[PATCH v8 0/6] cgroup/cpuset: Add new cpuset partition type & empty effecitve cpus

@@ -386,6 +386,41 @@ static inline bool is_in_v2_mode(void)
 	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
 }
 
+/**
+ * partition_is_populated - check if partition has tasks
+ * @cs: partition root to be checked
+ * @excluded_child: a child cpuset to be excluded in task checking
+ * Return: true if there are tasks, false otherwise
+ *
+ * It is assumed that @cs is a valid partition root. @excluded_child should
+ * be non-NULL when this cpuset is going to become a partition itself.
+ */
+static inline bool partition_is_populated(struct cpuset *cs,
+					  struct cpuset *excluded_child)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *child;
+
+	if (cs->css.cgroup->nr_populated_csets)
+		return true;
+	if (!excluded_child && !cs->nr_subparts_cpus)
+		return cgroup_is_populated(cs->css.cgroup);
+
+	rcu_read_lock();
+	cpuset_for_each_child(child, css, cs) {
+		if (child == excluded_child)
+			continue;
+		if (is_partition_root(child))
+			continue;
+		if (cgroup_is_populated(child->css.cgroup)) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+	return false;
+}
+
 /*
  * Return in pmask the portion of a task's cpusets's cpus_allowed that
  * are online and are capable of running the task.  If none are found,

@@ -1198,22 +1233,25 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 	if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
 		return -EBUSY;
 
-	/*
-	 * Enabling partition root is not allowed if not all the CPUs
-	 * can be granted from parent's effective_cpus or at least one
-	 * CPU will be left after that.
-	 */
-	if ((cmd == partcmd_enable) &&
-	   (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
-	     cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus)))
-		return -EINVAL;
-
-	/*
-	 * A cpumask update cannot make parent's effective_cpus become empty.
-	 */
 	adding = deleting = false;
 	old_prs = new_prs = cpuset->partition_root_state;
 	if (cmd == partcmd_enable) {
+		/*
+		 * Enabling partition root is not allowed if not all the CPUs
+		 * can be granted from parent's effective_cpus.
+		 */
+		if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus))
+			return -EINVAL;
+
+		/*
+		 * A parent can be left with no CPU as long as there is no
+		 * task directly associated with the parent partition. For
+		 * such a parent, no new task can be moved into it.
+		 */
+		if (partition_is_populated(parent, cpuset) &&
+		    cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))
+			return -EINVAL;
+
 		cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
 		adding = true;
 	} else if (cmd == partcmd_disable) {

@@ -1235,9 +1273,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
 					parent->subparts_cpus);
 		/*
-		 * Return error if the new effective_cpus could become empty.
+		 * Return error if the new effective_cpus could become empty
+		 * and there are tasks in the parent.
 		 */
-		if (adding &&
+		if (adding && partition_is_populated(parent, cpuset) &&
 		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
 			if (!deleting)
 				return -EINVAL;

@@ -1263,8 +1302,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		 */
 		adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
 				     parent->effective_cpus);
-		part_error = cpumask_equal(tmp->addmask,
-					   parent->effective_cpus);
+		part_error = cpumask_equal(tmp->addmask, parent->effective_cpus) &&
+			     partition_is_populated(parent, cpuset);
 	}
 
 	if (cmd == partcmd_update) {

@@ -1366,9 +1405,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 
 		/*
 		 * If it becomes empty, inherit the effective mask of the
-		 * parent, which is guaranteed to have some CPUs.
+		 * parent, which is guaranteed to have some CPUs unless
+		 * it is a partition root that has explicitly distributed
+		 * out all its CPUs.
 		 */
 		if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
+			if (is_partition_root(cp) &&
+			    cpumask_equal(cp->cpus_allowed, cp->subparts_cpus))
+				goto update_parent_subparts;
+
 			cpumask_copy(tmp->new_cpus, parent->effective_cpus);
 			if (!cp->use_parent_ecpus) {
 				cp->use_parent_ecpus = true;

@@ -1390,6 +1435,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 			continue;
 		}
 
