15 files changed, 117 insertions, 125 deletions

diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 3a912ab42bb5..c40115d4e34d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -29,12 +29,12 @@ 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);
 
 #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/ext.h b/include/linux/sched/ext.h
index 1d70a9867fb1..7047101dbf58 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -146,6 +146,7 @@ struct sched_ext_entity {
 	u32			weight;
 	s32			sticky_cpu;
 	s32			holding_cpu;
+	s32			selected_cpu;
 	u32			kf_mask;	/* see scx_kf_mask above */
 	struct task_struct	*kf_tasks[2];	/* see SCX_CALL_OP_TASK() */
 	atomic_long_t		ops_state;
@@ -163,7 +164,7 @@ struct sched_ext_entity {
 
 	/*
 	 * Runtime budget in nsecs. This is usually set through
-	 * scx_bpf_dispatch() but can also be modified directly by the BPF
+	 * scx_bpf_dsq_insert() but can also be modified directly by the BPF
 	 * scheduler. Automatically decreased by SCX as the task executes. On
 	 * depletion, a scheduling event is triggered.
 	 *
@@ -175,10 +176,10 @@ struct sched_ext_entity {
 
 	/*
 	 * Used to order tasks when dispatching to the vtime-ordered priority
-	 * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime()
-	 * but can also be modified directly by the BPF scheduler. Modifying it
-	 * while a task is queued on a dsq may mangle the ordering and is not
-	 * recommended.
+	 * queue of a dsq. This is usually set through
+	 * scx_bpf_dsq_insert_vtime() but can also be modified directly by the
+	 * BPF scheduler. Modifying it while a task is queued on a dsq may
+	 * mangle the ordering and is not recommended.
 	 */
 	u64			dsq_vtime;
 
@@ -205,12 +206,25 @@ struct sched_ext_entity {
 void sched_ext_free(struct task_struct *p);
 void print_scx_info(const char *log_lvl, struct task_struct *p);
 void scx_softlockup(u32 dur_s);
+bool scx_rcu_cpu_stall(void);
 
 #else	/* !CONFIG_SCHED_CLASS_EXT */
 
 static inline void sched_ext_free(struct task_struct *p) {}
 static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
 static inline void scx_softlockup(u32 dur_s) {}
+static inline bool scx_rcu_cpu_stall(void) { return false; }
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
+
+struct scx_task_group {
+#ifdef CONFIG_EXT_GROUP_SCHED
+	u32			flags;		/* SCX_TG_* */
+	u32			weight;
+	u64			bw_period_us;
+	u64			bw_quota_us;
+	u64			bw_burst_us;
+#endif
+};
+
 #endif	/* _LINUX_SCHED_EXT_H */
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 412cdaba33eb..17e04859b9a4 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -18,10 +18,6 @@ extern int sched_cpu_dying(unsigned int cpu);
 # define sched_cpu_dying	NULL
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void idle_task_exit(void);
-#else
 static inline void idle_task_exit(void) {}
-#endif
 
 #endif /* _LINUX_SCHED_HOTPLUG_H */
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index e670ac282333..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
@@ -79,6 +75,21 @@ 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 +102,15 @@ 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/isolation.h b/include/linux/sched/isolation.h
index 2b461129d1fa..d8501f4709b5 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -7,16 +7,21 @@
 #include <linux/tick.h>
 
 enum hk_type {
-	HK_TYPE_TIMER,
-	HK_TYPE_RCU,
-	HK_TYPE_MISC,
-	HK_TYPE_SCHED,
-	HK_TYPE_TICK,
 	HK_TYPE_DOMAIN,
-	HK_TYPE_WQ,
 	HK_TYPE_MANAGED_IRQ,
-	HK_TYPE_KTHREAD,
-	HK_TYPE_MAX
+	HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_MAX,
+
+	/*
+	 * The following housekeeping types are only set by the nohz_full
+	 * boot commandline option. So they can share the same value.
+	 */
+	HK_TYPE_TICK    = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_TIMER   = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_RCU     = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_MISC    = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_WQ      = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 928a626725e6..2201da0afecc 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -140,7 +140,7 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH)
 /* same as above but performs the slow path from the async context. Can
  * be called from the atomic context as well
  */
@@ -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/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/signal.h b/include/linux/sched/signal.h
index d5d03d919df8..1ef1edbaaf79 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -136,7 +136,8 @@ struct signal_struct {
 #ifdef CONFIG_POSIX_TIMERS
 
 	/* POSIX.1b Interval Timers */
-	unsigned int		next_posix_timer_id;
+	unsigned int		timer_create_restore_ids:1;
+	atomic_t		next_posix_timer_id;
 	struct hlist_head	posix_timers;
 	struct hlist_head	ignored_posix_timers;
 
diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h
index fb1e295e7e63..166b19af956f 100644
--- a/include/linux/sched/smt.h
+++ b/include/linux/sched/smt.h
@@ -12,7 +12,7 @@ static __always_inline bool sched_smt_active(void)
 	return static_branch_likely(&sched_smt_present);
 }
 #else
-static inline bool sched_smt_active(void) { return false; }
+static __always_inline bool sched_smt_active(void) { return false; }
 #endif
 
 void arch_smt_update(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 0f2aeb37bbb0..ea41795a352b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -43,6 +43,7 @@ struct kernel_clone_args {
 	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
+	unsigned int kill_seq;
 };
 
 /*
@@ -108,11 +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)
 {
@@ -134,24 +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
@@ -164,7 +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/task_stack.h b/include/linux/sched/task_stack.h
index cffad65bdc6a..1fab7e9043a3 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -53,7 +53,7 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct
  * When the stack grows up, this is the highest address.
  * Beyond that position, we corrupt data on the next page.
  */
-static inline unsigned long *end_of_stack(struct task_struct *p)
+static inline unsigned long *end_of_stack(const struct task_struct *p)
 {
 #ifdef CONFIG_STACK_GROWSUP
 	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
@@ -106,7 +106,6 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 #endif
 extern void set_task_stack_end_magic(struct task_struct *tsk);
 
-#ifndef __HAVE_ARCH_KSTACK_END
 static inline int kstack_end(void *addr)
 {
 	/* Reliable end of stack detection:
@@ -114,6 +113,5 @@ static inline int kstack_end(void *addr)
 	 */
 	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
 }
-#endif
 
 #endif /* _LINUX_SCHED_TASK_STACK_H */
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 4237daa5ac7a..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,
@@ -25,16 +24,12 @@ 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)
 {
@@ -114,7 +109,10 @@ struct sched_domain {
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
@@ -140,9 +138,7 @@ struct sched_domain {
 	unsigned int ttwu_move_affine;
 	unsigned int ttwu_move_balance;
 #endif
-#ifdef CONFIG_SCHED_DEBUG
 	char *name;
-#endif
 	union {
 		void *private;		/* used during construction */
 		struct rcu_head rcu;	/* used during destruction */
@@ -165,10 +161,6 @@ 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);
 
@@ -183,8 +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;
@@ -195,54 +185,16 @@ 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;
-#ifdef CONFIG_SCHED_DEBUG
 	char                *name;
-#endif
 };
 
 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);
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SD_INIT_NAME(type)		.name = #type
-#else
-# define SD_INIT_NAME(type)
-#endif
-
-#else /* CONFIG_SMP */
-
-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)
-{
-}
-
-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;
-}
-
-#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);
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 06cd8fb2f409..0f28b4623ad4 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -63,4 +63,38 @@ extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
 extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
+/* Spin unlock helpers to unlock and call wake_up_q with preempt disabled */
+static inline
+void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock(lock);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
+
+static inline
+void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock_irq(lock);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
+
+static inline
+void raw_spin_unlock_irqrestore_wake(raw_spinlock_t *lock, unsigned long flags,
+				     struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock_irqrestore(lock, flags);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
 #endif /* _LINUX_SCHED_WAKE_Q_H */