Merge tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - Revert the printk format based wchan() symbol resolution as it can
   leak the raw value in case that the symbol is not resolvable.

 - Make wchan() more robust and work with all kind of unwinders by
   enforcing that the task stays blocked while unwinding is in progress.

 - Prevent sched_fork() from accessing an invalid sched_task_group

 - Improve asymmetric packing logic

 - Extend scheduler statistics to RT and DL scheduling classes and add
   statistics for bandwith burst to the SCHED_FAIR class.

 - Properly account SCHED_IDLE entities

 - Prevent a potential deadlock when initial priority is assigned to a
   newly created kthread. A recent change to plug a race between cpuset
   and __sched_setscheduler() introduced a new lock dependency which is
   now triggered. Break the lock dependency chain by moving the priority
   assignment to the thread function.

 - Fix the idle time reporting in /proc/uptime for NOHZ enabled systems.

 - Improve idle balancing in general and especially for NOHZ enabled
   systems.

 - Provide proper interfaces for live patching so it does not have to
   fiddle with scheduler internals.

 - Add cluster aware scheduling support.

 - A small set of tweaks for RT (irqwork, wait_task_inactive(), various
   scheduler options and delaying mmdrop)

 - The usual small tweaks and improvements all over the place

* tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  sched/fair: Cleanup newidle_balance
  sched/fair: Remove sysctl_sched_migration_cost condition
  sched/fair: Wait before decaying max_newidle_lb_cost
  sched/fair: Skip update_blocked_averages if we are defering load balance
  sched/fair: Account update_blocked_averages in newidle_balance cost
  x86: Fix __get_wchan() for !STACKTRACE
  sched,x86: Fix L2 cache mask
  sched/core: Remove rq_relock()
  sched: Improve wake_up_all_idle_cpus() take #2
  irq_work: Also rcuwait for !IRQ_WORK_HARD_IRQ on PREEMPT_RT
  irq_work: Handle some irq_work in a per-CPU thread on PREEMPT_RT
  irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support.
  sched/rt: Annotate the RT balancing logic irqwork as IRQ_WORK_HARD_IRQ
  sched: Add cluster scheduler level for x86
  sched: Add cluster scheduler level in core and related Kconfig for ARM64
  topology: Represent clusters of CPUs within a die
  sched: Disable -Wunused-but-set-variable
  sched: Add wrapper for get_wchan() to keep task blocked
  x86: Fix get_wchan() to support the ORC unwinder
  proc: Use task_is_running() for wchan in /proc/$pid/stat
  ...

23 files changed, 1199 insertions, 577 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 5876e30c5740..60f1bfc3c7b2 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -2,10 +2,11 @@
 
 choice
 	prompt "Preemption Model"
-	default PREEMPT_NONE
+	default PREEMPT_NONE_BEHAVIOUR
 
-config PREEMPT_NONE
+config PREEMPT_NONE_BEHAVIOUR
 	bool "No Forced Preemption (Server)"
+	select PREEMPT_NONE if !PREEMPT_DYNAMIC
 	help
 	  This is the traditional Linux preemption model, geared towards
 	  throughput. It will still provide good latencies most of the
@@ -17,9 +18,10 @@ config PREEMPT_NONE
 	  raw processing power of the kernel, irrespective of scheduling
 	  latencies.
 
-config PREEMPT_VOLUNTARY
+config PREEMPT_VOLUNTARY_BEHAVIOUR
 	bool "Voluntary Kernel Preemption (Desktop)"
 	depends on !ARCH_NO_PREEMPT
+	select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC
 	help
 	  This option reduces the latency of the kernel by adding more
 	  "explicit preemption points" to the kernel code. These new
@@ -35,12 +37,10 @@ config PREEMPT_VOLUNTARY
 
 	  Select this if you are building a kernel for a desktop system.
 
-config PREEMPT
+config PREEMPT_BEHAVIOUR
 	bool "Preemptible Kernel (Low-Latency Desktop)"
 	depends on !ARCH_NO_PREEMPT
-	select PREEMPTION
-	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
-	select PREEMPT_DYNAMIC if HAVE_PREEMPT_DYNAMIC
+	select PREEMPT
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
@@ -58,7 +58,7 @@ config PREEMPT
 
 config PREEMPT_RT
 	bool "Fully Preemptible Kernel (Real-Time)"
-	depends on EXPERT && ARCH_SUPPORTS_RT
+	depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC
 	select PREEMPTION
 	help
 	  This option turns the kernel into a real-time kernel by replacing
@@ -75,6 +75,17 @@ config PREEMPT_RT
 
 endchoice
 
+config PREEMPT_NONE
+	bool
+
+config PREEMPT_VOLUNTARY
+	bool
+
+config PREEMPT
+	bool
+	select PREEMPTION
+	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
+
 config PREEMPT_COUNT
        bool
 
@@ -83,7 +94,10 @@ config PREEMPTION
        select PREEMPT_COUNT
 
 config PREEMPT_DYNAMIC
-	bool
+	bool "Preemption behaviour defined on boot"
+	depends on HAVE_PREEMPT_DYNAMIC
+	select PREEMPT
+	default y
 	help
 	  This option allows to define the preemption model on the kernel
 	  command line parameter and thus override the default preemption
diff --git a/kernel/exit.c b/kernel/exit.c
index a53863dafb3d..50f1692c732d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -63,6 +63,7 @@
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
 #include <linux/io_uring.h>
+#include <linux/kprobes.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -167,6 +168,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
+	kprobe_flush_task(tsk);
 	perf_event_delayed_put(tsk);
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 67679e3933f2..8e9feeef555e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2404,7 +2404,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	sched_post_fork(p);
+	sched_post_fork(p, args);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index db8c248ebc8c..f7df715ec28e 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -18,11 +18,36 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/smpboot.h>
 #include <asm/processor.h>
 #include <linux/kasan.h>
 
 static DEFINE_PER_CPU(struct llist_head, raised_list);
 static DEFINE_PER_CPU(struct llist_head, lazy_list);
+static DEFINE_PER_CPU(struct task_struct *, irq_workd);
+
+static void wake_irq_workd(void)
+{
+	struct task_struct *tsk = __this_cpu_read(irq_workd);
+
+	if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk)
+		wake_up_process(tsk);
+}
+
+#ifdef CONFIG_SMP
+static void irq_work_wake(struct irq_work *entry)
+{
+	wake_irq_workd();
+}
+
+static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) =
+	IRQ_WORK_INIT_HARD(irq_work_wake);
+#endif
+
+static int irq_workd_should_run(unsigned int cpu)
+{
+	return !llist_empty(this_cpu_ptr(&lazy_list));
+}
 
 /*
  * Claim the entry so that no one else will poke at it.
@@ -52,15 +77,29 @@ void __weak arch_irq_work_raise(void)
 /* Enqueue on current CPU, work must already be claimed and preempt disabled */
 static void __irq_work_queue_local(struct irq_work *work)
 {
+	struct llist_head *list;
+	bool rt_lazy_work = false;
+	bool lazy_work = false;
+	int work_flags;
+
+	work_flags = atomic_read(&work->node.a_flags);
+	if (work_flags & IRQ_WORK_LAZY)
+		lazy_work = true;
+	else if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
+		 !(work_flags & IRQ_WORK_HARD_IRQ))
+		rt_lazy_work = true;
+
+	if (lazy_work || rt_lazy_work)
+		list = this_cpu_ptr(&lazy_list);
+	else
+		list = this_cpu_ptr(&raised_list);
+
+	if (!llist_add(&work->node.llist, list))
+		return;
+
 	/* If the work is "lazy", handle it from next tick if any */
-	if (atomic_read(&work->node.a_flags) & IRQ_WORK_LAZY) {
-		if (llist_add(&work->node.llist, this_cpu_ptr(&lazy_list)) &&
-		    tick_nohz_tick_stopped())
-			arch_irq_work_raise();
-	} else {
-		if (llist_add(&work->node.llist, this_cpu_ptr(&raised_list)))
-			arch_irq_work_raise();
-	}
+	if (!lazy_work || tick_nohz_tick_stopped())
+		arch_irq_work_raise();
 }
 
 /* Enqueue the irq work @work on the current CPU */
@@ -104,17 +143,34 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (cpu != smp_processor_id()) {
 		/* Arch remote IPI send/receive backend aren't NMI safe */
 		WARN_ON_ONCE(in_nmi());
+
+		/*
+		 * On PREEMPT_RT the items which are not marked as
+		 * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work
+		 * item is used on the remote CPU to wake the thread.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
+		    !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) {
+
+			if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu)))
+				goto out;
+
+			work = &per_cpu(irq_work_wakeup, cpu);
+			if (!irq_work_claim(work))
+				goto out;
+		}
+
 		__smp_call_single_queue(cpu, &work->node.llist);
 	} else {
 		__irq_work_queue_local(work);
 	}
+out:
 	preempt_enable();
 
 	return true;
 #endif /* CONFIG_SMP */
 }
 
-
 bool irq_work_needs_cpu(void)
 {
 	struct llist_head *raised, *lazy;
@@ -160,6 +216,10 @@ void irq_work_single(void *arg)
 	 * else claimed it meanwhile.
 	 */
 	(void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY);
+
+	if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
+	    !arch_irq_work_has_interrupt())
+		rcuwait_wake_up(&work->irqwait);
 }
 
 static void irq_work_run_list(struct llist_head *list)
@@ -167,7 +227,12 @@ static void irq_work_run_list(struct llist_head *list)
 	struct irq_work *work, *tmp;
 	struct llist_node *llnode;
 
-	BUG_ON(!irqs_disabled());
+	/*
+	 * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed
+	 * in a per-CPU thread in preemptible context. Only the items which are
+	 * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context.
+	 */
+	BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT));
 
 	if (llist_empty(list))
 		return;
@@ -184,7 +249,10 @@ static void irq_work_run_list(struct llist_head *list)
 void irq_work_run(void)
 {
 	irq_work_run_list(this_cpu_ptr(&raised_list));
-	irq_work_run_list(this_cpu_ptr(&lazy_list));
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
+	else
+		wake_irq_workd();
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -194,7 +262,11 @@ void irq_work_tick(void)
 
 	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
 		irq_work_run_list(raised);
-	irq_work_run_list(this_cpu_ptr(&lazy_list));
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
+	else
+		wake_irq_workd();
 }
 
 /*
@@ -204,8 +276,42 @@ void irq_work_tick(void)
 void irq_work_sync(struct irq_work *work)
 {
 	lockdep_assert_irqs_enabled();
+	might_sleep();
+
+	if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
+	    !arch_irq_work_has_interrupt()) {
+		rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work),
+				   TASK_UNINTERRUPTIBLE);
+		return;
+	}
 
 	while (irq_work_is_busy(work))
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
+
+static void run_irq_workd(unsigned int cpu)
+{
+	irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+static void irq_workd_setup(unsigned int cpu)
+{
+	sched_set_fifo_low(current);
+}
+
+static struct smp_hotplug_thread irqwork_threads = {
+	.store                  = &irq_workd,
+	.setup			= irq_workd_setup,
+	.thread_should_run      = irq_workd_should_run,
+	.thread_fn              = run_irq_workd,
+	.thread_comm            = "irq_work/%u",
+};
+
+static __init int irq_work_init_threads(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		BUG_ON(smpboot_register_percpu_thread(&irqwork_threads));
+	return 0;
+}
+early_initcall(irq_work_init_threads);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 790a573bbe00..9a38e7581a5c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1250,10 +1250,10 @@ void kprobe_busy_end(void)
 }
 
