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 are:

   - irqtime accounting cleanups and enhancements. (Frederic Weisbecker)

   - schedstat debugging enhancements, make it more broadly runtime
     available. (Josh Poimboeuf)

   - More work on asymmetric topology/capacity scheduling. (Morten
     Rasmussen)

   - sched/wait fixes and cleanups. (Oleg Nesterov)

   - PELT (per entity load tracking) improvements. (Peter Zijlstra)

   - Rewrite and enhance select_idle_siblings(). (Peter Zijlstra)

   - sched/numa enhancements/fixes (Rik van Riel)

   - sched/cputime scalability improvements (Stanislaw Gruszka)

   - Load calculation arithmetics fixes. (Dietmar Eggemann)

   - sched/deadline enhancements (Tommaso Cucinotta)

   - Fix utilization accounting when switching to the SCHED_NORMAL
     policy. (Vincent Guittot)

   - ... plus misc cleanups and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/irqtime: Consolidate irqtime flushing code
  sched/irqtime: Consolidate accounting synchronization with u64_stats API
  u64_stats: Introduce IRQs disabled helpers
  sched/irqtime: Remove needless IRQs disablement on kcpustat update
  sched/irqtime: No need for preempt-safe accessors
  sched/fair: Fix min_vruntime tracking
  sched/debug: Add SCHED_WARN_ON()
  sched/core: Fix set_user_nice()
  sched/fair: Introduce set_curr_task() helper
  sched/core, ia64: Rename set_curr_task()
  sched/core: Fix incorrect utilization accounting when switching to fair class
  sched/core: Optimize SCHED_SMT
  sched/core: Rewrite and improve select_idle_siblings()
  sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched/core: Introduce 'struct sched_domain_shared'
  sched/core: Restructure destroy_sched_domain()
  sched/core: Remove unused @cpu argument from destroy_sched_domain*()
  sched/wait: Introduce init_wait_entry()
  sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock()
  sched/wait: Avoid abort_exclusive_wait() in ___wait_event()
  ...

1 files changed, 218 insertions, 104 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0a6a13c21c5a..fac6492f0b98 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1070,8 +1070,12 @@ static int migration_cpu_stop(void *data)
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
 	 * we're holding p->pi_lock.
 	 */
-	if (task_rq(p) == rq && task_on_rq_queued(p))
-		rq = __migrate_task(rq, p, arg->dest_cpu);
+	if (task_rq(p) == rq) {
+		if (task_on_rq_queued(p))
+			rq = __migrate_task(rq, p, arg->dest_cpu);
+		else
+			p->wake_cpu = arg->dest_cpu;
+	}
 	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock(&p->pi_lock);
 
@@ -1112,10 +1116,10 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 
 	p->sched_class->set_cpus_allowed(p, new_mask);
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE);
+	if (running)
+		set_curr_task(rq, p);
 }
 
 /*
@@ -1272,7 +1276,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		/*
 		 * Task isn't running anymore; make it appear like we migrated
 		 * it before it went to sleep. This means on wakeup we make the
-		 * previous cpu our targer instead of where it really is.
+		 * previous cpu our target instead of where it really is.
 		 */
 		p->wake_cpu = cpu;
 	}
@@ -1636,23 +1640,25 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
-#ifdef CONFIG_SCHEDSTATS
-	struct rq *rq = this_rq();
+	struct rq *rq;
 
-#ifdef CONFIG_SMP
-	int this_cpu = smp_processor_id();
+	if (!schedstat_enabled())
+		return;
+
+	rq = this_rq();
 
-	if (cpu == this_cpu) {
-		schedstat_inc(rq, ttwu_local);
-		schedstat_inc(p, se.statistics.nr_wakeups_local);
+#ifdef CONFIG_SMP
+	if (cpu == rq->cpu) {
+		schedstat_inc(rq->ttwu_local);
+		schedstat_inc(p->se.statistics.nr_wakeups_local);
 	} else {
 		struct sched_domain *sd;
 
