1 files changed, 129 insertions, 75 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index faf4d463bbff..3c11ae0a948d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -39,7 +39,7 @@
 #include <linux/completion.h>
 #include <linux/kernel_stat.h>
 #include <linux/debug_locks.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/profile.h>
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 #ifdef CONFIG_SMP
 static int root_task_group_empty(void)
 {
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
 #else /* !CONFIG_USER_SCHED */
@@ -676,20 +677,15 @@ inline void update_rq_clock(struct rq *rq)
 
 /**
  * runqueue_is_locked
+ * @cpu: the processor in question.
  *
  * Returns true if the current cpu runqueue is locked.
  * This interface allows printk to be called with the runqueue lock
  * held and know whether or not it is OK to wake up the klogd.
  */
-int runqueue_is_locked(void)
+int runqueue_is_locked(int cpu)
 {
-	int cpu = get_cpu();
-	struct rq *rq = cpu_rq(cpu);
-	int ret;
-
-	ret = spin_is_locked(&rq->lock);
-	put_cpu();
-	return ret;
+	return spin_is_locked(&cpu_rq(cpu)->lock);
 }
 
 /*
@@ -786,7 +782,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp)
 	return single_open(filp, sched_feat_show, NULL);
 }
 
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
 	.open		= sched_feat_open,
 	.write		= sched_feat_write,
 	.read		= seq_read,
@@ -1569,11 +1565,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-struct update_shares_data {
-	unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -1583,12 +1575,12 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 static void update_group_shares_cpu(struct task_group *tg, int cpu,
 				    unsigned long sd_shares,
 				    unsigned long sd_rq_weight,
-				    struct update_shares_data *usd)
+				    unsigned long *usd_rq_weight)
 {
 	unsigned long shares, rq_weight;
 	int boost = 0;
 
-	rq_weight = usd->rq_weight[cpu];
+	rq_weight = usd_rq_weight[cpu];
 	if (!rq_weight) {
 		boost = 1;
 		rq_weight = NICE_0_LOAD;
@@ -1623,7 +1615,7 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
 static int tg_shares_up(struct task_group *tg, void *data)
 {
 	unsigned long weight, rq_weight = 0, shares = 0;
-	struct update_shares_data *usd;
+	unsigned long *usd_rq_weight;
 	struct sched_domain *sd = data;
 	unsigned long flags;
 	int i;
@@ -1632,11 +1624,11 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		return 0;
 
 	local_irq_save(flags);
-	usd = &__get_cpu_var(update_shares_data);
+	usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
 
 	for_each_cpu(i, sched_domain_span(sd)) {
 		weight = tg->cfs_rq[i]->load.weight;
-		usd->rq_weight[i] = weight;
+		usd_rq_weight[i] = weight;
 
 		/*
 		 * If there are currently no tasks on the cpu pretend there
@@ -1657,7 +1649,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		shares = tg->shares;
 
 	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
 
 	local_irq_restore(flags);
 
@@ -2001,6 +1993,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	spin_lock_irqsave(&rq->lock, flags);
+	set_task_cpu(p, cpu);
+	p->cpus_allowed = cpumask_of_cpu(cpu);
+	p->rt.nr_cpus_allowed = 1;
+	p->flags |= PF_THREAD_BOUND;
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2013,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) &&
+	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
 			(&p->se == cfs_rq_of(&p->se)->next ||
 			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
@@ -2059,7 +2083,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (task_hot(p, old_rq->clock, NULL))
 			schedstat_inc(p, se.nr_forced2_migrations);
 #endif
-		perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
 				     1, 1, NULL, 0);
 	}
 	p->se.vruntime -= old_cfsrq->min_vruntime -
@@ -2317,7 +2341,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
 	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
-	struct rq *rq;
+	struct rq *rq, *orig_rq;
 
 	if (!sched_feat(SYNC_WAKEUPS))
 		wake_flags &= ~WF_SYNC;
@@ -2325,7 +2349,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	this_cpu = get_cpu();
 
 	smp_wmb();
-	rq = task_rq_lock(p, &flags);
+	rq = orig_rq = task_rq_lock(p, &flags);
 	update_rq_clock(rq);
 	if (!(p->state & state))
 		goto out;
@@ -2356,6 +2380,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 		set_task_cpu(p, cpu);
 
 	rq = task_rq_lock(p, &flags);
+
+	if (rq != orig_rq)
+		update_rq_clock(rq);
+
 	WARN_ON(p->state != TASK_WAKING);
 	cpu = task_cpu(p);
 
@@ -2521,22 +2549,17 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	__sched_fork(p);
 
 	/*
-	 * Make sure we do not leak PI boosting priority to the child.
-	 */
-	p->prio = current->normal_prio;
-
-	/*
 	 * Revert to default priority/policy on fork if requested.
 	 */
 	if (unlikely(p->sched_reset_on_fork)) {
-		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
 			p->policy = SCHED_NORMAL;
-
-		if (p->normal_prio < DEFAULT_PRIO)
-			p->prio = DEFAULT_PRIO;
+			p->normal_prio = p->static_prio;
+		}
 
 		if (PRIO_TO_NICE(p->static_prio) < 0) {
 			p->static_prio = NICE_TO_PRIO(0);
+			p->normal_prio = p->static_prio;
 			set_load_weight(p);
 		}
 
@@ -2547,6 +2570,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
 		p->sched_reset_on_fork = 0;
 	}
 
+	/*
+	 * Make sure we do not leak PI boosting priority to the child.
+	 */
+	p->prio = current->normal_prio;
+
 	if (!rt_prio(p->prio))
 		p->sched_class = &fair_sched_class;
 
@@ -2587,8 +2615,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	BUG_ON(p->state != TASK_RUNNING);
 	update_rq_clock(rq);
 
-	p->prio = effective_prio(p);
-
 	if (!p->sched_class->task_new || !current->se.on_rq) {
 		activate_task(rq, p, 0);
 	} else {
@@ -2724,7 +2750,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	finish_arch_switch(prev);
-	perf_counter_task_sched_in(current, cpu_of(rq));
+	perf_event_task_sched_in(current, cpu_of(rq));
 	finish_lock_switch(rq, prev);
 
 	fire_sched_in_preempt_notifiers(current);
@@ -2910,6 +2936,19 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
+unsigned long nr_iowait_cpu(void)
+{
+	struct rq *this = this_rq();
+	return atomic_read(&this->nr_iowait);
+}
+
+unsigned long this_cpu_load(void)
+{
+	struct rq *this = this_rq();
+	return this->cpu_load[0];
+}
+
+
 /* Variables and functions for calc_load */
 static atomic_long_t calc_load_tasks;
 static unsigned long calc_load_update;
@@ -3651,6 +3690,7 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
  * @group: sched_group whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
@@ -5085,17 +5125,16 @@ void account_idle_time(cputime_t cputime)
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-	cputime_t one_jiffy = jiffies_to_cputime(1);
-	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
 	if (user_tick)
-		account_user_time(p, one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
-		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
 				    one_jiffy_scaled);
 	else
-		account_idle_time(one_jiffy);
+		account_idle_time(cputime_one_jiffy);
 }
 
 /*
@@ -5199,7 +5238,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	spin_unlock(&rq->lock);
 
-	perf_counter_task_tick(curr, cpu);
+	perf_event_task_tick(curr, cpu);
 
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
@@ -5415,7 +5454,7 @@ need_resched_nonpreemptible:
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
-		perf_counter_task_sched_out(prev, next, cpu);
+		perf_event_task_sched_out(prev, next, cpu);
 
 		rq->nr_switches++;
 		rq->curr = next;
@@ -6714,9 +6753,6 @@ EXPORT_SYMBOL(yield);
 /*
  * 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.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
  */
 void __sched io_schedule(void)
 {
@@ -6825,23 +6861,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 	if (retval)
 		goto out_unlock;
 
-	/*
-	 * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER
-	 * tasks that are on an otherwise idle runqueue:
-	 */
-	time_slice = 0;
-	if (p->policy == SCHED_RR) {
-		time_slice = DEF_TIMESLICE;
-	} else if (p->policy != SCHED_FIFO) {
-		struct sched_entity *se = &p->se;
-		unsigned long flags;
-		struct rq *rq;
+	time_slice = p->sched_class->get_rr_interval(p);
 
-		rq = task_rq_lock(p, &flags);
-		if (rq->cfs.load.weight)
-			time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
-		task_rq_unlock(rq, &flags);
-	}
 	read_unlock(&tasklist_lock);
 	jiffies_to_timespec(time_slice, &t);
 	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
@@ -7692,7 +7713,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 /*
  * Register at high priority so that task migration (migrate_all_tasks)
  * happens before everything else.  This has to be lower priority than
- * the notifier in the perf_counter subsystem, though.
+ * the notifier in the perf_event subsystem, though.
  */
 static struct notifier_block __cpuinitdata migration_notifier = {
 	.notifier_call = migration_call,
@@ -9171,6 +9192,7 @@ void __init sched_init_smp(void)
 	cpumask_var_t non_isolated_cpus;
 
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 #if defined(CONFIG_NUMA)
 	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
@@ -9202,7 +9224,6 @@ void __init sched_init_smp(void)
 	sched_init_granularity();
 	free_cpumask_var(non_isolated_cpus);
 
-	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 	init_sched_rt_class();
 }
 #else
@@ -9415,6 +9436,10 @@ void __init sched_init(void)
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_GROUP_SCHED */
 
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+					    __alignof__(unsigned long));
+#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
@@ -9540,16 +9565,16 @@ void __init sched_init(void)
 	current->sched_class = &fair_sched_class;
 
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
 	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+	zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
-	perf_counter_init();
+	perf_event_init();
 
 	scheduler_running = 1;
 }
@@ -10321,7 +10346,7 @@ static int sched_rt_global_constraints(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 int sched_rt_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret;
@@ -10332,7 +10357,7 @@ int sched_rt_handler(struct ctl_table *table, int write,
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
-	ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
 		ret = sched_rt_global_constraints();
@@ -10386,8 +10411,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 }
 
 static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		      struct task_struct *tsk)
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
@@ -10397,15 +10421,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	if (tsk->sched_class != &fair_sched_class)
 		return -EINVAL;
 #endif
+	return 0;
+}
 
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		      struct task_struct *tsk, bool threadgroup)
+{
+	int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+	if (retval)
+		return retval;
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			retval = cpu_cgroup_can_attach_task(cgrp, c);
+			if (retval) {
+				rcu_read_unlock();
+				return retval;
+			}
+		}
+		rcu_read_unlock();
+	}
 	return 0;
 }
 
 static void
 cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-			struct cgroup *old_cont, struct task_struct *tsk)
+		  struct cgroup *old_cont, struct task_struct *tsk,
+		  bool threadgroup)
 {
 	sched_move_task(tsk);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			sched_move_task(c);
+		}
+		rcu_read_unlock();
+	}
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED