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

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

   - tickless load average calculation enhancements (Byungchul Park)

   - vtime handling enhancements (Frederic Weisbecker)

   - scalability improvement via properly aligning a key structure field
     (Jiri Olsa)

   - various stop_machine() fixes (Oleg Nesterov)

   - sched/numa enhancement (Rik van Riel)

   - various fixes and improvements (Andi Kleen, Dietmar Eggemann,
     Geliang Tang, Hiroshi Shimamoto, Joonwoo Park, Peter Zijlstra,
     Waiman Long, Wanpeng Li, Yuyang Du)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  sched/fair: Fix new task's load avg removed from source CPU in wake_up_new_task()
  sched/core: Move sched_entity::avg into separate cache line
  x86/fpu: Properly align size in CHECK_MEMBER_AT_END_OF() macro
  sched/deadline: Fix the earliest_dl.next logic
  sched/fair: Disable the task group load_avg update for the root_task_group
  sched/fair: Move the cache-hot 'load_avg' variable into its own cacheline
  sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats()
  sched/core: Move the sched_to_prio[] arrays out of line
  sched/cputime: Convert vtime_seqlock to seqcount
  sched/cputime: Introduce vtime accounting check for readers
  sched/cputime: Rename vtime_accounting_enabled() to vtime_accounting_cpu_enabled()
  sched/cputime: Correctly handle task guest time on housekeepers
  sched/cputime: Clarify vtime symbols and document them
  sched/cputime: Remove extra cost in task_cputime()
  sched/fair: Make it possible to account fair load avg consistently
  sched/fair: Modify the comment about lock assumptions in migrate_task_rq_fair()
  stop_machine: Clean up the usage of the preemption counter in cpu_stopper_thread()
  stop_machine: Shift the 'done != NULL' check from cpu_stop_signal_done() to callers
  stop_machine: Kill cpu_stop_done->executed
  stop_machine: Change __stop_cpus() to rely on cpu_stop_queue_work()
  ...

arch/x86/kernel/fpu/init.c

@@ -143,9 +143,18 @@ static void __init fpu__init_system_generic(void)
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
-/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+/* Get alignment of the TYPE. */
+#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
+
+/*
+ * Enforce that 'MEMBER' is the last field of 'TYPE'.
+ *
+ * Align the computed size with alignment of the TYPE,
+ * because that's how C aligns structs.
+ */
 #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
-	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
+	BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \
+					   TYPE_ALIGN(TYPE)))
 
 /*
  * We append the 'struct fpu' to the task_struct:

include/linux/context_tracking.h

@@ -86,7 +86,7 @@ static inline void context_tracking_init(void) { }
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 static inline void guest_enter(void)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_guest_enter(current);
 	else
 		current->flags |= PF_VCPU;
@@ -100,7 +100,7 @@ static inline void guest_exit(void)
 	if (context_tracking_is_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;

include/linux/init_task.h

@@ -150,7 +150,7 @@ extern struct task_group root_task_group;
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
-	.vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock),	\
+	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
 	.vtime_snap = 0,				\
 	.vtime_snap_whence = VTIME_SYS,
 #else

include/linux/sched.h

@@ -177,9 +177,9 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 extern void calc_global_load(unsigned long ticks);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void update_cpu_load_nohz(void);
+extern void update_cpu_load_nohz(int active);
 #else
-static inline void update_cpu_load_nohz(void) { }
+static inline void update_cpu_load_nohz(int active) { }
 #endif
 
 extern unsigned long get_parent_ip(unsigned long addr);
@@ -1268,8 +1268,13 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_SMP
-	/* Per entity load average tracking */
-	struct sched_avg	avg;
+	/*
+	 * Per entity load average tracking.
+	 *
+	 * Put into separate cache line so it does not
+	 * collide with read-mostly values above.
+	 */
+	struct sched_avg	avg ____cacheline_aligned_in_smp;
 #endif
 };
 
@@ -1520,11 +1525,14 @@ struct task_struct {
 	cputime_t gtime;
 	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqlock_t vtime_seqlock;
+	seqcount_t vtime_seqcount;
 	unsigned long long vtime_snap;
 	enum {
-		VTIME_SLEEPING = 0,
+		/* Task is sleeping or running in a CPU with VTIME inactive */
+		VTIME_INACTIVE = 0,
+		/* Task runs in userspace in a CPU with VTIME active */
 		VTIME_USER,
+		/* Task runs in kernelspace in a CPU with VTIME active */
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif

include/linux/stop_machine.h

@@ -29,7 +29,7 @@ struct cpu_stop_work {
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
-void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+bool 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);
@@ -65,7 +65,7 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work)
 	preempt_enable();
 }
 
-static inline void stop_one_cpu_nowait(unsigned int cpu,
+static inline bool stop_one_cpu_nowait(unsigned int cpu,
 				       cpu_stop_fn_t fn, void *arg,
 				       struct cpu_stop_work *work_buf)
 {
@@ -74,7 +74,10 @@ static inline void stop_one_cpu_nowait(unsigned int cpu,
 		work_buf->fn = fn;
 		work_buf->arg = arg;
 		schedule_work(&work_buf->work);
+		return true;
 	}
+
+	return false;
 }
 
 static inline int stop_cpus(const struct cpumask *cpumask,

include/linux/vtime.h

@@ -10,16 +10,27 @@
 struct task_struct;
 
 /*
- * vtime_accounting_enabled() definitions/declarations
+ * vtime_accounting_cpu_enabled() definitions/declarations
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-static inline bool vtime_accounting_enabled(void) { return true; }
+static inline bool vtime_accounting_cpu_enabled(void) { return true; }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+/*
+ * Checks if vtime is enabled on some CPU. Cputime readers want to be careful
+ * in that case and compute the tickless cputime.
+ * For now vtime state is tied to context tracking. We might want to decouple
+ * those later if necessary.
+ */
 static inline bool vtime_accounting_enabled(void)
 {
-	if (context_tracking_is_enabled()) {
+	return context_tracking_is_enabled();
+}
+
+static inline bool vtime_accounting_cpu_enabled(void)
+{
+	if (vtime_accounting_enabled()) {
 		if (context_tracking_cpu_is_enabled())
 			return true;
 	}
@@ -29,7 +40,7 @@ static inline bool vtime_accounting_enabled(void)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-static inline bool vtime_accounting_enabled(void) { return false; }
+static inline bool vtime_accounting_cpu_enabled(void) { return false; }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 
@@ -44,7 +55,7 @@ extern void vtime_task_switch(struct task_struct *prev);
 extern void vtime_common_task_switch(struct task_struct *prev);
 static inline void vtime_task_switch(struct task_struct *prev)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_common_task_switch(prev);
 }
 #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */
@@ -59,7 +70,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk);
 extern void vtime_common_account_irq_enter(struct task_struct *tsk);
 static inline void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_common_account_irq_enter(tsk);
 }
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -78,7 +89,7 @@ extern void vtime_gen_account_irq_exit(struct task_struct *tsk);
 
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_gen_account_irq_exit(tsk);
 }
 

include/linux/wait.h

@@ -102,6 +102,36 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
 	q->func		= func;
 }
 
+/**
+ * waitqueue_active -- locklessly test for waiters on the queue
+ * @q: the waitqueue to test for waiters
+ *
+ * returns true if the wait list is not empty
+ *
+ * NOTE: this function is lockless and requires care, incorrect usage _will_
+ * lead to sporadic and non-obvious failure.
+ *
+ * Use either while holding wait_queue_head_t::lock or when used for wakeups
+ * with an extra smp_mb() like:
+ *
+ *      CPU0 - waker                    CPU1 - waiter
+ *
+ *                                      for (;;) {
+ *      @cond = true;                     prepare_to_wait(&wq, &wait, state);
+ *      smp_mb();                         // smp_mb() from set_current_state()
+ *      if (waitqueue_active(wq))         if (@cond)
+ *        wake_up(wq);                      break;
+ *                                        schedule();
+ *                                      }
+ *                                      finish_wait(&wq, &wait);
+ *
+ * Because without the explicit smp_mb() it's possible for the
+ * waitqueue_active() load to get hoisted over the @cond store such that we'll
+ * observe an empty wait list while the waiter might not observe @cond.
+ *
+ * Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
+ * which (when the lock is uncontended) are of roughly equal cost.
+ */
 static inline int waitqueue_active(wait_queue_head_t *q)
 {
 	return !list_empty(&q->task_list);

kernel/fork.c

@@ -1349,9 +1349,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	prev_cputime_init(&p->prev_cputime);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqlock_init(&p->vtime_seqlock);
+	seqcount_init(&p->vtime_seqcount);
 	p->vtime_snap = 0;
-	p->vtime_snap_whence = VTIME_SLEEPING;
+	p->vtime_snap_whence = VTIME_INACTIVE;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)

kernel/sched/auto_group.c

@@ -212,7 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 	ag = autogroup_task_get(p);
 
 	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
+	err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]);
 	if (!err)
 		ag->nice = nice;
 	up_write(&ag->lock);

kernel/sched/core.c

@@ -731,7 +731,7 @@ bool sched_can_stop_tick(void)
 	if (current->policy == SCHED_RR) {
 		struct sched_rt_entity *rt_se = &current->rt;
 
-		return rt_se->run_list.prev == rt_se->run_list.next;
+		return list_is_singular(&rt_se->run_list);
 	}
 
 	/*
@@ -823,8 +823,8 @@ static void set_load_weight(struct task_struct *p)
 		return;
 	}
 
-	load->weight = scale_load(prio_to_weight[prio]);
-	load->inv_weight = prio_to_wmult[prio];
+	load->weight = scale_load(sched_prio_to_weight[prio]);
+	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1071,8 +1071,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
 {
 	lockdep_assert_held(&rq->lock);
 
-	dequeue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	dequeue_task(rq, p, 0);
 	set_task_cpu(p, new_cpu);
 	raw_spin_unlock(&rq->lock);
 
@@ -1080,8 +1080,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
 
 	raw_spin_lock(&rq->lock);
 	BUG_ON(task_cpu(p) != new_cpu);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	enqueue_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1274,6 +1274,15 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
 			!p->on_rq);
 
+	/*
+	 * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
+	 * because schedstat_wait_{start,end} rebase migrating task's wait_start
+	 * time relying on p->on_rq.
+	 */
+	WARN_ON_ONCE(p->state == TASK_RUNNING &&
+		     p->sched_class == &fair_sched_class &&
+		     (p->on_rq && !task_on_rq_migrating(p)));
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * The caller should hold either p->pi_lock or rq->lock, when changing
@@ -1310,9 +1319,11 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
 
+		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 	} else {
 		/*
@@ -2194,6 +2205,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq			= NULL;
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
@@ -7442,6 +7457,9 @@ int in_sched_functions(unsigned long addr)
  */
 struct task_group root_task_group;
 LIST_HEAD(task_groups);
+
+/* Cacheline aligned slab cache for task_group */
+static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
@@ -7499,11 +7517,12 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
+	task_group_cache = KMEM_CACHE(task_group, 0);
+
 	list_add(&root_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&root_task_group.children);
 	INIT_LIST_HEAD(&root_task_group.siblings);
 	autogroup_init(&init_task);
-
 #endif /* CONFIG_CGROUP_SCHED */
 
 	for_each_possible_cpu(i) {
@@ -7784,7 +7803,7 @@ static void free_sched_group(struct task_group *tg)
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
 	autogroup_free(tg);
-	kfree(tg);
+	kmem_cache_free(task_group_cache, tg);
 }
 
 /* allocate runqueue etc for a new task group */
@@ -7792,7 +7811,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 {
 	struct task_group *tg;
 
-	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+	tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
 	if (!tg)
 		return ERR_PTR(-ENOMEM);
 
@@ -8697,3 +8716,44 @@ void dump_cpu_task(int cpu)
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }
+
+/*
+ * Nice levels are multiplicative, with a gentle 10% change for every
+ * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
+ * nice 1, it will get ~10% less CPU time than another CPU-bound task
+ * that remained on nice 0.
+ *
+ * The "10% effect" is relative and cumulative: from _any_ nice level,
+ * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
+ * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
+ * If a task goes up by ~10% and another task goes down by ~10% then
+ * the relative distance between them is ~25%.)
+ */
+const int sched_prio_to_weight[40] = {
+ /* -20 */     88761,     71755,     56483,     46273,     36291,
+ /* -15 */     29154,     23254,     18705,     14949,     11916,
+ /* -10 */      9548,      7620,      6100,      4904,      3906,
+ /*  -5 */      3121,      2501,      1991,      1586,      1277,
+ /*   0 */      1024,       820,       655,       526,       423,
+ /*   5 */       335,       272,       215,       172,       137,
+ /*  10 */       110,        87,        70,        56,        45,
+ /*  15 */        36,        29,        23,        18,        15,
+};
+
+/*
+ * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
+ *
+ * In cases where the weight does not change often, we can use the
+ * precalculated inverse to speed up arithmetics by turning divisions
+ * into multiplications:
+ */
+const u32 sched_prio_to_wmult[40] = {
+ /* -20 */     48388,     59856,     76040,     92818,    118348,
+ /* -15 */    147320,    184698,    229616,    287308,    360437,
+ /* -10 */    449829,    563644,    704093,    875809,   1099582,
+ /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
+ /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
+ /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
+ /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
+ /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
+};

kernel/sched/cputime.c

@@ -466,7 +466,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		return;
 
 	if (sched_clock_irqtime) {
@@ -680,7 +680,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 {
 	unsigned long long delta = vtime_delta(tsk);
 
-	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
+	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
 	tsk->vtime_snap += delta;
 
 	/* CHECKME: always safe to convert nsecs to cputime? */
@@ -696,37 +696,37 @@ static void __vtime_account_system(struct task_struct *tsk)
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_gen_account_irq_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	if (context_tracking_in_user())
 		tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_cpu;
 
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	delta_cpu = get_vtime_delta(tsk);
 	tsk->vtime_snap_whence = VTIME_SYS;
 	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_user_enter(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_guest_enter(struct task_struct *tsk)
@@ -738,19 +738,19 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 * synchronization against the reader (task_gtime())
 	 * that can thus safely catch up with a tickless delta.
 	 */
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	current->flags |= PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
 
 void vtime_guest_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	current->flags &= ~PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
@@ -763,24 +763,26 @@ void vtime_account_idle(struct task_struct *tsk)
 
 void arch_vtime_task_switch(struct task_struct *prev)
 {
-	write_seqlock(&prev->vtime_seqlock);
-	prev->vtime_snap_whence = VTIME_SLEEPING;
-	write_sequnlock(&prev->vtime_seqlock);
+	write_seqcount_begin(&prev->vtime_seqcount);
+	prev->vtime_snap_whence = VTIME_INACTIVE;
+	write_seqcount_end(&prev->vtime_seqcount);
 
-	write_seqlock(&current->vtime_seqlock);
+	write_seqcount_begin(&current->vtime_seqcount);
 	current->vtime_snap_whence = VTIME_SYS;
 	current->vtime_snap = sched_clock_cpu(smp_processor_id());
-	write_sequnlock(&current->vtime_seqlock);
+	write_seqcount_end(&current->vtime_seqcount);
 }
 
 void vtime_init_idle(struct task_struct *t, int cpu)
 {
 	unsigned long flags;
 
-	write_seqlock_irqsave(&t->vtime_seqlock, flags);
+	local_irq_save(flags);
+	write_seqcount_begin(&t->vtime_seqcount);
 	t->vtime_snap_whence = VTIME_SYS;
 	t->vtime_snap = sched_clock_cpu(cpu);
-	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
+	write_seqcount_end(&t->vtime_seqcount);
+	local_irq_restore(flags);
 }
 
 cputime_t task_gtime(struct task_struct *t)
@@ -788,17 +790,17 @@ cputime_t task_gtime(struct task_struct *t)
 	unsigned int seq;
 	cputime_t gtime;
 
-	if (!context_tracking_is_enabled())
+	if (!vtime_accounting_enabled())
 		return t->gtime;
 
 	do {
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		gtime = t->gtime;
-		if (t->flags & PF_VCPU)
+		if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU)
 			gtime += vtime_delta(t);
 
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 
 	return gtime;
 }
@@ -821,7 +823,7 @@ fetch_task_cputime(struct task_struct *t,
 		*udelta = 0;
 		*sdelta = 0;
 
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		if (u_dst)
 			*u_dst = *u_src;
@@ -829,7 +831,7 @@ fetch_task_cputime(struct task_struct *t,
 			*s_dst = *s_src;
 
 		/* Task is sleeping, nothing to add */
-		if (t->vtime_snap_whence == VTIME_SLEEPING ||
+		if (t->vtime_snap_whence == VTIME_INACTIVE ||
 		    is_idle_task(t))
 			continue;
 
@@ -845,7 +847,7 @@ fetch_task_cputime(struct task_struct *t,
 			if (t->vtime_snap_whence == VTIME_SYS)
 				*sdelta = delta;
 		}
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 }
 
 
@@ -853,6 +855,14 @@ void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utime)
+			*utime = t->utime;
+		if (stime)
+			*stime = t->stime;
+		return;
+	}
+
 	fetch_task_cputime(t, utime, stime, &t->utime,
 			   &t->stime, &udelta, &sdelta);
 	if (utime)
@@ -866,6 +876,14 @@ void task_cputime_scaled(struct task_struct *t,
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utimescaled)
+			*utimescaled = t->utimescaled;
+		if (stimescaled)
+			*stimescaled = t->stimescaled;
+		return;
+	}
+
 	fetch_task_cputime(t, utimescaled, stimescaled,
 			   &t->utimescaled, &t->stimescaled, &udelta, &sdelta);
 	if (utimescaled)

kernel/sched/deadline.c

@@ -176,8 +176,10 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 		}
 	}
 
-	if (leftmost)
+	if (leftmost) {
 		dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+		dl_rq->earliest_dl.next = p->dl.deadline;
+	}
 
 	rb_link_node(&p->pushable_dl_tasks, parent, link);
 	rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -195,6 +197,10 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 
 		next_node = rb_next(&p->pushable_dl_tasks);
 		dl_rq->pushable_dl_tasks_leftmost = next_node;
+		if (next_node) {
+			dl_rq->earliest_dl.next = rb_entry(next_node,
+				struct task_struct, pushable_dl_tasks)->dl.deadline;
+		}
 	}
 
 	rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -782,42 +788,14 @@ static void update_curr_dl(struct rq *rq)
 
 #ifdef CONFIG_SMP
 
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
-
-static inline u64 next_deadline(struct rq *rq)
-{
-	struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
-
-	if (next && dl_prio(next->prio))
-		return next->dl.deadline;
-	else
-		return 0;
-}
-
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 {
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_rq->earliest_dl.curr == 0 ||
 	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
-		/*
-		 * If the dl_rq had no -deadline tasks, or if the new task
-		 * has shorter deadline than the current one on dl_rq, we
-		 * know that the previous earliest becomes our next earliest,
-		 * as the new task becomes the earliest itself.
-		 */
-		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
 		dl_rq->earliest_dl.curr = deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
-	} else if (dl_rq->earliest_dl.next == 0 ||
-		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
-		/*
-		 * On the other hand, if the new -deadline task has a
-		 * a later deadline than the earliest one on dl_rq, but
-		 * it is earlier than the next (if any), we must
-		 * recompute the next-earliest.
-		 */
-		dl_rq->earliest_dl.next = next_deadline(rq);
 	}
 }
 
@@ -839,7 +817,6 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 
 		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
-		dl_rq->earliest_dl.next = next_deadline(rq);
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
 	}
 }
@@ -1274,28 +1251,6 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 	return 0;
 }
 
-/* Returns the second earliest -deadline task, NULL otherwise */
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
-{
-	struct rb_node *next_node = rq->dl.rb_leftmost;
-	struct sched_dl_entity *dl_se;
-	struct task_struct *p = NULL;
-
-next_node:
-	next_node = rb_next(next_node);
-	if (next_node) {
-		dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
-		p = dl_task_of(dl_se);
-
-		if (pick_dl_task(rq, p, cpu))
-			return p;
-
-		goto next_node;
-	}
-
-	return NULL;
-}
-
 /*
  * Return the earliest pushable rq's task, which is suitable to be executed
  * on the CPU, NULL otherwise:

kernel/sched/fair.c

@@ -738,12 +738,56 @@ static void update_curr_fair(struct rq *rq)
 	update_curr(cfs_rq_of(&rq->curr->se));
 }
 
+#ifdef CONFIG_SCHEDSTATS
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
+	u64 wait_start = rq_clock(rq_of(cfs_rq));
+
+	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
+	    likely(wait_start > se->statistics.wait_start))
+		wait_start -= se->statistics.wait_start;
+
+	se->statistics.wait_start = wait_start;
 }
 
+static void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct task_struct *p;
+	u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+
+	if (entity_is_task(se)) {
+		p = task_of(se);
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			se->statistics.wait_start = delta;
+			return;
+		}
+		trace_sched_stat_wait(p, delta);
+	}
+
+	se->statistics.wait_max = max(se->statistics.wait_max, delta);
+	se->statistics.wait_count++;
+	se->statistics.wait_sum += delta;
+	se->statistics.wait_start = 0;
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+#endif
+
 /*
  * Task is being enqueued - update stats:
  */
@@ -757,23 +801,6 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_stats_wait_start(cfs_rq, se);
 }
 
-static void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
-	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
-	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-#ifdef CONFIG_SCHEDSTATS
-	if (entity_is_task(se)) {
-		trace_sched_stat_wait(task_of(se),
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-	}
-#endif
-	schedstat_set(se->statistics.wait_start, 0);
-}
-
 static inline void
 update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2155,6 +2182,7 @@ void task_numa_work(struct callback_head *work)
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
+	u64 runtime = p->se.sum_exec_runtime;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
 	unsigned long nr_pte_updates = 0;
@@ -2277,6 +2305,17 @@ void task_numa_work(struct callback_head *work)
 	else
 		reset_ptenuma_scan(p);
 	up_read(&mm->mmap_sem);
+
+	/*
+	 * Make sure tasks use at least 32x as much time to run other code
+	 * than they used here, to limit NUMA PTE scanning overhead to 3% max.
+	 * Usually update_task_scan_period slows down scanning enough; on an
+	 * overloaded system we need to limit overhead on a per task basis.
+	 */
+	if (unlikely(p->se.sum_exec_runtime != runtime)) {
+		u64 diff = p->se.sum_exec_runtime - runtime;
+		p->node_stamp += 32 * diff;
+	}
 }
 
 /*
@@ -2670,12 +2709,64 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
 	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
+	/*
+	 * No need to update load_avg for root_task_group as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
 	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
 }
 
+/*
+ * Called within set_task_rq() right before setting a task's cpu. The
+ * caller only guarantees p->pi_lock is held; no other assumptions,
+ * including the state of rq->lock, should be made.
+ */
+void set_task_rq_fair(struct sched_entity *se,
+		      struct cfs_rq *prev, struct cfs_rq *next)
+{
+	if (!sched_feat(ATTACH_AGE_LOAD))
+		return;
+
+	/*
+	 * We are supposed to update the task to "current" time, then its up to
+	 * date and ready to go to new CPU/cfs_rq. But we have difficulty in
+	 * getting what current time is, so simply throw away the out-of-date
+	 * time. This will result in the wakee task is less decayed, but giving
+	 * the wakee more load sounds not bad.
+	 */
+	if (se->avg.last_update_time && prev) {
+		u64 p_last_update_time;
+		u64 n_last_update_time;
+
+#ifndef CONFIG_64BIT
+		u64 p_last_update_time_copy;
+		u64 n_last_update_time_copy;
+
+		do {
+			p_last_update_time_copy = prev->load_last_update_time_copy;
+			n_last_update_time_copy = next->load_last_update_time_copy;
+
+			smp_rmb();
+
+			p_last_update_time = prev->avg.last_update_time;
+			n_last_update_time = next->avg.last_update_time;
+
+		} while (p_last_update_time != p_last_update_time_copy ||
+			 n_last_update_time != n_last_update_time_copy);
+#else
+		p_last_update_time = prev->avg.last_update_time;
+		n_last_update_time = next->avg.last_update_time;
+#endif
+		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
+				  &se->avg, 0, 0, NULL);
+		se->avg.last_update_time = n_last_update_time;
+	}
+}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2809,48 +2900,48 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		max_t(s64,  cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
 }
 
-/*
- * Task first catches up with cfs_rq, and then subtract
- * itself from the cfs_rq (task must be off the queue now).
- */
-void remove_entity_load_avg(struct sched_entity *se)
-{
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 last_update_time;
-
 #ifndef CONFIG_64BIT
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
 	u64 last_update_time_copy;
+	u64 last_update_time;
 
 	do {
 		last_update_time_copy = cfs_rq->load_last_update_time_copy;
 		smp_rmb();
 		last_update_time = cfs_rq->avg.last_update_time;
 	} while (last_update_time != last_update_time_copy);
-#else
-	last_update_time = cfs_rq->avg.last_update_time;
-#endif
 
-	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
-	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
-	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
+	return last_update_time;
 }
-
-/*
- * Update the rq's load with the elapsed running time before entering
- * idle. if the last scheduled task is not a CFS task, idle_enter will
- * be the only way to update the runnable statistic.
- */
-void idle_enter_fair(struct rq *this_rq)
+#else
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
 {
+	return cfs_rq->avg.last_update_time;
 }
+#endif
 
 /*
- * Update the rq's load with the elapsed idle time before a task is
- * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
- * be the only way to update the runnable statistic.
+ * Task first catches up with cfs_rq, and then subtract
+ * itself from the cfs_rq (task must be off the queue now).
  */
-void idle_exit_fair(struct rq *this_rq)
+void remove_entity_load_avg(struct sched_entity *se)
 {
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 last_update_time;
+
+	/*
+	 * Newly created task or never used group entity should not be removed
+	 * from its (source) cfs_rq
+	 */
+	if (se->avg.last_update_time == 0)
+		return;
+
+	last_update_time = cfs_rq_last_update_time(cfs_rq);
+
+	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
+	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
 }
 
 static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
@@ -4240,42 +4331,37 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
  */
 
