IB/ipoib: Make the carrier_on_task race aware

We blindly assume that we can just take the rtnl lock and that will
prevent races with downing this interface.  Unfortunately, that's not
the case.  In ipoib_mcast_stop_thread() we will call flush_workqueue()
in an attempt to clear out all remaining instances of ipoib_join_task.
But, since this task is put on the same workqueue as the join task,
the flush_workqueue waits on this thread too.  But this thread is
deadlocked on the rtnl lock.  The better thing here is to use trylock
and loop on that until we either get the lock or we see that
FLAG_OPER_UP has been cleared, in which case we don't need to do
anything anyway and we just return.

While investigating which flag should be used, FLAG_ADMIN_UP or
FLAG_OPER_UP, it was determined that FLAG_OPER_UP was the more
appropriate flag to use.  However, there was a mix of these two flags in
use in the existing code.  So while we check for that flag here as part
of this race fix, also cleanup the two places that had used the less
appropriate flag for their tests.

Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index eee66d13e5b9acf9a6c700777a7082f7bbdc8e7e..c63a598d0b41d6edd1a4025a3691d70c1d0acc4c 100644 (file)
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -353,18 +353,27 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work)
                                                   carrier_on_task);
        struct ib_port_attr attr;
 
-       /*
-        * Take rtnl_lock to avoid racing with ipoib_stop() and
-        * turning the carrier back on while a device is being
-        * removed.
-        */
        if (ib_query_port(priv->ca, priv->port, &attr) ||
            attr.state != IB_PORT_ACTIVE) {
                ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
                return;
        }
 
-       rtnl_lock();
+       /*
+        * Take rtnl_lock to avoid racing with ipoib_stop() and
+        * turning the carrier back on while a device is being
+        * removed.  However, ipoib_stop() will attempt to flush
+        * the workqueue while holding the rtnl lock, so loop
+        * on trylock until either we get the lock or we see
+        * FLAG_OPER_UP go away as that signals that we are bailing
+        * and can safely ignore the carrier on work.
+        */
+       while (!rtnl_trylock()) {
+               if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+                       return;
+               else
+                       msleep(20);
+       }
        if (!ipoib_cm_admin_enabled(priv->dev))
                dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu));
        netif_carrier_on(priv->dev);
@@ -535,7 +544,7 @@ void ipoib_mcast_join_task(struct work_struct *work)
        if (!priv->broadcast) {
                struct ipoib_mcast *broadcast;
 
-               if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+               if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
                        return;
 
                broadcast = ipoib_mcast_alloc(dev, 1);
@@ -882,7 +891,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
                ipoib_mcast_free(mcast);
        }
 
-       if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+       if (test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
                ipoib_mcast_start_thread(dev);
 }