1 files changed, 103 insertions, 137 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1f37fe7f77a4..2f7937ee9e3a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -306,65 +306,8 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-/*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	lockdep_assert_held(&p->pi_lock);
-
-	for (;;) {
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
-	__acquires(p->pi_lock)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	for (;;) {
-		raw_spin_lock_irqsave(&p->pi_lock, *flags);
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
-
-static void __task_rq_unlock(struct rq *rq)
-	__releases(rq->lock)
-{
-	raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
-	__releases(rq->lock)
-	__releases(p->pi_lock)
-{
-	raw_spin_unlock(&rq->lock);
-	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-}
+/* cpus with isolated domains */
+cpumask_var_t cpu_isolated_map;
 
 /*
  * this_rq_lock - lock this runqueue and disable interrupts.
@@ -750,6 +693,23 @@ static inline bool got_nohz_idle_kick(void)
 bool sched_can_stop_tick(void)
 {
 	/*
+	 * FIFO realtime policy runs the highest priority task. Other runnable
+	 * tasks are of a lower priority. The scheduler tick does nothing.
+	 */
+	if (current->policy == SCHED_FIFO)
+		return true;
+
+	/*
+	 * Round-robin realtime tasks time slice with other tasks at the same
+	 * realtime priority. Is this task the only one at this priority?
+	 */
+	if (current->policy == SCHED_RR) {
+		struct sched_rt_entity *rt_se = &current->rt;
+
+		return rt_se->run_list.prev == rt_se->run_list.next;
+	}
+
+	/*
 	 * More than one running task need preemption.
 	 * nr_running update is assumed to be visible
 	 * after IPI is sent from wakers.
@@ -1056,6 +1016,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		rq_clock_skip_update(rq, true);
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -1086,10 +1053,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		struct task_migration_notifier tmn;
+
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+
+		tmn.task = p;
+		tmn.from_cpu = task_cpu(p);
+		tmn.to_cpu = new_cpu;
+
+		atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
 	}
 
 	__set_task_cpu(p, new_cpu);
@@ -2899,7 +2874,7 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
-static void preempt_schedule_common(void)
+static void __sched notrace preempt_schedule_common(void)
 {
 	do {
 		__preempt_count_add(PREEMPT_ACTIVE);
@@ -3094,6 +3069,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
+		if (rt_prio(oldprio))
+			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
 	}
 
@@ -4418,36 +4395,29 @@ EXPORT_SYMBOL_GPL(yield_to);
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
-void __sched io_schedule(void)
-{
-	struct rq *rq = raw_rq();
-
-	delayacct_blkio_start();
-	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
-	schedule();
-	current->in_iowait = 0;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
 long __sched io_schedule_timeout(long timeout)
 {
-	struct rq *rq = raw_rq();
+	int old_iowait = current->in_iowait;
+	struct rq *rq;
 	long ret;
 
+	current->in_iowait = 1;
+	if (old_iowait)
+		blk_schedule_flush_plug(current);
+	else
+		blk_flush_plug(current);
+
 	delayacct_blkio_start();
+	rq = raw_rq();
 	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
 	ret = schedule_timeout(timeout);
-	current->in_iowait = 0;
+	current->in_iowait = old_iowait;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
+
 	return ret;
 }
+EXPORT_SYMBOL(io_schedule_timeout);
 
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
@@ -5385,36 +5355,13 @@ static int sched_cpu_active(struct notifier_block *nfb,
 static int sched_cpu_inactive(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
-	unsigned long flags;
-	long cpu = (long)hcpu;
-	struct dl_bw *dl_b;
-
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
-		set_cpu_active(cpu, false);
-
-		/* explicitly allow suspend */
-		if (!(action & CPU_TASKS_FROZEN)) {
-			bool overflow;
-			int cpus;
-
-			rcu_read_lock_sched();
-			dl_b = dl_bw_of(cpu);
-
-			raw_spin_lock_irqsave(&dl_b->lock, flags);
-			cpus = dl_bw_cpus(cpu);
-			overflow = __dl_overflow(dl_b, cpus, 0, 0);
-			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-			rcu_read_unlock_sched();
-
-			if (overflow)
-				return notifier_from_errno(-EBUSY);
-		}
+		set_cpu_active((long)hcpu, false);
 		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
 	}
-
-	return NOTIFY_DONE;
 }
 
 static int __init migration_init(void)
@@ -5462,9 +5409,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  struct cpumask *groupmask)
 {
 	struct sched_group *group = sd->groups;
-	char str[256];
 
-	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
 	cpumask_clear(groupmask);
 
 	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@@ -5477,7 +5422,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %s level %s\n", str, sd->name);
+	printk(KERN_CONT "span %*pbl level %s\n",
+	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
@@ -5496,17 +5442,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		/*
-		 * Even though we initialize ->capacity to something semi-sane,
-		 * we leave capacity_orig unset. This allows us to detect if
-		 * domain iteration is still funny without causing /0 traps.
-		 */
-		if (!group->sgc->capacity_orig) {
-			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
-			break;
-		}
-
 		if (!cpumask_weight(sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
@@ -5522,9 +5457,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
-		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
-
-		printk(KERN_CONT " %s", str);
+		printk(KERN_CONT " %*pbl",
+		       cpumask_pr_args(sched_group_cpus(group)));
 		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
 			printk(KERN_CONT " (cpu_capacity = %d)",
 				group->sgc->capacity);
@@ -5880,9 +5814,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	update_top_cache_domain(cpu);
 }
 
-/* cpus with isolated domains */
-static cpumask_var_t cpu_isolated_map;
-
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
@@ -5991,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		 * die on a /0 trap.
 		 */
 		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->capacity_orig = sg->sgc->capacity;
 
 		/*
 		 * Make sure the first group of this domain contains the
@@ -6302,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 	 */
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
+		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 110;
 		sd->smt_gain = 1178; /* ~15% */
 
@@ -7067,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 		 */
 
 	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
 		cpuset_update_active_cpus(true);
 		break;
 	default:
@@ -7079,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
 			       void *hcpu)
 {
-	switch (action) {
+	unsigned long flags;
+	long cpu = (long)hcpu;
+	struct dl_bw *dl_b;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
+		/* explicitly allow suspend */
+		if (!(action & CPU_TASKS_FROZEN)) {
+			bool overflow;
+			int cpus;
+
+			rcu_read_lock_sched();
+			dl_b = dl_bw_of(cpu);
+
+			raw_spin_lock_irqsave(&dl_b->lock, flags);
+			cpus = dl_bw_cpus(cpu);
+			overflow = __dl_overflow(dl_b, cpus, 0, 0);
+			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+			rcu_read_unlock_sched();
+
+			if (overflow)
+				return notifier_from_errno(-EBUSY);
+		}
 		cpuset_update_active_cpus(false);
 		break;
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -7225,8 +7177,8 @@ void __init sched_init(void)
 		rq->calc_load_active = 0;
 		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs);
-		init_rt_rq(&rq->rt, rq);
-		init_dl_rq(&rq->dl, rq);
+		init_rt_rq(&rq->rt);
+		init_dl_rq(&rq->dl);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -7266,7 +7218,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
 		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -7644,6 +7596,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {
 	struct task_struct *g, *p;
 
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
 	for_each_process_thread(g, p) {
 		if (rt_task(p) && task_group(p) == tg)
 			return 1;
@@ -7736,6 +7694,17 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 {
 	int i, err = 0;
 
+	/*
+	 * Disallowing the root group RT runtime is BAD, it would disallow the
+	 * kernel creating (and or operating) RT threads.
+	 */
+	if (tg == &root_task_group && rt_runtime == 0)
+		return -EINVAL;
+
+	/* No period doesn't make any sense. */
+	if (rt_period == 0)
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
@@ -7792,9 +7761,6 @@ static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
 	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
-	if (rt_period == 0)
-		return -EINVAL;
-
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
 
@@ -7851,7 +7817,7 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static int sched_dl_global_constraints(void)
+static int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
@@ -7952,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write,
 		if (ret)
 			goto undo;
 
-		ret = sched_rt_global_constraints();
+		ret = sched_dl_global_validate();
 		if (ret)
 			goto undo;
 
-		ret = sched_dl_global_constraints();
+		ret = sched_rt_global_constraints();
 		if (ret)
 			goto undo;