summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
diff options
context:
space:
mode:
authorYossi Etigin <yossi.openib@gmail.com>2008-09-16 11:57:45 -0700
committerRoland Dreier <rolandd@cisco.com>2008-09-16 11:57:45 -0700
commite8224e4b804b4fd26723191c1891101a5959bb8a (patch)
tree94aa1274989fca8154bd3912d5f73239e705e7a3 /drivers/infiniband/ulp/ipoib/ipoib_multicast.c
parent1941246dd98089dd637f44d3bd4f6cc1c61aa9e4 (diff)
IPoIB: Fix deadlock on RTNL between bcast join comp and ipoib_stop()
Taking rtnl_lock in ipoib_mcast_join_complete() causes a deadlock with ipoib_stop(). We avoid it by scheduling the piece of code that takes the lock on ipoib_workqueue instead of executing it directly. This works because we only flush the ipoib_workqueue with the RTNL not held. The deadlock happens because ipoib_stop() calls ipoib_ib_dev_down() which calls ipoib_mcast_dev_flush(), which calls ipoib_mcast_free(), which calls ipoib_mcast_leave(). The latter calls ib_sa_free_multicast(), and this waits until the multicast completion handler finishes. This handler is ipoib_mcast_join_complete(), which waits for the rtnl_lock(), which was already taken by ipoib_stop(). This bug was introduced in commit a77a57a1 ("IPoIB: Fix deadlock on RTNL in ipoib_stop()"). Signed-off-by: Yossi Etigin <yosefe@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'drivers/infiniband/ulp/ipoib/ipoib_multicast.c')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c31
1 files changed, 21 insertions, 10 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index ac33c8f3ea8..aae28620a6e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -366,6 +366,21 @@ static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast)
return ret;
}
+void ipoib_mcast_carrier_on_task(struct work_struct *work)
+{
+ struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
+ carrier_on_task);
+
+ /*
+ * Take rtnl_lock to avoid racing with ipoib_stop() and
+ * turning the carrier back on while a device is being
+ * removed.
+ */
+ rtnl_lock();
+ netif_carrier_on(priv->dev);
+ rtnl_unlock();
+}
+
static int ipoib_mcast_join_complete(int status,
struct ib_sa_multicast *multicast)
{
@@ -392,16 +407,12 @@ static int ipoib_mcast_join_complete(int status,
&priv->mcast_task, 0);
mutex_unlock(&mcast_mutex);
- if (mcast == priv->broadcast) {
- /*
- * Take RTNL lock here to avoid racing with
- * ipoib_stop() and turning the carrier back
- * on while a device is being removed.
- */
- rtnl_lock();
- netif_carrier_on(dev);
- rtnl_unlock();
- }
+ /*
+ * Defer carrier on work to ipoib_workqueue to avoid a
+ * deadlock on rtnl_lock here.
+ */
+ if (mcast == priv->broadcast)
+ queue_work(ipoib_workqueue, &priv->carrier_on_task);
return 0;
}