From e9139f765ac7048cadc9981e962acdf8b08eabf3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 30 Oct 2024 13:43:43 +0100
Subject: sched: Employ sched_change guards

As proposed a long while ago -- and half done by scx -- wrap the
scheduler's 'change' pattern in a guard helper.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/cleanup.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 2573585b7f06..ae381675455d 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -340,6 +340,11 @@ _label:                                                         \
 #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond)	\
 static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 
+#define DEFINE_CLASS_IS_UNCONDITIONAL(_name)		\
+	__DEFINE_CLASS_IS_CONDITIONAL(_name, false);	\
+	static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{ return (void *)1; }
+
 #define __GUARD_IS_ERR(_ptr)                                       \
 	({                                                         \
 		unsigned long _rc = (__force unsigned long)(_ptr); \
-- 
cgit v1.2.3


From b079d93796528053cde322f2ca838c2d21c297e7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 10 Sep 2025 10:08:05 +0200
Subject: sched: Rename do_set_cpus_allowed()

Hopefully saner naming.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/sched.h  |  4 ++--
 kernel/cgroup/cpuset.c |  2 +-
 kernel/kthread.c       |  4 ++--
 kernel/sched/core.c    | 16 ++++++++--------
 kernel/sched/sched.h   |  2 +-
 5 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cbb7340c5866..77426c347cff 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1861,8 +1861,8 @@ extern int task_can_attach(struct task_struct *p);
 extern int dl_bw_alloc(int cpu, u64 dl_bw);
 extern void dl_bw_free(int cpu, u64 dl_bw);
 
-/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */
-extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
+/* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */
+extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask);
 
 /**
  * set_cpus_allowed_ptr - set CPU affinity mask of a task
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 52468d2c178a..185e820cd1df 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4180,7 +4180,7 @@ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	rcu_read_lock();
 	cs_mask = task_cs(tsk)->cpus_allowed;
 	if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) {
-		do_set_cpus_allowed(tsk, cs_mask);
+		set_cpus_allowed_force(tsk, cs_mask);
 		changed = true;
 	}
 	rcu_read_unlock();
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 832bd2afecc6..99a3808d086f 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -599,7 +599,7 @@ static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mas
 	}
 
 	scoped_guard (raw_spinlock_irqsave, &p->pi_lock)
-		do_set_cpus_allowed(p, mask);
+		set_cpus_allowed_force(p, mask);
 
 	/* It's safe because the task is inactive. */
 	p->flags |= PF_NO_SETAFFINITY;
@@ -880,7 +880,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
 	kthread_fetch_affinity(kthread, affinity);
 
 	scoped_guard (raw_spinlock_irqsave, &p->pi_lock)
-		do_set_cpus_allowed(p, affinity);
+		set_cpus_allowed_force(p, affinity);
 
 	mutex_unlock(&kthreads_hotplug_lock);
 out:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 805e65007e62..638bffd4c1a2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2331,7 +2331,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 }
 
 static void
-__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
 
 static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 {
@@ -2348,7 +2348,7 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 
 	scoped_guard (task_rq_lock, p) {
 		update_rq_clock(scope.rq);
-		__do_set_cpus_allowed(p, &ac);
+		do_set_cpus_allowed(p, &ac);
 	}
 }
 
@@ -2662,7 +2662,7 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx
 }
 
 static void
-__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
 {
 	struct rq *rq = task_rq(p);
 	bool queued, running;
@@ -2692,7 +2692,7 @@ __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
  * Used for kthread_bind() and select_fallback_rq(), in both cases the user
  * affinity (if any) should be destroyed too.
  */
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask)
 {
 	struct affinity_context ac = {
 		.new_mask  = new_mask,
@@ -2706,7 +2706,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 
 	scoped_guard (__task_rq_lock, p) {
 		update_rq_clock(scope.rq);
-		__do_set_cpus_allowed(p, &ac);
+		do_set_cpus_allowed(p, &ac);
 	}
 
 	/*
@@ -2745,7 +2745,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 	 * Use pi_lock to protect content of user_cpus_ptr
 	 *
 	 * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
-	 * do_set_cpus_allowed().
+	 * set_cpus_allowed_force().
 	 */
 	raw_spin_lock_irqsave(&src->pi_lock, flags);
 	if (src->user_cpus_ptr) {
@@ -3073,7 +3073,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 		goto out;
 	}
 
-	__do_set_cpus_allowed(p, ctx);
+	do_set_cpus_allowed(p, ctx);
 
 	return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
 
@@ -3482,7 +3482,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			}
 			fallthrough;
 		case possible:
-			do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
+			set_cpus_allowed_force(p, task_cpu_fallback_mask(p));
 			state = fail;
 			break;
 		case fail:
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b23ce9c77611..ea2ea8fd6505 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2617,7 +2617,7 @@ static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
 static inline cpumask_t *alloc_user_cpus_ptr(int node)
 {
 	/*
-	 * See do_set_cpus_allowed() above for the rcu_head usage.
+	 * See set_cpus_allowed_force() above for the rcu_head usage.
 	 */
 	int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
 
-- 
cgit v1.2.3


From 50653216e4ff7a74c95b2ee9ec439916875556ec Mon Sep 17 00:00:00 2001
From: Joel Fernandes <joelagnelf@nvidia.com>
Date: Sat, 9 Aug 2025 14:47:50 -0400
Subject: sched: Add support to pick functions to take rf

Some pick functions like the internal pick_next_task_fair() already take
rf but some others dont. We need this for scx's server pick function.
Prepare for this by having pick functions accept it.

[peterz: - added RETRY_TASK handling
         - removed pick_next_task_fair indirection]
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched.h    |  7 ++-----
 kernel/sched/core.c      | 35 ++++++++++++++++++++++++++---------
 kernel/sched/deadline.c  |  8 ++++----
 kernel/sched/ext.c       |  2 +-
 kernel/sched/fair.c      | 26 ++++++--------------------
 kernel/sched/idle.c      |  2 +-
 kernel/sched/rt.c        |  2 +-
 kernel/sched/sched.h     | 10 ++++++----
 kernel/sched/stop_task.c |  2 +-
 9 files changed, 48 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 77426c347cff..07576479c0ed 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -637,8 +637,8 @@ struct sched_rt_entity {
 #endif
 } __randomize_layout;
 
-typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
-typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+struct rq_flags;
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf);
 
 struct sched_dl_entity {
 	struct rb_node			rb_node;
@@ -730,9 +730,6 @@ struct sched_dl_entity {
 	 * dl_server_update().
 	 *
 	 * @rq the runqueue this server is for
-	 *
-	 * @server_has_tasks() returns true if @server_pick return a
-	 * runnable task.
 	 */
 	struct rq			*rq;
 	dl_server_pick_f		server_pick_task;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9fc990ff6845..a75d45680f9c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5901,7 +5901,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
-			p = pick_task_idle(rq);
+			p = pick_task_idle(rq, rf);
 			put_prev_set_next_task(rq, prev, p);
 		}
 
@@ -5913,11 +5913,15 @@ restart:
 
 	for_each_active_class(class) {
 		if (class->pick_next_task) {
-			p = class->pick_next_task(rq, prev);
+			p = class->pick_next_task(rq, prev, rf);
+			if (unlikely(p == RETRY_TASK))
+				goto restart;
 			if (p)
 				return p;
 		} else {
-			p = class->pick_task(rq);
+			p = class->pick_task(rq, rf);
+			if (unlikely(p == RETRY_TASK))
+				goto restart;
 			if (p) {
 				put_prev_set_next_task(rq, prev, p);
 				return p;
@@ -5947,7 +5951,11 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 	return a->core_cookie == b->core_cookie;
 }
 
-static inline struct task_struct *pick_task(struct rq *rq)
+/*
+ * Careful; this can return RETRY_TASK, it does not include the retry-loop
+ * itself due to the whole SMT pick retry thing below.
+ */
+static inline struct task_struct *pick_task(struct rq *rq, struct rq_flags *rf)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -5955,7 +5963,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	rq->dl_server = NULL;
 
 	for_each_active_class(class) {
-		p = class->pick_task(rq);
+		p = class->pick_task(rq, rf);
 		if (p)
 			return p;
 	}
@@ -5970,7 +5978,7 @@ static void queue_core_balance(struct rq *rq);
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *next, *p, *max = NULL;
+	struct task_struct *next, *p, *max;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
 	bool core_clock_updated = (rq == rq->core);
@@ -6055,7 +6063,10 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * and there are no cookied tasks running on siblings.
 	 */
 	if (!need_sync) {
-		next = pick_task(rq);
+restart_single:
+		next = pick_task(rq, rf);
+		if (unlikely(next == RETRY_TASK))
+			goto restart_single;
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
 			rq->core_dl_server = NULL;
@@ -6075,6 +6086,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 *
 	 * Tie-break prio towards the current CPU
 	 */
+restart_multi:
+	max = NULL;
 	for_each_cpu_wrap(i, smt_mask, cpu) {
 		rq_i = cpu_rq(i);
 