 /*
- * This function is called from finish_task_switch when task tk becomes dead,
- * so that we can recycle any function-return probe instances associated
- * with this task. These left over instances represent probed functions
- * that have been called but will never return.
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any function-return probe instances
+ * associated with this task. These left over instances represent probed
+ * functions that have been called but will never return.
  */
 void kprobe_flush_task(struct task_struct *tk)
 {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5b37a8567168..4a4d7092a2d8 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -270,6 +270,7 @@ EXPORT_SYMBOL_GPL(kthread_parkme);
 
 static int kthread(void *_create)
 {
+	static const struct sched_param param = { .sched_priority = 0 };
 	/* Copy data: it's on kthread's stack */
 	struct kthread_create_info *create = _create;
 	int (*threadfn)(void *data) = create->threadfn;
@@ -300,6 +301,13 @@ static int kthread(void *_create)
 	init_completion(&self->parked);
 	current->vfork_done = &self->exited;
 
+	/*
+	 * The new thread inherited kthreadd's priority and CPU mask. Reset
+	 * back to default in case they have been changed.
+	 */
+	sched_setscheduler_nocheck(current, SCHED_NORMAL, &param);
+	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD));
+
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
@@ -397,7 +405,6 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 	}
 	task = create->result;
 	if (!IS_ERR(task)) {
-		static const struct sched_param param = { .sched_priority = 0 };
 		char name[TASK_COMM_LEN];
 
 		/*
@@ -406,13 +413,6 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 		 */
 		vsnprintf(name, sizeof(name), namefmt, args);
 		set_task_comm(task, name);
-		/*
-		 * root may have changed our (kthreadd's) priority or CPU mask.
-		 * The kernel thread should not inherit these properties.
-		 */
-		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(task,
-				     housekeeping_cpumask(HK_FLAG_KTHREAD));
 	}
 	kfree(create);
 	return task;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 291b857a6e20..5683ac0d2566 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -13,7 +13,6 @@
 #include "core.h"
 #include "patch.h"
 #include "transition.h"
-#include "../sched/sched.h"
 
 #define MAX_STACK_ENTRIES  100
 #define STACK_ERR_BUF_SIZE 128
@@ -240,7 +239,7 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
  * Determine whether it's safe to transition the task to the target patch state
  * by looking for any to-be-patched or to-be-unpatched functions on its stack.
  */
-static int klp_check_stack(struct task_struct *task, char *err_buf)
+static int klp_check_stack(struct task_struct *task, const char **oldname)
 {
 	static unsigned long entries[MAX_STACK_ENTRIES];
 	struct klp_object *obj;
@@ -248,12 +247,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 	int ret, nr_entries;
 
 	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
-	if (ret < 0) {
-		snprintf(err_buf, STACK_ERR_BUF_SIZE,
-			 "%s: %s:%d has an unreliable stack\n",
-			 __func__, task->comm, task->pid);
-		return ret;
-	}
+	if (ret < 0)
+		return -EINVAL;
 	nr_entries = ret;
 
 	klp_for_each_object(klp_transition_patch, obj) {
@@ -262,11 +257,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 		klp_for_each_func(obj, func) {
 			ret = klp_check_stack_func(func, entries, nr_entries);
 			if (ret) {
-				snprintf(err_buf, STACK_ERR_BUF_SIZE,
-					 "%s: %s:%d is sleeping on function %s\n",
-					 __func__, task->comm, task->pid,
-					 func->old_name);
-				return ret;
+				*oldname = func->old_name;
+				return -EADDRINUSE;
 			}
 		}
 	}
@@ -274,6 +266,22 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 	return 0;
 }
 
+static int klp_check_and_switch_task(struct task_struct *task, void *arg)
+{
+	int ret;
+
+	if (task_curr(task) && task != current)
+		return -EBUSY;
+
+	ret = klp_check_stack(task, arg);
+	if (ret)
+		return ret;
+
+	clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	task->patch_state = klp_target_state;
+	return 0;
+}
+
 /*
  * Try to safely switch a task to the target patch state.  If it's currently
  * running, or it's sleeping on a to-be-patched or to-be-unpatched function, or
@@ -281,13 +289,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
  */
 static bool klp_try_switch_task(struct task_struct *task)
 {
-	static char err_buf[STACK_ERR_BUF_SIZE];
-	struct rq *rq;
-	struct rq_flags flags;
+	const char *old_name;
 	int ret;
-	bool success = false;
-
-	err_buf[0] = '\0';
 
 	/* check if this task has already switched over */
 	if (task->patch_state == klp_target_state)
@@ -305,36 +308,31 @@ static bool klp_try_switch_task(struct task_struct *task)
 	 * functions.  If all goes well, switch the task to the target patch
 	 * state.
 	 */
-	rq = task_rq_lock(task, &flags);
+	ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+	switch (ret) {
+	case 0:		/* success */
+		break;
 
-	if (task_running(rq, task) && task != current) {
-		snprintf(err_buf, STACK_ERR_BUF_SIZE,
-			 "%s: %s:%d is running\n", __func__, task->comm,
-			 task->pid);
-		goto done;
+	case -EBUSY:	/* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d is running\n",
+			 __func__, task->comm, task->pid);
+		break;
+	case -EINVAL:	/* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d has an unreliable stack\n",
+			 __func__, task->comm, task->pid);
+		break;
+	case -EADDRINUSE: /* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d is sleeping on function %s\n",
+			 __func__, task->comm, task->pid, old_name);
+		break;
+
+	default:
+		pr_debug("%s: Unknown error code (%d) when trying to switch %s:%d\n",
+			 __func__, ret, task->comm, task->pid);
+		break;
 	}
 
-	ret = klp_check_stack(task, err_buf);
-	if (ret)
-		goto done;
-
-	success = true;
-
-	clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
-	task->patch_state = klp_target_state;
-
-done:
-	task_rq_unlock(rq, task, &flags);
-
-	/*
-	 * Due to console deadlock issues, pr_debug() can't be used while
-	 * holding the task rq lock.  Instead we have to use a temporary buffer
-	 * and print the debug message after releasing the lock.
-	 */
-	if (err_buf[0] != '\0')
-		pr_debug("%s", err_buf);
-
-	return success;
+	return !ret;
 }
 
 /*
@@ -415,8 +413,11 @@ void klp_try_complete_transition(void)
 	for_each_possible_cpu(cpu) {
 		task = idle_task(cpu);
 		if (cpu_online(cpu)) {
-			if (!klp_try_switch_task(task))
+			if (!klp_try_switch_task(task)) {
 				complete = false;
+				/* Make idle task go through the main loop. */
+				wake_up_if_idle(cpu);
+			}
 		} else if (task->patch_state != klp_target_state) {
 			/* offline idle tasks can be switched immediately */
 			clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 806160c44b17..171bc848e8e3 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -928,7 +928,7 @@ reset_ipi:
 }
 
 /* Callback function for scheduler to check locked-down task.  */
-static bool trc_inspect_reader(struct task_struct *t, void *arg)
+static int trc_inspect_reader(struct task_struct *t, void *arg)
 {
 	int cpu = task_cpu(t);
 	bool in_qs = false;
@@ -939,7 +939,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 
 		// If no chance of heavyweight readers, do it the hard way.
 		if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-			return false;
+			return -EINVAL;
 
 		// If heavyweight readers are enabled on the remote task,
 		// we can inspect its state despite its currently running.
@@ -947,7 +947,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 		n_heavy_reader_attempts++;
 		if (!ofl && // Check for "running" idle tasks on offline CPUs.
 		    !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
-			return false; // No quiescent state, do it the hard way.
+			return -EINVAL; // No quiescent state, do it the hard way.
 		n_heavy_reader_updates++;
 		if (ofl)
 			n_heavy_reader_ofl_updates++;
@@ -962,7 +962,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 	t->trc_reader_checked = true;
 
 	if (in_qs)
-		return true;  // Already in quiescent state, done!!!
+		return 0;  // Already in quiescent state, done!!!
 
 	// The task is in a read-side critical section, so set up its
 	// state so that it will awaken the grace-period kthread upon exit
@@ -970,7 +970,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
 	WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
-	return true;
+	return 0;
 }
 
 /* Attempt to extract the state for the specified task. */
@@ -992,7 +992,7 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 
 	// Attempt to nail down the task for inspection.
 	get_task_struct(t);
-	if (try_invoke_on_locked_down_task(t, trc_inspect_reader, NULL)) {
+	if (!task_call_func(t, trc_inspect_reader, NULL)) {
 		put_task_struct(t);
 		return;
 	}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 677ee3d8671b..5e2fa6fd97f1 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -240,16 +240,16 @@ struct rcu_stall_chk_rdr {
  * Report out the state of a not-running task that is stalling the
  * current RCU grace period.
  */
-static bool check_slow_task(struct task_struct *t, void *arg)
+static int check_slow_task(struct task_struct *t, void *arg)
 {
 	struct rcu_stall_chk_rdr *rscrp = arg;
 
 	if (task_curr(t))
-		return false; // It is running, so decline to inspect it.
+		return -EBUSY; // It is running, so decline to inspect it.
 	rscrp->nesting = t->rcu_read_lock_nesting;
 	rscrp->rs = t->rcu_read_unlock_special;
 	rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
-	return true;
+	return 0;
 }
 
 /*
@@ -283,7 +283,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	while (i) {
 		t = ts[--i];
-		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
+		if (task_call_func(t, check_slow_task, &rscr))
 			pr_cont(" P%d", t->pid);
 		else
 			pr_cont(" P%d/%d:%c%c%c%c",
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 978fcfca5871..c7421f2d05e1 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -3,6 +3,10 @@ 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.
+ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
+
 # These files are disabled because they produce non-interesting flaky coverage
 # that is not a function of syscall inputs. E.g. involuntary context switches.
 KCOV_INSTRUMENT := n
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bc0e242e434c..523fd602ea90 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,7 +74,11 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
+#ifdef CONFIG_PREEMPT_RT
+const_debug unsigned int sysctl_sched_nr_migrate = 8;
+#else
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
+#endif
 
 /*
  * period over which we measure -rt task CPU usage in us.
@@ -1962,6 +1966,25 @@ bool sched_task_on_rq(struct task_struct *p)
 	return task_on_rq_queued(p);
 }
 
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long ip = 0;
+	unsigned int state;
+
+	if (!p || p == current)
+		return 0;
+
+	/* Only get wchan if task is blocked and we can keep it that way. */
+	raw_spin_lock_irq(&p->pi_lock);
+	state = READ_ONCE(p->__state);
+	smp_rmb(); /* see try_to_wake_up() */
+	if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
+		ip = __get_wchan(p);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	return ip;
+}
+
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (!(flags & ENQUEUE_NOCLOCK))
@@ -3251,7 +3274,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 			ktime_t to = NSEC_PER_SEC / HZ;
 
 			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
 			continue;
 		}
 
@@ -3489,11 +3512,11 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 #ifdef CONFIG_SMP
 	if (cpu == rq->cpu) {
 		__schedstat_inc(rq->ttwu_local);
-		__schedstat_inc(p->se.statistics.nr_wakeups_local);
+		__schedstat_inc(p->stats.nr_wakeups_local);
 	} else {
 		struct sched_domain *sd;
 
-		__schedstat_inc(p->se.statistics.nr_wakeups_remote);
+		__schedstat_inc(p->stats.nr_wakeups_remote);
 		rcu_read_lock();
 		for_each_domain(rq->cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
@@ -3505,14 +3528,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	}
 
 	if (wake_flags & WF_MIGRATED)
-		__schedstat_inc(p->se.statistics.nr_wakeups_migrate);
+		__schedstat_inc(p->stats.nr_wakeups_migrate);
 #endif /* CONFIG_SMP */
 
 	__schedstat_inc(rq->ttwu_count);
-	__schedstat_inc(p->se.statistics.nr_wakeups);
+	__schedstat_inc(p->stats.nr_wakeups);
 
 	if (wake_flags & WF_SYNC)
-		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
+		__schedstat_inc(p->stats.nr_wakeups_sync);
 }
 
 /*
@@ -3691,15 +3714,11 @@ void wake_up_if_idle(int cpu)
 	if (!is_idle_task(rcu_dereference(rq->curr)))
 		goto out;
 
-	if (set_nr_if_polling(rq->idle)) {
-		trace_sched_wake_idle_without_ipi(cpu);
-	} else {
-		rq_lock_irqsave(rq, &rf);
-		if (is_idle_task(rq->curr))
-			smp_send_reschedule(cpu);
-		/* Else CPU is not idle, do nothing here: */
-		rq_unlock_irqrestore(rq, &rf);
-	}
+	rq_lock_irqsave(rq, &rf);
+	if (is_idle_task(rq->curr))
+		resched_curr(rq);
+	/* Else CPU is not idle, do nothing here: */
+	rq_unlock_irqrestore(rq, &rf);
 
 out:
 	rcu_read_unlock();
@@ -4106,46 +4125,61 @@ out:
 }
 
 /**
- * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * task_call_func - Invoke a function on task in fixed state
  * @p: Process for which the function is to be invoked, can be @current.
  * @func: Function to invoke.
  * @arg: Argument to function.
  *
- * If the specified task can be quickly locked into a definite state
- * (either sleeping or on a given runqueue), arrange to keep it in that
- * state while invoking @func(@arg).  This function can use ->on_rq and
- * task_curr() to work out what the state is, if required.  Given that
- * @func can be invoked with a runqueue lock held, it had better be quite
- * lightweight.
+ * Fix the task in it's current state by avoiding wakeups and or rq operations
+ * and call @func(@arg) on it.  This function can use ->on_rq and task_curr()
+ * to work out what the state is, if required.  Given that @func can be invoked
+ * with a runqueue lock held, it had better be quite lightweight.
  *
  * Returns:
- *	@false if the task slipped out from under the locks.
- *	@true if the task was locked onto a runqueue or is sleeping.
- *		However, @func can override this by returning @false.
+ *   Whatever @func returns
  */
-bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 {
+	struct rq *rq = NULL;
+	unsigned int state;
 	struct rq_flags rf;
-	bool ret = false;
-	struct rq *rq;
+	int ret;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-	if (p->on_rq) {
+
+	state = READ_ONCE(p->__state);
+
+	/*
+	 * Ensure we load p->on_rq after p->__state, otherwise it would be
+	 * possible to, falsely, observe p->on_rq == 0.
+	 *
+	 * See try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+
+	/*
+	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
+	 * the task is blocked. Make sure to check @state since ttwu() can drop
+	 * locks at the end, see ttwu_queue_wakelist().
+	 */
+	if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq)
 		rq = __task_rq_lock(p, &rf);
-		if (task_rq(p) == rq)
-			ret = func(p, arg);
+
+	/*
+	 * At this point the task is pinned; either:
+	 *  - blocked and we're holding off wakeups	 (pi->lock)
+	 *  - woken, and we're holding off enqueue	 (rq->lock)
+	 *  - queued, and we're holding off schedule	 (rq->lock)
+	 *  - running, and we're holding off de-schedule (rq->lock)
+	 *
+	 * The called function (@func) can use: task_curr(), p->on_rq and
+	 * p->__state to differentiate between these states.
+	 */
+	ret = func(p, arg);
+
+	if (rq)
 		rq_unlock(rq, &rf);
-	} else {
-		switch (READ_ONCE(p->__state)) {
-		case TASK_RUNNING:
-		case TASK_WAKING:
-			break;
-		default:
-			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
-			if (!p->on_rq)
-				ret = func(p, arg);
-		}
-	}
+
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 	return ret;
 }
@@ -4196,7 +4230,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SCHEDSTATS
 	/* Even if schedstat is disabled, there should not be garbage */
-	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+	memset(&p->stats, 0, sizeof(p->stats));
 #endif
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
@@ -4328,8 +4362,6 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
  */
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
-	unsigned long flags;
-
 	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as NEW here. This guarantees that
@@ -4375,24 +4407,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	init_entity_runnable_average(&p->se);
 
-	/*
-	 * The child is not yet in the pid-hash so no cgroup attach races,
-	 * and the cgroup is pinned to this child due to cgroup_fork()
-	 * is ran before sched_fork().
-	 *
-	 * Silence PROVE_RCU.
-	 */
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	rseq_migrate(p);
-	/*
-	 * We're setting the CPU for the first time, we don't migrate,
-	 * so use __set_task_cpu().
-	 */
-	__set_task_cpu(p, smp_processor_id());
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-
 #ifdef CONFIG_SCHED_INFO
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
@@ -4408,8 +4422,29 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_post_fork(struct task_struct *p)
+void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
+	unsigned long flags;
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group *tg;
+#endif
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+#ifdef CONFIG_CGROUP_SCHED
+	tg = container_of(kargs->cset->subsys[cpu_cgrp_id],
+			  struct task_group, css);
+	p->sched_task_group = autogroup_task_group(p, tg);
+#endif
+	rseq_migrate(p);
+	/*
+	 * We're setting the CPU for the first time, we don't migrate,
+	 * so use __set_task_cpu().
+	 */
+	__set_task_cpu(p, smp_processor_id());
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
 	uclamp_post_fork(p);
 }
 
@@ -4836,18 +4871,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 */
 	if (mm) {
 		membarrier_mm_sync_core_before_usermode(mm);
-		mmdrop(mm);
+		mmdrop_sched(mm);
 	}
 	if (unlikely(prev_state == TASK_DEAD)) {
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
 
-		/*
-		 * Remove function-return probe instances associated with this
-		 * task and put them back on the free list.
-		 */
-		kprobe_flush_task(prev);
-
 		/* Task is done with its stack. */
 		put_task_stack(prev);
 
@@ -5580,8 +5609,7 @@ restart:
 			return p;
 	}
 
-	/* The idle class should always have a runnable task: */
-	BUG();
+	BUG(); /* The idle class should always have a runnable task. */
 }
 
 #ifdef CONFIG_SCHED_CORE
@@ -5603,54 +5631,18 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 	return a->core_cookie == b->core_cookie;
 }
 
-// XXX fairness/fwd progress conditions
-/*
- * Returns
- * - NULL if there is no runnable task for this class.
- * - the highest priority task for this runqueue if it matches
- *   rq->core->core_cookie or its priority is greater than max.
- * - Else returns idle_task.
- */
-static struct task_struct *
-pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max, bool in_fi)
+static inline struct task_struct *pick_task(struct rq *rq)
 {
-	struct task_struct *class_pick, *cookie_pick;
-	unsigned long cookie = rq->core->core_cookie;
-
-	class_pick = class->pick_task(rq);
-	if (!class_pick)
-		return NULL;
-
-	if (!cookie) {
-		/*
-		 * If class_pick is tagged, return it only if it has
-		 * higher priority than max.
-		 */
-		if (max && class_pick->core_cookie &&
-		    prio_less(class_pick, max, in_fi))
-			return idle_sched_class.pick_task(rq);
+	const struct sched_class *class;
+	struct task_struct *p;
 
-		return class_pick;
+	for_each_class(class) {
+		p = class->pick_task(rq);
+		if (p)
+			return p;
 	}
 
-	/*
-	 * If class_pick is idle or matches cookie, return early.
-	 */
-	if (cookie_equals(class_pick, cookie))
-		return class_pick;
-
-	cookie_pick = sched_core_find(rq, cookie);
-
-	/*
-	 * If class > max && class > cookie, it is the highest priority task on
-	 * the core (so far) and it must be selected, otherwise we must go with
-	 * the cookie pick in order to satisfy the constraint.
-	 */
-	if (prio_less(cookie_pick, class_pick, in_fi) &&
-	    (!max || prio_less(max, class_pick, in_fi)))
-		return class_pick;
-
-	return cookie_pick;
+	BUG(); /* The idle class should always have a runnable task. */
 }
 
 extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
@@ -5658,11 +5650,12 @@ extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_f
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *next, *max = NULL;
-	const struct sched_class *class;
+	struct task_struct *next, *p, *max = NULL;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
-	int i, j, cpu, occ = 0;
+	unsigned long cookie;
+	int i, cpu, occ = 0;
+	struct rq *rq_i;
 	bool need_sync;
 
 	if (!sched_core_enabled(rq))
@@ -5735,12 +5728,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * and there are no cookied tasks running on siblings.
 	 */
 	if (!need_sync) {
-		for_each_class(class) {
-			next = class->pick_task(rq);
-			if (next)
-				break;
-		}
-
+		next = pick_task(rq);
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
 			/*
@@ -5753,76 +5741,51 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 	}
 
-	for_each_cpu(i, smt_mask) {
-		struct rq *rq_i = cpu_rq(i);
-
-		rq_i->core_pick = NULL;
+	/*
+	 * For each thread: do the regular task pick and find the max prio task
+	 * amongst them.
+	 *
+	 * Tie-break prio towards the current CPU
+	 */
+	for_each_cpu_wrap(i, smt_mask, cpu) {
+		rq_i = cpu_rq(i);
 
 		if (i != cpu)
 			update_rq_clock(rq_i);
+
+		p = rq_i->core_pick = pick_task(rq_i);
+		if (!max || prio_less(max, p, fi_before))
+			max = p;
 	}
 
+	cookie = rq->core->core_cookie = max->core_cookie;
+
 	/*
-	 * Try and select tasks for each sibling in descending sched_class
-	 * order.
+	 * For each thread: try and find a runnable task that matches @max or
+	 * force idle.
 	 */
-	for_each_class(class) {
-again:
-		for_each_cpu_wrap(i, smt_mask, cpu) {
-			struct rq *rq_i = cpu_rq(i);
-			struct task_struct *p;
-
-			if (rq_i->core_pick)
-				continue;
+	for_each_cpu(i, smt_mask) {
+		rq_i = cpu_rq(i);
+		p = rq_i->core_pick;
 
-			/*
-			 * If this sibling doesn't yet have a suitable task to
-			 * run; ask for the most eligible task, given the
-			 * highest priority task already selected for this
-			 * core.
-			 */
-			p = pick_task(rq_i, class, max, fi_before);
+		if (!cookie_equals(p, cookie)) {
+			p = NULL;
+			if (cookie)
+				p = sched_core_find(rq_i, cookie);
 			if (!p)
-				continue;
+				p = idle_sched_class.pick_task(rq_i);
+		}
 
-			if (!is_task_rq_idle(p))
-				occ++;
+		rq_i->core_pick = p;
 
-			rq_i->core_pick = p;
-			if (rq_i->idle == p && rq_i->nr_running) {
+		if (p == rq_i->idle) {
+			if (rq_i->nr_running) {
 				rq->core->core_forceidle = true;
 				if (!fi_before)
 					rq->core->core_forceidle_seq++;
 			}
-
-			/*
-			 * If this new candidate is of higher priority than the
-			 * previous; and they're incompatible; we need to wipe
-			 * the slate and start over. pick_task makes sure that
-			 * p's priority is more than max if it doesn't match
-			 * max's cookie.
-			 *
-			 * NOTE: this is a linear max-filter and is thus bounded
-			 * in execution time.
-			 */
-			if (!max || !cookie_match(max, p)) {
-				struct task_struct *old_max = max;
-
-				rq->core->core_cookie = p->core_cookie;
-				max = p;
-
-				if (old_max) {
-					rq->core->core_forceidle = false;
-					for_each_cpu(j, smt_mask) {
-						if (j == i)
-							continue;
-
-						cpu_rq(j)->core_pick = NULL;
-					}
-					occ = 1;
-					goto again;
-				}
-			}
+		} else {
+			occ++;
 		}
 	}
 
@@ -5842,7 +5805,7 @@ again:
 	 * non-matching user state.
 	 */
 	for_each_cpu(i, smt_mask) {
-		struct rq *rq_i = cpu_rq(i);
+		rq_i = cpu_rq(i);
 
