1 files changed, 94 insertions, 72 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 0516af415085..3f2e502d609b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -293,7 +293,7 @@ static DEFINE_SPINLOCK(task_group_lock);
  *  limitation from this.)
  */
 #define MIN_SHARES	2
-#define MAX_SHARES	(1UL << 18)
+#define MAX_SHARES	(1UL << (18 + SCHED_LOAD_RESOLUTION))
 
 static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
 #endif
@@ -605,10 +605,10 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
- * holds that lock for each task it moves into the cgroup. Therefore
- * by holding that lock, we pin the task to the current cgroup.
+ * We use task_subsys_state_check() and extend the RCU verification with
+ * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
+ * task it moves into the cgroup. Therefore by holding either of those locks,
+ * we pin the task to the current cgroup.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -616,7 +616,8 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock));
+			lockdep_is_held(&p->pi_lock) ||
+			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -1330,13 +1331,25 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
 	u64 tmp;
 
-	tmp = (u64)delta_exec * weight;
+	/*
+	 * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
+	 * entities since MIN_SHARES = 2. Treat weight as 1 if less than
+	 * 2^SCHED_LOAD_RESOLUTION.
+	 */
+	if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
+		tmp = (u64)delta_exec * scale_load_down(weight);
+	else
+		tmp = (u64)delta_exec;
 
 	if (!lw->inv_weight) {
-		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
+		unsigned long w = scale_load_down(lw->weight);
+
+		if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
 			lw->inv_weight = 1;
+		else if (unlikely(!w))
+			lw->inv_weight = WMULT_CONST;
 		else
-			lw->inv_weight = WMULT_CONST / lw->weight;
+			lw->inv_weight = WMULT_CONST / w;
 	}
 
 	/*
@@ -1778,17 +1791,20 @@ static void dec_nr_running(struct rq *rq)
 
 static void set_load_weight(struct task_struct *p)
 {
+	int prio = p->static_prio - MAX_RT_PRIO;
+	struct load_weight *load = &p->se.load;
+
 	/*
 	 * SCHED_IDLE tasks get minimal weight:
 	 */
 	if (p->policy == SCHED_IDLE) {
-		p->se.load.weight = WEIGHT_IDLEPRIO;
-		p->se.load.inv_weight = WMULT_IDLEPRIO;
+		load->weight = scale_load(WEIGHT_IDLEPRIO);
+		load->inv_weight = WMULT_IDLEPRIO;
 		return;
 	}
 
-	p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
-	p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
+	load->weight = scale_load(prio_to_weight[prio]);
+	load->inv_weight = prio_to_wmult[prio];
 }
 
 static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -2185,6 +2201,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
+	/*
+	 * The caller should hold either p->pi_lock or rq->lock, when changing
+	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+	 *
+	 * sched_move_task() holds both and thus holding either pins the cgroup,
+	 * see set_task_rq().
+	 *
+	 * Furthermore, all task_rq users should acquire both locks, see
+	 * task_rq_lock().
+	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
 				      lockdep_is_held(&task_rq(p)->lock)));
 #endif
@@ -2432,6 +2458,10 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		}
 		rcu_read_unlock();
 	}
+
+	if (wake_flags & WF_MIGRATED)
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+
 #endif /* CONFIG_SMP */
 
 	schedstat_inc(rq, ttwu_count);
@@ -2440,9 +2470,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
 
-	if (cpu != task_cpu(p))
-		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-
 #endif /* CONFIG_SCHEDSTATS */
 }
 
@@ -2558,7 +2585,26 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
 	if (!next)
 		smp_send_reschedule(cpu);
 }
-#endif
+
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
+{
+	struct rq *rq;
+	int ret = 0;
+
+	rq = __task_rq_lock(p);
+	if (p->on_cpu) {
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+		ttwu_do_wakeup(rq, p, wake_flags);
+		ret = 1;
+	}
+	__task_rq_unlock(rq);
+
+	return ret;
+
+}
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+#endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu)
 {
@@ -2566,6 +2612,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		sched_clock_cpu(cpu); /* sync clocks x-cpu */
 		ttwu_queue_remote(p, cpu);
 		return;
 	}
@@ -2616,17 +2663,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	while (p->on_cpu) {
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 		/*
-		 * If called from interrupt context we could have landed in the
-		 * middle of schedule(), in this case we should take care not
-		 * to spin on ->on_cpu if p is current, since that would
-		 * deadlock.
+		 * In case the architecture enables interrupts in
+		 * context_switch(), we cannot busy wait, since that
+		 * would lead to deadlocks when an interrupt hits and
+		 * tries to wake up @prev. So bail and do a complete
+		 * remote wakeup.
 		 */
-		if (p == current) {
-			ttwu_queue(p, cpu);
+		if (ttwu_activate_remote(p, wake_flags))
 			goto stat;
-		}
-#endif
+#else
 		cpu_relax();
+#endif
 	}
 	/*
 	 * Pairs with the smp_wmb() in finish_lock_switch().
@@ -2640,8 +2687,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		p->sched_class->task_waking(p);
 
 	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (task_cpu(p) != cpu)
+	if (task_cpu(p) != cpu) {
+		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
+	}
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu);
@@ -5826,7 +5875,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
-	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+	do_set_cpus_allowed(idle, cpumask_of(cpu));
 	/*
 	 * We're having a chicken and egg problem, even though we are
 	 * holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -5914,6 +5963,16 @@ static inline void sched_init_granularity(void)
 }
 
 #ifdef CONFIG_SMP
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	if (p->sched_class && p->sched_class->set_cpus_allowed)
+		p->sched_class->set_cpus_allowed(p, new_mask);
+	else {
+		cpumask_copy(&p->cpus_allowed, new_mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	}
+}
+
 /*
  * This is how migration works:
  *
@@ -5959,12 +6018,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 	}
 
-	if (p->sched_class->set_cpus_allowed)
-		p->sched_class->set_cpus_allowed(p, new_mask);
-	else {
-		cpumask_copy(&p->cpus_allowed, new_mask);
-		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
-	}
+	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
@@ -6527,7 +6581,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->cpu_power != SCHED_LOAD_SCALE) {
+		if (group->cpu_power != SCHED_POWER_SCALE) {
 			printk(KERN_CONT " (cpu_power = %d)",
 				group->cpu_power);
 		}
@@ -7902,7 +7956,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_power = SCHED_LOAD_SCALE;
+		rq->cpu_power = SCHED_POWER_SCALE;
 		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -8749,42 +8803,10 @@ cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	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,
-		  bool threadgroup)
+cpu_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	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();
-	}
 }
 
 static void
@@ -8806,14 +8828,14 @@ cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
 				u64 shareval)
 {
-	return sched_group_set_shares(cgroup_tg(cgrp), shareval);
+	return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval));
 }
 
 static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
-	return (u64) tg->shares;
+	return (u64) scale_load_down(tg->shares);
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -8872,8 +8894,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
 	.create		= cpu_cgroup_create,
 	.destroy	= cpu_cgroup_destroy,
-	.can_attach	= cpu_cgroup_can_attach,
-	.attach		= cpu_cgroup_attach,
+	.can_attach_task = cpu_cgroup_can_attach_task,
+	.attach_task	= cpu_cgroup_attach_task,
 	.exit		= cpu_cgroup_exit,
 	.populate	= cpu_cgroup_populate,
 	.subsys_id	= cpu_cgroup_subsys_id,