+update_parent_subparts:
 		/*
 		 * update_parent_subparts_cpumask() should have been called
 		 * for cs already in update_cpumask(). We should also call

@@ -2189,6 +2235,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
+	/*
+	 * On default hierarchy, task cannot be moved to a cpuset with empty
+	 * effective cpus.
+	 */
+	if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus))
+		goto out_unlock;
+
 	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->cpus_allowed);
 		if (ret)

@@ -3053,7 +3106,8 @@ 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))
+	/* A partition root is allowed to have empty effective cpus */
+	if (cpumask_empty(new_cpus) && !is_partition_root(cs))
 		cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
 	if (nodes_empty(*new_mems))
 		*new_mems = parent_cs(cs)->effective_mems;

@@ -3122,11 +3176,12 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 
 	/*
 	 * In the unlikely event that a partition root has empty
-	 * effective_cpus or its parent becomes erroneous, we have to
-	 * transition it to the erroneous state.
+	 * effective_cpus with tasks or its parent becomes erroneous, we
+	 * have to transition it to the erroneous state.
 	 */
-	if (is_partition_root(cs) && (cpumask_empty(&new_cpus) ||
-	   (parent->partition_root_state == PRS_ERROR))) {
+	if (is_partition_root(cs) &&
+	   ((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) ||
+	    (parent->partition_root_state == PRS_ERROR))) {
 		if (cs->nr_subparts_cpus) {
 			spin_lock_irq(&callback_lock);
 			cs->nr_subparts_cpus = 0;

@@ -3136,13 +3191,15 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 		}
 
 		/*
-		 * If the effective_cpus is empty because the child
-		 * partitions take away all the CPUs, we can keep
-		 * the current partition and let the child partitions
-		 * fight for available CPUs.
+		 * Force the partition to become invalid if either one of
+		 * the following conditions hold:
+		 * 1) empty effective cpus but not valid empty partition.
+		 * 2) parent is invalid or doesn't grant any cpus to child
+		 *    partitions.
 		 */
 		if ((parent->partition_root_state == PRS_ERROR) ||
-		     cpumask_empty(&new_cpus)) {
+		    (cpumask_empty(&new_cpus) &&
+		     partition_is_populated(cs, NULL))) {
 			int old_prs;
 
 			update_parent_subparts_cpumask(cs, partcmd_disable,

@@ -1227,29 +1227,27 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		return -EINVAL;
 
 	/*
-	 * Enabling/disabling partition root is not allowed if there are
-	 * online children.
+	 * Enabling partition root is not allowed if there are online children.
 	 */
-	if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
+	if ((cmd == partcmd_enable) && css_has_online_children(&cpuset->css))
 		return -EBUSY;
 
 	adding = deleting = false;
 	old_prs = new_prs = cpuset->partition_root_state;
 	if (cmd == partcmd_enable) {
 		/*
-		 * Enabling partition root is not allowed if not all the CPUs
-		 * can be granted from parent's effective_cpus.
+		 * Enabling partition root is not allowed if cpus_allowed isn't
+		 * a subset of parent's cpus_allowed.
 		 */
-		if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus))
+		if (!cpumask_subset(cpuset->cpus_allowed, parent->cpus_allowed))
 			return -EINVAL;
 
 		/*
 		 * A parent can be left with no CPU as long as there is no
-		 * task directly associated with the parent partition. For
-		 * such a parent, no new task can be moved into it.
+		 * task directly associated with the parent partition.
 		 */
 		if (partition_is_populated(parent, cpuset) &&
-		    cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))
+		    cpumask_subset(parent->effective_cpus, cpuset->cpus_allowed))
 			return -EINVAL;
 
 		cpumask_copy(tmp->addmask, cpuset->cpus_allowed);

@@ -1261,54 +1259,52 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		/*
 		 * partcmd_update with newmask:
 		 *
+		 * Compute add/delete mask to/from subparts_cpus
+		 *
 		 * delmask = cpus_allowed & ~newmask & parent->subparts_cpus
-		 * addmask = newmask & parent->effective_cpus
+		 * addmask = newmask & parent->cpus_allowed
 		 *		     & ~parent->subparts_cpus
 		 */
 		cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask);
 		deleting = cpumask_and(tmp->delmask, tmp->delmask,
 				       parent->subparts_cpus);
 
-		cpumask_and(tmp->addmask, newmask, parent->effective_cpus);
+		cpumask_and(tmp->addmask, newmask, parent->cpus_allowed);
 		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
 					parent->subparts_cpus);
 		/*
-		 * Return error if the new effective_cpus could become empty
-		 * and there are tasks in the parent.
+		 * Make partition invalid if parent's effective_cpus could
+                 * become empty and there are tasks in the parent.
 		 */
-		if (adding && partition_is_populated(parent, cpuset) &&
-		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
-			if (!deleting)
-				return -EINVAL;
-			/*
-			 * As some of the CPUs in subparts_cpus might have
-			 * been offlined, we need to compute the real delmask
-			 * to confirm that.
-			 */
-			if (!cpumask_and(tmp->addmask, tmp->delmask,
-					 cpu_active_mask))
-				return -EINVAL;
-			cpumask_copy(tmp->addmask, parent->effective_cpus);
-		}
+		part_error = partition_is_populated(parent, cpuset) &&
+			cpumask_subset(parent->effective_cpus, tmp->addmask) &&
+			!cpumask_intersects(tmp->delmask, cpu_active_mask);
 	} else {
 		/*
 		 * partcmd_update w/o newmask:
 		 *
 		 * addmask = cpus_allowed & parent->effective_cpus
 		 *
-		 * Note that parent's subparts_cpus may have been
-		 * pre-shrunk in case there is a change in the cpu list.
-		 * So no deletion is needed.
+		 * This gets invoked either due to a hotplug event or
+                 * from update_cpumasks_hier() where we can't return an
+                 * error. This can cause a partition root to become invalid
+                 * in the case of a hotplug.
+		 *
+		 * A partition error happens when:
+		 * 1) Cpuset is valid partition, but parent does not distribute
+		 *    out any CPUs.
+		 * 2) Parent has tasks and all its effective CPUs will have
+		 *    to be distributed out.
 		 */
 		adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
 				     parent->effective_cpus);
-		part_error = cpumask_equal(tmp->addmask, parent->effective_cpus) &&
-			     partition_is_populated(parent, cpuset);
+		part_error = (is_partition_root(cpuset) &&
+			      !parent->nr_subparts_cpus) ||
+			     (cpumask_equal(parent->effective_cpus, tmp->addmask) &&
+			      partition_is_populated(parent, cpuset));
 	}
 
 	if (cmd == partcmd_update) {
-		int prev_prs = cpuset->partition_root_state;
-
 		/*
 		 * Check for possible transition between PRS_ENABLED
 		 * and PRS_ERROR.

@@ -1323,13 +1319,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 				new_prs = PRS_ENABLED;
 			break;
 		}
-		/*
-		 * Set part_error if previously in invalid state.
-		 */
-		part_error = (prev_prs == PRS_ERROR);
 	}
 
-	if (!part_error && (new_prs == PRS_ERROR))
+	if ((old_prs == PRS_ERROR) && (new_prs == PRS_ERROR))
 		return 0;	/* Nothing need to be done */
 
 	if (new_prs == PRS_ERROR) {

@@ -1382,6 +1374,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
  * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
  * @cs:  the cpuset to consider
  * @tmp: temp variables for calculating effective_cpus & partition setup
+ * @force: don't skip any descendant cpusets if set
  *
  * When configured cpumask is changed, the effective cpumasks of this cpuset
  * and all its descendants need to be updated.

@@ -1390,7 +1383,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
  *
  * Called with cpuset_rwsem held
  */
-static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
+static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
+				 bool force)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;

@@ -1400,6 +1394,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 	rcu_read_lock();
 	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
 		struct cpuset *parent = parent_cs(cp);
+		bool update_parent = false;
 
 		compute_effective_cpumask(tmp->new_cpus, cp, parent);
 

@@ -1427,9 +1422,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 
 		/*
 		 * Skip the whole subtree if the cpumask remains the same
-		 * and has no partition root state.
+		 * with no partition root state and force flag not set.
 		 */
-		if (!cp->partition_root_state &&
+		if (!cp->partition_root_state && !force &&
 		    cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {
 			pos_css = css_rightmost_descendant(pos_css);
 			continue;

@@ -1466,8 +1461,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 				break;
 
 			case PRS_ENABLED:
-				if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
-					update_tasks_cpumask(parent);
+				update_parent = true;
 				break;
 
 			case PRS_ERROR:

@@ -1483,40 +1477,41 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 			continue;
 		rcu_read_unlock();
 
+		if (update_parent) {
+			if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
+				update_tasks_cpumask(parent);
+			/*
+			 * The cpuset partition_root_state may be changed
+			 * to PRS_ERROR. Capture it.
+			 */
+			new_prs = cp->partition_root_state;
+		}
+
 		spin_lock_irq(&callback_lock);
 
-		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
-		if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) {
+		if (cp->nr_subparts_cpus && (new_prs <= 0)) {
+			/*
+			 * Put all active subparts_cpus back to effective_cpus.
+			 */
+			cpumask_or(tmp->new_cpus, tmp->new_cpus,
+				   cp->subparts_cpus);
+			cpumask_and(tmp->new_cpus, tmp->new_cpus,
+				    cpu_active_mask);
 			cp->nr_subparts_cpus = 0;
 			cpumask_clear(cp->subparts_cpus);
-		} else if (cp->nr_subparts_cpus) {
+		}
+
+		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
+		if (cp->nr_subparts_cpus) {
 			/*
 			 * Make sure that effective_cpus & subparts_cpus
 			 * are mutually exclusive.
-			 *
-			 * In the unlikely event that effective_cpus
-			 * becomes empty. we clear cp->nr_subparts_cpus and
-			 * let its child partition roots to compete for
-			 * CPUs again.
 			 */
 			cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
 				       cp->subparts_cpus);
-			if (cpumask_empty(cp->effective_cpus)) {
-				cpumask_copy(cp->effective_cpus, tmp->new_cpus);
-				cpumask_clear(cp->subparts_cpus);
-				cp->nr_subparts_cpus = 0;
-			} else if (!cpumask_subset(cp->subparts_cpus,
-						   tmp->new_cpus)) {
-				cpumask_andnot(cp->subparts_cpus,
-					cp->subparts_cpus, tmp->new_cpus);
-				cp->nr_subparts_cpus
-					= cpumask_weight(cp->subparts_cpus);
-			}
 		}
 
-		if (new_prs != old_prs)
-			cp->partition_root_state = new_prs;
-
+		cp->partition_root_state = new_prs;
 		spin_unlock_irq(&callback_lock);
 		notify_partition_change(cp, old_prs, new_prs);
 

@@ -1570,7 +1565,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 		if (!sibling->use_parent_ecpus)
 			continue;
 
-		update_cpumasks_hier(sibling, tmp);
+		update_cpumasks_hier(sibling, tmp, false);
 	}
 	rcu_read_unlock();
 }

@@ -1643,13 +1638,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	 * Make sure that subparts_cpus is a subset of cpus_allowed.
 	 */
 	if (cs->nr_subparts_cpus) {
-		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
-			       cs->cpus_allowed);
+		cpumask_and(cs->subparts_cpus, cs->subparts_cpus,
+			    cs->cpus_allowed);
 		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
 	}
 	spin_unlock_irq(&callback_lock);
 
-	update_cpumasks_hier(cs, &tmp);
+	update_cpumasks_hier(cs, &tmp, false);
 
 	if (cs->partition_root_state) {
 		struct cpuset *parent = parent_cs(cs);

@@ -2071,20 +2066,23 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 	} else {
 		/*
-		 * Turning off partition root will clear the
-		 * CS_CPU_EXCLUSIVE bit.
+		 * Switch back to member is always allowed even if it
+                 * disables child partitions.
 		 */
-		if (old_prs == PRS_ERROR) {
-			update_flag(CS_CPU_EXCLUSIVE, cs, 0);
-			err = 0;
-			goto out;
+		err = 0;
+		update_parent_subparts_cpumask(cs, partcmd_disable, NULL,
+					       &tmpmask);
+		/*
+		 * If there are child partitions, we have to disable them.
+		 */
+		if (unlikely(cs->nr_subparts_cpus)) {
+			spin_lock_irq(&callback_lock);
+			cs->nr_subparts_cpus = 0;
+			cpumask_clear(cs->subparts_cpus);
+			compute_effective_cpumask(cs->effective_cpus, cs, parent);
+			spin_unlock_irq(&callback_lock);
 		}
 
-		err = update_parent_subparts_cpumask(cs, partcmd_disable,
-						     NULL, &tmpmask);
-		if (err)
-			goto out;
-
 		/* Turning off CS_CPU_EXCLUSIVE will not return error */
 		update_flag(CS_CPU_EXCLUSIVE, cs, 0);
 	}

@@ -2105,6 +2103,11 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		spin_lock_irq(&callback_lock);
 		cs->partition_root_state = new_prs;
 		spin_unlock_irq(&callback_lock);
+		/*
+		 * Update child cpusets when disabling partition.
+		 */
+		if (new_prs == PRS_DISABLED && !list_empty(&cs->css.children))
+			update_cpumasks_hier(cs, &tmpmask, true);
 		notify_partition_change(cs, old_prs, new_prs);
 	}
 

@@ -3176,12 +3179,32 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 
 	/*
 	 * In the unlikely event that a partition root has empty
-	 * effective_cpus with tasks or its parent becomes erroneous, we
-	 * have to transition it to the erroneous state.
+	 * effective_cpus with tasks, we will have to invalidate child
+	 * partitions, if present, by setting nr_subparts_cpus to 0 to
+	 * reclaim their cpus.
+	 */
+	if (is_partition_root(cs) && cpumask_empty(&new_cpus) &&
+	    cs->nr_subparts_cpus && partition_is_populated(cs, NULL)) {
+		spin_lock_irq(&callback_lock);
+		cs->nr_subparts_cpus = 0;
+		cpumask_clear(cs->subparts_cpus);
+		spin_unlock_irq(&callback_lock);
+		compute_effective_cpumask(&new_cpus, cs, parent);
+	}
+
+	/*
+	 * Force the partition to become invalid if either one of
+	 * the following conditions hold:
+	 * 1) empty effective cpus with tasks in partition
+	 * 2) parent is invalid or doesn't grant any cpus to child partitions.
 	 */
 	if (is_partition_root(cs) &&
 	   ((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) ||
-	    (parent->partition_root_state == PRS_ERROR))) {
+	    !parent->nr_subparts_cpus)) {
+		int old_prs;
+
+		update_parent_subparts_cpumask(cs, partcmd_disable,
+					       NULL, tmp);
 		if (cs->nr_subparts_cpus) {
 			spin_lock_irq(&callback_lock);
 			cs->nr_subparts_cpus = 0;

@@ -3190,40 +3213,23 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 			compute_effective_cpumask(&new_cpus, cs, parent);
 		}
 
-		/*
-		 * Force the partition to become invalid if either one of
-		 * the following conditions hold:
-		 * 1) empty effective cpus but not valid empty partition.
-		 * 2) parent is invalid or doesn't grant any cpus to child
-		 *    partitions.
-		 */
-		if ((parent->partition_root_state == PRS_ERROR) ||
-		    (cpumask_empty(&new_cpus) &&
-		     partition_is_populated(cs, NULL))) {
-			int old_prs;
-
-			update_parent_subparts_cpumask(cs, partcmd_disable,
-						       NULL, tmp);
-			old_prs = cs->partition_root_state;
-			if (old_prs != PRS_ERROR) {
-				spin_lock_irq(&callback_lock);
-				cs->partition_root_state = PRS_ERROR;
-				spin_unlock_irq(&callback_lock);
-				notify_partition_change(cs, old_prs, PRS_ERROR);
-			}
+		old_prs = cs->partition_root_state;
+		if (old_prs != PRS_ERROR) {
+			spin_lock_irq(&callback_lock);
+			cs->partition_root_state = PRS_ERROR;
+			spin_unlock_irq(&callback_lock);
+			notify_partition_change(cs, old_prs, PRS_ERROR);
 		}
 		cpuset_force_rebuild();
 	}
 
 	/*
 	 * On the other hand, an erroneous partition root may be transitioned
-	 * back to a regular one or a partition root with no CPU allocated
-	 * from the parent may change to erroneous.
+	 * back to a regular one.
 	 */
-	if (is_partition_root(parent) &&
-	   ((cs->partition_root_state == PRS_ERROR) ||
-	    !cpumask_intersects(&new_cpus, parent->subparts_cpus)) &&
-	     update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
+	else if (is_partition_root(parent) &&
+		(cs->partition_root_state == PRS_ERROR) &&
+		 update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
 		cpuset_force_rebuild();
 
 update_tasks:

@@ -172,6 +172,8 @@ struct cpuset {
  *
  *   1 - partition root
  *
+ *   2 - partition root without load balancing (isolated)
+ *
  *  -1 - invalid partition root
  *       None of the cpus in cpus_allowed can be put into the parent's
  *       subparts_cpus. In this case, the cpuset is not a real partition

@@ -181,6 +183,7 @@ struct cpuset {
  */
 #define PRS_DISABLED		0
 #define PRS_ENABLED		1
+#define PRS_ISOLATED		2
 #define PRS_ERROR		-1
 
 /*

@@ -1306,17 +1309,22 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 
 	if (cmd == partcmd_update) {
 		/*
-		 * Check for possible transition between PRS_ENABLED
-		 * and PRS_ERROR.
+		 * Check for possible transition between PRS_ERROR and
+		 * PRS_ENABLED/PRS_ISOLATED.
 		 */
 		switch (cpuset->partition_root_state) {
 		case PRS_ENABLED:
+		case PRS_ISOLATED:
 			if (part_error)
 				new_prs = PRS_ERROR;
 			break;
 		case PRS_ERROR:
-			if (!part_error)
+			if (part_error)
+				break;
+			if (is_sched_load_balance(cpuset))
 				new_prs = PRS_ENABLED;
+			else
+				new_prs = PRS_ISOLATED;
 			break;
 		}
 	}

@@ -1461,6 +1469,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 				break;
 
 			case PRS_ENABLED:
+			case PRS_ISOLATED:
 				update_parent = true;
 				break;
 

@@ -2028,6 +2037,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 static int update_prstate(struct cpuset *cs, int new_prs)
 {
 	int err, old_prs = cs->partition_root_state;
+	bool sched_domain_rebuilt = false;
 	struct cpuset *parent = parent_cs(cs);
 	struct tmpmasks tmpmask;
 

@@ -2064,6 +2074,22 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 			update_flag(CS_CPU_EXCLUSIVE, cs, 0);
 			goto out;
 		}
+
+		if (new_prs == PRS_ISOLATED) {
+			/*
+			 * Disable the load balance flag should not return an
+			 * error unless the system is running out of memory.
+			 */
+			update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
+			sched_domain_rebuilt = true;
+		}
+	} else if (old_prs && new_prs) {
+		/*
+		 * A change in load balance state only, no change in cpumasks.
+		 */
+		update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED));
+		err = 0;
+		goto out;	/* Sched domain is rebuilt in update_flag() */
 	} else {
 		/*
 		 * Switch back to member is always allowed even if it

@@ -2085,6 +2111,12 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 
 		/* Turning off CS_CPU_EXCLUSIVE will not return error */
 		update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+
+		if (!is_sched_load_balance(cs)) {
+			/* Make sure load balance is on */
+			update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
+			sched_domain_rebuilt = true;
+		}
 	}
 
 	/*

@@ -2097,7 +2129,8 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	if (parent->child_ecpus_count)
 		update_sibling_cpumasks(parent, cs, &tmpmask);
 
-	rebuild_sched_domains_locked();
+	if (!sched_domain_rebuilt)
+		rebuild_sched_domains_locked();
 out:
 	if (!err) {
 		spin_lock_irq(&callback_lock);

@@ -2609,6 +2642,9 @@ static int sched_partition_show(struct seq_file *seq, void *v)
 	case PRS_ENABLED:
 		seq_puts(seq, "root\n");
 		break;
+	case PRS_ISOLATED:
+		seq_puts(seq, "isolated\n");
+		break;
 	case PRS_DISABLED:
 		seq_puts(seq, "member\n");
 		break;

@@ -2635,6 +2671,8 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
 		val = PRS_ENABLED;
 	else if (!strcmp(buf, "member"))
 		val = PRS_DISABLED;
+	else if (!strcmp(buf, "isolated"))
+		val = PRS_ISOLATED;
 	else
 		return -EINVAL;
 

@@ -78,6 +78,24 @@ struct fmeter {
 	spinlock_t lock;	/* guards read or write of above */
 };
 
+/*
+ * Invalid partition error code
+ */
+enum prs_errcode {
+	PERR_NONE = 0,
+	PERR_INVCPUS,
+	PERR_NOCPUS,
+	PERR_PARENT,
+	PERR_HOTPLUG,
+};
+
+static const char * const perr_strings[] = {
+	[PERR_INVCPUS] = "Invalid change to cpuset.cpus",
+	[PERR_PARENT]  = "Parent is no longer a valid partition root",
+	[PERR_NOCPUS]  = "Parent unable to distribute cpu downstream",
+	[PERR_HOTPLUG] = "No cpu available due to hotplug",
+};
+
 struct cpuset {
 	struct cgroup_subsys_state css;
 

@@ -163,6 +181,9 @@ struct cpuset {
 
 	/* Handle for cpuset.cpus.partition */
 	struct cgroup_file partition_file;
+
+	/* Invalid partition error code, not lock protected */
+	enum prs_errcode prs_err;
 };
 
 /*

@@ -275,8 +296,13 @@ static inline int is_partition_root(const struct cpuset *cs)
 static inline void notify_partition_change(struct cpuset *cs,
 					   int old_prs, int new_prs)
 {
-	if (old_prs != new_prs)
-		cgroup_file_notify(&cs->partition_file);
+	if (old_prs == new_prs)
+		return;
+	cgroup_file_notify(&cs->partition_file);
+
+	/* Reset prs_err if not invalid */
+	if (new_prs != PRS_ERROR)
+		WRITE_ONCE(cs->prs_err, PERR_NONE);
 }
 
 static struct cpuset top_cpuset = {

@@ -1282,6 +1308,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		part_error = partition_is_populated(parent, cpuset) &&
 			cpumask_subset(parent->effective_cpus, tmp->addmask) &&
 			!cpumask_intersects(tmp->delmask, cpu_active_mask);
+
+		if ((READ_ONCE(cpuset->prs_err) == PERR_NONE) && part_error)
+			WRITE_ONCE(cpuset->prs_err, PERR_INVCPUS);
 	} else {
 		/*
 		 * partcmd_update w/o newmask:

@@ -1305,6 +1334,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 			      !parent->nr_subparts_cpus) ||
 			     (cpumask_equal(parent->effective_cpus, tmp->addmask) &&
 			      partition_is_populated(parent, cpuset));
+
+		if (is_partition_root(cpuset) && part_error)
+			WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS);
 	}
 
 	if (cmd == partcmd_update) {

@@ -1478,6 +1510,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 				 * When parent is invalid, it has to be too.
 				 */
 				new_prs = PRS_ERROR;
+				WRITE_ONCE(cp->prs_err, PERR_PARENT);
 				break;
 			}
 		}

@@ -2637,6 +2670,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
 static int sched_partition_show(struct seq_file *seq, void *v)
 {
 	struct cpuset *cs = css_cs(seq_css(seq));
+	const char *err;
 
 	switch (cs->partition_root_state) {
 	case PRS_ENABLED: