Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The main changes in this cycle were:

   - sched/fair load tracking fixes and cleanups (Byungchul Park)

   - Make load tracking frequency scale invariant (Dietmar Eggemann)

   - sched/deadline updates (Juri Lelli)

   - stop machine fixes, cleanups and enhancements for bugs triggered by
     CPU hotplug stress testing (Oleg Nesterov)

   - scheduler preemption code rework: remove PREEMPT_ACTIVE and related
     cleanups (Peter Zijlstra)

   - Rework the sched_info::run_delay code to fix races (Peter Zijlstra)

   - Optimize per entity utilization tracking (Peter Zijlstra)

   - ... misc other fixes, cleanups and smaller updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
  sched: Move cpu_active() tests from stop_two_cpus() into migrate_swap_stop()
  sched: Start stopper early
  stop_machine: Kill cpu_stop_threads->setup() and cpu_stop_unpark()
  stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()
  stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled
  stop_machine: Introduce __cpu_stop_queue_work() and cpu_stop_queue_two_works()
  stop_machine: Ensure that a queued callback will be called before cpu_stop_park()
  sched/x86: Fix typo in __switch_to() comments
  sched/core: Remove a parameter in the migrate_task_rq() function
  sched/core: Drop unlikely behind BUG_ON()
  sched/core: Fix task and run queue sched_info::run_delay inconsistencies
  sched/numa: Fix task_tick_fair() from disabling numa_balancing
  sched/core: Add preempt_count invariant check
  sched/core: More notrace annotations
  sched/core: Kill PREEMPT_ACTIVE
  sched/core, sched/x86: Kill thread_info::saved_preempt_count
  sched/core: Simplify preempt_count tests
  sched/core: Robustify preemption leak checks
  sched/core: Stop setting PREEMPT_ACTIVE
  ...

26 files changed, 492 insertions, 469 deletions

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index b12f81022a6b..01bcde84d3e4 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,12 +30,9 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define init_task_preempt_count(p) do { \
-	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
-} while (0)
+#define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \
 	per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
 } while (0)
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8afdc3e44247..809877e9030b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -57,7 +57,6 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
 	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
@@ -69,7 +68,6 @@ struct thread_info {
 	.task		= &tsk,			\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 737527b40e5b..9f950917528b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -280,14 +280,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		set_iopl_mask(next->iopl);
 
 	/*
-	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
-	 * preempt_count of all tasks was equal here and this would not be
-	 * needed.
-	 */
-	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
-	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
-
-	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
 	 */
 	if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b35921a670b2..e835d263a33b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -332,7 +332,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch FS and GS.
 	 *
-	 * These are even more complicated than FS and GS: they have
+	 * These are even more complicated than DS and ES: they have
 	 * 64-bit bases are that controlled by arch_prctl.  Those bases
 	 * only differ from the values in the GDT or LDT if the selector
 	 * is 0.
@@ -401,14 +401,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	this_cpu_write(current_task, next_p);
 
-	/*
-	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
-	 * preempt_count of all tasks was equal here and this would not be
-	 * needed.
-	 */
-	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
-	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
-
 	/* Reload esp0 and ss1.  This changes current_thread_info(). */
 	load_sp0(tss, next);
 
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 0bec580a4885..5d8ffa3e6f8c 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -24,7 +24,7 @@ static __always_inline void preempt_count_set(int pc)
  * must be macros to avoid header recursion hell
  */
 #define init_task_preempt_count(p) do { \
-	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+	task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
 } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bea8dd8ff5e0..75e4e30677f1 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -26,7 +26,6 @@
  *         SOFTIRQ_MASK:	0x0000ff00
  *         HARDIRQ_MASK:	0x000f0000
  *             NMI_MASK:	0x00100000
- *       PREEMPT_ACTIVE:	0x00200000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
@@ -53,10 +52,6 @@
 
 #define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
 
-#define PREEMPT_ACTIVE_BITS	1
-#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -126,8 +121,7 @@
  * Check whether we were atomic before we did preempt_disable():
  * (used by the scheduler)
  */
-#define in_atomic_preempt_off() \
-		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
 
