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
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -6410,6 +6410,11 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
+	sched_proxy_exec= [KNL]
+			Enables or disables "proxy execution" style
+			solution to mutex-based priority inversion.
+			Format: <bool>
+
 	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.

MAINTAINERS

@@ -22319,6 +22319,7 @@ F:	include/linux/wait.h
 F:	include/uapi/linux/sched.h
 F:	kernel/fork.c
 F:	kernel/sched/
+F:	tools/sched/
 
 SCHEDULER - SCHED_EXT
 R:	Tejun Heo <tj@kernel.org>

arch/powerpc/kernel/smp.c

@@ -1700,28 +1700,23 @@ static void __init build_sched_topology(void)
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(smallcore_smt_mask, powerpc_smt_flags, SMT);
 	} else {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
-		};
+		powerpc_topology[i++] = SDTL_INIT(cpu_smt_mask, powerpc_smt_flags, SMT);
 	}
 #endif
 	if (shared_caches) {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(shared_cache_mask, powerpc_shared_cache_flags, CACHE);
 	}
+
 	if (has_coregroup_support()) {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(cpu_mc_mask, powerpc_shared_proc_flags, MC);
 	}
-	powerpc_topology[i++] = (struct sched_domain_topology_level){
-		cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
-	};
+
+	powerpc_topology[i++] = SDTL_INIT(cpu_cpu_mask, powerpc_shared_proc_flags, PKG);
 
 	/* There must be one trailing NULL entry left.  */
 	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);

arch/s390/kernel/topology.c

@@ -531,11 +531,11 @@ static const struct cpumask *cpu_drawer_mask(int cpu)
 }
 
 static struct sched_domain_topology_level s390_topology[] = {
-	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
-	{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
+	SDTL_INIT(cpu_thread_mask, cpu_smt_flags, SMT),
+	SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC),
+	SDTL_INIT(cpu_book_mask, NULL, BOOK),
+	SDTL_INIT(cpu_drawer_mask, NULL, DRAWER),
+	SDTL_INIT(cpu_cpu_mask, NULL, PKG),
 	{ NULL, },
 };
 

arch/x86/kernel/smpboot.c

@@ -478,44 +478,41 @@ static int x86_cluster_flags(void)
  */
 static bool x86_has_numa_in_package;
 
-static struct sched_domain_topology_level x86_topology[6];
+static struct sched_domain_topology_level x86_topology[] = {
+	SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT),
+#ifdef CONFIG_SCHED_CLUSTER
+	SDTL_INIT(cpu_clustergroup_mask, x86_cluster_flags, CLS),
+#endif
+#ifdef CONFIG_SCHED_MC
+	SDTL_INIT(cpu_coregroup_mask, x86_core_flags, MC),
+#endif
+	SDTL_INIT(cpu_cpu_mask, x86_sched_itmt_flags, PKG),
+	{ NULL },
+};
 
 static void __init build_sched_topology(void)
 {
-	int i = 0;
+	struct sched_domain_topology_level *topology = x86_topology;
 
-#ifdef CONFIG_SCHED_SMT
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT)
-	};
-#endif
-#ifdef CONFIG_SCHED_CLUSTER
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
-	};
-#endif
-#ifdef CONFIG_SCHED_MC
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC)
-	};
-#endif
 	/*
-	 * When there is NUMA topology inside the package skip the PKG domain
-	 * since the NUMA domains will auto-magically create the right spanning
-	 * domains based on the SLIT.
+	 * When there is NUMA topology inside the package invalidate the
+	 * PKG domain since the NUMA domains will auto-magically create the
+	 * right spanning domains based on the SLIT.
 	 */
-	if (!x86_has_numa_in_package) {
-		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG)
-		};
+	if (x86_has_numa_in_package) {
+		unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2;
+
+		memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom]));
 	}
 
 	/*
-	 * There must be one trailing NULL entry left.
+	 * Drop the SMT domains if there is only one thread per-core
+	 * since it'll get degenerated by the scheduler anyways.
 	 */
-	BUG_ON(i >= ARRAY_SIZE(x86_topology)-1);
+	if (cpu_smt_num_threads <= 1)
+		++topology;
 
-	set_sched_topology(x86_topology);
+	set_sched_topology(topology);
 }
 
 void set_cpu_sibling_map(int cpu)

include/linux/cpu.h

@@ -187,11 +187,6 @@ static inline void arch_cpu_finalize_init(void) { }
 
 void play_idle_precise(u64 duration_ns, u64 latency_ns);
 
-static inline void play_idle(unsigned long duration_us)
-{
-	play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void cpuhp_report_idle_dead(void);
 #else

include/linux/preempt.h

@@ -369,8 +369,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
-#ifdef CONFIG_SMP
-
 /*
  * Migrate-Disable and why it is undesired.
  *
@@ -429,13 +427,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 extern void migrate_disable(void);
 extern void migrate_enable(void);
 
-#else
-
-static inline void migrate_disable(void) { }
-static inline void migrate_enable(void) { }
-
-#endif /* CONFIG_SMP */
-
 /**
  * preempt_disable_nested - Disable preemption inside a normally preempt disabled section
  *

include/linux/psi_types.h

@@ -84,11 +84,9 @@ enum psi_aggregators {
 struct psi_group_cpu {
 	/* 1st cacheline updated by the scheduler */
 
-	/* Aggregator needs to know of concurrent changes */
-	seqcount_t seq ____cacheline_aligned_in_smp;
-
 	/* States of the tasks belonging to this group */
-	unsigned int tasks[NR_PSI_TASK_COUNTS];
+	unsigned int tasks[NR_PSI_TASK_COUNTS]
+			____cacheline_aligned_in_smp;
 
 	/* Aggregate pressure state derived from the tasks */
 	u32 state_mask;

include/linux/sched.h

@@ -34,6 +34,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
+#include <linux/spinlock.h>
 #include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/netdevice_xmit.h>
@@ -395,15 +396,10 @@ enum uclamp_id {
 	UCLAMP_CNT
 };
 
-#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 {
 	int sched_priority;
@@ -584,7 +580,15 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				prev_sum_exec_runtime;
 	u64				vruntime;
-	s64				vlag;
+	union {
+		/*
+		 * When !@on_rq this field is vlag.
+		 * When cfs_rq->curr == se (which implies @on_rq)
+		 * this field is vprot. See protect_slice().
+		 */
+		s64                     vlag;
+		u64                     vprot;
+	};
 	u64				slice;
 
 	u64				nr_migrations;
@@ -600,7 +604,6 @@ struct sched_entity {
 	unsigned long			runnable_weight;
 #endif
 
-#ifdef CONFIG_SMP
 	/*
 	 * Per entity load average tracking.
 	 *
@@ -608,7 +611,6 @@ struct sched_entity {
 	 * collide with read-mostly values above.
 	 */
 	struct sched_avg		avg;
-#endif
 };
 
 struct sched_rt_entity {
@@ -701,6 +703,7 @@ struct sched_dl_entity {
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
+	unsigned int			dl_server_idle    : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -838,7 +841,6 @@ struct task_struct {
 	struct alloc_tag		*alloc_tag;
 #endif
 
-#ifdef CONFIG_SMP
 	int				on_cpu;
 	struct __call_single_node	wake_entry;
 	unsigned int			wakee_flips;
@@ -854,7 +856,6 @@ struct task_struct {
 	 */
 	int				recent_used_cpu;
 	int				wake_cpu;
-#endif
 	int				on_rq;
 
 	int				prio;
@@ -913,9 +914,7 @@ struct task_struct {
 	cpumask_t			*user_cpus_ptr;
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
-#ifdef CONFIG_SMP
 	unsigned short			migration_disabled;
-#endif
 	unsigned short			migration_flags;
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -947,10 +946,8 @@ struct task_struct {
 	struct sched_info		sched_info;
 
 	struct list_head		tasks;
-#ifdef CONFIG_SMP
 	struct plist_node		pushable_tasks;
 	struct rb_node			pushable_dl_tasks;
-#endif
 
