Merge branch 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "Mostly changes to get the v2 interface ready.  The core features are
  mostly ready now and I think it's reasonable to expect to drop the
  devel mask in one or two devel cycles at least for a subset of
  controllers.

   - cgroup added a controller dependency mechanism so that block cgroup
     can depend on memory cgroup.  This will be used to finally support
     IO provisioning on the writeback traffic, which is currently being
     implemented.

   - The v2 interface now uses a separate table so that the interface
     files for the new interface are explicitly declared in one place.
     Each controller will explicitly review and add the files for the
     new interface.

   - cpuset is getting ready for the hierarchical behavior which is in
     the similar style with other controllers so that an ancestor's
     configuration change doesn't change the descendants' configurations
     irreversibly and processes aren't silently migrated when a CPU or
     node goes down.

  All the changes are to the new interface and no behavior changed for
  the multiple hierarchies"

* 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (29 commits)
  cpuset: fix the WARN_ON() in update_nodemasks_hier()
  cgroup: initialize cgrp_dfl_root_inhibit_ss_mask from !->dfl_files test
  cgroup: make CFTYPE_ONLY_ON_DFL and CFTYPE_NO_ internal to cgroup core
  cgroup: distinguish the default and legacy hierarchies when handling cftypes
  cgroup: replace cgroup_add_cftypes() with cgroup_add_legacy_cftypes()
  cgroup: rename cgroup_subsys->base_cftypes to ->legacy_cftypes
  cgroup: split cgroup_base_files[] into cgroup_{dfl|legacy}_base_files[]
  cpuset: export effective masks to userspace
  cpuset: allow writing offlined masks to cpuset.cpus/mems
  cpuset: enable onlined cpu/node in effective masks
  cpuset: refactor cpuset_hotplug_update_tasks()
  cpuset: make cs->{cpus, mems}_allowed as user-configured masks
  cpuset: apply cs->effective_{cpus,mems}
  cpuset: initialize top_cpuset's configured masks at mount
  cpuset: use effective cpumask to build sched domains
  cpuset: inherit ancestor's masks if effective_{cpus, mems} becomes empty
  cpuset: update cs->effective_{cpus, mems} when config changes
  cpuset: update cpuset->effective_{cpus,mems} at hotplug
  cpuset: add cs->effective_cpus and cs->effective_mems
  cgroup: clean up sane_behavior handling
  ...

1 files changed, 306 insertions, 194 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 116a4164720a..22874d7cf2c0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -76,8 +76,34 @@ struct cpuset {
 	struct cgroup_subsys_state css;
 
 	unsigned long flags;		/* "unsigned long" so bitops work */
-	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */
-	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */
+
+	/*
+	 * On default hierarchy:
+	 *
+	 * The user-configured masks can only be changed by writing to
+	 * cpuset.cpus and cpuset.mems, and won't be limited by the
+	 * parent masks.
+	 *
+	 * The effective masks is the real masks that apply to the tasks
+	 * in the cpuset. They may be changed if the configured masks are
+	 * changed or hotplug happens.
+	 *
+	 * effective_mask == configured_mask & parent's effective_mask,
+	 * and if it ends up empty, it will inherit the parent's mask.
+	 *
+	 *
+	 * On legacy hierachy:
+	 *
+	 * The user-configured masks are always the same with effective masks.
+	 */
+
+	/* user-configured CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t cpus_allowed;
+	nodemask_t mems_allowed;
+
+	/* effective CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t effective_cpus;
+	nodemask_t effective_mems;
 
 	/*
 	 * This is old Memory Nodes tasks took on.
@@ -307,9 +333,9 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->cpus_allowed, cpu_online_mask))
+	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
 		cs = parent_cs(cs);
-	cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask);
+	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
 /*
@@ -325,9 +351,9 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
  */
 static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
 {
-	while (!nodes_intersects(cs->mems_allowed, node_states[N_MEMORY]))
+	while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY]))
 		cs = parent_cs(cs);
-	nodes_and(*pmask, cs->mems_allowed, node_states[N_MEMORY]);
+	nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]);
 }
 
