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

Pull scheduler changes from Ingo Molnar:
 "The biggest change is the cleanup/simplification of the load-balancer:
  instead of the current practice of architectures twiddling scheduler
  internal data structures and providing the scheduler domains in
  colorfully inconsistent ways, we now have generic scheduler code in
  kernel/sched/core.c:sched_init_numa() that looks at the architecture's
  node_distance() parameters and (while not fully trusting it) deducts a
  NUMA topology from it.

  This inevitably changes balancing behavior - hopefully for the better.

  There are various smaller optimizations, cleanups and fixlets as well"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Taint kernel with TAINT_WARN after sleep-in-atomic bug
  sched: Remove stale power aware scheduling remnants and dysfunctional knobs
  sched/debug: Fix printing large integers on 32-bit platforms
  sched/fair: Improve the ->group_imb logic
  sched/nohz: Fix rq->cpu_load[] calculations
  sched/numa: Don't scale the imbalance
  sched/fair: Revert sched-domain iteration breakage
  sched/x86: Rewrite set_cpu_sibling_map()
  sched/numa: Fix the new NUMA topology bits
  sched/numa: Rewrite the CONFIG_NUMA sched domain support
  sched/fair: Propagate 'struct lb_env' usage into find_busiest_group
  sched/fair: Add some serialization to the sched_domain load-balance walk
  sched/fair: Let minimally loaded cpu balance the group
  sched: Change rq->nr_running to unsigned int
  x86/numa: Check for nonsensical topologies on real hw as well
  x86/numa: Hard partition cpu topology masks on node boundaries
  x86/numa: Allow specifying node_distance() for numa=fake
  x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly
  sched: Update documentation and comments
  sched_rt: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt()

6 files changed, 352 insertions, 608 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d2e2e173d8f..d833cc94eed 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -693,8 +693,6 @@ int tg_nop(struct task_group *tg, void *data)
 }
 #endif
 
-void update_cpu_load(struct rq *this_rq);
-
 static void set_load_weight(struct task_struct *p)
 {
 	int prio = p->static_prio - MAX_RT_PRIO;
@@ -2481,22 +2479,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
  * scheduler tick (TICK_NSEC). With tickless idle this will not be called
  * every tick. We fix it up based on jiffies.
  */
-void update_cpu_load(struct rq *this_rq)
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+			      unsigned long pending_updates)
 {
-	unsigned long this_load = this_rq->load.weight;
-	unsigned long curr_jiffies = jiffies;
-	unsigned long pending_updates;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
 
-	/* Avoid repeated calls on same jiffy, when moving in and out of idle */
-	if (curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
 	/* Update our load: */
 	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
 	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
@@ -2521,9 +2510,45 @@ void update_cpu_load(struct rq *this_rq)
 	sched_avg_update(this_rq);
 }
 
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+void update_idle_cpu_load(struct rq *this_rq)
+{
+	unsigned long curr_jiffies = jiffies;
+	unsigned long load = this_rq->load.weight;
+	unsigned long pending_updates;
+
+	/*
+	 * Bloody broken means of dealing with nohz, but better than nothing..
+	 * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
+	 * update and see 0 difference the one time and 2 the next, even though
+	 * we ticked at roughtly the same rate.
+	 *
+	 * Hence we only use this from nohz_idle_balance() and skip this
+	 * nonsense when called from the scheduler_tick() since that's
+	 * guaranteed a stable rate.
+	 */
+	if (load || curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	this_rq->last_load_update_tick = curr_jiffies;
+
+	__update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from scheduler_tick()
+ */
 static void update_cpu_load_active(struct rq *this_rq)
 {
-	update_cpu_load(this_rq);
+	/*
+	 * See the mess in update_idle_cpu_load().
+	 */
+	this_rq->last_load_update_tick = jiffies;
+	__update_cpu_load(this_rq, this_rq->load.weight, 1);
 
 	calc_load_account_active(this_rq);
 }
@@ -3108,6 +3133,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
 	dump_stack();
+	add_taint(TAINT_WARN);
 }
 
 /*
@@ -5555,7 +5581,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+		if (!(sd->flags & SD_OVERLAP) &&
+		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
@@ -5893,99 +5920,11 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-#ifdef CONFIG_NUMA
-
-/**
- * find_next_best_node - find the next node to include in a sched_domain
- * @node: node whose sched_domain we're building
- * @used_nodes: nodes already in the sched_domain
- *
- * Find the next node to include in a given scheduling domain. Simply
- * finds the closest node not already in the @used_nodes map.
- *
- * Should use nodemask_t.
- */
-static int find_next_best_node(int node, nodemask_t *used_nodes)
-{
-	int i, n, val, min_val, best_node = -1;
-
-	min_val = INT_MAX;
-
-	for (i = 0; i < nr_node_ids; i++) {
-		/* Start at @node */
-		n = (node + i) % nr_node_ids;
-
-		if (!nr_cpus_node(n))
-			continue;
-
-		/* Skip already used nodes */
-		if (node_isset(n, *used_nodes))
-			continue;
-
-		/* Simple min distance search */
-		val = node_distance(node, n);
-
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
-		}
-	}
-
-	if (best_node != -1)
-		node_set(best_node, *used_nodes);
-	return best_node;
-}
-
-/**
- * sched_domain_node_span - get a cpumask for a node's sched_domain
- * @node: node whose cpumask we're constructing
- * @span: resulting cpumask
- *
- * Given a node, construct a good cpumask for its sched_domain to span. It
- * should be one that prevents unnecessary balancing, but also spreads tasks
- * out optimally.
- */
-static void sched_domain_node_span(int node, struct cpumask *span)
-{
-	nodemask_t used_nodes;
-	int i;
-
-	cpumask_clear(span);
-	nodes_clear(used_nodes);
-
-	cpumask_or(span, span, cpumask_of_node(node));
-	node_set(node, used_nodes);
-
-	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 */
-
 static const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));
 }
 
-int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
-
 struct sd_data {
 	struct sched_domain **__percpu sd;
 	struct sched_group **__percpu sg;
@@ -6015,6 +5954,7 @@ struct sched_domain_topology_level {
 	sched_domain_init_f init;
 	sched_domain_mask_f mask;
 	int		    flags;
+	int		    numa_level;
 	struct sd_data      data;
 };
 
@@ -6206,10 +6146,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
 }
 
 SD_INIT_FUNC(CPU)
-#ifdef CONFIG_NUMA
- SD_INIT_FUNC(ALLNODES)
- SD_INIT_FUNC(NODE)
-#endif
 #ifdef CONFIG_SCHED_SMT
  SD_INIT_FUNC(SIBLING)
 #endif
@@ -6331,15 +6267,184 @@ static struct sched_domain_topology_level default_topology[] = {
 	{ sd_init_BOOK, cpu_book_mask, },
 #endif
 	{ sd_init_CPU, cpu_cpu_mask, },
-#ifdef CONFIG_NUMA
-	{ sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
-	{ sd_init_ALLNODES, cpu_allnodes_mask, },
-#endif
 	{ NULL, },
 };
 
 static struct sched_domain_topology_level *sched_domain_topology = default_topology;
 
+#ifdef CONFIG_NUMA
+
+static int sched_domains_numa_levels;
+static int sched_domains_numa_scale;
+static int *sched_domains_numa_distance;
+static struct cpumask ***sched_domains_numa_masks;
+static int sched_domains_curr_level;
+
+static inline int sd_local_flags(int level)
+{
+	if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+		return 0;
+
+	return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
+}
+
+static struct sched_domain *
+sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
+{
+	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
+	int level = tl->numa_level;
+	int sd_weight = cpumask_weight(
+			sched_domains_numa_masks[level][cpu_to_node(cpu)]);
+
+	*sd = (struct sched_domain){
+		.min_interval		= sd_weight,
+		.max_interval		= 2*sd_weight,
+		.busy_factor		= 32,
+		.imbalance_pct		= 125,
+		.cache_nice_tries	= 2,
+		.busy_idx		= 3,
+		.idle_idx		= 2,
+		.newidle_idx		= 0,
+		.wake_idx		= 0,
+		.forkexec_idx		= 0,
+
+		.flags			= 1*SD_LOAD_BALANCE
+					| 1*SD_BALANCE_NEWIDLE
+					| 0*SD_BALANCE_EXEC
+					| 0*SD_BALANCE_FORK
+					| 0*SD_BALANCE_WAKE
+					| 0*SD_WAKE_AFFINE
+					| 0*SD_PREFER_LOCAL
+					| 0*SD_SHARE_CPUPOWER
+					| 0*SD_SHARE_PKG_RESOURCES
+					| 1*SD_SERIALIZE
+					| 0*SD_PREFER_SIBLING
+					| sd_local_flags(level)
+					,
+		.last_balance		= jiffies,
+		.balance_interval	= sd_weight,
+	};
+	SD_INIT_NAME(sd, NUMA);
+	sd->private = &tl->data;
+
+	/*
+	 * Ugly hack to pass state to sd_numa_mask()...
+	 */
+	sched_domains_curr_level = tl->numa_level;
+
+	return sd;
+}
+
+static const struct cpumask *sd_numa_mask(int cpu)
+{
+	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+}
+
+static void sched_init_numa(void)
+{
+	int next_distance, curr_distance = node_distance(0, 0);
+	struct sched_domain_topology_level *tl;
+	int level = 0;
+	int i, j, k;
+
+	sched_domains_numa_scale = curr_distance;
+	sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+	if (!sched_domains_numa_distance)
+		return;
+
+	/*
+	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+	 * unique distances in the node_distance() table.
+	 *
+	 * Assumes node_distance(0,j) includes all distances in
+	 * node_distance(i,j) in order to avoid cubic time.
+	 *
+	 * XXX: could be optimized to O(n log n) by using sort()
+	 */
+	next_distance = curr_distance;
+	for (i = 0; i < nr_node_ids; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			int distance = node_distance(0, j);
+			if (distance > curr_distance &&
+					(distance < next_distance ||
+					 next_distance == curr_distance))
+				next_distance = distance;
+		}
+		if (next_distance != curr_distance) {
+			sched_domains_numa_distance[level++] = next_distance;
+			sched_domains_numa_levels = level;
+			curr_distance = next_distance;
+		} else break;
+	}
+	/*
+	 * 'level' contains the number of unique distances, excluding the
+	 * identity distance node_distance(i,i).
+	 *
+	 * The sched_domains_nume_distance[] array includes the actual distance
+	 * numbers.
+	 */
+
+	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+	if (!sched_domains_numa_masks)
+		return;
+
+	/*
+	 * Now for each level, construct a mask per node which contains all
+	 * cpus of nodes that are that many hops away from us.
+	 */
+	for (i = 0; i < level; i++) {
+		sched_domains_numa_masks[i] =
+			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+		if (!sched_domains_numa_masks[i])
+			return;
+
+		for (j = 0; j < nr_node_ids; j++) {
+			struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+			if (!mask)
+				return;
+
+			sched_domains_numa_masks[i][j] = mask;
+
+			for (k = 0; k < nr_node_ids; k++) {
+				if (node_distance(j, k) > sched_domains_numa_distance[i])
+					continue;
+
+				cpumask_or(mask, mask, cpumask_of_node(k));
+			}
+		}
+	}
+
+	tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
+			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
+	if (!tl)
+		return;
+
+	/*
+	 * Copy the default topology bits..
+	 */
+	for (i = 0; default_topology[i].init; i++)
+		tl[i] = default_topology[i];
+
+	/*
+	 * .. and append 'j' levels of NUMA goodness.
+	 */
+	for (j = 0; j < level; i++, j++) {
+		tl[i] = (struct sched_domain_topology_level){
+			.init = sd_numa_init,
+			.mask = sd_numa_mask,
+			.flags = SDTL_OVERLAP,
+			.numa_level = j,
+		};
+	}
+
+	sched_domain_topology = tl;
+}
+#else
+static inline void sched_init_numa(void)
+{
+}
+#endif /* CONFIG_NUMA */
+
 static int __sdt_alloc(const struct cpumask *cpu_map)
 {
 	struct sched_domain_topology_level *tl;
@@ -6707,97 +6812,6 @@ match2:
 	mutex_unlock(&sched_domains_mutex);
 }
 
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-static void reinit_sched_domains(void)
-{
-	get_online_cpus();
-
-	/* Destroy domains first to force the rebuild */
-	partition_sched_domains(0, NULL, NULL);
-
-	rebuild_sched_domains();
-	put_online_cpus();
-}
-
-static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
-{
-	unsigned int level = 0;
-
-	if (sscanf(buf, "%u", &level) != 1)
-		return -EINVAL;
-
-	/*
-	 * level is always be positive so don't check for
-	 * level < POWERSAVINGS_BALANCE_NONE which is 0
-	 * What happens on 0 or 1 byte write,
-	 * need to check for count as well?
-	 */
-
-	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
-		return -EINVAL;
-
-	if (smt)
-		sched_smt_power_savings = level;
-	else
-		sched_mc_power_savings = level;
-
-	reinit_sched_domains();
-
-	return count;
-}
-
-#ifdef CONFIG_SCHED_MC
-static ssize_t sched_mc_power_savings_show(struct device *dev,
-					   struct device_attribute *attr,
-					   char *buf)
-{
-	return sprintf(buf, "%u\n", sched_mc_power_savings);
-}
-static ssize_t sched_mc_power_savings_store(struct device *dev,
-					    struct device_attribute *attr,
-					    const char *buf, size_t count)
-{
-	return sched_power_savings_store(buf, count, 0);
-}
-static DEVICE_ATTR(sched_mc_power_savings, 0644,
-		   sched_mc_power_savings_show,
-		   sched_mc_power_savings_store);
-#endif
-
-#ifdef CONFIG_SCHED_SMT
-static ssize_t sched_smt_power_savings_show(struct device *dev,
-					    struct device_attribute *attr,
-					    char *buf)
-{
-	return sprintf(buf, "%u\n", sched_smt_power_savings);
-}
-static ssize_t sched_smt_power_savings_store(struct device *dev,
-					    struct device_attribute *attr,
-					     const char *buf, size_t count)
-{
-	return sched_power_savings_store(buf, count, 1);
-}
-static DEVICE_ATTR(sched_smt_power_savings, 0644,
-		   sched_smt_power_savings_show,
-		   sched_smt_power_savings_store);
-#endif
-
-int __init sched_create_sysfs_power_savings_entries(struct device *dev)
-{
-	int err = 0;
-
-#ifdef CONFIG_SCHED_SMT
-	if (smt_capable())
-		err = device_create_file(dev, &dev_attr_sched_smt_power_savings);
-#endif
-#ifdef CONFIG_SCHED_MC
-	if (!err && mc_capable())
-		err = device_create_file(dev, &dev_attr_sched_mc_power_savings);
-#endif
-	return err;
-}
-#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-
 /*
  * Update cpusets according to cpu_active mask.  If cpusets are
  * disabled, cpuset_update_active_cpus() becomes a simple wrapper
@@ -6835,6 +6849,8 @@ void __init sched_init_smp(void)
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
 	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
+	sched_init_numa();
+
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
 	init_sched_domains(cpu_active_mask);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 09acaa15161..6f79596e0ea 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -202,7 +202,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(spread0));
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
-	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
@@ -260,8 +260,14 @@ static void print_cpu(struct seq_file *m, int cpu)
 	SEQ_printf(m, "\ncpu#%d\n", cpu);
 #endif
 
-#define P(x) \
-	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))
+#define P(x)								\
+do {									\
+	if (sizeof(rq->x) == 4)						\
+		SEQ_printf(m, "  .%-30s: %ld\n", #x, (long)(rq->x));	\
+	else								\
+		SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x));\
+} while (0)
+
 #define PN(x) \
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e9553640c1c..940e6d17cf9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2721,7 +2721,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 		 * If power savings logic is enabled for a domain, see if we
 		 * are not overloaded, if so, don't balance wider.
 		 */
-		if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {
+		if (tmp->flags & (SD_PREFER_LOCAL)) {
 			unsigned long power = 0;
 			unsigned long nr_running = 0;
 			unsigned long capacity;
@@ -2734,9 +2734,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 
 			capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
 
-			if (tmp->flags & SD_POWERSAVINGS_BALANCE)
-				nr_running /= 2;
-
 			if (nr_running < capacity)
 				want_sd = 0;
 		}
@@ -3082,7 +3079,7 @@ struct lb_env {
 	struct rq		*dst_rq;
 
 	enum cpu_idle_type	idle;
-	long			load_move;
+	long			imbalance;
 	unsigned int		flags;
 
 	unsigned int		loop;
@@ -3218,7 +3215,7 @@ static unsigned long task_h_load(struct task_struct *p);
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
- * move_tasks tries to move up to load_move weighted load from busiest to
+ * move_tasks tries to move up to imbalance weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
  * Returns 1 if successful and 0 otherwise.
  *
@@ -3231,7 +3228,7 @@ static int move_tasks(struct lb_env *env)
 	unsigned long load;
 	int pulled = 0;
 
-	if (env->load_move <= 0)
+	if (env->imbalance <= 0)
 		return 0;
 
 	while (!list_empty(tasks)) {
@@ -3257,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
 		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
 
-		if ((load / 2) > env->load_move)
+		if ((load / 2) > env->imbalance)
 			goto next;
 
 		if (!can_migrate_task(p, env))
@@ -3265,7 +3262,7 @@ static int move_tasks(struct lb_env *env)
 
 		move_task(p, env);
 		pulled++;
-		env->load_move -= load;
+		env->imbalance -= load;
 
 #ifdef CONFIG_PREEMPT
 		/*
@@ -3281,7 +3278,7 @@ static int move_tasks(struct lb_env *env)
 		 * We only want to steal up to the prescribed amount of
 		 * weighted load.
 		 */
-		if (env->load_move <= 0)
+		if (env->imbalance <= 0)
 			break;
 
 		continue;
@@ -3435,14 +3432,6 @@ struct sd_lb_stats {
 	unsigned int  busiest_group_weight;
 
 	int group_imb; /* Is there imbalance in this sd */
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	int power_savings_balance; /* Is powersave balance needed for this sd */
-	struct sched_group *group_min; /* Least loaded group in sd */
-	struct sched_group *group_leader; /* Group which relieves group_min */
-	unsigned long min_load_per_task; /* load_per_task in group_min */
-	unsigned long leader_nr_running; /* Nr running of group_leader */
-	unsigned long min_nr_running; /* Nr running of group_min */
-#endif
 };
 
 /*
@@ -3486,148 +3475,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-/**
- * init_sd_power_savings_stats - Initialize power savings statistics for
- * the given sched_domain, during load balancing.
- *
- * @sd: Sched domain whose power-savings statistics are to be initialized.
- * @sds: Variable containing the statistics for sd.
- * @idle: Idle status of the CPU at which we're performing load-balancing.
- */
-static inline void init_sd_power_savings_stats(struct sched_domain *sd,
-	struct sd_lb_stats *sds, enum cpu_idle_type idle)
-{
-	/*
-	 * Busy processors will not participate in power savings
-	 * balance.
-	 */
-	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
-		sds->power_savings_balance = 0;
-	else {
-		sds->power_savings_balance = 1;
-		sds->min_nr_running = ULONG_MAX;
-		sds->leader_nr_running = 0;
-	}
-}
-
-/**
- * update_sd_power_savings_stats - Update the power saving stats for a
- * sched_domain while performing load balancing.
- *
- * @group: sched_group belonging to the sched_domain under consideration.
- * @sds: Variable containing the statistics of the sched_domain
- * @local_group: Does group contain the CPU for which we're performing
- * 		load balancing ?
- * @sgs: Variable containing the statistics of the group.
- */
-static inline void update_sd_power_savings_stats(struct sched_group *group,
-	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
-{
-
-	if (!sds->power_savings_balance)
-		return;
-
-	/*
-	 * If the local group is idle or completely loaded
-	 * no need to do power savings balance at this domain
-	 */
-	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
-				!sds->this_nr_running))
-		sds->power_savings_balance = 0;
-
-	/*
-	 * If a group is already running at full capacity or idle,
-	 * don't include that group in power savings calculations
-	 */
-	if (!sds->power_savings_balance ||
-		sgs->sum_nr_running >= sgs->group_capacity ||
-		!sgs->sum_nr_running)
-		return;
-
-	/*
-	 * Calculate the group which has the least non-idle load.
-	 * This is the group from where we need to pick up the load
-	 * for saving power
-	 */
-	if ((sgs->sum_nr_running < sds->min_nr_running) ||
-	    (sgs->sum_nr_running == sds->min_nr_running &&
-	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
-		sds->group_min = group;
-		sds->min_nr_running = sgs->sum_nr_running;
-		sds->min_load_per_task = sgs->sum_weighted_load /
-						sgs->sum_nr_running;
-	}
-
-	/*
-	 * Calculate the group which is almost near its
-	 * capacity but still has some space to pick up some load
-	 * from other group and save more power
-	 */
-	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
-		return;
-
-	if (sgs->sum_nr_running > sds->leader_nr_running ||
-	    (sgs->sum_nr_running == sds->leader_nr_running &&
-	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
-		sds->group_leader = group;
-		sds->leader_nr_running = sgs->sum_nr_running;
-	}
-}
-
-/**
- * check_power_save_busiest_group - see if there is potential for some power-savings balance
- * @sds: Variable containing the statistics of the sched_domain
- *	under consideration.
- * @this_cpu: Cpu at which we're currently performing load-balancing.
- * @imbalance: Variable to store the imbalance.
- *
- * Description:
- * Check if we have potential to perform some power-savings balance.
- * If yes, set the busiest group to be the least loaded group in the
- * sched_domain, so that it's CPUs can be put to idle.
- *
- * Returns 1 if there is potential to perform power-savings balance.
- * Else returns 0.
- */
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-					int this_cpu, unsigned long *imbalance)
-{
-	if (!sds->power_savings_balance)
-		return 0;
-
-	if (sds->this != sds->group_leader ||
-			sds->group_leader == sds->group_min)
-		return 0;
-
-	*imbalance = sds->min_load_per_task;
-	sds->busiest = sds->group_min;
-
-	return 1;
-
-}
-#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-static inline void init_sd_power_savings_stats(struct sched_domain *sd,
-	struct sd_lb_stats *sds, enum cpu_idle_type idle)
-{
-	return;
-}
-
-static inline void update_sd_power_savings_stats(struct sched_group *group,
-	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
-{
-	return;
-}
-
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-					int this_cpu, unsigned long *imbalance)
-{
-	return 0;
-}
-#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-
-
 unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
 {
 	return SCHED_POWER_SCALE;
@@ -3765,24 +3612,22 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @sd: The sched_domain whose statistics are to be updated.
  * @group: sched_group whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
-static inline void update_sg_lb_stats(struct sched_domain *sd,
-			struct sched_group *group, int this_cpu,
-			enum cpu_idle_type idle, int load_idx,
+static inline void update_sg_lb_stats(struct lb_env *env,
+			struct sched_group *group, int load_idx,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
 {
-	unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
-	int i;
+	unsigned long nr_running, max_nr_running, min_nr_running;
+	unsigned long load, max_cpu_load, min_cpu_load;
 	unsigned int balance_cpu = -1, first_idle_cpu = 0;
 	unsigned long avg_load_per_task = 0;
+	int i;
 
 	if (local_group)
 		balance_cpu = group_first_cpu(group);
@@ -3791,10 +3636,13 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	max_cpu_load = 0;
 	min_cpu_load = ~0UL;
 	max_nr_running = 0;
+	min_nr_running = ~0UL;
 
 	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
 		struct rq *rq = cpu_rq(i);
 
+		nr_running = rq->nr_running;
+
 		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
 			if (idle_cpu(i) && !first_idle_cpu) {
@@ -3805,16 +3653,19 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 			load = target_load(i, load_idx);
 		} else {
 			load = source_load(i, load_idx);
-			if (load > max_cpu_load) {
+			if (load > max_cpu_load)
 				max_cpu_load = load;
-				max_nr_running = rq->nr_running;
-			}
 			if (min_cpu_load > load)
 				min_cpu_load = load;
+
+			if (nr_running > max_nr_running)
+				max_nr_running = nr_running;
+			if (min_nr_running > nr_running)
+				min_nr_running = nr_running;
 		}
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_nr_running += nr_running;
 		sgs->sum_weighted_load += weighted_cpuload(i);
 		if (idle_cpu(i))
 			sgs->idle_cpus++;
@@ -3827,14 +3678,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 * to do the newly idle load balance.
 	 */
 	if (local_group) {
-		if (idle != CPU_NEWLY_IDLE) {
-			if (balance_cpu != this_cpu) {
+		if (env->idle != CPU_NEWLY_IDLE) {
+			if (balance_cpu != env->dst_cpu) {
 				*balance = 0;
 				return;
 			}
-			update_group_power(sd, this_cpu);
+			update_group_power(env->sd, env->dst_cpu);
 		} else if (time_after_eq(jiffies, group->sgp->next_update))
-			update_group_power(sd, this_cpu);
+			update_group_power(env->sd, env->dst_cpu);
 	}
 
 	/* Adjust by relative CPU power of the group */
@@ -3852,13 +3703,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if (sgs->sum_nr_running)
 		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
+	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task &&
+	    (max_nr_running - min_nr_running) > 1)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
 						SCHED_POWER_SCALE);
 	if (!sgs->group_capacity)
-		sgs->group_capacity = fix_small_capacity(sd, group);
+		sgs->group_capacity = fix_small_capacity(env->sd, group);
 	sgs->group_weight = group->group_weight;
 
 	if (sgs->group_capacity > sgs->sum_nr_running)
@@ -3876,11 +3728,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
  * Determine if @sg is a busier group than the previously selected
  * busiest group.
  */
-static bool update_sd_pick_busiest(struct sched_domain *sd,
+static bool update_sd_pick_busiest(struct lb_env *env,
 				   struct sd_lb_stats *sds,
 				   struct sched_group *sg,
-				   struct sg_lb_stats *sgs,
-				   int this_cpu)
+				   struct sg_lb_stats *sgs)
 {
 	if (sgs->avg_load <= sds->max_load)
 		return false;
@@ -3896,8 +3747,8 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
 	 * numbered CPUs in the group, therefore mark all groups
 	 * higher than ourself as busy.
 	 */
-	if ((sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
-	    this_cpu < group_first_cpu(sg)) {
+	if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
+	    env->dst_cpu < group_first_cpu(sg)) {
 		if (!sds->busiest)
 			return true;
 
@@ -3917,28 +3768,27 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
-static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
-			enum cpu_idle_type idle, const struct cpumask *cpus,
-			int *balance, struct sd_lb_stats *sds)
+static inline void update_sd_lb_stats(struct lb_env *env,
+				      const struct cpumask *cpus,
+				      int *balance, struct sd_lb_stats *sds)
 {
-	struct sched_domain *child = sd->child;
-	struct sched_group *sg = sd->groups;
+	struct sched_domain *child = env->sd->child;
+	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats sgs;
 	int load_idx, prefer_sibling = 0;
 
 	if (child && child->flags & SD_PREFER_SIBLING)
 		prefer_sibling = 1;
 
-	init_sd_power_savings_stats(sd, sds, idle);
-	load_idx = get_sd_load_idx(sd, idle);
+	load_idx = get_sd_load_idx(env->sd, env->idle);
 
 	do {
 		int local_group;
 
-		local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
+		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
-				local_group, cpus, balance, &sgs);
+		update_sg_lb_stats(env, sg, load_idx, local_group,
+				   cpus, balance, &sgs);
 
 		if (local_group && !(*balance))
 			return;
@@ -3966,7 +3816,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->this_load_per_task = sgs.sum_weighted_load;
 			sds->this_has_capacity = sgs.group_has_capacity;
 			sds->this_idle_cpus = sgs.idle_cpus;
-		} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
+		} else if (update_sd_pick_busiest(env, sds, sg, &sgs)) {
 			sds->max_load = sgs.avg_load;
 			sds->busiest = sg;
 			sds->busiest_nr_running = sgs.sum_nr_running;
@@ -3978,9 +3828,8 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->group_imb = sgs.group_imb;
 		}
 
-		update_sd_power_savings_stats(sg, sds, local_group, &sgs);
 		sg = sg->next;
-	} while (sg != sd->groups);
+	} while (sg != env->sd->groups);
 }
 
 /**
@@ -4008,24 +3857,23 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
  * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
  * @imbalance: returns amount of imbalanced due to packing.
  */
-static int check_asym_packing(struct sched_domain *sd,
-			      struct sd_lb_stats *sds,
-			      int this_cpu, unsigned long *imbalance)
+static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 {
 	int busiest_cpu;
 
-	if (!(sd->flags & SD_ASYM_PACKING))
+	if (!(env->sd->flags & SD_ASYM_PACKING))
 		return 0;
 
 	if (!sds->busiest)
 		return 0;
 
 	busiest_cpu = group_first_cpu(sds->busiest);
-	if (this_cpu > busiest_cpu)
+	if (env->dst_cpu > busiest_cpu)
 		return 0;
 
-	*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power,
-				       SCHED_POWER_SCALE);
+	env->imbalance = DIV_ROUND_CLOSEST(
+		sds->max_load * sds->busiest->sgp->power, SCHED_POWER_SCALE);
+
 	return 1;
 }
 
@@ -4037,8 +3885,8 @@ static int check_asym_packing(struct sched_domain *sd,
  * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
  * @imbalance: Variable to store the imbalance.
  */
-static inline void fix_small_imbalance(struct sd_lb_stats *sds,
-				int this_cpu, unsigned long *imbalance)
+static inline
+void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)