Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  sched: Change wait_for_completion_*_timeout() to return a signed long
  sched, autogroup: Fix reference leak
  sched, autogroup: Fix potential access to freed memory
  sched: Remove redundant CONFIG_CGROUP_SCHED ifdef
  sched: Fix interactivity bug by charging unaccounted run-time on entity re-weight
  sched: Move periodic share updates to entity_tick()
  printk: Use this_cpu_{read|write} api on printk_pending
  sched: Make pushable_tasks CONFIG_SMP dependant
  sched: Add 'autogroup' scheduling feature: automated per session task groups
  sched: Fix unregister_fair_sched_group()
  sched: Remove unused argument dest_cpu to migrate_task()
  mutexes, sched: Introduce arch_mutex_cpu_relax()
  sched: Add some clock info to sched_debug
  cpu: Remove incorrect BUG_ON
  cpu: Remove unused variable
  sched: Fix UP build breakage
  sched: Make task dump print all 15 chars of proc comm
  sched: Update tg->shares after cpu.shares write
  sched: Allow update_cfs_load() to update global load
  sched: Implement demand based update_cfs_load()
  ...

19 files changed, 785 insertions, 585 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index f6e726f1849..cb7a1efa9c2 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -189,7 +189,6 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
-	struct task_struct *caller;
 	unsigned long mod;
 	void *hcpu;
 };
@@ -198,7 +197,6 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
-	unsigned int cpu = (unsigned long)param->hcpu;
 	int err;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -208,11 +206,6 @@ static int __ref take_cpu_down(void *_param)
 
 	cpu_notify(CPU_DYING | param->mod, param->hcpu);
 
-	if (task_cpu(param->caller) == cpu)
-		move_task_off_dead_cpu(cpu, param->caller);
-	/* Force idle task to run as soon as we yield: it should
-	   immediately notice cpu is offline and die quickly. */
-	sched_idle_next();
 	return 0;
 }
 
@@ -223,7 +216,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
-		.caller = current,
 		.mod = mod,
 		.hcpu = hcpu,
 	};
@@ -253,9 +245,15 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 	BUG_ON(cpu_online(cpu));
 
-	/* Wait for it to sleep (leaving idle task). */
+	/*
+	 * The migration_call() CPU_DYING callback will have removed all
+	 * runnable tasks from the cpu, there's only the idle task left now
+	 * that the migration thread is done doing the stop_machine thing.
+	 *
+	 * Wait for the stop thread to go away.
+	 */
 	while (!idle_cpu(cpu))
-		yield();
+		cpu_relax();
 
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
diff --git a/kernel/fork.c b/kernel/fork.c
index 5447dc7defa..7d164e25b0f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -174,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig)
 
 static inline void put_signal_struct(struct signal_struct *sig)
 {
-	if (atomic_dec_and_test(&sig->sigcnt))
+	if (atomic_dec_and_test(&sig->sigcnt)) {
+		sched_autogroup_exit(sig);
 		free_signal_struct(sig);
+	}
 }
 
 void __put_task_struct(struct task_struct *tsk)
@@ -905,6 +907,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	posix_cpu_timers_init_group(sig);
 
 	tty_audit_fork(sig);
+	sched_autogroup_fork(sig);
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
@@ -1315,7 +1318,7 @@ bad_fork_cleanup_mm:
 	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
-		free_signal_struct(p->signal);
+		put_signal_struct(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5f92acc5f95..91a5fa25054 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -577,7 +577,9 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
  */
 static int irq_thread(void *data)
 {
-	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+	static struct sched_param param = {
+		.sched_priority = MAX_USER_RT_PRIO/2,
+	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
 	int wake, oneshot = desc->status & IRQ_ONESHOT;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index ca61bbdd44b..5355cfd44a3 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -148,7 +148,7 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 	wait_for_completion(&create.done);
 
 	if (!IS_ERR(create.result)) {
-		struct sched_param param = { .sched_priority = 0 };
+		static struct sched_param param = { .sched_priority = 0 };
 		va_list args;
 
 		va_start(args, namefmt);
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 200407c1502..a5889fb28ec 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -199,7 +199,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
diff --git a/kernel/printk.c b/kernel/printk.c
index a23315dc449..ab3ffc5b3b6 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1074,17 +1074,17 @@ static DEFINE_PER_CPU(int, printk_pending);
 
 void printk_tick(void)
 {
-	if (__get_cpu_var(printk_pending)) {
-		__get_cpu_var(printk_pending) = 0;
+	if (__this_cpu_read(printk_pending)) {
+		__this_cpu_write(printk_pending, 0);
 		wake_up_interruptible(&log_wait);
 	}
 }
 
 int printk_needs_cpu(int cpu)
 {
-	if (unlikely(cpu_is_offline(cpu)))
+	if (cpu_is_offline(cpu))
 		printk_tick();
-	return per_cpu(printk_pending, cpu);
+	return __this_cpu_read(printk_pending);
 }
 
 void wake_up_klogd(void)
diff --git a/kernel/sched.c b/kernel/sched.c
index 260132961a9..04949089e76 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,9 +75,11 @@
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
+#include <asm/mutex.h>
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
+#include "sched_autogroup.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -253,6 +255,8 @@ struct task_group {
 	/* runqueue "owned" by this group on each cpu */
 	struct cfs_rq **cfs_rq;
 	unsigned long shares;
+
+	atomic_t load_weight;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -268,24 +272,19 @@ struct task_group {
 	struct task_group *parent;
 	struct list_head siblings;
 	struct list_head children;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 };
 
 #define root_task_group init_task_group
 
-/* task_group_lock serializes add/remove of task groups and also changes to
- * a task group's cpu shares.
- */
+/* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-#ifdef CONFIG_SMP
-static int root_task_group_empty(void)
-{
-	return list_empty(&root_task_group.children);
-}
-#endif
-
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
 
 /*
@@ -342,6 +341,7 @@ struct cfs_rq {
 	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
 	 * list is used during load balance.
 	 */
+	int on_list;
 	struct list_head leaf_cfs_rq_list;
 	struct task_group *tg;	/* group that "owns" this runqueue */
 
@@ -360,14 +360,17 @@ struct cfs_rq {
 	unsigned long h_load;
 
 	/*
-	 * this cpu's part of tg->shares
+	 * Maintaining per-cpu shares distribution for group scheduling
+	 *
+	 * load_stamp is the last time we updated the load average
+	 * load_last is the last time we updated the load average and saw load
+	 * load_unacc_exec_time is currently unaccounted execution time
 	 */
-	unsigned long shares;
+	u64 load_avg;
+	u64 load_period;
+	u64 load_stamp, load_last, load_unacc_exec_time;
 
-	/*
-	 * load.weight at the time we set shares
-	 */
-	unsigned long rq_weight;
+	unsigned long load_contribution;
 #endif
 #endif
 };
@@ -605,11 +608,14 @@ static inline int cpu_of(struct rq *rq)
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
+	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
-	return container_of(css, struct task_group, css);
+	tg = container_of(css, struct task_group, css);
+
+	return autogroup_task_group(p, tg);
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -793,20 +799,6 @@ late_initcall(sched_init_debug);
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
- * ratelimit for updating the group shares.
- * default: 0.25ms
- */
-unsigned int sysctl_sched_shares_ratelimit = 250000;
-unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
-
-/*
- * Inject some fuzzyness into changing the per-cpu group shares
- * this avoids remote rq-locks at the expense of fairness.
- * default: 4
- */
-unsigned int sysctl_sched_shares_thresh = 4;
-
-/*
  * period over which we average the RT time consumption, measured
  * in ms.
  *
@@ -1355,6 +1347,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
 	lw->inv_weight = 0;
 }
 
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+	lw->weight = w;
+	lw->inv_weight = 0;
+}
+
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
  * of tasks with abnormal "nice" values across CPUs the contribution that
@@ -1543,101 +1541,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static __read_mostly unsigned long __percpu *update_shares_data;
-
-static void __set_se_shares(struct sched_entity *se, unsigned long shares);
-
-/*
- * Calculate and set the cpu's group shares.
- */
-static void update_group_shares_cpu(struct task_group *tg, int cpu,
-				    unsigned long sd_shares,
-				    unsigned long sd_rq_weight,
-				    unsigned long *usd_rq_weight)
-{
-	unsigned long shares, rq_weight;
-	int boost = 0;
-
-	rq_weight = usd_rq_weight[cpu];
-	if (!rq_weight) {
-		boost = 1;
-		rq_weight = NICE_0_LOAD;
-	}
-
-	/*
-	 *             \Sum_j shares_j * rq_weight_i
-	 * shares_i =  -----------------------------
-	 *                  \Sum_j rq_weight_j
-	 */
-	shares = (sd_shares * rq_weight) / sd_rq_weight;
-	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
-
-	if (abs(shares - tg->se[cpu]->load.weight) >
-			sysctl_sched_shares_thresh) {
-		struct rq *rq = cpu_rq(cpu);
-		unsigned long flags;
-
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
-		tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
-		__set_se_shares(tg->se[cpu], shares);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-	}
-}
-
-/*
- * Re-compute the task group their per cpu shares over the given domain.
- * This needs to be done in a bottom-up fashion because the rq weight of a
- * parent group depends on the shares of its child groups.
- */
-static int tg_shares_up(struct task_group *tg, void *data)
-{
-	unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
-	unsigned long *usd_rq_weight;
-	struct sched_domain *sd = data;
-	unsigned long flags;
-	int i;
-
-	if (!tg->se[0])
-		return 0;
-
-	local_irq_save(flags);
-	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;
-
-		rq_weight += weight;
-		/*
-		 * If there are currently no tasks on the cpu pretend there
-		 * is one of average load so that when a new task gets to
-		 * run here it will not get delayed by group starvation.
-		 */
-		if (!weight)
-			weight = NICE_0_LOAD;
-
-		sum_weight += weight;
-		shares += tg->cfs_rq[i]->shares;
-	}
-
-	if (!rq_weight)
-		rq_weight = sum_weight;
-
-	if ((!shares && rq_weight) || shares > tg->shares)
-		shares = tg->shares;
-
-	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
-		shares = tg->shares;
-
-	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
 /*
  * Compute the cpu's hierarchical load factor for each task group.
  * This needs to be done in a top-down fashion because the load of a child
@@ -1652,7 +1555,7 @@ static int tg_load_down(struct task_group *tg, void *data)
 		load = cpu_rq(cpu)->load.weight;
 	} else {
 		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->cfs_rq[cpu]->shares;
+		load *= tg->se[cpu]->load.weight;
 		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
 	}
 
@@ -1661,34 +1564,11 @@ static int tg_load_down(struct task_group *tg, void *data)
 	return 0;
 }
 
-static void update_shares(struct sched_domain *sd)
-{
-	s64 elapsed;
-	u64 now;
-
-	if (root_task_group_empty())
-		return;
-
-	now = local_clock();
-	elapsed = now - sd->last_update;
-
-	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
-		sd->last_update = now;
-		walk_tg_tree(tg_nop, tg_shares_up, sd);
-	}
-}
-
 static void update_h_load(long cpu)
 {
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
-#else
-
-static inline void update_shares(struct sched_domain *sd)
-{
-}
-
 #endif
 
 #ifdef CONFIG_PREEMPT
@@ -1810,15 +1690,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-#ifdef CONFIG_SMP
-	cfs_rq->shares = shares;
-#endif
-}
-#endif
-
 static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
@@ -2063,6 +1934,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_autogroup.c"
 #include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
@@ -2255,10 +2127,8 @@ static int migration_cpu_stop(void *data);
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static bool migrate_task(struct task_struct *p, int dest_cpu)
+static bool migrate_task(struct task_struct *p, struct rq *rq)
 {
-	struct rq *rq = task_rq(p);
-
 	/*
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
@@ -2438,18 +2308,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		return dest_cpu;
 
 	/* No more Mr. Nice Guy. */
-	if (unlikely(dest_cpu >= nr_cpu_ids)) {
-		dest_cpu = cpuset_cpus_allowed_fallback(p);
-		/*
-		 * Don't tell them about moving exiting tasks or
-		 * kernel threads (both mm NULL), since they never
-		 * leave kernel.
-		 */
-		if (p->mm && printk_ratelimit()) {
-			printk(KERN_INFO "process %d (%s) no "
-			       "longer affine to cpu%d\n",
-			       task_pid_nr(p), p->comm, cpu);
-		}
+	dest_cpu = cpuset_cpus_allowed_fallback(p);
+	/*
+	 * Don't tell them about moving exiting tasks or
+	 * kernel threads (both mm NULL), since they never
+	 * leave kernel.
+	 */
+	if (p->mm && printk_ratelimit()) {
+		printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+				task_pid_nr(p), p->comm, cpu);
 	}
 
 	return dest_cpu;
@@ -2785,7 +2652,9 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
+#ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+#endif
 
 	put_cpu();
 }
@@ -3549,7 +3418,7 @@ void sched_exec(void)
 	 * select_task_rq() can race against ->cpus_allowed
 	 */
 	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+	    likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
 		struct migration_arg arg = { p, dest_cpu };
 
 		task_rq_unlock(rq, &flags);
@@ -4214,7 +4083,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 		if (task_thread_info(rq->curr) != owner || need_resched())
 			return 0;
 
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 
 	return 1;
@@ -4526,7 +4395,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
 					  unsigned long timeout)
 {
@@ -4559,7 +4428,7 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_killable_timeout(struct completion *x,
 				     unsigned long timeout)
 {
@@ -4901,7 +4770,7 @@ static bool check_same_owner(struct task_struct *p)
 }
 
 static int __sched_setscheduler(struct task_struct *p, int policy,
-				struct sched_param *param, bool user)
+				const struct sched_param *param, bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
@@ -5056,7 +4925,7 @@ recheck:
  * NOTE that the task may be already dead.
  */
 int sched_setscheduler(struct task_struct *p, int policy,
-		       struct sched_param *param)
+		       const struct sched_param *param)
 {
 	return __sched_setscheduler(p, policy, param, true);
 }
@@ -5074,7 +4943,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
  * but our caller might not have that capability.
  */
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
-			       struct sched_param *param)
+			       const struct sched_param *param)
 {
 	return __sched_setscheduler(p, policy, param, false);
 }
@@ -5590,7 +5459,7 @@ void sched_show_task(struct task_struct *p)
 	unsigned state;
 
 	state = p->state ? __ffs(p->state) + 1 : 0;
-	printk(KERN_INFO "%-13.13s %c", p->comm,
+	printk(KERN_INFO "%-15.15s %c", p->comm,
 		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
 #if BITS_PER_LONG == 32
 	if (state == TASK_RUNNING)
@@ -5754,7 +5623,6 @@ static void update_sysctl(void)
 	SET_SYSCTL(sched_min_granularity);
 	SET_SYSCTL(sched_latency);
 	SET_SYSCTL(sched_wakeup_granularity);
-	SET_SYSCTL(sched_shares_ratelimit);
 #undef SET_SYSCTL
 }
 
@@ -5830,7 +5698,7 @@ again:
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (migrate_task(p, dest_cpu)) {
+	if (migrate_task(p, rq)) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, &flags);
@@ -5912,29 +5780,20 @@ static int migration_cpu_stop(void *data)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
 /*
- * Figure out where task on dead CPU should go, use force if necessary.
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
  */
-void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void idle_task_exit(void)
 {
-	struct rq *rq = cpu_rq(dead_cpu);
-	int needs_cpu, uninitialized_var(dest_cpu);
-	unsigned long flags;
+	struct mm_struct *mm = current->active_mm;
 
-	local_irq_save(flags);
+	BUG_ON(cpu_online(smp_processor_id()));
 
-	raw_spin_lock(&rq->lock);
-	needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
-	if (needs_cpu)
-		dest_cpu = select_fallback_rq(dead_cpu, p);
-	raw_spin_unlock(&rq->lock);
-	/*
-	 * It can only fail if we race with set_cpus_allowed(),
-	 * in the racer should migrate the task anyway.
-	 */
-	if (needs_cpu)
-		__migrate_task(p, dead_cpu, dest_cpu);
-	local_irq_restore(flags);
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
 }
 
 /*
@@ -5947,128 +5806,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 static void migrate_nr_uninterruptible(struct rq *rq_src)
 {
 	struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-	unsigned long flags;
 
-	local_irq_save(flags);
-	double_rq_lock(rq_src, rq_dest);
 	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
 	rq_src->nr_uninterruptible = 0;
-	double_rq_unlock(rq_src, rq_dest);
-	local_irq_restore(flags);
-}
-
-/* Run through task list and migrate tasks from the dead cpu. */
-static void migrate_live_tasks(int src_cpu)
-{
-	struct task_struct *p, *t;
-
-	read_lock(&tasklist_lock);
-
-	do_each_thread(t, p) {
-		if (p == current)
-			continue;
-
-		if (task_cpu(p) == src_cpu)
-			move_task_off_dead_cpu(src_cpu, p);
-	} while_each_thread(t, p);
-
-	read_unlock(&tasklist_lock);
 }
 
 /*
- * Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible.
- * Used by CPU offline code.
+ * remove the tasks which were accounted by rq from calc_load_tasks.
  */
-void sched_idle_next(void)
+static void calc_global_load_remove(struct rq *rq)
 {
-	int this_cpu = smp_processor_id();
-	struct rq *rq = cpu_rq(this_cpu);
-	struct task_struct *p = rq->idle;
-	unsigned long flags;
-
-	/* cpu has to be offline */
-	BUG_ON(cpu_online(this_cpu));
-
-	/*
-	 * Strictly not necessary since rest of the CPUs are stopped by now
-	 * and interrupts disabled on the current cpu.
-	 */
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
-	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-
-	activate_task(rq, p, 0);
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+	rq->calc_load_active = 0;
 }
 
 /*
- * Ensures that the idle task is using init_mm right before its cpu goes
- * offline.
+ * Migrate all tasks from the rq, sleeping tasks will be migrated by
+ * try_to_wake_up()->select_task_rq().
+ *
+ * Called with rq->lock held even though we'er in stop_machine() and
+ * there's no concurrency possible, we hold the required locks anyway
+ * because of lock validation efforts.
  */
-void idle_task_exit(void)
-{
-	struct mm_struct *mm = current->active_mm;
-
-	BUG_ON(cpu_online(smp_processor_id()));
-
-	if (mm != &init_mm)
-		switch_mm(mm, &init_mm, current);
-	mmdrop(mm);
-}
-
-/* called under rq->lock with disabled interrupts */
-static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+static void migrate_tasks(unsigned int dead_cpu)
 {
 	struct rq *rq = cpu_rq(dead_cpu);
-
-	/* Must be exiting, otherwise would be on tasklist. */
-	BUG_ON(!p->exit_state);
-
-	/* Cannot have done final schedule yet: would have vanished. */
-	BUG_ON(p->state == TASK_DEAD);
-
-	get_task_struct(p);
+	struct task_struct *next, *stop = rq->stop;
+	int dest_cpu;
 
 	/*
-	 * Drop lock around migration; if someone else moves it,
-	 * that's OK. No task can be added to this CPU, so iteration is
-	 * fine.
+	 * Fudge the rq selection such that the below task selection loop
+	 * doesn't get stuck on the currently eligible stop task.
+	 *
+	 * We're currently inside stop_machine() and the rq is either stuck
+	 * in the stop_machine_cpu_stop() loop, or we're executing this code,
+	 * either way we should never end up calling schedule() until we're
+	 * done here.
 	 */
-	raw_spin_unlock_irq(&rq->lock);
-	move_task_off_dead_cpu(dead_cpu, p);
-	raw_spin_lock_irq(&rq->lock);
-
-	put_task_struct(p);
-}
-
-/* release_task() removes task from tasklist, so we won't find dead tasks. */
-static void migrate_dead_tasks(unsigned int dead_cpu)
-{
-	struct rq *rq = cpu_rq(dead_cpu);
-	struct task_struct *next;
+	rq->stop = NULL;
 
 	for ( ; ; ) {
-		if (!rq->nr_running)
+		/*
+		 * There's this thread running, bail when that's the only
+		 * remaining thread.
+		 */
+		if (rq->nr_running == 1)
 			break;
+
 		next = pick_next_task(rq);
-		if (!next)
-			break;
+		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
-		migrate_dead(dead_cpu, next);
 
+		/* Find suitable destination for @next, with force if needed. */
+		dest_cpu = select_fallback_rq(dead_cpu, next);
+		raw_spin_unlock(&rq->lock);
+
+		__migrate_task(next, dead_cpu, dest_cpu);
+
+		raw_spin_lock(&rq->lock);
 	}
-}
 
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
- */
-static void calc_global_load_remove(struct rq *rq)
-{
-	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
-	rq->calc_load_active = 0;
+	rq->stop = stop;
 }
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -6278,15 +6078,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	unsigned long flags;
 	struct rq *rq = cpu_rq(cpu);
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
 		rq->calc_load_update = calc_load_update;
 		break;
 
 	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
@@ -6298,30 +6096,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		migrate_live_tasks(cpu);
-		/* Idle task back to normal (off runqueue, low prio) */
-		raw_spin_lock_irq(&rq->lock);
-		deactivate_task(rq, rq->idle, 0);
-		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
-		rq->idle->sched_class = &idle_sched_class;
-		migrate_dead_tasks(cpu);
-		raw_spin_unlock_irq(&rq->lock);
-		migrate_nr_uninterruptible(rq);
-		BUG_ON(rq->nr_running != 0);
-		calc_global_load_remove(rq);
-		break;
-
 	case CPU_DYING:
-	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 			set_rq_offline(rq);
 		}
+		migrate_tasks(cpu);
+		BUG_ON(rq->nr_running != 1); /* the migration thread */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+		migrate_nr_uninterruptible(rq);
+		calc_global_load_remove(rq);
 		break;
 #endif
 	}
@@ -8052,15 +7839,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
-				struct sched_entity *se, int cpu, int add,
+				struct sched_entity *se, int cpu,
 				struct sched_entity *parent)
 {
 	struct rq *rq = cpu_rq(cpu);
 	tg->cfs_rq[cpu] = cfs_rq;
 	init_cfs_rq(cfs_rq, rq);
 	cfs_rq->tg = tg;
-	if (add)
-		list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
 
 	tg->se[cpu] = se;
 	/* se could be NULL for init_task_group */
@@ -8073,15 +7858,14 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	se->load.weight = tg->shares;
-	se->load.inv_weight = 0;
+	update_load_set(&se->load, 0);
 	se->parent = parent;
 }
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
-		struct sched_rt_entity *rt_se, int cpu, int add,
+		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -8090,8 +7874,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	init_rt_rq(rt_rq, rq);
 	rt_rq->tg = tg;
 	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
-	if (add)
-		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
 
 	tg->rt_se[cpu] = rt_se;
 	if (!rt_se)
@@ -8164,13 +7946,9 @@ void __init sched_init(void)
 #ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
-
+	autogroup_init(&init_task);
 #endif /* CONFIG_CGROUP_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;
 
@@ -8184,7 +7962,6 @@ void __init sched_init(void)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		init_task_group.shares = init_task_group_load;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
 		/*
 		 * How much cpu bandwidth does init_task_group get?
 		 *
@@ -8204,16 +7981,13 @@ void __init sched_init(void)
 		 * We achieve this by letting init_task_group's tasks sit
 		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
 		 */
-		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#endif
+		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
 		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
-		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#endif
+		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, NULL);
 #endif