diff options
| author | Roland Dreier <rolandd@cisco.com> | 2008-08-19 15:01:32 -0700 |
|---|---|---|
| committer | Roland Dreier <rolandd@cisco.com> | 2008-08-19 15:01:32 -0700 |
| commit | a77a57a1a22afc31891d95879fe3cf2ab03838b0 (patch) | |
| tree | 14f0b4a4e50f4e112d3189c75357e34829d78704 /drivers | |
| parent | ffaa5b984a9322bbd5d9a7f0814ca2ce70feebe5 (diff) | |
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: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 19 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 10 |
2 files changed, 18 insertions, 11 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index f51201b17bf..7e9e218738f 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -156,14 +156,8 @@ static int ipoib_stop(struct net_device *dev) netif_stop_queue(dev); - /* - * Now flush workqueue to make sure a scheduled task doesn't - * bring our internal state back up. - */ - flush_workqueue(ipoib_workqueue); - - ipoib_ib_dev_down(dev, 1); - ipoib_ib_dev_stop(dev, 1); + ipoib_ib_dev_down(dev, 0); + ipoib_ib_dev_stop(dev, 0); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; @@ -1314,7 +1308,7 @@ sysfs_failed: register_failed: ib_unregister_event_handler(&priv->event_handler); - flush_scheduled_work(); + flush_workqueue(ipoib_workqueue); event_failed: ipoib_dev_cleanup(priv->dev); @@ -1373,7 +1367,12 @@ static void ipoib_remove_one(struct ib_device *device) list_for_each_entry_safe(priv, tmp, dev_list, list) { 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); ipoib_dev_cleanup(priv->dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 8950e9546f4..ac33c8f3ea8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -392,8 +392,16 @@ static int ipoib_mcast_join_complete(int status, &priv->mcast_task, 0); 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); + rtnl_unlock(); + } return 0; } |