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
  ...

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)
 

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,		\
 }
 

arch/x86/kernel/process_32.c

@@ -279,14 +279,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
 		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
 	 */

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);
 

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 { \

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() \

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.

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 */

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;

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 */
 

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;

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;
 }
 

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)

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;
 }

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 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
  *
  * 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 @@ static int __sched_setscheduler(struct task_struct *p,
 	} 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 @@ static int __sched_setscheduler(struct task_struct *p,
 		 * 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 @@ static int __sched_setscheduler(struct task_struct *p,
 	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);
 
@@ -3947,11 +3971,15 @@ static int __sched_setscheduler(struct task_struct *p,
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued) {
+		int enqueue_flags = ENQUEUE_RESTORE;
 		/*
 		 * We enqueue to tail when the priority of a task is
 		 * increased (user space view).
 		 */
-		enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+		if (oldprio <= p->prio)
+			enqueue_flags |= ENQUEUE_HEAD;
+
+		enqueue_task(rq, p, enqueue_flags);
 	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
@@ -5101,7 +5129,7 @@ void sched_setnuma(struct task_struct *p, int nid)
 	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);
 
@@ -5110,7 +5138,7 @@ void sched_setnuma(struct task_struct *p, int nid)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, ENQUEUE_RESTORE);
 	task_rq_unlock(rq, p, &flags);
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -5531,21 +5559,27 @@ static void set_cpu_rq_start_time(void)
 static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
+	int cpu = (long)hcpu;
+
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_STARTING:
 		set_cpu_rq_start_time();
 		return NOTIFY_OK;
+
 	case CPU_ONLINE:
 		/*
 		 * At this point a starting CPU has marked itself as online via
 		 * set_cpu_online(). But it might not yet have marked itself
 		 * as active, which is essential from here on.
-		 *
-		 * Thus, fall-through and help the starting CPU along.
 		 */
+		set_cpu_active(cpu, true);
+		stop_machine_unpark(cpu);
+		return NOTIFY_OK;
+
 	case CPU_DOWN_FAILED:
-		set_cpu_active((long)hcpu, true);
+		set_cpu_active(cpu, true);
 		return NOTIFY_OK;
+
 	default:
 		return NOTIFY_DONE;
 	}
@@ -6477,7 +6511,8 @@ static struct sched_domain_topology_level default_topology[] = {
 	{ NULL, },
 };
 
-struct sched_domain_topology_level *sched_domain_topology = default_topology;
+static struct sched_domain_topology_level *sched_domain_topology =
+	default_topology;
 
 #define for_each_sd_topology(tl)			\
 	for (tl = sched_domain_topology; tl->mask; tl++)
@@ -7478,7 +7513,7 @@ void __init sched_init(void)
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 static inline int preempt_count_equals(int preempt_offset)
 {
-	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
+	int nested = preempt_count() + rcu_preempt_depth();
 
 	return (nested == preempt_offset);
 }
@@ -7725,7 +7760,7 @@ void sched_move_task(struct task_struct *tsk)
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
-		dequeue_task(rq, tsk, 0);
+		dequeue_task(rq, tsk, DEQUEUE_SAVE);
 	if (unlikely(running))
 		put_prev_task(rq, tsk);
 
@@ -7741,7 +7776,7 @@ void sched_move_task(struct task_struct *tsk)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_move_group)
-		tsk->sched_class->task_move_group(tsk, queued);
+		tsk->sched_class->task_move_group(tsk);
 	else
 #endif
 		set_task_rq(tsk, task_cpu(tsk));
@@ -7749,7 +7784,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, tsk, 0);
+		enqueue_task(rq, tsk, ENQUEUE_RESTORE);
 
 	task_rq_unlock(rq, tsk, &flags);
 }
@@ -8213,14 +8248,6 @@ static void cpu_cgroup_exit(struct cgroup_subsys_state *css,
 			    struct cgroup_subsys_state *old_css,
 			    struct task_struct *task)
 {
-	/*
-	 * cgroup_exit() is called in the copy_process() failure path.
-	 * Ignore this case since the task hasn't ran yet, this avoids
-	 * trying to poke a half freed task state from generic code.
-	 */
-	if (!(task->flags & PF_EXITING))
-		return;
-
 	sched_move_task(task);
 }
 

kernel/sched/cpudeadline.c

@@ -31,11 +31,6 @@ static inline int right_child(int i)
 	return (i << 1) + 2;
 }
 
-static inline int dl_time_before(u64 a, u64 b)
-{
-	return (s64)(a - b) < 0;
-}
-
 static void cpudl_exchange(struct cpudl *cp, int a, int b)
 {
 	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;

kernel/sched/cpudeadline.h

@@ -2,6 +2,7 @@
 #define _LINUX_CPUDL_H
 
 #include <linux/sched.h>
+#include <linux/sched/deadline.h>
 
 #define IDX_INVALID     -1
 

kernel/sched/fair.c

@@ -661,11 +661,12 @@ static unsigned long task_h_load(struct task_struct *p);
 
 /*
  * We choose a half-life close to 1 scheduling period.
- * Note: The tables below are dependent on this value.
+ * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are
+ * dependent on this value.
  */
 #define LOAD_AVG_PERIOD 32
 #define LOAD_AVG_MAX 47742 /* maximum possible load avg */
-#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */
+#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_AVG_MAX */
 
 /* Give new sched_entity start runnable values to heavy its load in infant time */
 void init_entity_runnable_average(struct sched_entity *se)
@@ -682,7 +683,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 	sa->load_avg = scale_load_down(se->load.weight);
 	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
 	sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
-	sa->util_sum = LOAD_AVG_MAX;
+	sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
@@ -2069,7 +2070,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	int local = !!(flags & TNF_FAULT_LOCAL);
 	int priv;
 
-	if (!numabalancing_enabled)
+	if (!static_branch_likely(&sched_numa_balancing))
 		return;
 
 	/* for example, ksmd faulting in a user's mm */
@@ -2157,7 +2158,7 @@ void task_numa_work(struct callback_head *work)
 	struct vm_area_struct *vma;
 	unsigned long start, end;
 	unsigned long nr_pte_updates = 0;
-	long pages;
+	long pages, virtpages;
 
 	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
 
@@ -2203,9 +2204,11 @@ void task_numa_work(struct callback_head *work)
 	start = mm->numa_scan_offset;
 	pages = sysctl_numa_balancing_scan_size;
 	pages <<= 20 - PAGE_SHIFT; /* MB in pages */
+	virtpages = pages * 8;	   /* Scan up to this much virtual space */
 	if (!pages)
 		return;
 
+
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, start);
 	if (!vma) {
@@ -2240,18 +2243,22 @@ void task_numa_work(struct callback_head *work)
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
 			end = min(end, vma->vm_end);
-			nr_pte_updates += change_prot_numa(vma, start, end);
+			nr_pte_updates = change_prot_numa(vma, start, end);
 
 			/*
-			 * Scan sysctl_numa_balancing_scan_size but ensure that
-			 * at least one PTE is updated so that unused virtual
-			 * address space is quickly skipped.
+			 * Try to scan sysctl_numa_balancing_size worth of
+			 * hpages that have at least one present PTE that
+			 * is not already pte-numa. If the VMA contains
+			 * areas that are unused or already full of prot_numa
+			 * PTEs, scan up to virtpages, to skip through those
+			 * areas faster.
 			 */
 			if (nr_pte_updates)
 				pages -= (end - start) >> PAGE_SHIFT;
+			virtpages -= (end - start) >> PAGE_SHIFT;
 
 			start = end;
-			if (pages <= 0)
+			if (pages <= 0 || virtpages <= 0)
 				goto out;
 
 			cond_resched();
@@ -2515,6 +2522,12 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
+#if (SCHED_LOAD_SHIFT - SCHED_LOAD_RESOLUTION) != 10 || SCHED_CAPACITY_SHIFT != 10
+#error "load tracking assumes 2^10 as unit"
+#endif
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
 /*
  * We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
@@ -2547,10 +2560,10 @@ static __always_inline int
 __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
-	u64 delta, periods;
+	u64 delta, scaled_delta, periods;
 	u32 contrib;
-	int delta_w, decayed = 0;
-	unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
+	unsigned int delta_w, scaled_delta_w, decayed = 0;
+	unsigned long scale_freq, scale_cpu;
 
 	delta = now - sa->last_update_time;
 	/*
@@ -2571,6 +2584,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		return 0;
 	sa->last_update_time = now;
 
+	scale_freq = arch_scale_freq_capacity(NULL, cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
 	/* delta_w is the amount already accumulated against our next period */
 	delta_w = sa->period_contrib;
 	if (delta + delta_w >= 1024) {
@@ -2585,13 +2601,16 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		 * period and accrue it.
 		 */
 		delta_w = 1024 - delta_w;
+		scaled_delta_w = cap_scale(delta_w, scale_freq);
 		if (weight) {
-			sa->load_sum += weight * delta_w;
-			if (cfs_rq)
-				cfs_rq->runnable_load_sum += weight * delta_w;
+			sa->load_sum += weight * scaled_delta_w;
+			if (cfs_rq) {
+				cfs_rq->runnable_load_sum +=
+						weight * scaled_delta_w;
+			}
 		}
 		if (running)
-			sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT;
+			sa->util_sum += scaled_delta_w * scale_cpu;
 
 		delta -= delta_w;
 
@@ -2608,23 +2627,25 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		contrib = __compute_runnable_contrib(periods);
+		contrib = cap_scale(contrib, scale_freq);
 		if (weight) {
 			sa->load_sum += weight * contrib;
 			if (cfs_rq)
 				cfs_rq->runnable_load_sum += weight * contrib;
 		}
 		if (running)
-			sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT;
+			sa->util_sum += contrib * scale_cpu;
 	}
 
 	/* Remainder of delta accrued against u_0` */
+	scaled_delta = cap_scale(delta, scale_freq);
 	if (weight) {
-		sa->load_sum += weight * delta;
+		sa->load_sum += weight * scaled_delta;
 		if (cfs_rq)
-			cfs_rq->runnable_load_sum += weight * delta;
+			cfs_rq->runnable_load_sum += weight * scaled_delta;
 	}
 	if (running)
-		sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT;
+		sa->util_sum += scaled_delta * scale_cpu;
 
 	sa->period_contrib += delta;
 
@@ -2634,7 +2655,7 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 			cfs_rq->runnable_load_avg =
 				div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
 		}
-		sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX;
+		sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
 	}
 
 	return decayed;
@@ -2677,8 +2698,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
 		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum -
-			((r * LOAD_AVG_MAX) >> SCHED_LOAD_SHIFT), 0);
+		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
 	}
 
 	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2696,33 +2716,70 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 static inline void update_load_avg(struct sched_entity *se, int update_tg)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	int cpu = cpu_of(rq_of(cfs_rq));
 	u64 now = cfs_rq_clock_task(cfs_rq);
+	int cpu = cpu_of(rq_of(cfs_rq));
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
 	 * track group sched_entity load average for task_h_load calc in migration
 	 */
 	__update_load_avg(now, cpu, &se->avg,
-		se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
+			  se->on_rq * scale_load_down(se->load.weight),
+			  cfs_rq->curr == se, NULL);
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
 }
 
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (!sched_feat(ATTACH_AGE_LOAD))
+		goto skip_aging;
+
+	/*
+	 * If we got migrated (either between CPUs or between cgroups) we'll
+	 * have aged the average right before clearing @last_update_time.
+	 */
+	if (se->avg.last_update_time) {
+		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+				  &se->avg, 0, 0, NULL);
+
+		/*
+		 * XXX: we could have just aged the entire load away if we've been
+		 * absent from the fair class for too long.
+		 */
+	}
+
+skip_aging:
+	se->avg.last_update_time = cfs_rq->avg.last_update_time;
+	cfs_rq->avg.load_avg += se->avg.load_avg;
+	cfs_rq->avg.load_sum += se->avg.load_sum;
+	cfs_rq->avg.util_avg += se->avg.util_avg;
+	cfs_rq->avg.util_sum += se->avg.util_sum;
+}
+
+static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
+			  cfs_rq->curr == se, NULL);
+
+	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
+	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
+	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
+	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+}
+
 /* Add the load generated by se into cfs_rq's load average */
 static inline void
 enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct sched_avg *sa = &se->avg;
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int migrated = 0, decayed;
+	int migrated, decayed;
 
-	if (sa->last_update_time == 0) {
-		sa->last_update_time = now;
-		migrated = 1;
-	}
-	else {
+	migrated = !sa->last_update_time;
+	if (!migrated) {
 		__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
 			se->on_rq * scale_load_down(se->load.weight),
 			cfs_rq->curr == se, NULL);
@@ -2733,12 +2790,8 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->runnable_load_avg += sa->load_avg;
 	cfs_rq->runnable_load_sum += sa->load_sum;
 
-	if (migrated) {
-		cfs_rq->avg.load_avg += sa->load_avg;
-		cfs_rq->avg.load_sum += sa->load_sum;
-		cfs_rq->avg.util_avg += sa->util_avg;
-		cfs_rq->avg.util_sum += sa->util_sum;
-	}
+	if (migrated)
+		attach_entity_load_avg(cfs_rq, se);
 
 	if (decayed || migrated)
 		update_tg_load_avg(cfs_rq, 0);
@@ -2753,7 +2806,7 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->runnable_load_avg =
 		max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
 	cfs_rq->runnable_load_sum =
-		max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
+		max_t(s64,  cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
 }
 
 /*
@@ -2821,6 +2874,11 @@ static inline void
 dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
 
+static inline void
+attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+static inline void
+detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+
 static inline int idle_balance(struct rq *rq)
 {
 	return 0;
@@ -4817,32 +4875,39 @@ static int select_idle_sibling(struct task_struct *p, int target)
 done:
 	return target;
 }
+
 /*
- * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * cpu_util returns the amount of capacity of a CPU that is used by CFS
  * tasks. The unit of the return value must be the one of capacity so we can
- * compare the usage with the capacity of the CPU that is available for CFS
- * task (ie cpu_capacity).
- * cfs.avg.util_avg is the sum of running time of runnable tasks on a
- * CPU. It represents the amount of utilization of a CPU in the range
- * [0..SCHED_LOAD_SCALE].  The usage of a CPU can't be higher than the full
- * capacity of the CPU because it's about the running time on this CPU.
- * Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE
- * because of unfortunate rounding in util_avg or just
- * after migrating tasks until the average stabilizes with the new running
- * time. So we need to check that the usage stays into the range
- * [0..cpu_capacity_orig] and cap if necessary.
- * Without capping the usage, a group could be seen as overloaded (CPU0 usage
- * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ * compare the utilization with the capacity of the CPU that is available for
+ * CFS task (ie cpu_capacity).
+ *
+ * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
+ * recent utilization of currently non-runnable tasks on a CPU. It represents
+ * the amount of utilization of a CPU in the range [0..capacity_orig] where
+ * capacity_orig is the cpu_capacity available at the highest frequency
+ * (arch_scale_freq_capacity()).
+ * The utilization of a CPU converges towards a sum equal to or less than the
+ * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
+ * the running time on this CPU scaled by capacity_curr.
+ *
+ * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
+ * higher than capacity_orig because of unfortunate rounding in
+ * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
+ * the average stabilizes with the new running time. We need to check that the
+ * utilization stays within the range of [0..capacity_orig] and cap it if
+ * necessary. Without utilization capping, a group could be seen as overloaded
+ * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
+ * available capacity. We allow utilization to overshoot capacity_curr (but not
+ * capacity_orig) as it useful for predicting the capacity required after task
+ * migrations (scheduler-driven DVFS).
  */
-static int get_cpu_usage(int cpu)
+static int cpu_util(int cpu)
 {
-	unsigned long usage = cpu_rq(cpu)->cfs.avg.util_avg;
+	unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
 	unsigned long capacity = capacity_orig_of(cpu);
 
-	if (usage >= SCHED_LOAD_SCALE)
-		return capacity;
-
-	return (usage * capacity) >> SCHED_LOAD_SHIFT;
+	return (util >= capacity) ? capacity : util;
 }
 
 /*
@@ -4945,7 +5010,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
  * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
  * other assumptions, including the state of rq->lock, should be made.
  */
-static void migrate_task_rq_fair(struct task_struct *p, int next_cpu)
+static void migrate_task_rq_fair(struct task_struct *p)
 {
 	/*
 	 * We are supposed to update the task to "current" time, then its up to date
@@ -5525,10 +5590,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	unsigned long src_faults, dst_faults;
 	int src_nid, dst_nid;
 
-	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+	if (!static_branch_likely(&sched_numa_balancing))
 		return -1;
 
-	if (!sched_feat(NUMA))
+	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
 		return -1;
 
 	src_nid = cpu_to_node(env->src_cpu);
@@ -5934,7 +5999,7 @@ struct sg_lb_stats {
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long load_per_task;
 	unsigned long group_capacity;
-	unsigned long group_usage; /* Total usage of the group */
+	unsigned long group_util; /* Total utilization of the group */
 	unsigned int sum_nr_running; /* Nr tasks running in the group */
 	unsigned int idle_cpus;
 	unsigned int group_weight;
@@ -6010,19 +6075,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
-	if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
-		return sd->smt_gain / sd->span_weight;
-
-	return SCHED_CAPACITY_SCALE;
-}
-
-unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
-	return default_scale_cpu_capacity(sd, cpu);
-}
-
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -6052,16 +6104,9 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = SCHED_CAPACITY_SCALE;
+	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
 	struct sched_group *sdg = sd->groups;
 
-	if (sched_feat(ARCH_CAPACITY))
-		capacity *= arch_scale_cpu_capacity(sd, cpu);
-	else
-		capacity *= default_scale_cpu_capacity(sd, cpu);
-
-	capacity >>= SCHED_CAPACITY_SHIFT;
-
 	cpu_rq(cpu)->cpu_capacity_orig = capacity;
 
 	capacity *= scale_rt_capacity(cpu);
@@ -6187,8 +6232,8 @@ static inline int sg_imbalanced(struct sched_group *group)
  * group_has_capacity returns true if the group has spare capacity that could
  * be used by some tasks.
  * We consider that a group has spare capacity if the  * number of task is
- * smaller than the number of CPUs or if the usage is lower than the available
- * capacity for CFS tasks.
+ * smaller than the number of CPUs or if the utilization is lower than the
+ * available capacity for CFS tasks.
  * For the latter, we use a threshold to stabilize the state, to take into
  * account the variance of the tasks' load and to return true if the available
  * capacity in meaningful for the load balancer.
@@ -6202,7 +6247,7 @@ group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
 		return true;
 
 	if ((sgs->group_capacity * 100) >
-			(sgs->group_usage * env->sd->imbalance_pct))
+			(sgs->group_util * env->sd->imbalance_pct))
 		return true;
 
 	return false;
@@ -6223,15 +6268,15 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
 		return false;
 
 	if ((sgs->group_capacity * 100) <
-			(sgs->group_usage * env->sd->imbalance_pct))
+			(sgs->group_util * env->sd->imbalance_pct))
 		return true;
 
 	return false;
 }
 
-static enum group_type group_classify(struct lb_env *env,
-		struct sched_group *group,
-		struct sg_lb_stats *sgs)
+static inline enum
+group_type group_classify(struct sched_group *group,
+			  struct sg_lb_stats *sgs)
 {
 	if (sgs->group_no_capacity)
 		return group_overloaded;
@@ -6271,7 +6316,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->group_usage += get_cpu_usage(i);
+		sgs->group_util += cpu_util(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
 		if (rq->nr_running > 1)
@@ -6296,7 +6341,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_weight = group->group_weight;
 
 	sgs->group_no_capacity = group_is_overloaded(env, sgs);
-	sgs->group_type = group_classify(env, group, sgs);
+	sgs->group_type = group_classify(group, sgs);
 }
 
 /**
@@ -6430,7 +6475,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		    group_has_capacity(env, &sds->local_stat) &&
 		    (sgs->sum_nr_running > 1)) {
 			sgs->group_no_capacity = 1;
-			sgs->group_type = group_overloaded;
+			sgs->group_type = group_classify(sg, sgs);
 		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
@@ -7610,8 +7655,22 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 	 * When the cpu is attached to null domain for ex, it will not be
 	 * updated.
 	 */
-	if (likely(update_next_balance))
+	if (likely(update_next_balance)) {
 		rq->next_balance = next_balance;
+
+#ifdef CONFIG_NO_HZ_COMMON
+		/*
+		 * If this CPU has been elected to perform the nohz idle
+		 * balance. Other idle CPUs have already rebalanced with
+		 * nohz_idle_balance() and nohz.next_balance has been
+		 * updated accordingly. This CPU is now running the idle load
+		 * balance for itself and we need to update the
+		 * nohz.next_balance accordingly.
+		 */
+		if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance))
+			nohz.next_balance = rq->next_balance;
+#endif
+	}
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -7624,6 +7683,9 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 	int this_cpu = this_rq->cpu;
 	struct rq *rq;
 	int balance_cpu;
+	/* Earliest time when we have to do rebalance again */
+	unsigned long next_balance = jiffies + 60*HZ;
+	int update_next_balance = 0;
 
 	if (idle != CPU_IDLE ||
 	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
@@ -7655,10 +7717,19 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 			rebalance_domains(rq, CPU_IDLE);
 		}
 
-		if (time_after(this_rq->next_balance, rq->next_balance))
-			this_rq->next_balance = rq->next_balance;
+		if (time_after(next_balance, rq->next_balance)) {
+			next_balance = rq->next_balance;
+			update_next_balance = 1;
+		}
 	}
-	nohz.next_balance = this_rq->next_balance;
+
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
 end:
 	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
 }
@@ -7811,7 +7882,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 		entity_tick(cfs_rq, se, queued);
 	}
 
-	if (numabalancing_enabled)
+	if (static_branch_unlikely(&sched_numa_balancing))
 		task_tick_numa(rq, curr);
 }
 
@@ -7887,21 +7958,39 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 		check_preempt_curr(rq, p, 0);
 }
 
-static void switched_from_fair(struct rq *rq, struct task_struct *p)
+static inline bool vruntime_normalized(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when it's
-	 * switched back to the fair class the enqueue_entity(.flags=0) will
-	 * do the right thing.
+	 * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
+	 * the dequeue_entity(.flags=0) will already have normalized the
+	 * vruntime.
+	 */
+	if (p->on_rq)
+		return true;
+
+	/*
+	 * When !on_rq, vruntime of the task has usually NOT been normalized.
+	 * But there are some cases where it has already been normalized:
 	 *
-	 * If it's queued, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it's !queued, then only when
-	 * the task is sleeping will it still have non-normalized vruntime.
+	 * - A forked child which is waiting for being woken up by
+	 *   wake_up_new_task().
+	 * - A task which has been woken up by try_to_wake_up() and
+	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 */
-	if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) {
+	if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+		return true;
+
+	return false;
+}
+
+static void detach_task_cfs_rq(struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	if (!vruntime_normalized(p)) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
@@ -7910,28 +7999,14 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
 
-#ifdef CONFIG_SMP
 	/* Catch up with the cfs_rq and remove our load when we leave */
-	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq), &se->avg,
-		se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
-
-	cfs_rq->avg.load_avg =
-		max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum =
-		max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg =
-		max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum =
-		max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
-#endif
+	detach_entity_load_avg(cfs_rq, se);
 }
 
-/*
- * We switched to the sched_fair class.
- */
-static void switched_to_fair(struct rq *rq, struct task_struct *p)
+static void attach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
@@ -7941,31 +8016,33 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
 #endif
 
-	if (!task_on_rq_queued(p)) {
+	/* Synchronize task with its cfs_rq */
+	attach_entity_load_avg(cfs_rq, se);
 
+	if (!vruntime_normalized(p))
+		se->vruntime += cfs_rq->min_vruntime;
+}
+
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+	detach_task_cfs_rq(p);
+}
+
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
+{
+	attach_task_cfs_rq(p);
+
+	if (task_on_rq_queued(p)) {
 		/*
-		 * Ensure the task has a non-normalized vruntime when it is switched
-		 * back to the fair class with !queued, so that enqueue_entity() at
-		 * wake-up time will do the right thing.
-		 *
-		 * If it's queued, then the enqueue_entity(.flags=0) makes the task
-		 * has non-normalized vruntime, if it's !queued, then it still has
-		 * normalized vruntime.
+		 * We were most likely switched from sched_rt, so
+		 * kick off the schedule if running, otherwise just see
+		 * if we can still preempt the current task.
 		 */
-		if (p->state != TASK_RUNNING)
-			se->vruntime += cfs_rq_of(se)->min_vruntime;
-		return;
+		if (rq->curr == p)
+			resched_curr(rq);
+		else
+			check_preempt_curr(rq, p, 0);
 	}
-
-	/*
-	 * We were most likely switched from sched_rt, so
-	 * kick off the schedule if running, otherwise just see
-	 * if we can still preempt the current task.
-	 */
-	if (rq->curr == p)
-		resched_curr(rq);
-	else
-		check_preempt_curr(rq, p, 0);
 }
 
 /* Account for a task changing its policy or group.
@@ -8000,56 +8077,16 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_move_group_fair(struct task_struct *p, int queued)
+static void task_move_group_fair(struct task_struct *p)
 {
-	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq;
-
-	/*
-	 * If the task was not on the rq at the time of this cgroup movement
-	 * it must have been asleep, sleeping tasks keep their ->vruntime
-	 * absolute on their old rq until wakeup (needed for the fair sleeper
-	 * bonus in place_entity()).
-	 *
-	 * If it was on the rq, we've just 'preempted' it, which does convert
-	 * ->vruntime to a relative base.
-	 *
-	 * Make sure both cases convert their relative position when migrating
-	 * to another cgroup's rq. This does somewhat interfere with the
-	 * fair sleeper stuff for the first placement, but who cares.
-	 */
-	/*
-	 * When !queued, vruntime of the task has usually NOT been normalized.
-	 * But there are some cases where it has already been normalized:
-	 *
-	 * - Moving a forked child which is waiting for being woken up by
-	 *   wake_up_new_task().
-	 * - Moving a task which has been woken up by try_to_wake_up() and
-	 *   waiting for actually being woken up by sched_ttwu_pending().
-	 *
-	 * To prevent boost or penalty in the new cfs_rq caused by delta
-	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
-	 */
-	if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING))
-		queued = 1;
-
-	if (!queued)
-		se->vruntime -= cfs_rq_of(se)->min_vruntime;
+	detach_task_cfs_rq(p);
 	set_task_rq(p, task_cpu(p));
-	se->depth = se->parent ? se->parent->depth + 1 : 0;
-	if (!queued) {
-		cfs_rq = cfs_rq_of(se);
-		se->vruntime += cfs_rq->min_vruntime;
 
 #ifdef CONFIG_SMP
-		/* Virtually synchronize task with its new cfs_rq */
-		p->se.avg.last_update_time = cfs_rq->avg.last_update_time;
-		cfs_rq->avg.load_avg += p->se.avg.load_avg;
-		cfs_rq->avg.load_sum += p->se.avg.load_sum;
-		cfs_rq->avg.util_avg += p->se.avg.util_avg;
-		cfs_rq->avg.util_sum += p->se.avg.util_sum;
+	/* Tell se's cfs_rq has been changed -- migrated */
+	p->se.avg.last_update_time = 0;
 #endif
-	}
+	attach_task_cfs_rq(p);
 }
 
 void free_fair_sched_group(struct task_group *tg)

kernel/sched/features.h

@@ -36,11 +36,6 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true)
  */
 SCHED_FEAT(WAKEUP_PREEMPTION, true)
 
-/*
- * Use arch dependent cpu capacity functions
- */
-SCHED_FEAT(ARCH_CAPACITY, true)
-
 SCHED_FEAT(HRTICK, false)
 SCHED_FEAT(DOUBLE_TICK, false)
 SCHED_FEAT(LB_BIAS, true)
@@ -72,19 +67,5 @@ SCHED_FEAT(RT_PUSH_IPI, true)
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
+SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
-/*
- * Apply the automatic NUMA scheduling policy. Enabled automatically
- * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=
- */
-#ifdef CONFIG_NUMA_BALANCING
-
-/*
- * NUMA will favor moving tasks towards nodes where a higher number of
- * hinting faults are recorded during active load balancing. It will
- * resist moving tasks towards nodes where a lower number of hinting
- * faults have been recorded.
- */
-SCHED_FEAT(NUMA,	true)
-#endif

kernel/sched/rt.c

@@ -635,11 +635,11 @@ bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.
  */
-static int do_balance_runtime(struct rt_rq *rt_rq)
+static void do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 	struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
-	int i, weight, more = 0;
+	int i, weight;
 	u64 rt_period;
 
 	weight = cpumask_weight(rd->span);
@@ -673,7 +673,6 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 				diff = rt_period - rt_rq->rt_runtime;
 			iter->rt_runtime -= diff;
 			rt_rq->rt_runtime += diff;
-			more = 1;
 			if (rt_rq->rt_runtime == rt_period) {
 				raw_spin_unlock(&iter->rt_runtime_lock);
 				break;
@@ -683,8 +682,6 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 		raw_spin_unlock(&iter->rt_runtime_lock);
 	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
-
-	return more;
 }
 
 /*
@@ -796,26 +793,19 @@ static void __enable_runtime(struct rq *rq)
 	}
 }
 
-static int balance_runtime(struct rt_rq *rt_rq)
+static void balance_runtime(struct rt_rq *rt_rq)
 {
-	int more = 0;
-
 	if (!sched_feat(RT_RUNTIME_SHARE))
-		return more;
+		return;
 
 	if (rt_rq->rt_time > rt_rq->rt_runtime) {
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-		more = do_balance_runtime(rt_rq);
+		do_balance_runtime(rt_rq);
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
 	}
-
-	return more;
 }
 #else /* !CONFIG_SMP */
-static inline int balance_runtime(struct rt_rq *rt_rq)
-{
-	return 0;
-}
+static inline void balance_runtime(struct rt_rq *rt_rq) {}
 #endif /* CONFIG_SMP */
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)

kernel/sched/sched.h

@@ -84,6 +84,10 @@ static inline void update_cpu_load_active(struct rq *this_rq) { }
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+static inline int idle_policy(int policy)
+{
+	return policy == SCHED_IDLE;
+}
 static inline int fair_policy(int policy)
 {
 	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
@@ -98,6 +102,11 @@ static inline int dl_policy(int policy)
 {
 	return policy == SCHED_DEADLINE;
 }
+static inline bool valid_policy(int policy)
+{
+	return idle_policy(policy) || fair_policy(policy) ||
+		rt_policy(policy) || dl_policy(policy);
+}
 
 static inline int task_has_rt_policy(struct task_struct *p)
 {
@@ -109,11 +118,6 @@ static inline int task_has_dl_policy(struct task_struct *p)
 	return dl_policy(p->policy);
 }
 
-static inline bool dl_time_before(u64 a, u64 b)
-{
-	return (s64)(a - b) < 0;
-}
-
 /*
  * Tells if entity @a should preempt entity @b.
  */
@@ -1003,17 +1007,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
-#ifdef CONFIG_NUMA_BALANCING
-#define sched_feat_numa(x) sched_feat(x)
-#ifdef CONFIG_SCHED_DEBUG
-#define numabalancing_enabled sched_feat_numa(NUMA)
-#else
-extern bool numabalancing_enabled;
-#endif /* CONFIG_SCHED_DEBUG */
-#else
-#define sched_feat_numa(x) (0)
-#define numabalancing_enabled (0)
-#endif /* CONFIG_NUMA_BALANCING */
+extern struct static_key_false sched_numa_balancing;
 
 static inline u64 global_rt_period(void)
 {
@@ -1157,16 +1151,18 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#define ENQUEUE_WAKEUP		1
-#define ENQUEUE_HEAD		2
+#define ENQUEUE_WAKEUP		0x01
+#define ENQUEUE_HEAD		0x02
 #ifdef CONFIG_SMP
-#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
+#define ENQUEUE_WAKING		0x04	/* sched_class::task_waking was called */
 #else
-#define ENQUEUE_WAKING		0
+#define ENQUEUE_WAKING		0x00
 #endif
-#define ENQUEUE_REPLENISH	8
+#define ENQUEUE_REPLENISH	0x08
+#define ENQUEUE_RESTORE	0x10
 
-#define DEQUEUE_SLEEP		1
+#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SAVE		0x02
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -1194,7 +1190,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
-	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
+	void (*migrate_task_rq)(struct task_struct *p);
 
 	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1227,7 +1223,7 @@ struct sched_class {
 	void (*update_curr) (struct rq *rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*task_move_group) (struct task_struct *p, int on_rq);
+	void (*task_move_group) (struct task_struct *p);
 #endif
 };
 
@@ -1405,6 +1401,17 @@ unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
 }
 #endif
 
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+	if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
+		return sd->smt_gain / sd->span_weight;
+
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
 static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 {
 	rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));

kernel/smpboot.c

@@ -222,9 +222,8 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
 {
 	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
 
-	if (ht->pre_unpark)
-		ht->pre_unpark(cpu);
-	kthread_unpark(tsk);
+	if (!ht->selfparking)
+		kthread_unpark(tsk);
 }
 
 void smpboot_unpark_threads(unsigned int cpu)

kernel/stop_machine.c

@@ -73,21 +73,24 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
 	}
 }
 
+static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
+					struct cpu_stop_work *work)
+{
+	list_add_tail(&work->list, &stopper->works);
+	wake_up_process(stopper->thread);
+}
+
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-
 	unsigned long flags;
 
 	spin_lock_irqsave(&stopper->lock, flags);
-
-	if (stopper->enabled) {
-		list_add_tail(&work->list, &stopper->works);
-		wake_up_process(stopper->thread);
-	} else
+	if (stopper->enabled)
+		__cpu_stop_queue_work(stopper, work);
+	else
 		cpu_stop_signal_done(work->done, false);
-
 	spin_unlock_irqrestore(&stopper->lock, flags);
 }
 
@@ -213,6 +216,31 @@ static int multi_cpu_stop(void *data)
 	return err;
 }
 
+static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
+				    int cpu2, struct cpu_stop_work *work2)
+{
+	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
+	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+	int err;
+
+	lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
+	spin_lock_irq(&stopper1->lock);
+	spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+
+	err = -ENOENT;
+	if (!stopper1->enabled || !stopper2->enabled)
+		goto unlock;
+
+	err = 0;
+	__cpu_stop_queue_work(stopper1, work1);
+	__cpu_stop_queue_work(stopper2, work2);
+unlock:
+	spin_unlock(&stopper2->lock);
+	spin_unlock_irq(&stopper1->lock);
+	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
+
+	return err;
+}
 /**
  * stop_two_cpus - stops two cpus
  * @cpu1: the cpu to stop
@@ -247,24 +275,13 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	cpu_stop_init_done(&done, 2);
 	set_state(&msdata, MULTI_STOP_PREPARE);
 
-	/*
-	 * If we observe both CPUs active we know _cpu_down() cannot yet have
-	 * queued its stop_machine works and therefore ours will get executed
-	 * first. Or its not either one of our CPUs that's getting unplugged,
-	 * in which case we don't care.
-	 *
-	 * This relies on the stopper workqueues to be FIFO.
-	 */
-	if (!cpu_active(cpu1) || !cpu_active(cpu2)) {
+	if (cpu1 > cpu2)
+		swap(cpu1, cpu2);
+	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) {
 		preempt_enable();
 		return -ENOENT;
 	}
 
-	lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
-	cpu_stop_queue_work(cpu1, &work1);
-	cpu_stop_queue_work(cpu2, &work2);
-	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
-
 	preempt_enable();
 
 	wait_for_completion(&done.completion);
@@ -452,6 +469,18 @@ static void cpu_stopper_thread(unsigned int cpu)
 	}
 }
 
+void stop_machine_park(int cpu)
+{
+	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	/*
+	 * Lockless. cpu_stopper_thread() will take stopper->lock and flush
+	 * the pending works before it parks, until then it is fine to queue
+	 * the new works.
+	 */
+	stopper->enabled = false;
+	kthread_park(stopper->thread);
+}
+
 extern void sched_set_stop_task(int cpu, struct task_struct *stop);
 
 static void cpu_stop_create(unsigned int cpu)
@@ -462,26 +491,16 @@ static void cpu_stop_create(unsigned int cpu)
 static void cpu_stop_park(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-	struct cpu_stop_work *work, *tmp;
-	unsigned long flags;
 
-	/* drain remaining works */
-	spin_lock_irqsave(&stopper->lock, flags);
-	list_for_each_entry_safe(work, tmp, &stopper->works, list) {
-		list_del_init(&work->list);
-		cpu_stop_signal_done(work->done, false);
-	}
-	stopper->enabled = false;
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	WARN_ON(!list_empty(&stopper->works));
 }
 
-static void cpu_stop_unpark(unsigned int cpu)
+void stop_machine_unpark(int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-	spin_lock_irq(&stopper->lock);
 	stopper->enabled = true;
-	spin_unlock_irq(&stopper->lock);
+	kthread_unpark(stopper->thread);
 }
 
 static struct smp_hotplug_thread cpu_stop_threads = {
@@ -490,9 +509,7 @@ static struct smp_hotplug_thread cpu_stop_threads = {
 	.thread_fn		= cpu_stopper_thread,
 	.thread_comm		= "migration/%u",
 	.create			= cpu_stop_create,
-	.setup			= cpu_stop_unpark,
 	.park			= cpu_stop_park,
-	.pre_unpark		= cpu_stop_unpark,
 	.selfparking		= true,
 };
 
@@ -508,6 +525,7 @@ static int __init cpu_stop_init(void)
 	}
 
 	BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads));
+	stop_machine_unpark(raw_smp_processor_id());
 	stop_machine_initialized = true;
 	return 0;
 }

kernel/trace/ftrace.c

@@ -5697,7 +5697,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 }
 
 static void
-ftrace_graph_probe_sched_switch(void *ignore,
+ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 			struct task_struct *prev, struct task_struct *next)
 {
 	unsigned long long timestamp;

kernel/trace/trace_sched_switch.c

@@ -16,7 +16,8 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 
 static void
-probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, bool preempt,
+		   struct task_struct *prev, struct task_struct *next)
 {
 	if (unlikely(!sched_ref))
 		return;

kernel/trace/trace_sched_wakeup.c

@@ -420,7 +420,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void notrace
-probe_wakeup_sched_switch(void *ignore,
+probe_wakeup_sched_switch(void *ignore, bool preempt,
 			  struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;