Scheduler updates for v6.16:

Core & fair scheduler changes:
 
   - Tweak wait_task_inactive() to force dequeue sched_delayed tasks
     (John Stultz)
 
   - Adhere to place_entity() constraints (Peter Zijlstra)
 
   - Allow decaying util_est when util_avg > CPU capacity (Pierre Gondois)
 
   - Fix up wake_up_sync() vs DELAYED_DEQUEUE (Xuewen Yan)
 
 Energy management:
 
   - Introduce sched_update_asym_prefer_cpu() (K Prateek Nayak)
 
   - cpufreq/amd-pstate: Update asym_prefer_cpu when core rankings change
     (K Prateek Nayak)
 
   - Align uclamp and util_est and call before freq update (Xuewen Yan)
 
 CPU isolation:
 
   - Make use of more than one housekeeping CPU (Phil Auld)
 
 RT scheduler:
 
   - Fix race in push_rt_task() (Harshit Agarwal)
 
   - Add kernel cmdline option for rt_group_sched (Michal Koutný)
 
 Scheduler topology support:
 
   - Improve topology_span_sane speed (Steve Wahl)
 
 Scheduler debugging:
 
   - Move and extend the sched_process_exit() tracepoint (Andrii Nakryiko)
 
   - Add RT_GROUP WARN checks for non-root task_groups (Michal Koutný)
 
   - Fix trace_sched_switch(.prev_state) (Peter Zijlstra)
 
   - Untangle cond_resched() and live-patching (Peter Zijlstra)
 
 Fixes and cleanups:
 
   - Misc fixes and cleanups (K Prateek Nayak, Michal Koutný,
     Peter Zijlstra, Xuewen Yan)
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmgy50ARHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1jFQQ/+KXl2XDg1V/VVmMG8GmtDlR29V3M3ricy
 D7/2s0D1Y1ErHb+pRMBG31EubT9/bXjUshWIuuf51DciSLBmpELHxY5J+AevRa0L
 /pHFwSvP6H5pDakI/xZ01FlYt7PxZGs+1m1o2615Mbwq6J2bjZTan54CYzrdpLOy
 Nqb3OT4tSqU1+7SV7hVForBpZp9u3CvVBRt/wE6vcHltW/I486bM8OCOd2XrUlnb
 QoIRliGI9KHpqCpbAeKPRSKXpf9tZv/AijZ+0WUu2yY8iwSN4p3RbbbwdCipjVQj
 w5I5oqKI6cylFfl2dEFWXVO+tLBihs06w8KSQrhYmQ9DUu4RGBVM9ORINGDBPejL
 bvoQh1mAkqvIL+oodujdbMDIqLupvOEtVSvwzR7SJn8BJSB00js88ngCWLjo/CcU
 imLbWy9FSBLvOswLBzQthgAJEj+ejCkOIbcvM2lINWhX/zNsMFaaqYcO1wRunGGR
 SavTI1s+ZksCQY6vCwRkwPrOZjyg91TA/q4FK102fHL1IcthH6xubE4yi4lTIUYs
 L56HuGm8e7Shc8M2Y5rAYsVG3GoIHFLXnptOn2HnCRWaAAJYsBaLUlzoBy9MxCfw
 I2YVDCylkQxevosSi2XxXo3tbM6auISU9SelAT/dAz32V1rsjWQojRJXeGYKIbu7
 KBuN/dLItW0=
 =s/ra
 -----END PGP SIGNATURE-----

Merge tag 'sched-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core & fair scheduler changes:

   - Tweak wait_task_inactive() to force dequeue sched_delayed tasks
     (John Stultz)

   - Adhere to place_entity() constraints (Peter Zijlstra)

   - Allow decaying util_est when util_avg > CPU capacity (Pierre
     Gondois)

   - Fix up wake_up_sync() vs DELAYED_DEQUEUE (Xuewen Yan)

  Energy management:

   - Introduce sched_update_asym_prefer_cpu() (K Prateek Nayak)

   - cpufreq/amd-pstate: Update asym_prefer_cpu when core rankings
     change (K Prateek Nayak)

   - Align uclamp and util_est and call before freq update (Xuewen Yan)

  CPU isolation:

   - Make use of more than one housekeeping CPU (Phil Auld)

  RT scheduler:

   - Fix race in push_rt_task() (Harshit Agarwal)

   - Add kernel cmdline option for rt_group_sched (Michal Koutný)

  Scheduler topology support:

   - Improve topology_span_sane speed (Steve Wahl)

  Scheduler debugging:

   - Move and extend the sched_process_exit() tracepoint (Andrii
     Nakryiko)

   - Add RT_GROUP WARN checks for non-root task_groups (Michal Koutný)

   - Fix trace_sched_switch(.prev_state) (Peter Zijlstra)

   - Untangle cond_resched() and live-patching (Peter Zijlstra)

  Fixes and cleanups:

   - Misc fixes and cleanups (K Prateek Nayak, Michal Koutný, Peter
     Zijlstra, Xuewen Yan)"

* tag 'sched-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  sched/uclamp: Align uclamp and util_est and call before freq update
  sched/util_est: Simplify condition for util_est_{en,de}queue()
  sched/fair: Fixup wake_up_sync() vs DELAYED_DEQUEUE
  sched,livepatch: Untangle cond_resched() and live-patching
  sched/core: Tweak wait_task_inactive() to force dequeue sched_delayed tasks
  sched/fair: Adhere to place_entity() constraints
  sched/debug: Print the local group's asym_prefer_cpu
  cpufreq/amd-pstate: Update asym_prefer_cpu when core rankings change
  sched/topology: Introduce sched_update_asym_prefer_cpu()
  sched/fair: Use READ_ONCE() to read sg->asym_prefer_cpu
  sched/isolation: Make use of more than one housekeeping cpu
  sched/rt: Fix race in push_rt_task
  sched: Add annotations to RT_GROUP_SCHED fields
  sched: Add RT_GROUP WARN checks for non-root task_groups
  sched: Do not construct nor expose RT_GROUP_SCHED structures if disabled
  sched: Bypass bandwitdh checks with runtime disabled RT_GROUP_SCHED
  sched: Skip non-root task_groups with disabled RT_GROUP_SCHED
  sched: Add commadline option for RT_GROUP_SCHED toggling
  sched: Always initialize rt_rq's task_group
  sched: Remove unneeed macro wrap
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -6320,6 +6320,11 @@
 			Memory area to be used by remote processor image,
 			managed by CMA.
 
+	rt_group_sched=	[KNL] Enable or disable SCHED_RR/FIFO group scheduling
+			when CONFIG_RT_GROUP_SCHED=y. Defaults to
+			!CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED.
+			Format: <bool>
+
 	rw		[KNL] Mount root device read-write on boot
 
 	S		[KNL] Run init in single mode

drivers/cpufreq/amd-pstate.c

@@ -831,8 +831,10 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	if (highest_perf_changed) {
 		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
 
-		if (cur_high < CPPC_MAX_PERF)
+		if (cur_high < CPPC_MAX_PERF) {
 			sched_set_itmt_core_prio((int)cur_high, cpu);
+			sched_update_asym_prefer_cpu(cpu, prev_high, cur_high);
+		}
 	}
 }
 

include/linux/livepatch_sched.h

@@ -3,27 +3,23 @@
 #define _LINUX_LIVEPATCH_SCHED_H_
 
 #include <linux/jump_label.h>
-#include <linux/static_call_types.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_LIVEPATCH
 
 void __klp_sched_try_switch(void);
 
-#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
 DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
 
-static __always_inline void klp_sched_try_switch(void)
+static __always_inline void klp_sched_try_switch(struct task_struct *curr)
 {
-	if (static_branch_unlikely(&klp_sched_try_switch_key))
+	if (static_branch_unlikely(&klp_sched_try_switch_key) &&
+	    READ_ONCE(curr->__state) & TASK_FREEZABLE)
 		__klp_sched_try_switch();
 }
 
-#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 #else /* !CONFIG_LIVEPATCH */
-static inline void klp_sched_try_switch(void) {}
+static inline void klp_sched_try_switch(struct task_struct *curr) {}
-static inline void __klp_sched_try_switch(void) {}
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_SCHED_H_ */

include/linux/sched.h

@@ -44,7 +44,6 @@
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
-#include <linux/livepatch_sched.h>
 #include <linux/uidgid_types.h>
 #include <linux/tracepoint-defs.h>
 #include <asm/kmap_size.h>
@@ -2089,9 +2088,6 @@ extern int __cond_resched(void);
 
 #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
-void sched_dynamic_klp_enable(void);
-void sched_dynamic_klp_disable(void);
-
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
 static __always_inline int _cond_resched(void)
@@ -2112,7 +2108,6 @@ static __always_inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return __cond_resched();
 }
 
@@ -2122,7 +2117,6 @@ static inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return 0;
 }
 

include/linux/sched/topology.h

@@ -195,6 +195,8 @@ struct sched_domain_topology_level {
 };
 
 extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
+extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio);
+
 
 # define SD_INIT_NAME(type)		.name = #type
 
@@ -223,6 +225,10 @@ static inline bool cpus_share_resources(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)

include/trace/events/sched.h

@@ -326,11 +326,37 @@ DEFINE_EVENT(sched_process_template, sched_process_free,
 	     TP_ARGS(p));
 
 /*
- * Tracepoint for a task exiting:
+ * Tracepoint for a task exiting.
+ * Note, it's a superset of sched_process_template and should be kept
+ * compatible as much as possible. sched_process_exits has an extra
+ * `group_dead` argument, so sched_process_template can't be used,
+ * unfortunately, just like sched_migrate_task above.
  */
-DEFINE_EVENT(sched_process_template, sched_process_exit,
+TRACE_EVENT(sched_process_exit,
-	     TP_PROTO(struct task_struct *p),
+
-	     TP_ARGS(p));
+	TP_PROTO(struct task_struct *p, bool group_dead),
+
+	TP_ARGS(p, group_dead),
+
+	TP_STRUCT__entry(
+		__array(	char,	comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	pid			)
+		__field(	int,	prio			)
+		__field(	bool,	group_dead		)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+		__entry->pid		= p->pid;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
+		__entry->group_dead	= group_dead;
+	),
+
+	TP_printk("comm=%s pid=%d prio=%d group_dead=%s",
+		  __entry->comm, __entry->pid, __entry->prio,
+		  __entry->group_dead ? "true" : "false"
+	)
+);
 
 /*
  * Tracepoint for waiting on task to unschedule:

init/Kconfig

@@ -1075,6 +1075,17 @@ config RT_GROUP_SCHED
 	  realtime bandwidth for them.
 	  See Documentation/scheduler/sched-rt-group.rst for more information.
 
+config RT_GROUP_SCHED_DEFAULT_DISABLED
+	bool "Require boot parameter to enable group scheduling for SCHED_RR/FIFO"
+	depends on RT_GROUP_SCHED
+	default n
+	help
+	  When set, the RT group scheduling is disabled by default. The option
+	  is in inverted form so that mere RT_GROUP_SCHED enables the group
+	  scheduling.
+
+	  Say N if unsure.
+
 config EXT_GROUP_SCHED
 	bool
 	depends on SCHED_CLASS_EXT && CGROUP_SCHED

kernel/exit.c

@@ -942,12 +942,12 @@ void __noreturn do_exit(long code)
 
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
+	trace_sched_process_exit(tsk, group_dead);
 
 	exit_mm();
 
 	if (group_dead)
 		acct_process();
-	trace_sched_process_exit(tsk);
 
 	exit_sem(tsk);
 	exit_shm(tsk);

kernel/livepatch/transition.c

@@ -29,22 +29,13 @@ static unsigned int klp_signals_cnt;
 
 /*
  * When a livepatch is in progress, enable klp stack checking in
- * cond_resched().  This helps CPU-bound kthreads get patched.
+ * schedule().  This helps CPU-bound kthreads get patched.
  */
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-#define klp_cond_resched_enable() sched_dynamic_klp_enable()
-#define klp_cond_resched_disable() sched_dynamic_klp_disable()
-
-#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
 DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
-EXPORT_SYMBOL(klp_sched_try_switch_key);
 
-#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
-#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
+#define klp_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
-
-#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
 /*
  * This work can be performed periodically to finish patching or unpatching any
@@ -365,27 +356,19 @@ static bool klp_try_switch_task(struct task_struct *task)
 
 void __klp_sched_try_switch(void)
 {
+	/*
+	 * This function is called from __schedule() while a context switch is
+	 * about to happen. Preemption is already disabled and klp_mutex
+	 * can't be acquired.
+	 * Disabled preemption is used to prevent racing with other callers of
+	 * klp_try_switch_task(). Thanks to task_call_func() they won't be
+	 * able to switch to this task while it's running.
+	 */
+	lockdep_assert_preemption_disabled();
+
 	if (likely(!klp_patch_pending(current)))
 		return;
 
-	/*
-	 * This function is called from cond_resched() which is called in many
-	 * places throughout the kernel.  Using the klp_mutex here might
-	 * deadlock.
-	 *
-	 * Instead, disable preemption to prevent racing with other callers of
-	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
-	 * able to switch this task while it's running.
-	 */
-	preempt_disable();
-
-	/*
-	 * Make sure current didn't get patched between the above check and
-	 * preempt_disable().
-	 */
-	if (unlikely(!klp_patch_pending(current)))
-		goto out;
-
 	/*
 	 * Enforce the order of the TIF_PATCH_PENDING read above and the
 	 * klp_target_state read in klp_try_switch_task().  The corresponding
@@ -395,11 +378,7 @@ void __klp_sched_try_switch(void)
 	smp_rmb();
 
 	klp_try_switch_task(current);
-
-out:
-	preempt_enable();
 }
-EXPORT_SYMBOL(__klp_sched_try_switch);
 
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
@@ -508,7 +487,7 @@ void klp_try_complete_transition(void)
 	}
 
 	/* Done!  Now cleanup the data structures. */
-	klp_cond_resched_disable();
+	klp_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -560,7 +539,7 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
-	klp_cond_resched_enable();
+	klp_resched_enable();
 
 	klp_signals_cnt = 0;
 }

kernel/sched/core.c

@@ -66,6 +66,7 @@
 #include <linux/vtime.h>
 #include <linux/wait_api.h>
 #include <linux/workqueue_api.h>
+#include <linux/livepatch_sched.h>
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 # ifdef CONFIG_GENERIC_ENTRY
@@ -1752,7 +1753,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	}
 }
 
-static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags)
 {
 	enum uclamp_id clamp_id;
 
@@ -1768,7 +1769,8 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
-	if (p->se.sched_delayed)
+	/* Only inc the delayed task which being woken up. */
+	if (p->se.sched_delayed && !(flags & ENQUEUE_DELAYED))
 		return;
 
 	for_each_clamp_id(clamp_id)
@@ -2036,7 +2038,7 @@ static void __init init_uclamp(void)
 }
 
 #else /* !CONFIG_UCLAMP_TASK */
-static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { }
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags) { }
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
 static inline void uclamp_fork(struct task_struct *p) { }
 static inline void uclamp_post_fork(struct task_struct *p) { }
@@ -2072,12 +2074,14 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	p->sched_class->enqueue_task(rq, p, flags);
 	/*
-	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
+	 * Can be before ->enqueue_task() because uclamp considers the
-	 * ->sched_delayed.
+	 * ENQUEUE_DELAYED task before its ->sched_delayed gets cleared
+	 * in ->enqueue_task().
 	 */
-	uclamp_rq_inc(rq, p);
+	uclamp_rq_inc(rq, p, flags);
+
+	p->sched_class->enqueue_task(rq, p, flags);
 
 	psi_enqueue(p, flags);
 
@@ -2283,6 +2287,12 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &rf);
+		/*
+		 * If task is sched_delayed, force dequeue it, to avoid always
+		 * hitting the tick timeout in the queued case
+		 */
+		if (p->se.sched_delayed)
+			dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		trace_sched_wait_task(p);
 		running = task_on_cpu(rq, p);
 		queued = task_on_rq_queued(p);
@@ -6571,12 +6581,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Otherwise marks the task's __state as RUNNING
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-			      unsigned long task_state)
+			      unsigned long *task_state_p)
 {
+	unsigned long task_state = *task_state_p;
 	int flags = DEQUEUE_NOCLOCK;
 
 	if (signal_pending_state(task_state, p)) {
 		WRITE_ONCE(p->__state, TASK_RUNNING);
+		*task_state_p = TASK_RUNNING;
 		return false;
 	}
 
@@ -6668,6 +6680,8 @@ static void __sched notrace __schedule(int sched_mode)
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
+	klp_sched_try_switch(prev);
+
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
 
@@ -6713,7 +6727,7 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		try_to_block_task(rq, prev, prev_state);
+		try_to_block_task(rq, prev, &prev_state);
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7328,7 +7342,6 @@ EXPORT_STATIC_CALL_TRAMP(might_resched);
 static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
 int __sched dynamic_cond_resched(void)
 {
-	klp_sched_try_switch();
 	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
 		return 0;
 	return __cond_resched();
@@ -7500,7 +7513,6 @@ int sched_dynamic_mode(const char *str)
 #endif
 
 static DEFINE_MUTEX(sched_dynamic_mutex);
-static bool klp_override;
 
 static void __sched_dynamic_update(int mode)
 {
@@ -7508,7 +7520,6 @@ static void __sched_dynamic_update(int mode)
 	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
 	 * the ZERO state, which is invalid.
 	 */
-	if (!klp_override)
 	preempt_dynamic_enable(cond_resched);
 	preempt_dynamic_enable(might_resched);
 	preempt_dynamic_enable(preempt_schedule);
@@ -7518,7 +7529,6 @@ static void __sched_dynamic_update(int mode)
 
 	switch (mode) {
 	case preempt_dynamic_none:
-		if (!klp_override)
 		preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
@@ -7530,7 +7540,6 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_voluntary:
-		if (!klp_override)
 		preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_enable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
@@ -7542,7 +7551,6 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_full:
-		if (!klp_override)
 		preempt_dynamic_disable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_enable(preempt_schedule);
@@ -7554,7 +7562,6 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_lazy:
-		if (!klp_override)
 		preempt_dynamic_disable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_enable(preempt_schedule);
@@ -7576,36 +7583,6 @@ void sched_dynamic_update(int mode)
 	mutex_unlock(&sched_dynamic_mutex);
 }
 
-#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-
-static int klp_cond_resched(void)
-{
-	__klp_sched_try_switch();
-	return __cond_resched();
-}
-
-void sched_dynamic_klp_enable(void)
-{
-	mutex_lock(&sched_dynamic_mutex);
-
-	klp_override = true;
-	static_call_update(cond_resched, klp_cond_resched);
-
-	mutex_unlock(&sched_dynamic_mutex);
-}
-
-void sched_dynamic_klp_disable(void)
-{
-	mutex_lock(&sched_dynamic_mutex);
-
-	klp_override = false;
-	__sched_dynamic_update(preempt_dynamic_mode);
-
-	mutex_unlock(&sched_dynamic_mutex);
-}
-
-#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 static int __init setup_preempt_mode(char *str)
 {
 	int mode = sched_dynamic_mode(str);
@@ -9018,7 +8995,7 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 	unsigned long flags;
 
 	spin_lock_irqsave(&task_group_lock, flags);
-	list_add_rcu(&tg->list, &task_groups);
+	list_add_tail_rcu(&tg->list, &task_groups);
 
 	/* Root should already exist: */
 	WARN_ON(!parent);
@@ -9204,11 +9181,15 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 	struct task_struct *task;
 	struct cgroup_subsys_state *css;
 
+	if (!rt_group_sched_enabled())
+		goto scx_check;
+
 	cgroup_taskset_for_each(task, css, tset) {
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
 	}
-#endif
+scx_check:
+#endif /* CONFIG_RT_GROUP_SCHED */
 	return scx_cgroup_can_attach(tset);
 }
 
@@ -9861,18 +9842,6 @@ static struct cftype cpu_legacy_files[] = {
 		.seq_show = cpu_cfs_local_stat_show,
 	},
 #endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	{
-		.name = "rt_runtime_us",
-		.read_s64 = cpu_rt_runtime_read,
-		.write_s64 = cpu_rt_runtime_write,
-	},
-	{
-		.name = "rt_period_us",
-		.read_u64 = cpu_rt_period_read_uint,
-		.write_u64 = cpu_rt_period_write_uint,
-	},
-#endif
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	{
 		.name = "uclamp.min",
@@ -9890,6 +9859,55 @@ static struct cftype cpu_legacy_files[] = {
 	{ }	/* Terminate */
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static struct cftype rt_group_files[] = {
+	{
+		.name = "rt_runtime_us",
+		.read_s64 = cpu_rt_runtime_read,
+		.write_s64 = cpu_rt_runtime_write,
+	},
+	{
+		.name = "rt_period_us",
+		.read_u64 = cpu_rt_period_read_uint,
+		.write_u64 = cpu_rt_period_write_uint,
+	},
+	{ }	/* Terminate */
+};
+
+# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
+DEFINE_STATIC_KEY_FALSE(rt_group_sched);
+# else
+DEFINE_STATIC_KEY_TRUE(rt_group_sched);
+# endif
+
+static int __init setup_rt_group_sched(char *str)
+{
+	long val;
+
+	if (kstrtol(str, 0, &val) || val < 0 || val > 1) {
+		pr_warn("Unable to set rt_group_sched\n");
+		return 1;
+	}
+	if (val)
+		static_branch_enable(&rt_group_sched);
+	else
+		static_branch_disable(&rt_group_sched);
+
+	return 1;
+}
+__setup("rt_group_sched=", setup_rt_group_sched);
+
+static int __init cpu_rt_group_init(void)
+{
+	if (!rt_group_sched_enabled())
+		return 0;
+
+	WARN_ON(cgroup_add_legacy_cftypes(&cpu_cgrp_subsys, rt_group_files));
+	return 0;
+}
+subsys_initcall(cpu_rt_group_init);
+#endif /* CONFIG_RT_GROUP_SCHED */
+
 static int cpu_extra_stat_show(struct seq_file *sf,
 			       struct cgroup_subsys_state *css)
 {

kernel/sched/debug.c

@@ -588,6 +588,10 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
 	debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
 	debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
 	debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level);
+
+	if (sd->flags & SD_ASYM_PACKING)
+		debugfs_create_u32("group_asym_prefer_cpu", 0444, parent,
+				   (u32 *)&sd->groups->asym_prefer_cpu);
 }
 
 void update_sched_domain_debugfs(void)

kernel/sched/fair.c

@@ -3795,6 +3795,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		update_entity_lag(cfs_rq, se);
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
+		cfs_rq->nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
@@ -3821,10 +3822,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
-		update_load_add(&cfs_rq->load, se->load.weight);
 		place_entity(cfs_rq, se, 0);
+		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
+		cfs_rq->nr_queued++;
 
 		/*
 		 * The entity's vruntime has been adjusted, so let's check
@@ -4932,13 +4934,6 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	if (last_ewma_diff < UTIL_EST_MARGIN)
 		goto done;
 
-	/*
-	 * To avoid overestimation of actual task utilization, skip updates if
-	 * we cannot grant there is idle time in this CPU.
-	 */
-	if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
-		return;
-
 	/*
 	 * To avoid underestimate of task utilization, skip updates of EWMA if
 	 * we cannot grant that thread got all CPU time it wanted.
@@ -6941,7 +6936,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
+	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
 		util_est_enqueue(&rq->cfs, p);
 
 	if (flags & ENQUEUE_DELAYED) {
@@ -7181,7 +7176,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
+	if (!p->se.sched_delayed)
 		util_est_dequeue(&rq->cfs, p);
 
 	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
@@ -7196,6 +7191,11 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	return true;
 }
 
+static inline unsigned int cfs_h_nr_delayed(struct rq *rq)
+{
+	return (rq->cfs.h_nr_queued - rq->cfs.h_nr_runnable);
+}
+
 #ifdef CONFIG_SMP
 
 /* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */
@@ -7357,8 +7357,12 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
 		return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
 
-	if (sync && cpu_rq(this_cpu)->nr_running == 1)
+	if (sync) {
+		struct rq *rq = cpu_rq(this_cpu);
+
+		if ((rq->nr_running - cfs_h_nr_delayed(rq)) == 1)
 			return this_cpu;
+	}
 
 	if (available_idle_cpu(prev_cpu))
 		return prev_cpu;
@@ -10256,7 +10260,7 @@ sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group
 	    (sgs->group_weight - sgs->idle_cpus != 1))
 		return false;
 
-	return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu);
+	return sched_asym(env->sd, env->dst_cpu, READ_ONCE(group->asym_prefer_cpu));
 }
 
 /* One group has more than one SMT CPU while the other group does not */
@@ -10493,7 +10497,8 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 	case group_asym_packing:
 		/* Prefer to move from lowest priority CPU's work */
-		return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu);
+		return sched_asym_prefer(READ_ONCE(sds->busiest->asym_prefer_cpu),
+					 READ_ONCE(sg->asym_prefer_cpu));
 
 	case group_misfit_task:
 		/*

kernel/sched/isolation.c

@@ -40,7 +40,7 @@ int housekeeping_any_cpu(enum hk_type type)
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			cpu = cpumask_any_and_distribute(housekeeping.cpumasks[type], cpu_online_mask);
 			if (likely(cpu < nr_cpu_ids))
 				return cpu;
 			/*

kernel/sched/rt.c

@@ -89,6 +89,7 @@ void init_rt_rq(struct rt_rq *rt_rq)
 	rt_rq->rt_throttled = 0;
 	rt_rq->rt_runtime = 0;
 	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
+	rt_rq->tg = &root_task_group;
 #endif
 }
 
@@ -175,11 +176,14 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
+	/* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 	return rt_rq->rq;
 }
 
 static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 {
+	WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
 	return rt_se->rt_rq;
 }
 
@@ -187,11 +191,15 @@ static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_se->rt_rq;
 
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 	return rt_rq->rq;
 }
 
 void unregister_rt_sched_group(struct task_group *tg)
 {
+	if (!rt_group_sched_enabled())
+		return;
+
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
 }
@@ -200,6 +208,9 @@ void free_rt_sched_group(struct task_group *tg)
 {
 	int i;
 
+	if (!rt_group_sched_enabled())
+		return;
+
 	for_each_possible_cpu(i) {
 		if (tg->rt_rq)
 			kfree(tg->rt_rq[i]);
@@ -244,6 +255,9 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	struct sched_rt_entity *rt_se;
 	int i;
 
+	if (!rt_group_sched_enabled())
+		return 1;
+
 	tg->rt_rq = kcalloc(nr_cpu_ids, sizeof(rt_rq), GFP_KERNEL);
 	if (!tg->rt_rq)
 		goto err;
@@ -482,9 +496,6 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
 
 static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
 {
-	if (!rt_rq->tg)
-		return RUNTIME_INF;
-
 	return rt_rq->rt_runtime;
 }
 
@@ -497,6 +508,11 @@ typedef struct task_group *rt_rq_iter_t;
 
 static inline struct task_group *next_task_group(struct task_group *tg)
 {
+	if (!rt_group_sched_enabled()) {
+		WARN_ON(tg != &root_task_group);
+		return NULL;
+	}
+
 	do {
 		tg = list_entry_rcu(tg->list.next,
 			typeof(struct task_group), list);
@@ -509,9 +525,9 @@ static inline struct task_group *next_task_group(struct task_group *tg)
 }
 
 #define for_each_rt_rq(rt_rq, iter, rq)					\
-	for (iter = container_of(&task_groups, typeof(*iter), list);	\
+	for (iter = &root_task_group;					\
-		(iter = next_task_group(iter)) &&			\
+		iter && (rt_rq = iter->rt_rq[cpu_of(rq)]);		\
-		(rt_rq = iter->rt_rq[cpu_of(rq)]);)
+		iter = next_task_group(iter))
 
 #define for_each_sched_rt_entity(rt_se) \
 	for (; rt_se; rt_se = rt_se->parent)
@@ -1066,13 +1082,12 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	/*
 	 * Change rq's cpupri only if rt_rq is the top queue.
 	 */
-	if (&rq->rt != rt_rq)
+	if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
 		return;
-#endif
+
 	if (rq->online && prio < prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
@@ -1082,13 +1097,12 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	/*
 	 * Change rq's cpupri only if rt_rq is the top queue.
 	 */
-	if (&rq->rt != rt_rq)
+	if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
 		return;
-#endif
+
 	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
@@ -1156,7 +1170,6 @@ inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	if (rt_se_boosted(rt_se))
 		rt_rq->rt_nr_boosted++;
 
-	if (rt_rq->tg)
 	start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
 }
 
@@ -1257,11 +1270,9 @@ static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_arr
 static inline struct sched_statistics *
 __schedstats_from_rt_se(struct sched_rt_entity *rt_se)
 {
-#ifdef CONFIG_RT_GROUP_SCHED
 	/* schedstats is not supported for rt group. */
 	if (!rt_entity_is_task(rt_se))
 		return NULL;
-#endif
 
 	return &rt_task_of(rt_se)->stats;
 }
@@ -1883,6 +1894,27 @@ static int find_lowest_rq(struct task_struct *task)
 	return -1;
 }
 
+static struct task_struct *pick_next_pushable_task(struct rq *rq)
+{
+	struct task_struct *p;
+
+	if (!has_pushable_tasks(rq))
+		return NULL;
+
+	p = plist_first_entry(&rq->rt.pushable_tasks,
+			      struct task_struct, pushable_tasks);
+
+	BUG_ON(rq->cpu != task_cpu(p));
+	BUG_ON(task_current(rq, p));
+	BUG_ON(task_current_donor(rq, p));
+	BUG_ON(p->nr_cpus_allowed <= 1);
+
+	BUG_ON(!task_on_rq_queued(p));
+	BUG_ON(!rt_task(p));
+
+	return p;
+}
+
 /* Will lock the rq it finds */
 static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 {
@@ -1913,18 +1945,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			/*
 			 * We had to unlock the run queue. In
 			 * the mean time, task could have
-			 * migrated already or had its affinity changed.
+			 * migrated already or had its affinity changed,
-			 * Also make sure that it wasn't scheduled on its rq.
+			 * therefore check if the task is still at the
+			 * head of the pushable tasks list.
 			 * It is possible the task was scheduled, set
 			 * "migrate_disabled" and then got preempted, so we must
 			 * check the task migration disable flag here too.
 			 */
-			if (unlikely(task_rq(task) != rq ||
+			if (unlikely(is_migration_disabled(task) ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
-				     task_on_cpu(rq, task) ||
+				     task != pick_next_pushable_task(rq))) {
-				     !rt_task(task) ||
-				     is_migration_disabled(task) ||
-				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
 				lowest_rq = NULL;
@@ -1944,27 +1974,6 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 	return lowest_rq;
 }
 
-static struct task_struct *pick_next_pushable_task(struct rq *rq)
-{
-	struct task_struct *p;
-
-	if (!has_pushable_tasks(rq))
-		return NULL;
-
-	p = plist_first_entry(&rq->rt.pushable_tasks,
-			      struct task_struct, pushable_tasks);
-
-	BUG_ON(rq->cpu != task_cpu(p));
-	BUG_ON(task_current(rq, p));
-	BUG_ON(task_current_donor(rq, p));
-	BUG_ON(p->nr_cpus_allowed <= 1);
-
-	BUG_ON(!task_on_rq_queued(p));
-	BUG_ON(!rt_task(p));
-
-	return p;
-}
-
 /*
  * If the current CPU has more than one RT task, see if the non
  * running task can migrate over to a CPU that is running a task
@@ -2602,8 +2611,9 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
 {
 	struct rt_rq *rt_rq;
 
-#ifdef CONFIG_RT_GROUP_SCHED
+#ifdef CONFIG_RT_GROUP_SCHED // XXX maybe add task_rt_rq(), see also sched_rt_period_rt_rq
 	rt_rq = task_group(p)->rt_rq[cpu];
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 #else
 	rt_rq = &cpu_rq(cpu)->rt;
 #endif
@@ -2713,6 +2723,9 @@ static int tg_rt_schedulable(struct task_group *tg, void *data)
 	    tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
+	if (WARN_ON(!rt_group_sched_enabled() && tg != &root_task_group))
+		return -EBUSY;
+
 	total = to_ratio(period, runtime);
 
 	/*
@@ -2868,7 +2881,7 @@ static int sched_rt_global_constraints(void)
 int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 {
 	/* Don't accept real-time tasks when there is no way for them to run */
-	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+	if (rt_group_sched_enabled() && rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
 		return 0;
 
 	return 1;

kernel/sched/sched.h

@@ -813,15 +813,17 @@ struct rt_rq {
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	int			rt_throttled;
-	u64			rt_time;
+	u64			rt_time; /* consumed RT time, goes up in update_curr_rt */
-	u64			rt_runtime;
+	u64			rt_runtime; /* allotted RT time, "slice" from rt_bandwidth, RT sharing/balancing */
 	/* Nests inside the rq lock: */
 	raw_spinlock_t		rt_runtime_lock;
 
 	unsigned int		rt_nr_boosted;
 
-	struct rq		*rq;
+	struct rq		*rq; /* this is always top-level rq, cache? */
-	struct task_group	*tg;
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group	*tg; /* this tg has "this" rt_rq on given CPU for runnable entities */
 #endif
 };
 
@@ -1498,6 +1500,23 @@ static inline bool sched_group_cookie_match(struct rq *rq,
 }
 
 #endif /* !CONFIG_SCHED_CORE */
+#ifdef CONFIG_RT_GROUP_SCHED
+# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
+DECLARE_STATIC_KEY_FALSE(rt_group_sched);
+static inline bool rt_group_sched_enabled(void)
+{
+	return static_branch_unlikely(&rt_group_sched);
+}
+# else
+DECLARE_STATIC_KEY_TRUE(rt_group_sched);
+static inline bool rt_group_sched_enabled(void)
+{
+	return static_branch_likely(&rt_group_sched);
+}
+# endif /* CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED */
+#else
+# define rt_group_sched_enabled()	false
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 static inline void lockdep_assert_rq_held(struct rq *rq)
 {
@@ -2146,6 +2165,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * p->rt.rt_rq is NULL initially and it is easier to assign
+	 * root_task_group's rt_rq than switching in rt_rq_of_se()
+	 * Clobbers tg(!)
+	 */
+	if (!rt_group_sched_enabled())
+		tg = &root_task_group;
 	p->rt.rt_rq  = tg->rt_rq[cpu];
 	p->rt.parent = tg->rt_se[cpu];
 #endif

kernel/sched/syscalls.c

@@ -634,13 +634,14 @@ change:
 		 * Do not allow real-time tasks into groups that have no runtime
 		 * assigned.
 		 */
-		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+		if (rt_group_sched_enabled() &&
+				rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
 			retval = -EPERM;
 			goto unlock;
 		}
-#endif
+#endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_SMP
 		if (dl_bandwidth_enabled() && dl_policy(policy) &&
 				!(attr->sched_flags & SCHED_FLAG_SUGOV)) {

kernel/sched/topology.c

@@ -1333,6 +1333,64 @@ next:
 	update_group_capacity(sd, cpu);
 }
 
+#ifdef CONFIG_SMP
+
+/* Update the "asym_prefer_cpu" when arch_asym_cpu_priority() changes. */
+void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+	int asym_prefer_cpu = cpu;
+	struct sched_domain *sd;
+
+	guard(rcu)();
+
+	for_each_domain(cpu, sd) {
+		struct sched_group *sg;
+		int group_cpu;
+
+		if (!(sd->flags & SD_ASYM_PACKING))
+			continue;
+
+		/*
+		 * Groups of overlapping domain are replicated per NUMA
+		 * node and will require updating "asym_prefer_cpu" on
+		 * each local copy.
+		 *
+		 * If you are hitting this warning, consider moving
+		 * "sg->asym_prefer_cpu" to "sg->sgc->asym_prefer_cpu"
+		 * which is shared by all the overlapping groups.
+		 */
+		WARN_ON_ONCE(sd->flags & SD_OVERLAP);
+
+		sg = sd->groups;
+		if (cpu != sg->asym_prefer_cpu) {
+			/*
+			 * Since the parent is a superset of the current group,
+			 * if the cpu is not the "asym_prefer_cpu" at the
+			 * current level, it cannot be the preferred CPU at a
+			 * higher levels either.
+			 */
+			if (!sched_asym_prefer(cpu, sg->asym_prefer_cpu))
+				return;
+
+			WRITE_ONCE(sg->asym_prefer_cpu, cpu);
+			continue;
+		}
+
+		/* Ranking has improved; CPU is still the preferred one. */
+		if (new_prio >= old_prio)
+			continue;
+
+		for_each_cpu(group_cpu, sched_group_span(sg)) {
+			if (sched_asym_prefer(group_cpu, asym_prefer_cpu))
+				asym_prefer_cpu = group_cpu;
+		}
+
+		WRITE_ONCE(sg->asym_prefer_cpu, asym_prefer_cpu);
+	}
+}
+
+#endif /* CONFIG_SMP */
+
 /*
  * Set of available CPUs grouped by their corresponding capacities
  * Each list entry contains a CPU mask reflecting CPUs that share the same
@@ -2098,7 +2156,7 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		if (!masks[i][j])
 			break;
-		cpu = cpumask_any_and(cpus, masks[i][j]);
+		cpu = cpumask_any_and_distribute(cpus, masks[i][j]);
 		if (cpu < nr_cpu_ids) {
 			found = cpu;
 			break;
@@ -2347,16 +2405,26 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 
 /*
  * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
- * any two given CPUs at this (non-NUMA) topology level.
+ * any two given CPUs on non-NUMA topology levels.
  */
-static bool topology_span_sane(struct sched_domain_topology_level *tl,
+static bool topology_span_sane(const struct cpumask *cpu_map)
-			      const struct cpumask *cpu_map, int cpu)
 {
-	int i = cpu + 1;
+	struct sched_domain_topology_level *tl;
+	struct cpumask *covered, *id_seen;
+	int cpu;
+
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+	id_seen = sched_domains_tmpmask2;
+
+	for_each_sd_topology(tl) {
 
 		/* NUMA levels are allowed to overlap */
 		if (tl->flags & SDTL_OVERLAP)
-		return true;
+			continue;
+
+		cpumask_clear(covered);
+		cpumask_clear(id_seen);
 
 		/*
 		 * Non-NUMA levels cannot partially overlap - they must be either
@@ -2364,18 +2432,27 @@ static bool topology_span_sane(struct sched_domain_topology_level *tl,
 		 * breaking the sched_group lists - i.e. a later get_group() pass
 		 * breaks the linking done for an earlier span.
 		 */
-	for_each_cpu_from(i, cpu_map) {
+		for_each_cpu(cpu, cpu_map) {
-		/*
+			const struct cpumask *tl_cpu_mask = tl->mask(cpu);
-		 * We should 'and' all those masks with 'cpu_map' to exactly
+			int id;
-		 * match the topology we're about to build, but that can only
-		 * remove CPUs, which only lessens our ability to detect
-		 * overlaps
-		 */
-		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
-		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
-			return false;
-	}
 
+			/* lowest bit set in this mask is used as a unique id */
+			id = cpumask_first(tl_cpu_mask);
+
+			if (cpumask_test_cpu(id, id_seen)) {
+				/* First CPU has already been seen, ensure identical spans */
+				if (!cpumask_equal(tl->mask(id), tl_cpu_mask))
+					return false;
+			} else {
+				/* First CPU hasn't been seen before, ensure it's a completely new span */
+				if (cpumask_intersects(tl_cpu_mask, covered))
+					return false;
+
+				cpumask_or(covered, covered, tl_cpu_mask);
+				cpumask_set_cpu(id, id_seen);
+			}
+		}
+	}
 	return true;
 }
 
@@ -2408,9 +2485,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		sd = NULL;
 		for_each_sd_topology(tl) {
 
-			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
-				goto error;
-
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 
 			has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
@@ -2424,6 +2498,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		}
 	}
 
+	if (WARN_ON(!topology_span_sane(cpu_map)))
+		goto error;
+
 	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {