[PATCH v3 2/2] cpuset: Allow v2 behavior in v1 cgroup

[Waiman Long <longman@redhat.com>]

Cpuset v2 has some useful behaviors that are not present in v1 because
of backward compatibility concern. One of that is the restoration of
the original cpu and memory node mask after a hot removal and addition
event sequence.

This patch makes the cpuset controller to check the
CGRP_ROOT_CPUSET_V2_MODE flag and use the v2 behavior if it is set.

Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/cgroup/cpuset.c | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 9ed6a05..060d575 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -300,6 +300,16 @@ static inline int is_spread_slab(const struct cpuset *cs)
 static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
 
 /*
+ * Cgroup v2 behavior is used when on default hierarchy or the
+ * cgroup_v2_mode flag is set.
+ */
+static inline bool is_in_v2_mode(void)
+{
+	return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
+	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
+}
+
+/*
  * This is ugly, but preserves the userspace API for existing cpuset
  * users. If someone tries to mount the "cpuset" filesystem, we
  * silently switch it to mount "cgroup" instead
@@ -489,8 +499,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
 	ret = -EACCES;
-	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-	    !is_cpuset_subset(trial, par))
+	if (!is_in_v2_mode() && !is_cpuset_subset(trial, par))
 		goto out;
 
 	/*
@@ -903,8 +912,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some CPUs.
 		 */
-		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-		    cpumask_empty(new_cpus))
+		if (is_in_v2_mode() && cpumask_empty(new_cpus))
 			cpumask_copy(new_cpus, parent->effective_cpus);
 
 		/* Skip the whole subtree if the cpumask remains the same. */
@@ -921,7 +929,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		cpumask_copy(cp->effective_cpus, new_cpus);
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
 		update_tasks_cpumask(cp);
@@ -1157,8 +1165,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some MEMs.
 		 */
-		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-		    nodes_empty(*new_mems))
+		if (is_in_v2_mode() && nodes_empty(*new_mems))
 			*new_mems = parent->effective_mems;
 
 		/* Skip the whole subtree if the nodemask remains the same. */
@@ -1175,7 +1182,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		cp->effective_mems = *new_mems;
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		WARN_ON(!is_in_v2_mode() &&
 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
 
 		update_tasks_nodemask(cp);
@@ -1467,7 +1474,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 
 	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
-	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+	if (!is_in_v2_mode() &&
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
@@ -1985,7 +1992,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	cpuset_inc();
 
 	spin_lock_irq(&callback_lock);
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
+	if (is_in_v2_mode()) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
 	}
@@ -2062,7 +2069,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_lock(&cpuset_mutex);
 	spin_lock_irq(&callback_lock);
 
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
+	if (is_in_v2_mode()) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
 		top_cpuset.mems_allowed = node_possible_map;
 	} else {
@@ -2256,7 +2263,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs)
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
+	if (is_in_v2_mode())
 		hotplug_update_tasks(cs, &new_cpus, &new_mems,
 				     cpus_updated, mems_updated);
 	else
@@ -2287,7 +2294,7 @@ 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_subsys_on_dfl(cpuset_cgrp_subsys);
+	bool on_dfl = is_in_v2_mode();
 
 	mutex_lock(&cpuset_mutex);
 
-- 
1.8.3.1