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 ...
author: Linus Torvalds 2022-03-22 14:39:12 -0700
committer: Linus Torvalds 2022-03-22 14:39:12 -0700
commit: 3fe2f7446f1e029b220f7f650df6d138f91651f2 (patch)
tree: bc6f9adc91f9e4fd4d78f49f1188388ebfa90bcb /kernel/sched
parent: ebd326ce724d5b2e5274724e6d6a46a046e28203 (diff)
parent: ffea9fb319360b9ead8befac6bb2db2b54fd53e6 (diff)
33 files changed, 1204 insertions, 765 deletions
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_clock_stable_early = 0;
 
@@ -196,7 +194,7 @@ void clear_sched_clock_stable(void)
 		__clear_sched_clock_stable();
 }
 
-static void __sched_clock_gtod_offset(void)
+notrace static void __sched_clock_gtod_offset(void)
 {
 	struct sched_clock_data *scd = this_scd();
 
@@ -246,12 +244,12 @@ late_initcall(sched_clock_init_late);
  * min, max except they take wrapping into account
  */
 
-static inline u64 wrap_min(u64 x, u64 y)
+notrace static inline u64 wrap_min(u64 x, u64 y)
 {
 	return (s64)(x - y) < 0 ? x : y;
 }
 
-static inline u64 wrap_max(u64 x, u64 y)
+notrace static inline u64 wrap_max(u64 x, u64 y)
 {
 	return (s64)(x - y) > 0 ? x : y;
 }
@@ -262,7 +260,7 @@ static inline u64 wrap_max(u64 x, u64 y)
  *  - filter out backward motion
  *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-static u64 sched_clock_local(struct sched_clock_data *scd)
+notrace static u64 sched_clock_local(struct sched_clock_data *scd)
 {
 	u64 now, clock, old_clock, min_clock, max_clock, gtod;
 	s64 delta;
@@ -295,7 +293,7 @@ again:
 	return clock;
 }
 
-static u64 sched_clock_remote(struct sched_clock_data *scd)
+notrace static u64 sched_clock_remote(struct sched_clock_data *scd)
 {
 	struct sched_clock_data *my_scd = this_scd();
 	u64 this_clock, remote_clock;
@@ -362,7 +360,7 @@ again:
  *
  * See cpu_clock().
  */
-u64 sched_clock_cpu(int cpu)
+notrace u64 sched_clock_cpu(int cpu)
 {
 	struct sched_clock_data *scd;
 	u64 clock;
@@ -386,7 +384,7 @@ u64 sched_clock_cpu(int cpu)
 }
 EXPORT_SYMBOL_GPL(sched_clock_cpu);
 
-void sched_clock_tick(void)
+notrace void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
 
@@ -403,7 +401,7 @@ void sched_clock_tick(void)
 	sched_clock_local(scd);
 }
 
-void sched_clock_tick_stable(void)
+notrace void sched_clock_tick_stable(void)
 {
 	if (!sched_clock_stable())
 		return;
@@ -423,7 +421,7 @@ void sched_clock_tick_stable(void)
 /*
  * We are going deep-idle (irqs are disabled):
  */
-void sched_clock_idle_sleep_event(void)
+notrace void sched_clock_idle_sleep_event(void)
 {
 	sched_clock_cpu(smp_processor_id());
 }
@@ -432,7 +430,7 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
 /*
  * We just idled; resync with ktime.
  */
-void sched_clock_idle_wakeup_event(void)
+notrace void sched_clock_idle_wakeup_event(void)
 {
 	unsigned long flags;
 
@@ -458,7 +456,7 @@ void __init sched_clock_init(void)
 	local_irq_enable();
 }
 
-u64 sched_clock_cpu(int cpu)
+notrace u64 sched_clock_cpu(int cpu)
 {
 	if (!static_branch_likely(&sched_clock_running))
 		return 0;
@@ -476,7 +474,7 @@ u64 sched_clock_cpu(int cpu)
  * On bare metal this function should return the same as local_clock.
  * Architectures and sub-architectures can override this.
  */
-u64 __weak running_clock(void)
+notrace u64 __weak running_clock(void)
 {
 	return local_clock();
 }
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a778554f9dad..35f15c26ed54 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * Generic wait-for-completion handler;
  *
@@ -11,7 +12,6 @@
  * typically be used for exclusion which gives rise to priority inversion.
  * Waiting for completion is a typically sync point, but not an exclusion point.
  */
-#include "sched.h"
 
 /**
  * complete: - signals a single thread waiting on this completion
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6c56ee848e2a..6dc68465116b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,26 +6,90 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-#undef CREATE_TRACE_POINTS
-
-#include "sched.h"
+#include <linux/highmem.h>
+#include <linux/hrtimer_api.h>
+#include <linux/ktime_api.h>
+#include <linux/sched/signal.h>
+#include <linux/syscalls_api.h>
+#include <linux/debug_locks.h>
+#include <linux/prefetch.h>
+#include <linux/capability.h>
+#include <linux/pgtable_api.h>
+#include <linux/wait_bit.h>
+#include <linux/jiffies.h>
+#include <linux/spinlock_api.h>
+#include <linux/cpumask_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/hardirq.h>
+#include <linux/softirq.h>
+#include <linux/refcount_api.h>
+#include <linux/topology.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/cond_resched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/nohz.h>
+#include <linux/sched/rseq_api.h>
+#include <linux/sched/rt.h>
 
-#include <linux/nospec.h>
 #include <linux/blkdev.h>
+#include <linux/context_tracking.h>
+#include <linux/cpuset.h>
+#include <linux/delayacct.h>
+#include <linux/init_task.h>
+#include <linux/interrupt.h>
+#include <linux/ioprio.h>
+#include <linux/kallsyms.h>
 #include <linux/kcov.h>
+#include <linux/kprobes.h>
+#include <linux/llist_api.h>
+#include <linux/mmu_context.h>
+#include <linux/mmzone.h>
+#include <linux/mutex_api.h>
+#include <linux/nmi.h>
+#include <linux/nospec.h>
+#include <linux/perf_event_api.h>
+#include <linux/profile.h>
+#include <linux/psi.h>
+#include <linux/rcuwait_api.h>
+#include <linux/sched/wake_q.h>
 #include <linux/scs.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/vtime.h>
+#include <linux/wait_api.h>
+#include <linux/workqueue_api.h>
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+# ifdef CONFIG_GENERIC_ENTRY
+#  include <linux/entry-common.h>
+# endif
+#endif
+
+#include <uapi/linux/sched/types.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
-#include "../workqueue_internal.h"
-#include "../../fs/io-wq.h"
-#include "../smpboot.h"
+#define CREATE_TRACE_POINTS
+#include <linux/sched/rseq_api.h>
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
+#include "sched.h"
+#include "stats.h"
+#include "autogroup.h"
 
+#include "autogroup.h"
 #include "pelt.h"
 #include "smp.h"
+#include "stats.h"
+
+#include "../workqueue_internal.h"
+#include "../../fs/io-wq.h"
+#include "../smpboot.h"
 
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
@@ -36,6 +100,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
@@ -1024,13 +1089,13 @@ int get_nohz_timer_target(void)
 	struct sched_domain *sd;
 	const struct cpumask *hk_mask;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+	if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
 		if (!idle_cpu(cpu))
 			return cpu;
 		default_cpu = cpu;
 	}
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+	hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
@@ -1046,7 +1111,7 @@ int get_nohz_timer_target(void)
 	}
 
 	if (default_cpu == -1)
-		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+		default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
 	cpu = default_cpu;
 unlock:
 	rcu_read_unlock();
@@ -4834,7 +4899,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 {
 	struct rq *rq = this_rq();
 	struct mm_struct *mm = rq->prev_mm;
-	long prev_state;
+	unsigned int prev_state;
 
 	/*
 	 * The previous task will have left us with a preempt_count of 2
@@ -5379,7 +5444,7 @@ static void sched_tick_start(int cpu)
 	int os;
 	struct tick_work *twork;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -5400,7 +5465,7 @@ static void sched_tick_stop(int cpu)
 	struct tick_work *twork;
 	int os;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -6298,7 +6363,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -6490,17 +6555,31 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 	 */
 	if (likely(!preemptible()))
 		return;
-
 	preempt_schedule_common();
 }
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
-DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#ifndef preempt_schedule_dynamic_enabled
+#define preempt_schedule_dynamic_enabled	preempt_schedule
+#define preempt_schedule_dynamic_disabled	NULL
+#endif
+DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
 EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
+void __sched notrace dynamic_preempt_schedule(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
+		return;
+	preempt_schedule();
+}
+NOKPROBE_SYMBOL(dynamic_preempt_schedule);
+EXPORT_SYMBOL(dynamic_preempt_schedule);
+#endif
 #endif
-
 
 /**
  * preempt_schedule_notrace - preempt_schedule called by tracing
@@ -6555,147 +6634,27 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
-DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
-EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#ifndef preempt_schedule_notrace_dynamic_enabled
+#define preempt_schedule_notrace_dynamic_enabled	preempt_schedule_notrace
+#define preempt_schedule_notrace_dynamic_disabled	NULL
 #endif
-
-#endif /* CONFIG_PREEMPTION */
-
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-#include <linux/entry-common.h>
-
-/*
- * SC:cond_resched
- * SC:might_resched
- * SC:preempt_schedule
- * SC:preempt_schedule_notrace
- * SC:irqentry_exit_cond_resched
- *
- *
- * NONE:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- RET0
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
- *
- * VOLUNTARY:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- __cond_resched
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
- *
- * FULL:
- *   cond_resched               <- RET0
- *   might_resched              <- RET0
- *   preempt_schedule           <- preempt_schedule
- *   preempt_schedule_notrace   <- preempt_schedule_notrace
- *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
- */
-
-enum {
-	preempt_dynamic_undefined = -1,
-	preempt_dynamic_none,
-	preempt_dynamic_voluntary,
-	preempt_dynamic_full,
-};
-
-int preempt_dynamic_mode = preempt_dynamic_undefined;
-
-int sched_dynamic_mode(const char *str)
-{
-	if (!strcmp(str, "none"))
-		return preempt_dynamic_none;
-
-	if (!strcmp(str, "voluntary"))
-		return preempt_dynamic_voluntary;
-
-	if (!strcmp(str, "full"))
-		return preempt_dynamic_full;
-
-	return -EINVAL;
-}
-
-void sched_dynamic_update(int mode)
-{
-	/*
-	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
-	 * the ZERO state, which is invalid.
-	 */
-	static_call_update(cond_resched, __cond_resched);
-	static_call_update(might_resched, __cond_resched);
-	static_call_update(preempt_schedule, __preempt_schedule_func);
-	static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
-	static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
-
-	switch (mode) {
-	case preempt_dynamic_none:
-		static_call_update(cond_resched, __cond_resched);
-		static_call_update(might_resched, (void *)&__static_call_return0);
-		static_call_update(preempt_schedule, NULL);
-		static_call_update(preempt_schedule_notrace, NULL);
-		static_call_update(irqentry_exit_cond_resched, NULL);
-		pr_info("Dynamic Preempt: none\n");
-		break;
-
-	case preempt_dynamic_voluntary:
-		static_call_update(cond_resched, __cond_resched);
-		static_call_update(might_resched, __cond_resched);
-		static_call_update(preempt_schedule, NULL);
-		static_call_update(preempt_schedule_notrace, NULL);
-		static_call_update(irqentry_exit_cond_resched, NULL);
-		pr_info("Dynamic Preempt: voluntary\n");
-		break;
-
-	case preempt_dynamic_full:
-		static_call_update(cond_resched, (void *)&__static_call_return0);
-		static_call_update(might_resched, (void *)&__static_call_return0);
-		static_call_update(preempt_schedule, __preempt_schedule_func);
-		static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
-		static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
-		pr_info("Dynamic Preempt: full\n");
-		break;
-	}
-
-	preempt_dynamic_mode = mode;
-}
-
-static int __init setup_preempt_mode(char *str)
-{
-	int mode = sched_dynamic_mode(str);
-	if (mode < 0) {
-		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-		return 0;
-	}
-
-	sched_dynamic_update(mode);
-	return 1;
-}
-__setup("preempt=", setup_preempt_mode);
-
-static void __init preempt_dynamic_init(void)
+DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
+void __sched notrace dynamic_preempt_schedule_notrace(void)
 {
-	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
-		if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
-			sched_dynamic_update(preempt_dynamic_none);
-		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
-			sched_dynamic_update(preempt_dynamic_voluntary);
-		} else {
-			/* Default static call setting, nothing to do */
-			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
-			preempt_dynamic_mode = preempt_dynamic_full;
-			pr_info("Dynamic Preempt: full\n");
-		}
-	}
+	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
+		return;
+	preempt_schedule_notrace();
 }
+NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
+EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
+#endif
+#endif
 
-#else /* !CONFIG_PREEMPT_DYNAMIC */
-
-static inline void preempt_dynamic_init(void) { }
-
-#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
+#endif /* CONFIG_PREEMPTION */
 
 /*
  * This is the entry point to schedule() from kernel preemption
@@ -8202,11 +8161,35 @@ EXPORT_SYMBOL(__cond_resched);
 #endif
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define cond_resched_dynamic_enabled	__cond_resched
+#define cond_resched_dynamic_disabled	((void *)&__static_call_return0)
 DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
 EXPORT_STATIC_CALL_TRAMP(cond_resched);
 
+#define might_resched_dynamic_enabled	__cond_resched
+#define might_resched_dynamic_disabled	((void *)&__static_call_return0)
 DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
 EXPORT_STATIC_CALL_TRAMP(might_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
+int __sched dynamic_cond_resched(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
+		return 0;
+	return __cond_resched();
+}
+EXPORT_SYMBOL(dynamic_cond_resched);
+
+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
+int __sched dynamic_might_resched(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_might_resched))
+		return 0;
+	return __cond_resched();
+}
+EXPORT_SYMBOL(dynamic_might_resched);
+#endif
 #endif
 
 /*
@@ -8271,6 +8254,154 @@ int __cond_resched_rwlock_write(rwlock_t *lock)
 }
 EXPORT_SYMBOL(__cond_resched_rwlock_write);
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+#ifdef CONFIG_GENERIC_ENTRY
+#include <linux/entry-common.h>
+#endif
+
+/*
+ * SC:cond_resched
+ * SC:might_resched
+ * SC:preempt_schedule
+ * SC:preempt_schedule_notrace
+ * SC:irqentry_exit_cond_resched
+ *
+ *
+ * NONE:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * VOLUNTARY:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- __cond_resched
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * FULL:
+ *   cond_resched               <- RET0
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- preempt_schedule
+ *   preempt_schedule_notrace   <- preempt_schedule_notrace
+ *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
+ */
+
+enum {
+	preempt_dynamic_undefined = -1,
+	preempt_dynamic_none,
+	preempt_dynamic_voluntary,
+	preempt_dynamic_full,
+};
+
+int preempt_dynamic_mode = preempt_dynamic_undefined;
+
+int sched_dynamic_mode(const char *str)
+{
+	if (!strcmp(str, "none"))
+		return preempt_dynamic_none;
+
+	if (!strcmp(str, "voluntary"))
+		return preempt_dynamic_voluntary;
+
+	if (!strcmp(str, "full"))
+		return preempt_dynamic_full;
+
+	return -EINVAL;
+}
+
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define preempt_dynamic_enable(f)	static_call_update(f, f##_dynamic_enabled)
+#define preempt_dynamic_disable(f)	static_call_update(f, f##_dynamic_disabled)
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+#define preempt_dynamic_enable(f)	static_key_enable(&sk_dynamic_##f.key)
+#define preempt_dynamic_disable(f)	static_key_disable(&sk_dynamic_##f.key)
+#else
+#error "Unsupported PREEMPT_DYNAMIC mechanism"
+#endif
+
+void sched_dynamic_update(int mode)
+{
+	/*
+	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
+	 * the ZERO state, which is invalid.
+	 */
+	preempt_dynamic_enable(cond_resched);
+	preempt_dynamic_enable(might_resched);
+	preempt_dynamic_enable(preempt_schedule);
+	preempt_dynamic_enable(preempt_schedule_notrace);
+	preempt_dynamic_enable(irqentry_exit_cond_resched);
+
+	switch (mode) {
+	case preempt_dynamic_none:
+		preempt_dynamic_enable(cond_resched);
+		preempt_dynamic_disable(might_resched);
+		preempt_dynamic_disable(preempt_schedule);
+		preempt_dynamic_disable(preempt_schedule_notrace);
+		preempt_dynamic_disable(irqentry_exit_cond_resched);
+		pr_info("Dynamic Preempt: none\n");
+		break;
+
+	case preempt_dynamic_voluntary:
+		preempt_dynamic_enable(cond_resched);
+		preempt_dynamic_enable(might_resched);
+		preempt_dynamic_disable(preempt_schedule);
+		preempt_dynamic_disable(preempt_schedule_notrace);
+		preempt_dynamic_disable(irqentry_exit_cond_resched);
+		pr_info("Dynamic Preempt: voluntary\n");
+		break;
+
+	case preempt_dynamic_full:
+		preempt_dynamic_disable(cond_resched);
+		preempt_dynamic_disable(might_resched);
+		preempt_dynamic_enable(preempt_schedule);
+		preempt_dynamic_enable(preempt_schedule_notrace);
+		preempt_dynamic_enable(irqentry_exit_cond_resched);
+		pr_info("Dynamic Preempt: full\n");
+		break;
+	}
+
+	preempt_dynamic_mode = mode;
+}
+
+static int __init setup_preempt_mode(char *str)
+{
+	int mode = sched_dynamic_mode(str);
+	if (mode < 0) {
+		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
+		return 0;
+	}
+
+	sched_dynamic_update(mode);
+	return 1;
+}
+__setup("preempt=", setup_preempt_mode);
+
+static void __init preempt_dynamic_init(void)
+{
+	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
+		if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
+			sched_dynamic_update(preempt_dynamic_none);
+		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
+			sched_dynamic_update(preempt_dynamic_voluntary);
+		} else {
+			/* Default static call setting, nothing to do */
+			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
+			preempt_dynamic_mode = preempt_dynamic_full;
+			pr_info("Dynamic Preempt: full\n");
+		}
+	}
+}
+
+#else /* !CONFIG_PREEMPT_DYNAMIC */
+
+static inline void preempt_dynamic_init(void) { }
+
+#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
+
 /**
  * yield - yield the current processor to other threads.
  *
@@ -8706,7 +8837,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 {
 	int ret = 1;
 
-	if (!cpumask_weight(cur))
+	if (cpumask_empty(cur))
 		return ret;
 
 	ret = dl_cpuset_cpumask_can_shrink(cur, trial);
@@ -8734,8 +8865,11 @@ int task_can_attach(struct task_struct *p,
 	}
 
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed))
-		ret = dl_task_can_attach(p, cs_cpus_allowed);
+					      cs_cpus_allowed)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+
+		ret = dl_cpu_busy(cpu, p);
+	}
 
 out:
 	return ret;
@@ -9019,8 +9153,10 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		if (dl_cpu_busy(cpu))
-			return -EBUSY;
+		int ret = dl_cpu_busy(cpu, NULL);
+
+		if (ret)
+			return ret;
 		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
@@ -9050,6 +9186,7 @@ int sched_cpu_activate(unsigned int cpu)
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
+		sched_update_numa(cpu, true);
 		sched_domains_numa_masks_set(cpu);
 		cpuset_cpu_active();
 	}
@@ -9128,10 +9265,12 @@ int sched_cpu_deactivate(unsigned int cpu)
 	if (!sched_smp_initialized)
 		return 0;
 
+	sched_update_numa(cpu, false);
 	ret = cpuset_cpu_inactive(cpu);
 	if (ret) {
 		balance_push_set(cpu, false);
 		set_cpu_active(cpu, true);
+		sched_update_numa(cpu, true);
 		return ret;
 	}
 	sched_domains_numa_masks_clear(cpu);
@@ -9234,7 +9373,7 @@ int sched_cpu_dying(unsigned int cpu)
 
 void __init sched_init_smp(void)
 {
-	sched_init_numa();
+	sched_init_numa(NUMA_NO_NODE);
 
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
@@ -9246,7 +9385,7 @@ void __init sched_init_smp(void)
 	mutex_unlock(&sched_domains_mutex);
 
 	/* Move init over to a non-isolated CPU */
-	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
+	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
 		BUG();
 	current->flags &= ~PF_NO_SETAFFINITY;
 	sched_init_granularity();
@@ -9346,7 +9485,6 @@ void __init sched_init(void)
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
-	init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
 
 #ifdef CONFIG_SMP
 	init_defrootdomain();
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index c8746a9a7ada..38a2cec21014 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -1,8 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
-#include <linux/prctl.h>
-#include "sched.h"
-
 /*
  * A simple wrapper around refcount. An allocated sched_core_cookie's
  * address is used to compute the cookie of the task.
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 3d06c5e4220d..0de9dda09949 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -1,12 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
+
 /*
  * CPU accounting code for task groups.
  *
  * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
  * (balbir@in.ibm.com).
  */
-#include <asm/irq_regs.h>
-#include "sched.h"
 
 /* Time spent by the tasks of the CPU accounting group executing in ... */
 enum cpuacct_stat_index {
@@ -334,14 +333,13 @@ static struct cftype files[] = {
  */
 void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
+	unsigned int cpu = task_cpu(tsk);
 	struct cpuacct *ca;
 
-	rcu_read_lock();
+	lockdep_assert_rq_held(cpu_rq(cpu));
 
 	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
-		__this_cpu_add(*ca->cpuusage, cputime);
-
-	rcu_read_unlock();
+		*per_cpu_ptr(ca->cpuusage, cpu) += cputime;
 }
 
 /*
@@ -353,10 +351,8 @@ void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 {
 	struct cpuacct *ca;
 
-	rcu_read_lock();
 	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
 		__this_cpu_add(ca->cpustat->cpustat[index], val);
-	rcu_read_unlock();
 }
 
 struct cgroup_subsys cpuacct_cgrp_subsys = {
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index ceb03d76c0cc..02d970a879ed 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -1,12 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *  kernel/sched/cpudl.c
+ *  kernel/sched/cpudeadline.c
  *
  *  Global CPU deadline management
  *
  *  Author: Juri Lelli <j.lelli@sssup.it>
  */
-#include "sched.h"
 
 static inline int parent(int i)
 {
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 7c2fe50fd76d..5252fb191fae 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,9 +5,6 @@
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
-#include <linux/cpufreq.h>
-
-#include "sched.h"
 
 DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index cffcd08f4ec8..3dbf351d12d5 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -6,13 +6,6 @@
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "sched.h"
-
-#include <linux/sched/cpufreq.h>
-#include <trace/events/power.h>
-
 #define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
 
 struct sugov_tunables {
@@ -289,6 +282,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * into the same scale so we can compare.
 	 */
 	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
 }
@@ -348,8 +342,11 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
 	 */
-	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
@@ -395,8 +392,11 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	/*
 	 * Do not reduce the target performance level if the CPU has not been
 	 * idle recently, as the reduction is likely to be premature then.
+	 *
+	 * Except when the rq is capped by uclamp_max.
 	 */
-	if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
+	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index d583f2aa744e..fa9ce9d83683 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -22,7 +22,6 @@
  *  worst case complexity of O(min(101, nr_domcpus)), though the scenario that
  *  yields the worst case search is fairly contrived.
  */
-#include "sched.h"
 
 /*
  * p->rt_priority   p->prio   newpri   cpupri
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index b7ec42732b28..78a233d43757 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -2,7 +2,6 @@
 /*
  * Simple CPU accounting cgroup controller
  */
-#include "sched.h"
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d2c072b0ef01..fb4255ae0b2c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -15,10 +15,6 @@
  *                    Michael Trimarchi <michael@amarulasolutions.com>,
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
-#include "sched.h"
-#include "pelt.h"
-
-struct dl_bandwidth def_dl_bandwidth;
 
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
@@ -130,6 +126,21 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 	rd->visit_gen = gen;
 	return false;
 }
+
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
+	int i;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		struct rq *rq = cpu_rq(i);
+
+		rq->dl.extra_bw += bw;
+	}
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -150,9 +161,38 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 {
 	return false;
 }
+
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
+
+	dl->extra_bw += bw;
+}
 #endif
 
 static inline
+void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
+{
+	dl_b->total_bw -= tsk_bw;
+	__dl_update(dl_b, (s32)tsk_bw / cpus);
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
+{
+	dl_b->total_bw += tsk_bw;
+	__dl_update(dl_b, -((s32)tsk_bw / cpus));
+}
+
+static inline bool
+__dl_overflow(struct dl_bw *dl_b, unsigned long cap, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
+}
+
+static inline
 void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->running_bw;
@@ -408,7 +448,7 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	return dl_rq->root.rb_leftmost == &dl_se->rb_node;
+	return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
 }
 
 static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
@@ -423,12 +463,10 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
-	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
 	if (global_rt_runtime() == RUNTIME_INF)
 		dl_b->bw = -1;
 	else
 		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
-	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
 	dl_b->total_bw = 0;
 }
 
@@ -683,15 +721,6 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 }
 
-static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_dl_task(struct rq *rq)
-{
-}
-
 static inline void deadline_queue_push_tasks(struct rq *rq)
 {
 }
@@ -1393,6 +1422,9 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = inactive_task_timer;
 }
 
+#define __node_2_dle(node) \
+	rb_entry((node), struct sched_dl_entity, rb_node)
+
 #ifdef CONFIG_SMP
 
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
@@ -1422,10 +1454,9 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		cpudl_clear(&rq->rd->cpudl, rq->cpu);
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 	} else {
-		struct rb_node *leftmost = dl_rq->root.rb_leftmost;
-		struct sched_dl_entity *entry;
+		struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
+		struct sched_dl_entity *entry = __node_2_dle(leftmost);
 
-		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline);
 	}
@@ -1466,9 +1497,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	dec_dl_migration(dl_se, dl_rq);
 }
 
-#define __node_2_dle(node) \
-	rb_entry((node), struct sched_dl_entity, rb_node)
-
 static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
 {
 	return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
@@ -1931,15 +1959,14 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	deadline_queue_push_tasks(rq);
 }
 
-static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
-						   struct dl_rq *dl_rq)
+static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
 {
 	struct rb_node *left = rb_first_cached(&dl_rq->root);
 
 	if (!left)
 		return NULL;
 
-	return rb_entry(left, struct sched_dl_entity, rb_node);
+	return __node_2_dle(left);
 }
 
 static struct task_struct *pick_task_dl(struct rq *rq)
@@ -1951,7 +1978,7 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
-	dl_se = pick_next_dl_entity(rq, dl_rq);
+	dl_se = pick_next_dl_entity(dl_rq);
 	BUG_ON(!dl_se);
 	p = dl_task_of(dl_se);
 
@@ -2034,15 +2061,17 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
  */
 static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
 {
-	struct rb_node *next_node = rq->dl.pushable_dl_tasks_root.rb_leftmost;
 	struct task_struct *p = NULL;
+	struct rb_node *next_node;
 
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
+	next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root);
+
 next_node:
 	if (next_node) {
-		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+		p = __node_2_pdl(next_node);
 
 		if (pick_dl_task(rq, p, cpu))
 			return p;
@@ -2208,8 +2237,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
-	p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost,
-		     struct task_struct, pushable_dl_tasks);
+	p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
@@ -2240,12 +2268,6 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (is_migration_disabled(next_task))
-		return 0;
-
-	if (WARN_ON(next_task == rq->curr))
-		return 0;
-
 	/*
 	 * If next_task preempts rq->curr, and rq->curr
 	 * can move away, it makes sense to just reschedule
@@ -2258,6 +2280,12 @@ retry:
 		return 0;
 	}
 
+	if (is_migration_disabled(next_task))
+		return 0;
+
+	if (WARN_ON(next_task == rq->curr))
+		return 0;
+
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
@@ -2731,9 +2759,6 @@ void sched_dl_do_global(void)
 	int cpu;
 	unsigned long flags;
 
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
@@ -2955,41 +2980,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 }
 
 #ifdef CONFIG_SMP
-int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
-{
-	unsigned long flags, cap;
-	unsigned int dest_cpu;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int ret;
-
-	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
-
-	rcu_read_lock_sched();
-	dl_b = dl_bw_of(dest_cpu);
-	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(dest_cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
-	if (overflow) {
-		ret = -EBUSY;
-	} else {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		int cpus = dl_bw_cpus(dest_cpu);
-
-		__dl_add(dl_b, p->dl.dl_bw, cpus);
-		ret = 0;
-	}
-	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-	rcu_read_unlock_sched();
-
-	return ret;
-}
-
 int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 				 const struct cpumask *trial)
 {
@@ -3011,7 +3001,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-bool dl_cpu_busy(unsigned int cpu)
+int dl_cpu_busy(int cpu, struct task_struct *p)
 {
 	unsigned long flags, cap;
 	struct dl_bw *dl_b;
@@ -3021,11 +3011,22 @@ bool dl_cpu_busy(unsigned int cpu)
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
 	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, 0);
+	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
+
+	if (!overflow && p) {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	}
+
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
-	return overflow;
+	return overflow ? -EBUSY : 0;
 }
 #endif
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index aa29211de1bf..bb3d63bdf4ae 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -6,7 +6,6 @@
  *
  * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
  */
-#include "sched.h"
 
 /*
  * This allows printing both to /proc/sched_debug and
@@ -931,25 +930,15 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 {
 #ifdef CONFIG_NUMA_BALANCING
-	struct mempolicy *pol;
-
 	if (p->mm)
 		P(mm->numa_scan_seq);
 
-	task_lock(p);
-	pol = p->mempolicy;
-	if (pol && !(pol->flags & MPOL_F_MORON))
-		pol = NULL;
-	mpol_get(pol);
-	task_unlock(p);
-
 	P(numa_pages_migrated);
 	P(numa_preferred_nid);
 	P(total_numa_faults);
 	SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
 			task_node(p), task_numa_group_id(p));
 	show_numa_stats(p, m);
-	mpol_put(pol);
 #endif
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5146163bfabb..ee0664c9d291 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -20,7 +20,38 @@
  *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
+#include <linux/energy_model.h>
+#include <linux/mmap_lock.h>
+#include <linux/hugetlb_inline.h>
+#include <linux/jiffies.h>
+#include <linux/mm_api.h>
+#include <linux/highmem.h>
+#include <linux/spinlock_api.h>
+#include <linux/cpumask_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/softirq.h>
+#include <linux/refcount_api.h>
+#include <linux/topology.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/cond_resched.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/isolation.h>
+
+#include <linux/cpuidle.h>
+#include <linux/interrupt.h>
+#include <linux/mempolicy.h>
+#include <linux/mutex_api.h>
+#include <linux/profile.h>
+#include <linux/psi.h>
+#include <linux/ratelimit.h>
+
+#include <asm/switch_to.h>
+
+#include <linux/sched/cond_resched.h>
+
 #include "sched.h"
+#include "stats.h"
+#include "autogroup.h"
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
@@ -1259,10 +1290,10 @@ static bool numa_is_active_node(int nid, struct numa_group *ng)
 
 /* Handle placement on systems where not all nodes are directly connected. */
 static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
-					int maxdist, bool task)
+					int lim_dist, bool task)
 {
 	unsigned long score = 0;
-	int node;
+	int node, max_dist;
 
 	/*
 	 * All nodes are directly connected, and the same distance
@@ -1271,6 +1302,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 	if (sched_numa_topology_type == NUMA_DIRECT)
 		return 0;
 
+	/* sched_max_numa_distance may be changed in parallel. */
+	max_dist = READ_ONCE(sched_max_numa_distance);
 	/*
 	 * This code is called for each node, introducing N^2 complexity,
 	 * which should be ok given the number of nodes rarely exceeds 8.
@@ -1283,7 +1316,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * The furthest away nodes in the system are not interesting
 		 * for placement; nid was already counted.
 		 */
-		if (dist == sched_max_numa_distance || node == nid)
+		if (dist >= max_dist || node == nid)
 			continue;
 
 		/*
@@ -1293,8 +1326,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * "hoplimit", only nodes closer by than "hoplimit" are part
 		 * of each group. Skip other nodes.
 		 */
-		if (sched_numa_topology_type == NUMA_BACKPLANE &&
-					dist >= maxdist)
+		if (sched_numa_topology_type == NUMA_BACKPLANE && dist >= lim_dist)
 			continue;
 
 		/* Add up the faults from nearby nodes. */
@@ -1312,8 +1344,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * This seems to result in good task placement.
 		 */
 		if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
-			faults *= (sched_max_numa_distance - dist);
-			faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
+			faults *= (max_dist - dist);
+			faults /= (max_dist - LOCAL_DISTANCE);
 		}
 
 		score += faults;
@@ -1489,6 +1521,7 @@ struct task_numa_env {
 
 	int src_cpu, src_nid;
 	int dst_cpu, dst_nid;
+	int imb_numa_nr;
 
 	struct numa_stats src_stats, dst_stats;
 
@@ -1503,7 +1536,7 @@ struct task_numa_env {
 static unsigned long cpu_load(struct rq *rq);
 static unsigned long cpu_runnable(struct rq *rq);
 static inline long adjust_numa_imbalance(int imbalance,
-					int dst_running, int dst_weight);
+					int dst_running, int imb_numa_nr);
 
 static inline enum
 numa_type numa_classify(unsigned int imbalance_pct,
@@ -1884,7 +1917,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 		dst_running = env->dst_stats.nr_running + 1;
 		imbalance = max(0, dst_running - src_running);
 		imbalance = adjust_numa_imbalance(imbalance, dst_running,
-							env->dst_stats.weight);
+						  env->imb_numa_nr);
 
 		/* Use idle CPU if there is no imbalance */
 		if (!imbalance) {
@@ -1949,8 +1982,10 @@ static int task_numa_migrate(struct task_struct *p)
 	 */
 	rcu_read_lock();
 	sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
-	if (sd)
+	if (sd) {
 		env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
+		env.imb_numa_nr = sd->imb_numa_nr;
+	}
 	rcu_read_unlock();
 
 	/*
@@ -1985,7 +2020,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 */
 	ng = deref_curr_numa_group(p);
 	if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) {
-		for_each_online_node(nid) {
+		for_each_node_state(nid, N_CPU) {
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
 
@@ -2083,13 +2118,13 @@ static void numa_group_count_active_nodes(struct numa_group *numa_group)
 	unsigned long faults, max_faults = 0;
 	int nid, active_nodes = 0;
 
-	for_each_online_node(nid) {
+	for_each_node_state(nid, N_CPU) {
 		faults = group_faults_cpu(numa_group, nid);
 		if (faults > max_faults)
 			max_faults = faults;
 	}
 
-	for_each_online_node(nid) {
+	for_each_node_state(nid, N_CPU) {
 		faults = group_faults_cpu(numa_group, nid);
 		if (faults * ACTIVE_NODE_FRACTION > max_faults)
 			active_nodes++;
@@ -2243,7 +2278,7 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 
 		dist = sched_max_numa_distance;
 
-		for_each_online_node(node) {
+		for_each_node_state(node, N_CPU) {
 			score = group_weight(p, node, dist);
 			if (score > max_score) {
 				max_score = score;
@@ -2262,7 +2297,7 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 	 * inside the highest scoring group of nodes. The nodemask tricks
 	 * keep the complexity of the search down.
 	 */
-	nodes = node_online_map;
+	nodes = node_states[N_CPU];
 	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
 		unsigned long max_faults = 0;
 		nodemask_t max_group = NODE_MASK_NONE;
@@ -2401,6 +2436,21 @@ static void task_numa_placement(struct task_struct *p)
 		}
 	}
 
+	/* Cannot migrate task to CPU-less node */
+	if (max_nid != NUMA_NO_NODE && !node_state(max_nid, N_CPU)) {
+		int near_nid = max_nid;
+		int distance, near_distance = INT_MAX;
+
+		for_each_node_state(nid, N_CPU) {
+			distance = node_distance(max_nid, nid);
+			if (distance < near_distance) {
+				near_nid = nid;
+				near_distance = distance;
+			}
+		}
+		max_nid = near_nid;
+	}
+
 	if (ng) {
 		numa_group_count_active_nodes(ng);
 		spin_unlock_irq(group_lock);
@@ -2825,6 +2875,8 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 	/* Protect against double add, see task_tick_numa and task_numa_work */
 	p->numa_work.next		= &p->numa_work;
 	p->numa_faults			= NULL;
+	p->numa_pages_migrated		= 0;
+	p->total_numa_faults		= 0;
 	RCU_INIT_POINTER(p->numa_group, NULL);
 	p->last_task_numa_placement	= 0;
 	p->last_sum_exec_runtime	= 0;
@@ -9040,9 +9092,9 @@ static bool update_pick_idlest(struct sched_group *idlest,
  * This is an approximation as the number of running tasks may not be
  * related to the number of busy CPUs due to sched_setaffinity.
  */
-static inline bool allow_numa_imbalance(int dst_running, int dst_weight)
+static inline bool allow_numa_imbalance(int running, int imb_numa_nr)
 {
-	return (dst_running < (dst_weight >> 2));
+	return running <= imb_numa_nr;
 }
 
 /*
@@ -9176,12 +9228,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 				return idlest;
 #endif
 			/*
-			 * Otherwise, keep the task on this node to stay close
-			 * its wakeup source and improve locality. If there is
-			 * a real need of migration, periodic load balance will
-			 * take care of it.
+			 * Otherwise, keep the task close to the wakeup source
+			 * and improve locality if the number of running tasks
+			 * would remain below threshold where an imbalance is
+			 * allowed. If there is a real need of migration,
+			 * periodic load balance will take care of it.
 			 */
-			if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight))
+			if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, sd->imb_numa_nr))
 				return NULL;
 		}
 
@@ -9273,9 +9326,9 @@ next_group:
 #define NUMA_IMBALANCE_MIN 2
 
 static inline long adjust_numa_imbalance(int imbalance,
-				int dst_running, int dst_weight)
+				int dst_running, int imb_numa_nr)
 {
-	if (!allow_numa_imbalance(dst_running, dst_weight))
+	if (!allow_numa_imbalance(dst_running, imb_numa_nr))
 		return imbalance;
 
 	/*
@@ -9387,7 +9440,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		/* Consider allowing a small imbalance between NUMA groups */
 		if (env->sd->flags & SD_NUMA) {
 			env->imbalance = adjust_numa_imbalance(env->imbalance,
-				busiest->sum_nr_running, busiest->group_weight);
+				local->sum_nr_running + 1, env->sd->imb_numa_nr);
 		}
 
 		return;
@@ -10351,7 +10404,7 @@ static inline int on_null_domain(struct rq *rq)
  * - When one of the busy CPUs notice that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
- * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set
  *   anywhere yet.
  */
 
@@ -10360,7 +10413,7 @@ static inline int find_new_ilb(void)
 	int ilb;
 	const struct cpumask *hk_mask;
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_MISC);
+	hk_mask = housekeeping_cpumask(HK_TYPE_MISC);
 
 	for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
 
@@ -10376,7 +10429,7 @@ static inline int find_new_ilb(void)
 
 /*
  * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
- * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
+ * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {
@@ -10589,7 +10642,7 @@ void nohz_balance_enter_idle(int cpu)
 		return;
 
 	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
-	if (!housekeeping_cpu(cpu, HK_FLAG_SCHED))
+	if (!housekeeping_cpu(cpu, HK_TYPE_SCHED))
 		return;
 
 	/*
@@ -10805,7 +10858,7 @@ static void nohz_newidle_balance(struct rq *this_rq)
 	 * This CPU doesn't want to be disturbed by scheduler
 	 * housekeeping
 	 */
-	if (!housekeeping_cpu(this_cpu, HK_FLAG_SCHED))
+	if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED))
 		return;
 
 	/* Will wake up very soon. No time for doing anything else*/
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index d17b0a5ce6ac..8f8b5020e76a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -6,9 +6,6 @@
  * (NOTE: these are not related to SCHED_IDLE batch scheduled
  *        tasks which are handled in sched/fair.c )
  */
-#include "sched.h"
-
-#include <trace/events/power.h>
 
 /* Linker adds these: start and end of __cpuidle functions */
 extern char __cpuidle_text_start[], __cpuidle_text_end[];
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 7f06eaf12818..373d42c707bc 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -7,136 +7,179 @@
  * Copyright (C) 2017-2018 SUSE, Frederic Weisbecker
  *
  */
-#include "sched.h"
+
+enum hk_flags {
+	HK_FLAG_TIMER		= BIT(HK_TYPE_TIMER),
+	HK_FLAG_RCU		= BIT(HK_TYPE_RCU),
+	HK_FLAG_MISC		= BIT(HK_TYPE_MISC),
+	HK_FLAG_SCHED		= BIT(HK_TYPE_SCHED),
+	HK_FLAG_TICK		= BIT(HK_TYPE_TICK),
+	HK_FLAG_DOMAIN		= BIT(HK_TYPE_DOMAIN),
+	HK_FLAG_WQ		= BIT(HK_TYPE_WQ),
+	HK_FLAG_MANAGED_IRQ	= BIT(HK_TYPE_MANAGED_IRQ),
+	HK_FLAG_KTHREAD		= BIT(HK_TYPE_KTHREAD),
+};
 
 DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
 EXPORT_SYMBOL_GPL(housekeeping_overridden);
-static cpumask_var_t housekeeping_mask;
-static unsigned int housekeeping_flags;
 
-bool housekeeping_enabled(enum hk_flags flags)
+struct housekeeping {
+	cpumask_var_t cpumasks[HK_TYPE_MAX];
+	unsigned long flags;
+};
+
+static struct housekeeping housekeeping;
+
+bool housekeeping_enabled(enum hk_type type)
 {
-	return !!(housekeeping_flags & flags);
+	return !!(housekeeping.flags & BIT(type));
 }
 EXPORT_SYMBOL_GPL(housekeeping_enabled);
 
-int housekeeping_any_cpu(enum hk_flags flags)
+int housekeeping_any_cpu(enum hk_type type)
 {
 	int cpu;
 
 	if (static_branch_unlikely(&housekeeping_overridden)) {
-		if (housekeeping_flags & flags) {
-			cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id());
+		if (housekeeping.flags & BIT(type)) {
+			cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id());
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			return cpumask_any_and(housekeeping_mask, cpu_online_mask);
+			return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
 		}
 	}
 	return smp_processor_id();
 }
 EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
 
-const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
-			return housekeeping_mask;
+		if (housekeeping.flags & BIT(type))
+			return housekeeping.cpumasks[type];
 	return cpu_possible_mask;
 }
 EXPORT_SYMBOL_GPL(housekeeping_cpumask);
 
-void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
+void housekeeping_affine(struct task_struct *t, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
-			set_cpus_allowed_ptr(t, housekeeping_mask);
+		if (housekeeping.flags & BIT(type))
+			set_cpus_allowed_ptr(t, housekeeping.cpumasks[type]);
 }
 EXPORT_SYMBOL_GPL(housekeeping_affine);
 
-bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
+bool housekeeping_test_cpu(int cpu, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
-			return cpumask_test_cpu(cpu, housekeeping_mask);
+		if (housekeeping.flags & BIT(type))
+			return cpumask_test_cpu(cpu, housekeeping.cpumasks[type]);
 	return true;
 }
 EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
 
 void __init housekeeping_init(void)
 {
-	if (!housekeeping_flags)
+	enum hk_type type;
+
+	if (!housekeeping.flags)
 		return;
 
 	static_branch_enable(&housekeeping_overridden);
 
-	if (housekeeping_flags & HK_FLAG_TICK)
+	if (housekeeping.flags & HK_FLAG_TICK)
 		sched_tick_offload_init();
 
-	/* We need at least one CPU to handle housekeeping work */
-	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
+	for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
+		/* We need at least one CPU to handle housekeeping work */
+		WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type]));
+	}
 }
 
-static int __init housekeeping_setup(char *str, enum hk_flags flags)
+static void __init housekeeping_setup_type(enum hk_type type,
+					   cpumask_var_t housekeeping_staging)
 {
-	cpumask_var_t non_housekeeping_mask;
-	cpumask_var_t tmp;
+
+	alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]);
+	cpumask_copy(housekeeping.cpumasks[type],
+		     housekeeping_staging);
+}
+
+static int __init housekeeping_setup(char *str, unsigned long flags)
+{
+	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+	int err = 0;
+
+	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
+		if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+			pr_warn("Housekeeping: nohz unsupported."
+				" Build with CONFIG_NO_HZ_FULL\n");
+			return 0;
+		}
+	}
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
 	if (cpulist_parse(str, non_housekeeping_mask) < 0) {
 		pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
-		free_bootmem_cpumask_var(non_housekeeping_mask);
-		return 0;
+		goto free_non_housekeeping_mask;
 	}
 
-	alloc_bootmem_cpumask_var(&tmp);
-	if (!housekeeping_flags) {
-		alloc_bootmem_cpumask_var(&housekeeping_mask);
-		cpumask_andnot(housekeeping_mask,
-			       cpu_possible_mask, non_housekeeping_mask);
+	alloc_bootmem_cpumask_var(&housekeeping_staging);
+	cpumask_andnot(housekeeping_staging,
+		       cpu_possible_mask, non_housekeeping_mask);
 
-		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
-		if (cpumask_empty(tmp)) {
+	if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+		__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
+		__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+		if (!housekeeping.flags) {
 			pr_warn("Housekeeping: must include one present CPU, "
 				"using boot CPU:%d\n", smp_processor_id());
-			__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
-			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
-		}
-	} else {
-		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
-		if (cpumask_empty(tmp))
-			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
-		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
-		if (!cpumask_equal(tmp, housekeeping_mask)) {
-			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
-			free_bootmem_cpumask_var(tmp);
-			free_bootmem_cpumask_var(non_housekeeping_mask);
-			return 0;
 		}
 	}
-	free_bootmem_cpumask_var(tmp);
 
-	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
-		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
-			tick_nohz_full_setup(non_housekeeping_mask);
-		} else {
-			pr_warn("Housekeeping: nohz unsupported."
-				" Build with CONFIG_NO_HZ_FULL\n");
-			free_bootmem_cpumask_var(non_housekeeping_mask);
-			return 0;
+	if (!housekeeping.flags) {
+		/* First setup call ("nohz_full=" or "isolcpus=") */
+		enum hk_type type;
+
+		for_each_set_bit(type, &flags, HK_TYPE_MAX)
+			housekeeping_setup_type(type, housekeeping_staging);
+	} else {
+		/* Second setup call ("nohz_full=" after "isolcpus=" or the reverse) */
+		enum hk_type type;
+		unsigned long iter_flags = flags & housekeeping.flags;
+
+		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) {
+			if (!cpumask_equal(housekeeping_staging,
+					   housekeeping.cpumasks[type])) {
+				pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
+				goto free_housekeeping_staging;
+			}
 		}
+
+		iter_flags = flags & ~housekeeping.flags;
+
+		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX)
+			housekeeping_setup_type(type, housekeeping_staging);
 	}
 
-	housekeeping_flags |= flags;
+	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK))
+		tick_nohz_full_setup(non_housekeeping_mask);
+
+	housekeeping.flags |= flags;
+	err = 1;
 
+free_housekeeping_staging:
+	free_bootmem_cpumask_var(housekeeping_staging);
+free_non_housekeeping_mask:
 	free_bootmem_cpumask_var(non_housekeeping_mask);
 
-	return 1;
+	return err;
 }
 
 static int __init housekeeping_nohz_full_setup(char *str)
 {
-	unsigned int flags;
+	unsigned long flags;
 
 	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
 		HK_FLAG_MISC | HK_FLAG_KTHREAD;
@@ -147,7 +190,7 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);
 
 static int __init housekeeping_isolcpus_setup(char *str)
 {
-	unsigned int flags = 0;
+	unsigned long flags = 0;
 	bool illegal = false;
 	char *par;
 	int len;
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 954b229868d9..52c8f8226b0d 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -6,7 +6,6 @@
  * figure. Its a silly number but people think its important. We go through
  * great pains to make it work on big machines and tickless kernels.
  */
-#include "sched.h"
 
 /*
  * Global load-average calculations
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 3d2825408e3a..0c5be7ebb1dc 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -4,7 +4,6 @@
  *
  * membarrier system call
  */
-#include "sched.h"
 
 /*
  * For documentation purposes, here are some membarrier ordering
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a554e3bbab2b..0f310768260c 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -24,10 +24,6 @@
  *  Author: Vincent Guittot <vincent.guittot@linaro.org>
  */
 
-#include <linux/sched.h>
-#include "sched.h"
-#include "pelt.h"
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index e14358178849..a4fa3aadfcba 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -137,21 +137,6 @@
  * sampling of the aggregate task states would be.
  */
 
-#include "../workqueue_internal.h"
-#include <linux/sched/loadavg.h>
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/seqlock.h>
-#include <linux/uaccess.h>
-#include <linux/cgroup.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/ctype.h>
-#include <linux/file.h>
-#include <linux/poll.h>
-#include <linux/psi.h>
-#include "sched.h"
-
 static int psi_bug __read_mostly;
 
 DEFINE_STATIC_KEY_FALSE(psi_disabled);
@@ -523,7 +508,7 @@ static void init_triggers(struct psi_group *group, u64 now)
 static u64 update_triggers(struct psi_group *group, u64 now)
 {
 	struct psi_trigger *t;
-	bool new_stall = false;
+	bool update_total = false;
 	u64 *total = group->total[PSI_POLL];
 
 	/*
@@ -532,24 +517,35 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	 */
 	list_for_each_entry(t, &group->triggers, node) {
 		u64 growth;
+		bool new_stall;
 
-		/* Check for stall activity */
-		if (group->polling_total[t->state] == total[t->state])
-			continue;
+		new_stall = group->polling_total[t->state] != total[t->state];
 
+		/* Check for stall activity or a previous threshold breach */
+		if (!new_stall && !t->pending_event)
+			continue;
 		/*
-		 * Multiple triggers might be looking at the same state,
-		 * remember to update group->polling_total[] once we've
-		 * been through all of them. Also remember to extend the
-		 * polling time if we see new stall activity.
+		 * Check for new stall activity, as well as deferred
+		 * events that occurred in the last window after the
+		 * trigger had already fired (we want to ratelimit
+		 * events without dropping any).
 		 */
-		new_stall = true;
-
-		/* Calculate growth since last update */
-		growth = window_update(&t->win, now, total[t->state]);
-		if (growth < t->threshold)
-			continue;
-
+		if (new_stall) {
+			/*
+			 * Multiple triggers might be looking at the same state,
+			 * remember to update group->polling_total[] once we've
+			 * been through all of them. Also remember to extend the
+			 * polling time if we see new stall activity.
+			 */
+			update_total = true;
+
+			/* Calculate growth since last update */
+			growth = window_update(&t->win, now, total[t->state]);
+			if (growth < t->threshold)
+				continue;
+
+			t->pending_event = true;
+		}
 		/* Limit event signaling to once per window */
 		if (now < t->last_event_time + t->win.size)
 			continue;
@@ -558,9 +554,11 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 		if (cmpxchg(&t->event, 0, 1) == 0)
 			wake_up_interruptible(&t->event_wait);
 		t->last_event_time = now;
+		/* Reset threshold breach flag once event got generated */
+		t->pending_event = false;
 	}
 
-	if (new_stall)
+	if (update_total)
 		memcpy(group->polling_total, total,
 				sizeof(group->polling_total));
 
@@ -1124,6 +1122,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->event = 0;
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
+	t->pending_event = false;
 
 	mutex_lock(&group->trigger_lock);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7b4f4fbbb404..a32c46889af8 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -3,9 +3,6 @@
  * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
  * policies)
  */
-#include "sched.h"
-
-#include "pelt.h"
 
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
@@ -271,8 +268,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
 #ifdef CONFIG_SMP
 
-static void pull_rt_task(struct rq *this_rq);
-
 static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
@@ -429,15 +424,6 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
-static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_rt_task(struct rq *this_rq)
-{
-}
-
 static inline void rt_queue_push_tasks(struct rq *rq)
 {
 }
@@ -1730,8 +1716,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
 	rt_queue_push_tasks(rq);
 }
 
-static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
-						   struct rt_rq *rt_rq)
+static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array = &rt_rq->active;
 	struct sched_rt_entity *next = NULL;
@@ -1753,7 +1738,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
-		rt_se = pick_next_rt_entity(rq, rt_rq);
+		rt_se = pick_next_rt_entity(rt_rq);
 		BUG_ON(!rt_se);
 		rt_rq = group_rt_rq(rt_se);
 	} while (rt_rq);
@@ -2026,6 +2011,16 @@ static int push_rt_task(struct rq *rq, bool pull)
 		return 0;
 
 retry:
+	/*
+	 * It's possible that the next_task slipped in of
+	 * higher priority than current. If that's the case
+	 * just reschedule current.
+	 */
+	if (unlikely(next_task->prio < rq->curr->prio)) {
+		resched_curr(rq);
+		return 0;
+	}
+
 	if (is_migration_disabled(next_task)) {
 		struct task_struct *push_task = NULL;
 		int cpu;
@@ -2033,6 +2028,18 @@ retry:
 		if (!pull || rq->push_busy)
 			return 0;
 
+		/*
+		 * Invoking find_lowest_rq() on anything but an RT task doesn't
+		 * make sense. Per the above priority check, curr has to
+		 * be of higher priority than next_task, so no need to
+		 * reschedule when bailing out.
+		 *
+		 * Note that the stoppers are masqueraded as SCHED_FIFO
+		 * (cf. sched_set_stop_task()), so we can't rely on rt_task().
+		 */
+		if (rq->curr->sched_class != &rt_sched_class)
+			return 0;
+
 		cpu = find_lowest_rq(rq->curr);
 		if (cpu == -1 || cpu == rq->cpu)
 			return 0;
@@ -2057,16 +2064,6 @@ retry:
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
-	/*
-	 * It's possible that the next_task slipped in of
-	 * higher priority than current. If that's the case
-	 * just reschedule current.
-	 */
-	if (unlikely(next_task->prio < rq->curr->prio)) {
-		resched_curr(rq);
-		return 0;
-	}
-
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index de53be905739..58263f90c559 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,86 +2,98 @@
 /*
  * Scheduler internal types and methods:
  */
-#include <linux/sched.h>
+#ifndef _KERNEL_SCHED_SCHED_H
+#define _KERNEL_SCHED_SCHED_H
 
+#include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
-#include <linux/sched/clock.h>
-#include <linux/sched/coredump.h>
 #include <linux/sched/cpufreq.h>
-#include <linux/sched/cputime.h>
 #include <linux/sched/deadline.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/hotplug.h>
-#include <linux/sched/idle.h>
-#include <linux/sched/init.h>
-#include <linux/sched/isolation.h>
-#include <linux/sched/jobctl.h>
+#include <linux/sched.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
-#include <linux/sched/nohz.h>
-#include <linux/sched/numa_balancing.h>
-#include <linux/sched/prio.h>
-#include <linux/sched/rt.h>
+#include <linux/sched/rseq_api.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/smt.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/task_flags.h>
 #include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
 #include <linux/sched/topology.h>
-#include <linux/sched/user.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/xacct.h>
 
-#include <uapi/linux/sched/types.h>
-
-#include <linux/binfmts.h>
-#include <linux/bitops.h>
-#include <linux/compat.h>
-#include <linux/context_tracking.h>
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/bug.h>
+#include <linux/capability.h>
+#include <linux/cgroup_api.h>
+#include <linux/cgroup.h>
 #include <linux/cpufreq.h>
-#include <linux/cpuidle.h>
-#include <linux/cpuset.h>
+#include <linux/cpumask_api.h>
 #include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/delayacct.h>
-#include <linux/energy_model.h>
-#include <linux/init_task.h>
-#include <linux/kprobes.h>
+#include <linux/file.h>
+#include <linux/fs_api.h>
+#include <linux/hrtimer_api.h>
+#include <linux/interrupt.h>
+#include <linux/irq_work.h>
+#include <linux/jiffies.h>
+#include <linux/kref_api.h>
 #include <linux/kthread.h>
-#include <linux/membarrier.h>
-#include <linux/migrate.h>
-#include <linux/mmu_context.h>
-#include <linux/nmi.h>
+#include <linux/ktime_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/lockdep.h>
+#include <linux/minmax.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mutex_api.h>
+#include <linux/plist.h>
+#include <linux/poll.h>
 #include <linux/proc_fs.h>
-#include <linux/prefetch.h>
 #include <linux/profile.h>
 #include <linux/psi.h>
-#include <linux/ratelimit.h>
-#include <linux/rcupdate_wait.h>
-#include <linux/security.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/softirq.h>
+#include <linux/spinlock_api.h>
+#include <linux/static_key.h>
 #include <linux/stop_machine.h>
-#include <linux/suspend.h>
-#include <linux/swait.h>
+#include <linux/syscalls_api.h>
 #include <linux/syscalls.h>
-#include <linux/task_work.h>
-#include <linux/tsacct_kern.h>
+#include <linux/tick.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync_api.h>
+#include <linux/uaccess.h>
+#include <linux/wait_api.h>
+#include <linux/wait_bit.h>
+#include <linux/workqueue_api.h>
+
+#include <trace/events/power.h>
+#include <trace/events/sched.h>
+
+#include "../workqueue_internal.h"
+
+#ifdef CONFIG_CGROUP_SCHED
+#include <linux/cgroup.h>
+#include <linux/psi.h>
+#endif
 
-#include <asm/tlb.h>
+#ifdef CONFIG_SCHED_DEBUG
+# include <linux/static_key.h>
+#endif
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
+# include <asm/paravirt_api_clock.h>
 #endif
 
 #include "cpupri.h"
 #include "cpudeadline.h"
 
-#include <trace/events/sched.h>
-
 #ifdef CONFIG_SCHED_DEBUG
-# define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x)      WARN_ONCE(x, #x)
 #else
-# define SCHED_WARN_ON(x)	({ (void)(x), 0; })
+# define SCHED_WARN_ON(x)      ({ (void)(x), 0; })
 #endif
 
 struct rq;
@@ -301,29 +313,6 @@ struct dl_bw {
 	u64			total_bw;
 };
 
-static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
-
-static inline
-void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
-	dl_b->total_bw -= tsk_bw;
-	__dl_update(dl_b, (s32)tsk_bw / cpus);
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
-	dl_b->total_bw += tsk_bw;
-	__dl_update(dl_b, -((s32)tsk_bw / cpus));
-}
-
-static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap,
-				 u64 old_bw, u64 new_bw)
-{
-	return dl_b->bw != -1 &&
-	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
-}
-
 /*
  * Verify the fitness of task @p to run on @cpu taking into account the
  * CPU original capacity and the runtime/deadline ratio of the task.
@@ -347,15 +336,11 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
 extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
-extern int  dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern bool dl_cpu_busy(unsigned int cpu);
+extern int  dl_cpu_busy(int cpu, struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_SCHED
 
-#include <linux/cgroup.h>
-#include <linux/psi.h>
-
 struct cfs_rq;
 struct rt_rq;
 
@@ -1662,12 +1647,14 @@ enum numa_topology_type {
 extern enum numa_topology_type sched_numa_topology_type;
 extern int sched_max_numa_distance;
 extern bool find_numa_distance(int distance);
-extern void sched_init_numa(void);
+extern void sched_init_numa(int offline_node);
+extern void sched_update_numa(int cpu, bool online);
 extern void sched_domains_numa_masks_set(unsigned int cpu);
 extern void sched_domains_numa_masks_clear(unsigned int cpu);
 extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
 #else
-static inline void sched_init_numa(void) { }
+static inline void sched_init_numa(int offline_node) { }
+static inline void sched_update_numa(int cpu, bool online) { }
 static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
 static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
 static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
@@ -1854,7 +1841,6 @@ static inline void flush_smp_call_function_from_idle(void) { }
 #endif
 
 #include "stats.h"
-#include "autogroup.h"
 
 #if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS)
 
@@ -1950,7 +1936,6 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
 #ifdef CONFIG_SCHED_DEBUG
-# include <linux/static_key.h>
 # define const_debug __read_mostly
 #else
 # define const_debug const
@@ -2331,7 +2316,6 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
-extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
@@ -2747,32 +2731,6 @@ extern void nohz_run_idle_balance(int cpu);
 static inline void nohz_run_idle_balance(int cpu) { }
 #endif
 
-#ifdef CONFIG_SMP
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
-	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
-	int i;
-
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	for_each_cpu_and(i, rd->span, cpu_active_mask) {
-		struct rq *rq = cpu_rq(i);
-
-		rq->dl.extra_bw += bw;
-	}
-}
-#else
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
-	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
-
-	dl->extra_bw += bw;
-}
-#endif
-
-
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
 	u64			total;
@@ -2841,88 +2799,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
 static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
-#ifdef CONFIG_UCLAMP_TASK
-unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
-
-/**
- * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
- * @rq:		The rq to clamp against. Must not be NULL.
- * @util:	The util value to clamp.
- * @p:		The task to clamp against. Can be NULL if you want to clamp
- *		against @rq only.
- *
- * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
- *
- * If sched_uclamp_used static key is disabled, then just return the util
- * without any clamping since uclamp aggregation at the rq level in the fast
- * path is disabled, rendering this operation a NOP.
- *
- * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
- * will return the correct effective uclamp value of the task even if the
- * static key is disabled.
- */
-static __always_inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	unsigned long min_util = 0;
-	unsigned long max_util = 0;
-
-	if (!static_branch_likely(&sched_uclamp_used))
-		return util;
-
-	if (p) {
-		min_util = uclamp_eff_value(p, UCLAMP_MIN);
-		max_util = uclamp_eff_value(p, UCLAMP_MAX);
-
-		/*
-		 * Ignore last runnable task's max clamp, as this task will
-		 * reset it. Similarly, no need to read the rq's min clamp.
-		 */
-		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
-			goto out;
-	}
-
-	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
-	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
-out:
-	/*
-	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
-	 * RUNNABLE tasks with _different_ clamps, we can end up with an
-	 * inversion. Fix it now when the clamps are applied.
-	 */
-	if (unlikely(min_util >= max_util))
-		return min_util;
-
-	return clamp(util, min_util, max_util);
-}
-
-/*
- * When uclamp is compiled in, the aggregation at rq level is 'turned off'
- * by default in the fast path and only gets turned on once userspace performs
- * an operation that requires it.
- *
- * Returns true if userspace opted-in to use uclamp and aggregation at rq level
- * hence is active.
- */
-static inline bool uclamp_is_used(void)
-{
-	return static_branch_likely(&sched_uclamp_used);
-}
-#else /* CONFIG_UCLAMP_TASK */
-static inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	return util;
-}
-
-static inline bool uclamp_is_used(void)
-{
-	return false;
-}
-#endif /* CONFIG_UCLAMP_TASK */
-
 #ifdef arch_scale_freq_capacity
 # ifndef arch_scale_freq_invariant
 #  define arch_scale_freq_invariant()	true
@@ -3020,6 +2896,105 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 }
 #endif
 
+#ifdef CONFIG_UCLAMP_TASK
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq:		The rq to clamp against. Must not be NULL.
+ * @util:	The util value to clamp.
+ * @p:		The task to clamp against. Can be NULL if you want to clamp
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
+static __always_inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
+{
+	unsigned long min_util = 0;
+	unsigned long max_util = 0;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return util;
+
+	if (p) {
+		min_util = uclamp_eff_value(p, UCLAMP_MIN);
+		max_util = uclamp_eff_value(p, UCLAMP_MAX);
+
+		/*
+		 * Ignore last runnable task's max clamp, as this task will
+		 * reset it. Similarly, no need to read the rq's min clamp.
+		 */
+		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+			goto out;
+	}
+
+	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
+	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+out:
+	/*
+	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
+	 * RUNNABLE tasks with _different_ clamps, we can end up with an
+	 * inversion. Fix it now when the clamps are applied.
+	 */
+	if (unlikely(min_util >= max_util))
+		return min_util;
+
+	return clamp(util, min_util, max_util);
+}
+
+/* Is the rq being capped/throttled by uclamp_max? */
+static inline bool uclamp_rq_is_capped(struct rq *rq)
+{
+	unsigned long rq_util;
+	unsigned long max_util;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return false;
+
+	rq_util = cpu_util_cfs(cpu_of(rq)) + cpu_util_rt(rq);
+	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+
+	return max_util != SCHED_CAPACITY_SCALE && rq_util >= max_util;
+}
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	return static_branch_likely(&sched_uclamp_used);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
+{
+	return util;
+}
+
+static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
+#endif /* CONFIG_UCLAMP_TASK */
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
@@ -3118,3 +3093,4 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
+#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 07dde2928c79..857f837f52cb 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -2,7 +2,6 @@
 /*
  * /proc/schedstat implementation
  */
-#include "sched.h"
 
 void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
 			       struct sched_statistics *stats)
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 3a3c826dd83a..baa839c1ba96 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -1,4 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _KERNEL_STATS_H
+#define _KERNEL_STATS_H
 
 #ifdef CONFIG_SCHEDSTATS
 
@@ -298,3 +300,5 @@ sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *n
 # define sched_info_dequeue(rq, t)	do { } while (0)
 # define sched_info_switch(rq, t, next)	do { } while (0)
 #endif /* CONFIG_SCHED_INFO */
+
+#endif /* _KERNEL_STATS_H */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 0b165a25f22f..d04073a93eb4 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -7,7 +7,6 @@
  *
  * See kernel/stop_machine.c
  */
-#include "sched.h"
 
 #ifdef CONFIG_SMP
 static int
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index e1c655f928c7..76b9b796e695 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -2,7 +2,6 @@
 /*
  * <linux/swait.h> (simple wait queues ) implementation:
  */
-#include "sched.h"
 
 void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
 			     struct lock_class_key *key)
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d201a7052a29..810750e62118 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2,7 +2,6 @@
 /*
  * Scheduler topology setup/handling methods
  */
-#include "sched.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
 
@@ -74,7 +73,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!cpumask_weight(sched_group_span(group))) {
+		if (cpumask_empty(sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
@@ -1366,7 +1365,7 @@ static void asym_cpu_capacity_scan(void)
 	list_for_each_entry(entry, &asym_cap_list, link)
 		cpumask_clear(cpu_capacity_span(entry));
 
-	for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_FLAG_DOMAIN))
+	for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN))
 		asym_cpu_capacity_update_data(cpu);
 
 	list_for_each_entry_safe(entry, next, &asym_cap_list, link) {
@@ -1492,8 +1491,6 @@ static int			sched_domains_curr_level;
 int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
 static struct cpumask		***sched_domains_numa_masks;
-
-static unsigned long __read_mostly *sched_numa_onlined_nodes;
 #endif
 
 /*
@@ -1651,6 +1648,7 @@ static struct sched_domain_topology_level default_topology[] = {
 
 static struct sched_domain_topology_level *sched_domain_topology =
 	default_topology;
+static struct sched_domain_topology_level *sched_domain_topology_saved;
 
 #define for_each_sd_topology(tl)			\
 	for (tl = sched_domain_topology; tl->mask; tl++)
@@ -1661,6 +1659,7 @@ void set_sched_topology(struct sched_domain_topology_level *tl)
 		return;
 
 	sched_domain_topology = tl;
+	sched_domain_topology_saved = NULL;
 }
 
 #ifdef CONFIG_NUMA
@@ -1684,8 +1683,12 @@ static void sched_numa_warn(const char *str)
 
 	for (i = 0; i < nr_node_ids; i++) {
 		printk(KERN_WARNING "  ");
-		for (j = 0; j < nr_node_ids; j++)
-			printk(KERN_CONT "%02d ", node_distance(i,j));
+		for (j = 0; j < nr_node_ids; j++) {
+			if (!node_state(i, N_CPU) || !node_state(j, N_CPU))
+				printk(KERN_CONT "(%02d) ", node_distance(i,j));
+			else
+				printk(KERN_CONT " %02d  ", node_distance(i,j));
+		}
 		printk(KERN_CONT "\n");
 	}
 	printk(KERN_WARNING "\n");
@@ -1693,19 +1696,34 @@ static void sched_numa_warn(const char *str)
 
 bool find_numa_distance(int distance)
 {
-	int i;
+	bool found = false;
+	int i, *distances;
 
 	if (distance == node_distance(0, 0))
 		return true;
 
+	rcu_read_lock();
+	distances = rcu_dereference(sched_domains_numa_distance);
+	if (!distances)
+		goto unlock;
 	for (i = 0; i < sched_domains_numa_levels; i++) {
-		if (sched_domains_numa_distance[i] == distance)
-			return true;
+		if (distances[i] == distance) {
+			found = true;
+			break;
+		}
 	}
+unlock:
+	rcu_read_unlock();
 
-	return false;
+	return found;
 }
 
+#define for_each_cpu_node_but(n, nbut)		\
+	for_each_node_state(n, N_CPU)		\
+		if (n == nbut)			\
+			continue;		\
+		else
+
 /*
  * A system can have three types of NUMA topology:
  * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
@@ -1725,7 +1743,7 @@ bool find_numa_distance(int distance)
  *   there is an intermediary node C, which is < N hops away from both
  *   nodes A and B, the system is a glueless mesh.
  */
-static void init_numa_topology_type(void)
+static void init_numa_topology_type(int offline_node)
 {
 	int a, b, c, n;
 
@@ -1736,14 +1754,14 @@ static void init_numa_topology_type(void)
 		return;
 	}
 
-	for_each_online_node(a) {
-		for_each_online_node(b) {
+	for_each_cpu_node_but(a, offline_node) {
+		for_each_cpu_node_but(b, offline_node) {
 			/* Find two nodes furthest removed from each other. */
 			if (node_distance(a, b) < n)
 				continue;
 
 			/* Is there an intermediary node between a and b? */
-			for_each_online_node(c) {
+			for_each_cpu_node_but(c, offline_node) {
 				if (node_distance(a, c) < n &&
 				    node_distance(b, c) < n) {
 					sched_numa_topology_type =
@@ -1756,17 +1774,22 @@ static void init_numa_topology_type(void)
 			return;
 		}
 	}
+
+	pr_err("Failed to find a NUMA topology type, defaulting to DIRECT\n");
+	sched_numa_topology_type = NUMA_DIRECT;
 }
 
 
 #define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
 
-void sched_init_numa(void)
+void sched_init_numa(int offline_node)
 {
 	struct sched_domain_topology_level *tl;
 	unsigned long *distance_map;
 	int nr_levels = 0;
 	int i, j;
+	int *distances;
+	struct cpumask ***masks;
 
 	/*
 	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
@@ -1777,12 +1800,13 @@ void sched_init_numa(void)
 		return;
 
 	bitmap_zero(distance_map, NR_DISTANCE_VALUES);
-	for (i = 0; i < nr_node_ids; i++) {
-		for (j = 0; j < nr_node_ids; j++) {
+	for_each_cpu_node_but(i, offline_node) {
+		for_each_cpu_node_but(j, offline_node) {
 			int distance = node_distance(i, j);
 
 			if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
 				sched_numa_warn("Invalid distance value range");
+				bitmap_free(distance_map);
 				return;
 			}
 
@@ -1795,16 +1819,17 @@ void sched_init_numa(void)
 	 */
 	nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES);
 
-	sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
-	if (!sched_domains_numa_distance) {
+	distances = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
+	if (!distances) {
 		bitmap_free(distance_map);
 		return;
 	}
 
 	for (i = 0, j = 0; i < nr_levels; i++, j++) {
 		j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
-		sched_domains_numa_distance[i] = j;
+		distances[i] = j;
 	}
+	rcu_assign_pointer(sched_domains_numa_distance, distances);
 
 	bitmap_free(distance_map);
 
@@ -1826,8 +1851,8 @@ void sched_init_numa(void)
 	 */
 	sched_domains_numa_levels = 0;
 
-	sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
-	if (!sched_domains_numa_masks)
+	masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
+	if (!masks)
 		return;
 
 	/*
@@ -1835,31 +1860,20 @@ void sched_init_numa(void)
 	 * CPUs of nodes that are that many hops away from us.
 	 */
 	for (i = 0; i < nr_levels; i++) {
-		sched_domains_numa_masks[i] =
-			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
-		if (!sched_domains_numa_masks[i])
+		masks[i] = kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+		if (!masks[i])
 			return;
 
-		for (j = 0; j < nr_node_ids; j++) {
+		for_each_cpu_node_but(j, offline_node) {
 			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
 			int k;
 
 			if (!mask)
 				return;
 
-			sched_domains_numa_masks[i][j] = mask;
-
-			for_each_node(k) {
-				/*
-				 * Distance information can be unreliable for
-				 * offline nodes, defer building the node
-				 * masks to its bringup.
-				 * This relies on all unique distance values
-				 * still being visible at init time.
-				 */
-				if (!node_online(j))
-					continue;
+			masks[i][j] = mask;
 
+			for_each_cpu_node_but(k, offline_node) {
 				if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
 					sched_numa_warn("Node-distance not symmetric");
 
@@ -1870,6 +1884,7 @@ void sched_init_numa(void)
 			}
 		}
 	}
+	rcu_assign_pointer(sched_domains_numa_masks, masks);
 
 	/* Compute default topology size */
 	for (i = 0; sched_domain_topology[i].mask; i++);
@@ -1907,59 +1922,67 @@ void sched_init_numa(void)
 		};
 	}
 
+	sched_domain_topology_saved = sched_domain_topology;
 	sched_domain_topology = tl;
 
 	sched_domains_numa_levels = nr_levels;
-	sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
+	WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]);
 
-	init_numa_topology_type();
-
-	sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL);
-	if (!sched_numa_onlined_nodes)
-		return;
-
-	bitmap_zero(sched_numa_onlined_nodes, nr_node_ids);
-	for_each_online_node(i)
-		bitmap_set(sched_numa_onlined_nodes, i, 1);
+	init_numa_topology_type(offline_node);
 }
 
-static void __sched_domains_numa_masks_set(unsigned int node)
-{
-	int i, j;
-
-	/*
-	 * NUMA masks are not built for offline nodes in sched_init_numa().
-	 * Thus, when a CPU of a never-onlined-before node gets plugged in,
-	 * adding that new CPU to the right NUMA masks is not sufficient: the
-	 * masks of that CPU's node must also be updated.
-	 */
-	if (test_bit(node, sched_numa_onlined_nodes))
-		return;
 
-	bitmap_set(sched_numa_onlined_nodes, node, 1);
-
-	for (i = 0; i < sched_domains_numa_levels; i++) {
-		for (j = 0; j < nr_node_ids; j++) {
-			if (!node_online(j) || node == j)
-				continue;
+static void sched_reset_numa(void)
+{
+	int nr_levels, *distances;
+	struct cpumask ***masks;
 
-			if (node_distance(j, node) > sched_domains_numa_distance[i])
+	nr_levels = sched_domains_numa_levels;
+	sched_domains_numa_levels = 0;
+	sched_max_numa_distance = 0;
+	sched_numa_topology_type = NUMA_DIRECT;
+	distances = sched_domains_numa_distance;
+	rcu_assign_pointer(sched_domains_numa_distance, NULL);
+	masks = sched_domains_numa_masks;
+	rcu_assign_pointer(sched_domains_numa_masks, NULL);
+	if (distances || masks) {
+		int i, j;
+
+		synchronize_rcu();
+		kfree(distances);
+		for (i = 0; i < nr_levels && masks; i++) {
+			if (!masks[i])
 				continue;
-
-			/* Add remote nodes in our masks */
-			cpumask_or(sched_domains_numa_masks[i][node],
-				   sched_domains_numa_masks[i][node],
-				   sched_domains_numa_masks[0][j]);
+			for_each_node(j)
+				kfree(masks[i][j]);
+			kfree(masks[i]);
 		}
+		kfree(masks);
+	}
+	if (sched_domain_topology_saved) {
+		kfree(sched_domain_topology);
+		sched_domain_topology = sched_domain_topology_saved;
+		sched_domain_topology_saved = NULL;
 	}
+}
 
+/*
+ * Call with hotplug lock held
+ */
+void sched_update_numa(int cpu, bool online)
+{
+	int node;
+
+	node = cpu_to_node(cpu);
 	/*
-	 * A new node has been brought up, potentially changing the topology
-	 * classification.
-	 *
-	 * Note that this is racy vs any use of sched_numa_topology_type :/
+	 * Scheduler NUMA topology is updated when the first CPU of a
+	 * node is onlined or the last CPU of a node is offlined.
 	 */
-	init_numa_topology_type();
+	if (cpumask_weight(cpumask_of_node(node)) != 1)
+		return;
+
+	sched_reset_numa();
+	sched_init_numa(online ? NUMA_NO_NODE : node);
 }
 
 void sched_domains_numa_masks_set(unsigned int cpu)
@@ -1967,11 +1990,9 @@ void sched_domains_numa_masks_set(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	int i, j;
 
-	__sched_domains_numa_masks_set(node);
-
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		for (j = 0; j < nr_node_ids; j++) {
-			if (!node_online(j))
+			if (!node_state(j, N_CPU))
 				continue;
 
 			/* Set ourselves in the remote node's masks */
@@ -1986,8 +2007,10 @@ void sched_domains_numa_masks_clear(unsigned int cpu)
 	int i, j;
 
 	for (i = 0; i < sched_domains_numa_levels; i++) {
-		for (j = 0; j < nr_node_ids; j++)
-			cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
+		for (j = 0; j < nr_node_ids; j++) {
+			if (sched_domains_numa_masks[i][j])
+				cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
+		}
 	}
 }
 
@@ -2001,14 +2024,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu)
  */
 int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
 {
-	int i, j = cpu_to_node(cpu);
+	int i, j = cpu_to_node(cpu), found = nr_cpu_ids;
+	struct cpumask ***masks;
 
+	rcu_read_lock();
+	masks = rcu_dereference(sched_domains_numa_masks);
+	if (!masks)
+		goto unlock;
 	for (i = 0; i < sched_domains_numa_levels; i++) {
-		cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]);
-		if (cpu < nr_cpu_ids)
-			return cpu;
+		if (!masks[i][j])
+			break;
+		cpu = cpumask_any_and(cpus, masks[i][j]);
+		if (cpu < nr_cpu_ids) {
+			found = cpu;
+			break;
+		}
 	}
-	return nr_cpu_ids;
+unlock:
+	rcu_read_unlock();
+
+	return found;
 }
 
 #endif /* CONFIG_NUMA */
@@ -2242,6 +2277,57 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		}
 	}
 
+	/*
+	 * Calculate an allowed NUMA imbalance such that LLCs do not get
+	 * imbalanced.
+	 */
+	for_each_cpu(i, cpu_map) {
+		unsigned int imb = 0;
+		unsigned int imb_span = 1;
+
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			struct sched_domain *child = sd->child;
+
+			if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child &&
+			    (child->flags & SD_SHARE_PKG_RESOURCES)) {
+				struct sched_domain __rcu *top_p;
+				unsigned int nr_llcs;
+
+				/*
+				 * For a single LLC per node, allow an
+				 * imbalance up to 25% of the node. This is an
+				 * arbitrary cutoff based on SMT-2 to balance
+				 * between memory bandwidth and avoiding
+				 * premature sharing of HT resources and SMT-4
+				 * or SMT-8 *may* benefit from a different
+				 * cutoff.
+				 *
+				 * For multiple LLCs, allow an imbalance
+				 * until multiple tasks would share an LLC
+				 * on one node while LLCs on another node
+				 * remain idle.
+				 */
+				nr_llcs = sd->span_weight / child->span_weight;
+				if (nr_llcs == 1)
+					imb = sd->span_weight >> 2;
+				else
+					imb = nr_llcs;
+				sd->imb_numa_nr = imb;
+
+				/* Set span based on the first NUMA domain. */
+				top_p = sd->parent;
+				while (top_p && !(top_p->flags & SD_NUMA)) {
+					top_p = top_p->parent;
+				}
+				imb_span = top_p ? top_p->span_weight : sd->span_weight;
+			} else {
+				int factor = max(1U, (sd->span_weight / imb_span));
+
+				sd->imb_numa_nr = imb * factor;
+			}
+		}
+	}
+
 	/* Calculate CPU capacity for physical packages and nodes */
 	for (i = nr_cpumask_bits-1; i >= 0; i--) {
 		if (!cpumask_test_cpu(i, cpu_map))
@@ -2351,7 +2437,7 @@ int sched_init_domains(const struct cpumask *cpu_map)
 	doms_cur = alloc_sched_domains(ndoms_cur);
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
-	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN));
+	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_TYPE_DOMAIN));
 	err = build_sched_domains(doms_cur[0], NULL);
 
 	return err;
@@ -2440,7 +2526,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 		if (doms_new) {
 			n = 1;
 			cpumask_and(doms_new[0], cpu_active_mask,
-				    housekeeping_cpumask(HK_FLAG_DOMAIN));
+				    housekeeping_cpumask(HK_TYPE_DOMAIN));
 		}
 	} else {
 		n = ndoms_new;
@@ -2475,7 +2561,7 @@ match1:
 		n = 0;
 		doms_new = &fallback_doms;
 		cpumask_and(doms_new[0], cpu_active_mask,
-			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
 	}
 
 	/* Build new domains: */
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index eca38107b32f..9860bb9a847c 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -4,7 +4,6 @@
  *
  * (C) 2004 Nadia Yvette Chambers, Oracle
  */
-#include "sched.h"
 
 void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index 02ce292b9bc0..d4788f810b55 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
+
 /*
  * The implementation of the wait_bit*() and related waiting APIs:
  */
-#include "sched.h"
 
 #define WAIT_TABLE_BITS 8
 #define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
author	Linus Torvalds	2022-03-22 14:39:12 -0700
committer	Linus Torvalds	2022-03-22 14:39:12 -0700
commit	3fe2f7446f1e029b220f7f650df6d138f91651f2 (patch)
tree	bc6f9adc91f9e4fd4d78f49f1188388ebfa90bcb /kernel/sched
parent	ebd326ce724d5b2e5274724e6d6a46a046e28203 (diff)
parent	ffea9fb319360b9ead8befac6bb2db2b54fd53e6 (diff)