Commit a77a57a1 authored by Roland Dreier's avatar Roland Dreier

IPoIB: Fix deadlock on RTNL in ipoib_stop()

Commit c8c2afe3 ("IPoIB: Use rtnl lock/unlock when changing device
flags") added a call to rtnl_lock() in ipoib_mcast_join_task(), which
is run from the ipoib_workqueue.  However, ipoib_stop() (which is run
inside rtnl_lock()) flushes this workqueue, which leads to a deadlock
if the join task is pending.

Fix this by simply not flushing the workqueue from ipoib_stop().  It
turns out that we really don't care about workqueue tasks running
during or after ipoib_stop(), as long as we make sure to flush the
workqueue before unregistering a netdev.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=1114>.
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
parent ffaa5b98
...@@ -156,14 +156,8 @@ static int ipoib_stop(struct net_device *dev) ...@@ -156,14 +156,8 @@ static int ipoib_stop(struct net_device *dev)
netif_stop_queue(dev); netif_stop_queue(dev);
/* ipoib_ib_dev_down(dev, 0);
* Now flush workqueue to make sure a scheduled task doesn't ipoib_ib_dev_stop(dev, 0);
* bring our internal state back up.
*/
flush_workqueue(ipoib_workqueue);
ipoib_ib_dev_down(dev, 1);
ipoib_ib_dev_stop(dev, 1);
if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
struct ipoib_dev_priv *cpriv; struct ipoib_dev_priv *cpriv;
...@@ -1314,7 +1308,7 @@ sysfs_failed: ...@@ -1314,7 +1308,7 @@ sysfs_failed:
register_failed: register_failed:
ib_unregister_event_handler(&priv->event_handler); ib_unregister_event_handler(&priv->event_handler);
flush_scheduled_work(); flush_workqueue(ipoib_workqueue);
event_failed: event_failed:
ipoib_dev_cleanup(priv->dev); ipoib_dev_cleanup(priv->dev);
...@@ -1373,7 +1367,12 @@ static void ipoib_remove_one(struct ib_device *device) ...@@ -1373,7 +1367,12 @@ static void ipoib_remove_one(struct ib_device *device)
list_for_each_entry_safe(priv, tmp, dev_list, list) { list_for_each_entry_safe(priv, tmp, dev_list, list) {
ib_unregister_event_handler(&priv->event_handler); ib_unregister_event_handler(&priv->event_handler);
flush_scheduled_work();
rtnl_lock();
dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
rtnl_unlock();
flush_workqueue(ipoib_workqueue);
unregister_netdev(priv->dev); unregister_netdev(priv->dev);
ipoib_dev_cleanup(priv->dev); ipoib_dev_cleanup(priv->dev);
......
...@@ -392,8 +392,16 @@ static int ipoib_mcast_join_complete(int status, ...@@ -392,8 +392,16 @@ static int ipoib_mcast_join_complete(int status,
&priv->mcast_task, 0); &priv->mcast_task, 0);
mutex_unlock(&mcast_mutex); mutex_unlock(&mcast_mutex);
if (mcast == priv->broadcast) 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); netif_carrier_on(dev);
rtnl_unlock();
}
return 0; return 0;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment