IB/ipoib: Add missing locking when CM object is deleted

Commit b63b70d87741 ("IPoIB: Use a private hash table for path lookup
in xmit path") introduced a bug where in ipoib_cm_destroy_tx() a CM
object is moved between lists without any supported locking.  Under a
stress test, this eventually leads to list corruption and a crash.

Previously when this routine was called, callers were taking the
device priv lock.  Currently this function is called from the RCU
callback associated with neighbour deletion.  Fix the race by taking
the same lock we used to before.

Signed-off-by: Shlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 95ecf4e..24683fd 100644 (file)
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1271,12 +1271,15 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path
 void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 {
        struct ipoib_dev_priv *priv = netdev_priv(tx->dev);
+       unsigned long flags;
        if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
+               spin_lock_irqsave(&priv->lock, flags);
                list_move(&tx->list, &priv->cm.reap_list);
                queue_work(ipoib_workqueue, &priv->cm.reap_task);
                ipoib_dbg(priv, "Reap connection for gid %pI6\n",
                          tx->neigh->daddr + 4);
                tx->neigh = NULL;
+               spin_unlock_irqrestore(&priv->lock, flags);
        }
 }