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+		schedstat_inc(p->se.statistics.nr_wakeups_remote);
 		rcu_read_lock();
-		for_each_domain(this_cpu, sd) {
+		for_each_domain(rq->cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				schedstat_inc(sd, ttwu_wake_remote);
+				schedstat_inc(sd->ttwu_wake_remote);
 				break;
 			}
 		}
@@ -1660,17 +1666,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	}
 
 	if (wake_flags & WF_MIGRATED)
-		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-
+		schedstat_inc(p->se.statistics.nr_wakeups_migrate);
 #endif /* CONFIG_SMP */
 
-	schedstat_inc(rq, ttwu_count);
-	schedstat_inc(p, se.statistics.nr_wakeups);
+	schedstat_inc(rq->ttwu_count);
+	schedstat_inc(p->se.statistics.nr_wakeups);
 
 	if (wake_flags & WF_SYNC)
-		schedstat_inc(p, se.statistics.nr_wakeups_sync);
-
-#endif /* CONFIG_SCHEDSTATS */
+		schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
 static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
@@ -2091,8 +2094,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	ttwu_queue(p, cpu, wake_flags);
 stat:
-	if (schedstat_enabled())
-		ttwu_stat(p, cpu, wake_flags);
+	ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -2102,6 +2104,7 @@ out:
 /**
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
+ * @cookie: context's cookie for pinning
  *
  * Put @p on the run-queue if it's not already there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
@@ -2140,8 +2143,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0, cookie);
-	if (schedstat_enabled())
-		ttwu_stat(p, smp_processor_id(), 0);
+	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }
@@ -3199,6 +3201,9 @@ static inline void preempt_latency_stop(int val) { }
  */
 static noinline void __schedule_bug(struct task_struct *prev)
 {
+	/* Save this before calling printk(), since that will clobber it */
+	unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
+
 	if (oops_in_progress)
 		return;
 
@@ -3209,13 +3214,12 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
-#ifdef CONFIG_DEBUG_PREEMPT
-	if (in_atomic_preempt_off()) {
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
+	    && in_atomic_preempt_off()) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(current->preempt_disable_ip);
+		print_ip_sym(preempt_disable_ip);
 		pr_cont("\n");
 	}
-#endif
 	if (panic_on_warn)
 		panic("scheduling while atomic\n");
 
@@ -3241,7 +3245,7 @@ static inline void schedule_debug(struct task_struct *prev)
 
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
-	schedstat_inc(this_rq(), sched_count);
+	schedstat_inc(this_rq()->sched_count);
 }
 
 /*
@@ -3334,17 +3338,6 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	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))
@@ -3412,6 +3405,33 @@ static void __sched notrace __schedule(bool preempt)
 }
 STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */
 
+void __noreturn do_task_dead(void)
+{
+	/*
+	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+	 * when the following two conditions become true.
+	 *   - There is race condition of mmap_sem (It is acquired by
+	 *     exit_mm()), and
+	 *   - SMI occurs before setting TASK_RUNINNG.
+	 *     (or hypervisor of virtual machine switches to other guest)
+	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+	 *
+	 * To avoid it, we have to wait for releasing tsk->pi_lock which
+	 * is held by try_to_wake_up()
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&current->pi_lock);
+
+	/* causes final put_task_struct in finish_task_switch(). */
+	__set_current_state(TASK_DEAD);
+	current->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
+	__schedule(false);
+	BUG();
+	/* Avoid "noreturn function does return".  */
+	for (;;)
+		cpu_relax();	/* For when BUG is null */
+}
+
 static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
@@ -3694,10 +3714,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	p->prio = prio;
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
+	if (running)
+		set_curr_task(rq, p);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -3711,7 +3731,8 @@ out_unlock:
 
 void set_user_nice(struct task_struct *p, long nice)
 {
-	int old_prio, delta, queued;
+	bool queued, running;
+	int old_prio, delta;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -3733,8 +3754,11 @@ void set_user_nice(struct task_struct *p, long nice)
 		goto out_unlock;
 	}
 	queued = task_on_rq_queued(p);
+	running = task_current(rq, p);
 	if (queued)
 		dequeue_task(rq, p, DEQUEUE_SAVE);
+	if (running)
+		put_prev_task(rq, p);
 
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
@@ -3751,6 +3775,8 @@ void set_user_nice(struct task_struct *p, long nice)
 		if (delta < 0 || (delta > 0 && task_running(rq, p)))
 			resched_curr(rq);
 	}
+	if (running)
+		set_curr_task(rq, p);
 out_unlock:
 	task_rq_unlock(rq, p, &rf);
 }
@@ -4250,8 +4276,6 @@ change:
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, attr, pi);
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued) {
 		/*
 		 * We enqueue to tail when the priority of a task is
@@ -4262,6 +4286,8 @@ change:
 
 		enqueue_task(rq, p, queue_flags);
 	}
+	if (running)
+		set_curr_task(rq, p);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	preempt_disable(); /* avoid rq from going away on us */
@@ -4853,7 +4879,7 @@ SYSCALL_DEFINE0(sched_yield)
 {
 	struct rq *rq = this_rq_lock();
 
-	schedstat_inc(rq, yld_count);
+	schedstat_inc(rq->yld_count);
 	current->sched_class->yield_task(rq);
 
 	/*
@@ -4870,6 +4896,7 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
+#ifndef CONFIG_PREEMPT
 int __sched _cond_resched(void)
 {
 	if (should_resched(0)) {
@@ -4879,6 +4906,7 @@ int __sched _cond_resched(void)
 	return 0;
 }
 EXPORT_SYMBOL(_cond_resched);
+#endif
 
 /*
  * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
@@ -5004,7 +5032,7 @@ again:
 
 	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
 	if (yielded) {
-		schedstat_inc(rq, yld_count);
+		schedstat_inc(rq->yld_count);
 		/*
 		 * Make p's CPU reschedule; pick_next_entity takes care of
 		 * fairness.
@@ -5424,10 +5452,10 @@ void sched_setnuma(struct task_struct *p, int nid)
 
 	p->numa_preferred_nid = nid;
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE);
+	if (running)
+		set_curr_task(rq, p);
 	task_rq_unlock(rq, p, &rf);
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -5724,6 +5752,8 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 	}
 }
 #else /* !CONFIG_SCHED_DEBUG */
+
+# define sched_debug_enabled 0
 # define sched_domain_debug(sd, cpu) do { } while (0)
 static inline bool sched_debug(void)
 {
@@ -5742,6 +5772,7 @@ static int sd_degenerate(struct sched_domain *sd)
 			 SD_BALANCE_FORK |
 			 SD_BALANCE_EXEC |
 			 SD_SHARE_CPUCAPACITY |
+			 SD_ASYM_CPUCAPACITY |
 			 SD_SHARE_PKG_RESOURCES |
 			 SD_SHARE_POWERDOMAIN)) {
 		if (sd->groups != sd->groups->next)
@@ -5772,6 +5803,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 				SD_BALANCE_NEWIDLE |
 				SD_BALANCE_FORK |
 				SD_BALANCE_EXEC |
+				SD_ASYM_CPUCAPACITY |
 				SD_SHARE_CPUCAPACITY |
 				SD_SHARE_PKG_RESOURCES |
 				SD_PREFER_SIBLING |
@@ -5916,10 +5948,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
 	} while (sg != first);
 }
 
-static void free_sched_domain(struct rcu_head *rcu)
+static void destroy_sched_domain(struct sched_domain *sd)
 {
-	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-
 	/*
 	 * If its an overlapping domain it has private groups, iterate and
 	 * nuke them all.
@@ -5930,18 +5960,26 @@ static void free_sched_domain(struct rcu_head *rcu)
 		kfree(sd->groups->sgc);
 		kfree(sd->groups);
 	}
+	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+		kfree(sd->shared);
 	kfree(sd);
 }
 
-static void destroy_sched_domain(struct sched_domain *sd, int cpu)
+static void destroy_sched_domains_rcu(struct rcu_head *rcu)
 {
-	call_rcu(&sd->rcu, free_sched_domain);
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+
+	while (sd) {
+		struct sched_domain *parent = sd->parent;
+		destroy_sched_domain(sd);
+		sd = parent;
+	}
 }
 
