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, 24 insertions, 33 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index b958fe48e020..977e133bb8a4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3,7 +3,9 @@
  * Scheduler topology setup/handling methods
  */
 
+#include <linux/sched/isolation.h>
 #include <linux/bsearch.h>
+#include "sched.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
 void sched_domains_mutex_lock(void)
@@ -87,7 +89,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!(sd->flags & SD_OVERLAP) &&
+		if (!(sd->flags & SD_NUMA) &&
 		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
@@ -100,7 +102,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				group->sgc->id,
 				cpumask_pr_args(sched_group_span(group)));
 
-		if ((sd->flags & SD_OVERLAP) &&
+		if ((sd->flags & SD_NUMA) &&
 		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
 			printk(KERN_CONT " mask=%*pbl",
 				cpumask_pr_args(group_balance_mask(group)));
@@ -313,7 +315,7 @@ static int __init sched_energy_aware_sysctl_init(void)
 }
 
 late_initcall(sched_energy_aware_sysctl_init);
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
 
 static void free_pd(struct perf_domain *pd)
 {
@@ -449,9 +451,9 @@ free:
 
 	return false;
 }
-#else
+#else /* !(CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL): */
 static void free_pd(struct perf_domain *pd) { }
-#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
+#endif /* !(CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */
 
 static void free_rootdomain(struct rcu_head *rcu)
 {
@@ -1318,8 +1320,6 @@ 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)
 {
@@ -1344,7 +1344,7 @@ void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
 		 * "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);
+		WARN_ON_ONCE(sd->flags & SD_NUMA);
 
 		sg = sd->groups;
 		if (cpu != sg->asym_prefer_cpu) {
@@ -1374,8 +1374,6 @@ void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
 	}
 }
 
-#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
@@ -1598,7 +1596,7 @@ static int			sched_domains_curr_level;
 int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
 static struct cpumask		***sched_domains_numa_masks;
-#endif
+#endif /* CONFIG_NUMA */
 
 /*
  * SD_flags allowed in topology descriptions.
@@ -1714,7 +1712,7 @@ sd_init(struct sched_domain_topology_level *tl,
 				       SD_WAKE_AFFINE);
 		}
 
-#endif
+#endif /* CONFIG_NUMA */
 	} else {
 		sd->cache_nice_tries = 1;
 	}
@@ -1739,17 +1737,17 @@ sd_init(struct sched_domain_topology_level *tl,
  */
 static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT),
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
-	{ cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) },
+	SDTL_INIT(cpu_clustergroup_mask, cpu_cluster_flags, CLS),
 #endif
 
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC),
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
+	SDTL_INIT(cpu_cpu_mask, NULL, PKG),
 	{ NULL, },
 };
 
@@ -2010,23 +2008,14 @@ void sched_init_numa(int offline_node)
 	/*
 	 * Add the NUMA identity distance, aka single NODE.
 	 */
-	tl[i++] = (struct sched_domain_topology_level){
-		.mask = sd_numa_mask,
-		.numa_level = 0,
-		SD_INIT_NAME(NODE)
-	};
+	tl[i++] = SDTL_INIT(sd_numa_mask, NULL, NODE);
 
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
 	for (j = 1; j < nr_levels; i++, j++) {
-		tl[i] = (struct sched_domain_topology_level){
-			.mask = sd_numa_mask,
-			.sd_flags = cpu_numa_flags,
-			.flags = SDTL_OVERLAP,
-			.numa_level = j,
-			SD_INIT_NAME(NUMA)
-		};
+		tl[i] = SDTL_INIT(sd_numa_mask, cpu_numa_flags, NUMA);
+		tl[i].numa_level = j;
 	}
 
 	sched_domain_topology_saved = sched_domain_topology;
@@ -2337,7 +2326,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 			if (sdd->sd) {
 				sd = *per_cpu_ptr(sdd->sd, j);
-				if (sd && (sd->flags & SD_OVERLAP))
+				if (sd && (sd->flags & SD_NUMA))
 					free_sched_groups(sd->groups, 0);
 				kfree(*per_cpu_ptr(sdd->sd, j));
 			}
@@ -2403,9 +2392,13 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
 	id_seen = sched_domains_tmpmask2;
 
 	for_each_sd_topology(tl) {
+		int tl_common_flags = 0;
+
+		if (tl->sd_flags)
+			tl_common_flags = (*tl->sd_flags)();
 
 		/* NUMA levels are allowed to overlap */
-		if (tl->flags & SDTL_OVERLAP)
+		if (tl_common_flags & SD_NUMA)
 			continue;
 
 		cpumask_clear(covered);
@@ -2476,8 +2469,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP)
-				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
 		}
@@ -2490,7 +2481,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			if (sd->flags & SD_OVERLAP) {
+			if (sd->flags & SD_NUMA) {
 				if (build_overlap_sched_groups(sd, i))
 					goto error;
 			} else {