1 files changed, 95 insertions, 287 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index b387a8de26a5..d1ad69b270ca 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -174,41 +174,6 @@ struct task_group {
 	struct sched_entity **se;
 	/* runqueue "owned" by this group on each cpu */
 	struct cfs_rq **cfs_rq;
-
-	/*
-	 * shares assigned to a task group governs how much of cpu bandwidth
-	 * is allocated to the group. The more shares a group has, the more is
-	 * the cpu bandwidth allocated to it.
-	 *
-	 * For ex, lets say that there are three task groups, A, B and C which
-	 * have been assigned shares 1000, 2000 and 3000 respectively. Then,
-	 * cpu bandwidth allocated by the scheduler to task groups A, B and C
-	 * should be:
-	 *
-	 *	Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
-	 *	Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
-	 *	Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
-	 *
-	 * The weight assigned to a task group's schedulable entities on every
-	 * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
-	 * group's shares. For ex: lets say that task group A has been
-	 * assigned shares of 1000 and there are two CPUs in a system. Then,
-	 *
-	 *  tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
-	 *
-	 * Note: It's not necessary that each of a task's group schedulable
-	 *	 entity have the same weight on all CPUs. If the group
-	 *	 has 2 of its tasks on CPU0 and 1 task on CPU1, then a
-	 *	 better distribution of weight could be:
-	 *
-	 *	tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
-	 *	tg_A->se[1]->load.weight = 1/2 * 2000 =  667
-	 *
-	 * rebalance_shares() is responsible for distributing the shares of a
-	 * task groups like this among the group's schedulable entities across
-	 * cpus.
-	 *
-	 */
 	unsigned long shares;
 #endif
 
@@ -250,22 +215,12 @@ static DEFINE_SPINLOCK(task_group_lock);
 static DEFINE_MUTEX(doms_cur_mutex);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-/* kernel thread that runs rebalance_shares() periodically */
-static struct task_struct *lb_monitor_task;
-static int load_balance_monitor(void *unused);
-#endif
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares);
-
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
 #else
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
 #endif
 
-#define MIN_GROUP_SHARES	2
-
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
 
@@ -346,7 +301,7 @@ struct cfs_rq {
 	/* 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr;
+	struct sched_entity *curr, *next;
 
 	unsigned long nr_spread_over;
 
@@ -668,6 +623,8 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
  */
 unsigned int sysctl_sched_rt_period = 1000000;
 
+static __read_mostly int scheduler_running;
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -689,14 +646,16 @@ unsigned long long cpu_clock(int cpu)
 	unsigned long flags;
 	struct rq *rq;
 
-	local_irq_save(flags);
-	rq = cpu_rq(cpu);
 	/*
 	 * Only call sched_clock() if the scheduler has already been
 	 * initialized (some code might call cpu_clock() very early):
 	 */
-	if (rq->idle)
-		update_rq_clock(rq);
+	if (unlikely(!scheduler_running))
+		return 0;
+
+	local_irq_save(flags);
+	rq = cpu_rq(cpu);
+	update_rq_clock(rq);
 	now = rq->clock;
 	local_irq_restore(flags);
 
@@ -1125,7 +1084,7 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 	u64 tmp;
 
 	if (unlikely(!lw->inv_weight))
-		lw->inv_weight = (WMULT_CONST - lw->weight/2) / lw->weight + 1;
+		lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
 
 	tmp = (u64)delta_exec * weight;
 	/*
@@ -1149,11 +1108,13 @@ calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
+	lw->inv_weight = 0;
 }
 
 static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
 {
 	lw->weight -= dec;
+	lw->inv_weight = 0;
 }
 
 /*
@@ -1241,16 +1202,6 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 #endif
 
-static inline void inc_cpu_load(struct rq *rq, unsigned long load)
-{
-	update_load_add(&rq->load, load);
-}
-
-static inline void dec_cpu_load(struct rq *rq, unsigned long load)
-{
-	update_load_sub(&rq->load, load);
-}
-
 #ifdef CONFIG_SMP
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1268,14 +1219,26 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
 #define sched_class_highest (&rt_sched_class)
 
-static void inc_nr_running(struct rq *rq)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
+{
+	update_load_add(&rq->load, p->se.load.weight);
+}
+
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
+{
+	update_load_sub(&rq->load, p->se.load.weight);
+}
+
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running++;
+	inc_load(rq, p);
 }
 
-static void dec_nr_running(struct rq *rq)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running--;
+	dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -1367,7 +1330,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, wakeup);
-	inc_nr_running(rq);
+	inc_nr_running(p, rq);
 }
 
 /*
@@ -1379,7 +1342,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
 		rq->nr_uninterruptible++;
 
 	dequeue_task(rq, p, sleep);
-	dec_nr_running(rq);
+	dec_nr_running(p, rq);
 }
 
 /**
@@ -2019,7 +1982,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		 * management (if any):
 		 */
 		p->sched_class->task_new(rq, p);
-		inc_nr_running(rq);
+		inc_nr_running(p, rq);
 	}
 	check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP
@@ -3885,7 +3848,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
-	long *switch_count;
+	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
@@ -4307,11 +4270,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	oldprio = p->prio;
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
@@ -4320,10 +4282,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	p->prio = prio;
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		enqueue_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -4358,8 +4319,10 @@ void set_user_nice(struct task_struct *p, long nice)
 		goto out_unlock;
 	}
 	on_rq = p->se.on_rq;
-	if (on_rq)
+	if (on_rq) {
 		dequeue_task(rq, p, 0);
+		dec_load(rq, p);
+	}
 
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
@@ -4369,6 +4332,7 @@ void set_user_nice(struct task_struct *p, long nice)
 
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
+		inc_load(rq, p);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4458,7 +4422,7 @@ int task_nice(const struct task_struct *p)
 {
 	return TASK_NICE(p);
 }
-EXPORT_SYMBOL_GPL(task_nice);
+EXPORT_SYMBOL(task_nice);
 
 /**
  * idle_cpu - is a given cpu idle currently?
@@ -4617,19 +4581,17 @@ recheck:
 	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		deactivate_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		activate_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -5136,7 +5098,7 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
 	time_slice = 0;
 	if (p->policy == SCHED_RR) {
 		time_slice = DEF_TIMESLICE;
-	} else {
+	} else if (p->policy != SCHED_FIFO) {
 		struct sched_entity *se = &p->se;
 		unsigned long flags;
 		struct rq *rq;
@@ -5917,7 +5879,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		spin_unlock_irq(&rq->lock);
 		break;
 
-	case CPU_DOWN_PREPARE:
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
@@ -7083,21 +7046,6 @@ void __init sched_init_smp(void)
 	if (set_cpus_allowed(current, non_isolated_cpus) < 0)
 		BUG();
 	sched_init_granularity();
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	if (nr_cpu_ids == 1)
-		return;
-
-	lb_monitor_task = kthread_create(load_balance_monitor, NULL,
-					 "group_balance");
-	if (!IS_ERR(lb_monitor_task)) {
-		lb_monitor_task->flags |= PF_NOFREEZE;
-		wake_up_process(lb_monitor_task);
-	} else {
-		printk(KERN_ERR "Could not create load balance monitor thread"
-			"(error = %ld) \n", PTR_ERR(lb_monitor_task));
-	}
-#endif
 }
 #else
 void __init sched_init_smp(void)
@@ -7284,6 +7232,8 @@ void __init sched_init(void)
 	 * During early bootup we pretend to be a normal task:
 	 */
 	current->sched_class = &fair_sched_class;
+
+	scheduler_running = 1;
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -7418,157 +7368,6 @@ void set_curr_task(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_GROUP_SCHED
 
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
-/*
- * distribute shares of all task groups among their schedulable entities,
- * to reflect load distribution across cpus.
- */
-static int rebalance_shares(struct sched_domain *sd, int this_cpu)
-{
-	struct cfs_rq *cfs_rq;
-	struct rq *rq = cpu_rq(this_cpu);
-	cpumask_t sdspan = sd->span;
-	int balanced = 1;
-
-	/* Walk thr' all the task groups that we have */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		int i;
-		unsigned long total_load = 0, total_shares;
-		struct task_group *tg = cfs_rq->tg;
-
-		/* Gather total task load of this group across cpus */
-		for_each_cpu_mask(i, sdspan)
-			total_load += tg->cfs_rq[i]->load.weight;
-
-		/* Nothing to do if this group has no load */
-		if (!total_load)
-			continue;
-
-		/*
-		 * tg->shares represents the number of cpu shares the task group
-		 * is eligible to hold on a single cpu. On N cpus, it is
-		 * eligible to hold (N * tg->shares) number of cpu shares.
-		 */
-		total_shares = tg->shares * cpus_weight(sdspan);
-
-		/*
-		 * redistribute total_shares across cpus as per the task load
-		 * distribution.
-		 */
-		for_each_cpu_mask(i, sdspan) {
-			unsigned long local_load, local_shares;
-
-			local_load = tg->cfs_rq[i]->load.weight;
-			local_shares = (local_load * total_shares) / total_load;
-			if (!local_shares)
-				local_shares = MIN_GROUP_SHARES;
-			if (local_shares == tg->se[i]->load.weight)
-				continue;
-
-			spin_lock_irq(&cpu_rq(i)->lock);
-			set_se_shares(tg->se[i], local_shares);
-			spin_unlock_irq(&cpu_rq(i)->lock);
-			balanced = 0;
-		}
-	}
-
-	return balanced;
-}
-
-/*
- * How frequently should we rebalance_shares() across cpus?
- *
- * The more frequently we rebalance shares, the more accurate is the fairness
- * of cpu bandwidth distribution between task groups. However higher frequency
- * also implies increased scheduling overhead.
- *
- * sysctl_sched_min_bal_int_shares represents the minimum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * sysctl_sched_max_bal_int_shares represents the maximum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * These settings allows for the appropriate trade-off between accuracy of
- * fairness and the associated overhead.
- *
- */
-
-/* default: 8ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_min_bal_int_shares = 8;
-
-/* default: 128ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_max_bal_int_shares = 128;
-
-/* kernel thread that runs rebalance_shares() periodically */
-static int load_balance_monitor(void *unused)
-{
-	unsigned int timeout = sysctl_sched_min_bal_int_shares;
-	struct sched_param schedparm;
-	int ret;
-
-	/*
-	 * We don't want this thread's execution to be limited by the shares
-	 * assigned to default group (init_task_group). Hence make it run
-	 * as a SCHED_RR RT task at the lowest priority.
-	 */
-	schedparm.sched_priority = 1;
-	ret = sched_setscheduler(current, SCHED_RR, &schedparm);
-	if (ret)
-		printk(KERN_ERR "Couldn't set SCHED_RR policy for load balance"
-				" monitor thread (error = %d) \n", ret);
-
-	while (!kthread_should_stop()) {
-		int i, cpu, balanced = 1;
-
-		/* Prevent cpus going down or coming up */
-		get_online_cpus();
-		/* lockout changes to doms_cur[] array */
-		lock_doms_cur();
-		/*
-		 * Enter a rcu read-side critical section to safely walk rq->sd
-		 * chain on various cpus and to walk task group list
-		 * (rq->leaf_cfs_rq_list) in rebalance_shares().
-		 */
-		rcu_read_lock();
-
-		for (i = 0; i < ndoms_cur; i++) {
-			cpumask_t cpumap = doms_cur[i];
-			struct sched_domain *sd = NULL, *sd_prev = NULL;
-
-			cpu = first_cpu(cpumap);
-
-			/* Find the highest domain at which to balance shares */
-			for_each_domain(cpu, sd) {
-				if (!(sd->flags & SD_LOAD_BALANCE))
-					continue;
-				sd_prev = sd;
-			}
-
-			sd = sd_prev;
-			/* sd == NULL? No load balance reqd in this domain */
-			if (!sd)
-				continue;
-
-			balanced &= rebalance_shares(sd, cpu);
-		}
-
-		rcu_read_unlock();
-
-		unlock_doms_cur();
-		put_online_cpus();
-
-		if (!balanced)
-			timeout = sysctl_sched_min_bal_int_shares;
-		else if (timeout < sysctl_sched_max_bal_int_shares)
-			timeout *= 2;
-
-		msleep_interruptible(timeout);
-	}
-
-	return 0;
-}
-#endif	/* CONFIG_SMP */
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void free_fair_sched_group(struct task_group *tg)
 {
@@ -7817,47 +7616,46 @@ void sched_move_task(struct task_struct *tsk)
 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
 
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, tsk, 0);
-		if (unlikely(running))
-			tsk->sched_class->put_prev_task(rq, tsk);
-	}
+	if (unlikely(running))
+		tsk->sched_class->put_prev_task(rq, tsk);
 
 	set_task_rq(tsk, task_cpu(tsk));
 
-	if (on_rq) {
-		if (unlikely(running))
-			tsk->sched_class->set_curr_task(rq);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (tsk->sched_class->moved_group)
+		tsk->sched_class->moved_group(tsk);
+#endif
+
+	if (unlikely(running))
+		tsk->sched_class->set_curr_task(rq);
+	if (on_rq)
 		enqueue_task(rq, tsk, 0);
-	}
 
 	task_rq_unlock(rq, &flags);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-/* rq->lock to be locked by caller */
 static void set_se_shares(struct sched_entity *se, unsigned long shares)
 {
 	struct cfs_rq *cfs_rq = se->cfs_rq;
 	struct rq *rq = cfs_rq->rq;
 	int on_rq;
 
-	if (!shares)
-		shares = MIN_GROUP_SHARES;
+	spin_lock_irq(&rq->lock);
 
 	on_rq = se->on_rq;
-	if (on_rq) {
+	if (on_rq)
 		dequeue_entity(cfs_rq, se, 0);
-		dec_cpu_load(rq, se->load.weight);
-	}
 
 	se->load.weight = shares;
 	se->load.inv_weight = div64_64((1ULL<<32), shares);
 
-	if (on_rq) {
+	if (on_rq)
 		enqueue_entity(cfs_rq, se, 0);
-		inc_cpu_load(rq, se->load.weight);
-	}
+
+	spin_unlock_irq(&rq->lock);
 }
 
 static DEFINE_MUTEX(shares_mutex);
@@ -7867,18 +7665,18 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	int i;
 	unsigned long flags;
 
+	/*
+	 * A weight of 0 or 1 can cause arithmetics problems.
+	 * (The default weight is 1024 - so there's no practical
+	 *  limitation from this.)
+	 */
+	if (shares < 2)
+		shares = 2;
+
 	mutex_lock(&shares_mutex);
 	if (tg->shares == shares)
 		goto done;
 
-	if (shares < MIN_GROUP_SHARES)
-		shares = MIN_GROUP_SHARES;
-
-	/*
-	 * Prevent any load balance activity (rebalance_shares,
-	 * load_balance_fair) from referring to this group first,
-	 * by taking it off the rq->leaf_cfs_rq_list on each cpu.
-	 */
 	spin_lock_irqsave(&task_group_lock, flags);
 	for_each_possible_cpu(i)
 		unregister_fair_sched_group(tg, i);
@@ -7892,11 +7690,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	 * w/o tripping rebalance_share or load_balance_fair.
 	 */
 	tg->shares = shares;
-	for_each_possible_cpu(i) {
-		spin_lock_irq(&cpu_rq(i)->lock);
+	for_each_possible_cpu(i)
 		set_se_shares(tg->se[i], shares);
-		spin_unlock_irq(&cpu_rq(i)->lock);
-	}
 
 	/*
 	 * Enable load balance activity on this group, by inserting it back on
@@ -7928,9 +7723,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 	if (runtime == RUNTIME_INF)
 		return 1ULL << 16;
 
-	runtime *= (1ULL << 16);
-	div64_64(runtime, period);
-	return runtime;
+	return div64_64(runtime << 16, period);
 }
 
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
@@ -7954,25 +7747,40 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 	return total + to_ratio(period, runtime) < global_ratio;
 }
 
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+	do_each_thread(g, p) {
+		if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+			return 1;
+	} while_each_thread(g, p);
+	return 0;
+}
+
 int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 {
 	u64 rt_runtime, rt_period;
 	int err = 0;
 
-	rt_period = sysctl_sched_rt_period * NSEC_PER_USEC;
+	rt_period = (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
 	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
 	if (rt_runtime_us == -1)
-		rt_runtime = rt_period;
+		rt_runtime = RUNTIME_INF;
 
 	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	if (rt_runtime_us == 0 && tg_has_rt_tasks(tg)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 	if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
 		err = -EINVAL;
 		goto unlock;
 	}
-	if (rt_runtime_us == -1)
-		rt_runtime = RUNTIME_INF;
 	tg->rt_runtime = rt_runtime;
  unlock:
+	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return err;