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
  ...

1 files changed, 12 insertions, 35 deletions

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 557246880a7e..3f06ab84d53f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -6,6 +6,9 @@
  *
  * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
  */
+#include <linux/debugfs.h>
+#include <linux/nmi.h>
+#include "sched.h"
 
 /*
  * This allows printing both to /sys/kernel/debug/sched/debug and
@@ -90,10 +93,10 @@ static void sched_feat_enable(int i)
 {
 	static_key_enable_cpuslocked(&sched_feat_keys[i]);
 }
-#else
+#else /* !CONFIG_JUMP_LABEL: */
 static void sched_feat_disable(int i) { };
 static void sched_feat_enable(int i) { };
-#endif /* CONFIG_JUMP_LABEL */
+#endif /* !CONFIG_JUMP_LABEL */
 
 static int sched_feat_set(char *cmp)
 {
@@ -166,8 +169,6 @@ static const struct file_operations sched_feat_fops = {
 	.release	= single_release,
 };
 
-#ifdef CONFIG_SMP
-
 static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf,
 				   size_t cnt, loff_t *ppos)
 {
@@ -214,8 +215,6 @@ static const struct file_operations sched_scaling_fops = {
 	.release	= single_release,
 };
 
-#endif /* SMP */
-
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
 static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf,
@@ -283,7 +282,6 @@ static const struct file_operations sched_dynamic_fops = {
 
 __read_mostly bool sched_debug_verbose;
 
-#ifdef CONFIG_SMP
 static struct dentry           *sd_dentry;
 
 
@@ -311,9 +309,6 @@ static ssize_t sched_verbose_write(struct file *filp, const char __user *ubuf,
 
 	return result;
 }
-#else
-#define sched_verbose_write debugfs_write_file_bool
-#endif
 
 static const struct file_operations sched_verbose_fops = {
 	.read =         debugfs_read_file_bool,
@@ -512,7 +507,6 @@ static __init int sched_init_debug(void)
 	debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
 	debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
 
-#ifdef CONFIG_SMP
 	debugfs_create_file("tunable_scaling", 0644, debugfs_sched, NULL, &sched_scaling_fops);
 	debugfs_create_u32("migration_cost_ns", 0644, debugfs_sched, &sysctl_sched_migration_cost);
 	debugfs_create_u32("nr_migrate", 0644, debugfs_sched, &sysctl_sched_nr_migrate);
@@ -520,7 +514,6 @@ static __init int sched_init_debug(void)
 	sched_domains_mutex_lock();
 	update_sched_domain_debugfs();
 	sched_domains_mutex_unlock();
-#endif
 
 #ifdef CONFIG_NUMA_BALANCING
 	numa = debugfs_create_dir("numa_balancing", debugfs_sched);
@@ -530,7 +523,7 @@ static __init int sched_init_debug(void)
 	debugfs_create_u32("scan_period_max_ms", 0644, numa, &sysctl_numa_balancing_scan_period_max);
 	debugfs_create_u32("scan_size_mb", 0644, numa, &sysctl_numa_balancing_scan_size);
 	debugfs_create_u32("hot_threshold_ms", 0644, numa, &sysctl_numa_balancing_hot_threshold);
-#endif
+#endif /* CONFIG_NUMA_BALANCING */
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
@@ -540,8 +533,6 @@ static __init int sched_init_debug(void)
 }
 late_initcall(sched_init_debug);
 
-#ifdef CONFIG_SMP
-
 static cpumask_var_t		sd_sysctl_cpus;
 
 static int sd_flags_show(struct seq_file *m, void *v)
@@ -652,8 +643,6 @@ void dirty_sched_domain_sysctl(int cpu)
 		__cpumask_set_cpu(cpu, sd_sysctl_cpus);
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
@@ -690,18 +679,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	}
 
 	P(se->load.weight);
-#ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
 	P(se->avg.runnable_avg);
-#endif
 
 #undef PN_SCHEDSTAT
 #undef PN
 #undef P_SCHEDSTAT
 #undef P
 }
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
 static DEFINE_SPINLOCK(sched_debug_lock);
@@ -854,7 +841,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_queued", cfs_rq->h_nr_queued);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_idle", cfs_rq->h_nr_idle);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
-#ifdef CONFIG_SMP
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
 			cfs_rq->avg.load_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_avg",
@@ -874,8 +860,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->tg_load_avg_contrib);
 	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
 			atomic_long_read(&cfs_rq->tg->load_avg));
-#endif
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_CFS_BANDWIDTH
 	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
 			cfs_rq->throttled);
@@ -929,11 +914,7 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x))
 
 	PU(dl_nr_running);
-#ifdef CONFIG_SMP
 	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
-#else
-	dl_bw = &dl_rq->dl_bw;
-#endif
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 
@@ -951,9 +932,9 @@ static void print_cpu(struct seq_file *m, int cpu)
 		SEQ_printf(m, "cpu#%d, %u.%03u MHz\n",
 			   cpu, freq / 1000, (freq % 1000));
 	}
-#else
+#else /* !CONFIG_X86: */
 	SEQ_printf(m, "cpu#%d\n", cpu);
-#endif
+#endif /* !CONFIG_X86 */
 
 #define P(x)								\
 do {									\
@@ -976,12 +957,10 @@ do {									\
 #undef P
 #undef PN
 
-#ifdef CONFIG_SMP
 #define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 	P64(avg_idle);
 	P64(max_idle_balance_cost);
 #undef P64
-#endif
 
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, schedstat_val(rq->n));
 	if (schedstat_enabled()) {
@@ -1163,7 +1142,7 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 	SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
 			task_node(p), task_numa_group_id(p));
 	show_numa_stats(p, m);
-#endif
+#endif /* CONFIG_NUMA_BALANCING */
 }
 
 void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
@@ -1247,7 +1226,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	__PS("nr_involuntary_switches", p->nivcsw);
 
 	P(se.load.weight);
-#ifdef CONFIG_SMP
 	P(se.avg.load_sum);
 	P(se.avg.runnable_sum);
 	P(se.avg.util_sum);
@@ -1256,13 +1234,12 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 	PM(se.avg.util_est, ~UTIL_AVG_UNCHANGED);
-#endif
 #ifdef CONFIG_UCLAMP_TASK
 	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
 	__PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value);
 	__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
 	__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
-#endif
+#endif /* CONFIG_UCLAMP_TASK */
 	P(policy);
 	P(prio);
 	if (task_has_dl_policy(p)) {