rbd: eliminate a race in lock_dwork draining on unmap

Given how rbd_lock_add_request() and rbd_img_exclusive_lock() are
written, lock_dwork may be (re)queued more than it's actually needed:
for example in case a new I/O request comes in while we are in the
middle of rbd_acquire_lock() on behalf of another I/O request.  This is
expected and with rbd_release_lock() preemptively canceling lock_dwork
is benign under normal operation.

A more problematic example is maybe_kick_acquire():

    if (have_requests || delayed_work_pending(&rbd_dev->lock_dwork)) {
            dout("%s rbd_dev %p kicking lock_dwork\n", __func__, rbd_dev);
            mod_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork, 0);
    }

It's not unrealistic for lock_dwork to get canceled right after
delayed_work_pending() returns true and for mod_delayed_work() to
requeue it right there anyway.  This is a classic TOCTOU race.

When it comes to unmapping the image, there is an implicit assumption
of no self-initiated exclusive lock activity past the point of return
from rbd_dev_image_unlock() which unlocks the lock if it happens to be
held.  This unlock is assumed to be final and lock_dwork (as well as
all other exclusive lock tasks, really) isn't expected to get queued
again.  However, lock_dwork is canceled only in cancel_tasks_sync()
(i.e. later in the unmap sequence) and on top of that the cancellation
can get in effect nullified by maybe_kick_acquire().  This may result
in rbd_acquire_lock() executing after rbd_dev_device_release() and
rbd_dev_image_release() run and free and/or reset a bunch of things.
One of the possible failure modes then is a violated

    rbd_assert(rbd_image_format_valid(rbd_dev->image_format));

in rbd_dev_header_info() which is called via rbd_dev_refresh() from
rbd_post_acquire_action().

Redo exclusive lock task draining to provide saner semantics and try
to meet the assumptions around rbd_dev_image_unlock().

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4065336ebd1f1ac95b2f6311e686fb80b0680ed5..6c1e7347e6a72ef1566cd89b371040b74e7fb805 100644 (file)
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4565,24 +4565,12 @@ out:
        return ret;
 }
 
        return ret;
 }
 

-static void cancel_tasks_sync(struct rbd_device *rbd_dev)
-{
-       dout("%s rbd_dev %p\n", __func__, rbd_dev);
-
-       cancel_work_sync(&rbd_dev->acquired_lock_work);
-       cancel_work_sync(&rbd_dev->released_lock_work);
-       cancel_delayed_work_sync(&rbd_dev->lock_dwork);
-       cancel_work_sync(&rbd_dev->unlock_work);
-}
-

 /*
  * header_rwsem must not be held to avoid a deadlock with
  * rbd_dev_refresh() when flushing notifies.
  */
 static void rbd_unregister_watch(struct rbd_device *rbd_dev)
 {
 /*
  * header_rwsem must not be held to avoid a deadlock with
  * rbd_dev_refresh() when flushing notifies.
  */
 static void rbd_unregister_watch(struct rbd_device *rbd_dev)
 {

-       cancel_tasks_sync(rbd_dev);
-

        mutex_lock(&rbd_dev->watch_mutex);
        if (rbd_dev->watch_state == RBD_WATCH_STATE_REGISTERED)
                __rbd_unregister_watch(rbd_dev);
        mutex_lock(&rbd_dev->watch_mutex);
        if (rbd_dev->watch_state == RBD_WATCH_STATE_REGISTERED)
                __rbd_unregister_watch(rbd_dev);


@@ -6548,10 +6536,18 @@ out_err:
 
 static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
 {
 
 static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
 {

+       dout("%s rbd_dev %p\n", __func__, rbd_dev);
+
+       disable_delayed_work_sync(&rbd_dev->lock_dwork);
+       disable_work_sync(&rbd_dev->unlock_work);
+

        down_write(&rbd_dev->lock_rwsem);
        if (__rbd_is_lock_owner(rbd_dev))
                __rbd_release_lock(rbd_dev);
        up_write(&rbd_dev->lock_rwsem);
        down_write(&rbd_dev->lock_rwsem);
        if (__rbd_is_lock_owner(rbd_dev))
                __rbd_release_lock(rbd_dev);
        up_write(&rbd_dev->lock_rwsem);

+
+       flush_work(&rbd_dev->acquired_lock_work);
+       flush_work(&rbd_dev->released_lock_work);

 }
 
 /*
 }
 
 /*