-static void destroy_sched_domains(struct sched_domain *sd, int cpu)
+static void destroy_sched_domains(struct sched_domain *sd)
 {
-	for (; sd; sd = sd->parent)
-		destroy_sched_domain(sd, cpu);
+	if (sd)
+		call_rcu(&sd->rcu, destroy_sched_domains_rcu);
 }
 
 /*
@@ -5956,14 +5994,14 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
 DEFINE_PER_CPU(struct sched_domain *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_busy);
 DEFINE_PER_CPU(struct sched_domain *, sd_asym);
 
 static void update_top_cache_domain(int cpu)
 {
+	struct sched_domain_shared *sds = NULL;
 	struct sched_domain *sd;
-	struct sched_domain *busy_sd = NULL;
 	int id = cpu;
 	int size = 1;
 
@@ -5971,13 +6009,13 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
-		busy_sd = sd->parent; /* sd_busy */
+		sds = sd->shared;
 	}
-	rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
+	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
 
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
@@ -6013,7 +6051,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			 */
 			if (parent->flags & SD_PREFER_SIBLING)
 				tmp->flags |= SD_PREFER_SIBLING;
-			destroy_sched_domain(parent, cpu);
+			destroy_sched_domain(parent);
 		} else
 			tmp = tmp->parent;
 	}
@@ -6021,7 +6059,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	if (sd && sd_degenerate(sd)) {
 		tmp = sd;
 		sd = sd->parent;
-		destroy_sched_domain(tmp, cpu);
+		destroy_sched_domain(tmp);
 		if (sd)
 			sd->child = NULL;
 	}
@@ -6031,7 +6069,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	rq_attach_root(rq, rd);
 	tmp = rq->sd;
 	rcu_assign_pointer(rq->sd, sd);
-	destroy_sched_domains(tmp, cpu);
+	destroy_sched_domains(tmp);
 
 	update_top_cache_domain(cpu);
 }
@@ -6274,7 +6312,6 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 		return;
 
 	update_group_capacity(sd, cpu);
-	atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
 }
 
 /*
@@ -6362,6 +6399,9 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
 	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
+	if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
+		*per_cpu_ptr(sdd->sds, cpu) = NULL;
+
 	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
 		*per_cpu_ptr(sdd->sg, cpu) = NULL;
 
@@ -6381,26 +6421,37 @@ static int sched_domains_curr_level;
 /*
  * SD_flags allowed in topology descriptions.
  *
- * SD_SHARE_CPUCAPACITY      - describes SMT topologies
- * SD_SHARE_PKG_RESOURCES - describes shared caches
- * SD_NUMA                - describes NUMA topologies
- * SD_SHARE_POWERDOMAIN   - describes shared power domain
+ * These flags are purely descriptive of the topology and do not prescribe
+ * behaviour. Behaviour is artificial and mapped in the below sd_init()
+ * function:
+ *
+ *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
+ *   SD_SHARE_PKG_RESOURCES - describes shared caches
+ *   SD_NUMA                - describes NUMA topologies
+ *   SD_SHARE_POWERDOMAIN   - describes shared power domain
+ *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
+ *
+ * Odd one out, which beside describing the topology has a quirk also
+ * prescribes the desired behaviour that goes along with it:
  *
- * Odd one out:
- * SD_ASYM_PACKING        - describes SMT quirks
+ *   SD_ASYM_PACKING        - describes SMT quirks
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY |		\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA |			\
 	 SD_ASYM_PACKING |		\
+	 SD_ASYM_CPUCAPACITY |		\
 	 SD_SHARE_POWERDOMAIN)
 
 static struct sched_domain *
-sd_init(struct sched_domain_topology_level *tl, int cpu)
+sd_init(struct sched_domain_topology_level *tl,
+	const struct cpumask *cpu_map,
+	struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
-	int sd_weight, sd_flags = 0;
+	struct sd_data *sdd = &tl->data;
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	int sd_id, sd_weight, sd_flags = 0;
 
 #ifdef CONFIG_NUMA
 	/*
@@ -6449,15 +6500,26 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 		.smt_gain		= 0,
 		.max_newidle_lb_cost	= 0,
 		.next_decay_max_lb_cost	= jiffies,
+		.child			= child,
 #ifdef CONFIG_SCHED_DEBUG
 		.name			= tl->name,
 #endif
 	};
 
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	sd_id = cpumask_first(sched_domain_span(sd));
+
 	/*
 	 * Convert topological properties into behaviour.
 	 */
 
+	if (sd->flags & SD_ASYM_CPUCAPACITY) {
+		struct sched_domain *t = sd;
+
+		for_each_lower_domain(t)
+			t->flags |= SD_BALANCE_WAKE;
+	}
+
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 110;
@@ -6489,7 +6551,17 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 		sd->idle_idx = 1;
 	}
 
-	sd->private = &tl->data;
+	/*
+	 * For all levels sharing cache; connect a sched_domain_shared
+	 * instance.
+	 */
+	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
+		atomic_inc(&sd->shared->ref);
+		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
+	}
+
+	sd->private = sdd;
 
 	return sd;
 }
@@ -6516,6 +6588,9 @@ static struct sched_domain_topology_level *sched_domain_topology =
 
 void set_sched_topology(struct sched_domain_topology_level *tl)
 {
+	if (WARN_ON_ONCE(sched_smp_initialized))
+		return;
+
 	sched_domain_topology = tl;
 }
 
@@ -6796,6 +6871,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 		if (!sdd->sd)
 			return -ENOMEM;
 
+		sdd->sds = alloc_percpu(struct sched_domain_shared *);
+		if (!sdd->sds)
+			return -ENOMEM;
+
 		sdd->sg = alloc_percpu(struct sched_group *);
 		if (!sdd->sg)
 			return -ENOMEM;
@@ -6806,6 +6885,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 		for_each_cpu(j, cpu_map) {
 			struct sched_domain *sd;
+			struct sched_domain_shared *sds;
 			struct sched_group *sg;
 			struct sched_group_capacity *sgc;
 
@@ -6816,6 +6896,13 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 			*per_cpu_ptr(sdd->sd, j) = sd;
 
+			sds = kzalloc_node(sizeof(struct sched_domain_shared),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sds)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sds, j) = sds;
+
 			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
 			if (!sg)
@@ -6855,6 +6942,8 @@ static void __sdt_free(const struct cpumask *cpu_map)
 				kfree(*per_cpu_ptr(sdd->sd, j));
 			}
 
+			if (sdd->sds)
+				kfree(*per_cpu_ptr(sdd->sds, j));
 			if (sdd->sg)
 				kfree(*per_cpu_ptr(sdd->sg, j));
 			if (sdd->sgc)
@@ -6862,6 +6951,8 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		}
 		free_percpu(sdd->sd);
 		sdd->sd = NULL;
+		free_percpu(sdd->sds);
+		sdd->sds = NULL;
 		free_percpu(sdd->sg);
 		sdd->sg = NULL;
 		free_percpu(sdd->sgc);
@@ -6873,16 +6964,12 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 		struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = sd_init(tl, cpu);
-	if (!sd)
-		return child;
+	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
 
-	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
 	if (child) {
 		sd->level = child->level + 1;
 		sched_domain_level_max = max(sched_domain_level_max, sd->level);
 		child->parent = sd;
-		sd->child = child;
 
 		if (!cpumask_subset(sched_domain_span(child),
 				    sched_domain_span(sd))) {
@@ -6913,6 +7000,7 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	enum s_alloc alloc_state;
 	struct sched_domain *sd;
 	struct s_data d;
+	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
@@ -6963,11 +7051,22 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
+		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
+
+		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
+		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
+			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+
 		cpu_attach_domain(sd, d.rd, i);
 	}
 	rcu_read_unlock();
 
+	if (rq && sched_debug_enabled) {
+		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
+	}
+
 	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);
@@ -7326,6 +7425,22 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
+#ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+
+static void sched_init_smt(void)
+{
+	/*
+	 * We've enumerated all CPUs and will assume that if any CPU
+	 * has SMT siblings, CPU0 will too.
+	 */
+	if (cpumask_weight(cpu_smt_mask(0)) > 1)
+		static_branch_enable(&sched_smt_present);
+}
+#else
+static inline void sched_init_smt(void) { }
+#endif
+
 void __init sched_init_smp(void)
 {
 	cpumask_var_t non_isolated_cpus;
@@ -7355,6 +7470,9 @@ void __init sched_init_smp(void)
 
 	init_sched_rt_class();
 	init_sched_dl_class();
+
+	sched_init_smt();
+
 	sched_smp_initialized = true;
 }
 
@@ -7392,6 +7510,7 @@ static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
+DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
 void __init sched_init(void)
 {
@@ -7428,6 +7547,8 @@ void __init sched_init(void)
 	for_each_possible_cpu(i) {
 		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
 			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
+		per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
@@ -7530,10 +7651,6 @@ void __init sched_init(void)
 
 	set_load_weight(&init_task);
 
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
-#endif
-
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */
@@ -7541,11 +7658,6 @@ void __init sched_init(void)
 	enter_lazy_tlb(&init_mm, current);
 
 	/*
-	 * During early bootup we pretend to be a normal task:
-	 */
-	current->sched_class = &fair_sched_class;
-
-	/*
 	 * Make us the idle thread. Technically, schedule() should not be
 	 * called from this thread, however somewhere below it might be,
 	 * but because we are the idle thread, we just pick up running again
@@ -7599,6 +7711,7 @@ EXPORT_SYMBOL(__might_sleep);
 void ___might_sleep(const char *file, int line, int preempt_offset)
 {
 	static unsigned long prev_jiffy;	/* ratelimiting */
+	unsigned long preempt_disable_ip;
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
@@ -7609,6 +7722,9 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 		return;
 	prev_jiffy = jiffies;
 
+	/* Save this before calling printk(), since that will clobber it */
+	preempt_disable_ip = get_preempt_disable_ip(current);
+
 	printk(KERN_ERR
 		"BUG: sleeping function called from invalid context at %s:%d\n",
 			file, line);
@@ -7623,14 +7739,14 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	debug_show_held_locks(current);
 	if (irqs_disabled())
 		print_irqtrace_events(current);
-#ifdef CONFIG_DEBUG_PREEMPT
-	if (!preempt_count_equals(preempt_offset)) {
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
+	    && !preempt_count_equals(preempt_offset)) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(current->preempt_disable_ip);
+		print_ip_sym(preempt_disable_ip);
 		pr_cont("\n");
 	}
-#endif
 	dump_stack();
+	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
 EXPORT_SYMBOL(___might_sleep);
 #endif
@@ -7651,12 +7767,10 @@ void normalize_rt_tasks(void)
 		if (p->flags & PF_KTHREAD)
 			continue;
 
-		p->se.exec_start		= 0;
-#ifdef CONFIG_SCHEDSTATS
-		p->se.statistics.wait_start	= 0;
-		p->se.statistics.sleep_start	= 0;
-		p->se.statistics.block_start	= 0;
-#endif
+		p->se.exec_start = 0;
+		schedstat_set(p->se.statistics.wait_start,  0);
+		schedstat_set(p->se.statistics.sleep_start, 0);
+		schedstat_set(p->se.statistics.block_start, 0);
 
 		if (!dl_task(p) && !rt_task(p)) {
 			/*
@@ -7717,7 +7831,7 @@ struct task_struct *curr_task(int cpu)
  *
  * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
  */
-void set_curr_task(int cpu, struct task_struct *p)
+void ia64_set_curr_task(int cpu, struct task_struct *p)
 {
 	cpu_curr(cpu) = p;
 }
@@ -7848,10 +7962,10 @@ void sched_move_task(struct task_struct *tsk)
 
 	sched_change_group(tsk, TASK_MOVE_GROUP);
 
-	if (unlikely(running))
-		tsk->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
+	if (unlikely(running))
+		set_curr_task(rq, tsk);
 
 	task_rq_unlock(rq, tsk, &rf);
 }