[PATCH v4] 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. Under this modification, the
race window is removed by initialising poll_wait and poll_timer in
group_init which are executed only once at beginning.

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

Fixes: 461daba06bdc ("psi: eliminate kthread_worker from psi trigger
scheduling mechanism")

Signed-off-by: ziwei.dai <ziwei.dai@xxxxxxxxxx>
Signed-off-by: ke.wang <ke.wang@xxxxxxxxxx>
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
---
v2: change del_timer_sync to del_timer in psi_trigger_destroy
v3: remove timer_setup within psi_tirgger_create
    protect del_timer by extending the critical section of mutex_lock
v4: amend fix information on comment
---
---
 kernel/sched/psi.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index cc25a3c..7b53217 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);
 }
 
@@ -1157,9 +1161,7 @@ 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);
 	}
 
@@ -1214,16 +1216,8 @@ static void psi_trigger_destroy(struct kref *ref)
 		}
 	}
 
-	mutex_unlock(&group->trigger_lock);
-
-	/*
-	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_task RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_task
-	 */
-	synchronize_rcu();
 	/*
-	 * Destroy the kworker after releasing trigger_lock to prevent a
+	 * Destroy psimon after releasing trigger_lock to prevent a
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
 	if (task_to_destroy) {
@@ -1233,9 +1227,20 @@ 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);
+		del_timer(&group->poll_timer);
+		mutex_unlock(&group->trigger_lock);
 		kthread_stop(task_to_destroy);
+	} else {
+		mutex_unlock(&group->trigger_lock);
 	}
+
+	/*
+	 * Wait for both *trigger_ptr from psi_trigger_replace and
+	 * poll_task RCUs to complete their read-side critical sections
+	 * before destroying the trigger and optionally the poll_task
+	 */
+	synchronize_rcu();
+
 	kfree(t);
 }
 
-- 
1.9.1