Merge tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

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

   - Cancel the slice protection of the idle entity (Zihan Zhou)
   - Reduce the default slice to avoid tasks getting an extra tick
     (Zihan Zhou)
   - Force propagating min_slice of cfs_rq when {en,de}queue tasks
     (Tianchen Ding)
   - Refactor can_migrate_task() to elimate looping (I Hsin Cheng)
   - Add unlikey branch hints to several system calls (Colin Ian King)
   - Optimize current_clr_polling() on certain architectures (Yujun
     Dong)

  Deadline scheduler: (Juri Lelli)
   - Remove redundant dl_clear_root_domain call
   - Move dl_rebuild_rd_accounting to cpuset.h

  Uclamp:
   - Use the uclamp_is_used() helper instead of open-coding it (Xuewen
     Yan)
   - Optimize sched_uclamp_used static key enabling (Xuewen Yan)

  Scheduler topology support: (Juri Lelli)
   - Ignore special tasks when rebuilding domains
   - Add wrappers for sched_domains_mutex
   - Generalize unique visiting of root domains
   - Rebuild root domain accounting after every update
   - Remove partition_and_rebuild_sched_domains
   - Stop exposing partition_sched_domains_locked

  RSEQ: (Michael Jeanson)
   - Update kernel fields in lockstep with CONFIG_DEBUG_RSEQ=y
   - Fix segfault on registration when rseq_cs is non-zero
   - selftests: Add rseq syscall errors test
   - selftests: Ensure the rseq ABI TLS is actually 1024 bytes

  Membarriers:
   - Fix redundant load of membarrier_state (Nysal Jan K.A.)

  Scheduler debugging:
   - Introduce and use preempt_model_str() (Sebastian Andrzej Siewior)
   - Make CONFIG_SCHED_DEBUG unconditional (Ingo Molnar)

  Fixes and cleanups:
   - Always save/restore x86 TSC sched_clock() on suspend/resume
     (Guilherme G. Piccoli)
   - Misc fixes and cleanups (Thorsten Blum, Juri Lelli, Sebastian
     Andrzej Siewior)"

* tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  cpuidle, sched: Use smp_mb__after_atomic() in current_clr_polling()
  sched/debug: Remove CONFIG_SCHED_DEBUG
  sched/debug: Remove CONFIG_SCHED_DEBUG from self-test config files
  sched/debug, Documentation: Remove (most) CONFIG_SCHED_DEBUG references from documentation
  sched/debug: Make CONFIG_SCHED_DEBUG functionality unconditional
  sched/debug: Make 'const_debug' tunables unconditional __read_mostly
  sched/debug: Change SCHED_WARN_ON() to WARN_ON_ONCE()
  rseq/selftests: Fix namespace collision with rseq UAPI header
  include/{topology,cpuset}: Move dl_rebuild_rd_accounting to cpuset.h
  sched/topology: Stop exposing partition_sched_domains_locked
  cgroup/cpuset: Remove partition_and_rebuild_sched_domains
  sched/topology: Remove redundant dl_clear_root_domain call
  sched/deadline: Rebuild root domain accounting after every update
  sched/deadline: Generalize unique visiting of root domains
  sched/topology: Wrappers for sched_domains_mutex
  sched/deadline: Ignore special tasks when rebuilding domains
  tracing: Use preempt_model_str()
  xtensa: Rely on generic printing of preemption model
  x86: Rely on generic printing of preemption model
  s390: Rely on generic printing of preemption model
  ...

9 files changed, 45 insertions, 25 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 835e7b793f6a..5466c96a33db 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -125,9 +125,11 @@ static inline int cpuset_do_page_mem_spread(void)
 
 extern bool current_cpuset_is_being_rebound(void);
 
+extern void dl_rebuild_rd_accounting(void);
 extern void rebuild_sched_domains(void);
 
 extern void cpuset_print_current_mems_allowed(void);
+extern void cpuset_reset_sched_domains(void);
 
 /*
  * read_mems_allowed_begin is required when making decisions involving
@@ -259,11 +261,20 @@ static inline bool current_cpuset_is_being_rebound(void)
 	return false;
 }
 
+static inline void dl_rebuild_rd_accounting(void)
+{
+}
+
 static inline void rebuild_sched_domains(void)
 {
 	partition_sched_domains(1, NULL, NULL);
 }
 
