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>
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index b0ffc9a..05eb41b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -293,6 +293,7 @@
struct delayed_work pkey_poll_task;
struct delayed_work mcast_task;
+ struct work_struct carrier_on_task;
struct work_struct flush_light;
struct work_struct flush_normal;
struct work_struct flush_heavy;
@@ -464,6 +465,7 @@
void ipoib_dev_cleanup(struct net_device *dev);
void ipoib_mcast_join_task(struct work_struct *work);
+void ipoib_mcast_carrier_on_task(struct work_struct *work);
void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb);
void ipoib_mcast_restart_task(struct work_struct *work);