5 files changed, 93 insertions, 59 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 2f85a9a831b..b640107fb73 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -72,13 +72,14 @@ enum {
 	IPOIB_MAX_MCAST_QUEUE     = 3,
 
 	IPOIB_FLAG_OPER_UP 	  = 0,
-	IPOIB_FLAG_ADMIN_UP 	  = 1,
-	IPOIB_PKEY_ASSIGNED 	  = 2,
-	IPOIB_PKEY_STOP 	  = 3,
-	IPOIB_FLAG_SUBINTERFACE   = 4,
-	IPOIB_MCAST_RUN 	  = 5,
-	IPOIB_STOP_REAPER         = 6,
-	IPOIB_MCAST_STARTED       = 7,
+	IPOIB_FLAG_INITIALIZED    = 1,
+	IPOIB_FLAG_ADMIN_UP 	  = 2,
+	IPOIB_PKEY_ASSIGNED 	  = 3,
+	IPOIB_PKEY_STOP 	  = 4,
+	IPOIB_FLAG_SUBINTERFACE   = 5,
+	IPOIB_MCAST_RUN 	  = 6,
+	IPOIB_STOP_REAPER         = 7,
+	IPOIB_MCAST_STARTED       = 8,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
@@ -217,10 +218,16 @@ struct ipoib_neigh {
 	struct list_head    list;
 };
 
+/*
+ * We stash a pointer to our private neighbour information after our
+ * hardware address in neigh->ha.  The ALIGN() expression here makes
+ * sure that this pointer is stored aligned so that an unaligned
+ * load is not needed to dereference it.
+ */
 static inline struct ipoib_neigh **to_ipoib_neigh(struct neighbour *neigh)
 {
-	return (struct ipoib_neigh **) (neigh->ha + 24 -
-					(offsetof(struct neighbour, ha) & 4));
+	return (void*) neigh + ALIGN(offsetof(struct neighbour, ha) +
+				     INFINIBAND_ALEN, sizeof(void *));
 }
 
 extern struct workqueue_struct *ipoib_workqueue;
@@ -253,7 +260,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev);
 
 int ipoib_ib_dev_open(struct net_device *dev);
 int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev);
+int ipoib_ib_dev_down(struct net_device *dev, int flush);
 int ipoib_ib_dev_stop(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 86bcdd72a10..ed65202878d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -416,25 +416,46 @@ int ipoib_ib_dev_open(struct net_device *dev)
 	ret = ipoib_ib_post_receives(dev);
 	if (ret) {
 		ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret);
+		ipoib_ib_dev_stop(dev);
 		return -1;
 	}
 
 	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
 	queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, HZ);
 
+	set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+
 	return 0;
 }
 
+static void ipoib_pkey_dev_check_presence(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	u16 pkey_index = 0;
+
+	if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
+		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+	else
+		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+}
+
 int ipoib_ib_dev_up(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	ipoib_pkey_dev_check_presence(dev);
+
+	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
+		ipoib_dbg(priv, "PKEY is not assigned.\n");
+		return 0;
+	}
+
 	set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 
 	return ipoib_mcast_start_thread(dev);
 }
 
-int ipoib_ib_dev_down(struct net_device *dev)
+int ipoib_ib_dev_down(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -449,10 +470,11 @@ int ipoib_ib_dev_down(struct net_device *dev)
 		set_bit(IPOIB_PKEY_STOP, &priv->flags);
 		cancel_delayed_work(&priv->pkey_task);
 		mutex_unlock(&pkey_mutex);
-		flush_workqueue(ipoib_workqueue);
+		if (flush)
+			flush_workqueue(ipoib_workqueue);
 	}
 
-	ipoib_mcast_stop_thread(dev, 1);
+	ipoib_mcast_stop_thread(dev, flush);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_flush_paths(dev);
@@ -481,6 +503,8 @@ int ipoib_ib_dev_stop(struct net_device *dev)
 	struct ipoib_tx_buf *tx_req;
 	int i;
 
+	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+
 	/*
 	 * Move our QP to the error state and then reinitialize in
 	 * when all work requests have completed or have been flushed.
@@ -585,12 +609,19 @@ void ipoib_ib_dev_flush(void *_dev)
 	struct net_device *dev = (struct net_device *)_dev;
 	struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv;
 
-	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) ) {
+		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
 		return;
+	}
+
+	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
+		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
+		return;
+	}
 
 	ipoib_dbg(priv, "flushing\n");
 
-	ipoib_ib_dev_down(dev);
+	ipoib_ib_dev_down(dev, 0);
 
 	/*
 	 * The device could have been brought down between the start and when
@@ -603,7 +634,7 @@ void ipoib_ib_dev_flush(void *_dev)
 
 	/* Flush any child interfaces too */
 	list_for_each_entry(cpriv, &priv->child_intfs, list)
-		ipoib_ib_dev_flush(&cpriv->dev);
+		ipoib_ib_dev_flush(cpriv->dev);
 
 	mutex_unlock(&priv->vlan_mutex);
 }
@@ -630,17 +661,6 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
  * change async notification is available.
  */
 
-static void ipoib_pkey_dev_check_presence(struct net_device *dev)
-{
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	u16 pkey_index = 0;
-
-	if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
-		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-	else
-		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-}
-
 void ipoib_pkey_poll(void *dev_ptr)
 {
 	struct net_device *dev = dev_ptr;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index c3b5f79d116..9b0bd7c746c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -133,7 +133,13 @@ static int ipoib_stop(struct net_device *dev)
 
 	netif_stop_queue(dev);
 
-	ipoib_ib_dev_down(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);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
@@ -247,7 +253,6 @@ static void path_free(struct net_device *dev, struct ipoib_path *path)
 		if (neigh->ah)
 			ipoib_put_ah(neigh->ah);
 		*to_ipoib_neigh(neigh->neighbour) = NULL;
-		neigh->neighbour->ops->destructor = NULL;
 		kfree(neigh);
 	}
 
@@ -513,12 +518,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 			   be32_to_cpup((__be32 *) skb->dst->neighbour->ha));
 	} else {
 		neigh->ah  = NULL;
-		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
-			__skb_queue_tail(&neigh->queue, skb);
-		} else {
-			++priv->stats.tx_dropped;
-			dev_kfree_skb_any(skb);
-		}
+		__skb_queue_tail(&neigh->queue, skb);
 
 		if (!path->query && path_rec_start(dev, path))
 			goto err;
@@ -530,7 +530,6 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 err:
 	*to_ipoib_neigh(skb->dst->neighbour) = NULL;
 	list_del(&neigh->list);
-	neigh->neighbour->ops->destructor = NULL;
 	kfree(neigh);
 
 	++priv->stats.tx_dropped;
@@ -724,7 +723,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
 	 * destination address onto the front of the skb so we can
 	 * figure out where to send the packet later.
 	 */
-	if (!skb->dst || !skb->dst->neighbour) {
+	if ((!skb->dst || !skb->dst->neighbour) && daddr) {
 		struct ipoib_pseudoheader *phdr =
 			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
 		memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
@@ -737,6 +736,11 @@ static void ipoib_set_mcast_list(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
+		ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set");
+		return;
+	}
+
 	queue_work(ipoib_workqueue, &priv->restart_task);
 }
 
@@ -769,21 +773,9 @@ static void ipoib_neigh_destructor(struct neighbour *n)
 		ipoib_put_ah(ah);
 }
 
-static int ipoib_neigh_setup(struct neighbour *neigh)
-{
-	/*
-	 * Is this kosher?  I can't find anybody in the kernel that
-	 * sets neigh->destructor, so we should be able to set it here
-	 * without trouble.
-	 */
-	neigh->ops->destructor = ipoib_neigh_destructor;
-
-	return 0;
-}
-
 static int ipoib_neigh_setup_dev(struct net_device *dev, struct neigh_parms *parms)
 {
-	parms->neigh_setup = ipoib_neigh_setup;
+	parms->neigh_destructor = ipoib_neigh_destructor;
 
 	return 0;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index a2408d7ec59..93c462eaf4f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -115,7 +115,6 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 		if (neigh->ah)
 			ipoib_put_ah(neigh->ah);
 		*to_ipoib_neigh(neigh->neighbour) = NULL;
-		neigh->neighbour->ops->destructor = NULL;
 		kfree(neigh);
 	}
 
@@ -213,6 +212,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 {
 	struct net_device *dev = mcast->dev;
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct ipoib_ah *ah;
 	int ret;
 
 	mcast->mcmember = *mcmember;
@@ -269,8 +269,8 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 				av.static_rate, priv->local_rate,
 				ib_sa_rate_enum_to_int(mcast->mcmember.rate));
 
-		mcast->ah = ipoib_create_ah(dev, priv->pd, &av);
-		if (!mcast->ah) {
+		ah = ipoib_create_ah(dev, priv->pd, &av);
+		if (!ah) {
 			ipoib_warn(priv, "ib_address_create failed\n");
 		} else {
 			ipoib_dbg_mcast(priv, "MGID " IPOIB_GID_FMT
@@ -280,6 +280,10 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 					be16_to_cpu(mcast->mcmember.mlid),
 					mcast->mcmember.sl);
 		}
+
+		spin_lock_irq(&priv->lock);
+		mcast->ah = ah;
+		spin_unlock_irq(&priv->lock);
 	}
 
 	/* actually send any queued packets */
@@ -432,9 +436,11 @@ static void ipoib_mcast_join_complete(int status,
 	if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
 		mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
 
+	mutex_lock(&mcast_mutex);
+
+	spin_lock_irq(&priv->lock);
 	mcast->query = NULL;
 
-	mutex_lock(&mcast_mutex);
 	if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) {
 		if (status == -ETIMEDOUT)
 			queue_work(ipoib_workqueue, &priv->mcast_task);
@@ -443,6 +449,7 @@ static void ipoib_mcast_join_complete(int status,
 					   mcast->backoff * HZ);
 	} else
 		complete(&mcast->done);
+	spin_unlock_irq(&priv->lock);
 	mutex_unlock(&mcast_mutex);
 
 	return;
@@ -630,21 +637,27 @@ int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
 	if (flush)
 		flush_workqueue(ipoib_workqueue);
 
+	spin_lock_irq(&priv->lock);
 	if (priv->broadcast && priv->broadcast->query) {
 		ib_sa_cancel_query(priv->broadcast->query_id, priv->broadcast->query);
 		priv->broadcast->query = NULL;
+		spin_unlock_irq(&priv->lock);
 		ipoib_dbg_mcast(priv, "waiting for bcast\n");
 		wait_for_completion(&priv->broadcast->done);
-	}
+	} else
+		spin_unlock_irq(&priv->lock);
 
 	list_for_each_entry(mcast, &priv->multicast_list, list) {
+		spin_lock_irq(&priv->lock);
 		if (mcast->query) {
 			ib_sa_cancel_query(mcast->query_id, mcast->query);
 			mcast->query = NULL;
+			spin_unlock_irq(&priv->lock);
 			ipoib_dbg_mcast(priv, "waiting for MGID " IPOIB_GID_FMT "\n",
 					IPOIB_GID_ARG(mcast->mcmember.mgid));
 			wait_for_completion(&mcast->done);
-		}
+		} else
+			spin_unlock_irq(&priv->lock);
 	}
 
 	return 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index faaf10e5fc7..5f0388027b2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -251,10 +251,12 @@ void ipoib_event(struct ib_event_handler *handler,
 	struct ipoib_dev_priv *priv =
 		container_of(handler, struct ipoib_dev_priv, event_handler);
 
-	if (record->event == IB_EVENT_PORT_ACTIVE ||
+	if (record->event == IB_EVENT_PORT_ERR    ||
+	    record->event == IB_EVENT_PKEY_CHANGE ||
+	    record->event == IB_EVENT_PORT_ACTIVE ||
 	    record->event == IB_EVENT_LID_CHANGE  ||
 	    record->event == IB_EVENT_SM_CHANGE) {
-		ipoib_dbg(priv, "Port active event\n");
-		schedule_work(&priv->flush_task);
+		ipoib_dbg(priv, "Port state change event\n");
+		queue_work(ipoib_workqueue, &priv->flush_task);
 	}
 }