+static inline void cpuset_reset_sched_domains(void)
+{
+	partition_sched_domains(1, NULL, NULL);
+}
+
 static inline void cpuset_print_current_mems_allowed(void)
 {
 }
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 78318d49276d..65efc0f5ea2e 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -240,9 +240,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	struct em_perf_state *ps;
 	int i;
 
-#ifdef CONFIG_SCHED_DEBUG
 	WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n");
-#endif
 
 	if (!sum_util)
 		return 0;
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index ca86235ac15c..3e9808f2b549 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -515,6 +515,8 @@ static inline bool preempt_model_rt(void)
 	return IS_ENABLED(CONFIG_PREEMPT_RT);
 }
 
+extern const char *preempt_model_str(void);
+
 /*
  * Does the preemption model allow non-cooperative preemption?
  *
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c15365a30c0..4659898c0299 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -382,6 +382,11 @@ enum uclamp_id {
 #ifdef CONFIG_SMP
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
+extern void sched_domains_mutex_lock(void);
+extern void sched_domains_mutex_unlock(void);
+#else
+static inline void sched_domains_mutex_lock(void) { }
+static inline void sched_domains_mutex_unlock(void) { }
 #endif
 
 struct sched_param {
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 3a912ab42bb5..f9aabbc9d22e 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -34,7 +34,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 struct root_domain;
 extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
+extern void dl_clear_root_domain_cpu(int cpu);
 
 #endif /* CONFIG_SMP */
 
+extern u64 dl_cookie;
+extern bool dl_bw_visited(int cpu, u64 cookie);
+
 #endif /* _LINUX_SCHED_DEADLINE_H */
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index b5035afa2396..35ed4577a6cc 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -35,12 +35,10 @@ extern void show_stack(struct task_struct *task, unsigned long *sp,
 
 extern void sched_show_task(struct task_struct *p);
 
-#ifdef CONFIG_SCHED_DEBUG
 struct seq_file;
 extern void proc_sched_show_task(struct task_struct *p,
 				 struct pid_namespace *ns, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
-#endif
 
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched		__section(".sched.text")
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index e670ac282333..439f6029d3b9 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -79,6 +79,21 @@ static __always_inline bool __must_check current_clr_polling_and_test(void)
 	return unlikely(tif_need_resched());
 }
 
+static __always_inline void current_clr_polling(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+	 * Once the bit is cleared, we'll get IPIs with every new
+	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+	 * fold.
+	 */
+	smp_mb__after_atomic(); /* paired with resched_curr() */
+
+	preempt_fold_need_resched();
+}
+
 #else
 static inline void __current_set_polling(void) { }
 static inline void __current_clr_polling(void) { }
@@ -91,21 +106,15 @@ static inline bool __must_check current_clr_polling_and_test(void)
 {
 	return unlikely(tif_need_resched());
 }
-#endif
 
 static __always_inline void current_clr_polling(void)
 {
 	__current_clr_polling();
 
-	/*
-	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
-	 * Once the bit is cleared, we'll get IPIs with every new
-	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
-	 * fold.
-	 */
 	smp_mb(); /* paired with resched_curr() */
 
 	preempt_fold_need_resched();
 }
+#endif
 
 #endif /* _LINUX_SCHED_IDLE_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 928a626725e6..b13474825130 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -531,6 +531,13 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	/*
+	 * The atomic_read() below prevents CSE. The following should
+	 * help the compiler generate more efficient code on architectures
+	 * where sync_core_before_usermode() is a no-op.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
+		return;
 	if (current->mm != mm)
 		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 7f3dbafe1817..7b4301b7235f 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -25,16 +25,12 @@ enum {
 };
 #undef SD_FLAG
 
-#ifdef CONFIG_SCHED_DEBUG
-
 struct sd_flag_debug {
 	unsigned int meta_flags;
 	char *name;
 };
 extern const struct sd_flag_debug sd_flag_debug[];
 
-#endif
-
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {
@@ -166,10 +162,6 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
-extern void partition_sched_domains_locked(int ndoms_new,
-					   cpumask_var_t doms_new[],
-					   struct sched_domain_attr *dattr_new);
-
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
@@ -211,12 +203,6 @@ extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
-			       struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline void
 partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {