < MAX_RT_PRIO; i++) {
-		INIT_LIST_HEAD(array->queue + i);
-		__clear_bit(i, array->bitmap);
-	}
-	/* delimiter for bit-search: */
-	__set_bit(MAX_RT_PRIO, array->bitmap);
-
-#if defined CONFIG_SMP
-	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
-	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
-	rt_rq->overloaded = 0;
-	plist_head_init(&rt_rq->pushable_tasks);
-#endif /* CONFIG_SMP */
-	/* We start is dequeued state, because no RT tasks are queued */
-	rt_rq->rt_queued = 0;
-
-	rt_rq->rt_time = 0;
-	rt_rq->rt_throttled = 0;
-	rt_rq->rt_runtime = 0;
-	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
-}
-
-#ifdef CONFIG_RT_GROUP_SCHED
 static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	hrtimer_cancel(&rt_b->rt_period_timer);
@@ -195,7 +196,6 @@ void unregister_rt_sched_group(struct task_group *tg)
 {
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
-
 }
 
 void free_rt_sched_group(struct task_group *tg)
@@ -253,8 +253,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	if (!tg->rt_se)
 		goto err;
 
-	init_rt_bandwidth(&tg->rt_bandwidth,
-			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
+	init_rt_bandwidth(&tg->rt_bandwidth, ktime_to_ns(global_rt_period()), 0);
 
 	for_each_possible_cpu(i) {
 		rt_rq = kzalloc_node(sizeof(struct rt_rq),
@@ -604,70 +603,6 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 	return &rt_rq->tg->rt_bandwidth;
 }
 
-#else /* !CONFIG_RT_GROUP_SCHED */
-
-static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_runtime;
-}
-
-static inline u64 sched_rt_period(struct rt_rq *rt_rq)
-{
-	return ktime_to_ns(def_rt_bandwidth.rt_period);
-}
-
-typedef struct rt_rq *rt_rq_iter_t;
-
-#define for_each_rt_rq(rt_rq, iter, rq) \
-	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
-
-#define for_each_sched_rt_entity(rt_se) \
-	for (; rt_se; rt_se = NULL)
-
-static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
-{
-	return NULL;
-}
-
-static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
-{
-	struct rq *rq = rq_of_rt_rq(rt_rq);
-
-	if (!rt_rq->rt_nr_running)
-		return;
-
-	enqueue_top_rt_rq(rt_rq);
-	resched_curr(rq);
-}
-
-static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
-{
-	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
-}
-
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-
-static inline const struct cpumask *sched_rt_period_mask(void)
-{
-	return cpu_online_mask;
-}
-
-static inline
-struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
-{
-	return &cpu_rq(cpu)->rt;
-}
-
-static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
-{
-	return &def_rt_bandwidth;
-}
-
-#endif /* CONFIG_RT_GROUP_SCHED */
-
 bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -859,7 +794,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	const struct cpumask *span;
 
 	span = sched_rt_period_mask();
-#ifdef CONFIG_RT_GROUP_SCHED
+
 	/*
 	 * FIXME: isolated CPUs should really leave the root task group,
 	 * whether they are isolcpus or were isolated via cpusets, lest
@@ -871,7 +806,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	 */
 	if (rt_b == &root_task_group.rt_bandwidth)
 		span = cpu_online_mask;
-#endif
+
 	for_each_cpu(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
@@ -938,18 +873,6 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	return idle;
 }
 
-static inline int rt_se_prio(struct sched_rt_entity *rt_se)
-{
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct rt_rq *rt_rq = group_rt_rq(rt_se);
-
-	if (rt_rq)
-		return rt_rq->highest_prio.curr;
-#endif
-
-	return rt_task_of(rt_se)->prio;
-}
-
 static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 {
 	u64 runtime = sched_rt_runtime(rt_rq);
@@ -993,6 +916,72 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 	return 0;
 }
 
+#else /* !CONFIG_RT_GROUP_SCHED */
+
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
+#define for_each_sched_rt_entity(rt_se) \
+	for (; rt_se; rt_se = NULL)
+
+static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
+{
+	return NULL;
+}
+
+static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	if (!rt_rq->rt_nr_running)
+		return;
+
+	enqueue_top_rt_rq(rt_rq);
+	resched_curr(rq);
+}
+
+static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
+{
+	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
+}
+
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return false;
+}
+
+static inline const struct cpumask *sched_rt_period_mask(void)
+{
+	return cpu_online_mask;
+}
+
+static inline
+struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
+{
+	return &cpu_rq(cpu)->rt;
+}
+
+#ifdef CONFIG_SMP
+static void __enable_runtime(struct rq *rq) { }
+static void __disable_runtime(struct rq *rq) { }
+#endif
+
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static inline int rt_se_prio(struct sched_rt_entity *rt_se)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct rt_rq *rt_rq = group_rt_rq(rt_se);
+
+	if (rt_rq)
+		return rt_rq->highest_prio.curr;
+#endif
+
+	return rt_task_of(rt_se)->prio;
+}
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -1000,7 +989,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
-	struct sched_rt_entity *rt_se = &curr->rt;
 	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
@@ -1010,6 +998,9 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely(delta_exec <= 0))
 		return;
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct sched_rt_entity *rt_se = &curr->rt;
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1028,6 +1019,7 @@ static void update_curr_rt(struct rq *rq)
 				do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
 		}
 	}
+#endif
 }
 
 static void
@@ -1184,7 +1176,6 @@ dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 static void
 inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
-	start_rt_bandwidth(&def_rt_bandwidth);
 }
 
 static inline
@@ -1492,7 +1483,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 		enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
+static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
@@ -1500,6 +1491,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_rt_entity(rt_se, flags);
 
 	dequeue_pushable_task(rq, p);
+
+	return true;
 }
 
 /*
@@ -1755,17 +1748,7 @@ static struct task_struct *pick_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
-{
-	struct task_struct *p = pick_task_rt(rq);
-
-	if (p)
-		set_next_task_rt(rq, p, true);
-
-	return p;
-}
-
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 	struct rt_rq *rt_rq = &rq->rt;
@@ -2652,13 +2635,12 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.wakeup_preempt		= wakeup_preempt_rt,
 
-	.pick_next_task		= pick_next_task_rt,
+	.pick_task		= pick_task_rt,
 	.put_prev_task		= put_prev_task_rt,
 	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_rt,
-	.pick_task		= pick_task_rt,
 	.select_task_rq		= select_task_rq_rt,
 	.set_cpus_allowed       = set_cpus_allowed_common,
 	.rq_online              = rq_online_rt,
@@ -2912,19 +2894,6 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 #ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
-	unsigned long flags;
-	int i;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = global_rt_runtime();
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
-
 	return 0;
 }
 #endif /* CONFIG_SYSCTL */
@@ -2944,12 +2913,6 @@ static int sched_rt_global_validate(void)
 
 static void sched_rt_do_global(void)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
 static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,