IPoIB: Don't start send-only joins while multicast thread is stopped

Fix the following race scenario:
  - Device is up.
  - Port event or set mcast list triggers ipoib_mcast_stop_thread,
    this cancels the query and waits on mcast "done" completion.
  - Completion is called and "done" is set.
  - Meanwhile, ipoib_mcast_send arrives and starts a new query,
    re-initializing "done".

Fix this by adding a "multicast started" bit and checking it before
starting a send-only join.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

2 files changed, 16 insertions, 0 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index e0a5412b7e68..2f85a9a831b1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -78,6 +78,7 @@ enum {
         IPOIB_FLAG_SUBINTERFACE   = 4,
         IPOIB_MCAST_RUN           = 5,
         IPOIB_STOP_REAPER         = 6,
+        IPOIB_MCAST_STARTED       = 7,
 
         IPOIB_MAX_BACKOFF_SECONDS = 16,
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index ccaa0c387076..1c7148208ce8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -601,6 +601,10 @@ int ipoib_mcast_start_thread(struct net_device *dev)
                 queue_work(ipoib_workqueue, &priv->mcast_task);
         mutex_unlock(&mcast_mutex);
 
+        spin_lock_irq(&priv->lock);
+        set_bit(IPOIB_MCAST_STARTED, &priv->flags);
+        spin_unlock_irq(&priv->lock);
+
         return 0;
 }
 
@@ -611,6 +615,10 @@ int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
 
         ipoib_dbg_mcast(priv, "stopping multicast thread\n");
 
+        spin_lock_irq(&priv->lock);
+        clear_bit(IPOIB_MCAST_STARTED, &priv->flags);
+        spin_unlock_irq(&priv->lock);
+
         mutex_lock(&mcast_mutex);
         clear_bit(IPOIB_MCAST_RUN, &priv->flags);
         cancel_delayed_work(&priv->mcast_task);
@@ -693,6 +701,12 @@ void ipoib_mcast_send(struct net_device *dev, union ib_gid *mgid,
          */
         spin_lock(&priv->lock);
 
+        if (!test_bit(IPOIB_MCAST_STARTED, &priv->flags)) {
+                ++priv->stats.tx_dropped;
+                dev_kfree_skb_any(skb);
+                goto unlock;
+        }
+
         mcast = __ipoib_mcast_find(dev, mgid);
         if (!mcast) {
                 /* Let's create a new send only group now */
@@ -754,6 +768,7 @@ out:
                 ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
         }
 
+unlock:
         spin_unlock(&priv->lock);
 }