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

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Add the SYSTEM_SCHEDULING bootup state to move various scheduler
     debug checks earlier into the bootup. This turns silent and
     sporadically deadly bugs into nice, deterministic splats. Fix some
     of the splats that triggered. (Thomas Gleixner)

   - A round of restructuring and refactoring of the load-balancing and
     topology code (Peter Zijlstra)

   - Another round of consolidating ~20 of incremental scheduler code
     history: this time in terms of wait-queue nomenclature. (I didn't
     get much feedback on these renaming patches, and we can still
     easily change any names I might have misplaced, so if anyone hates
     a new name, please holler and I'll fix it.) (Ingo Molnar)

   - sched/numa improvements, fixes and updates (Rik van Riel)

   - Another round of x86/tsc scheduler clock code improvements, in hope
     of making it more robust (Peter Zijlstra)

   - Improve NOHZ behavior (Frederic Weisbecker)

   - Deadline scheduler improvements and fixes (Luca Abeni, Daniel
     Bristot de Oliveira)

   - Simplify and optimize the topology setup code (Lauro Ramos
     Venancio)

   - Debloat and decouple scheduler code some more (Nicolas Pitre)

   - Simplify code by making better use of llist primitives (Byungchul
     Park)

   - ... plus other fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  sched/cputime: Refactor the cputime_adjust() code
  sched/debug: Expose the number of RT/DL tasks that can migrate
  sched/numa: Hide numa_wake_affine() from UP build
  sched/fair: Remove effective_load()
  sched/numa: Implement NUMA node level wake_affine()
  sched/fair: Simplify wake_affine() for the single socket case
  sched/numa: Override part of migrate_degrades_locality() when idle balancing
  sched/rt: Move RT related code from sched/core.c to sched/rt.c
  sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
  sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
  sched/fair: Spare idle load balancing on nohz_full CPUs
  nohz: Move idle balancer registration to the idle path
  sched/loadavg: Generalize "_idle" naming to "_nohz"
  sched/core: Drop the unused try_get_task_struct() helper function
  sched/fair: WARN() and refuse to set buddy when !se->on_rq
  sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
  sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
  sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
  sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
  sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
  ...

1 files changed, 339 insertions, 91 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 1b0b4fb12837..79895aec281e 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -10,6 +10,7 @@ DEFINE_MUTEX(sched_domains_mutex);
 
 /* Protected by sched_domains_mutex: */
 cpumask_var_t sched_domains_tmpmask;
+cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
@@ -35,7 +36,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 	cpumask_clear(groupmask);
 
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
 
 	if (!(sd->flags & SD_LOAD_BALANCE)) {
 		printk("does not load-balance\n");
@@ -45,14 +46,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %*pbl level %s\n",
+	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
 				"CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain"
 				" CPU%d\n", cpu);
 	}
@@ -65,29 +66,47 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!cpumask_weight(sched_group_cpus(group))) {
+		if (!cpumask_weight(sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
 		}
 
 		if (!(sd->flags & SD_OVERLAP) &&
-		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
+		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
 		}
 
-		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+		cpumask_or(groupmask, groupmask, sched_group_span(group));
 
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %lu)",
-				group->sgc->capacity);
+		printk(KERN_CONT " %d:{ span=%*pbl",
+				group->sgc->id,
+				cpumask_pr_args(sched_group_span(group)));
+
+		if ((sd->flags & SD_OVERLAP) &&
+		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
+			printk(KERN_CONT " mask=%*pbl",
+				cpumask_pr_args(group_balance_mask(group)));
+		}
+
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
+			printk(KERN_CONT " cap=%lu", group->sgc->capacity);
+
+		if (group == sd->groups && sd->child &&
+		    !cpumask_equal(sched_domain_span(sd->child),
+				   sched_group_span(group))) {
+			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
 		}
 
+		printk(KERN_CONT " }");
+
 		group = group->next;
+
+		if (group != sd->groups)
+			printk(KERN_CONT ",");
+
 	} while (group != sd->groups);
 	printk(KERN_CONT "\n");
 
@@ -113,7 +132,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
 
 	for (;;) {
 		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
@@ -477,46 +496,214 @@ enum s_alloc {
 };
 
 /*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the balance mask.
  *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
+ * The balance mask are all those CPUs that could actually end up at this
+ * group. See build_balance_mask().
  *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * CPU they're built on, so check that.
+ * Also see should_we_balance().
  */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+int group_balance_cpu(struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	return cpumask_first(group_balance_mask(sg));
+}
+
+
+/*
+ * NUMA topology (first read the regular topology blurb below)
+ *
+ * Given a node-distance table, for example:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  30  20
+ *     1:  20  10  20  30
+ *     2:  30  20  10  20
+ *     3:  20  30  20  10
+ *
+ * which represents a 4 node ring topology like:
+ *
+ *   0 ----- 1
+ *   |       |
+ *   |       |
+ *   |       |
+ *   3 ----- 2
+ *
+ * We want to construct domains and groups to represent this. The way we go
+ * about doing this is to build the domains on 'hops'. For each NUMA level we
+ * construct the mask of all nodes reachable in @level hops.
+ *
+ * For the above NUMA topology that gives 3 levels:
+ *
+ * NUMA-2	0-3		0-3		0-3		0-3
+ *  groups:	{0-1,3},{1-3}	{0-2},{0,2-3}	{1-3},{0-1,3}	{0,2-3},{0-2}
+ *
+ * NUMA-1	0-1,3		0-2		1-3		0,2-3
+ *  groups:	{0},{1},{3}	{0},{1},{2}	{1},{2},{3}	{0},{2},{3}
+ *
+ * NUMA-0	0		1		2		3
+ *
+ *
+ * As can be seen; things don't nicely line up as with the regular topology.
+ * When we iterate a domain in child domain chunks some nodes can be
+ * represented multiple times -- hence the "overlap" naming for this part of
+ * the topology.
+ *
+ * In order to minimize this overlap, we only build enough groups to cover the
+ * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
+ *
+ * Because:
+ *
+ *  - the first group of each domain is its child domain; this
+ *    gets us the first 0-1,3
+ *  - the only uncovered node is 2, who's child domain is 1-3.
+ *
+ * However, because of the overlap, computing a unique CPU for each group is
+ * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
+ * groups include the CPUs of Node-0, while those CPUs would not in fact ever
+ * end up at those groups (they would end up in group: 0-1,3).
+ *
+ * To correct this we have to introduce the group balance mask. This mask
+ * will contain those CPUs in the group that can reach this group given the
+ * (child) domain tree.
+ *
+ * With this we can once again compute balance_cpu and sched_group_capacity
+ * relations.
+ *
+ * XXX include words on how balance_cpu is unique and therefore can be
+ * used for sched_group_capacity links.
+ *
+ *
+ * Another 'interesting' topology is:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  20  30
+ *     1:  20  10  20  20
+ *     2:  20  20  10  20
+ *     3:  30  20  20  10
+ *
+ * Which looks a little like:
+ *
+ *   0 ----- 1
+ *   |     / |
+ *   |   /   |
+ *   | /     |
+ *   2 ----- 3
+ *
+ * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
+ * are not.
+ *
+ * This leads to a few particularly weird cases where the sched_domain's are
+ * not of the same number for each cpu. Consider:
+ *
+ * NUMA-2	0-3						0-3
+ *  groups:	{0-2},{1-3}					{1-3},{0-2}
+ *
+ * NUMA-1	0-2		0-3		0-3		1-3
+ *
+ * NUMA-0	0		1		2		3
+ *
+ */
+
+
+/*
+ * Build the balance mask; it contains only those CPUs that can arrive at this
+ * group and should be considered to continue balancing.
+ *
+ * We do this during the group creation pass, therefore the group information
+ * isn't complete yet, however since each group represents a (child) domain we
+ * can fully construct this using the sched_domain bits (which are already
+ * complete).
+ */
+static void
+build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
+{
+	const struct cpumask *sg_span = sched_group_span(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	cpumask_clear(mask);
+
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
 			continue;
 
-		cpumask_set_cpu(i, sched_group_mask(sg));
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
+			continue;
+
+		cpumask_set_cpu(i, mask);
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(mask));
 }
 
 /*
- * Return the canonical balance CPU for this group, this is the first CPU
- * of this group that's also in the iteration mask.
+ * XXX: This creates per-node group entries; since the load-balancer will
+ * immediately access remote memory to construct this group's load-balance
+ * statistics having the groups node local is of dubious benefit.
  */
-int group_balance_cpu(struct sched_group *sg)
+static struct sched_group *
+build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 {
-	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+	struct sched_group *sg;
+	struct cpumask *sg_span;
+
+	sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			GFP_KERNEL, cpu_to_node(cpu));
+
+	if (!sg)
+		return NULL;
+
+	sg_span = sched_group_span(sg);
+	if (sd->child)
+		cpumask_copy(sg_span, sched_domain_span(sd->child));
+	else
+		cpumask_copy(sg_span, sched_domain_span(sd));
+
+	return sg;
+}
+
+static void init_overlap_sched_group(struct sched_domain *sd,
+				     struct sched_group *sg)
+{
+	struct cpumask *mask = sched_domains_tmpmask2;
+	struct sd_data *sdd = sd->private;
+	struct cpumask *sg_span;
+	int cpu;
+
+	build_balance_mask(sd, sg, mask);
+	cpu = cpumask_first_and(sched_group_span(sg), mask);
+
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	if (atomic_inc_return(&sg->sgc->ref) == 1)
+		cpumask_copy(group_balance_mask(sg), mask);
+	else
+		WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));
+
+	/*
+	 * Initialize sgc->capacity such that even if we mess up the
+	 * domains and no possible iteration will get us here, we won't
+	 * die on a /0 trap.
+	 */
+	sg_span = sched_group_span(sg);
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
 }
 
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
-	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	struct sched_group *first = NULL, *last = NULL, *sg;
 	const struct cpumask *span = sched_domain_span(sd);
 	struct cpumask *covered = sched_domains_tmpmask;
 	struct sd_data *sdd = sd->private;
@@ -525,7 +712,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct cpumask *sg_span;
 
 		if (cpumask_test_cpu(i, covered))
@@ -533,44 +720,27 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 		sibling = *per_cpu_ptr(sdd->sd, i);
 
-		/* See the comment near build_group_mask(). */
+		/*
+		 * Asymmetric node setups can result in situations where the
+		 * domain tree is of unequal depth, make sure to skip domains
+		 * that already cover the entire range.
+		 *
+		 * In that case build_sched_domains() will have terminated the
+		 * iteration early and our sibling sd spans will be empty.
+		 * Domains should always include the CPU they're built on, so
+		 * check that.
+		 */
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
-		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				GFP_KERNEL, cpu_to_node(cpu));
-
+		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
 
-		sg_span = sched_group_cpus(sg);
-		if (sibling->child)
-			cpumask_copy(sg_span, sched_domain_span(sibling->child));
-		else
-			cpumask_set_cpu(i, sg_span);
-
+		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
-		if (atomic_inc_return(&sg->sgc->ref) == 1)
-			build_group_mask(sd, sg);
-
-		/*
-		 * Initialize sgc->capacity such that even if we mess up the
-		 * domains and no possible iteration will get us here, we won't
-		 * die on a /0 trap.
-		 */
-		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
-		/*
-		 * Make sure the first group of this domain contains the
-		 * canonical balance CPU. Otherwise the sched_domain iteration
-		 * breaks. See update_sg_lb_stats().
-		 */
-		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
-		    group_balance_cpu(sg) == cpu)
-			groups = sg;
+		init_overlap_sched_group(sd, sg);
 
 		if (!first)
 			first = sg;
@@ -579,7 +749,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 		last->next = first;
 	}
-	sd->groups = groups;
+	sd->groups = first;
 
 	return 0;
 
@@ -589,23 +759,106 @@ fail:
 	return -ENOMEM;
 }
 
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+
+/*
+ * Package topology (also see the load-balance blurb in fair.c)
+ *
+ * The scheduler builds a tree structure to represent a number of important
+ * topology features. By default (default_topology[]) these include:
+ *
+ *  - Simultaneous multithreading (SMT)
+ *  - Multi-Core Cache (MC)
+ *  - Package (DIE)
+ *
+ * Where the last one more or less denotes everything up to a NUMA node.
+ *
+ * The tree consists of 3 primary data structures:
+ *
+ *	sched_domain -> sched_group -> sched_group_capacity
+ *	    ^ ^             ^ ^
+ *          `-'             `-'
+ *
+ * The sched_domains are per-cpu and have a two way link (parent & child) and
+ * denote the ever growing mask of CPUs belonging to that level of topology.
+ *
+ * Each sched_domain has a circular (double) linked list of sched_group's, each
+ * denoting the domains of the level below (or individual CPUs in case of the
+ * first domain level). The sched_group linked by a sched_domain includes the
+ * CPU of that sched_domain [*].
+ *
+ * Take for instance a 2 threaded, 2 core, 2 cache cluster part:
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * DIE  [                             ]
+ * MC   [             ] [             ]
+ * SMT  [     ] [     ] [     ] [     ]
+ *
+ *  - or -
+ *
+ * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
+ * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * One way to think about it is: sched_domain moves you up and down among these
+ * topology levels, while sched_group moves you sideways through it, at child
+ * domain granularity.
+ *
+ * sched_group_capacity ensures each unique sched_group has shared storage.
+ *
+ * There are two related construction problems, both require a CPU that
+ * uniquely identify each group (for a given domain):
+ *
+ *  - The first is the balance_cpu (see should_we_balance() and the
+ *    load-balance blub in fair.c); for each group we only want 1 CPU to
+ *    continue balancing at a higher domain.
+ *
+ *  - The second is the sched_group_capacity; we want all identical groups
+ *    to share a single sched_group_capacity.
+ *
+ * Since these topologies are exclusive by construction. That is, its
+ * impossible for an SMT thread to belong to multiple cores, and cores to
+ * be part of multiple caches. There is a very clear and unique location
+ * for each CPU in the hierarchy.
+ *
+ * Therefore computing a unique CPU for each group is trivial (the iteration
+ * mask is redundant and set all 1s; all CPUs in a group will end up at _that_
+ * group), we can simply pick the first CPU in each group.
+ *
+ *
+ * [*] in other words, the first group of each domain is its child domain.
+ */
+
+static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
+	struct sched_group *sg;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg) {
-		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	sg = *per_cpu_ptr(sdd->sg, cpu);
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+
+	/* For claim_allocations: */
+	atomic_inc(&sg->ref);
+	atomic_inc(&sg->sgc->ref);
 
-		/* For claim_allocations: */
-		atomic_set(&(*sg)->sgc->ref, 1);
+	if (child) {
+		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
+		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
+	} else {
+		cpumask_set_cpu(cpu, sched_group_span(sg));
+		cpumask_set_cpu(cpu, group_balance_mask(sg));
 	}
 
-	return cpu;
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+	return sg;
 }
 
 /*
@@ -624,34 +877,20 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 	struct cpumask *covered;
 	int i;
 
-	get_group(cpu, sdd, &sd->groups);
-	atomic_inc(&sd->groups->ref);
-
-	if (cpu != cpumask_first(span))
-		return 0;
-
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct sched_group *sg;
-		int group, j;
 
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		group = get_group(i, sdd, &sg);
-		cpumask_setall(sched_group_mask(sg));
+		sg = get_group(i, sdd);
 
-		for_each_cpu(j, span) {
-			if (get_group(j, sdd, NULL) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
+		cpumask_or(covered, covered, sched_group_span(sg));
 
 		if (!first)
 			first = sg;
@@ -660,6 +899,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 	}
 	last->next = first;
+	sd->groups = first;
 
 	return 0;
 }
@@ -683,12 +923,12 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 	do {
 		int cpu, max_cpu = -1;
 
-		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg->group_weight = cpumask_weight(sched_group_span(sg));
 
 		if (!(sd->flags & SD_ASYM_PACKING))
 			goto next;
 
-		for_each_cpu(cpu, sched_group_cpus(sg)) {
+		for_each_cpu(cpu, sched_group_span(sg)) {
 			if (max_cpu < 0)
 				max_cpu = cpu;
 			else if (sched_asym_prefer(cpu, max_cpu))
@@ -1308,6 +1548,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
+#ifdef CONFIG_SCHED_DEBUG
+			sgc->id = j;
+#endif
+
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}
@@ -1407,7 +1651,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+			if (tl->flags & SDTL_OVERLAP)
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
@@ -1478,7 +1722,7 @@ static struct sched_domain_attr		*dattr_cur;
  * cpumask) fails, then fallback to a single sched domain,
  * as determined by the single cpumask fallback_doms.
  */
-cpumask_var_t				fallback_doms;
+static cpumask_var_t			fallback_doms;
 
 /*
  * arch_update_cpu_topology lets virtualized architectures update the
@@ -1520,10 +1764,14 @@ 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.
  */
-int init_sched_domains(const struct cpumask *cpu_map)
+int sched_init_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL);
+	zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL);
+	zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+
 	arch_update_cpu_topology();
 	ndoms_cur = 1;
 	doms_cur = alloc_sched_domains(ndoms_cur);