[PATCH v3] cgroup: avoid flushing global workqueue in cgroup1_pidlist_destroy_all

From: Junnan Zhang <[email protected]>

cgroup1_pidlist_destroy_all() flushes the global
cgroup_pidlist_destroy_wq while destroying a cgroup. Because all cgroup
v1 pidlist destruction work items are queued on the same shared workqueue,
a single slow or stuck work item (e.g. waiting for pidlist_mutex held by a
user-space reader) blocks every concurrent cgroup destruction path.

This can lead to kworker tasks stuck in flush_workqueue() for over
hung_task_timeout seconds, as observed on busy systems running Docker or
Kubernetes workloads.

  INFO: task kworker/0:1:1438499 blocked for more than 120 seconds.
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  kworker/0:1 D 0 1438499 2 0x80000080
  Workqueue: cgroup_destroy css_free_rwork_fn
  ? __schedule+0x296/0x900
  schedule+0x28/0x80
  schedule_timeout+0x1ee/0x3a0
  ? kvm_sched_clock_read+0xd/0x20
  wait_for_completion+0x12c/0x190
  ? wake_up_q+0x70/0x70
  flush_workqueue+0x132/0x430
  ? cgroup1_pidlist_destroy_all+0x7c/0xa0
  cgroup1_pidlist_destroy_all+0x7c/0xa0
  css_free_rwork_fn+0xb5/0x390
  process_one_work+0x195/0x3e0
  worker_thread+0x30/0x390
  ? process_one_work+0x3e0/0x3e0
  kthread+0x113/0x130
  ? kthread_create_worker_on_cpu+0x70/0x70
  ret_from_fork+0x1f/0x40

Fix it by moving the cgroup's pidlists to a local orphan list under
pidlist_mutex, clearing their ->owner pointer, and then cancelling each
pidlist's delayed work outside the lock. The destroy work function now
checks ->owner and skips freeing orphaned pidlists, so
cgroup1_pidlist_destroy_all() can free them safely without flushing the
whole shared workqueue.

Signed-off-by: Junnan Zhang <[email protected]>
Signed-off-by: Shouxin Sun <[email protected]>

---
v1 -> v2:
 - Fix a NULL pointer dereference in cgroup_pidlist_destroy_work_fn():
   use the cached owner pointer for mutex_unlock(), as ->owner may have
   been cleared concurrently by cgroup1_pidlist_destroy_all(). Spotted
   by Sashiko AI review.

v2 -> v3:
 - Use READ_ONCE()/WRITE_ONCE() for the ->owner field shared between
   cgroup1_pidlist_destroy_all() and cgroup_pidlist_destroy_work_fn() to
   prevent data races. Spotted by Sashiko AI review.
---
 kernel/cgroup/cgroup-v1.c | 53 ++++++++++++++++++++++++++++-----------
 1 file changed, 38 insertions(+), 15 deletions(-)

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index a4337c9b5287..9abe8b791bb1 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -206,13 +206,31 @@ struct cgroup_pidlist {
 void cgroup1_pidlist_destroy_all(struct cgroup *cgrp)
 {
 	struct cgroup_pidlist *l, *tmp_l;
+	LIST_HEAD(orphan);
+
+	/*
+	 * Move pidlists to a local orphan list and mark them as owner-less.
+	 * The destroy work function will see ->owner == NULL and skip freeing.
+	 * We then cancel and free them outside pidlist_mutex to avoid
+	 * flush_workqueue() blocking on the shared workqueue.
+	 */
 
 	mutex_lock(&cgrp->pidlist_mutex);
-	list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
-		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+	list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) {
+		list_del(&l->links);
+		WRITE_ONCE(l->owner, NULL);
+		list_add(&l->links, &orphan);
+	}
 	mutex_unlock(&cgrp->pidlist_mutex);
 
-	flush_workqueue(cgroup_pidlist_destroy_wq);
+	list_for_each_entry_safe(l, tmp_l, &orphan, links) {
+		list_del(&l->links);
+		cancel_delayed_work_sync(&l->destroy_dwork);
+		kvfree(l->list);
+		put_pid_ns(l->key.ns);
+		kfree(l);
+	}
+
 	BUG_ON(!list_empty(&cgrp->pidlists));
 }
 
@@ -222,21 +240,26 @@ static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
 	struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
 						destroy_dwork);
 	struct cgroup_pidlist *tofree = NULL;
+	struct cgroup *owner;
 
-	mutex_lock(&l->owner->pidlist_mutex);
+	owner = READ_ONCE(l->owner);
+	if (owner) {
+		mutex_lock(&owner->pidlist_mutex);
 
-	/*
-	 * Destroy iff we didn't get queued again.  The state won't change
-	 * as destroy_dwork can only be queued while locked.
-	 */
-	if (!delayed_work_pending(dwork)) {
-		list_del(&l->links);
-		kvfree(l->list);
-		put_pid_ns(l->key.ns);
-		tofree = l;
-	}
+		/*
+		 * Destroy iff we didn't get queued again and we're still
+		 * owned by the cgroup.  If ->owner was cleared by
+		 * cgroup1_pidlist_destroy_all(), it will free us.
+		 */
+		if (READ_ONCE(l->owner) == owner && !delayed_work_pending(dwork)) {
+			list_del(&l->links);
+			kvfree(l->list);
+			put_pid_ns(l->key.ns);
+			tofree = l;
+		}
 
-	mutex_unlock(&l->owner->pidlist_mutex);
+		mutex_unlock(&owner->pidlist_mutex);
+	}
 	kfree(tofree);
 }
 
-- 
2.43.0