workqueue: Add a new flag to spot the potential UAF error

Currently if the user queues a new work item unintentionally
into a wq after the destroy_workqueue(wq), the work still can
be queued and scheduled without any noticeable kernel message
before the end of a RCU grace period.

As a debug-aid facility, this commit adds a new flag
__WQ_DESTROYING to spot that issue by triggering a kernel WARN
message.

Signed-off-by: Richard Clark <[email protected]>
Reviewed-by: Lai Jiangshan <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>

Author: richardxnuclark

include/linux/workqueue.h

@@ -335,6 +335,7 @@ enum {
 	 */
 	WQ_POWER_EFFICIENT	= 1 << 7,
 
+	__WQ_DESTROYING		= 1 << 15, /* internal: workqueue is destroying */
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */

kernel/workqueue.c

@@ -1433,9 +1433,13 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	lockdep_assert_irqs_disabled();
 
 
-	/* if draining, only works from the same workqueue are allowed */
-	if (unlikely(wq->flags & __WQ_DRAINING) &&
-	    WARN_ON_ONCE(!is_chained_work(wq)))
+	/*
+	 * For a draining wq, only works from the same workqueue are
+	 * allowed. The __WQ_DESTROYING helps to spot the issue that
+	 * queues a new work item to a wq after destroy_workqueue(wq).
+	 */
+	if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) &&
+		     WARN_ON_ONCE(!is_chained_work(wq))))
 		return;
 	rcu_read_lock();
 retry:
@@ -4414,6 +4418,11 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	 */
 	workqueue_sysfs_unregister(wq);
 
+	/* mark the workqueue destruction is in progress */
+	mutex_lock(&wq->mutex);
+	wq->flags |= __WQ_DESTROYING;
+	mutex_unlock(&wq->mutex);
+
 	/* drain it before proceeding with destruction */
 	drain_workqueue(wq);