Merge tag 'sched-core-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Load-balancing updates:

   - 'flatten the pick': improve cgroup scheduling, which has always
     been problematic and painful, which has caused various scheduling
     misbehavior such as the mishandling of reniced tasks et al.

     Add various cgroup weight distribution methods via cgroup_mode:
     'up', 'max', 'concur' and 'tasks' - with the default being 'concur'
     which is the most precise yet also most expensive version.

     Finally, change cgroup scheduling to a single runqueue (Peter
     Zijlstra)

   - Series to improve the scheduling latency of short slice tasks
     (Vincent Guittot)

   - Series to fix cluster scheduling in the presence of asymmetric
     capacity (Ricardo Neri)

   - Prefer fully idle cores for NOHZ balancing (Andrea Righi)

   - Don't trigger active load-balancing if src_rq->curr is not on_rq
     (Xin Zhao)

  PSI updates:

   - Skip irqtime accounting when no new irq time has elapsed (Usama
     Arif)

  Scheduler debugging updates:

   - Remove unused schedstats (Shrikanth Hegde)

   - Defer freeing of cpumask memblock memory to initcall (Waiman Long)

  Misc fixes and updates by Yu C Chen, K Prateek Nayak, Peter Zijlstra,
  Vincent Guittot, Xin Zhao, Yury Norov, Zhan Xusheng"

* tag 'sched-core-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  sched/fair: Fix flat hierarchy
  sched/isolation: Defer freeing of cpumask memblock memory to initcall
  sched/topology: Restore SD_PREFER_SIBLING in domains with asymmetric capacity
  sched/fair: Allow load balancing between CPUs of identical capacity
  sched/fair: Skip misfit load accounting when the destination CPU cannot help
  sched/fair: Check CPU capacity before comparing group types during load balance
  sched/fair: Also gate overloaded status update for SD_ASYM_CPUCAPACITY
  sched/fair: Do not skip CPUs of similar capacity with busy SMT siblings
  sched/fair: Prefer fully idle cores for NOHZ balancing
  stop_machine: Make stop_one_cpu_nowait() return void
  sched/eevdf: Delayed dequeue task can't preempt
  sched/fair: Fix stale comments referring to removed CFS concepts
  sched/debug: Remove unused schedstats
  sched/psi: skip irqtime accounting when no new irq time has elapsed
  sched/fair: Reflow sched_balance_rq()
  sched/fair: Simplify balance_interval reset logic in sched_balance_rq()
  sched/fair: Don't trigger active lb if src_rq->curr is not on_rq
  sched/eevdf: Speedup short slice task scheduling
  sched/eevdf: Always update slice protection
  sched/eevdf: Cancel slice protection if short slice task is eligible
  ...

4 files changed, 18 insertions, 16 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 65d76a38974b..9db2d4fcead1 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -80,6 +80,7 @@ extern void lockdep_assert_cpuset_lock_held(void);
 extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern int cpuset_num_cpus(struct cgroup *cgroup);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -216,6 +217,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 	return false;
 }
 
+static inline int cpuset_num_cpus(struct cgroup *cgroup)
+{
+	return num_online_cpus();
+}
+
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 {
 	return node_possible_map;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e4136c2b2a3..3188fc78ac9b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -550,7 +550,6 @@ struct sched_statistics {
 	s64				exec_max;
 	u64				slice_max;
 
-	u64				nr_migrations_cold;
 	u64				nr_failed_migrations_affine;
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
@@ -563,8 +562,6 @@ struct sched_statistics {
 	u64				nr_wakeups_remote;
 	u64				nr_wakeups_affine;
 	u64				nr_wakeups_affine_attempts;
-	u64				nr_wakeups_passive;
-	u64				nr_wakeups_idle;
 
 #ifdef CONFIG_SCHED_CORE
 	u64				core_forceidle_sum;
@@ -575,6 +572,7 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
+	struct load_weight		h_load;
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 42839cfa2778..dc3ec2452ee1 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -146,8 +146,7 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
 /*
  * Prefer to place tasks in a sibling domain
  *
- * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
- * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ * Set up until domains start spanning NUMA nodes.
  *
  * NEEDS_GROUPS: Load balancing flag.
  */
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 01011113d226..84e7fb627ba4 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_STOP_MACHINE
 #define _LINUX_STOP_MACHINE
 
+#include <linux/bug.h>
 #include <linux/cpu.h>
 #include <linux/cpumask_types.h>
 #include <linux/smp.h>
@@ -31,7 +32,7 @@ struct cpu_stop_work {
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
-bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 void stop_machine_park(int cpu);
 void stop_machine_unpark(int cpu);
@@ -68,19 +69,17 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work)
 	preempt_enable();
 }
 
-static inline bool stop_one_cpu_nowait(unsigned int cpu,
+static inline void stop_one_cpu_nowait(unsigned int cpu,
 				       cpu_stop_fn_t fn, void *arg,
 				       struct cpu_stop_work *work_buf)
 {
-	if (cpu == smp_processor_id()) {
-		INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn);
-		work_buf->fn = fn;
-		work_buf->arg = arg;
-		schedule_work(&work_buf->work);
-		return true;
-	}
-
-	return false;
+	if (WARN_ON_ONCE(cpu != smp_processor_id()))
+		return;
+
+	INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn);
+	work_buf->fn = fn;
+	work_buf->arg = arg;
+	schedule_work(&work_buf->work);
 }
 
 static inline void print_stop_info(const char *log_lvl, struct task_struct *task) { }