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
@@ -146,18 +140,6 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
-#define preempt_active_enter() \
-do { \
-	preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
-	barrier(); \
-} while (0)
-
-#define preempt_active_exit() \
-do { \
-	barrier(); \
-	preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
-} while (0)
-
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 56667292d1e4..9e1e06c3ce05 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -599,20 +599,26 @@ struct task_cputime_atomic {
 		.sum_exec_runtime = ATOMIC64_INIT(0),		\
 	}
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
-#else
-#define PREEMPT_DISABLED	PREEMPT_ENABLED
-#endif
+#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
+/*
+ * Disable preemption until the scheduler is running -- use an unconditional
+ * value so that it also works on !PREEMPT_COUNT kernels.
+ *
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
+ */
+#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET
 
 /*
- * Disable preemption until the scheduler is running.
- * Reset by start_kernel()->sched_init()->init_idle().
+ * Initial preempt_count value; reflects the preempt_count schedule invariant
+ * which states that during context switches:
  *
- * We include PREEMPT_ACTIVE to avoid cond_resched() from working
- * before the scheduler is active -- see should_resched().
+ *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
+ *
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
  */
-#define INIT_PREEMPT_COUNT	(PREEMPT_DISABLED + PREEMPT_ACTIVE)
+#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
@@ -1142,8 +1148,6 @@ struct sched_domain_topology_level {
 #endif
 };
 
-extern struct sched_domain_topology_level *sched_domain_topology;
-
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
 extern void wake_up_if_idle(int cpu);
 
@@ -1192,10 +1196,10 @@ struct load_weight {
 
 /*
  * The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors the amount of time that a sched_entity is
- * runnable on a rq into its weight. For cfs_rq, it is the aggregated
- * such weights of all runnable and blocked sched_entities.
- * 2) util_avg factors frequency scaling into the amount of time
+ * 1) load_avg factors frequency scaling into the amount of time that a
+ * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the
+ * aggregated such weights of all runnable and blocked sched_entities.
+ * 2) util_avg factors frequency and cpu scaling into the amount of time
  * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
  * For cfs_rq, it is the aggregated such times of all runnable and
  * blocked sched_entities.
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 9d303b8847df..9089a2ae913d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -21,4 +21,9 @@ static inline int dl_task(struct task_struct *p)
 	return dl_prio(p->prio);
 }
 
+static inline bool dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
 #endif /* _SCHED_DEADLINE_H */
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index e6109a6cd8f6..12910cf19869 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -24,9 +24,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @pre_unpark:		Optional unpark function, called before the thread is
- *			unparked (cpu online). This is not guaranteed to be
- *			called on the target cpu of the thread. Careful!
  * @cpumask:		Internal state.  To update which threads are unparked,
  *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
@@ -42,7 +39,6 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	void				(*pre_unpark)(unsigned int cpu);
 	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 414d924318ce..0adedca24c5b 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -33,6 +33,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+void stop_machine_park(int cpu);
+void stop_machine_unpark(int cpu);
 
 #else	/* CONFIG_SMP */
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 539d6bc3216a..9b90c57517a9 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -104,22 +104,17 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
 {
-	long state = p->state;
-
-#ifdef CONFIG_PREEMPT
 #ifdef CONFIG_SCHED_DEBUG
 	BUG_ON(p != current);
 #endif /* CONFIG_SCHED_DEBUG */
+
 	/*
-	 * For all intents and purposes a preempted task is a running task.
+	 * Preemption ignores task state, therefore preempted tasks are always
+	 * RUNNING (we will not have dequeued if state != RUNNING).
 	 */
-	if (preempt_count() & PREEMPT_ACTIVE)
-		state = TASK_RUNNING | TASK_STATE_MAX;
-#endif /* CONFIG_PREEMPT */
-
-	return state;
+	return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
 }
 #endif /* CREATE_TRACE_POINTS */
 
@@ -128,10 +123,11 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
  */
 TRACE_EVENT(sched_switch,
 
-	TP_PROTO(struct task_struct *prev,
+	TP_PROTO(bool preempt,
+		 struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(prev, next),
+	TP_ARGS(preempt, prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -147,7 +143,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 14a9cdf8abe9..85ff5e26e23b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -291,8 +291,8 @@ static inline void check_for_tasks(int dead_cpu)
 {
 	struct task_struct *g, *p;
 
-	read_lock_irq(&tasklist_lock);
-	do_each_thread(g, p) {
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
 		if (!p->on_rq)
 			continue;
 		/*
@@ -307,8 +307,8 @@ static inline void check_for_tasks(int dead_cpu)
 
 		pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
 			p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
-	} while_each_thread(g, p);
-	read_unlock_irq(&tasklist_lock);
+	}
+	read_unlock(&tasklist_lock);
 }
 
 struct take_cpu_down_param {
@@ -331,7 +331,7 @@ static int take_cpu_down(void *_param)
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
 	/* Park the stopper thread */
-	kthread_park(current);
+	stop_machine_park((long)param->hcpu);
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 0e93b63bbc59..07110c6020a0 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -706,10 +706,12 @@ void do_exit(long code)
 	smp_mb();
 	raw_spin_unlock_wait(&tsk->pi_lock);
 
-	if (unlikely(in_atomic()))
+	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
 			current->comm, task_pid_nr(current),
 			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
 
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index bbb72b4f64a1..8251e75dd9c0 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -170,7 +170,8 @@ rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 	 * then right waiter has a dl_prio() too.
 	 */
 	if (dl_prio(left->prio))
-		return (left->task->dl.deadline < right->task->dl.deadline);
+		return dl_time_before(left->task->dl.deadline,
+				      right->task->dl.deadline);
 
 	return 0;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f7402f7eb448..aa5973220ad2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -817,7 +817,7 @@ static void set_load_weight(struct task_struct *p)
 	/*
 	 * SCHED_IDLE tasks get minimal weight:
 	 */
-	if (p->policy == SCHED_IDLE) {
+	if (idle_policy(p->policy)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
 		return;
@@ -827,17 +827,19 @@ static void set_load_weight(struct task_struct *p)
 	load->inv_weight = prio_to_wmult[prio];
 }
 
-static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
+static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_queued(rq, p);
+	if (!(flags & ENQUEUE_RESTORE))
+		sched_info_queued(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
-static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
+static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_dequeued(rq, p);
+	if (!(flags & DEQUEUE_SAVE))
+		sched_info_dequeued(rq, p);
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -1178,7 +1180,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		 * holding rq->lock.
 		 */
 		lockdep_assert_held(&rq->lock);
-		dequeue_task(rq, p, 0);
+		dequeue_task(rq, p, DEQUEUE_SAVE);
 	}
 	if (running)
 		put_prev_task(rq, p);
@@ -1188,7 +1190,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, ENQUEUE_RESTORE);
 }
 
 /*
@@ -1292,7 +1294,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	if (task_cpu(p) != new_cpu) {
 		if (p->sched_class->migrate_task_rq)
-			p->sched_class->migrate_task_rq(p, new_cpu);
+			p->sched_class->migrate_task_rq(p);
 		p->se.nr_migrations++;
 		perf_event_task_migrate(p);
 	}
@@ -1333,12 +1335,16 @@ static int migrate_swap_stop(void *data)
 	struct rq *src_rq, *dst_rq;
 	int ret = -EAGAIN;
 
+	if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
+		return -EAGAIN;
+
 	src_rq = cpu_rq(arg->src_cpu);
 	dst_rq = cpu_rq(arg->dst_cpu);
 
 	double_raw_lock(&arg->src_task->pi_lock,
 			&arg->dst_task->pi_lock);
 	double_rq_lock(src_rq, dst_rq);
+
 	if (task_cpu(arg->dst_task) != arg->dst_cpu)
 		goto unlock;
 
@@ -1574,13 +1580,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			goto out;
 		}
 
+		/* No more Mr. Nice Guy. */
 		switch (state) {
 		case cpuset:
-			/* No more Mr. Nice Guy. */
-			cpuset_cpus_allowed_fallback(p);
-			state = possible;
-			break;
-
+			if (IS_ENABLED(CONFIG_CPUSETS)) {
+				cpuset_cpus_allowed_fallback(p);
+				state = possible;
+				break;
+			}
+			/* fall-through */
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
@@ -1692,7 +1700,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 #endif /* CONFIG_SCHEDSTATS */
 }
 
-static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
+static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
 {
 	activate_task(rq, p, en_flags);
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -2114,23 +2122,17 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
+DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
+
 #ifdef CONFIG_NUMA_BALANCING
-#ifdef CONFIG_SCHED_DEBUG
+
 void set_numabalancing_state(bool enabled)
 {
 	if (enabled)
-		sched_feat_set("NUMA");
+		static_branch_enable(&sched_numa_balancing);
 	else
-		sched_feat_set("NO_NUMA");
+		static_branch_disable(&sched_numa_balancing);
 }
-#else
-__read_mostly bool numabalancing_enabled;
-
-void set_numabalancing_state(bool enabled)
-{
-	numabalancing_enabled = enabled;
-}
-#endif /* CONFIG_SCHED_DEBUG */
 
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_numa_balancing(struct ctl_table *table, int write,
@@ -2138,7 +2140,7 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 {
 	struct ctl_table t;
 	int err;
-	int state = numabalancing_enabled;
+	int state = static_branch_likely(&sched_numa_balancing);
 
 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -2349,6 +2351,8 @@ void wake_up_new_task(struct task_struct *p)
 	struct rq *rq;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	/* Initialize new task's runnable average */
+	init_entity_runnable_average(&p->se);
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
@@ -2358,8 +2362,6 @@ void wake_up_new_task(struct task_struct *p)
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 
-	/* Initialize new task's runnable average */
-	init_entity_runnable_average(&p->se);
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -2483,7 +2485,6 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
-	trace_sched_switch(prev, next);
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
@@ -2517,6 +2518,22 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
 
+	/*
+	 * The previous task will have left us with a preempt_count of 2
+	 * because it left us after:
+	 *
+	 *	schedule()
+	 *	  preempt_disable();			// 1
+	 *	  __schedule()
+	 *	    raw_spin_lock_irq(&rq->lock)	// 2
+	 *
+	 * Also, see FORK_PREEMPT_COUNT.
+	 */
+	if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
+		      "corrupted preempt_count: %s/%d/0x%x\n",
+		      current->comm, current->pid, preempt_count()))
+		preempt_count_set(FORK_PREEMPT_COUNT);
+
 	rq->prev_mm = NULL;
 
 	/*
@@ -2601,8 +2618,15 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 {
 	struct rq *rq;
 
-	/* finish_task_switch() drops rq->lock and enables preemtion */
-	preempt_disable();
+	/*
+	 * New tasks start with FORK_PREEMPT_COUNT, see there and
+	 * finish_task_switch() for details.
+	 *
+	 * finish_task_switch() will drop rq->lock() and lower preempt_count
+	 * and the preempt_enable() will end up enabling preemption (on
+	 * PREEMPT_COUNT kernels).
+	 */
+
 	rq = finish_task_switch(prev);
 	balance_callback(rq);
 	preempt_enable();
@@ -2960,15 +2984,13 @@ static noinline void __schedule_bug(struct task_struct *prev)
 static inline void schedule_debug(struct task_struct *prev)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
-	BUG_ON(unlikely(task_stack_end_corrupted(prev)));
+	BUG_ON(task_stack_end_corrupted(prev));
 #endif
-	/*
-	 * Test if we are atomic. Since do_exit() needs to call into
-	 * schedule() atomically, we ignore that path. Otherwise whine
-	 * if we are scheduling when we should not.
-	 */
-	if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
+
+	if (unlikely(in_atomic_preempt_off())) {
 		__schedule_bug(prev);
+		preempt_count_set(PREEMPT_DISABLED);
+	}
 	rcu_sleep_check();
 
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
@@ -3054,7 +3076,7 @@ again:
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched __schedule(void)
+static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -3066,6 +3088,17 @@ static void __sched __schedule(void)
 	rcu_note_context_switch();
 	prev = rq->curr;
 
+	/*
+	 * do_exit() calls schedule() with preemption disabled as an exception;
+	 * however we must fix that up, otherwise the next task will see an
+	 * inconsistent (higher) preempt count.
+	 *
+	 * It also avoids the below schedule_debug() test from complaining
+	 * about this.
+	 */
+	if (unlikely(prev->state == TASK_DEAD))
+		preempt_enable_no_resched_notrace();
+
 	schedule_debug(prev);
 
 	if (sched_feat(HRTICK))
@@ -3083,7 +3116,7 @@ static void __sched __schedule(void)
 	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
 
 	switch_count = &prev->nivcsw;
-	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+	if (!preempt && prev->state) {
 		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
@@ -3119,6 +3152,7 @@ static void __sched __schedule(void)
 		rq->curr = next;
 		++*switch_count;
 
+		trace_sched_switch(preempt, prev, next);
 		rq = context_switch(rq, prev, next); /* unlocks the rq */
 		cpu = cpu_of(rq);
 	} else {
@@ -3148,7 +3182,7 @@ asmlinkage __visible void __sched schedule(void)
 	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule();
+		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
 }
@@ -3188,9 +3222,9 @@ void __sched schedule_preempt_disabled(void)
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
-		preempt_active_enter();
-		__schedule();
-		preempt_active_exit();
+		preempt_disable_notrace();
+		__schedule(true);
+		preempt_enable_no_resched_notrace();
 
 		/*
 		 * Check again in case we missed a preemption opportunity
@@ -3241,24 +3275,17 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 		return;
 
 	do {
-		/*
-		 * Use raw __prempt_count() ops that don't call function.
-		 * We can't call functions before disabling preemption which
-		 * disarm preemption tracing recursions.
-		 */
-		__preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
-		barrier();
+		preempt_disable_notrace();
 		/*
 		 * Needs preempt disabled in case user_exit() is traced
 		 * and the tracer calls preempt_enable_notrace() causing
 		 * an infinite recursion.
 		 */
 		prev_ctx = exception_enter();
-		__schedule();
+		__schedule(true);
 		exception_exit(prev_ctx);
 
-		barrier();
-		__preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+		preempt_enable_no_resched_notrace();
 	} while (need_resched());
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
@@ -3281,11 +3308,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	prev_state = exception_enter();
 
 	do {
-		preempt_active_enter();
+		preempt_disable();
 		local_irq_enable();
-		__schedule();
+		__schedule(true);
 		local_irq_disable();
-		preempt_active_exit();
+		sched_preempt_enable_no_resched();
 	} while (need_resched());
 
 	exception_exit(prev_state);
@@ -3313,7 +3340,7 @@ EXPORT_SYMBOL(default_wake_function);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, queued, running, enqueue_flag = 0;
+	int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
@@ -3345,7 +3372,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, 0);
+		dequeue_task(rq, p, DEQUEUE_SAVE);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -3363,7 +3390,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
-			enqueue_flag = ENQUEUE_REPLENISH;
+			enqueue_flag |= ENQUEUE_REPLENISH;
 		} else
 			p->dl.dl_boosted = 0;
 		p->sched_class = &dl_sched_class;
@@ -3371,7 +3398,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
 		if (oldprio < prio)
-			enqueue_flag = ENQUEUE_HEAD;
+			enqueue_flag |= ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
@@ -3423,7 +3450,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	}
 	queued = task_on_rq_queued(p);
 	if (queued)
-		dequeue_task(rq, p, 0);
+		dequeue_task(rq, p, DEQUEUE_SAVE);
 
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
@@ -3432,7 +3459,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (queued) {
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, ENQUEUE_RESTORE);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -3753,10 +3780,7 @@ recheck:
 	} else {
 		reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
 
-		if (policy != SCHED_DEADLINE &&
-				policy != SCHED_FIFO && policy != SCHED_RR &&
-				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
-				policy != SCHED_IDLE)
+		if (!valid_policy(policy))
 			return -EINVAL;
 	}
 
@@ -3812,7 +3836,7 @@ recheck:
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
-		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+		if (idle_policy(p->policy) && !idle_policy(policy)) {
 			if (!can_nice(p, task_nice(p)))
 				return -EPERM;
 		}
@@ -3937,7 +3961,7 @@ change:
 	queued = task_on_rq_queued(p);
 	running = task_