 /*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ * The exact cpuload calculated at every tick would be:
+ *
+ *   load' = (1 - 1/2^i) * load + (1/2^i) * cur_load
+ *
+ * If a cpu misses updates for n ticks (as it was idle) and update gets
+ * called on the n+1-th tick when cpu may be busy, then we have:
  *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *   load_n   = (1 - 1/2^i)^n * load_0
+ *   load_n+1 = (1 - 1/2^i)   * load_n + (1/2^i) * cur_load
  *
  * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ *   load' = (1 - 1/2^i)^n * load
+ *
+ * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors.
+ * This allows us to precompute the above in said factors, thereby allowing the
+ * reduction of an arbitrary n in O(log_2 n) steps. (See also
+ * fixed_power_int())
  *
  * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
  */
 #define DEGRADE_SHIFT		7
-static const unsigned char
-		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
-		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
-					{0, 0, 0, 0, 0, 0, 0, 0},
-					{64, 32, 8, 0, 0, 0, 0, 0},
-					{96, 72, 40, 12, 1, 0, 0},
-					{112, 98, 75, 43, 15, 1, 0},
-					{120, 112, 98, 76, 45, 16, 2} };
+
+static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+	{   0,   0,  0,  0,  0,  0, 0, 0 },
+	{  64,  32,  8,  0,  0,  0, 0, 0 },
+	{  96,  72, 40, 12,  1,  0, 0, 0 },
+	{ 112,  98, 75, 43, 15,  1, 0, 0 },
+	{ 120, 112, 98, 76, 45, 16, 2, 0 }
+};
 
 /*
  * Update cpu_load for any missed ticks, due to tickless idle. The backlog
@@ -4306,14 +4392,46 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
 	return load;
 }
 
-/*
+/**
+ * __update_cpu_load - update the rq->cpu_load[] statistics
+ * @this_rq: The rq to update statistics for
+ * @this_load: The current load
+ * @pending_updates: The number of missed updates
+ * @active: !0 for NOHZ_FULL
+ *
  * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
+ * scheduler tick (TICK_NSEC).
+ *
+ * This function computes a decaying average:
+ *
+ *   load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load
+ *
+ * Because of NOHZ it might not get called on every tick which gives need for
+ * the @pending_updates argument.
+ *
+ *   load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1
+ *             = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load
+ *             = A * (A * load[i]_n-2 + B) + B
+ *             = A * (A * (A * load[i]_n-3 + B) + B) + B
+ *             = A^3 * load[i]_n-3 + (A^2 + A + 1) * B
+ *             = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B
+ *             = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B
+ *             = (1 - 1/2^i)^n * (load[i]_0 - load) + load
+ *
+ * In the above we've assumed load_n := load, which is true for NOHZ_FULL as
+ * any change in load would have resulted in the tick being turned back on.
+ *
+ * For regular NOHZ, this reduces to:
+ *
+ *   load[i]_n = (1 - 1/2^i)^n * load[i]_0
+ *
+ * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra
+ * term. See the @active paramter.
  */
 static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
-			      unsigned long pending_updates)
+			      unsigned long pending_updates, int active)
 {
+	unsigned long tickless_load = active ? this_rq->cpu_load[0] : 0;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
@@ -4325,8 +4443,9 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
 
 		/* scale is effectively 1 << i now, and >> i divides by scale */
 
-		old_load = this_rq->cpu_load[i];
+		old_load = this_rq->cpu_load[i] - tickless_load;
 		old_load = decay_load_missed(old_load, pending_updates - 1, i);
+		old_load += tickless_load;
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4381,16 +4500,17 @@ static void update_idle_cpu_load(struct rq *this_rq)
 	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
 	this_rq->last_load_update_tick = curr_jiffies;
 
-	__update_cpu_load(this_rq, load, pending_updates);
+	__update_cpu_load(this_rq, load, pending_updates, 0);
 }
 
 /*
  * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
  */
-void update_cpu_load_nohz(void)
+void update_cpu_load_nohz(int active)
 {
 	struct rq *this_rq = this_rq();
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
+	unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0;
 	unsigned long pending_updates;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
@@ -4401,10 +4521,11 @@ void update_cpu_load_nohz(void)
 	if (pending_updates) {
 		this_rq->last_load_update_tick = curr_jiffies;
 		/*
-		 * We were idle, this means load 0, the current load might be
-		 * !0 due to remote wakeups and the sort.
+		 * In the regular NOHZ case, we were idle, this means load 0.
+		 * In the NOHZ_FULL case, we were non-idle, we should consider
+		 * its weighted load.
 		 */
-		__update_cpu_load(this_rq, 0, pending_updates);
+		__update_cpu_load(this_rq, load, pending_updates, active);
 	}
 	raw_spin_unlock(&this_rq->lock);
 }
@@ -4420,7 +4541,7 @@ void update_cpu_load_active(struct rq *this_rq)
 	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, load, 1);
+	__update_cpu_load(this_rq, load, 1, 1);
 }
 
 /*
@@ -5007,8 +5128,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
- * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
- * other assumptions, including the state of rq->lock, should be made.
+ * previous cpu. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
  */
 static void migrate_task_rq_fair(struct task_struct *p)
 {
@@ -5721,8 +5841,8 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	deactivate_task(env->src_rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	deactivate_task(env->src_rq, p, 0);
 	set_task_cpu(p, env->dst_cpu);
 }
 
@@ -5855,8 +5975,8 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	activate_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -6302,7 +6422,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			bool *overload)
 {
 	unsigned long load;
-	int i;
+	int i, nr_running;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -6319,7 +6439,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->group_util += cpu_util(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
-		if (rq->nr_running > 1)
+		nr_running = rq->nr_running;
+		if (nr_running > 1)
 			*overload = true;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -6327,7 +6448,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->nr_preferred_running += rq->nr_preferred_running;
 #endif
 		sgs->sum_weighted_load += weighted_cpuload(i);
-		if (idle_cpu(i))
+		/*
+		 * No need to call idle_cpu() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
 	}
 
@@ -7248,8 +7372,6 @@ static int idle_balance(struct rq *this_rq)
 	int pulled_task = 0;
 	u64 curr_cost = 0;
 
-	idle_enter_fair(this_rq);
-
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -7330,10 +7452,8 @@ static int idle_balance(struct rq *this_rq)
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
 
-	if (pulled_task) {
-		idle_exit_fair(this_rq);
+	if (pulled_task)
 		this_rq->idle_stamp = 0;
-	}
 
 	return pulled_task;
 }

kernel/sched/idle_task.c

@@ -47,7 +47,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
-	idle_exit_fair(rq);
 	rq_last_tick_reset(rq);
 }
 

kernel/sched/sched.h

@@ -248,7 +248,12 @@ struct task_group {
 	unsigned long shares;
 
 #ifdef	CONFIG_SMP
-	atomic_long_t load_avg;
+	/*
+	 * load_avg can be heavily contended at clock tick time, so put
+	 * it in its own cacheline separated from the fields above which
+	 * will also be accessed at each tick.
+	 */
+	atomic_long_t load_avg ____cacheline_aligned;
 #endif
 #endif
 
@@ -335,7 +340,15 @@ extern void sched_move_task(struct task_struct *tsk);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-#endif
+
+#ifdef CONFIG_SMP
+extern void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next);
+#else /* !CONFIG_SMP */
+static inline void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next) { }
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #else /* CONFIG_CGROUP_SCHED */
 
@@ -933,6 +946,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
 	p->se.cfs_rq = tg->cfs_rq[cpu];
 	p->se.parent = tg->se[cpu];
 #endif
@@ -1113,46 +1127,8 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #define WEIGHT_IDLEPRIO                3
 #define WMULT_IDLEPRIO         1431655765
 
-/*
- * Nice levels are multiplicative, with a gentle 10% change for every
- * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
- * nice 1, it will get ~10% less CPU time than another CPU-bound task
- * that remained on nice 0.
- *
- * The "10% effect" is relative and cumulative: from _any_ nice level,
- * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
- * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
- * If a task goes up by ~10% and another task goes down by ~10% then
- * the relative distance between them is ~25%.)
- */
-static const int prio_to_weight[40] = {
- /* -20 */     88761,     71755,     56483,     46273,     36291,
- /* -15 */     29154,     23254,     18705,     14949,     11916,
- /* -10 */      9548,      7620,      6100,      4904,      3906,
- /*  -5 */      3121,      2501,      1991,      1586,      1277,
- /*   0 */      1024,       820,       655,       526,       423,
- /*   5 */       335,       272,       215,       172,       137,
- /*  10 */       110,        87,        70,        56,        45,
- /*  15 */        36,        29,        23,        18,        15,
-};
-
-/*
- * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
- *
- * In cases where the weight does not change often, we can use the
- * precalculated inverse to speed up arithmetics by turning divisions
- * into multiplications:
- */
-static const u32 prio_to_wmult[40] = {
- /* -20 */     48388,     59856,     76040,     92818,    118348,
- /* -15 */    147320,    184698,    229616,    287308,    360437,
- /* -10 */    449829,    563644,    704093,    875809,   1099582,
- /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
- /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
- /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
- /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
- /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
-};
+extern const int sched_prio_to_weight[40];
+extern const u32 sched_prio_to_wmult[40];
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_HEAD		0x02
@@ -1252,16 +1228,8 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void idle_enter_fair(struct rq *this_rq);
-extern void idle_exit_fair(struct rq *this_rq);
-
 extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
 
-#else
-
-static inline void idle_enter_fair(struct rq *rq) { }
-static inline void idle_exit_fair(struct rq *rq) { }
-
 #endif
 
 #ifdef CONFIG_CPU_IDLE

kernel/stop_machine.c

@@ -28,7 +28,6 @@
  */
 struct cpu_stop_done {
 	atomic_t		nr_todo;	/* nr left to execute */
-	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
 	struct completion	completion;	/* fired if nr_todo reaches 0 */
 };
@@ -63,14 +62,10 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 }
 
 /* signal completion unless @done is NULL */
-static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+static void cpu_stop_signal_done(struct cpu_stop_done *done)
 {
-	if (done) {
-		if (executed)
-			done->executed = true;
 	if (atomic_dec_and_test(&done->nr_todo))
 		complete(&done->completion);
-	}
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
@@ -81,17 +76,21 @@ static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
-static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
+static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	unsigned long flags;
+	bool enabled;
 
 	spin_lock_irqsave(&stopper->lock, flags);
-	if (stopper->enabled)
+	enabled = stopper->enabled;
+	if (enabled)
 		__cpu_stop_queue_work(stopper, work);
-	else
-		cpu_stop_signal_done(work->done, false);
+	else if (work->done)
+		cpu_stop_signal_done(work->done);
 	spin_unlock_irqrestore(&stopper->lock, flags);
+
+	return enabled;
 }
 
 /**
@@ -124,9 +123,10 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
 
 	cpu_stop_init_done(&done, 1);
-	cpu_stop_queue_work(cpu, &work);
+	if (!cpu_stop_queue_work(cpu, &work))
+		return -ENOENT;
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /* This controls the threads on each CPU. */
@@ -258,7 +258,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	struct cpu_stop_work work1, work2;
 	struct multi_stop_data msdata;
 
-	preempt_disable();
 	msdata = (struct multi_stop_data){
 		.fn = fn,
 		.data = arg,
@@ -277,16 +276,11 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 
 	if (cpu1 > cpu2)
 		swap(cpu1, cpu2);
-	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) {
-		preempt_enable();
+	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2))
 		return -ENOENT;
-	}
-
-	preempt_enable();
 
 	wait_for_completion(&done.completion);
-
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -302,23 +296,28 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
  *
  * CONTEXT:
  * Don't care.
+ *
+ * RETURNS:
+ * true if cpu_stop_work was queued successfully and @fn will be called,
+ * false otherwise.
  */
-void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			struct cpu_stop_work *work_buf)
 {
 	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
-	cpu_stop_queue_work(cpu, work_buf);
+	return cpu_stop_queue_work(cpu, work_buf);
 }
 
 /* static data for stop_cpus */
 static DEFINE_MUTEX(stop_cpus_mutex);
 
-static void queue_stop_cpus_work(const struct cpumask *cpumask,
+static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 				 cpu_stop_fn_t fn, void *arg,
 				 struct cpu_stop_done *done)
 {
 	struct cpu_stop_work *work;
 	unsigned int cpu;
+	bool queued = false;
 
 	/*
 	 * Disable preemption while queueing to avoid getting
@@ -331,9 +330,12 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask,
 		work->fn = fn;
 		work->arg = arg;
 		work->done = done;
-		cpu_stop_queue_work(cpu, work);
+		if (cpu_stop_queue_work(cpu, work))
+			queued = true;
 	}
 	lg_global_unlock(&stop_cpus_lock);
+
+	return queued;
 }
 
 static int __stop_cpus(const struct cpumask *cpumask,
@@ -342,9 +344,10 @@ static int __stop_cpus(const struct cpumask *cpumask,
 	struct cpu_stop_done done;
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
-	queue_stop_cpus_work(cpumask, fn, arg, &done);
+	if (!queue_stop_cpus_work(cpumask, fn, arg, &done))
+		return -ENOENT;
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -432,7 +435,6 @@ static void cpu_stopper_thread(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	struct cpu_stop_work *work;
-	int ret;
 
 repeat:
 	work = NULL;
@@ -448,23 +450,19 @@ static void cpu_stopper_thread(unsigned int cpu)
 		cpu_stop_fn_t fn = work->fn;
 		void *arg = work->arg;
 		struct cpu_stop_done *done = work->done;
-		char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
-
-		/* cpu stop callbacks are not allowed to sleep */
-		preempt_disable();
+		int ret;
 
+		/* cpu stop callbacks must not sleep, make in_atomic() == T */
+		preempt_count_inc();
 		ret = fn(arg);
+		if (done) {
 			if (ret)
 				done->ret = ret;
-
-		/* restore preemption and check it's still balanced */
-		preempt_enable();
+			cpu_stop_signal_done(done);
+		}
+		preempt_count_dec();
 		WARN_ONCE(preempt_count(),
-			  "cpu_stop: %s(%p) leaked preempt count\n",
-			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
-					  ksym_buf), arg);
-
-		cpu_stop_signal_done(done, true);
+			  "cpu_stop: %pf(%p) leaked preempt count\n", fn, arg);
 		goto repeat;
 	}
 }

kernel/time/tick-sched.c

@@ -694,11 +694,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	return tick;
 }
 
-static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now, int active)
 {
 	/* Update jiffies first */
 	tick_do_update_jiffies64(now);
-	update_cpu_load_nohz();
+	update_cpu_load_nohz(active);
 
 	calc_load_exit_idle();
 	touch_softlockup_watchdog();
@@ -725,7 +725,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	if (can_stop_full_tick())
 		tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
 	else if (ts->tick_stopped)
-		tick_nohz_restart_sched_tick(ts, ktime_get());
+		tick_nohz_restart_sched_tick(ts, ktime_get(), 1);
 #endif
 }
 
@@ -875,7 +875,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	unsigned long ticks;
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		return;
 	/*
 	 * We stopped the tick in idle. Update process times would miss the
@@ -916,7 +916,7 @@ void tick_nohz_idle_exit(void)
 		tick_nohz_stop_idle(ts, now);
 
 	if (ts->tick_stopped) {
-		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_restart_sched_tick(ts, now, 0);
 		tick_nohz_account_idle_ticks(ts);
 	}