Merge v6.16.9linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 37 insertions, 12 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a723b7dc6e4e..20f76b217650 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * of concurrent destructions.  Use a separate workqueue so that cgroup
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
+ *
+ * A cgroup destruction should enqueue work sequentially to:
+ * cgroup_offline_wq: use for css offline work
+ * cgroup_release_wq: use for css release work
+ * cgroup_free_wq: use for free work
+ *
+ * Rationale for using separate workqueues:
+ * The cgroup root free work may depend on completion of other css offline
+ * operations. If all tasks were enqueued to a single workqueue, this could
+ * create a deadlock scenario where:
+ * - Free work waits for other css offline work to complete.
+ * - But other css offline work is queued after free work in the same queue.
+ *
+ * Example deadlock scenario with single workqueue (cgroup_destroy_wq):
+ * 1. umount net_prio
+ * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)
+ * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)
+ * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.
+ * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,
+ *    which can never complete as it's behind in the same queue and
+ *    workqueue's max_active is 1.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+static struct workqueue_struct *cgroup_offline_wq;
+static struct workqueue_struct *cgroup_release_wq;
+static struct workqueue_struct *cgroup_free_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
@@ -5553,7 +5576,7 @@ static void css_release_work_fn(struct work_struct *work)
 	cgroup_unlock();
 
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -5562,7 +5585,7 @@ static void css_release(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5696,7 +5719,7 @@ err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
 }
 
@@ -5934,7 +5957,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 
 	if (atomic_dec_and_test(&css->online_cnt)) {
 		INIT_WORK(&css->destroy_work, css_killed_work_fn);
-		queue_work(cgroup_destroy_wq, &css->destroy_work);
+		queue_work(cgroup_offline_wq, &css->destroy_work);
 	}
 }
 
@@ -6320,8 +6343,14 @@ static int __init cgroup_wq_init(void)
 	 * We would prefer to do this in cgroup_init() above, but that
 	 * is called before init_workqueues(): so leave this until after.
 	 */
-	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
-	BUG_ON(!cgroup_destroy_wq);
+	cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1);
+	BUG_ON(!cgroup_offline_wq);
+
+	cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1);
+	BUG_ON(!cgroup_release_wq);
+
+	cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1);
+	BUG_ON(!cgroup_free_wq);
 	return 0;
 }
 core_initcall(cgroup_wq_init);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 717e3d1d6a2f..f3a97005713d 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6794,12 +6794,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void)
 		 * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to
 		 * the current local DSQ for running tasks and thus are not
 		 * visible to the BPF scheduler.
-		 *
-		 * Also skip re-enqueueing tasks that can only run on this
-		 * CPU, as they would just be re-added to the same local
-		 * DSQ without any benefit.
 		 */
-		if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1)
+		if (p->migration_pending)
 			continue;
 
 		dispatch_dequeue(rq, p);