5 files changed, 108 insertions, 59 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 2c13123bfd69..962fbcb57dc7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -766,12 +766,14 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	skb_orphan(skb);
 	skb_dst_drop(skb);
 
-	if (netif_queue_stopped(dev))
-		if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP |
-				     IB_CQ_REPORT_MISSED_EVENTS)) {
+	if (netif_queue_stopped(dev)) {
+		rc = ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP |
+				      IB_CQ_REPORT_MISSED_EVENTS);
+		if (unlikely(rc < 0))
 			ipoib_warn(priv, "IPoIB/CM:request notify on send CQ failed\n");
+		else if (rc)
 			napi_schedule(&priv->send_napi);
-		}
+	}
 
 	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req);
 	if (unlikely(rc)) {
@@ -876,7 +878,7 @@ int ipoib_cm_dev_open(struct net_device *dev)
 
 	priv->cm.id = ib_create_cm_id(priv->ca, ipoib_cm_rx_handler, dev);
 	if (IS_ERR(priv->cm.id)) {
-		printk(KERN_WARNING "%s: failed to create CM ID\n", priv->ca->name);
+		pr_warn("%s: failed to create CM ID\n", priv->ca->name);
 		ret = PTR_ERR(priv->cm.id);
 		goto err_cm;
 	}
@@ -884,8 +886,8 @@ int ipoib_cm_dev_open(struct net_device *dev)
 	ret = ib_cm_listen(priv->cm.id, cpu_to_be64(IPOIB_CM_IETF_ID | priv->qp->qp_num),
 			   0);
 	if (ret) {
-		printk(KERN_WARNING "%s: failed to listen on ID 0x%llx\n", priv->ca->name,
-		       IPOIB_CM_IETF_ID | priv->qp->qp_num);
+		pr_warn("%s: failed to listen on ID 0x%llx\n", priv->ca->name,
+			IPOIB_CM_IETF_ID | priv->qp->qp_num);
 		goto err_listen;
 	}
 
@@ -1456,8 +1458,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	int e = skb_queue_empty(&priv->cm.skb_queue);
 
-	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
@@ -1563,7 +1564,7 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge)
 	priv->cm.srq = ib_create_srq(priv->pd, &srq_init_attr);
 	if (IS_ERR(priv->cm.srq)) {
 		if (PTR_ERR(priv->cm.srq) != -ENOSYS)
-			printk(KERN_WARNING "%s: failed to allocate SRQ, error %ld\n",
+			pr_warn("%s: failed to allocate SRQ, error %ld\n",
 			       priv->ca->name, PTR_ERR(priv->cm.srq));
 		priv->cm.srq = NULL;
 		return;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 3b96cdaf9a83..10384ea50bed 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -644,7 +644,7 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 
 	if (netif_queue_stopped(dev))
 		if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP |
-				     IB_CQ_REPORT_MISSED_EVENTS))
+				     IB_CQ_REPORT_MISSED_EVENTS) < 0)
 			ipoib_warn(priv, "request notify on send CQ failed\n");
 
 	rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
@@ -1085,8 +1085,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 
 	netif_addr_unlock_bh(priv->dev);
 
-	err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
-			  priv->dev, &port, &index);
+	err = ib_find_gid(priv->ca, &search_gid, priv->dev, &port, &index);
 
 	netif_addr_lock_bh(priv->dev);
 
@@ -1236,13 +1235,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
-		rtnl_lock();
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
 
-		result = ipoib_ib_dev_open(dev);
-		rtnl_unlock();
-		if (result)
+		if (ipoib_ib_dev_open(dev))
 			return;
 
 		if (netif_queue_stopped(dev))
@@ -1282,7 +1278,9 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
+	rtnl_lock();
 	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
+	rtnl_unlock();
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 12b7f911f0e5..5930c7d9a8fb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -768,13 +768,30 @@ static void path_rec_completion(int status,
 	if (!status) {
 		struct rdma_ah_attr av;
 
-		if (!ib_init_ah_from_path(priv->ca, priv->port, pathrec, &av))
+		if (!ib_init_ah_attr_from_path(priv->ca, priv->port,
+					       pathrec, &av))
 			ah = ipoib_create_ah(dev, priv->pd, &av);
 	}
 
 	spin_lock_irqsave(&priv->lock, flags);
 
 	if (!IS_ERR_OR_NULL(ah)) {
+		/*
+		 * pathrec.dgid is used as the database key from the LLADDR,
+		 * it must remain unchanged even if the SA returns a different
+		 * GID to use in the AH.
+		 */
+		if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw,
+			   sizeof(union ib_gid))) {
+			ipoib_dbg(
+				priv,
+				"%s got PathRec for gid %pI6 while asked for %pI6\n",
+				dev->name, pathrec->dgid.raw,
+				path->pathrec.dgid.raw);
+			memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw,
+			       sizeof(union ib_gid));
+		}
+
 		path->pathrec = *pathrec;
 
 		old_ah   = path->ah;
@@ -840,6 +857,23 @@ static void path_rec_completion(int status,
 	}
 }
 
+static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path,
+			  void *gid)
+{
+	path->dev = priv->dev;
+
+	if (rdma_cap_opa_ah(priv->ca, priv->port))
+		path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA;
+	else
+		path->pathrec.rec_type = SA_PATH_REC_TYPE_IB;
+
+	memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid));
+	path->pathrec.sgid	    = priv->local_gid;
+	path->pathrec.pkey	    = cpu_to_be16(priv->pkey);
+	path->pathrec.numb_path     = 1;
+	path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class;
+}
+
 static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -852,21 +886,11 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid)
 	if (!path)
 		return NULL;
 
-	path->dev = dev;
-
 	skb_queue_head_init(&path->queue);
 
 	INIT_LIST_HEAD(&path->neigh_list);
 
-	if (rdma_cap_opa_ah(priv->ca, priv->port))
-		path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA;
-	else
-		path->pathrec.rec_type = SA_PATH_REC_TYPE_IB;
-	memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid));
-	path->pathrec.sgid	    = priv->local_gid;
-	path->pathrec.pkey	    = cpu_to_be16(priv->pkey);
-	path->pathrec.numb_path     = 1;
-	path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class;
+	init_path_rec(priv, path, gid);
 
 	return path;
 }
@@ -902,8 +926,8 @@ static int path_rec_start(struct net_device *dev,
 	return 0;
 }
 
-static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
-			   struct net_device *dev)
+static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr,
+					  struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	struct rdma_netdev *rn = netdev_priv(dev);
@@ -917,7 +941,15 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 		spin_unlock_irqrestore(&priv->lock, flags);
 		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
-		return;
+		return NULL;
+	}
+
+	/* To avoid race condition, make sure that the
+	 * neigh will be added only once.
+	 */
+	if (unlikely(!list_empty(&neigh->list))) {
+		spin_unlock_irqrestore(&priv->lock, flags);
+		return neigh;
 	}
 
 	path = __path_find(dev, daddr + 4);
@@ -956,7 +988,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 			path->ah->last_send = rn->send(dev, skb, path->ah->ah,
 						       IPOIB_QPN(daddr));
 			ipoib_neigh_put(neigh);
-			return;
+			return NULL;
 		}
 	} else {
 		neigh->ah  = NULL;
@@ -973,7 +1005,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 	ipoib_neigh_put(neigh);
-	return;
+	return NULL;
 
 err_path:
 	ipoib_neigh_free(neigh);
@@ -983,6 +1015,8 @@ err_drop:
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 	ipoib_neigh_put(neigh);
+
+	return NULL;
 }
 
 static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
@@ -995,6 +1029,10 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
+	/* no broadcast means that all paths are (going to be) not valid */
+	if (!priv->broadcast)
+		goto drop_and_unlock;
+
 	path = __path_find(dev, phdr->hwaddr + 4);
 	if (!path || !path->valid) {
 		int new_path = 0;
@@ -1004,6 +1042,10 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			new_path = 1;
 		}
 		if (path) {
+			if (!new_path)
+				/* make sure there is no changes in the existing path record */
+				init_path_rec(priv, path, phdr->hwaddr + 4);
+
 			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
 				push_pseudo_header(skb, phdr->hwaddr);
 				__skb_queue_tail(&path->queue, skb);
@@ -1020,8 +1062,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			} else
 				__path_add(dev, path);
 		} else {
-			++dev->stats.tx_dropped;
-			dev_kfree_skb_any(skb);
+			goto drop_and_unlock;
 		}
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1041,11 +1082,16 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 		push_pseudo_header(skb, phdr->hwaddr);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
-		++dev->stats.tx_dropped;
-		dev_kfree_skb_any(skb);
+		goto drop_and_unlock;
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
+	return;
+
+drop_and_unlock:
+	++dev->stats.tx_dropped;
+	dev_kfree_skb_any(skb);
+	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
 static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -1091,8 +1137,9 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_TIPC):
 		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (unlikely(!neigh)) {
-			neigh_add_path(skb, phdr->hwaddr, dev);
-			return NETDEV_TX_OK;
+			neigh = neigh_add_path(skb, phdr->hwaddr, dev);
+			if (likely(!neigh))
+				return NETDEV_TX_OK;
 		}
 		break;
 	case htons(ETH_P_ARP):
@@ -1663,8 +1710,8 @@ static int ipoib_dev_init_default(struct net_device *dev)
 
 	priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
 	if (!priv->tx_ring) {
-		printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n",
-		       priv->ca->name, ipoib_sendq_size);
+		pr_warn("%s: failed to allocate TX ring (%d entries)\n",
+			priv->ca->name, ipoib_sendq_size);
 		goto out_rx_ring_cleanup;
 	}
 
@@ -2196,16 +2243,17 @@ static struct net_device *ipoib_add_port(const char *format,
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(hca, port, format);
-	if (!priv)
+	if (!priv) {
+		pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port);
 		goto alloc_mem_failed;
+	}
 
 	SET_NETDEV_DEV(priv->dev, hca->dev.parent);
 	priv->dev->dev_id = port - 1;
 
 	result = ib_query_port(hca, port, &attr);
 	if (result) {
-		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
-		       hca->name, port);
+		pr_warn("%s: ib_query_port %d failed\n", hca->name, port);
 		goto device_init_failed;
 	}
 
@@ -2220,8 +2268,8 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	result = ib_query_pkey(hca, port, 0, &priv->pkey);
 	if (result) {
-		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
-		       hca->name, port, result);
+		pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n",
+			hca->name, port, result);
 		goto device_init_failed;
 	}
 
@@ -2238,8 +2286,8 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	result = ib_query_gid(hca, port, 0, &priv->local_gid, NULL);
 	if (result) {
-		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
-		       hca->name, port, result);
+		pr_warn("%s: ib_query_gid port %d failed (ret = %d)\n",
+			hca->name, port, result);
 		goto device_init_failed;
 	}
 
@@ -2249,8 +2297,8 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	result = ipoib_dev_init(priv->dev, hca, port);
 	if (result) {
-		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
-		       hca->name, port, result);
+		pr_warn("%s: failed to initialize port %d (ret = %d)\n",
+			hca->name, port, result);
 		goto device_init_failed;
 	}
 
@@ -2260,8 +2308,8 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	result = register_netdev(priv->dev);
 	if (result) {
-		printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n",
-		       hca->name, port, result);
+		pr_warn("%s: couldn't register ipoib port %d; error %d\n",
+			hca->name, port, result);
 		goto register_failed;
 	}
 
@@ -2326,8 +2374,7 @@ static void ipoib_add_one(struct ib_device *device)
 	}
 
 	if (!count) {
-		pr_err("Failed to init port, removing it\n");
-		ipoib_remove_one(device, dev_list);
+		kfree(dev_list);
 		return;
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 93e149efc1f5..9b3f47ae2016 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -816,7 +816,10 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 		spin_lock_irqsave(&priv->lock, flags);
 		if (!neigh) {
 			neigh = ipoib_neigh_alloc(daddr, dev);
-			if (neigh) {
+			/* Make sure that the neigh will be added only
+			 * once to mcast list.
+			 */
+			if (neigh && list_empty(&neigh->list)) {
 				kref_get(&mcast->ah->ref);
 				neigh->ah	= mcast->ah;
 				list_add_tail(&neigh->list, &mcast->neigh_list);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index a1ed25422b72..984a88096f39 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -178,7 +178,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_rx_completion, NULL,
 				     priv, &cq_attr);
 	if (IS_ERR(priv->recv_cq)) {
-		printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name);
+		pr_warn("%s: failed to create receive CQ\n", ca->name);
 		goto out_cm_dev_cleanup;
 	}
 
@@ -187,7 +187,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->send_cq = ib_create_cq(priv->ca, ipoib_ib_tx_completion, NULL,
 				     priv, &cq_attr);
 	if (IS_ERR(priv->send_cq)) {
-		printk(KERN_WARNING "%s: failed to create send CQ\n", ca->name);
+		pr_warn("%s: failed to create send CQ\n", ca->name);
 		goto out_free_recv_cq;
 	}
 
@@ -208,7 +208,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 
 	priv->qp = ib_create_qp(priv->pd, &init_attr);
 	if (IS_ERR(priv->qp)) {
-		printk(KERN_WARNING "%s: failed to create QP\n", ca->name);
+		pr_warn("%s: failed to create QP\n", ca->name);
 		goto out_free_send_cq;
 	}