1 files changed, 324 insertions, 719 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index c4b3410d68d3..0516af415085 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,7 +231,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 #endif
 
 /*
- * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * sched_domains_mutex serializes calls to init_sched_domains,
  * detach_destroy_domains and partition_sched_domains.
  */
 static DEFINE_MUTEX(sched_domains_mutex);
@@ -328,7 +328,9 @@ struct cfs_rq {
 	 */
 	struct sched_entity *curr, *next, *last, *skip;
 
+#ifdef	CONFIG_SCHED_DEBUG
 	unsigned int nr_spread_over;
+#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
@@ -420,6 +422,7 @@ struct rt_rq {
  */
 struct root_domain {
 	atomic_t refcount;
+	struct rcu_head rcu;
 	cpumask_var_t span;
 	cpumask_var_t online;
 
@@ -463,7 +466,7 @@ struct rq {
 	u64 nohz_stamp;
 	unsigned char nohz_balance_kick;
 #endif
-	unsigned int skip_clock_update;
+	int skip_clock_update;
 
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
@@ -578,7 +581,7 @@ static inline int cpu_of(struct rq *rq)
 
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
-			      rcu_read_lock_sched_held() || \
+			      rcu_read_lock_held() || \
 			      lockdep_is_held(&sched_domains_mutex))
 
 /*
@@ -649,7 +652,7 @@ static void update_rq_clock(struct rq *rq)
 {
 	s64 delta;
 
-	if (rq->skip_clock_update)
+	if (rq->skip_clock_update > 0)
 		return;
 
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
@@ -1207,11 +1210,17 @@ int get_nohz_timer_target(void)
 	int i;
 	struct sched_domain *sd;
 
+	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd))
-			if (!idle_cpu(i))
-				return i;
+		for_each_cpu(i, sched_domain_span(sd)) {
+			if (!idle_cpu(i)) {
+				cpu = i;
+				goto unlock;
+			}
+		}
 	}
+unlock:
+	rcu_read_unlock();
 	return cpu;
 }
 /*
@@ -1321,15 +1330,15 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
 	u64 tmp;
 
+	tmp = (u64)delta_exec * weight;
+
 	if (!lw->inv_weight) {
 		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
 			lw->inv_weight = 1;
 		else
-			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
-				/ (lw->weight+1);
+			lw->inv_weight = WMULT_CONST / lw->weight;
 	}
 
-	tmp = (u64)delta_exec * weight;
 	/*
 	 * Check whether we'd overflow the 64-bit multiplication:
 	 */
@@ -2199,21 +2208,6 @@ struct migration_arg {
 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 need_migrate_task(struct task_struct *p)
-{
-	/*
-	 * If the task is not on a runqueue (and not running), then
-	 * the next wake-up will properly place the task.
-	 */
-	bool running = p->on_rq || p->on_cpu;
-	smp_rmb(); /* finish_lock_switch() */
-	return running;
-}
-
-/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2429,12 +2423,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		struct sched_domain *sd;
 
 		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+		rcu_read_lock();
 		for_each_domain(this_cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 				schedstat_inc(sd, ttwu_wake_remote);
 				break;
 			}
 		}
+		rcu_read_unlock();
 	}
 #endif /* CONFIG_SMP */
 
@@ -2745,7 +2741,7 @@ static void __sched_fork(struct task_struct *p)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p, int clone_flags)
+void sched_fork(struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
@@ -2827,7 +2823,7 @@ void sched_fork(struct task_struct *p, int clone_flags)
  * that must be done for every newly created context, then puts the task
  * on the runqueue and wakes it.
  */
-void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
+void wake_up_new_task(struct task_struct *p)
 {
 	unsigned long flags;
 	struct rq *rq;
@@ -4008,9 +4004,6 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
- *
- * It also gets called by the fork code, when changing the parent's
- * timeslices.
  */
 void scheduler_tick(void)
 {
@@ -4130,17 +4123,11 @@ static inline void schedule_debug(struct task_struct *prev)
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
 	schedstat_inc(this_rq(), sched_count);
-#ifdef CONFIG_SCHEDSTATS
-	if (unlikely(prev->lock_depth >= 0)) {
-		schedstat_inc(this_rq(), rq_sched_info.bkl_count);
-		schedstat_inc(prev, sched_info.bkl_count);
-	}
-#endif
 }
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->on_rq)
+	if (prev->on_rq || rq->skip_clock_update < 0)
 		update_rq_clock(rq);
 	prev->sched_class->put_prev_task(rq, prev);
 }
@@ -5861,11 +5848,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-#if defined(CONFIG_PREEMPT)
-	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
-#else
 	task_thread_info(idle)->preempt_count = 0;
-#endif
+
 	/*
 	 * The idle tasks have their own, simple scheduling class:
 	 */
@@ -5962,13 +5946,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 	rq = task_rq_lock(p, &flags);
 
+	if (cpumask_equal(&p->cpus_allowed, new_mask))
+		goto out;
+
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
-		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -5985,7 +5971,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (need_migrate_task(p)) {
+	if (p->on_rq) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &flags);
@@ -6465,6 +6451,8 @@ early_initcall(migration_init);
 
 #ifdef CONFIG_SMP
 
+static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
+
 #ifdef CONFIG_SCHED_DEBUG
 
 static __read_mostly int sched_domain_debug_enabled;
@@ -6560,7 +6548,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 static void sched_domain_debug(struct sched_domain *sd, int cpu)
 {
-	cpumask_var_t groupmask;
 	int level = 0;
 
 	if (!sched_domain_debug_enabled)
@@ -6573,20 +6560,14 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 
 	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
 
-	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
-		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
-		return;
-	}
-
 	for (;;) {
-		if (sched_domain_debug_one(sd, cpu, level, groupmask))
+		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
 			break;
 		level++;
 		sd = sd->parent;
 		if (!sd)
 			break;
 	}
-	free_cpumask_var(groupmask);
 }
 #else /* !CONFIG_SCHED_DEBUG */
 # define sched_domain_debug(sd, cpu) do { } while (0)
@@ -6643,12 +6624,11 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
-static void free_rootdomain(struct root_domain *rd)
+static void free_rootdomain(struct rcu_head *rcu)
 {
-	synchronize_sched();
+	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
-
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -6689,7 +6669,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	if (old_rd)
-		free_rootdomain(old_rd);
+		call_rcu_sched(&old_rd->rcu, free_rootdomain);
 }
 
 static int init_rootdomain(struct root_domain *rd)
@@ -6740,6 +6720,25 @@ static struct root_domain *alloc_rootdomain(void)
 	return rd;
 }
 
+static void free_sched_domain(struct rcu_head *rcu)
+{
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+	if (atomic_dec_and_test(&sd->groups->ref))
+		kfree(sd->groups);
+	kfree(sd);
+}
+
+static void destroy_sched_domain(struct sched_domain *sd, int cpu)
+{
+	call_rcu(&sd->rcu, free_sched_domain);
+}
+
+static void destroy_sched_domains(struct sched_domain *sd, int cpu)
+{
+	for (; sd; sd = sd->parent)
+		destroy_sched_domain(sd, cpu);
+}
+
 /*
  * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
  * hold the hotplug lock.
@@ -6750,9 +6749,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
 
-	for (tmp = sd; tmp; tmp = tmp->parent)
-		tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
-
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
 		struct sched_domain *parent = tmp->parent;
@@ -6763,12 +6759,15 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			tmp->parent = parent->parent;
 			if (parent->parent)
 				parent->parent->child = tmp;
+			destroy_sched_domain(parent, cpu);
 		} else
 			tmp = tmp->parent;
 	}
 
 	if (sd && sd_degenerate(sd)) {
+		tmp = sd;
 		sd = sd->parent;
+		destroy_sched_domain(tmp, cpu);
 		if (sd)
 			sd->child = NULL;
 	}
@@ -6776,7 +6775,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);
+	tmp = rq->sd;
 	rcu_assign_pointer(rq->sd, sd);
+	destroy_sched_domains(tmp, cpu);
 }
 
 /* cpus with isolated domains */
@@ -6792,56 +6793,6 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-/*
- * init_sched_build_groups takes the cpumask we wish to span, and a pointer
- * to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
- * (due to the fact that we keep track of groups covered with a struct cpumask).
- *
- * init_sched_build_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_power to 0.
- */
-static void
-init_sched_build_groups(const struct cpumask *span,
-			const struct cpumask *cpu_map,
-			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
-					struct sched_group **sg,
-					struct cpumask *tmpmask),
-			struct cpumask *covered, struct cpumask *tmpmask)
-{
-	struct sched_group *first = NULL, *last = NULL;
-	int i;
-
-	cpumask_clear(covered);
-
-	for_each_cpu(i, span) {
-		struct sched_group *sg;
-		int group = group_fn(i, cpu_map, &sg, tmpmask);
-		int j;
-
-		if (cpumask_test_cpu(i, covered))
-			continue;
-
-		cpumask_clear(sched_group_cpus(sg));
-		sg->cpu_power = 0;
-
-		for_each_cpu(j, span) {
-			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
-		if (!first)
-			first = sg;
-		if (last)
-			last->next = sg;
-		last = sg;
-	}
-	last->next = first;
-}
-
 #define SD_NODES_PER_DOMAIN 16
 
 #ifdef CONFIG_NUMA
@@ -6858,7 +6809,7 @@ init_sched_build_groups(const struct cpumask *span,
  */
 static int find_next_best_node(int node, nodemask_t *used_nodes)
 {
-	int i, n, val, min_val, best_node = 0;
+	int i, n, val, min_val, best_node = -1;
 
 	min_val = INT_MAX;
 
@@ -6882,7 +6833,8 @@ static int find_next_best_node(int node, nodemask_t *used_nodes)
 		}
 	}
 
-	node_set(best_node, *used_nodes);
+	if (best_node != -1)
+		node_set(best_node, *used_nodes);
 	return best_node;
 }
 
@@ -6908,315 +6860,130 @@ static void sched_domain_node_span(int node, struct cpumask *span)
 
 	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
 		int next_node = find_next_best_node(node, &used_nodes);
-
+		if (next_node < 0)
+			break;
 		cpumask_or(span, span, cpumask_of_node(next_node));
 	}
 }
+
+static const struct cpumask *cpu_node_mask(int cpu)
+{
+	lockdep_assert_held(&sched_domains_mutex);
+
+	sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask);
+
+	return sched_domains_tmpmask;
+}
+
+static const struct cpumask *cpu_allnodes_mask(int cpu)
+{
+	return cpu_possible_mask;
+}
 #endif /* CONFIG_NUMA */
 
-int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+static const struct cpumask *cpu_cpu_mask(int cpu)
+{
+	return cpumask_of_node(cpu_to_node(cpu));
+}
 
-/*
- * The cpus mask in sched_group and sched_domain hangs off the end.
- *
- * ( See the the comments in include/linux/sched.h:struct sched_group
- *   and struct sched_domain. )
- */
-struct static_sched_group {
-	struct sched_group sg;
-	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
-};
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
-struct static_sched_domain {
-	struct sched_domain sd;
-	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_group **__percpu sg;
 };
 
 struct s_data {
-#ifdef CONFIG_NUMA
-	int			sd_allnodes;
-	cpumask_var_t		domainspan;
-	cpumask_var_t		covered;
-	cpumask_var_t		notcovered;
-#endif
-	cpumask_var_t		nodemask;
-	cpumask_var_t		this_sibling_map;
-	cpumask_var_t		this_core_map;
-	cpumask_var_t		this_book_map;
-	cpumask_var_t		send_covered;
-	cpumask_var_t		tmpmask;
-	struct sched_group	**sched_group_nodes;
+	struct sched_domain ** __percpu sd;
 	struct root_domain	*rd;
 };
 
 enum s_alloc {
-	sa_sched_groups = 0,
 	sa_rootdomain,
-	sa_tmpmask,
-	sa_send_covered,
-	sa_this_book_map,
-	sa_this_core_map,
-	sa_this_sibling_map,
-	sa_nodemask,
-	sa_sched_group_nodes,
-#ifdef CONFIG_NUMA
-	sa_notcovered,
-	sa_covered,
-	sa_domainspan,
-#endif
+	sa_sd,
+	sa_sd_storage,
 	sa_none,
 };
 
-/*
- * SMT sched-domains:
- */
-#ifdef CONFIG_SCHED_SMT
-static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
+struct sched_domain_topology_level;
 
-static int
-cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
-		 struct sched_group **sg, struct cpumask *unused)
-{
-	if (sg)
-		*sg = &per_cpu(sched_groups, cpu).sg;
-	return cpu;
-}
-#endif /* CONFIG_SCHED_SMT */
-
-/*
- * multi-core sched-domains:
- */
-#ifdef CONFIG_SCHED_MC
-static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
+typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 
-static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
-{
-	int group;
-#ifdef CONFIG_SCHED_SMT
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#else
-	group = cpu;
-#endif
-	if (sg)
-		*sg = &per_cpu(sched_group_core, group).sg;
-	return group;
-}
-#endif /* CONFIG_SCHED_MC */
+struct sched_domain_topology_level {
+	sched_domain_init_f init;
+	sched_domain_mask_f mask;
+	struct sd_data      data;
+};
 
 /*
- * book sched-domains:
+ * Assumes the sched_domain tree is fully constructed
  */
-#ifdef CONFIG_SCHED_BOOK
-static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
-
-static int
-cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
+static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 {
-	int group = cpu;
-#ifdef CONFIG_SCHED_MC
-	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#endif
-	if (sg)
-		*sg = &per_cpu(sched_group_book, group).sg;
-	return group;
-}
-#endif /* CONFIG_SCHED_BOOK */
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	struct sched_domain *child = sd->child;
 
-static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
+	if (child)
+		cpu = cpumask_first(sched_domain_span(child));
 
-static int
-cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
-{
-	int group;
-#ifdef CONFIG_SCHED_BOOK
-	cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_MC)
-	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#else
-	group = cpu;
-#endif
 	if (sg)
-		*sg = &per_cpu(sched_group_phys, group).sg;
-	return group;
+		*sg = *per_cpu_ptr(sdd->sg, cpu);
+
+	return cpu;
 }
 
-#ifdef CONFIG_NUMA
 /*
- * The init_sched_build_groups can't handle what we want to do with node
- * groups, so roll our own. Now each node has its own list of groups which
- * gets dynamically allocated.
+ * build_sched_groups takes the cpumask we wish to span, and a pointer
+ * to a function which identifies what group(along with sched group) a CPU
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
+ *
+ * build_sched_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
  */
-static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
-static struct sched_group ***sched_group_nodes_bycpu;
-
-static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
-
-static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
-				 struct sched_group **sg,
-				 struct cpumask *nodemask)
-{
-	int group;
-
-	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
-	group = cpumask_first(nodemask);
-
-	if (sg)
-		*sg = &per_cpu(sched_group_allnodes, group).sg;
-	return group;
-}
-
-static void init_numa_sched_groups_power(struct sched_group *group_head)
-{
-	struct sched_group *sg = group_head;
-	int j;
-
-	if (!sg)
-		return;
-	do {
-		for_each_cpu(j, sched_group_cpus(sg)) {
-			struct sched_domain *sd;
-
-			sd = &per_cpu(phys_domains, j).sd;
-			if (j != group_first_cpu(sd->groups)) {
-				/*
-				 * Only add "power" once for each
-				 * physical package.
-				 */
-				continue;
-			}
-
-			sg->cpu_power += sd->groups->cpu_power;
-		}
-		sg = sg->next;
-	} while (sg != group_head);
-}
-
-static int build_numa_sched_groups(struct s_data *d,
-				   const struct cpumask *cpu_map, int num)
+static void
+build_sched_groups(struct sched_domain *sd)
 {
-	struct sched_domain *sd;
-	struct sched_group *sg, *prev;
-	int n, j;
-
-	cpumask_clear(d->covered);
-	cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
-	if (cpumask_empty(d->nodemask)) {
-		d->sched_group_nodes[num] = NULL;
-		goto out;
-	}
-
-	sched_domain_node_span(num, d->domainspan);
-	cpumask_and(d->domainspan, d->domainspan, cpu_map);
-
-	sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-			  GFP_KERNEL, num);
-	if (!sg) {
-		printk(KERN_WARNING "Can not alloc domain group for node %d\n",
-		       num);
-		return -ENOMEM;
-	}
-	d->sched_group_nodes[num] = sg;
-
-	for_each_cpu(j, d->nodemask) {
-		sd = &per_cpu(node_domains, j).sd;
-		sd->groups = sg;
-	}
-
-	sg->cpu_power = 0;
-	cpumask_copy(sched_group_cpus(sg), d->nodemask);
-	sg->next = sg;
-	cpumask_or(d->covered, d->covered, d->nodemask);
+	struct sched_group *first = NULL, *last = NULL;
+	struct sd_data *sdd = sd->private;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered;
+	int i;
 
-	prev = sg;
-	for (j = 0; j < nr_node_ids; j++) {
-		n = (num + j) % nr_node_ids;
-		cpumask_complement(d->notcovered, d->covered);
-		cpumask_and(d->tmpmask, d->notcovered, cpu_map);
-		cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
-		if (cpumask_empty(d->tmpmask))
-			break;
-		cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
-		if (cpumask_empty(d->tmpmask))
-			continue;
-		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				  GFP_KERNEL, num);
-		if (!sg) {
-			printk(KERN_WARNING
-			       "Can not alloc domain group for node %d\n", j);
-			return -ENOMEM;
-		}
-		sg->cpu_power = 0;
-		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
-		sg->next = prev->next;
-		cpumask_or(d->covered, d->covered, d->tmpmask);
-		prev->next = sg;
-		prev = sg;
-	}
-out:
-	return 0;
-}
-#endif /* CONFIG_NUMA */
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
 
-#ifdef CONFIG_NUMA
-/* Free memory allocated for various sched_group structures */
-static void free_sched_groups(const struct cpumask *cpu_map,
-			      struct cpumask *nodemask)
-{
-	int cpu, i;
+	cpumask_clear(covered);
 
-	for_each_cpu(cpu, cpu_map) {
-		struct sched_group **sched_group_nodes
-			= sched_group_nodes_bycpu[cpu];
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group = get_group(i, sdd, &sg);
+		int j;
 
-		if (!sched_group_nodes)
+		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		for (i = 0; i < nr_node_ids; i++) {
-			struct sched_group *oldsg, *sg = sched_group_nodes[i];
+		cpumask_clear(sched_group_cpus(sg));
+		sg->cpu_power = 0;
 
-			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-			if (cpumask_empty(nodemask))
+		for_each_cpu(j, span) {
+			if (get_group(j, sdd, NULL) != group)
 				continue;
 
-			if (sg == NULL)
-				continue;
-			sg = sg->next;
-next_sg:
-			oldsg = sg;
-			sg = sg->next;
-			kfree(oldsg);
-			if (oldsg != sched_group_nodes[i])
-				goto next_sg;
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
 		}
-		kfree(sched_group_nodes);
-		sched_group_nodes_bycpu[cpu] = NULL;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
 	}
+	last->next = first;
 }
-#else /* !CONFIG_NUMA */
-static void free_sched_groups(const struct cpumask *cpu_map,
-			      struct cpumask *nodemask)
-{
-}
-#endif /* CONFIG_NUMA */
 
 /*
  * Initialize sched groups cpu_power.
@@ -7230,11 +6997,6 @@ static void free_sched_groups(const struct cpumask *cpu_map,
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
-	struct sched_domain *child;
-	struct sched_group *group;
-	long power;
-	int weight;
-
 	WARN_ON(!sd || !sd->groups);
 
 	if (cpu != group_first_cpu(sd->groups))
@@ -7242,36 +7004,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
 
-	child = sd->child;
-
-	sd->groups->cpu_power = 0;
-
-	if (!child) {
-		power = SCHED_LOAD_SCALE;
-		weight = cpumask_weight(sched_domain_span(sd));
-		/*
-		 * SMT siblings share the power of a single core.
-		 * Usually multiple threads get a better yield out of
-		 * that one core than a single thread would have,
-		 * reflect that in sd->smt_gain.
-		 */
-		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-			power *= sd->smt_gain;
-			power /= weight;
-			power >>= SCHED_LOAD_SHIFT;
-		}
-		sd->groups->cpu_power += power;
-		return;
-	}
-
-	/*
-	 * Add cpu_power of each child group to this groups cpu_power.
-	 */
-	group = child->groups;
-	do {
-		sd->groups->cpu_power += group->cpu_power;
-		group = group->next;
-	} while (group != child->groups);
+	update_group_power(sd, cpu);
 }
 
 /*
@@ -7285,15 +7018,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 # define SD_INIT_NAME(sd, type)		do { } while (0)
 #endif
 
-#define	SD_INIT(sd, type)	sd_init_##type(sd)
-
-#define SD_INIT_FUNC(type)	\
-static noinline void sd_init_##type(struct sched_domain *sd)	\
-{								\
-	memset(sd, 0, sizeof(*sd));				\
-	*sd = SD_##type##_INIT;					\
-	sd->level = SD_LV_##type;				\
-	SD_INIT_NAME(sd, type);					\
+#define SD_INIT_FUNC(type)						\
+static noinline struct sched_domain *					\
+sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
+{									\
+	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
+	*sd = SD_##type##_INIT;						\
+	SD_INIT_NAME(sd, type);						\
+	sd->private = &tl->data;					\
+	return sd;							\
 }
 
 SD_INIT_FUNC(CPU)
@@ -7312,13 +7045,14 @@ SD_INIT_FUNC(CPU)
 #endif
 
 static int default_relax_domain_level = -1;
+int sched_domain_level_max;
 
 static int __init setup_relax_domain_level(char *str)
 {
 	unsigned long val;
 
 	val = simple_strtoul(str, NULL, 0);
-	if (val < SD_LV_MAX)
+	if (val < sched_domain_level_max)
 		default_relax_domain_level = val;
 
 	return 1;
@@ -7346,37 +7080,20 @@ static void set_domain_attribute(struct sched_domain *sd,
 	}
 }
 
+static void __sdt_free(const struct cpumask *cpu_map);
+static int __sdt_alloc(const struct cpumask *cpu_map);
+
 static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 				 const struct cpumask *cpu_map)
 {
 	switch (what) {
-	case sa_sched_groups:
-		free_sched_groups(cpu_map, d->tmpmask); /* fall through */
-		d->sched_group_nodes = NULL;
 	case sa_rootdomain:
-		free_rootdomain(d->rd); /* fall through */
-	case sa_tmpmask:
-		free_cpumask_var(d->tmpmask); /* fall through */
-	case sa_send_covered:
-		free_cpumask_var(d->send_covered); /* fall through */
-	case sa_this_book_map:
-		free_cpumask_var(d->this_book_map); /* fall through */
-	case sa_this_core_map:
-		free_cpumask_var(d->this_core_map); /* fall through */
-	case sa_this_sibling_map:
-		free_cpumask_var(d->this_sibling_map); /* fall through */
-	case sa_nodemask:
-		free_cpumask_var(d->nodemask); /* fall through */
-	case sa_sched_group_nodes:
-#ifdef CONFIG_NUMA
-		kfree(d->sched_group_nodes); /* fall through */
-	case sa_notcovered:
-		free_cpumask_var(d->notcovered); /* fall through */
-	case sa_covered:
-		free_cpumask_var(d->covered); /* fall through */
-	case sa_domainspan:
-		free_cpumask_var(d->domainspan); /* fall through */
-#endif
+		if (!atomic_read(&d->rd->refcount))
+			free_rootdomain(&d->rd->rcu); /* fall through */
+	case sa_sd:
+		free_percpu(d->sd); /* fall through */
+	case sa_sd_storage:
+		__sdt_free(cpu_map); /* fall through */
 	case sa_none:
 		break;
 	}
@@ -7385,308 +7102,212 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
 						   const struct cpumask *cpu_map)
 {
-#ifdef CONFIG_NUMA
-	if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
-		return sa_none;
-	if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
-		return sa_domainspan;
-	if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
-		return sa_covered;
-	/* Allocate the per-node list of sched groups */
-	d->sched_group_nodes = kcalloc(nr_node_ids,
-				      sizeof(struct sched_group *), GFP_KERNEL);
-	if (!d->sched_group_nodes) {
-		printk(KERN_WARNING "Can not alloc sched group node list\n");
-		return sa_notcovered;
-	}
-	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
-#endif
-	if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
-		return sa_sched_group_nodes;
-	if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
-		return sa_nodemask;
-	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
-		return sa_this_sibling_map;
-	if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
-		return sa_this_core_map;
-	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
-		return sa_this_book_map;
-	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
-		return sa_send_covered;
+	memset(d, 0, sizeof(*d));
+
+	if (__sdt_alloc(cpu_map))
+		return sa_sd_storage;
+	d->sd = alloc_percpu(struct sched_domain *);
+	if (!d->sd)
+		return sa_sd_storage;
 	d->rd = alloc_rootdomain();
-	if (!d->rd) {
-		printk(KERN_WARNING "Cannot alloc root domain\n");
-		return sa_tmpmask;
-	}
+	if (!d->rd)
+		return sa_sd;
 	return sa_rootdomain;
 }
 
-static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+/*
+ * NULL the sd_data elements we've used to build the sched_domain and
+ * sched_group structure so that the subsequent __free_domain_allocs()
+ * will not free the data we're using.
+ */
+static void claim_allocations(int cpu, struct sched_domain *sd)
 {
-	struct sched_domain *sd = NULL;
-#ifdef CONFIG_NUMA
-	struct sched_domain *parent;
-
-	d->sd_allnodes = 0;
-	if (cpumask_weight(cpu_map) >
-	    SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
-		sd = &per_cpu(allnodes_domains, i).sd;
-		SD_INIT(sd, ALLNODES);
-		set_domain_attribute(sd, attr);
-		cpumask_copy(sched_domain_span(sd), cpu_map);
-		cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
-		d->sd_allnodes = 1;
-	}
-	parent = sd;
-
-	sd = &per_cpu(node_domains, i).sd;
-	SD_INIT(sd, NODE);
-	set_domain_attribute(sd, attr);
-	sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
-	sd->parent = parent;
-	if (parent)
-		parent->child = sd;
-	cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
-#endif
-	return sd;
-}
+	struct sd_data *sdd = sd->private;
+	struct sched_group *sg = sd->groups;
 
-static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd;
-	sd = &per_cpu(phys_domains, i).sd;
-	SD_INIT(sd, CPU);
-	set_domain_attribute(sd, attr);
-	cpumask_copy(sched_domain_span(sd), d->nodemask);
-	sd->parent = parent;
-	if (parent)
-		parent->child = sd;
-	cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
-	return sd;
-}
+	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
+	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
-static struct sched_domain *__build_book_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_BOOK
-	sd = &per_cpu(book_domains, i).sd;
-	SD_INIT(sd, BOOK);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
-#endif
-	return sd;
+	if (cpu == cpumask_first(sched_group_cpus(sg))) {
+		WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg);
+		*per_cpu_ptr(sdd->sg, cpu) = NULL;
+	}
 }
 
-static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *cpu_smt_mask(int cpu)
 {
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_MC
-	sd = &per_cpu(core_domains, i).sd;
-	SD_INIT(sd, MC);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
-#endif
-	return sd;
+	return topology_thread_cpumask(cpu);
 }
-
-static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_SMT
-	sd = &per_cpu(cpu_domains, i).sd;
-	SD_INIT(sd, SIBLING);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
-	return sd;
-}
 
-static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
-			       const struct cpumask *cpu_map, int cpu)
-{
-	switch (l) {
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	case SD_LV_SIBLING: /* set up CPU (sibling) groups */
-		cpumask_and(d->this_sibling_map, cpu_map,
-			    topology_thread_cpumask(cpu));
-		if (cpu == cpumask_first(d->this_sibling_map))
-			init_sched_build_groups(d->this_sibling_map, cpu_map,
-						&cpu_to_cpu_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_SIBLING, cpu_smt_mask, },
 #endif
 #ifdef CONFIG_SCHED_MC
-	case SD_LV_MC: /* set up multi-core groups */
-		cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
-		if (cpu == cpumask_first(d->this_core_map))
-			init_sched_build_groups(d->this_core_map, cpu_map,
-						&cpu_to_core_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_MC, cpu_coregroup_mask, },
 #endif
 #ifdef CONFIG_SCHED_BOOK
-	case SD_LV_BOOK: /* set up book groups */
-		cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
-		if (cpu == cpumask_first(d->this_book_map))
-			init_sched_build_groups(d->this_book_map, cpu_map,
-						&cpu_to_book_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_BOOK, cpu_book_mask, },
 #endif
-	case SD_LV_CPU: /* set up physical groups */
-		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
-		if (!cpumask_empty(d->nodemask))
-			init_sched_build_groups(d->nodemask, cpu_map,
-						&cpu_to_phys_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_CPU, cpu_cpu_mask, },
 #ifdef CONFIG_NUMA
-	case SD_LV_ALLNODES:
-		init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
-					d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_NODE, cpu_node_mask, },
+	{ sd_init_ALLNODES, cpu_allnodes_mask, },
 #endif
-	default:
-		break;
+	{ NULL, },
+};
+
+static struct sched_domain_topology_level *sched_domain_topology = default_topology;
+
+static int __sdt_alloc(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		sdd->sd = alloc_percpu(struct sched_domain *);
+		if (!sdd->sd)
+			return -ENOMEM;
+
+		sdd->sg = alloc_percpu(struct sched_group *);
+		if (!sdd->sg)
+			return -ENOMEM;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd;
+			struct sched_group *sg;
+
+		       	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sd)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sd, j) = sd;
+
+			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sg)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sg, j) = sg;
+		}
+	}
+
+	return 0;
+}
+
+static void __sdt_free(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		for_each_cpu(j, cpu_map) {
+			kfree(*per_cpu_ptr(sdd->sd, j));
+			kfree(*per_cpu_ptr(sdd->sg, j));
+		}
+		free_percpu(sdd->sd);
+		free_percpu(sdd->sg);
+	}
+}
+
+struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+		struct s_data *d, const struct cpumask *cpu_map,
+		struct sched_domain_attr *attr, struct sched_domain *child,
+		int cpu)
+{
+	struct sched_domain *sd = tl->init(tl, cpu);
+	if (!sd)
+		return child;
+
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	if (child) {
+		sd->level = child->level + 1;
+		sched_domain_level_max = max(sched_domain_level_max, sd->level);
+		child->parent = sd;
 	}
+	sd->child = child;
+
+	return sd;
 }
 
 /*
  * Build sched domains for a given set of cpus and attach the sched domains
  * to the individual cpus
  */
-static int __build_sched_domains(const struct cpumask *cpu_map,
-				 struct sched_domain_attr *attr)
+static int build_sched_domains(const struct cpumask *cpu_map,
+			       struct sched_domain_attr *attr)
 {
 	enum s_alloc alloc_state = sa_none;
-	struct s_data d;
 	struct sched_domain *sd;
-	int i;
-#ifdef CONFIG_NUMA
-	d.sd_allnodes = 0;
-#endif
+	struct s_data d;
+	int i, ret = -ENOMEM;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
 	if (alloc_state != sa_rootdomain)
 		goto error;
-	alloc_state = sa_sched_groups;
 
-	/*
-	 * Set up domains for cpus specified by the cpu_map.
-	 */
+	/* Set up domains for cpus specified by the cpu_map. */
 	for_each_cpu(i, cpu_map) {
-		cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
-			    cpu_map);
-
-		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
-		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
-	}
-
-	for_each_cpu(i, cpu_map) {
-		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
-		build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
-		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
-	}
-
-	/* Set up physical groups */
-	for (i = 0; i < nr_node_ids; i++)
-		build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
+		struct sched_domain_topology_level *tl;
 
-#ifdef CONFIG_NUMA
-	/* Set up node groups */
-	if (d.sd_allnodes)
-		build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
+		sd = NULL;
+		for (tl = sched_domain_topology; tl->init; tl++)
+			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
 
-	for (i = 0; i < nr_node_ids; i++)
-		if (build_numa_sched_groups(&d, cpu_map, i))
-			goto error;
-#endif
+		while (sd->child)
+			sd = sd->child;
 
-	/* Calculate CPU power for physical packages and nodes */
-#ifdef CONFIG_SCHED_SMT
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(cpu_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
-#endif
-#ifdef CONFIG_SCHED_MC
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(core_domains, i).sd;
-		init_sched_groups_power(i, sd);
+		*per_cpu_ptr(d.sd, i) = sd;
 	}
-#endif
-#ifdef CONFIG_SCHED_BOOK
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(book_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
-#endif
 
+	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(phys_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			sd->span_weight = cpumask_weight(sched_domain_span(sd));
+			get_group(i, sd->private, &sd->groups);
+			atomic_inc(&sd->groups->ref);
 
-#ifdef CONFIG_NUMA
-	for (i = 0; i < nr_node_ids; i++)
-		init_numa_sched_groups_power(d.sched_group_nodes[i]);
+			if (i != cpumask_first(sched_domain_span(sd)))
+				continue;
 
-	if (d.sd_allnodes) {
-		struct sched_group *sg;
+			build_sched_groups(sd);
+		}
+	}
+
+	/* Calculate CPU power for physical packages and nodes */
+	for (i = nr_cpumask_bits-1; i >= 0; i--) {
+		if (!cpumask_test_cpu(i, cpu_map))
+			continue;
 
-		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
-								d.tmpmask);
-		init_numa_sched_groups_power(sg);
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			claim_allocations(i, sd);
+			init_sched_groups_power(i, sd);
+		}
 	}
-#endif
 
 	/* Attach the domains */
+	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-#ifdef CONFIG_SCHED_SMT
-		sd = &per_cpu(cpu_domains, i).sd;
-#elif defined(CONFIG_SCHED_MC)
-		sd = &per_cpu(core_domains, i).sd;
-#elif defined(CONFIG_SCHED_BOOK)
-		sd = &per_cpu(book_domains, i).sd;
-#else
-		sd = &per_cpu(phys_domains, i).sd;
-#endif
+		sd = *per_cpu_ptr(d.sd, i);
 		cpu_attach_domain(sd, d.rd, i);
 	}
+	rcu_read_unlock();
 
-	d.sched_group_nodes = NULL; /* don't free this we still need it */
-	__free_domain_allocs(&d, sa_tmpmask, cpu_map);
-	return 0;
-
+	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);
-	return -ENOMEM;
-}
-
-static int build_sched_domains(const struct cpumask *cpu_map)
-{
-	return __build_sched_domains(cpu_map, NULL);
+	return ret;
 }
 
 static cpumask_var_t *doms_cur;	/* current sched domains */
@@ -7741,7 +7362,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
  */
-static int arch_init_sched_domains(const struct cpumask *cpu_map)
+static int init_sched_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
@@ -7752,32 +7373,24 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map)
 		doms_cur = &fallback_doms;
 	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
 	dattr_cur = NULL;
-	err = build_sched_domains(doms_cur[0]);
+	err = build_sched_domains(doms_cur[0], NULL);
 	register_sched_domain_sysctl();
 
 	return err;
 }
 
-static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
-				       struct cpumask *tmpmask)
-{
-	free_sched_groups(cpu_map, tmpmask);
-}
-
 /*
  * Detach sched domains from a group of cpus specified in cpu_map
  * These cpus will now be attached to the NULL domain
  */
 static void detach_destroy_domains(const struct cpumask *cpu_map)
 {
-	/* Save because hotplug lock held. */
-	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
 	int i;
 
+	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
-	synchronize_sched();
-	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
+	rcu_read_unlock();
 }
 
 /* handle null as "default" */
@@ -7866,8 +7479,7 @@ match1:
 				goto match2;
 		}
 		/* no match - add a new doms_new */
-		__build_sched_domains(doms_new[i],
-					dattr_new ? dattr_new + i : NULL);
+		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
 match2:
 		;
 	}
@@ -7886,7 +7498,7 @@ match2:
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-static void arch_reinit_sched_domains(void)
+static void reinit_sched_domains(void)
 {
 	get_online_cpus();
 
@@ -7919,7 +7531,7 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 	else
 		sched_mc_power_savings = level;
 
-	arch_reinit_sched_domains();
+	reinit_sched_domains();
 
 	return count;
 }
@@ -8038,14 +7650,9 @@ void __init sched_init_smp(void)
 	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 **),
-								GFP_KERNEL);
-	BUG_ON(sched_group_nodes_bycpu == NULL);
-#endif
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
-	arch_init_sched_domains(cpu_active_mask);
+	init_sched_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
@@ -8352,6 +7959,7 @@ void __init sched_init(void)
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
 	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_NO_HZ
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT);
@@ -8624,7 +8232,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct rt_rq *rt_rq;
 	struct sched_rt_entity *rt_se;
-	struct rq *rq;
 	int i;
 
 	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8638,8 +8245,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		rt_rq = kzalloc_node(sizeof(struct rt_rq),
 				     GFP_KERNEL, cpu_to_node(i));
 		if (!rt_rq)