@@ -6086,7 +6099,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
-		rq_i->core_pick = p = pick_task(rq_i);
+		p = pick_task(rq_i, rf);
+		if (unlikely(p == RETRY_TASK))
+			goto restart_multi;
+
+		rq_i->core_pick = p;
 		rq_i->core_dl_server = rq_i->dl_server;
 
 		if (!max || prio_less(max, p, fi_before))
@@ -6108,7 +6125,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			if (cookie)
 				p = sched_core_find(rq_i, cookie);
 			if (!p)
-				p = idle_sched_class.pick_task(rq_i);
+				p = idle_sched_class.pick_task(rq_i, rf);
 		}
 
 		rq_i->core_pick = p;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 83e6175d79f5..48357d4609bf 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2352,7 +2352,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
  * __pick_next_task_dl - Helper to pick the next -deadline task to run.
  * @rq: The runqueue to pick the next task from.
  */
-static struct task_struct *__pick_task_dl(struct rq *rq)
+static struct task_struct *__pick_task_dl(struct rq *rq, struct rq_flags *rf)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2366,7 +2366,7 @@ again:
 	WARN_ON_ONCE(!dl_se);
 
 	if (dl_server(dl_se)) {
-		p = dl_se->server_pick_task(dl_se);
+		p = dl_se->server_pick_task(dl_se, rf);
 		if (!p) {
 			dl_server_stop(dl_se);
 			goto again;
@@ -2379,9 +2379,9 @@ again:
 	return p;
 }
 
-static struct task_struct *pick_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq, struct rq_flags *rf)
 {
-	return __pick_task_dl(rq);
+	return __pick_task_dl(rq, rf);
 }
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 949c3a6e24d4..dc743cac59cb 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2332,7 +2332,7 @@ static struct task_struct *first_local_task(struct rq *rq)
 					struct task_struct, scx.dsq_list.node);
 }
 
-static struct task_struct *pick_task_scx(struct rq *rq)
+static struct task_struct *pick_task_scx(struct rq *rq, struct rq_flags *rf)
 {
 	struct task_struct *prev = rq->curr;
 	struct task_struct *p;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 23ac05cca4a4..2554055c1ba1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8705,15 +8705,6 @@ static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context
 	set_task_max_allowed_capacity(p);
 }
 
-static int
-balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
-{
-	if (sched_fair_runnable(rq))
-		return 1;
-
-	return sched_balance_newidle(rq, rf) != 0;
-}
-
 static void set_next_buddy(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
@@ -8822,7 +8813,7 @@ preempt:
 	resched_curr_lazy(rq);
 }
 
-static struct task_struct *pick_task_fair(struct rq *rq)
+static struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
@@ -8866,7 +8857,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	int new_tasks;
 
 again:
-	p = pick_task_fair(rq);
+	p = pick_task_fair(rq, rf);
 	if (!p)
 		goto idle;
 	se = &p->se;
@@ -8945,14 +8936,10 @@ idle:
 	return NULL;
 }
 
-static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev)
-{
-	return pick_next_task_fair(rq, prev, NULL);
-}
-
-static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
+static struct task_struct *
+fair_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
 {
-	return pick_task_fair(dl_se->rq);
+	return pick_task_fair(dl_se->rq, rf);
 }
 
 void fair_server_init(struct rq *rq)
@@ -13644,11 +13631,10 @@ DEFINE_SCHED_CLASS(fair) = {
 	.wakeup_preempt		= check_preempt_wakeup_fair,
 
 	.pick_task		= pick_task_fair,
-	.pick_next_task		= __pick_next_task_fair,
+	.pick_next_task		= pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
-	.balance		= balance_fair,
 	.select_task_rq		= select_task_rq_fair,
 	.migrate_task_rq	= migrate_task_rq_fair,
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 055b0ddbcd54..7fa0b593bcff 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -466,7 +466,7 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
 	next->se.exec_start = rq_clock_task(rq);
 }
 