 /*
@@ -376,13 +402,20 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
 	if (!trial)
 		return NULL;
 
-	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) {
-		kfree(trial);
-		return NULL;
-	}
-	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL))
+		goto free_cs;
+	if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL))
+		goto free_cpus;
 
+	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+	cpumask_copy(trial->effective_cpus, cs->effective_cpus);
 	return trial;
+
+free_cpus:
+	free_cpumask_var(trial->cpus_allowed);
+free_cs:
+	kfree(trial);
+	return NULL;
 }
 
 /**
@@ -391,6 +424,7 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
  */
 static void free_trial_cpuset(struct cpuset *trial)
 {
+	free_cpumask_var(trial->effective_cpus);
 	free_cpumask_var(trial->cpus_allowed);
 	kfree(trial);
 }
@@ -436,9 +470,9 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	par = parent_cs(cur);
 
-	/* We must be a subset of our parent cpuset */
+	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
 	ret = -EACCES;
-	if (!is_cpuset_subset(trial, par))
+	if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
 		goto out;
 
 	/*
@@ -480,11 +514,11 @@ out:
 #ifdef CONFIG_SMP
 /*
  * Helper routine for generate_sched_domains().
- * Do cpusets a, b have overlapping cpus_allowed masks?
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
  */
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
-	return cpumask_intersects(a->cpus_allowed, b->cpus_allowed);
+	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
 }
 
 static void
@@ -601,7 +635,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms[0], top_cpuset.cpus_allowed);
+		cpumask_copy(doms[0], top_cpuset.effective_cpus);
 
 		goto done;
 	}
@@ -705,7 +739,7 @@ restart:
 			struct cpuset *b = csa[j];
 
 			if (apn == b->pn) {
-				cpumask_or(dp, dp, b->cpus_allowed);
+				cpumask_or(dp, dp, b->effective_cpus);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -757,7 +791,7 @@ static void rebuild_sched_domains_locked(void)
 	 * passing doms with offlined cpu to partition_sched_domains().
 	 * Anyways, hotplug work item will rebuild sched domains.
 	 */
-	if (!cpumask_equal(top_cpuset.cpus_allowed, cpu_active_mask))
+	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
 		goto out;
 
 	/* Generate domain masks and attrs */
@@ -781,45 +815,6 @@ void rebuild_sched_domains(void)
 	mutex_unlock(&cpuset_mutex);
 }
 
-/*
- * effective_cpumask_cpuset - return nearest ancestor with non-empty cpus
- * @cs: the cpuset in interest
- *
- * A cpuset's effective cpumask is the cpumask of the nearest ancestor
- * with non-empty cpus. We use effective cpumask whenever:
- * - we update tasks' cpus_allowed. (they take on the ancestor's cpumask
- *   if the cpuset they reside in has no cpus)
- * - we want to retrieve task_cs(tsk)'s cpus_allowed.
- *
- * Called with cpuset_mutex held. cpuset_cpus_allowed_fallback() is an
- * exception. See comments there.
- */
-static struct cpuset *effective_cpumask_cpuset(struct cpuset *cs)
-{
-	while (cpumask_empty(cs->cpus_allowed))
-		cs = parent_cs(cs);
-	return cs;
-}
-
-/*
- * effective_nodemask_cpuset - return nearest ancestor with non-empty mems
- * @cs: the cpuset in interest
- *
- * A cpuset's effective nodemask is the nodemask of the nearest ancestor
- * with non-empty memss. We use effective nodemask whenever:
- * - we update tasks' mems_allowed. (they take on the ancestor's nodemask
- *   if the cpuset they reside in has no mems)
- * - we want to retrieve task_cs(tsk)'s mems_allowed.
- *
- * Called with cpuset_mutex held.
- */
-static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
-{
-	while (nodes_empty(cs->mems_allowed))
-		cs = parent_cs(cs);
-	return cs;
-}
-
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
@@ -830,53 +825,80 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
  */
 static void update_tasks_cpumask(struct cpuset *cs)
 {
-	struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
 	struct css_task_iter it;
 	struct task_struct *task;
 
 	css_task_iter_start(&cs->css, &it);
 	while ((task = css_task_iter_next(&it)))
-		set_cpus_allowed_ptr(task, cpus_cs->cpus_allowed);
+		set_cpus_allowed_ptr(task, cs->effective_cpus);
 	css_task_iter_end(&it);
 }
 
