IPoIB: Fix crash when path record fails after path flush

Commit ee1e2c82 ("IPoIB: Refresh paths instead of flushing them on SM
change events") changed how paths are flushed on an SM event.  This
change introduces a problem if the path record query triggered by
fails, causing path->ah to become NULL.  A later successful path query
will then trigger WARN_ON() in path_rec_completion(), and crash
because path->ah has already been freed, so the ipoib_put_ah() inside
the lock in path_rec_completion() may actually drop the last reference
(contrary to the comment that claims this is safe).

Fix this by updating path->ah and freeing old_ah only when the path
record query is successful.  This prevents the neighbour AH and that
path AH from getting out of sync.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=1194>

Reported-by: Rabah Salem <ravah@mellanox.com>
Debugged-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 1b1df5c..e9ca3cb 100644 (file)
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -404,7 +404,7 @@ static void path_rec_completion(int status,
        struct net_device *dev = path->dev;
        struct ipoib_dev_priv *priv = netdev_priv(dev);
        struct ipoib_ah *ah = NULL;
-       struct ipoib_ah *old_ah;
+       struct ipoib_ah *old_ah = NULL;
        struct ipoib_neigh *neigh, *tn;
        struct sk_buff_head skqueue;
        struct sk_buff *skb;
@@ -428,12 +428,12 @@ static void path_rec_completion(int status,
 
        spin_lock_irqsave(&priv->lock, flags);
 
-       old_ah   = path->ah;
-       path->ah = ah;
-
        if (ah) {
                path->pathrec = *pathrec;
 
+               old_ah   = path->ah;
+               path->ah = ah;
+
                ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n",
                          ah, be16_to_cpu(pathrec->dlid), pathrec->sl);