cgroup/cpuset: Avoid unnecessary cpus & mems update in cpuset_hotplug_update_tasks()

As reported by sashiko [1], cpuset_hotplug_update_tasks() may perform
unnecessary task iteration and updating of tasks' CPU and node masks
when mems_allowed and/or cpus_allowed are not set in cpuset v2. It is
due to the fact that the temporary new_cpus and new_mems masks do not
inherit parent's effective_cpus/mems when they are empty which is the
expected behavior for cpuset v2 since commit 4ec22e9c5a90 ("cpuset:
Enable cpuset controller in default hierarchy").

Fix that and avoid unnecessary work by enhancing
compute_effective_cpumask() to add the empty cpumask check
and inheriting the parent's versions if empty when in v2. A new
compute_effective_nodemask() helper is also added to perform a similar
function for new effective_mems.

Add new test_cpuset_prs.sh test cases to confirm that effective_cpus
will inherit the parent's version if cpuset.cpus is empty.

[1] https://sashiko.dev/#/patchset/20260621032816.1806773-1-longman%40redhat.com

Suggested-by: Ridong Chen <ridong.chen@linux.dev>
Fixes: 4ec22e9c5a90 ("cpuset: Enable cpuset controller in default hierarchy")
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Ridong Chen <ridong.chen@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 26 insertions, 19 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 591e3aa487fc..a404894411dc 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1089,12 +1089,35 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
  * @cs: the cpuset the need to recompute the new effective_cpus mask
  * @parent: the parent cpuset
  *
+ * For v2, the parent's effective_cpus is inherited if cpumask is empty.
  * The result is valid only if the given cpuset isn't a partition root.
  */
 static void compute_effective_cpumask(struct cpumask *new_cpus,
 				      struct cpuset *cs, struct cpuset *parent)
 {
-	cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
+	bool has_cpus;
+
+	has_cpus = cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
+	if (!has_cpus && is_in_v2_mode())
+		cpumask_copy(new_cpus, parent->effective_cpus);
+}
+
+/**
+ * compute_effective_nodemask - Compute the effective nodemask of the cpuset
+ * @new_mems: the temp variable for the new effective_mems mask
+ * @cs: the cpuset the need to recompute the new effective_mems mask
+ * @parent: the parent cpuset
+ *
+ * For v2, the parent's effective_mems is inherited if nodemask is empty.
+ */
+static void compute_effective_nodemask(nodemask_t *new_mems,
+				       struct cpuset *cs, struct cpuset *parent)
+{
+	bool has_mems;
+
+	has_mems = nodes_and(*new_mems, cs->mems_allowed, parent->effective_mems);
+	if (!has_mems && is_in_v2_mode())
+		nodes_copy(*new_mems, parent->effective_mems);
 }
 
 /*
@@ -2144,15 +2167,6 @@ 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 unless
-		 * it is a partition root that has explicitly distributed
-		 * out all its CPUs.
-		 */
-		if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus))
-			cpumask_copy(tmp->new_cpus, parent->effective_cpus);
-
-		/*
 		 * Skip the whole subtree if
 		 * 1) the cpumask remains the same,
 		 * 2) has no partition root state,
@@ -2692,14 +2706,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
 		struct cpuset *parent = parent_cs(cp);
 
-		bool has_mems = 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 (is_in_v2_mode() && !has_mems)
-			*new_mems = parent->effective_mems;
+		compute_effective_nodemask(new_mems, cp, parent);
 
 		/* Skip the whole subtree if the nodemask remains the same. */
 		if (nodes_equal(*new_mems, cp->effective_mems)) {
@@ -3773,7 +3780,7 @@ retry:
 
 	parent = parent_cs(cs);
 	compute_effective_cpumask(&new_cpus, cs, parent);
-	nodes_and(new_mems, cs->mems_allowed, parent->effective_mems);
+	compute_effective_nodemask(&new_mems, cs, parent);
 
 	if (!tmp || !cs->partition_root_state)
 		goto update_tasks;