1 files changed, 156 insertions, 57 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 26058d0bebba..7f12624a393c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -83,7 +83,7 @@
 #endif
 
 #include "sched.h"
-#include "../workqueue_sched.h"
+#include "../workqueue_internal.h"
 #include "../smpboot.h"
 
 #define CREATE_TRACE_POINTS
@@ -1132,18 +1132,28 @@ EXPORT_SYMBOL_GPL(kick_process);
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
-	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+	int nid = cpu_to_node(cpu);
+	const struct cpumask *nodemask = NULL;
 	enum { cpuset, possible, fail } state = cpuset;
 	int dest_cpu;
 
-	/* Look for allowed, online CPU in same node. */
-	for_each_cpu(dest_cpu, nodemask) {
-		if (!cpu_online(dest_cpu))
-			continue;
-		if (!cpu_active(dest_cpu))
-			continue;
-		if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
-			return dest_cpu;
+	/*
+	 * If the node that the cpu is on has been offlined, cpu_to_node()
+	 * will return -1. There is no cpu on the node, and we should
+	 * select the cpu on the other node.
+	 */
+	if (nid != -1) {
+		nodemask = cpumask_of_node(nid);
+
+		/* Look for allowed, online CPU in same node. */
+		for_each_cpu(dest_cpu, nodemask) {
+			if (!cpu_online(dest_cpu))
+				continue;
+			if (!cpu_active(dest_cpu))
+				continue;
+			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+				return dest_cpu;
+		}
 	}
 
 	for (;;) {
@@ -1742,9 +1752,8 @@ EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
 	struct preempt_notifier *notifier;
-	struct hlist_node *node;
 
-	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+	hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
 		notifier->ops->sched_in(notifier, raw_smp_processor_id());
 }
 
@@ -1753,9 +1762,8 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 				 struct task_struct *next)
 {
 	struct preempt_notifier *notifier;
-	struct hlist_node *node;
 
-	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+	hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
 		notifier->ops->sched_out(notifier, next);
 }
 
@@ -1969,11 +1977,10 @@ context_switch(struct rq *rq, struct task_struct *prev,
 }
 
 /*
- * nr_running, nr_uninterruptible and nr_context_switches:
+ * nr_running and nr_context_switches:
  *
  * externally visible scheduler statistics: current number of runnable
- * threads, current number of uninterruptible-sleeping threads, total
- * number of context switches performed since bootup.
+ * threads, total number of context switches performed since bootup.
  */
 unsigned long nr_running(void)
 {
@@ -1985,23 +1992,6 @@ unsigned long nr_running(void)
 	return sum;
 }
 
-unsigned long nr_uninterruptible(void)
-{
-	unsigned long i, sum = 0;
-
-	for_each_possible_cpu(i)
-		sum += cpu_rq(i)->nr_uninterruptible;
-
-	/*
-	 * Since we read the counters lockless, it might be slightly
-	 * inaccurate. Do not allow it to go below zero though:
-	 */
-	if (unlikely((long)sum < 0))
-		sum = 0;
-
-	return sum;
-}
-
 unsigned long long nr_context_switches(void)
 {
 	int i;
@@ -2786,7 +2776,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
 	dump_stack();
-	add_taint(TAINT_WARN);
+	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
 
 /*
@@ -3268,7 +3258,8 @@ void complete_all(struct completion *x)
 EXPORT_SYMBOL(complete_all);
 
 static inline long __sched
-do_wait_for_common(struct completion *x, long timeout, int state)
+do_wait_for_common(struct completion *x,
+		   long (*action)(long), long timeout, int state)
 {
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
@@ -3281,7 +3272,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
 			}
 			__set_current_state(state);
 			spin_unlock_irq(&x->wait.lock);
-			timeout = schedule_timeout(timeout);
+			timeout = action(timeout);
 			spin_lock_irq(&x->wait.lock);
 		} while (!x->done && timeout);
 		__remove_wait_queue(&x->wait, &wait);
@@ -3292,17 +3283,30 @@ do_wait_for_common(struct completion *x, long timeout, int state)
 	return timeout ?: 1;
 }
 
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
+static inline long __sched
+__wait_for_common(struct completion *x,
+		  long (*action)(long), long timeout, int state)
 {
 	might_sleep();
 
 	spin_lock_irq(&x->wait.lock);
-	timeout = do_wait_for_common(x, timeout, state);
+	timeout = do_wait_for_common(x, action, timeout, state);
 	spin_unlock_irq(&x->wait.lock);
 	return timeout;
 }
 
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
 /**
  * wait_for_completion: - waits for completion of a task
  * @x:  holds the state of this particular completion
@@ -3339,6 +3343,39 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 EXPORT_SYMBOL(wait_for_completion_timeout);
 
 /**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+	wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
  * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
  * @x:  holds the state of this particular completion
  *
@@ -4364,20 +4401,32 @@ EXPORT_SYMBOL(yield);
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
  *
- * Returns true if we indeed boosted the target task.
+ * Returns:
+ *	true (>0) if we indeed boosted the target task.
+ *	false (0) if we failed to boost the target.
+ *	-ESRCH if there's no task to yield to.
  */
 bool __sched yield_to(struct task_struct *p, bool preempt)
 {
 	struct task_struct *curr = current;
 	struct rq *rq, *p_rq;
 	unsigned long flags;
-	bool yielded = 0;
+	int yielded = 0;
 
 	local_irq_save(flags);
 	rq = this_rq();
 
 again:
 	p_rq = task_rq(p);
+	/*
+	 * If we're the only runnable task on the rq and target rq also
+	 * has only one task, there's absolutely no point in yielding.
+	 */
+	if (rq->nr_running == 1 && p_rq->nr_running == 1) {
+		yielded = -ESRCH;
+		goto out_irq;
+	}
+
 	double_rq_lock(rq, p_rq);
 	while (task_rq(p) != p_rq) {
 		double_rq_unlock(rq, p_rq);
@@ -4385,13 +4434,13 @@ again:
 	}
 
 	if (!curr->sched_class->yield_to_task)
-		goto out;
+		goto out_unlock;
 
 	if (curr->sched_class != p->sched_class)
-		goto out;
+		goto out_unlock;
 
 	if (task_running(p_rq, p) || p->state)
-		goto out;
+		goto out_unlock;
 
 	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
 	if (yielded) {
@@ -4404,11 +4453,12 @@ again:
 			resched_task(p_rq->curr);
 	}
 
-out:
+out_unlock:
 	double_rq_unlock(rq, p_rq);
+out_irq:
 	local_irq_restore(flags);
 
-	if (yielded)
+	if (yielded > 0)
 		schedule();
 
 	return yielded;
@@ -4667,6 +4717,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 */
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
+	vtime_init_idle(idle);
 #if defined(CONFIG_SMP)
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif
@@ -7160,7 +7211,6 @@ static void free_sched_group(struct task_group *tg)
 struct task_group *sched_create_group(struct task_group *parent)
 {
 	struct task_group *tg;
-	unsigned long flags;
 
 	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
 	if (!tg)
@@ -7172,6 +7222,17 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
+	return tg;
+
+err:
+	free_sched_group(tg);
+	return ERR_PTR(-ENOMEM);
+}
+
+void sched_online_group(struct task_group *tg, struct task_group *parent)
+{
+	unsigned long flags;
+
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_add_rcu(&tg->list, &task_groups);
 
@@ -7181,12 +7242,6 @@ struct task_group *sched_create_group(struct task_group *parent)
 	INIT_LIST_HEAD(&tg->children);
 	list_add_rcu(&tg->siblings, &parent->children);
 	spin_unlock_irqrestore(&task_group_lock, flags);
-
-	return tg;
-
-err:
-	free_sched_group(tg);
-	return ERR_PTR(-ENOMEM);
 }
 
 /* rcu callback to free various structures associated with a task group */
@@ -7199,6 +7254,12 @@ static void free_sched_group_rcu(struct rcu_head *rhp)
 /* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
 {
+	/* wait for possible concurrent references to cfs_rqs complete */
+	call_rcu(&tg->rcu, free_sched_group_rcu);
+}
+
+void sched_offline_group(struct task_group *tg)
+{
 	unsigned long flags;
 	int i;
 
@@ -7210,9 +7271,6 @@ void sched_destroy_group(struct task_group *tg)
 	list_del_rcu(&tg->list);
 	list_del_rcu(&tg->siblings);
 	spin_unlock_irqrestore(&task_group_lock, flags);
-
-	/* wait for possible concurrent references to cfs_rqs complete */
-	call_rcu(&tg->rcu, free_sched_group_rcu);
 }
 
 /* change task's runqueue when it moves between groups.
@@ -7508,6 +7566,25 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/* make sure that internally we keep jiffies */
+	/* also, writing zero resets timeslice to default */
+	if (!ret && write) {
+		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
+
 int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -7564,6 +7641,19 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 	return &tg->css;
 }
 
+static int cpu_cgroup_css_online(struct cgroup *cgrp)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+	struct task_group *parent;
+
+	if (!cgrp->parent)
+		return 0;
+
+	parent = cgroup_tg(cgrp->parent);
+	sched_online_group(tg, parent);
+	return 0;
+}
+
 static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
@@ -7571,6 +7661,13 @@ static void cpu_cgroup_css_free(struct cgroup *cgrp)
 	sched_destroy_group(tg);
 }
 
+static void cpu_cgroup_css_offline(struct cgroup *cgrp)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+
+	sched_offline_group(tg);
+}
+
 static int cpu_cgroup_can_attach(struct cgroup *cgrp,
 				 struct cgroup_taskset *tset)
 {
@@ -7926,6 +8023,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_free	= cpu_cgroup_css_free,
+	.css_online	= cpu_cgroup_css_online,
+	.css_offline	= cpu_cgroup_css_offline,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,