Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

52 files changed, 1260 insertions, 812 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 5644abd5f8a8..8c6de5a9ecc4 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -96,8 +96,9 @@ config PREEMPTION
 config PREEMPT_DYNAMIC
 	bool "Preemption behaviour defined on boot"
 	depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT
+	select JUMP_LABEL if HAVE_PREEMPT_DYNAMIC_KEY
 	select PREEMPT_BUILD
-	default y
+	default y if HAVE_PREEMPT_DYNAMIC_CALL
 	help
 	  This option allows to define the preemption model on the kernel
 	  command line parameter and thus override the default preemption
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5de18448016c..ef88cc366bb8 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -833,7 +833,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
 		cpumask_and(doms[0], top_cpuset.effective_cpus,
-			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 		goto done;
 	}
@@ -863,7 +863,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
 		      cpumask_intersects(cp->cpus_allowed,
-					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
+					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
 			continue;
 
 		if (root_load_balance &&
@@ -952,7 +952,7 @@ restart:
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
-				cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN));
+				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 238cba15449f..5797c2a7a93f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1489,8 +1489,8 @@ int freeze_secondary_cpus(int primary)
 	cpu_maps_update_begin();
 	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
-		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
-			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+		if (!housekeeping_cpu(primary, HK_TYPE_TIMER))
+			primary = housekeeping_any_cpu(HK_TYPE_TIMER);
 	} else {
 		if (!cpu_online(primary))
 			primary = cpumask_first(cpu_online_mask);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 0543a2c92f20..ed10a95a6b1d 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -3,6 +3,7 @@
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
 #include <linux/highmem.h>
+#include <linux/jump_label.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
 #include <linux/tick.h>
@@ -394,7 +395,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	return ret;
 }
 
-void irqentry_exit_cond_resched(void)
+void raw_irqentry_exit_cond_resched(void)
 {
 	if (!preempt_count()) {
 		/* Sanity check RCU and thread stack */
@@ -406,7 +407,17 @@ void irqentry_exit_cond_resched(void)
 	}
 }
 #ifdef CONFIG_PREEMPT_DYNAMIC
-DEFINE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void)
+{
+	if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+		return;
+	raw_irqentry_exit_cond_resched();
+}
+#endif
 #endif
 
 noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
@@ -434,13 +445,9 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		}
 
 		instrumentation_begin();
-		if (IS_ENABLED(CONFIG_PREEMPTION)) {
-#ifdef CONFIG_PREEMPT_DYNAMIC
-			static_call(irqentry_exit_cond_resched)();
-#else
+		if (IS_ENABLED(CONFIG_PREEMPTION))
 			irqentry_exit_cond_resched();
-#endif
-		}
+
 		/* Covers both tracing and lockdep */
 		trace_hardirqs_on();
 		instrumentation_end();
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 39a41c56ad4f..1ed2b1739363 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
 {
 	const struct cpumask *hk_mask;
 
-	if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+	if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ))
 		return false;
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+	hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
 	if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
 		return false;
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f23ffd30385b..c03f71d5ec10 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -247,13 +247,13 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	 * online.
 	 */
 	if (irqd_affinity_is_managed(data) &&
-	    housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+	    housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) {
 		const struct cpumask *hk_mask, *prog_mask;
 
 		static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
 		static struct cpumask tmp_mask;
 
-		hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+		hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
 
 		raw_spin_lock(&tmp_mask_lock);
 		cpumask_and(&tmp_mask, mask, hk_mask);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 38c6dd822da8..d100d5a15b38 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -356,7 +356,7 @@ static int kthread(void *_create)
 	 * back to default in case they have been changed.
 	 */
 	sched_setscheduler_nocheck(current, SCHED_NORMAL, &param);
-	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD));
+	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD));
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
@@ -722,7 +722,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index ac17348187e4..99cf3a13954c 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -496,7 +496,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	struct rcu_tasks *rtp = arg;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current, HK_FLAG_RCU);
+	housekeeping_affine(current, HK_TYPE_RCU);
 	WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
 
 	/*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6082dd23408f..8360d86db1c0 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1218,9 +1218,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
-	cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU));
+	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
 	if (cpumask_empty(cm))
-		cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU));
+		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
 	set_cpus_allowed_ptr(t, cm);
 	mutex_unlock(&rnp->boost_kthread_mutex);
 	free_cpumask_var(cm);
@@ -1296,7 +1296,7 @@ static void rcu_bind_gp_kthread(void)
 {
 	if (!tick_nohz_full_enabled())
 		return;
-	housekeeping_affine(current, HK_FLAG_RCU);
+	housekeeping_affine(current, HK_TYPE_RCU);
 }
 
 /* Record the current task on dyntick-idle entry. */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 6d45ac3dae7f..97ac20b4f738 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -128,10 +128,10 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	int ret;
 
 #ifdef CONFIG_64BIT
-	if (get_user(ptr, &t->rseq->rseq_cs.ptr64))
+	if (get_user(ptr, &t->rseq->rseq_cs))
 		return -EFAULT;
 #else
-	if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+	if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr)))
 		return -EFAULT;
 #endif
 	if (!ptr) {
@@ -217,9 +217,9 @@ static int clear_rseq_cs(struct task_struct *t)
 	 * Set rseq_cs to NULL.
 	 */
 #ifdef CONFIG_64BIT
-	return put_user(0UL, &t->rseq->rseq_cs.ptr64);
+	return put_user(0UL, &t->rseq->rseq_cs);
 #else
-	if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+	if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs)))
 		return -EFAULT;
 	return 0;
 #endif
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index c83b37af155b..976092b7bd45 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
-endif
 
 # The compilers are complaining about unused variables inside an if(0) scope
 # block. This is daft, shut them up.
@@ -25,18 +22,13 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o loadavg.o clock.o cputime.o
-obj-y += idle.o fair.o rt.o deadline.o
-obj-y += wait.o wait_bit.o swait.o completion.o
-
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
-obj-$(CONFIG_SCHEDSTATS) += stats.o
-obj-$(CONFIG_SCHED_DEBUG) += debug.o
-obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
-obj-$(CONFIG_CPU_FREQ) += cpufreq.o
-obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
-obj-$(CONFIG_MEMBARRIER) += membarrier.o
-obj-$(CONFIG_CPU_ISOLATION) += isolation.o
-obj-$(CONFIG_PSI) += psi.o
-obj-$(CONFIG_SCHED_CORE) += core_sched.o
+#
+# Build efficiency:
+#
+# These compilation units have roughly the same size and complexity - so their
+# build parallelizes well and finishes roughly at once:
+#
+obj-y += core.o
+obj-y += fair.o
+obj-y += build_policy.o
+obj-y += build_utility.o
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 8629b37d118e..16092b49ff6a 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -1,14 +1,35 @@
 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * Auto-group scheduling implementation:
  */
-#include <linux/nospec.h>
-#include "sched.h"
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
 static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_autogroup_sysctls[] = {
+	{
+		.procname       = "sched_autogroup_enabled",
+		.data           = &sysctl_sched_autogroup_enabled,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{}
+};
+
+static void __init sched_autogroup_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_autogroup_sysctls);
+}
+#else
+#define sched_autogroup_sysctl_init() do { } while (0)
+#endif
+
 void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
@@ -198,6 +219,7 @@ void sched_autogroup_exit(struct signal_struct *sig)
 static int __init setup_autogroup(char *str)
 {
 	sysctl_sched_autogroup_enabled = 0;
+	sched_autogroup_sysctl_init();
 
 	return 1;
 }
diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h
index b96419974a1f..90d69f2c5eaf 100644
--- a/kernel/sched/autogroup.h
+++ b/kernel/sched/autogroup.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _KERNEL_SCHED_AUTOGROUP_H
+#define _KERNEL_SCHED_AUTOGROUP_H
+
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 struct autogroup {
@@ -27,6 +30,7 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)
 {
+	extern unsigned int sysctl_sched_autogroup_enabled;
 	int enabled = READ_ONCE(sysctl_sched_autogroup_enabled);
 
 	if (enabled && task_wants_autogroup(p, tg))
@@ -58,3 +62,5 @@ static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
 }
 
 #endif /* CONFIG_SCHED_AUTOGROUP */
+
+#endif /* _KERNEL_SCHED_AUTOGROUP_H */
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
new file mode 100644
index 000000000000..e0104b45029a
--- /dev/null
+++ b/kernel/sched/build_policy.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * These are the scheduling policy related scheduler files, built
+ * in a single compilation unit for build efficiency reasons.
+ *
+ * ( Incidentally, the size of the compilation unit is roughly
+ *   comparable to core.c and fair.c, the other two big
+ *   compilation units. This helps balance build time, while
+ *   coalescing source files to amortize header inclusion
+ *   cost. )
+ *
+ * core.c and fair.c are built separately.
+ */
+
+/* Headers: */
+#include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/posix-timers.h>
+#include <linux/sched/rt.h>
+
+#include <linux/cpuidle.h>
+#include <linux/jiffies.h>
+#include <linux/livepatch.h>
+#include <linux/psi.h>
+#include <linux/seqlock_api.h>
+#include <linux/slab.h>
+#include <linux/suspend.h>
+#include <linux/tsacct_kern.h>
+#include <linux/vtime.h>
+
+#include <uapi/linux/sched/types.h>
+
+#include "sched.h"
+
+#include "autogroup.h"
+#include "stats.h"
+#include "pelt.h"
+
+/* Source code modules: */
+
+#include "idle.c"
+
+#include "rt.c"
+
+#ifdef CONFIG_SMP
+# include "cpudeadline.c"
+# include "pelt.c"
+#endif
+
+#include "cputime.c"
+#include "deadline.c"
+
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
new file mode 100644
index 000000000000..eec0849b2aae
--- /dev/null
+++ b/kernel/sched/build_utility.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * These are various utility functions of the scheduler,
+ * built in a single compilation unit for build efficiency reasons.
+ *
+ * ( Incidentally, the size of the compilation unit is roughly
+ *   comparable to core.c, fair.c, smp.c and policy.c, the other
+ *   big compilation units. This helps balance build time, while
+ *   coalescing source files to amortize header inclusion
+ *   cost. )
+ */
+#include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/rseq_api.h>
+#include <linux/sched/task_stack.h>
+
+#include <linux/cpufreq.h>
+#include <linux/cpumask_api.h>
+#include <linux/cpuset.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/energy_model.h>
+#include <linux/hashtable_api.h>
+#include <linux/irq.h>
+#include <linux/kobject_api.h>
+#include <linux/membarrier.h>
+#include <linux/mempolicy.h>
+#include <linux/nmi.h>
+#include <linux/nospec.h>
+#include <linux/proc_fs.h>
+#include <linux/psi.h>
+#include <linux/psi.h>
+#include <linux/ptrace_api.h>
+#include <linux/sched_clock.h>
+#include <linux/security.h>
+#include <linux/spinlock_api.h>
+#include <linux/swait_api.h>
+#include <linux/timex.h>
+#include <linux/utsname.h>
+#include <linux/wait_api.h>
+#include <linux/workqueue_api.h>
+
+#include <uapi/linux/prctl.h>
+#include <uapi/linux/sched/types.h>
+
+#include <asm/switch_to.h>
+
+#include "sched.h"
+#include "sched-pelt.h"
+#include "stats.h"
+#include "autogroup.h"
+
+#include "clock.c"
+
+#ifdef CONFIG_CGROUP_CPUACCT
+# include "cpuacct.c"
+#endif
+
+#ifdef CONFIG_CPU_FREQ
+# include "cpufreq.c"
+#endif
+
+#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+# include "cpufreq_schedutil.c"
+#endif
+
+#ifdef CONFIG_SCHED_DEBUG
+# include "debug.c"
+#endif
+
+#ifdef CONFIG_SCHEDSTATS
+# include "stats.c"
+#endif
+
+#include "loadavg.c"
+#include "completion.c"
+#include "swait.c"
+#include "wait_bit.c"
+#include "wait.c"
+
+#ifdef CONFIG_SMP
+# include "cpupri.c"
+# include "stop_task.c"
+# include "topology.c"
+#endif
+
+#ifdef CONFIG_SCHED_CORE
+# include "core_sched.c"
+#endif
+
+#ifdef CONFIG_PSI
+# include "psi.c"
+#endif
+
+#ifdef CONFIG_MEMBARRIER
+# include "membarrier.c"
+#endif
+
+#ifdef CONFIG_CPU_ISOLATION
+# include "isolation.c"
+#endif
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+# include "autogroup.c"
+#endif
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c2b2859ddd82..d9272d9061a3 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -53,15 +53,13 @@
  * that is otherwise invisible (TSC gets stopped).
  *
  */
-#include "sched.h"
-#include <linux/sched_clock.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
  * This is default implementation.
  * Architectures and sub-architectures can override this.
  */
-unsigned long long __weak sched_clock(void)
+notrace unsigned long long __weak sched_clock(void)
 {
 	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
 					* (NSEC_PER_SEC / HZ);
@@ -95,28 +93,28 @@ struct sched_clock_data {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
-static inline struct sched_clock_data *this_scd(void)
+notrace static inline struct sched_clock_data *this_scd(void)
 {
 	return this_cpu_ptr(&sched_clock_data);
 }
 
-static inline struct sched_clock_data *cpu_sdc(int cpu)
+notrace static inline struct sched_clock_data *cpu_sdc(int cpu)
 {
 	return &per_cpu(sched_clock_data, cpu);
 }
 
-int sched_clock_stable(void)
+notrace int sched_clock_stable(void)
 {
 	return static_branch_likely(&__sched_clock_stable);
 }
 
-static void __scd_stamp(struct sched_clock_data *scd)
+notrace static void __scd_stamp(struct sched_clock_data *scd)
 {
 	scd->tick_gtod = ktime_get_ns();
 	scd->tick_raw = sched_clock();
 }
 
-static void __set_sched_clock_stable(void)
+notrace static void __set_sched_clock_stable(void)
 {
 	struct sched_clock_data *scd;
 
@@ -151,7 +149,7 @@ static void __set_sched_clock_stable(void)
  * The only way to fully avoid random clock jumps is to boot with:
  * "tsc=unstable".
  */
-static void __sched_clock_work(struct work_struct *work)
+notrace static void __sched_clock_work(struct work_struct *work)
 {
 	struct sched_clock_data *scd;
 	int cpu;
@@ -177,7 +175,7 @@ static void __sched_clock_work(struct work_struct *work)
 
 static DECLARE_WORK(sched_clock_work, __sched_clock_work);
 
-static void __clear_sched_clock_stable(void)
+notrace static void __clear_sched_clock_stable(void)
 {
 	if (!sched_clock_stable())
 		return;
@@ -186,7 +184,7 @@ static void __clear_sched_clock_stable(void)
 	schedule_work(&sched_clock_work);
 }
 
-void clear_sched_clock_stable(void)
+notrace void clear_sched_clock_stable(void)
 {
 	__sched_cl