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
@@ -1234,10 +1231,7 @@ struct task_struct {
 	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
-	/* Mutex deadlock detection: */
-	struct mutex_waiter		*blocked_on;
-#endif
+	struct mutex			*blocked_on;	/* lock we're blocked on */
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
@@ -1662,6 +1656,19 @@ struct task_struct {
 	randomized_struct_fields_end
 } __attribute__ ((aligned (64)));
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+DECLARE_STATIC_KEY_TRUE(__sched_proxy_exec);
+static inline bool sched_proxy_exec(void)
+{
+	return static_branch_likely(&__sched_proxy_exec);
+}
+#else
+static inline bool sched_proxy_exec(void)
+{
+	return false;
+}
+#endif
+
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
@@ -1776,12 +1783,8 @@ extern struct pid *cad_pid;
 
 static __always_inline bool is_percpu_thread(void)
 {
-#ifdef CONFIG_SMP
 	return (current->flags & PF_NO_SETAFFINITY) &&
 		(current->nr_cpus_allowed  == 1);
-#else
-	return true;
-#endif
 }
 
 /* Per-process atomic flags. */
@@ -1846,7 +1849,6 @@ extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpu
 extern int task_can_attach(struct task_struct *p);
 extern int dl_bw_alloc(int cpu, u64 dl_bw);
 extern void dl_bw_free(int cpu, u64 dl_bw);
-#ifdef CONFIG_SMP
 
 /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
@@ -1864,33 +1866,6 @@ extern void release_user_cpus_ptr(struct task_struct *p);
 extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask);
 extern void force_compatible_cpus_allowed_ptr(struct task_struct *p);
 extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p);
-#else
-static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
-{
-}
-static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
-{
-	/* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */
-	if ((*cpumask_bits(new_mask) & 1) == 0)
-		return -EINVAL;
-	return 0;
-}
-static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
-{
-	if (src->user_cpus_ptr)
-		return -EINVAL;
-	return 0;
-}
-static inline void release_user_cpus_ptr(struct task_struct *p)
-{
-	WARN_ON(p->user_cpus_ptr);
-}
-
-static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
-{
-	return 0;
-}
-#endif
 
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
@@ -1979,11 +1954,7 @@ extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 
-#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
-#else
-static inline void kick_process(struct task_struct *tsk) { }
-#endif
 
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
 #define set_task_comm(tsk, from) ({			\
@@ -2010,7 +1981,6 @@ extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec
 	buf;						\
 })
 
-#ifdef CONFIG_SMP
 static __always_inline void scheduler_ipi(void)
 {
 	/*
@@ -2020,9 +1990,6 @@ static __always_inline void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 }
-#else
-static inline void scheduler_ipi(void) { }
-#endif
 
 extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state);
 
@@ -2165,6 +2132,67 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
+#ifndef CONFIG_PREEMPT_RT
+static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
+{
+	struct mutex *m = p->blocked_on;
+
+	if (m)
+		lockdep_assert_held_once(&m->wait_lock);
+	return m;
+}
+
+static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	WARN_ON_ONCE(!m);
+	/* The task should only be setting itself as blocked */
+	WARN_ON_ONCE(p != current);
+	/* Currently we serialize blocked_on under the mutex::wait_lock */
+	lockdep_assert_held_once(&m->wait_lock);
+	/*
+	 * Check ensure we don't overwrite existing mutex value
+	 * with a different mutex. Note, setting it to the same
+	 * lock repeatedly is ok.
+	 */
+	WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
+	p->blocked_on = m;
+}
+
+static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	guard(raw_spinlock_irqsave)(&m->wait_lock);
+	__set_task_blocked_on(p, m);
+}
+
+static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	WARN_ON_ONCE(!m);
+	/* Currently we serialize blocked_on under the mutex::wait_lock */
+	lockdep_assert_held_once(&m->wait_lock);
+	/*
+	 * There may be cases where we re-clear already cleared
+	 * blocked_on relationships, but make sure we are not
+	 * clearing the relationship with a different lock.
+	 */
+	WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m);
+	p->blocked_on = NULL;
+}
+
+static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	guard(raw_spinlock_irqsave)(&m->wait_lock);
+	__clear_task_blocked_on(p, m);
+}
+#else
+static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
+{
+}
+
+static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
+{
+}
+#endif /* !CONFIG_PREEMPT_RT */
+
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
@@ -2204,8 +2232,6 @@ extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);
 
-#include <linux/spinlock.h>
-
 /*
  * In order to reduce various lock holder preemption latencies provide an
  * interface to see if a vCPU is currently running or not.
@@ -2228,7 +2254,6 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
-#ifdef CONFIG_SMP
 static inline bool owner_on_cpu(struct task_struct *owner)
 {
 	/*
@@ -2240,7 +2265,6 @@ static inline bool owner_on_cpu(struct task_struct *owner)
 
 /* Returns effective CPU energy utilization, as seen by the scheduler */
 unsigned long sched_cpu_util(int cpu);
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);

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);
 

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

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) { }

include/linux/sched/sd_flags.h

@@ -153,14 +153,6 @@ 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
  *

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).
 	 *
-	 * call_rcu() will schedule delayed_put_task_struct_rcu()
+	 * 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 __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);
 }

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);

init/Kconfig

@@ -142,6 +142,9 @@ config RUSTC_HAS_SPAN_FILE
 config RUSTC_HAS_UNNECESSARY_TRANSMUTES
 	def_bool RUSTC_VERSION >= 108800
 
+config RUSTC_HAS_FILE_WITH_NUL
+	def_bool RUSTC_VERSION >= 108900
+
 config PAHOLE_VERSION
 	int
 	default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
@@ -875,6 +878,18 @@ config UCLAMP_BUCKETS_COUNT
 
 	  If in doubt, use the default value.
 
+config SCHED_PROXY_EXEC
+	bool "Proxy Execution"
+	# Avoid some build failures w/ PREEMPT_RT until it can be fixed
+	depends on !PREEMPT_RT
+	# Need to investigate how to inform sched_ext of split contexts
+	depends on !SCHED_CLASS_EXT
+	# Not particularly useful until we get to multi-rq proxying
+	depends on EXPERT
+	help
+	  This option enables proxy execution, a mechanism for mutex-owning
+	  tasks to inherit the scheduling context of higher priority waiters.
+
 endmenu
 
 #

kernel/fork.c

@@ -2127,9 +2127,8 @@ __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
-#endif
+
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;

kernel/locking/mutex-debug.c

@@ -53,17 +53,18 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 {
 	lockdep_assert_held(&lock->wait_lock);
 
-	/* Mark the current thread as blocked on the lock: */
-	task->blocked_on = waiter;
+	/* Current thread can't be already blocked (since it's executing!) */
+	DEBUG_LOCKS_WARN_ON(__get_task_blocked_on(task));
 }
 
 void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
+	struct mutex *blocked_on = __get_task_blocked_on(task);
+
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
 	DEBUG_LOCKS_WARN_ON(waiter->task != task);
-	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
-	task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
 
 	INIT_LIST_HEAD(&waiter->list);
 	waiter->task = NULL;

kernel/locking/mutex.c

@@ -644,6 +644,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	__set_task_blocked_on(current, lock);
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -680,6 +681,12 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * As we likely have been woken up by task
+		 * that has cleared our blocked_on state, re-set
+		 * it to the lock we are trying to acquire.
+		 */
+		set_task_blocked_on(current, lock);
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -691,8 +698,15 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		if (first) {
 			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			/*
+			 * mutex_optimistic_spin() can call schedule(), so
+			 * clear blocked on so we don't become unselectable
+			 * to run.
+			 */
+			clear_task_blocked_on(current, lock);
 			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
 				break;
+			set_task_blocked_on(current, lock);
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -700,6 +714,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 acquired:
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -729,9 +744,11 @@ skip_wait:
 	return 0;
 
 err:
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
+	WARN_ON(__get_task_blocked_on(current));
 	trace_contention_end(lock, ret);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 	debug_mutex_free_waiter(&waiter);
@@ -942,6 +959,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
+		__clear_task_blocked_on(next, lock);
 		wake_q_add(&wake_q, next);
 	}
 

kernel/locking/mutex.h

@@ -6,7 +6,7 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-
+#ifndef CONFIG_PREEMPT_RT
 /*
  * This is the control structure for tasks blocked on mutex, which resides
  * on the blocked task's kernel stack:
@@ -70,3 +70,4 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 # define debug_mutex_unlock(lock)			do { } while (0)
 # define debug_mutex_init(lock, name, key)		do { } while (0)
 #endif /* !CONFIG_DEBUG_MUTEXES */
+#endif /* CONFIG_PREEMPT_RT */