-struct task_struct *pick_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf)
 {
 	scx_update_idle(rq, true, false);
 	return rq->idle;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9bc828d59121..1fd97f2d7ec6 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1695,7 +1695,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return rt_task_of(rt_se);
 }
 
-static struct task_struct *pick_task_rt(struct rq *rq)
+static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
 {
 	struct task_struct *p;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f4a323007dce..8946294929a4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2470,7 +2470,7 @@ struct sched_class {
 	/*
 	 * schedule/pick_next_task: rq->lock
 	 */
-	struct task_struct *(*pick_task)(struct rq *rq);
+	struct task_struct *(*pick_task)(struct rq *rq, struct rq_flags *rf);
 	/*
 	 * Optional! When implemented pick_next_task() should be equivalent to:
 	 *
@@ -2480,7 +2480,8 @@ struct sched_class {
 	 *       set_next_task_first(next);
 	 *   }
 	 */
-	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev,
+					      struct rq_flags *rf);
 
 	/*
 	 * sched_change:
@@ -2707,8 +2708,9 @@ static inline bool sched_fair_runnable(struct rq *rq)
 	return rq->cfs.nr_queued > 0;
 }
 
-extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_task_idle(struct rq *rq);
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev,
+					       struct rq_flags *rf);
+extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf);
 
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index d98c453c9b4e..4f9192be4b5b 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -32,7 +32,7 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool fir
 	stop->se.exec_start = rq_clock_task(rq);
 }
 
-static struct task_struct *pick_task_stop(struct rq *rq)
+static struct task_struct *pick_task_stop(struct rq *rq, struct rq_flags *rf)
 {
 	if (!sched_stop_runnable(rq))
 		return NULL;
-- 
cgit v1.2.3


From f5a538c07df26f5c601e41f7b9c7ade3e1e75803 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 31 Oct 2025 13:54:24 +0100
Subject: sched/deadline: Fix dl_server stop condition

Gabriel reported that the dl_server doesn't stop as expected.

The problem was found to be the fact that idle time and fair runtime are
treated equally. Both will count towards dl_server runtime and push the
activation forwards when it is in the zero-laxity wait state.

Notably:

  dl_server_update_idle()
    update_curr_dl_se()
      if (dl_defer && dl_throttled && dl_runtime_exceeded())
        hrtimer_try_to_cancel(); // stop timer
	replenish_dl_new_period()
	  deadline = now + dl_deadline; // fwd period
	  runtime = dl_runtime;
        start_dl_timer(); // restart timer

And while we do want idle time accounted towards the *current* activation of
the dl_server -- after all, a fair task could've ran if we had any -- we don't
necessarily want idle time to cause or push forward an activation.

Introduce dl_defer_idle to make this distinction. It will be set once idle time
pushed the activation forward, once set idle time will only be allowed to
consume any runtime but not push the activation. This will then cause
dl_server_timer() to fire, which will stop the dl_server.

Any non-idle time accounting during this phase will clear dl_defer_idle, so
only a full period of idle will cause the dl_server to stop.

Reported-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251101000057.GA2184199@noisy.programming.kicks-ass.net
---
 include/linux/sched.h   | 15 +++++++++------
 kernel/sched/deadline.c | 40 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 47 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 07576479c0ed..bb436ee1942d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -685,20 +685,22 @@ struct sched_dl_entity {
 	 *
 	 * @dl_server tells if this is a server entity.
 	 *
-	 * @dl_defer tells if this is a deferred or regular server. For
-	 * now only defer server exists.
-	 *
-	 * @dl_defer_armed tells if the deferrable server is waiting
-	 * for the replenishment timer to activate it.
-	 *
 	 * @dl_server_active tells if the dlserver is active(started).
 	 * dlserver is started on first cfs enqueue on an idle runqueue
 	 * and is stopped when a dequeue results in 0 cfs tasks on the
 	 * runqueue. In other words, dlserver is active only when cpu's
 	 * runqueue has atleast one cfs task.
 	 *
+	 * @dl_defer tells if this is a deferred or regular server. For
+	 * now only defer server exists.
+	 *
+	 * @dl_defer_armed tells if the deferrable server is waiting
+	 * for the replenishment timer to activate it.
+	 *
 	 * @dl_defer_running tells if the deferrable server is actually
 	 * running, skipping the defer phase.
+	 *
+	 * @dl_defer_idle tracks idle state
 	 */
 	unsigned int			dl_throttled      : 1;
 	unsigned int			dl_yielded        : 1;
@@ -709,6 +711,7 @@ struct sched_dl_entity {
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
+	unsigned int			dl_defer_idle     : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ece25caf379c..8307f24b8900 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1173,6 +1173,11 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
 		 */
 		rq->donor->sched_class->update_curr(rq);
 
