[PATCH 3/5] cgroup/cpuset: Allow non-top parent partition root to distribute out all CPUs

[Waiman Long]

Currently, a parent partition root cannot distribute all its CPUs to
child partition roots with no CPUs left. However in some use cases,
a management application may want to create a parent partition root as
a management unit with no task associated with it and has all its CPUs
distributed to various child partition roots dynamically according to
their needs. Leaving a cpu in the parent partition root in such a case is
now a waste.

To accommodate such use cases, a parent partition root can now have
all its CPUs distributed to its child partition roots as long as:
 1) it is not the top cpuset; and
 2) there is no task directly associated with the parent.

Once an empty parent partition root is formed, no new task can be moved
into it.

Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c | 44 +++++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 13 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 78dd6c91dcd6..ef19eb317fef 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1117,7 +1117,7 @@ enum subparts_cmd {
  * cpus_allowed can be granted or an error code will be returned.
  *
  * For partcmd_disable, the cpuset is being transofrmed from a partition
- * root back to a non-partition root. any CPUs in cpus_allowed that are in
+ * root back to a non-partition root. Any CPUs in cpus_allowed that are in
  * parent's subparts_cpus will be taken away from that cpumask and put back
  * into parent's effective_cpus. 0 should always be returned.
  *
@@ -1172,21 +1172,31 @@ 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;
 	if (cmd == partcmd_enable) {
+		bool parent_is_top_cpuset = !parent_cs(parent);
+		bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed,
+						      parent->effective_cpus);
+		/*
+		 * Enabling partition root is not allowed if not all the CPUs
+		 * can be granted from parent's effective_cpus. If the parent
+		 * is the top cpuset, at least one CPU must be left after that.
+		 */
+		if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
+		    (parent_is_top_cpuset && no_cpu_in_parent))
+			return -EINVAL;
+
+		/*
+		 * A non-top parent can be left with no CPU as long as there
+		 * is no task directly associated with the parent. For such
+		 * a parent, no new task can be moved into it.
+		 */
+		if (no_cpu_in_parent && parent->css.cgroup->nr_populated_csets)
+			return -EINVAL;
+
 		cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
 		adding = true;
 	} else if (cmd == partcmd_disable) {
@@ -1208,9 +1218,10 @@ 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 && parent->css.cgroup->nr_populated_csets &&
 		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
 			if (!deleting)
 				return -EINVAL;
@@ -2181,6 +2192,13 @@ 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)
-- 
2.18.1