drbd: add drbd_queue_work_if_unqueued helper

We sometimes do
    if (list_empty(&w.list))
	drbd_queue_work(&q, &w.list);

Removal (list_del_init) may happen outside all locks, after all
pending work entries have been moved to an on-stack local work list.

For not dynamically allocated, but embeded, work structs,
we must avoid to re-add until it really was removed.

Move that list_empty check inside the spin_lock(&q->q_lock)
within the helper function, and change to list_empty_careful().

This may have been the reason for a list_add corruption
inside drbd_queue_work().

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

2 files changed, 15 insertions, 4 deletions

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c88d6c6be70b..a71f8bb9dc80 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1778,6 +1778,17 @@ drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w)
 }
 
 static inline void
+drbd_queue_work_if_unqueued(struct drbd_work_queue *q, struct drbd_work *w)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&q->q_lock, flags);
+        if (list_empty_careful(&w->list))
+                list_add_tail(&w->list, &q->q);
+        spin_unlock_irqrestore(&q->q_lock, flags);
+        wake_up(&q->q_wait);
+}
+
+static inline void
 drbd_device_post_work(struct drbd_device *device, int work_bit)
 {
         if (!test_and_set_bit(work_bit, &device->flags)) {
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 9f0acb011f30..49b88731b349 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -452,9 +452,9 @@ void resync_timer_fn(unsigned long data)
 {
         struct drbd_device *device = (struct drbd_device *) data;
 
-        if (list_empty(&device->resync_work.list))
-                drbd_queue_work(&first_peer_device(device)->connection->sender_work,
-                                &device->resync_work);
+        drbd_queue_work_if_unqueued(
+                &first_peer_device(device)->connection->sender_work,
+                &device->resync_work);
 }
 
 static void fifo_set(struct fifo_buffer *fb, int value)
@@ -1968,7 +1968,7 @@ static void do_unqueued_work(struct drbd_connection *connection)
 static bool dequeue_work_batch(struct drbd_work_queue *queue, struct list_head *work_list)
 {
         spin_lock_irq(&queue->q_lock);
-        list_splice_init(&queue->q, work_list);
+        list_splice_tail_init(&queue->q, work_list);
         spin_unlock_irq(&queue->q_lock);
         return !list_empty(work_list);
 }