Merge tag 'sched-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduling updates:
   - Skip SCHED_IDLE rq for SCHED_IDLE tasks (Christian Loehle)
   - Remove superfluous rcu_read_lock() in the wakeup path (K Prateek Nayak)
   - Simplify the entry condition for update_idle_cpu_scan() (K Prateek Nayak)
   - Simplify SIS_UTIL handling in select_idle_cpu() (K Prateek Nayak)
   - Avoid overflow in enqueue_entity() (K Prateek Nayak)
   - Update overutilized detection (Vincent Guittot)
   - Prevent negative lag increase during delayed dequeue (Vincent Guittot)
   - Clear buddies for preempt_short (Vincent Guittot)
   - Implement more complex proportional newidle balance (Peter Zijlstra)
   - Increase weight bits for avg_vruntime (Peter Zijlstra)
   - Use full weight to __calc_delta() (Peter Zijlstra)

  RT and DL scheduling updates:
   - Fix incorrect schedstats for rt and dl thread (Dengjun Su)
   - Skip group schedulable check with rt_group_sched=0 (Michal Koutný)
   - Move group schedulability check to sched_rt_global_validate()
     (Michal Koutný)
   - Add reporting of runtime left & abs deadline to sched_getattr()
     for DEADLINE tasks (Tommaso Cucinotta)

  Scheduling topology updates by K Prateek Nayak:
   - Compute sd_weight considering cpuset partitions
   - Extract "imb_numa_nr" calculation into a separate helper
   - Allocate per-CPU sched_domain_shared in s_data
   - Switch to assigning "sd->shared" from s_data
   - Remove sched_domain_shared allocation with sd_data

  Energy-aware scheduling updates:
   - Filter false overloaded_group case for EAS (Vincent Guittot)
   - PM: EM: Switch to rcu_dereference_all() in wakeup path
     (Dietmar Eggemann)

  Infrastructure updates:
   - Replace use of system_unbound_wq with system_dfl_wq (Marco Crivellari)

  Proxy scheduling updates by John Stultz:
   - Make class_schedulers avoid pushing current, and get rid of proxy_tag_curr()
   - Minimise repeated sched_proxy_exec() checking
   - Fix potentially missing balancing with Proxy Exec
   - Fix and improve task::blocked_on et al handling
   - Add assert_balance_callbacks_empty() helper
   - Add logic to zap balancing callbacks if we pick again
   - Move attach_one_task() and attach_task() helpers to sched.h
   - Handle blocked-waiter migration (and return migration)
   - Add K Prateek Nayak to scheduler reviewers for proxy execution

  Misc cleanups and fixes by John Stultz, Joseph Salisbury, Peter
  Zijlstra, K Prateek Nayak, Michal Koutný, Randy Dunlap, Shrikanth
  Hegde, Vincent Guittot, Zhan Xusheng, Xie Yuanbin and Vincent Guittot"

* tag 'sched-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  sched/eevdf: Clear buddies for preempt_short
  sched/rt: Cleanup global RT bandwidth functions
  sched/rt: Move group schedulability check to sched_rt_global_validate()
  sched/rt: Skip group schedulable check with rt_group_sched=0
  sched/fair: Avoid overflow in enqueue_entity()
  sched: Use u64 for bandwidth ratio calculations
  sched/fair: Prevent negative lag increase during delayed dequeue
  sched/fair: Use sched_energy_enabled()
  sched: Handle blocked-waiter migration (and return migration)
  sched: Move attach_one_task and attach_task helpers to sched.h
  sched: Add logic to zap balance callbacks if we pick again
  sched: Add assert_balance_callbacks_empty helper
  sched/locking: Add special p->blocked_on==PROXY_WAKING value for proxy return-migration
  sched: Fix modifying donor->blocked on without proper locking
  locking: Add task::blocked_lock to serialize blocked_on state
  sched: Fix potentially missing balancing with Proxy Exec
  sched: Minimise repeated sched_proxy_exec() checking
  sched: Make class_schedulers avoid pushing current, and get rid of proxy_tag_curr()
  MAINTAINERS: Add K Prateek Nayak to scheduler reviewers
  sched/core: Get this cpu once in ttwu_queue_cond()
  ...

4 files changed, 85 insertions, 40 deletions

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index e7497f804644..c909a8ba22e8 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -248,7 +248,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	struct em_perf_state *ps;
 	int i;
 
-	WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n");
+	lockdep_assert(rcu_read_lock_any_held());
 
 	if (!sum_util)
 		return 0;
@@ -267,7 +267,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 * Find the lowest performance state of the Energy Model above the
 	 * requested performance.
 	 */
-	em_table = rcu_dereference(pd->em_table);
+	em_table = rcu_dereference_all(pd->em_table);
 	i = em_pd_get_efficient_state(em_table->state, pd, max_util);
 	ps = &em_table->state[i];
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 54820a427014..004e6d56a499 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1239,6 +1239,7 @@ struct task_struct {
 #endif
 
 	struct mutex			*blocked_on;	/* lock we're blocked on */
+	raw_spinlock_t			blocked_lock;
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
@@ -2180,61 +2181,85 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock) __must_hold(lock);
 })
 
 #ifndef CONFIG_PREEMPT_RT
+
+/*
+ * With proxy exec, if a task has been proxy-migrated, it may be a donor
+ * on a cpu that it can't actually run on. Thus we need a special state
+ * to denote that the task is being woken, but that it needs to be
+ * evaluated for return-migration before it is run. So if the task is
+ * blocked_on PROXY_WAKING, return migrate it before running it.
+ */
+#define PROXY_WAKING ((struct mutex *)(-1L))
+
 static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
 {
-	struct mutex *m = p->blocked_on;
-
-	if (m)
-		lockdep_assert_held_once(&m->wait_lock);
-	return m;
+	lockdep_assert_held_once(&p->blocked_lock);
+	return p->blocked_on == PROXY_WAKING ? NULL : p->blocked_on;
 }
 
 static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
-	struct mutex *blocked_on = READ_ONCE(p->blocked_on);
-
 	WARN_ON_ONCE(!m);
 	/* The task should only be setting itself as blocked */
 	WARN_ON_ONCE(p != current);
-	/* Currently we serialize blocked_on under the mutex::wait_lock */
-	lockdep_assert_held_once(&m->wait_lock);
+	/* Currently we serialize blocked_on under the task::blocked_lock */
+	lockdep_assert_held_once(&p->blocked_lock);
 	/*
 	 * Check ensure we don't overwrite existing mutex value
 	 * with a different mutex. Note, setting it to the same
 	 * lock repeatedly is ok.
 	 */
-	WARN_ON_ONCE(blocked_on && blocked_on != m);
-	WRITE_ONCE(p->blocked_on, m);
+	WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
+	p->blocked_on = m;
 }
 
-static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
+static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
-	guard(raw_spinlock_irqsave)(&m->wait_lock);
-	__set_task_blocked_on(p, m);
+	/* Currently we serialize blocked_on under the task::blocked_lock */
+	lockdep_assert_held_once(&p->blocked_lock);
+	/*
+	 * There may be cases where we re-clear already cleared
+	 * blocked_on relationships, but make sure we are not
+	 * clearing the relationship with a different lock.
+	 */
+	WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m && p->blocked_on != PROXY_WAKING);
+	p->blocked_on = NULL;
 }
 
-static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
-	if (m) {
-		struct mutex *blocked_on = READ_ONCE(p->blocked_on);
+	guard(raw_spinlock_irqsave)(&p->blocked_lock);
+	__clear_task_blocked_on(p, m);
+}
 
-		/* Currently we serialize blocked_on under the mutex::wait_lock */
-		lockdep_assert_held_once(&m->wait_lock);
-		/*
-		 * There may be cases where we re-clear already cleared
-		 * blocked_on relationships, but make sure we are not
-		 * clearing the relationship with a different lock.
-		 */
-		WARN_ON_ONCE(blocked_on && blocked_on != m);
+static inline void __set_task_blocked_on_waking(struct task_struct *p, struct mutex *m)
+{
+	/* Currently we serialize blocked_on under the task::blocked_lock */
+	lockdep_assert_held_once(&p->blocked_lock);
+
+	if (!sched_proxy_exec()) {
+		__clear_task_blocked_on(p, m);
+		return;
 	}
-	WRITE_ONCE(p->blocked_on, NULL);
+
+	/* Don't set PROXY_WAKING if blocked_on was already cleared */
+	if (!p->blocked_on)
+		return;
+	/*
+	 * There may be cases where we set PROXY_WAKING on tasks that were
+	 * already set to waking, but make sure we are not changing
+	 * the relationship with a different lock.
+	 */
+	WARN_ON_ONCE(m && p->blocked_on != m && p->blocked_on != PROXY_WAKING);
+	p->blocked_on = PROXY_WAKING;
 }
 
-static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+static inline void set_task_blocked_on_waking(struct task_struct *p, struct mutex *m)
 {
-	guard(raw_spinlock_irqsave)(&m->wait_lock);
-	__clear_task_blocked_on(p, m);
+	guard(raw_spinlock_irqsave)(&p->blocked_lock);
+	__set_task_blocked_on_waking(p, m);
 }
+
 #else
 static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
 {
@@ -2243,6 +2268,14 @@ static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mute
 static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
 {
 }
+
+static inline void __set_task_blocked_on_waking(struct task_struct *p, struct rt_mutex *m)
+{
+}
+
+static inline void set_task_blocked_on_waking(struct task_struct *p, struct rt_mutex *m)
+{
+}
 #endif /* !CONFIG_PREEMPT_RT */
 
 static __always_inline bool need_resched(void)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 45c0022b91ce..36553e14866d 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -95,6 +95,7 @@ struct sched_domain {
 	unsigned int newidle_call;
 	unsigned int newidle_success;
 	unsigned int newidle_ratio;
+	u64 newidle_stamp;
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 
@@ -141,18 +142,30 @@ struct sched_domain {
 
 	unsigned int span_weight;
 	/*
-	 * Span of all CPUs in this domain.
+	 * See sched_domain_span(), on why flex arrays are broken.
 	 *
-	 * NOTE: this field is variable length. (Allocated dynamically
-	 * by attaching extra space to the end of the structure,
-	 * depending on how many CPUs the kernel has booted up with)
-	 */
 	unsigned long span[];
+	 */
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 {
-	return to_cpumask(sd->span);
+	/*
+	 * Turns out that C flexible arrays are fundamentally broken since it
+	 * is allowed for offsetof(*sd, span) < sizeof(*sd), this means that
+	 * structure initialzation *sd = { ... }; which writes every byte
+	 * inside sizeof(*type), will over-write the start of the flexible
+	 * array.
+	 *
+	 * Luckily, the way we allocate sched_domain is by:
+	 *
+	 *   sizeof(*sd) + cpumask_size()
+	 *
+	 * this means that we have sufficient space for the whole flex array
+	 * *outside* of sizeof(*sd). So use that, and avoid using sd->span.
+	 */
+	unsigned long *bitmap = (void *)sd + sizeof(*sd);
+	return to_cpumask(bitmap);
 }
 
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
@@ -171,7 +184,6 @@ typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {
 	struct sched_domain *__percpu *sd;
-	struct sched_domain_shared *__percpu *sds;
 	struct sched_group *__percpu *sg;
 	struct sched_group_capacity *__percpu *sgc;
 };
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 9e29d79fc790..ace7379d627d 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -406,7 +406,7 @@ do {									\
 			  schedule())
 
 /**
- * wait_var_event_killable - wait for a variable to be updated and notified
+ * wait_var_event_interruptible - wait for a variable to be updated and notified
  * @var: the address of variable being waited on
  * @condition: the condition to wait for
  *
@@ -492,7 +492,7 @@ do {									\
  * wait_var_event_mutex - wait for a variable to be updated under a mutex
  * @var: the address of the variable being waited on
  * @condition: condition to wait for
- * @mutex: the mutex which protects updates to the variable
+ * @lock: the mutex which protects updates to the variable
  *
  * Wait for a condition which can only be reliably tested while holding
  * a mutex.  The variables assessed in the condition will normal be