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)