 /*
- * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
- * @root_cs: the root cpuset of the hierarchy
- * @update_root: update root cpuset or not?
+ * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_cpus: temp variable for calculating new effective_cpus
+ *
+ * When congifured cpumask is changed, the effective cpumasks of this cpuset
+ * and all its descendants need to be updated.
  *
- * This will update cpumasks of tasks in @root_cs and all other empty cpusets
- * which take on cpumask of @root_cs.
+ * On legacy hierachy, effective_cpus will be the same with cpu_allowed.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root)
+static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
+	bool need_rebuild_sched_domains = false;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs) {
-			if (!update_root)
-				continue;
-		} else {
-			/* skip the whole subtree if @cp have some CPU */
-			if (!cpumask_empty(cp->cpus_allowed)) {
-				pos_css = css_rightmost_descendant(pos_css);
-				continue;
-			}
+	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+		struct cpuset *parent = parent_cs(cp);
+
+		cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);
+
+		/*
+		 * If it becomes empty, inherit the effective mask of the
+		 * parent, which is guaranteed to have some CPUs.
+		 */
+		if (cpumask_empty(new_cpus))
+			cpumask_copy(new_cpus, parent->effective_cpus);
+
+		/* Skip the whole subtree if the cpumask remains the same. */
+		if (cpumask_equal(new_cpus, cp->effective_cpus)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
 		}
+
 		if (!css_tryget_online(&cp->css))
 			continue;
 		rcu_read_unlock();
 
+		mutex_lock(&callback_mutex);
+		cpumask_copy(cp->effective_cpus, new_cpus);
+		mutex_unlock(&callback_mutex);
+
+		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
+
 		update_tasks_cpumask(cp);
 
+		/*
+		 * If the effective cpumask of any non-empty cpuset is changed,
+		 * we need to rebuild sched domains.
+		 */
+		if (!cpumask_empty(cp->cpus_allowed) &&
+		    is_sched_load_balance(cp))
+			need_rebuild_sched_domains = true;
+
 		rcu_read_lock();
 		css_put(&cp->css);
 	}
 	rcu_read_unlock();
+
+	if (need_rebuild_sched_domains)
+		rebuild_sched_domains_locked();
 }
 
 /**
@@ -889,7 +911,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			  const char *buf)
 {
 	int retval;
-	int is_load_balanced;
 
 	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
 	if (cs == &top_cpuset)
@@ -908,7 +929,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		if (retval < 0)
 			return retval;
 
-		if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
+		if (!cpumask_subset(trialcs->cpus_allowed,
+				    top_cpuset.cpus_allowed))
 			return -EINVAL;
 	}
 
@@ -920,16 +942,12 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		return retval;
 
-	is_load_balanced = is_sched_load_balance(trialcs);
-
 	mutex_lock(&callback_mutex);
 	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
-	update_tasks_cpumask_hier(cs, true);
-
-	if (is_load_balanced)
-		rebuild_sched_domains_locked();
+	/* use trialcs->cpus_allowed as a temp variable */
+	update_cpumasks_hier(cs, trialcs->cpus_allowed);
 	return 0;
 }
 
@@ -951,15 +969,13 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
 	struct task_struct *tsk = current;
-	struct cpuset *mems_cs;
 
 	tsk->mems_allowed = *to;
 
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
 	rcu_read_lock();
-	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
-	guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
 	rcu_read_unlock();
 }
 
@@ -1028,13 +1044,12 @@ static void *cpuset_being_rebound;
 static void update_tasks_nodemask(struct cpuset *cs)
 {
 	static nodemask_t newmems;	/* protected by cpuset_mutex */
-	struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
 	struct css_task_iter it;
 	struct task_struct *task;
 
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
-	guarantee_online_mems(mems_cs, &newmems);
+	guarantee_online_mems(cs, &newmems);
 
 	/*
 	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
@@ -1077,36 +1092,52 @@ static void update_tasks_nodemask(struct cpuset *cs)
 }
 
 /*
- * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
- * @cs: the root cpuset of the hierarchy
- * @update_root: update the root cpuset or not?
+ * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_mems: a temp variable for calculating new effective_mems
  *
- * This will update nodemasks of tasks in @root_cs and all other empty cpusets
- * which take on nodemask of @root_cs.
+ * When configured nodemask is changed, the effective nodemasks of this cpuset
+ * and all its descendants need to be updated.
+ *
+ * On legacy hiearchy, effective_mems will be the same with mems_allowed.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root)
+static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs) {
-			if (!update_root)
-				continue;
-		} else {
-			/* skip the whole subtree if @cp have some CPU */
-			if (!nodes_empty(cp->mems_allowed)) {
-				pos_css = css_rightmost_descendant(pos_css);
-				continue;
-			}
+	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+		struct cpuset *parent = parent_cs(cp);
+
+		nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems);
+
+		/*
+		 * If it becomes empty, inherit the effective mask of the
+		 * parent, which is guaranteed to have some MEMs.
+		 */
+		if (nodes_empty(*new_mems))
+			*new_mems = parent->effective_mems;
+
+		/* Skip the whole subtree if the nodemask remains the same. */
+		if (nodes_equal(*new_mems, cp->effective_mems)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
 		}
+
 		if (!css_tryget_online(&cp->css))
 			continue;
 		rcu_read_unlock();
 
+		mutex_lock(&callback_mutex);
+		cp->effective_mems = *new_mems;
+		mutex_unlock(&callback_mutex);
+
+		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+			!nodes_equal(cp->mems_allowed, cp->effective_mems));
+
 		update_tasks_nodemask(cp);
 
 		rcu_read_lock();
@@ -1156,8 +1187,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 			goto done;
 
 		if (!nodes_subset(trialcs->mems_allowed,
-				node_states[N_MEMORY])) {
-			retval =  -EINVAL;
+				  top_cpuset.mems_allowed)) {
+			retval = -EINVAL;
 			goto done;
 		}
 	}
@@ -1174,7 +1205,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	cs->mems_allowed = trialcs->mems_allowed;
 	mutex_unlock(&callback_mutex);
 
-	update_tasks_nodemask_hier(cs, true);
+	/* use trialcs->mems_allowed as a temp variable */
+	update_nodemasks_hier(cs, &cs->mems_allowed);
 done:
 	return retval;
 }
@@ -1389,12 +1421,9 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 
 	mutex_lock(&cpuset_mutex);
 
-	/*
-	 * We allow to move tasks into an empty cpuset if sane_behavior
-	 * flag is set.
-	 */
+	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
-	if (!cgroup_sane_behavior(css->cgroup) &&
+	if (!cgroup_on_dfl(css->cgroup) &&
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
@@ -1452,8 +1481,6 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	struct task_struct *leader = cgroup_taskset_first(tset);
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *oldcs = cpuset_attach_old_cs;
-	struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
-	struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -1461,9 +1488,9 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	if (cs == &top_cpuset)
 		cpumask_copy(cpus_attach, cpu_possible_mask);
 	else
-		guarantee_online_cpus(cpus_cs, cpus_attach);
+		guarantee_online_cpus(cs, cpus_attach);
 
-	guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to);
+	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
 	cgroup_taskset_for_each(task, tset) {
 		/*
@@ -1480,11 +1507,9 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	 * Change mm, possibly for multiple threads in a threadgroup. This is
 	 * expensive and may sleep.
 	 */
-	cpuset_attach_nodemask_to = cs->mems_allowed;
+	cpuset_attach_nodemask_to = cs->effective_mems;
 	mm = get_task_mm(leader);
 	if (mm) {
-		struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs);
-
 		mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
 
 		/*
@@ -1495,7 +1520,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 		 * mm from.
 		 */
 		if (is_memory_migrate(cs)) {
-			cpuset_migrate_mm(mm, &mems_oldcs->old_mems_allowed,
+			cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 					  &cpuset_attach_nodemask_to);
 		}
 		mmput(mm);
@@ -1516,6 +1541,8 @@ typedef enum {
 	FILE_MEMORY_MIGRATE,
 	FILE_CPULIST,
 	FILE_MEMLIST,
+	FILE_EFFECTIVE_CPULIST,
+	FILE_EFFECTIVE_MEMLIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_MEM_HARDWALL,
@@ -1694,6 +1721,12 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_MEMLIST:
 		s += nodelist_scnprintf(s, count, cs->mems_allowed);
 		break;
+	case FILE_EFFECTIVE_CPULIST:
+		s += cpulist_scnprintf(s, count, cs->effective_cpus);
+		break;
+	case FILE_EFFECTIVE_MEMLIST:
+		s += nodelist_scnprintf(s, count, cs->effective_mems);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out_unlock;
@@ -1779,6 +1812,18 @@ static struct cftype files[] = {
 	},
 
 	{
+		.name = "effective_cpus",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_CPULIST,
+	},
+
+	{
+		.name = "effective_mems",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_MEMLIST,
+	},
+
+	{
 		.name = "cpu_exclusive",
 		.read_u64 = cpuset_read_u64,
 		.write_u64 = cpuset_write_u64,
@@ -1869,18 +1914,26 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
-	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) {
-		kfree(cs);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
+		goto free_cs;
+	if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
+		goto free_cpus;
 
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
 	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
+	cpumask_clear(cs->effective_cpus);
+	nodes_clear(cs->effective_mems);
 	fmeter_init(&cs->fmeter);
 	cs->relax_domain_level = -1;
 
 	return &cs->css;
+
+free_cpus:
+	free_cpumask_var(cs->cpus_allowed);
+free_cs:
+	kfree(cs);
+	return ERR_PTR(-ENOMEM);
 }
 
 static int cpuset_css_online(struct cgroup_subsys_state *css)
@@ -1903,6 +1956,13 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
 	cpuset_inc();
 
+	mutex_lock(&callback_mutex);
+	if (cgroup_on_dfl(cs->css.cgroup)) {
+		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
+		cs->effective_mems = parent->effective_mems;
+	}
+	mutex_unlock(&callback_mutex);
+
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
 		goto out_unlock;
 
@@ -1962,20 +2022,40 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
+	free_cpumask_var(cs->effective_cpus);
 	free_cpumask_var(cs->cpus_allowed);
 	kfree(cs);
 }
 
+static void cpuset_bind(struct cgroup_subsys_state *root_css)
+{
+	mutex_lock(&cpuset_mutex);
+	mutex_lock(&callback_mutex);
+
+	if (cgroup_on_dfl(root_css->cgroup)) {
+		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
+		top_cpuset.mems_allowed = node_possible_map;
+	} else {
+		cpumask_copy(top_cpuset.cpus_allowed,
+			     top_cpuset.effective_cpus);
+		top_cpuset.mems_allowed = top_cpuset.effective_mems;
+	}
+
+	mutex_unlock(&callback_mutex);
+	mutex_unlock(&cpuset_mutex);
+}
+
 struct cgroup_subsys cpuset_cgrp_subsys = {
-	.css_alloc = cpuset_css_alloc,
-	.css_online = cpuset_css_online,
-	.css_offline = cpuset_css_offline,
-	.css_free = cpuset_css_free,
-	.can_attach = cpuset_can_attach,
-	.cancel_attach = cpuset_cancel_attach,
-	.attach = cpuset_attach,
-	.base_cftypes = files,
-	.early_init = 1,
+	.css_alloc	= cpuset_css_alloc,
+	.css_online	= cpuset_css_online,
+	.css_offline	= cpuset_css_offline,
+	.css_free	= cpuset_css_free,
+	.can_attach	= cpuset_can_attach,
+	.cancel_attach	= cpuset_cancel_attach,
+	.attach		= cpuset_attach,
+	.bind		= cpuset_bind,
+	.legacy_cftypes	= files,
+	.early_init	= 1,
 };
 
 /**
@@ -1990,9 +2070,13 @@ int __init cpuset_init(void)
 
 	if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
 		BUG();
+	if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
+		BUG();
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
+	cpumask_setall(top_cpuset.effective_cpus);
+	nodes_setall(top_cpuset.effective_mems);
 
 	fmeter_init(&top_cpuset.fmeter);
 	set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
@@ -2035,6 +2119,66 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 	}
 }
 
+static void
+hotplug_update_tasks_legacy(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated)
+{
+	bool is_empty;
+
+	mutex_lock(&callback_mutex);
+	cpumask_copy(cs->cpus_allowed, new_cpus);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->mems_allowed = *new_mems;
+	cs->effective_mems = *new_mems;
+	mutex_unlock(&callback_mutex);
+
+	/*
+	 * Don't call update_tasks_cpumask() if the cpuset becomes empty,
+	 * as the tasks will be migratecd to an ancestor.
+	 */
+	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
+		update_tasks_cpumask(cs);
+	if (mems_updated && !nodes_empty(cs->mems_allowed))
+		update_tasks_nodemask(cs);
+
+	is_empty = cpumask_empty(cs->cpus_allowed) ||
+		   nodes_empty(cs->mems_allowed);
+
+	mutex_unlock(&cpuset_mutex);
+
+	/*
+	 * Move tasks to the nearest ancestor with execution resources,
+	 * This is full cgroup operation which will also call back into
+	 * cpuset. Should be done outside any lock.
+	 */
+	if (is_empty)
+		remove_tasks_in_empty_cpuset(cs);
+
+	mutex_lock(&cpuset_mutex);
+}
+
+static void
+hotplug_update_tasks(struct cpuset *cs,
+		     struct cpumask *new_cpus, nodemask_t *new_mems,
+		     bool cpus_updated, bool mems_updated)
+{
+	if (cpumask_empty(new_cpus))
+		cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
+	if (nodes_empty(*new_mems))
+		*new_mems = parent_cs(cs)->effective_mems;
+
+	mutex_lock(&callback_mutex);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->effective_mems = *new_mems;
+	mutex_unlock(&callback_mutex);
+
+	if (cpus_updated)
+		update_tasks_cpumask(cs);
+	if (mems_updated)
+		update_tasks_nodemask(cs);
+}
+
 /**
  * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
  * @cs: cpuset in interest
@@ -2045,11 +2189,10 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  */
 static void cpuset_hotplug_update_tasks(struct cpuset *cs)
 {
-	static cpumask_t off_cpus;
-	static nodemask_t off_mems;
-	bool is_empty;
-	bool sane = cgroup_sane_behavior(cs->css.cgroup);
-
+	static cpumask_t new_cpus;
+	static nodemask_t new_mems;
+	bool cpus_updated;
+	bool mems_updated;
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
 
@@ -2064,51 +2207,20 @@ retry:
 		goto retry;
 	}
 
-	cpumask_andnot(&off_cpus, cs->cpus_allowed, top_cpuset.cpus_allowed);
-	nodes_andnot(off_mems, cs->mems_allowed, top_cpuset.mems_allowed);
-
-	mutex_lock(&callback_mutex);
-	cpumask_andnot(cs->cpus_allowed, cs->cpus_allowed, &off_cpus);
-	mutex_unlock(&callback_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we need to update tasks' cpumask
-	 * for empty cpuset to take on ancestor's cpumask. Otherwise, don't
-	 * call update_tasks_cpumask() if the cpuset becomes empty, as
-	 * the tasks in it will be migrated to an ancestor.
-	 */
-	if ((sane && cpumask_empty(cs->cpus_allowed)) ||
-	    (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
-		update_tasks_cpumask(cs);
+	cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
+	nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
 
-	mutex_lock(&callback_mutex);
-	nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);
-	mutex_unlock(&callback_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we need to update tasks' nodemask
-	 * for empty cpuset to take on ancestor's nodemask. Otherwise, don't
-	 * call update_tasks_nodemask() if the cpuset becomes empty, as
-	 * the tasks in it will be migratd to an ancestor.
-	 */
-	if ((sane && nodes_empty(cs->mems_allowed)) ||
-	    (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
-		update_tasks_nodemask(cs);
+	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
+	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-	is_empty = cpumask_empty(cs->cpus_allowed) ||
-		nodes_empty(cs->mems_allowed);
+	if (cgroup_on_dfl(cs->css.cgroup))
+		hotplug_update_tasks(cs, &new_cpus, &new_mems,
+				     cpus_updated, mems_updated);
+	else
+		hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
+					    cpus_updated, mems_updated);
 
 	mutex_unlock(&cpuset_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we'll keep tasks in empty cpusets.
-	 *
-	 * Otherwise move tasks to the nearest ancestor with execution
-	 * resources.  This is full cgroup operation which will
-	 * also call back into cpuset.  Should be done outside any lock.
-	 */
-	if (!sane && is_empty)
-		remove_tasks_in_empty_cpuset(cs);
 }
 
 /**
@@ -2132,6 +2244,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
+	bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -2139,13 +2252,15 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	cpumask_copy(&new_cpus, cpu_active_mask);
 	new_mems = node_states[N_MEMORY];
 
-	cpus_updated = !cpumask_equal(top_cpuset.cpus_allowed, &new_cpus);
-	mems_updated = !nodes_equal(top_cpuset.mems_allowed, new_mems);
+	cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus);
+	mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
 
 	/* synchronize cpus_allowed to cpu_active_mask */
 	if (cpus_updated) {
 		mutex_lock(&callback_mutex);
-		cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+		if (!on_dfl)
+			cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+		cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
 		mutex_unlock(&callback_mutex);
 		/* we don't mess with cpumasks of tasks in top_cpuset */
 	}
@@ -2153,7 +2268,9 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	/* synchronize mems_allowed to N_MEMORY */
 	if (mems_updated) {
 		mutex_lock(&callback_mutex);
-		top_cpuset.mems_allowed = new_mems;
+		if (!on_dfl)
+			top_cpuset.mems_allowed = new_mems;
+		top_cpuset.effective_mems = new_mems;
 		mutex_unlock(&callback_mutex);
 		update_tasks_nodemask(&top_cpuset);
 	}
@@ -2228,6 +2345,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.mems_allowed = node_states[N_MEMORY];
 	top_cpuset.old_mems_allowed = top_cpuset.mems_allowed;
 
+	cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask);
+	top_cpuset.effective_mems = node_states[N_MEMORY];
+
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
 }
 
@@ -2244,23 +2364,17 @@ void __init cpuset_init_smp(void)
 
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
-	struct cpuset *cpus_cs;
-
 	mutex_lock(&callback_mutex);
 	rcu_read_lock();
-	cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
-	guarantee_online_cpus(cpus_cs, pmask);
+	guarantee_online_cpus(task_cs(tsk), pmask);
 	rcu_read_unlock();
 	mutex_unlock(&callback_mutex);
 }
 
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-	struct cpuset *cpus_cs;
-
 	rcu_read_lock();
-	cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
-	do_set_cpus_allowed(tsk, cpus_cs->cpus_allowed);
+	do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus);
 	rcu_read_unlock();
 
 	/*
@@ -2299,13 +2413,11 @@ void cpuset_init_current_mems_allowed(void)
 
 nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 {
-	struct cpuset *mems_cs;
 	nodemask_t mask;
 
 	mutex_lock(&callback_mutex);
 	rcu_read_lock();
-	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
-	guarantee_online_mems(mems_cs, &mask);
+	guarantee_online_mems(task_cs(tsk), &mask);
 	rcu_read_unlock();
 	mutex_unlock(&callback_mutex);