 		/*
 		 * An online sibling might have gone offline before a task
@@ -6319,20 +6282,14 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 	task_flags = tsk->flags;
 	/*
-	 * If a worker went to sleep, notify and ask workqueue whether
-	 * it wants to wake up a task to maintain concurrency.
-	 * As this function is called inside the schedule() context,
-	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
-	 * requires it.
+	 * If a worker goes to sleep, notify and ask workqueue whether it
+	 * wants to wake up a task to maintain concurrency.
 	 */
 	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
-		preempt_disable();
 		if (task_flags & PF_WQ_WORKER)
 			wq_worker_sleeping(tsk);
 		else
 			io_wq_worker_sleeping(tsk);
-		preempt_enable_no_resched();
 	}
 
 	if (tsk_is_pi_blocked(tsk))
@@ -6586,12 +6543,13 @@ EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
  */
 
 enum {
-	preempt_dynamic_none = 0,
+	preempt_dynamic_undefined = -1,
+	preempt_dynamic_none,
 	preempt_dynamic_voluntary,
 	preempt_dynamic_full,
 };
 
-int preempt_dynamic_mode = preempt_dynamic_full;
+int preempt_dynamic_mode = preempt_dynamic_undefined;
 
 int sched_dynamic_mode(const char *str)
 {
@@ -6664,7 +6622,27 @@ static int __init setup_preempt_mode(char *str)
 }
 __setup("preempt=", setup_preempt_mode);
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+static void __init preempt_dynamic_init(void)
+{
+	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
+		if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) {
+			sched_dynamic_update(preempt_dynamic_none);
+		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) {
+			sched_dynamic_update(preempt_dynamic_voluntary);
+		} else {
+			/* Default static call setting, nothing to do */
+			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR));
+			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 */
 
 /*
  * This is the entry point to schedule() from kernel preemption
@@ -9466,6 +9444,8 @@ void __init sched_init(void)
 
 	init_uclamp();
 
+	preempt_dynamic_init();
+
 	scheduler_running = 1;
 }
 
@@ -9640,9 +9620,9 @@ void normalize_rt_tasks(void)
 			continue;
 
 		p->se.exec_start = 0;
-		schedstat_set(p->se.statistics.wait_start,  0);
-		schedstat_set(p->se.statistics.sleep_start, 0);
-		schedstat_set(p->se.statistics.block_start, 0);
+		schedstat_set(p->stats.wait_start,  0);
+		schedstat_set(p->stats.sleep_start, 0);
+		schedstat_set(p->stats.block_start, 0);
 
 		if (!dl_task(p) && !rt_task(p)) {
 			/*
@@ -10484,15 +10464,21 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
 	if (schedstat_enabled() && tg != &root_task_group) {
+		struct sched_statistics *stats;
 		u64 ws = 0;
 		int i;
 
-		for_each_possible_cpu(i)
-			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+		for_each_possible_cpu(i) {
+			stats = __schedstats_from_se(tg->se[i]);
+			ws += schedstat_val(stats->wait_sum);
+		}
 
 		seq_printf(sf, "wait_sum %llu\n", ws);
 	}
 
+	seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst);
+	seq_printf(sf, "burst_time %llu\n", cfs_b->burst_time);
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
@@ -10608,16 +10594,20 @@ static int cpu_extra_stat_show(struct seq_file *sf,
 	{
 		struct task_group *tg = css_tg(css);
 		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
-		u64 throttled_usec;
+		u64 throttled_usec, burst_usec;
 
 		throttled_usec = cfs_b->throttled_time;
 		do_div(throttled_usec, NSEC_PER_USEC);
+		burst_usec = cfs_b->burst_time;
+		do_div(burst_usec, NSEC_PER_USEC);
 
 		seq_printf(sf, "nr_periods %d\n"
 			   "nr_throttled %d\n"
-			   "throttled_usec %llu\n",
+			   "throttled_usec %llu\n"
+			   "nr_bursts %d\n"
+			   "burst_usec %llu\n",
 			   cfs_b->nr_periods, cfs_b->nr_throttled,
-			   throttled_usec);
+			   throttled_usec, cfs_b->nr_burst, burst_usec);
 	}
 #endif
 	return 0;
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index 9a80e9a474c0..48ac72696012 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -11,7 +11,7 @@ struct sched_core_cookie {
 	refcount_t refcnt;
 };
 
-unsigned long sched_core_alloc_cookie(void)
+static unsigned long sched_core_alloc_cookie(void)
 {
 	struct sched_core_cookie *ck = kmalloc(sizeof(*ck), GFP_KERNEL);
 	if (!ck)
@@ -23,7 +23,7 @@ unsigned long sched_core_alloc_cookie(void)
 	return (unsigned long)ck;
 }
 
-void sched_core_put_cookie(unsigned long cookie)
+static void sched_core_put_cookie(unsigned long cookie)
 {
 	struct sched_core_cookie *ptr = (void *)cookie;
 
@@ -33,7 +33,7 @@ void sched_core_put_cookie(unsigned long cookie)
 	}
 }
 
-unsigned long sched_core_get_cookie(unsigned long cookie)
+static unsigned long sched_core_get_cookie(unsigned long cookie)
 {
 	struct sched_core_cookie *ptr = (void *)cookie;
 
@@ -53,7 +53,8 @@ unsigned long sched_core_get_cookie(unsigned long cookie)
  *
  * Returns: the old cookie
  */
-unsigned long sched_core_update_cookie(struct task_struct *p, unsigned long cookie)
+static unsigned long sched_core_update_cookie(struct task_struct *p,
+					      unsigned long cookie)
 {
 	unsigned long old_cookie;
 	struct rq_flags rf;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e94314633b39..d2c072b0ef01 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1265,8 +1265,10 @@ static void update_curr_dl(struct rq *rq)
 		return;
 	}
 
-	schedstat_set(curr->se.statistics.exec_max,
-		      max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->stats.exec_max,
+		      max(curr->stats.exec_max, delta_exec));
+
+	trace_sched_stat_runtime(curr, delta_exec, 0);
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
@@ -1472,6 +1474,82 @@ 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);
 }
 
+static inline struct sched_statistics *
+__schedstats_from_dl_se(struct sched_dl_entity *dl_se)
+{
+	return &dl_task_of(dl_se)->stats;
+}
+
+static inline void
+update_stats_wait_start_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+{
+	struct sched_statistics *stats;
+
+	if (!schedstat_enabled())
+		return;
+
+	stats = __schedstats_from_dl_se(dl_se);
+	__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+}
+
+static inline void
+update_stats_wait_end_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+{
+	struct sched_statistics *stats;
+
+	if (!schedstat_enabled())
+		return;
+
+	stats = __schedstats_from_dl_se(dl_se);
+	__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+}
+
+static inline void
+update_stats_enqueue_sleeper_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+{
+	struct sched_statistics *stats;
+
+	if (!schedstat_enabled())
+		return;
+
+	stats = __schedstats_from_dl_se(dl_se);
+	__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+}
+
+static inline void
+update_stats_enqueue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+			int flags)
+{
+	if (!schedstat_enabled())
+		return;
+
+	if (flags & ENQUEUE_WAKEUP)
+		update_stats_enqueue_sleeper_dl(dl_rq, dl_se);
+}
+
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+			int flags)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+
+	if (!schedstat_enabled())
+		return;
+
+	if ((flags & DEQUEUE_SLEEP)) {
+		unsigned int state;
+
+		state = READ_ONCE(p->__state);
+		if (state & TASK_INTERRUPTIBLE)
+			__schedstat_set(p->stats.sleep_start,
+					rq_clock(rq_of_dl_rq(dl_rq)));
+
+		if (state & TASK_UNINTERRUPTIBLE)
+			__schedstat_set(p->stats.block_start,
+					rq_clock(rq_of_dl_rq(dl_rq)));
+	}
+}
+
 static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
@@ -1502,6 +1580,8 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
 	BUG_ON(on_dl_rq(dl_se));
 
+	update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
+
 	/*
 	 * If this is a wakeup or a new instance, the scheduling
 	 * parameters of the task might need updating. Otherwise,
@@ -1598,6 +1678,9 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 	}
 
+	check_schedstat_required();
+	update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl);
+
 	enqueue_dl_entity(&p->dl, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
@@ -1606,6 +1689,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
+	update_stats_dequeue_dl(&rq->dl, &p->dl, flags);
 	dequeue_dl_entity(&p->dl);
 	dequeue_pushable_dl_task(rq, p);
 }
@@ -1825,7 +1909,12 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 
 static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 {
+	struct sched_dl_entity *dl_se = &p->dl;
+	struct dl_rq *dl_rq = &rq->dl;
+
 	p->se.exec_start = rq_clock_task(rq);
+	if (on_dl_rq(&p->dl))
+		update_stats_wait_end_dl(dl_rq, dl_se);
 
 	/* You can't push away the running task */
 	dequeue_pushable_dl_task(rq, p);
@@ -1882,6 +1971,12 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
+	struct sched_dl_entity *dl_se = &p->dl;
+	struct dl_rq *dl_rq = &rq->dl;
+
+	if (on_dl_rq(&p->dl))
+		update_stats_wait_start_dl(dl_rq, dl_se);
+
 	update_curr_dl(rq);
 
 	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 17a653b67006..7dcbaa31c5d9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -311,6 +311,7 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_u32("latency_ns", 0644, debugfs_sched, &sysctl_sched_latency);
 	debugfs_create_u32("min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_min_granularity);
+	debugfs_create_u32("idle_min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_idle_min_granularity);
 	debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity);
 
 	debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
@@ -448,9 +449,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	struct sched_entity *se = tg->se[cpu];
 
 #define P(F)		SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)F)
-#define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)schedstat_val(F))
+#define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	\
+		#F, (long long)schedstat_val(stats->F))
 #define PN(F)		SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define PN_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F)))
+#define PN_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", \
+		#F, SPLIT_NS((long long)schedstat_val(stats->F)))
 
 	if (!se)
 		return;
@@ -460,16 +463,19 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->sum_exec_runtime);
 
 	if (schedstat_enabled()) {
-		PN_SCHEDSTAT(se->statistics.wait_start);
-		PN_SCHEDSTAT(se->statistics.sleep_start);
-		PN_SCHEDSTAT(se->statistics.block_start);
-		PN_SCHEDSTAT(se->statistics.sleep_max);
-		PN_SCHEDSTAT(se->statistics.block_max);
-		PN_SCHEDSTAT(se->statistics.exec_max);
-		PN_SCHEDSTAT(se->statistics.slice_max);
-		PN_SCHEDSTAT(se->statistics.wait_max);
-		PN_SCHEDSTAT(se->statistics.wait_sum);
-		P_SCHEDSTAT(se->statistics.wait_count);
+		struct sched_statistics *stats;
+		stats = __schedstats_from_se(se);
+
+		PN_SCHEDSTAT(wait_start);
+		PN_SCHEDSTAT(sleep_start);
+		PN_SCHEDSTAT(block_start);
+		PN_SCHEDSTAT(sleep_max);
+		PN_SCHEDSTAT(block_max);
+		PN_SCHEDSTAT(exec_max);
+		PN_SCHEDSTAT(slice_max);
+		PN_SCHEDSTAT(wait_max);
+		PN_SCHEDSTAT(wait_sum);
+		P_SCHEDSTAT(wait_count);
 	}
 
 	P(se->load.weight);
@@ -535,10 +541,11 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
-	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)),
+	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
+		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime)));
+		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
+		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
@@ -614,6 +621,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
+			cfs_rq->idle_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_h_nr_running",
 			cfs_rq->idle_h_nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
@@ -810,6 +819,7 @@ static void sched_debug_header(struct seq_file *m)
 	SEQ_printf(m, "  .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
 	PN(sysctl_sched_latency);
 	PN(sysctl_sched_min_granularity);
+	PN(sysctl_sched_idle_min_granularity);
 	PN(sysctl_sched_wakeup_granularity);
 	P(sysctl_sched_child_runs_first);
 	P(sysctl_sched_features);
@@ -954,8 +964,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		"---------------------------------------------------------"
 		"----------\n");
 
-#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->F))
-#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F))
+#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->stats.F))
+#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->stats.F))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -968,33 +978,34 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
-		PN_SCHEDSTAT(se.statistics.sum_sleep_runtime);
-		PN_SCHEDSTAT(se.statistics.wait_start);
-		PN_SCHEDSTAT(se.statistics.sleep_start);
-		PN_SCHEDSTAT(se.statistics.block_start);
-		PN_SCHEDSTAT(se.statistics.sleep_max);
-		PN_SCHEDSTAT(se.statistics.block_max);
-		PN_SCHEDSTAT(se.statistics.exec_max);
-		PN_SCHEDSTAT(se.statistics.slice_max);
-		PN_SCHEDSTAT(se.statistics.wait_max);
-		PN_SCHEDSTAT(se.statistics.wait_sum);
-		P_SCHEDSTAT(se.statistics.wait_count);
-		PN_SCHEDSTAT(se.statistics.iowait_sum);
-		P_SCHEDSTAT(se.statistics.iowait_count);
-		P_SCHEDSTAT(se.statistics.nr_migrations_cold);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_running);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot);
-		P_SCHEDSTAT(se.statistics.nr_forced_migrations);
-		P_SCHEDSTAT(se.statistics.nr_wakeups);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_sync);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_migrate);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_local);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_remote);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_affine);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
+		PN_SCHEDSTAT(sum_sleep_runtime);
+		PN_SCHEDSTAT(sum_block_runtime);
+		PN_SCHEDSTAT(wait_start);
+		PN_SCHEDSTAT(sleep_start);
+		PN_SCHEDSTAT(block_start);
+		PN_SCHEDSTAT(sleep_max);
+		PN_SCHEDSTAT(block_max);
+		PN_SCHEDSTAT(exec_max);
+		PN_SCHEDSTAT(slice_max);
+		PN_SCHEDSTAT(wait_max);
+		PN_SCHEDSTAT(wait_sum);
+		P_SCHEDSTAT(wait_count);
+		PN_SCHEDSTAT(iowait_sum);
+		P_SCHEDSTAT(iowait_count);
+		P_SCHEDSTAT(nr_migrations_cold);
+		P_SCHEDSTAT(nr_failed_migrations_affine);
+		P_SCHEDSTAT(nr_failed_migrations_running);
+		P_SCHEDSTAT(nr_failed_migrations_hot);
+		P_SCHEDSTAT(nr_forced_migrations);
+		P_SCHEDSTAT(nr_wakeups);
+		P_SCHEDSTAT(nr_wakeups_sync);
+		P_SCHEDSTAT(nr_wakeups_migrate);
+		P_SCHEDSTAT(nr_wakeups_local);
+		P_SCHEDSTAT(nr_wakeups_remote);
+		P_SCHEDSTAT(nr_wakeups_affine);
+		P_SCHEDSTAT(nr_wakeups_affine_attempts);
+		P_SCHEDSTAT(nr_wakeups_passive);
+		P_SCHEDSTAT(nr_wakeups_idle);
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
@@ -1060,7 +1071,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+	memset(&p->stats, 0, sizeof(p->stats));
 #endif
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f6a05d9b5443..13950beb01a2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -60,6 +60,14 @@ unsigned int sysctl_sched_min_granularity			= 750000ULL;
 static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
 
 /*
+ * Minimal preemption granularity for CPU-bound SCHED_IDLE tasks.
+ * Applies only when SCHED_IDLE tasks compete with normal tasks.
+ *
+ * (default: 0.75 msec)
+ */
+unsigned int sysctl_sched_idle_min_granularity			= 750000ULL;
+
+/*
  * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
  */
 static unsigned int sched_nr_latency = 8;
@@ -665,6 +673,8 @@ static u64 __sched_period(unsigned long nr_running)
 		return sysctl_sched_latency;
 }
 
+static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq);
+
 /*
  * We calculate the wall-time slice from the period by taking a part
  * proportional to the weight.
@@ -674,6 +684,8 @@ static u64 __sched_period(unsigned long nr_running)
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned int nr_running = cfs_rq->nr_running;
+	struct sched_entity *init_se = se;
+	unsigned int min_gran;
 	u64 slice;
 
 	if (sched_feat(ALT_PERIOD))
@@ -684,12 +696,13 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	for_each_sched_entity(se) {
 		struct load_weight *load;
 		struct load_weight lw;
+		struct cfs_rq *qcfs_rq;
 
-		cfs_rq = cfs_rq_of(se);
-		load = &cfs_rq->load;
+		qcfs_rq = cfs_rq_of(se);
+		load = &qcfs_rq->load;
 
 		if (unlikely(!se->on_rq)) {
-			lw = cfs_rq->load;
+			lw = qcfs_rq->load;
 
 			update_load_add(&lw, se->load.weight);
 			load = &lw;
@@ -697,8 +710,14 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		slice = __calc_delta(slice, se->load.weight, load);
 	}
 
-	if (sched_feat(BASE_SLICE))
-		slice = max(slice, (u64)sysctl_sched_min_granularity);
+	if (sched_feat(BASE_SLICE)) {
+		if (se_is_idle(init_se) && !sched_idle_cfs_rq(cfs_rq))
+			min_gran = sysctl_sched_idle_min_granularity;
+		else
+			min_gran = sysctl_sched_min_granularity;
+
+		slice = max_t(u64, slice, min_gran);
+	}
 
 	return slice;
 }
@@ -837,8 +856,13 @@ static void update_curr(struct cfs_rq *cfs_rq)
 
 	curr->exec_start = now;
 
-	schedstat_set(curr->statistics.exec_max,
-		      max(delta_exec, curr->statistics.exec_max));
+	if (schedstat_enabled()) {
+		struct sched_statistics *stats;
+
+		stats = __schedstats_from_se(curr);
+		__schedstat_set(stats->exec_max,
+				max(delta_exec, stats->exec_max));
+	}
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
@@ -863,137 +887,70 @@ static void update_curr_fair(struct rq *rq)
 }
 
 static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_start_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 wait_start, prev_wait_start;
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
 
 	if (!schedstat_enabled())
 		return;
 
-	wait_start = rq_clock(rq_of(cfs_rq));
-	prev_wait_start = schedstat_val(se->statistics.wait_start);
+	stats = __schedstats_from_se(se);
 
-	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
-	    likely(wait_start > prev_wait_start))
-		wait_start -= prev_wait_start;
+	if (entity_is_task(se))
+		p = task_of(se);
 
-	__schedstat_set(se->statistics.wait_start, wait_start);
+	__update_stats_wait_start(rq_of(cfs_rq), p, stats);
 }
 
 static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	struct task_struct *p;
-	u64 delta;
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
 
 	if (!schedstat_enabled())
 		return;
 
+	stats = __schedstats_from_se(se);
+
 	/*
 	 * When the sched_schedstat changes from 0 to 1, some sched se
 	 * maybe already in the runqueue, the se->statistics.wait_start
 	 * will be 0.So it will let the delta wrong. We need to avoid this
 	 * scenario.
 	 */
-	if (unlikely(!schedstat_val(se->statistics.wait_start)))
+	if (unlikely(!schedstat_val(stats->wait_start)))
 		return;
 
-	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
-
-	if (entity_is_task(se)) {
+	if (entity_is_task(se))
 		p = task_of(se);
-		if (task_on_rq_migrating(p)) {
-			/*
-			 * Preserve migrating task's wait time so wait_start
-			 * time stamp can be adjusted to accumulate wait time
-			 * prior to migration.
-			 */
-			__schedstat_set(se->statistics.wait_start, delta);
-			return;
-		}
-		trace_sched_stat_wait(p, delta);
-	}
 
-	__schedstat_set(se->statistics.wait_max,
-		      max(schedstat_val(se->statistics.wait_max), delta));
-	__schedstat_inc(se->statistics.wait_count);
-	__schedstat_add(se->statistics.wait_sum, delta);
-	__schedstat_set(se->statistics.wait_start, 0);
+	__update_stats_wait_end(rq_of(cfs_rq), p, stats);
 }
 
 static inline void
-update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_enqueue_sleeper_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	struct sched_statistics *stats;
 	struct task_struct *tsk = NULL;
-	u64 sleep_start, block_start;
 
 	if (!schedstat_enabled())
 		return;
 
-	sleep_start = schedstat_val(se->statistics.sleep_start);
-	block_start = schedstat_val(se->statistics.block_start);
+	stats = __schedstats_from_se(se);
 
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (sleep_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(se->statistics.sleep_max)))
-			__schedstat_set(se->statistics.sleep_max, delta);
-
-		__schedstat_set(se->statistics.sleep_start, 0);
-		__schedstat_add(se->statistics.sum_sleep_runtime, delta);
-
-		if (tsk) {
-			account_scheduler_latency(tsk, delta >> 10, 1);
-			trace_sched_stat_sleep(tsk, delta);
-		}
-	}
-	if (block_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(se->statistics.block_max)))
-			__schedstat_set(se->statistics.block_max, delta);
-
-		__schedstat_set(se->statistics.block_start, 0);
-		__schedstat_add(se->statistics.sum_sleep_runtime, delta);
-
-		if (tsk) {
-			if (tsk->in_iowait) {
-				__schedstat_add(se->statistics.iowait_sum, delta);
-				__schedstat_inc(se->statistics.iowait_count);
-				trace_sched_stat_iowait(tsk, delta);
-			}
-
-			trace_sched_stat_blocked(tsk, delta);
-
-			/*
-			 * Blocking time is in units of nanosecs, so shift by
-			 * 20 to get a milliseconds-range estimation of the
-			 * amount of time that the task spent sleeping:
-			 */
-			if (unlikely(prof_on == SLEEP_PROFILING)) {
-				profile_hits(SLEEP_PROFILING,
-						(void *)get_wchan(tsk),
-						delta >> 20);
-			}
-			account_scheduler_latency(tsk, delta >> 10, 0);
-		}
-	}
+	__update_stats_enqueue_sleeper(rq_of(cfs_rq), tsk, stats);
 }
 
 /*
  * Task is being enqueued - update stats:
  */
 static inline void
-update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	if (!schedstat_enabled())
 		return;
@@ -1003,14 +960,14 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * a dequeue/enqueue event is a NOP)
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_start(cfs_rq, se);
+		update_stats_wait_start_fair(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
-		update_stats_enqueue_sleeper(cfs_rq, se);
+		update_stats_enqueue_sleeper_fair(cfs_rq, se);
 }
 
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 
 	if (!schedstat_enabled())
@@ -1021,7 +978,7 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * waiting task:
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end_fair(cfs_rq, se);
 
 	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
 		struct task_struct *tsk = task_of(se);
@@ -1030,10 +987,10 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		/* XXX racy against TTWU */
 		state = READ_ONCE(tsk->__state);
 		if (state & TASK_INTERRUPTIBLE)
-			__schedstat_set(se->statistics.sleep_start,
+			__schedstat_set(tsk->stats.sleep_start,
 				      rq_clock(rq_of(cfs_rq)));
 		if (state & TASK_UNINTERRUPTIBLE)
-			__schedstat_set(se->statistics.block_start,
+			__schedstat_set(tsk->stats.block_start,
 				      rq_clock(rq_of(cfs_rq)));
 	}
 }
@@ -1081,11 +1038,12 @@ struct numa_group {
 	unsigned long total_faults;
 	unsigned long max_faults_cpu;
 	/*
+	 * faults[] array is split into two regions: faults_mem and faults_cpu.
+	 *
 	 * Faults_cpu is used to decide whether memory should move
 	 * towards the CPU. As a consequence, these stats are weighted
 	 * more by CPU use than by memory faults.
 	 */
-	unsigned long *faults_cpu;
 	unsigned long faults[];
 };
 