+		if (dl_se->dl_defer_idle) {
+			dl_server_stop(dl_se);
+			return HRTIMER_NORESTART;
+		}
+
 		if (dl_se->dl_defer_armed) {
 			/*
 			 * First check if the server could consume runtime in background.
@@ -1420,10 +1425,11 @@ s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta
 }
 
 static inline void
-update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
-			int flags);
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, int flags);
+
 static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
 {
+	bool idle = rq->curr == rq->idle;
 	s64 scaled_delta_exec;
 
 	if (unlikely(delta_exec <= 0)) {
@@ -1444,6 +1450,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 
 	dl_se->runtime -= scaled_delta_exec;
 
+	if (dl_se->dl_defer_idle && !idle)
+		dl_se->dl_defer_idle = 0;
+
 	/*
 	 * The fair server can consume its runtime while throttled (not queued/
 	 * running as regular CFS).
@@ -1453,6 +1462,29 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 	 * starting a new period, pushing the activation.
 	 */
 	if (dl_se->dl_defer && dl_se->dl_throttled && dl_runtime_exceeded(dl_se)) {
+		/*
+		 * Non-servers would never get time accounted while throttled.
+		 */
+		WARN_ON_ONCE(!dl_server(dl_se));
+
+		/*
+		 * While the server is marked idle, do not push out the
+		 * activation further, instead wait for the period timer
+		 * to lapse and stop the server.
+		 */
+		if (dl_se->dl_defer_idle && idle) {
+			/*
+			 * The timer is at the zero-laxity point, this means
+			 * dl_server_stop() / dl_server_start() can happen
+			 * while now < deadline. This means update_dl_entity()
+			 * will not replenish. Additionally start_dl_timer()
+			 * will be set for 'deadline - runtime'. Negative
+			 * runtime will not do.
+			 */
+			dl_se->runtime = 0;
+			return;
+		}
+
 		/*
 		 * If the server was previously activated - the starving condition
 		 * took place, it this point it went away because the fair scheduler
@@ -1465,6 +1497,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 
 		replenish_dl_new_period(dl_se, dl_se->rq);
 
+		if (idle)
+			dl_se->dl_defer_idle = 1;
+
 		/*
 		 * Not being able to start the timer seems problematic. If it could not
 		 * be started for whatever reason, we need to "unthrottle" the DL server
@@ -1590,6 +1625,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 	hrtimer_try_to_cancel(&dl_se->dl_timer);
 	dl_se->dl_defer_armed = 0;
 	dl_se->dl_throttled = 0;
+	dl_se->dl_defer_idle = 0;
 	dl_se->dl_server_active = 0;
 }
 
-- 
cgit v1.2.3


From 33cf66d88306663d16e4759e9d24766b0aaa2e17 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 7 Nov 2025 17:01:31 +0100
Subject: sched/fair: Proportional newidle balance

Add a randomized algorithm that runs newidle balancing proportional to
its success rate.

This improves schbench significantly:

 6.18-rc4:			2.22 Mrps/s
 6.18-rc4+revert:		2.04 Mrps/s
 6.18-rc4+revert+random:	2.18 Mrps/S

Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%:

 6.17:			-6%
 6.17+revert:		 0%
 6.17+revert+random:	-1%

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Chris Mason <clm@meta.com>
Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com
Link: https://patch.msgid.link/20251107161739.770122091@infradead.org
---
 include/linux/sched/topology.h |  3 +++
 kernel/sched/core.c            |  3 +++
 kernel/sched/fair.c            | 44 ++++++++++++++++++++++++++++++++++++++----
 kernel/sched/features.h        |  5 +++++
 kernel/sched/sched.h           |  7 +++++++
 kernel/sched/topology.c        |  6 ++++++
 6 files changed, 64 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index bbcfdf12aa6e..45c0022b91ce 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -92,6 +92,9 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	/* idle_balance() stats */
+	unsigned int newidle_call;
+	unsigned int newidle_success;
+	unsigned int newidle_ratio;
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 699db3f46df6..9f10cfbdc228 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -121,6 +121,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
 DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -8489,6 +8490,8 @@ void __init sched_init_smp(void)
 {
 	sched_init_numa(NUMA_NO_NODE);
 
+	prandom_init_once(&sched_rnd_state);
+
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index abcbb67dd785..1855975b8248 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12224,11 +12224,27 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
-static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success)
+{
+	sd->newidle_call++;
+	sd->newidle_success += success;
+
+	if (sd->newidle_call >= 1024) {
+		sd->newidle_ratio = sd->newidle_success;
+		sd->newidle_call /= 2;
+		sd->newidle_success /= 2;
+	}
+}
+
+static inline bool
+update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success)
 {
 	unsigned long next_decay = sd->last_decay_max_lb_cost + HZ;
 	unsigned long now = jiffies;
 
+	if (cost)
+		update_newidle_stats(sd, success);
+
 	if (cost > sd->max_newidle_lb_cost) {
 		/*
 		 * Track max cost of a domain to make sure to not delay the
@@ -12276,7 +12292,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 		 * Decay the newidle max times here because this is a regular
 		 * visit to all the domains.
 		 */
-		need_decay = update_newidle_cost(sd, 0);
+		need_decay = update_newidle_cost(sd, 0, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -12912,6 +12928,22 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 			break;
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			unsigned int weight = 1;
+
+			if (sched_feat(NI_RANDOM)) {
+				/*
+				 * Throw a 1k sided dice; and only run
+				 * newidle_balance according to the success
+				 * rate.
+				 */
+				u32 d1k = sched_rng() % 1024;
+				weight = 1 + sd->newidle_ratio;
+				if (d1k > weight) {
+					update_newidle_stats(sd, 0);
+					continue;
+				}
+				weight = (1024 + weight/2) / weight;
+			}
 
 			pulled_task = sched_balance_rq(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
@@ -12919,10 +12951,14 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 
 			t1 = sched_clock_cpu(this_cpu);
 			domain_cost = t1 - t0;
-			update_newidle_cost(sd, domain_cost);
-
 			curr_cost += domain_cost;
 			t0 = t1;
+
+			/*
+			 * Track max cost of a domain to make sure to not delay the
+			 * next wakeup on the CPU.
+			 */
+			update_newidle_cost(sd, domain_cost, weight * !!pulled_task);
 		}
 
 		/*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 0607def744af..980d92bab8ab 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -121,3 +121,8 @@ SCHED_FEAT(WA_BIAS, true)
 SCHED_FEAT(UTIL_EST, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
+
+/*
+ * Do newidle balancing proportional to its success rate using randomization.
+ */
+SCHED_FEAT(NI_RANDOM, true)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index def9ab7b59d4..b419a4d98461 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
 #ifndef _KERNEL_SCHED_SCHED_H
 #define _KERNEL_SCHED_SCHED_H
 
+#include <linux/prandom.h>
 #include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/cpufreq.h>
@@ -1348,6 +1349,12 @@ static inline bool is_migration_disabled(struct task_struct *p)
 }
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DECLARE_PER_CPU(struct rnd_state, sched_rnd_state);
+
+static inline u32 sched_rng(void)
+{
+	return prandom_u32_state(this_cpu_ptr(&sched_rnd_state));
+}
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
 #define this_rq()		this_cpu_ptr(&runqueues)
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 711076aa4980..cf643a5ddedd 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1669,6 +1669,12 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+
+		/* 50% success rate */
+		.newidle_call		= 512,
+		.newidle_success	= 256,
+		.newidle_ratio		= 512,
+
 		.max_newidle_lb_cost	= 0,
 		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,
-- 
cgit v1.2.3


From c04507ac500e2cc8048000c2a849588227554e06 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sun, 16 Nov 2025 21:51:07 +0100
Subject: sched: Provide and use set_need_resched_current()

set_tsk_need_resched(current) requires set_preempt_need_resched(current) to
work correctly outside of the scheduler.

Provide set_need_resched_current() which wraps this correctly and replace
all the open coded instances.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://patch.msgid.link/20251116174750.665769842@linutronix.de
---
 arch/s390/mm/pfault.c    |  3 +--
 include/linux/sched.h    |  7 +++++++
 kernel/rcu/tiny.c        |  8 +++-----
 kernel/rcu/tree.c        | 14 +++++---------
 kernel/rcu/tree_exp.h    |  3 +--
 kernel/rcu/tree_plugin.h |  9 +++------
 kernel/rcu/tree_stall.h  |  3 +--
 7 files changed, 21 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index e6175d75e4b0..2f829448c719 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -199,8 +199,7 @@ block:
 			 * return to userspace schedule() to block.
 			 */
 			__set_current_state(TASK_UNINTERRUPTIBLE);
-			set_tsk_need_resched(tsk);
-			set_preempt_need_resched();
+			set_need_resched_current();
 		}
 	}
 out:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb436ee1942d..021d05aa941a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2058,6 +2058,13 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+static inline void set_need_resched_current(void)
+{
+	lockdep_assert_irqs_disabled();
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
+}
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c1ebfd51768b..585cade21010 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -70,12 +70,10 @@ void rcu_qs(void)
  */
 void rcu_sched_clock_irq(int user)
 {
-	if (user) {
+	if (user)
 		rcu_qs();
-	} else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
-		set_tsk_need_resched(current);
-		set_preempt_need_resched();
-	}
+	else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail)
+		set_need_resched_current();
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8293bae1dec1..85b82a7007b9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2696,10 +2696,8 @@ void rcu_sched_clock_irq(int user)
 	/* The load-acquire pairs with the store-release setting to true. */
 	if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
 		/* Idle and userspace execution already are quiescent states. */
-		if (!rcu_is_cpu_rrupt_from_idle() && !user) {
-			set_tsk_need_resched(current);
-			set_preempt_need_resched();
-		}
+		if (!rcu_is_cpu_rrupt_from_idle() && !user)
+			set_need_resched_current();
 		__this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	}
 	rcu_flavor_sched_clock_irq(user);
@@ -2824,7 +2822,6 @@ static void strict_work_handler(struct work_struct *work)
 /* Perform RCU core processing work for the current CPU.  */
 static __latent_entropy void rcu_core(void)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
 
@@ -2837,8 +2834,8 @@ static __latent_entropy void rcu_core(void)
 	if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
-		set_tsk_need_resched(current);
-		set_preempt_need_resched();
+		guard(irqsave)();
+		set_need_resched_current();
 	}
 
 	/* Update RCU state based on any recent quiescent states. */
@@ -2847,10 +2844,9 @@ static __latent_entropy void rcu_core(void)
 	/* No grace period and unregistered callbacks? */
 	if (!rcu_gp_in_progress() &&
 	    rcu_segcblist_is_enabled(&rdp->cblist) && !rcu_rdp_is_offloaded(rdp)) {
-		local_irq_save(flags);
+		guard(irqsave)();
 		if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 			rcu_accelerate_cbs_unlocked(rnp, rdp);
-		local_irq_restore(flags);
 	}
 
 	rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 6058a734090c..96c49c56fc14 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -729,8 +729,7 @@ static void rcu_exp_need_qs(void)
 	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
 	/* Store .exp before .rcu_urgent_qs. */
 	smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
+	set_need_resched_current();
 }
 
 #ifdef CONFIG_PREEMPT_RCU
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d85763336b3c..dbe2d02be824 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -753,8 +753,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			// Also if no expediting and no possible deboosting,
 			// slow is OK.  Plus nohz_full CPUs eventually get
 			// tick enabled.
-			set_tsk_need_resched(current);
-			set_preempt_need_resched();
+			set_need_resched_current();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
 			    needs_exp && rdp->defer_qs_iw_pending != DEFER_QS_PENDING &&
 			    cpu_online(rdp->cpu)) {
@@ -813,10 +812,8 @@ static void rcu_flavor_sched_clock_irq(int user)
 	if (rcu_preempt_depth() > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
-		if (rcu_preempt_need_deferred_qs(t)) {
-			set_tsk_need_resched(t);
-			set_preempt_need_resched();
-		}
+		if (rcu_preempt_need_deferred_qs(t))
+			set_need_resched_current();
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index d16afeb11506..b67532cb8770 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -763,8 +763,7 @@ static void print_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	 * progress and it could be we're stuck in kernel space without context
 	 * switches for an entirely unreasonable amount of time.
 	 */
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
+	set_need_resched_current();
 }
 
 static bool csd_lock_suppress_rcu_stall;
-- 
cgit v1.2.3