@@ -3457,6 +3457,7 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req)
lockdep_assert_held(&rbd_dev->lock_rwsem);
spin_lock(&rbd_dev->lock_lists_lock);
if (!list_empty(&img_req->lock_item)) {
+ rbd_assert(!list_empty(&rbd_dev->running_list));
list_del_init(&img_req->lock_item);
need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING &&
list_empty(&rbd_dev->running_list));
@@ -3476,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
if (rbd_lock_add_request(img_req))
return 1;
- if (rbd_dev->opts->exclusive) {
- WARN_ON(1); /* lock got released? */
- return -EROFS;
- }
-
/*
* Note the use of mod_delayed_work() in rbd_acquire_lock()
* and cancel_delayed_work() in wake_lock_waiters().
@@ -4601,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
rbd_warn(rbd_dev, "failed to update lock cookie: %d",
ret);
+ if (rbd_dev->opts->exclusive)
+ rbd_warn(rbd_dev,
+ "temporarily releasing lock on exclusive mapping");
+
/*
* Lock cookie cannot be updated on older OSDs, so do
* a manual release and queue an acquire.
Every time a watch is reestablished after getting lost, we need to update the cookie which involves quiescing exclusive lock. For this, we transition from RBD_LOCK_STATE_LOCKED to RBD_LOCK_STATE_QUIESCING roughly for the duration of rbd_reacquire_lock() call. If the mapping is exclusive and I/O happens to arrive in this time window, it's failed with EROFS (later translated to EIO) based on the wrong assumption in rbd_img_exclusive_lock() -- "lock got released?" check there stopped making sense with commit a2b1da09793d ("rbd: lock should be quiesced on reacquire"). To make it worse, any such I/O is added to the acquiring list before EROFS is returned and this sets up for violating rbd_lock_del_request() precondition that the request is either on the running list or not on any list at all -- see commit ded080c86b3f ("rbd: don't move requests to the running list on errors"). rbd_lock_del_request() ends up processing these requests as if they were on the running list which screws up quiescing_wait completion counter and ultimately leads to rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); being triggered on the next watch error. Signed-off-by: Ilya Dryomov <idryomov@gmail.com> --- drivers/block/rbd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)