@@ -1259,8 +1217,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 
 static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 {
-	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
-		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
+	return group->faults[task_faults_idx(NUMA_CPU, nid, 0)] +
+		group->faults[task_faults_idx(NUMA_CPU, nid, 1)];
 }
 
 static inline unsigned long group_faults_priv(struct numa_group *ng)
@@ -2116,7 +2074,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
- * Find out how many nodes on the workload is actively running on. Do this by
+ * Find out how many nodes the workload is actively running on. Do this by
  * tracking the nodes from which NUMA hinting faults are triggered. This can
  * be different from the set of nodes where the workload's memory is currently
  * located.
@@ -2170,7 +2128,7 @@ static void update_task_scan_period(struct task_struct *p,
 
 	/*
 	 * If there were no record hinting faults then either the task is
-	 * completely idle or all activity is areas that are not of interest
+	 * completely idle or all activity is in areas that are not of interest
 	 * to automatic numa balancing. Related to that, if there were failed
 	 * migration then it implies we are migrating too quickly or the local
 	 * node is overloaded. In either case, scan slower
@@ -2427,7 +2385,7 @@ static void task_numa_placement(struct task_struct *p)
 				 * is at the beginning of the numa_faults array.
 				 */
 				ng->faults[mem_idx] += diff;
-				ng->faults_cpu[mem_idx] += f_diff;
+				ng->faults[cpu_idx] += f_diff;
 				ng->total_faults += diff;
 				group_faults += ng->faults[mem_idx];
 			}
@@ -2481,7 +2439,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	if (unlikely(!deref_curr_numa_group(p))) {
 		unsigned int size = sizeof(struct numa_group) +
-				    4*nr_node_ids*sizeof(unsigned long);
+				    NR_NUMA_HINT_FAULT_STATS *
+				    nr_node_ids * sizeof(unsigned long);
 
 		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!grp)
@@ -2492,9 +2451,6 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		grp->max_faults_cpu = 0;
 		spin_lock_init(&grp->lock);
 		grp->gid = p->pid;
-		/* Second half of the array tracks nids where faults happen */
-		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
-						nr_node_ids;
 
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults[i];
@@ -2995,6 +2951,8 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running++;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running++;
 }
 
 static void
@@ -3008,6 +2966,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running--;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running--;
 }
 
 /*
@@ -4207,7 +4167,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	/* sleeps up to a single latency don't count. */
 	if (!initial) {
-		unsigned long thresh = sysctl_sched_latency;
+		unsigned long thresh;
+
+		if (se_is_idle(se))
+			thresh = sysctl_sched_min_granularity;
+		else
+			thresh = sysctl_sched_latency;
 
 		/*
 		 * Halve their sleep time's effect, to allow
@@ -4225,26 +4190,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
-static inline void check_schedstat_required(void)
-{
-#ifdef CONFIG_SCHEDSTATS
-	if (schedstat_enabled())
-		return;
-
-	/* Force schedstat enabled if a dependent tracepoint is active */
-	if (trace_sched_stat_wait_enabled()    ||
-			trace_sched_stat_sleep_enabled()   ||
-			trace_sched_stat_iowait_enabled()  ||
-			trace_sched_stat_blocked_enabled() ||
-			trace_sched_stat_runtime_enabled())  {
-		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
-			     "stat_blocked and stat_runtime require the "
-			     "kernel parameter schedstats=enable or "
-			     "kernel.sched_schedstats=1\n");
-	}
-#endif
-}
-
 static inline bool cfs_bandwidth_used(void);
 
 /*
@@ -4318,7 +4263,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		place_entity(cfs_rq, se, 0);
 
 	check_schedstat_required();
-	update_stats_enqueue(cfs_rq, se, flags);
+	update_stats_enqueue_fair(cfs_rq, se, flags);
 	check_spread(cfs_rq, se);
 	if (!curr)
 		__enqueue_entity(cfs_rq, se);
@@ -4402,7 +4347,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_load_avg(cfs_rq, se, UPDATE_TG);
 	se_update_runnable(se);
 
-	update_stats_dequeue(cfs_rq, se, flags);
+	update_stats_dequeue_fair(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -4487,7 +4432,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end_fair(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 	}
@@ -4502,9 +4447,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	if (schedstat_enabled() &&
 	    rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) {
-		schedstat_set(se->statistics.slice_max,
-			max((u64)schedstat_val(se->statistics.slice_max),
-			    se->sum_exec_runtime - se->prev_sum_exec_runtime));
+		struct sched_statistics *stats;
+
+		stats = __schedstats_from_se(se);
+		__schedstat_set(stats->slice_max,
+				max((u64)stats->slice_max,
+				    se->sum_exec_runtime - se->prev_sum_exec_runtime));
 	}
 
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
@@ -4586,7 +4534,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	check_spread(cfs_rq, prev);
 
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
+		update_stats_wait_start_fair(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
@@ -4687,11 +4635,20 @@ static inline u64 sched_cfs_bandwidth_slice(void)
  */
 void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 {
+	s64 runtime;
+
 	if (unlikely(cfs_b->quota == RUNTIME_INF))
 		return;
 
 	cfs_b->runtime += cfs_b->quota;
+	runtime = cfs_b->runtime_snap - cfs_b->runtime;
+	if (runtime > 0) {
+		cfs_b->burst_time += runtime;
+		cfs_b->nr_burst++;
+	}
+
 	cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
+	cfs_b->runtime_snap = cfs_b->runtime;
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -5577,6 +5534,17 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
+/*
+ * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use
+ * of idle_nr_running, which does not consider idle descendants of normal
+ * entities.
+ */
+static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->nr_running &&
+		cfs_rq->nr_running == cfs_rq->idle_nr_running;
+}
+
 #ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
@@ -5787,6 +5755,7 @@ static struct {
 	cpumask_var_t idle_cpus_mask;
 	atomic_t nr_cpus;
 	int has_blocked;		/* Idle CPUS has blocked load */
+	int needs_update;		/* Newly idle CPUs need their next_balance collated */
 	unsigned long next_balance;     /* in jiffy units */
 	unsigned long next_blocked;	/* Next update of blocked load in jiffies */
 } nohz ____cacheline_aligned;
@@ -5997,12 +5966,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits)
 		target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
-	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	schedstat_inc(p->stats.nr_wakeups_affine_attempts);
 	if (target == nr_cpumask_bits)
 		return prev_cpu;
 
 	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	schedstat_inc(p->stats.nr_wakeups_affine);
 	return target;
 }
 
@@ -6443,11 +6412,6 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_capacity(task_util, recent_used_cpu)) {
-		/*
-		 * Replace recent_used_cpu with prev as it is a potential
-		 * candidate for the next wake:
-		 */
-		p->recent_used_cpu = prev;
 		return recent_used_cpu;
 	}
 
@@ -7806,7 +7770,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
 		int cpu;
 
-		schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
+		schedstat_inc(p->stats.nr_failed_migrations_affine);
 
 		env->flags |= LBF_SOME_PINNED;
 
@@ -7840,7 +7804,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	env->flags &= ~LBF_ALL_PINNED;
 
 	if (task_running(env->src_rq, p)) {
-		schedstat_inc(p->se.statistics.nr_failed_migrations_running);
+		schedstat_inc(p->stats.nr_failed_migrations_running);
 		return 0;
 	}
 
@@ -7862,12 +7826,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	    env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 		if (tsk_cache_hot == 1) {
 			schedstat_inc(env->sd->lb_hot_gained[env->idle]);
-			schedstat_inc(p->se.statistics.nr_forced_migrations);
+			schedstat_inc(p->stats.nr_forced_migrations);
 		}
 		return 1;
 	}
 
-	schedstat_inc(p->se.statistics.nr_failed_migrations_hot);
+	schedstat_inc(p->stats.nr_failed_migrations_hot);
 	return 0;
 }
 
@@ -8602,6 +8566,99 @@ group_type group_classify(unsigned int imbalance_pct,
 }
 
 /**
+ * asym_smt_can_pull_tasks - Check whether the load balancing CPU can pull tasks
+ * @dst_cpu:	Destination CPU of the load balancing
+ * @sds:	Load-balancing data with statistics of the local group
+ * @sgs:	Load-balancing statistics of the candidate busiest group
+ * @sg:		The candidate busiest group
+ *
+ * Check the state of the SMT siblings of both @sds::local and @sg and decide
+ * if @dst_cpu can pull tasks.
+ *
+ * If @dst_cpu does not have SMT siblings, it can pull tasks if two or more of
+ * the SMT siblings of @sg are busy. If only one CPU in @sg is busy, pull tasks
+ * only if @dst_cpu has higher priority.
+ *
+ * If both @dst_cpu and @sg have SMT siblings, and @sg has exactly one more
+ * busy CPU than @sds::local, let @dst_cpu pull tasks if it has higher priority.
+ * Bigger imbalances in the number of busy CPUs will be dealt with in
+ * update_sd_pick_busiest().
+ *
+ * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings
+ * of @dst_cpu are idle and @sg has lower priority.
+ */
+static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds,
+				    struct sg_lb_stats *sgs,
+				    struct sched_group *sg)
+{
+#ifdef CONFIG_SCHED_SMT
+	bool local_is_smt, sg_is_smt;
+	int sg_busy_cpus;
+
+	local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY;
+	sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY;
+
+	sg_busy_cpus = sgs->group_weight - sgs->idle_cpus;
+
+	if (!local_is_smt) {
+		/*
+		 * If we are here, @dst_cpu is idle and does not have SMT
+		 * siblings. Pull tasks if candidate group has two or more
+		 * busy CPUs.
+		 */
+		if (sg_busy_cpus >= 2) /* implies sg_is_smt */
+			return true;
+
+		/*
+		 * @dst_cpu does not have SMT siblings. @sg may have SMT
+		 * siblings and only one is busy. In such case, @dst_cpu
+		 * can help if it has higher priority and is idle (i.e.,
+		 * it has no running tasks).
+		 */
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+	}
+
+	/* @dst_cpu has SMT siblings. */
+
+	if (sg_is_smt) {
+		int local_busy_cpus = sds->local->group_weight -
+				      sds->local_stat.idle_cpus;
+		int busy_cpus_delta = sg_busy_cpus - local_busy_cpus;
+
+		if (busy_cpus_delta == 1)
+			return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+		return false;
+	}
+
+	/*
+	 * @sg does not have SMT siblings. Ensure that @sds::local does not end
+	 * up with more than one busy SMT sibling and only pull tasks if there
+	 * are not busy CPUs (i.e., no CPU has running tasks).
+	 */
+	if (!sds->local_stat.sum_nr_running)
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+	return false;
+#else
+	/* Always return false so that callers deal with non-SMT cases. */
+	return false;
+#endif
+}
+
+static inline bool
+sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
+	   struct sched_group *group)
+{
+	/* Only do SMT checks if either local or candidate have SMT siblings */
+	if ((sds->local->flags & SD_SHARE_CPUCAPACITY) ||
+	    (group->flags & SD_SHARE_CPUCAPACITY))
+		return asym_smt_can_pull_tasks(env->dst_cpu, sds, sgs, group);
+
+	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
+}
+
+/**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @env: The load balancing environment.
  * @group: sched_group whose statistics are to be updated.
@@ -8609,6 +8666,7 @@ group_type group_classify(unsigned int imbalance_pct,
  * @sg_status: Holds flag indicating the status of the sched_group
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
+				      struct sd_lb_stats *sds,
 				      struct sched_group *group,
 				      struct sg_lb_stats *sgs,
 				      int *sg_status)
@@ -8617,7 +8675,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+	local_group = group == sds->local;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
@@ -8660,18 +8718,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		}
 	}
 
-	/* Check if dst CPU is idle and preferred to this group */
-	if (env->sd->flags & SD_ASYM_PACKING &&
-	    env->idle != CPU_NOT_IDLE &&
-	    sgs->sum_h_nr_running &&
-	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
-		sgs->group_asym_packing = 1;
-	}
-
 	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
 
+	/* Check if dst CPU is idle and preferred to this group */
+	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
+	    env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
+	    sched_asym(env, sds, sgs, group)) {
+		sgs->group_asym_packing = 1;
+	}
+
 	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
 
 	/* Computing avg_load makes sense only when group is overloaded */
@@ -9180,7 +9237,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sg, sgs, &sg_status);
+		update_sg_lb_stats(env, sds, sg, sgs, &sg_status);
 
 		if (local_group)
 			goto next_group;
@@ -9603,6 +9660,12 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		    nr_running == 1)
 			continue;
 
+		/* Make sure we only pull tasks from a CPU of lower priority */
+		if ((env->sd->flags & SD_ASYM_PACKING) &&
+		    sched_asym_prefer(i, env->dst_cpu) &&
+		    nr_running == 1)
+			continue;
+
 		switch (env->migration_type) {
 		case migrate_load:
 			/*
@@ -10176,6 +10239,30 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
+static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+{
+	if (cost > sd->max_newidle_lb_cost) {
+		/*
+		 * Track max cost of a domain to make sure to not delay the
+		 * next wakeup on the CPU.
+		 */
+		sd->max_newidle_lb_cost = cost;
+		sd->last_decay_max_lb_cost = jiffies;
+	} else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
+		/*
+		 * Decay the newidle max times by ~1% per second to ensure that
+		 * it is not outdated and the current max cost is actually
+		 * shorter.
+		 */
+		sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256;
+		sd->last_decay_max_lb_cost = jiffies;
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
@@ -10199,14 +10286,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 	for_each_domain(cpu, sd) {
 		/*
 		 * Decay the newidle max times here because this is a regular
-		 * visit to all the domains. Decay ~1% per second.
+		 * visit to all the domains.
 		 */
-		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
-			sd->max_newidle_lb_cost =
-				(sd->max_newidle_lb_cost * 253) / 256;
-			sd->next_decay_max_lb_cost = jiffies + HZ;
-			need_decay = 1;
-		}
+		need_decay = update_newidle_cost(sd, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -10375,7 +10457,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		goto out;
 
 	if (rq->nr_running >= 2) {
-		flags = NOHZ_KICK_MASK;
+		flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 		goto out;
 	}
 
@@ -10389,7 +10471,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * on.
 		 */
 		if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 	}
@@ -10403,7 +10485,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
 			if (sched_asym_prefer(i, cpu)) {
-				flags = NOHZ_KICK_MASK;
+				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 				goto unlock;
 			}
 		}
@@ -10416,7 +10498,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * to run the misfit task on.
 		 */
 		if (check_misfit_status(rq, sd)) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 
@@ -10443,13 +10525,16 @@ static void nohz_balancer_kick(struct rq *rq)
 		 */
 		nr_busy = atomic_read(&sds->nr_busy_cpus);
 		if (nr_busy > 1) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 	}
 unlock:
 	rcu_read_unlock();
 out:
+	if (READ_ONCE(nohz.needs_update))
+		flags |= NOHZ_NEXT_KICK;
+
 	if (flags)
 		kick_ilb(flags);
 }
@@ -10546,12 +10631,13 @@ void nohz_balance_enter_idle(int cpu)
 	/*
 	 * Ensures that if nohz_idle_balance() fails to observe our
 	 * @idle_cpus_mask store, it must observe the @has_blocked
-	 * store.
+	 * and @needs_update stores.
 	 */
 	smp_mb__after_atomic();
 
 	set_cpu_sd_state_idle(cpu);
 
+	WRITE_ONCE(nohz.needs_update, 1);
 out:
 	/*
 	 * Each time a cpu enter idle, we assume that it has blocked load and
@@ -10600,12 +10686,17 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 	/*
 	 * We assume there will be no idle load after this update and clear
 	 * the has_blocked flag. If a cpu enters idle in the mean time, it will
-	 * set the has_blocked flag and trig another update of idle load.
+	 * set the has_blocked flag and trigger another update of idle load.
 	 * Because a cpu that becomes idle, is added to idle_cpus_mask before
 	 * setting the flag, we are sure to not clear the state and not
 	 * check the load of an idle cpu.
+	 *
+	 * Same applies to idle_cpus_mask vs needs_update.
 	 */
-	WRITE_ONCE(nohz.has_blocked, 0);
+	if (flags & NOHZ_STATS_KICK)
+		WRITE_ONCE(nohz.has_blocked, 0);
+	if (flags & NOHZ_NEXT_KICK)
+		WRITE_ONCE(nohz.needs_update, 0);
 
 	/*
 	 * Ensures that if we miss the CPU, we must see the has_blocked
@@ -10627,13 +10718,17 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		 * balancing owner will pick it up.
 		 */
 		if (need_resched()) {
-			has_blocked_load = true;
+			if (flags & NOHZ_STATS_KICK)
+				has_blocked_load = true;
+			if (flags & NOHZ_NEXT_KICK)
+				WRITE_ONCE(nohz.needs_update, 1);
 			goto abort;
 		}
 
 		rq = cpu_rq(balance_cpu);
 
-		has_blocked_load |= update_nohz_stats(rq);
+		if (flags & NOHZ_STATS_KICK)
+			has_blocked_load |= update_nohz_stats(rq);
 
 		/*
 		 * If time for next balance is due,
@@ -10664,8 +10759,9 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 	if (likely(update_next_balance))
 		nohz.next_balance = next_balance;
 
-	WRITE_ONCE(nohz.next_blocked,
-		now + msecs_to_jiffies(LOAD_AVG_PERIOD));
+	if (flags & NOHZ_STATS_KICK)
+		WRITE_ONCE(nohz.next_blocked,
+			   now + msecs_to_jiffies(LOAD_AVG_PERIOD));
 
 abort:
 	/* There is still blocked load, enable periodic update */
@@ -10763,9 +10859,9 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
+	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	u64 curr_cost = 0;
 
 	update_misfit_status(NULL, this_rq);
 
@@ -10796,47 +10892,49 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	 */
 	rq_unpin_lock(this_rq, rf);
 
-	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
-	    !READ_ONCE(this_rq->rd->overload)) {
+	rcu_read_lock();
+	sd = rcu_dereference_check_sched_domain(this_rq->sd);
+
+	if (!READ_ONCE(this_rq->rd->overload) ||
+	    (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
 
-		rcu_read_lock();
-		sd = rcu_dereference_check_sched_domain(this_rq->sd);
 		if (sd)
 			update_next_balance(sd, &next_balance);
 		rcu_read_unlock();
 
 		goto out;
 	}
+	rcu_read_unlock();
 
 	raw_spin_rq_unlock(this_rq);
 
+	t0 = sched_clock_cpu(this_cpu);
 	update_blocked_averages(this_cpu);
+
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		int continue_balancing = 1;
-		u64 t0, domain_cost;
+		u64 domain_cost;
 
-		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
-			update_next_balance(sd, &next_balance);
+		update_next_balance(sd, &next_balance);
+
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
 			break;
-		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
-			t0 = sched_clock_cpu(this_cpu);
 
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
-			domain_cost = sched_clock_cpu(this_cpu) - t0;
-			if (domain_cost > sd->max_newidle_lb_cost)
-				sd->max_newidle_lb_cost = domain_cost;
+			t1 = sched_clock_cpu(this_cpu);
+			domain_cost = t1 - t0;
+			update_newidle_cost(sd, domain_cost);
 
 			curr_cost += domain_cost;
+			t0 = t1;
 		}
 
-		update_next_balance(sd, &next_balance);
-
 		/*
 		 * Stop searching for tasks to pull if there are
 		 * now runnable tasks on this rq.
@@ -11394,7 +11492,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!cfs_rq)
 			goto err;
 
-		se = kzalloc_node(sizeof(struct sched_entity),
+		se = kzalloc_node(sizeof(struct sched_entity_stats),
 				  GFP_KERNEL, cpu_to_node(i));
 		if (!se)
 			goto err_free_rq;
@@ -11560,7 +11658,7 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
 		struct sched_entity *se = tg->se[i];
-		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
+		struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i];
 		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
 		long idle_task_delta;
 		struct rq_flags rf;
@@ -11571,6 +11669,14 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 		if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq)))
 			goto next_cpu;
 
+		if (se->on_rq) {
+			parent_cfs_rq = cfs_rq_of(se);
+			if (cfs_rq_is_idle(grp_cfs_rq))
+				parent_cfs_rq->idle_nr_running++;
+			else
+				parent_cfs_rq->idle_nr_running--;
+		}
+
 		idle_task_delta = grp_cfs_rq->h_nr_running -
 				  grp_cfs_rq->idle_h_nr_running;
 		if (!cfs_rq_is_idle(grp_cfs_rq))
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 7f8dace0964c..1cf435bbcd9c 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,11 +46,16 @@ SCHED_FEAT(DOUBLE_TICK, false)
  */
 SCHED_FEAT(NONTASK_CAPACITY, true)
 
+#ifdef CONFIG_PREEMPT_RT
+SCHED_FEAT(TTWU_QUEUE, false)
+#else
+
 /*
  * Queue remote wakeups on the target CPU and process them
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
 SCHED_FEAT(TTWU_QUEUE, true)
+#endif
 
 /*
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3daf42a0f462..bb945f8faeca 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1009,8 +1009,10 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
-	schedstat_set(curr->se.statistics.exec_max,
-		      max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->stats.exec_max,
+		      max(curr->stats.exec_max, delta_exec));
+
+	trace_sched_stat_runtime(curr, delta_exec, 0);
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
@@ -1271,6 +1273,112 @@ static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_arr
 	rt_se->on_list = 0;
 }
 
+static inline struct sched_statistics *
+__schedstats_from_rt_se(struct sched_rt_entity *rt_se)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	/* schedstats is not supported for rt group. */
+	if (!rt_entity_is_task(rt_se))
+		return NULL;
+#endif
+
+	return &rt_task_of(rt_se)->stats;
+}
+
+static inline void
+update_stats_wait_start_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	stats = __schedstats_from_rt_se(rt_se);
+	if (!stats)
+		return;
+
+	__update_stats_wait_start(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_enqueue_sleeper_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	stats = __schedstats_from_rt_se(rt_se);
+	if (!stats)
+		return;
+
+	__update_stats_enqueue_sleeper(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_enqueue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
+			int flags)
+{
+	if (!schedstat_enabled())
+		return;
+
+	if (flags & ENQUEUE_WAKEUP)
+		update_stats_enqueue_sleeper_rt(rt_rq, rt_se);
+}
+
+static inline void
+update_stats_wait_end_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	stats = __schedstats_from_rt_se(rt_se);
+	if (!stats)
+		return;
+
+	__update_stats_wait_end(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
+			int flags)
+{
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	if ((flags & DEQUEUE_SLEEP) && p) {
+		unsigned int state;
+
+		state = READ_ONCE(p->__state);
+		if (state & TASK_INTERRUPTIBLE)
+			__schedstat_set(p->stats.sleep_start,
+					rq_clock(rq_of_rt_rq(rt_rq)));
+
+		if (state & TASK_UNINTERRUPTIBLE)
+			__schedstat_set(p->stats.block_start,
+					rq_clock(rq_of_rt_rq(rt_rq)));
+	}
+}
+
 static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
@@ -1344,6 +1452,8 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
+	update_stats_enqueue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+
 	dequeue_rt_stack(rt_se, flags);
 	for_each_sched_rt_entity(rt_se)
 		__enqueue_rt_entity(rt_se, flags);
@@ -1354,6 +1464,8 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
+	update_stats_dequeue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+
 	dequeue_rt_stack(rt_se, flags);
 
 	for_each_sched_rt_entity(rt_se) {
@@ -1376,6 +1488,9 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
+	check_schedstat_required();
+	update_stats_wait_start_rt(rt_rq_of_se(rt_se), rt_se);
+
 	enqueue_rt_entity(rt_se, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
@@ -1576,7 +1691,12 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 
 static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = &rq->rt;
+
 	p->se.exec_start = rq_clock_task(rq);
+	if (on_rt_rq(&p->rt))
+		update_stats_wait_end_rt(rt_rq, rt_se);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
@@ -1650,6 +1770,12 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 
 static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (on_rt_rq(&p->rt))
+		update_stats_wait_start_rt(rt_rq, rt_se);
+
 	update_curr_rt(rq);
 
 	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 66128dfc05fb..56ff343d4119 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -368,6 +368,7 @@ struct cfs_bandwidth {
 	u64			quota;
 	u64			runtime;
 	u64			burst;
+	u64			runtime_snap;
 	s64			hierarchical_quota;
 
 	u8			idle;
@@ -380,7 +381,9 @@ struct cfs_bandwidth {
 	/* Statistics: */
 	int			nr_periods;
 	int			nr_throttled;
+	int			nr_burst;
 	u64			throttled_time;
+	u64			burst_time;
 #endif
 };
 
@@ -529,6 +532,7 @@ struct cfs_rq {
 	struct load_weight	load;
 	unsigned int		nr_running;
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	u64			exec_clock;
@@ -1253,11 +1257,6 @@ extern void sched_core_dequeue(struct rq *rq, struct task_struct *p);
 extern void sched_core_get(void);
 extern void sched_core_put(void);
 
-extern unsigned long sched_core_alloc_cookie(void);
-extern void sched_core_put_cookie(unsigned long cookie);
-extern unsigned long sched_core_get_cookie(unsigned long cookie);
-extern unsigned long sched_core_update_cookie(struct task_struct *p, unsigned long cookie);
-
 #else /* !CONFIG_SCHED_CORE */
 
 static inline bool sched_core_enabled(struct rq *rq)
@@ -1421,11 +1420,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 
 extern void update_rq_clock(struct rq *rq);
 
-static inline u64 __rq_clock_broken(struct rq *rq)
-{
-	return READ_ONCE(rq->clock);
-}
-
 /*
  * rq::clock_update_flags bits
  *
@@ -1621,14 +1615,6 @@ rq_lock(struct rq *rq, struct rq_flags *rf)
 }
 
 static inline void
-rq_relock(struct rq *rq, struct rq_flags *rf)
-	__acquires(rq->lock)
-{
-	raw_spin_rq_lock(rq);
-	rq_repin_lock(rq, rf);
-}
-
-static inline void
 rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
@@ -1808,6 +1794,7 @@ struct sched_group {
 	unsigned int		group_weight;
 	struct sched_group_capacity *sgc;
 	int			asym_prefer_cpu;	/* CPU of highest priority in group */
+	int			flags;
 
 	/*
 	 * The CPUs this group covers.
@@ -2401,6 +2388,7 @@ extern const_debug unsigned int sysctl_sched_migration_cost;
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_idle_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern int sysctl_resched_latency_warn_ms;
 extern int sysctl_resched_latency_warn_once;
@@ -2708,12 +2696,18 @@ extern void cfs_bandwidth_usage_dec(void);
 #define NOHZ_BALANCE_KICK_BIT	0
 #define NOHZ_STATS_KICK_BIT	1
 #define NOHZ_NEWILB_KICK_BIT	2
+#define NOHZ_NEXT_KICK_BIT	3
 
+/* Run rebalance_domains() */
 #define NOHZ_BALANCE_KICK	BIT(NOHZ_BALANCE_KICK_BIT)
+/* Update blocked load */
 #define NOHZ_STATS_KICK		BIT(NOHZ_STATS_KICK_BIT)
+/* Update blocked load when entering idle */
 #define NOHZ_NEWILB_KICK	BIT(NOHZ_NEWILB_KICK_BIT)
+/* Update nohz.next_balance */
+#define NOHZ_NEXT_KICK		BIT(NOHZ_NEXT_KICK_BIT)
 
-#define NOHZ_KICK_MASK	(NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
+#define NOHZ_KICK_MASK	(NOHZ_BALANCE_KICK | NOHZ_STATS_KICK | NOHZ_NEXT_KICK)
 
 #define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)
 
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 3f93fc3b5648..07dde2928c79 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -4,6 +4,110 @@
  */
 #include "sched.h"
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats)
+{
+	u64 wait_start, prev_wait_start;
+
+	wait_start = rq_clock(rq);
+	prev_wait_start = schedstat_val(stats->wait_start);
+
+	if (p && likely(wait_start > prev_wait_start))
+		wait_start -= prev_wait_start;
+
+	__schedstat_set(stats->wait_start, wait_start);
+}
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats)
+{
+	u64 delta = rq_clock(rq) - schedstat_val(stats->wait_start);
+
+	if (p) {
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			__schedstat_set(stats->wait_start, delta);
+
+			return;
+		}
+
+		trace_sched_stat_wait(p, delta);
+	}
+
+	__schedstat_set(stats->wait_max,
+			max(schedstat_val(stats->wait_max), delta));
+	__schedstat_inc(stats->wait_count);
+	__schedstat_add(stats->wait_sum, delta);
+	__schedstat_set(stats->wait_start, 0);
+}
+
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats)
+{
+	u64 sleep_start, block_start;
+
+	sleep_start = schedstat_val(stats->sleep_start);
+	block_start = schedstat_val(stats->block_start);
+
+	if (sleep_start) {
+		u64 delta = rq_clock(rq) - sleep_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->sleep_max)))
+			__schedstat_set(stats->sleep_max, delta);
+
+		__schedstat_set(stats->sleep_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+
+		if (p) {
+			account_scheduler_latency(p, delta >> 10, 1);
+			trace_sched_stat_sleep(p, delta);
+		}
+	}
+
+	if (block_start) {
+		u64 delta = rq_clock(rq) - block_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->block_max)))
+			__schedstat_set(stats->block_max, delta);
+
+		__schedstat_set(stats->block_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+		__schedstat_add(stats->sum_block_runtime, delta);
+
+		if (p) {
+			if (p->in_iowait) {
+				__schedstat_add(stats->iowait_sum, delta);
+				__schedstat_inc(stats->iowait_count);
+				trace_sched_stat_iowait(p, delta);
+			}
+
+			trace_sched_stat_blocked(p, delta);
+
+			/*
+			 * Blocking time is in units of nanosecs, so shift by
+			 * 20 to get a milliseconds-range estimation of the
+			 * amount of time that the task spent sleeping:
+			 */
+			if (unlikely(prof_on == SLEEP_PROFILING)) {
+				profile_hits(SLEEP_PROFILING,
+					     (void *)get_wchan(p),
+					     delta >> 20);
+			}
+			account_scheduler_latency(p, delta >> 10, 0);
+		}
+	}
+}
+
 /*
  * Current schedstat API version.
  *
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index d8f8eb0c655b..cfb0893a83d4 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -2,6 +2,8 @@
 
 #ifdef CONFIG_SCHEDSTATS
 
+extern struct static_key_false sched_schedstats;
+
 /*
  * Expects runqueue lock to be held for atomicity of update
  */
@@ -40,7 +42,31 @@ rq_sched_info_dequeue(struct rq *rq, unsigned long long delta)
 #define   schedstat_val(var)		(var)
 #define   schedstat_val_or_zero(var)	((schedstat_enabled()) ? (var) : 0)
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats);
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats);
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats);
+
+static inline void
+check_schedstat_required(void)
+{
+	if (schedstat_enabled())
+		return;
+
+	/* Force schedstat enabled if a dependent tracepoint is active */
+	if (trace_sched_stat_wait_enabled()    ||
+	    trace_sched_stat_sleep_enabled()   ||
+	    trace_sched_stat_iowait_enabled()  ||
+	    trace_sched_stat_blocked_enabled() ||
+	    trace_sched_stat_runtime_enabled())
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1\n");
+}
+
 #else /* !CONFIG_SCHEDSTATS: */
+
 static inline void rq_sched_info_arrive  (struct rq *rq, unsigned long long delta) { }
 static inline void rq_sched_info_dequeue(struct rq *rq, unsigned long long delta) { }
 static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delta) { }
@@ -53,8 +79,31 @@ static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delt
 # define   schedstat_set(var, val)	do { } while (0)
 # define   schedstat_val(var)		0
 # define   schedstat_val_or_zero(var)	0
+
+# define __update_stats_wait_start(rq, p, stats)       do { } while (0)
+# define __update_stats_wait_end(rq, p, stats)         do { } while (0)
+# define __update_stats_enqueue_sleeper(rq, p, stats)  do { } while (0)
+# define check_schedstat_required()                    do { } while (0)
+
 #endif /* CONFIG_SCHEDSTATS */
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+struct sched_entity_stats {
+	struct sched_entity     se;
+	struct sched_statistics stats;
+} __no_randomize_layout;
+#endif
+
+static inline struct sched_statistics *
+__schedstats_from_se(struct sched_entity *se)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (!entity_is_task(se))
+		return &container_of(se, struct sched_entity_stats, se)->stats;
+#endif
+	return &task_of(se)->stats;
+}
+
 #ifdef CONFIG_PSI
 /*
  * PSI tracks state that persists across sleeps, such as iowaits and
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index f988ebe3febb..0b165a25f22f 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -78,8 +78,8 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.statistics.exec_max,
-			max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->stats.exec_max,
+		      max(curr->stats.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 4e8698e62f07..30169c7685b6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -526,7 +526,7 @@ static int init_rootdomain(struct root_domain *rd)
 #ifdef HAVE_RT_PUSH_IPI
 	rd->rto_cpu = -1;
 	raw_spin_lock_init(&rd->rto_lock);
-	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+	rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
 #endif
 
 	rd->visit_gen = 0;
@@ -688,7 +688,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
-	int numa_distance = 0;
 
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
@@ -716,13 +715,22 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 		tmp = sd;
 		sd = sd->parent;
 		destroy_sched_domain(tmp);
-		if (sd)
+		if (sd) {
+			struct sched_group *sg = sd->groups;
+
+			/*
+			 * sched groups hold the flags of the child sched
+			 * domain for convenience. Clear such flags since
+			 * the child is being destroyed.
+			 */
+			do {
+				sg->flags = 0;
+			} while (sg != sd->groups);
+
 			sd->child = NULL;
+		}
 	}
 
-	for (tmp = sd; tmp; tmp = tmp->parent)
-		numa_distance += !!(tmp->flags & SD_NUMA);
-
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);
@@ -916,10 +924,12 @@ build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 		return NULL;
 
 	sg_span = sched_group_span(sg);
-	if (sd->child)
+	if (sd->child) {
 		cpumask_copy(sg_span, sched_domain_span(sd->child));
-	else
+		sg->flags = sd->child->flags;
+	} else {
 		cpumask_copy(sg_span, sched_domain_span(sd));
+	}
 
 	atomic_inc(&sg->ref);
 	return sg;
@@ -1169,6 +1179,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	if (child) {
 		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
 		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
+		sg->flags = child->flags;
 	} else {
 		cpumask_set_cpu(cpu, sched_group_span(sg));
 		cpumask_set_cpu(cpu, group_balance_mask(sg));
@@ -1557,7 +1568,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
 		.max_newidle_lb_cost	= 0,
-		.next_decay_max_lb_cost	= jiffies,
+		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,
 #ifdef CONFIG_SCHED_DEBUG
 		.name			= tl->name,
@@ -1627,6 +1638,11 @@ static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 #endif
+
+#ifdef CONFIG_SCHED_CLUSTER
+	{ cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
+
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 #endif
diff --git a/kernel/smp.c b/kernel/smp.c
index f43ede0ab183..01a7c1706a58 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -1170,14 +1170,12 @@ void wake_up_all_idle_cpus(void)
 {
 	int cpu;
 
-	preempt_disable();
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-
-		wake_up_if_idle(cpu);
+	for_each_possible_cpu(cpu) {
+		preempt_disable();
+		if (cpu != smp_processor_id() && cpu_online(cpu))
+			wake_up_if_idle(cpu);
+		preempt_enable();
 	}
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus);