Merge tag 'sched-core-2025-07-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

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

   - Better tracking of maximum lag of tasks in presence of different
     slices duration, for better handling of lag in the fair scheduler
     (Vincent Guittot)

   - Clean up and standardize #if/#else/#endif markers throughout the
     entire scheduler code base (Ingo Molnar)

   - Make SMP unconditional: build the SMP scheduler's data structures
     and logic on UP kernel too, even though they are not used, to
     simplify the scheduler and remove around 200 #ifdef/[#else]/#endif
     blocks from the scheduler (Ingo Molnar)

   - Reorganize cgroup bandwidth control interface handling for better
     interfacing with sched_ext (Tejun Heo)

  Balancing:

   - Bump sd->max_newidle_lb_cost when newidle balance fails (Chris
     Mason)

   - Remove sched_domain_topology_level::flags to simplify the code
     (Prateek Nayak)

   - Simplify and clean up build_sched_topology() (Li Chen)

   - Optimize build_sched_topology() on large machines (Li Chen)

  Real-time scheduling:

   - Add initial version of proxy execution: a mechanism for
     mutex-owning tasks to inherit the scheduling context of higher
     priority waiters.

     Currently limited to a single runqueue and conditional on
     CONFIG_EXPERT, and other limitations (John Stultz, Peter Zijlstra,
     Valentin Schneider)

   - Deadline scheduler (Juri Lelli):
      - Fix dl_servers initialization order (Juri Lelli)
      - Fix DL scheduler's root domain reinitialization logic (Juri
        Lelli)
      - Fix accounting bugs after global limits change (Juri Lelli)
      - Fix scalability regression by implementing less agressive
        dl_server handling (Peter Zijlstra)

  PSI:

   - Improve scalability by optimizing psi_group_change() cpu_clock()
     usage (Peter Zijlstra)

  Rust changes:

   - Make Task, CondVar and PollCondVar methods inline to avoid
     unnecessary function calls (Kunwu Chan, Panagiotis Foliadis)

   - Add might_sleep() support for Rust code: Rust's "#[track_caller]"
     mechanism is used so that Rust's might_sleep() doesn't need to be
     defined as a macro (Fujita Tomonori)

   - Introduce file_from_location() (Boqun Feng)

  Debugging & instrumentation:

   - Make clangd usable with scheduler source code files again (Peter
     Zijlstra)

   - tools: Add root_domains_dump.py which dumps root domains info (Juri
     Lelli)

   - tools: Add dl_bw_dump.py for printing bandwidth accounting info
     (Juri Lelli)

  Misc cleanups & fixes:

   - Remove play_idle() (Feng Lee)

   - Fix check_preemption_disabled() (Sebastian Andrzej Siewior)

   - Do not call __put_task_struct() on RT if pi_blocked_on is set (Luis
     Claudio R. Goncalves)

   - Correct the comment in place_entity() (wang wei)"

* tag 'sched-core-2025-07-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (84 commits)
  sched/idle: Remove play_idle()
  sched: Do not call __put_task_struct() on rt if pi_blocked_on is set
  sched: Start blocked_on chain processing in find_proxy_task()
  sched: Fix proxy/current (push,pull)ability
  sched: Add an initial sketch of the find_proxy_task() function
  sched: Fix runtime accounting w/ split exec & sched contexts
  sched: Move update_curr_task logic into update_curr_se
  locking/mutex: Add p->blocked_on wrappers for correctness checks
  locking/mutex: Rework task_struct::blocked_on
  sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable
  sched/topology: Remove sched_domain_topology_level::flags
  x86/smpboot: avoid SMT domain attach/destroy if SMT is not enabled
  x86/smpboot: moves x86_topology to static initialize and truncate
  x86/smpboot: remove redundant CONFIG_SCHED_SMT
  smpboot: introduce SDTL_INIT() helper to tidy sched topology setup
  tools/sched: Add dl_bw_dump.py for printing bandwidth accounting info
  tools/sched: Add root_domains_dump.py which dumps root domains info
  sched/deadline: Fix accounting after global limits change
  sched/deadline: Reset extra_bw to max_bw when clearing root domains
  sched/deadline: Initialize dl_servers after SMP
  ...

6 files changed, 14 insertions, 76 deletions

diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index f9aabbc9d22e..c40115d4e34d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -29,15 +29,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
-#ifdef CONFIG_SMP
-
 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);
 
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 439f6029d3b9..8465ff1f20d1 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -11,11 +11,7 @@ enum cpu_idle_type {
 	CPU_MAX_IDLE_TYPES
 };
 
-#ifdef CONFIG_SMP
 extern void wake_up_if_idle(int cpu);
-#else
-static inline void wake_up_if_idle(int cpu) { }
-#endif
 
 /*
  * Idle thread specific functions to determine the need_resched
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index 6d67e9a5af6b..0db7f67935fe 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -6,7 +6,7 @@
  * This is the interface between the scheduler and nohz/dynticks:
  */
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
 extern void nohz_balance_enter_idle(int cpu);
 extern int get_nohz_timer_target(void);
 #else
@@ -23,7 +23,7 @@ static inline void calc_load_nohz_remote(struct rq *rq) { }
 static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
-#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
+#ifdef CONFIG_NO_HZ_COMMON
 extern void wake_up_nohz_cpu(int cpu);
 #else
 static inline void wake_up_nohz_cpu(int cpu) { }
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index b04a5d04dee9..42839cfa2778 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -154,14 +154,6 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
 SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
 
 /*
- * sched_groups of this level overlap
- *
- * SHARED_PARENT: Set for all NUMA levels above NODE.
- * NEEDS_GROUPS: Overlaps can only exist with more than one group.
- */
-SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
-
-/*
  * Cross-node balancing
  *
  * SHARED_PARENT: Set for all NUMA levels above NODE.
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ca1db4b92c32..ea41795a352b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -109,11 +109,7 @@ int kernel_wait(pid_t pid, int *stat);
 extern void free_task(struct task_struct *tsk);
 
 /* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
 extern void sched_exec(void);
-#else
-#define sched_exec()   {}
-#endif
 
 static inline struct task_struct *get_task_struct(struct task_struct *t)
 {
@@ -135,24 +131,17 @@ static inline void put_task_struct(struct task_struct *t)
 		return;
 
 	/*
-	 * In !RT, it is always safe to call __put_task_struct().
-	 * Under RT, we can only call it in preemptible context.
-	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
-		static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
-
-		lock_map_acquire_try(&put_task_map);
-		__put_task_struct(t);
-		lock_map_release(&put_task_map);
-		return;
-	}
-
-	/*
-	 * under PREEMPT_RT, we can't call put_task_struct
+	 * Under PREEMPT_RT, we can't call __put_task_struct
 	 * in atomic context because it will indirectly
-	 * acquire sleeping locks.
+	 * acquire sleeping locks. The same is true if the
+	 * current process has a mutex enqueued (blocked on
+	 * a PI chain).
+	 *
+	 * In !RT, it is always safe to call __put_task_struct().
+	 * Though, in order to simplify the code, resort to the
+	 * deferred call too.
 	 *
-	 * call_rcu() will schedule delayed_put_task_struct_rcu()
+	 * call_rcu() will schedule __put_task_struct_rcu_cb()
 	 * to be called in process context.
 	 *
 	 * __put_task_struct() is called when
@@ -165,7 +154,7 @@ static inline void put_task_struct(struct task_struct *t)
 	 *
 	 * delayed_free_task() also uses ->rcu, but it is only called
 	 * when it fails to fork a process. Therefore, there is no
-	 * way it can conflict with put_task_struct().
+	 * way it can conflict with __put_task_struct().
 	 */
 	call_rcu(&t->rcu, __put_task_struct_rcu_cb);
 }
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 198bb5cc1774..5263746b63e8 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -9,7 +9,6 @@
 /*
  * sched-domains (multiprocessor balancing) declarations:
  */
-#ifdef CONFIG_SMP
 
 /* Generate SD flag indexes */
 #define SD_FLAG(name, mflags) __##name,
@@ -176,8 +175,6 @@ bool cpus_share_resources(int this_cpu, int that_cpu);
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
 
-#define SDTL_OVERLAP	0x01
-
 struct sd_data {
 	struct sched_domain *__percpu *sd;
 	struct sched_domain_shared *__percpu *sds;
@@ -188,7 +185,6 @@ struct sd_data {
 struct sched_domain_topology_level {
 	sched_domain_mask_f mask;
 	sched_domain_flags_f sd_flags;
-	int		    flags;
 	int		    numa_level;
 	struct sd_data      data;
 	char                *name;
@@ -197,39 +193,8 @@ 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
-
-#else /* CONFIG_SMP */
-
-struct sched_domain_attr;
-
-static inline void
-partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-			struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-static inline bool cpus_share_cache(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-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 */
+#define SDTL_INIT(maskfn, flagsfn, dname) ((struct sched_domain_topology_level) \
+	    { .mask = maskfn, .sd_flags = flagsfn, .name = #dname })
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 extern void rebuild_sched_domains_energy(void);