Merge tag 'cgroup-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cpuset changes including the fix for an incorrect interaction with
   CPU hotplug and an optimization

 - Other doc and cosmetic changes

* tag 'cgroup-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup-v1/cpusets: update libcgroup project link
  cgroup/cpuset: Minor updates to test_cpuset_prs.sh
  cgroup/cpuset: Include offline CPUs when tasks' cpumasks in top_cpuset are updated
  cgroup/cpuset: Skip task update if hotplug doesn't affect current cpuset
  cpuset: Clean up cpuset_node_allowed
  cgroup: bpf: use cgroup_lock()/cgroup_unlock() wrappers

1 files changed, 19 insertions, 11 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 505d86b16642..e4ca2dd2b764 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1209,7 +1209,9 @@ void rebuild_sched_domains(void)
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
- * cpuset membership stays stable.
+ * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
+ * is used instead of effective_cpus to make sure all offline CPUs are also
+ * included as hotplug code won't update cpumasks for tasks in top_cpuset.
  */
 static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
@@ -1219,15 +1221,18 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 
 	css_task_iter_start(&cs->css, 0, &it);
 	while ((task = css_task_iter_next(&it))) {
-		/*
-		 * Percpu kthreads in top_cpuset are ignored
-		 */
-		if (top_cs && (task->flags & PF_KTHREAD) &&
-		    kthread_is_per_cpu(task))
-			continue;
+		const struct cpumask *possible_mask = task_cpu_possible_mask(task);
 
-		cpumask_and(new_cpus, cs->effective_cpus,
-			    task_cpu_possible_mask(task));
+		if (top_cs) {
+			/*
+			 * Percpu kthreads in top_cpuset are ignored
+			 */
+			if ((task->flags & PF_KTHREAD) && kthread_is_per_cpu(task))
+				continue;
+			cpumask_andnot(new_cpus, possible_mask, cs->subparts_cpus);
+		} else {
+			cpumask_and(new_cpus, possible_mask, cs->effective_cpus);
+		}
 		set_cpus_allowed_ptr(task, new_cpus);
 	}
 	css_task_iter_end(&it);
@@ -3618,6 +3623,8 @@ retry:
 update_tasks:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
+	if (!cpus_updated && !mems_updated)
+		goto unlock;	/* Hotplug doesn't affect this cpuset */
 
 	if (mems_updated)
 		check_insane_mems_config(&new_mems);
@@ -3629,6 +3636,7 @@ update_tasks:
 		hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
 					    cpus_updated, mems_updated);
 
+unlock:
 	percpu_up_write(&cpuset_rwsem);
 }
 
@@ -3941,7 +3949,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 }
 
 /*
- * __cpuset_node_allowed - Can we allocate on a memory node?
+ * cpuset_node_allowed - Can we allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -3980,7 +3988,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
-bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
+bool cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	struct cpuset *cs;		/* current cpuset ancestors */
 	bool allowed;			/* is allocation in zone z allowed? */