[PATCH 1/2] workqueue: skip lockdep wq dependency in cancel_work_sync()

From: Johannes Berg
Date: Tue Aug 21 2018 - 08:38:50 EST


From: Johannes Berg <johannes.berg@xxxxxxxxx>

In cancel_work_sync(), we can only have one of two cases, even
with an ordered workqueue:
* the work isn't running, just cancelled before it started
* the work is running, but then nothing else can be on the
workqueue before it

Thus, we need to skip the lockdep workqueue dependency handling,
otherwise we get false positive reports from lockdep saying that
we have a potential deadlock when the workqueue also has other
work items with locking, e.g.

work1_function() { mutex_lock(&mutex); ... }
work2_function() { /* nothing */ }

other_function() {
queue_work(ordered_wq, &work1);
queue_work(ordered_wq, &work2);
mutex_lock(&mutex);
cancel_work_sync(&work2);
}

As described above, this isn't a problem, but lockdep will
currently flag it as if cancel_work_sync() was flush_work(),
which *is* a problem.

Signed-off-by: Johannes Berg <johannes.berg@xxxxxxxxx>
---
kernel/workqueue.c | 37 ++++++++++++++++++++++---------------
1 file changed, 22 insertions(+), 15 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 78b192071ef7..a6c2b823f348 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2843,7 +2843,8 @@ void drain_workqueue(struct workqueue_struct *wq)
}
EXPORT_SYMBOL_GPL(drain_workqueue);

-static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+ bool from_cancel)
{
struct worker *worker = NULL;
struct worker_pool *pool;
@@ -2885,7 +2886,8 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
* workqueues the deadlock happens when the rescuer stalls, blocking
* forward progress.
*/
- if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) {
+ if (!from_cancel &&
+ (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) {
lock_map_acquire(&pwq->wq->lockdep_map);
lock_map_release(&pwq->wq->lockdep_map);
}
@@ -2896,6 +2898,22 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
return false;
}

+static bool __flush_work(struct work_struct *work, bool from_cancel)
+{
+ struct wq_barrier barr;
+
+ if (WARN_ON(!wq_online))
+ return false;
+
+ if (start_flush_work(work, &barr, from_cancel)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else {
+ return false;
+ }
+}
+
/**
* flush_work - wait for a work to finish executing the last queueing instance
* @work: the work to flush
@@ -2909,18 +2927,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
*/
bool flush_work(struct work_struct *work)
{
- struct wq_barrier barr;
-
- if (WARN_ON(!wq_online))
- return false;
-
- if (start_flush_work(work, &barr)) {
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- return true;
- } else {
- return false;
- }
+ return __flush_work(work, false);
}
EXPORT_SYMBOL_GPL(flush_work);

@@ -2986,7 +2993,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
* isn't executing.
*/
if (wq_online)
- flush_work(work);
+ __flush_work(work, true);

clear_work_data(work);

--
2.14.4