This fixes bug #1114 in bugzilla, which is a deadlock between ipoib_stop
and mcast_join_task.
ipoib_stop is called with rtnl_lock, and flushes ipoib_workqueue.
the flush operation might wait for mcast_join_task to finish, which
in turn might wait for rtnl_lock.
Signed-off-by: Yossi Etigin <[EMAIL PROTECTED]>
--
Index: b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
===================================================================
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2008-08-04
18:09:33.000000000 +0300
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2008-08-04
18:39:08.000000000 +0300
@@ -504,6 +504,7 @@
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, mcast_join_task.work);
struct net_device *dev = priv->dev;
+ int ret;
if (!test_bit(IPOIB_MCAST_RUN, &priv->flags))
return;
@@ -577,9 +578,16 @@
priv->mcast_mtu =
IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
if (!ipoib_cm_admin_enabled(dev)) {
- rtnl_lock();
- dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
- rtnl_unlock();
+ /* Avoid deadlock with ipoib_stop */
+ while (!(ret = rtnl_trylock()) &&
+ test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+ yield();
+
+ if (ret) {
+ dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
+ rtnl_unlock();
+ } else
+ ipoib_dbg_mcast(priv, "ignoring mtu setup because device is
down\n");
}
ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n");
--
--Yossi
_______________________________________________
ewg mailing list
ewg@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
