[[RFC]PATCH] psi: fix race between psi_trigger_create and psimon

[Huangzhaoyang]

From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>

Race detected between psimon_new and psimon_old as shown below, which
cause panic by accessing invalid psi_system->poll_wait->wait_queue_entry
and psi_system->poll_timer->entry->next. It is not necessary to reinit
resource of psi_system when psi_trigger_create.

psi_trigger_create      psimon_new     psimon_old
 init_waitqueue_head                    finish_wait
                                          spin_lock(lock_old)
	spin_lock_init(lock_new)
 wake_up_process(psimon_new)

                        finish_wait
                          spin_lock(lock_new)
                            list_del       list_del

Signed-off-by: ziwei.dai <ziwei.dai@xxxxxxxxxx>
Signed-off-by: ke.wang <ke.wang@xxxxxxxxxx>
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
---
 kernel/sched/psi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index cc25a3c..d00e585 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -182,6 +182,8 @@ struct psi_group psi_system = {
 
 static void psi_avgs_work(struct work_struct *work);
 
+static void poll_timer_fn(struct timer_list *t);
+
 static void group_init(struct psi_group *group)
 {
 	int cpu;
@@ -201,6 +203,8 @@ static void group_init(struct psi_group *group)
 	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
 	group->polling_until = 0;
+	init_waitqueue_head(&group->poll_wait);
+	timer_setup(&group->poll_timer, poll_timer_fn, 0);
 	rcu_assign_pointer(group->poll_task, NULL);
 }
 
@@ -1157,7 +1161,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 			return ERR_CAST(task);
 		}
 		atomic_set(&group->poll_wakeup, 0);
-		init_waitqueue_head(&group->poll_wait);
 		wake_up_process(task);
 		timer_setup(&group->poll_timer, poll_timer_fn, 0);
 		rcu_assign_pointer(group->poll_task, task);
@@ -1233,7 +1236,6 @@ static void psi_trigger_destroy(struct kref *ref)
 		 * But it might have been already scheduled before
 		 * that - deschedule it cleanly before destroying it.
 		 */
-		del_timer_sync(&group->poll_timer);
 		kthread_stop(task_to_destroy);
 	}
 	kfree(t);
-- 
1.9.1