Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

8 files changed, 317 insertions, 77 deletions

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 3ae2bfd31015..fe10a949aef9 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -177,7 +177,7 @@ int __init ibnl_init(void)
 		.input	= ibnl_rcv,
 	};
 
-	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg);
+	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
 	if (!nls) {
 		pr_warn("Failed to create netlink socket\n");
 		return -ENOMEM;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 45aedf1d9338..5213bab2d19b 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1155,7 +1155,7 @@ static int ring_kernel_db(struct c4iw_qp *qhp, u32 qid, u16 inc)
 		 */
 		if (cxgb4_dbfifo_count(qhp->rhp->rdev.lldi.ports[0], 1) <
 		    (qhp->rhp->rdev.lldi.dbfifo_int_thresh << 5)) {
-			writel(V_QID(qid) | V_PIDX(inc), qhp->wq.db);
+			writel(QID(qid) | PIDX(inc), qhp->wq.db);
 			break;
 		}
 		set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/drivers/infiniband/ulp/ipoib/Makefile b/drivers/infiniband/ulp/ipoib/Makefile
index 3090100f0de7..e5430dd50764 100644
--- a/drivers/infiniband/ulp/ipoib/Makefile
+++ b/drivers/infiniband/ulp/ipoib/Makefile
@@ -5,7 +5,8 @@ ib_ipoib-y					:= ipoib_main.o \
 						   ipoib_multicast.o \
 						   ipoib_verbs.o \
 						   ipoib_vlan.o \
-						   ipoib_ethtool.o
+						   ipoib_ethtool.o \
+						   ipoib_netlink.o
 ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_CM)		+= ipoib_cm.o
 ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_DEBUG)	+= ipoib_fs.o
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 0af216d21f87..196eb52f0035 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -104,6 +104,10 @@ enum {
 
 	MAX_SEND_CQE		  = 16,
 	IPOIB_CM_COPYBREAK	  = 256,
+
+	IPOIB_NON_CHILD		  = 0,
+	IPOIB_LEGACY_CHILD	  = 1,
+	IPOIB_RTNL_CHILD	  = 2,
 };
 
 #define	IPOIB_OP_RECV   (1ul << 31)
@@ -353,6 +357,7 @@ struct ipoib_dev_priv {
 	struct net_device *parent;
 	struct list_head child_intfs;
 	struct list_head list;
+	int    child_type;
 
 #ifdef CONFIG_INFINIBAND_IPOIB_CM
 	struct ipoib_cm_dev_priv cm;
@@ -512,6 +517,17 @@ void ipoib_event(struct ib_event_handler *handler,
 int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey);
 int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey);
 
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+		     u16 pkey, int child_type);
+
+int  __init ipoib_netlink_init(void);
+void __exit ipoib_netlink_fini(void);
+
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val);
+int  ipoib_set_mode(struct net_device *dev, const char *buf);
+
+void ipoib_setup(struct net_device *dev);
+
 void ipoib_pkey_poll(struct work_struct *work);
 int ipoib_pkey_dev_delay_open(struct net_device *dev);
 void ipoib_drain_cq(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 24683fda8e21..175581cf478c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1448,15 +1448,10 @@ static ssize_t show_mode(struct device *d, struct device_attribute *attr,
 		return sprintf(buf, "datagram\n");
 }
 
-static ssize_t set_mode(struct device *d, struct device_attribute *attr,
-			const char *buf, size_t count)
+int ipoib_set_mode(struct net_device *dev, const char *buf)
 {
-	struct net_device *dev = to_net_dev(d);
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-
 	/* flush paths if we switch modes so that connections are restarted */
 	if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) {
 		set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
@@ -1467,7 +1462,8 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
 
 		ipoib_flush_paths(dev);
-		return count;
+		rtnl_lock();
+		return 0;
 	}
 
 	if (!strcmp(buf, "datagram\n")) {
@@ -1476,14 +1472,32 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 		dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
 		rtnl_unlock();
 		ipoib_flush_paths(dev);
-
-		return count;
+		rtnl_lock();
+		return 0;
 	}
-	rtnl_unlock();
 
 	return -EINVAL;
 }
 
+static ssize_t set_mode(struct device *d, struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	struct net_device *dev = to_net_dev(d);
+	int ret;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = ipoib_set_mode(dev, buf);
+
+	rtnl_unlock();
+
+	if (!ret)
+		return count;
+
+	return ret;
+}
+
 static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode);
 
 int ipoib_cm_add_mode_attr(struct net_device *dev)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 1e19b5ae7c47..3f9a9ba2f9ec 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -173,6 +173,11 @@ static int ipoib_stop(struct net_device *dev)
 	return 0;
 }
 
+static void ipoib_uninit(struct net_device *dev)
+{
+	ipoib_dev_cleanup(dev);
+}
+
 static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -1257,6 +1262,9 @@ out:
 void ipoib_dev_cleanup(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv;
+	LIST_HEAD(head);
+
+	ASSERT_RTNL();
 
 	ipoib_delete_debug_files(dev);
 
@@ -1265,10 +1273,9 @@ void ipoib_dev_cleanup(struct net_device *dev)
 		/* Stop GC on child */
 		set_bit(IPOIB_STOP_NEIGH_GC, &cpriv->flags);
 		cancel_delayed_work(&cpriv->neigh_reap_task);
-		unregister_netdev(cpriv->dev);
-		ipoib_dev_cleanup(cpriv->dev);
-		free_netdev(cpriv->dev);
+		unregister_netdevice_queue(cpriv->dev, &head);
 	}
+	unregister_netdevice_many(&head);
 
 	ipoib_ib_dev_cleanup(dev);
 
@@ -1286,6 +1293,7 @@ static const struct header_ops ipoib_header_ops = {
 };
 
 static const struct net_device_ops ipoib_netdev_ops = {
+	.ndo_uninit		 = ipoib_uninit,
 	.ndo_open		 = ipoib_open,
 	.ndo_stop		 = ipoib_stop,
 	.ndo_change_mtu		 = ipoib_change_mtu,
@@ -1295,7 +1303,7 @@ static const struct net_device_ops ipoib_netdev_ops = {
 	.ndo_set_rx_mode	 = ipoib_set_mcast_list,
 };
 
-static void ipoib_setup(struct net_device *dev)
+void ipoib_setup(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -1373,12 +1381,9 @@ static ssize_t show_umcast(struct device *dev,
 	return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
 }
 
-static ssize_t set_umcast(struct device *dev,
-			  struct device_attribute *attr,
-			  const char *buf, size_t count)
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val)
 {
-	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
-	unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+	struct ipoib_dev_priv *priv = netdev_priv(ndev);
 
 	if (umcast_val > 0) {
 		set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
@@ -1386,6 +1391,15 @@ static ssize_t set_umcast(struct device *dev,
 				"by userspace\n");
 	} else
 		clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+}
+
+static ssize_t set_umcast(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+
+	ipoib_set_umcast(to_net_dev(dev), umcast_val);
 
 	return count;
 }
@@ -1657,7 +1671,6 @@ static void ipoib_remove_one(struct ib_device *device)
 		flush_workqueue(ipoib_workqueue);
 
 		unregister_netdev(priv->dev);
-		ipoib_dev_cleanup(priv->dev);
 		free_netdev(priv->dev);
 	}
 
@@ -1709,8 +1722,15 @@ static int __init ipoib_init_module(void)
 	if (ret)
 		goto err_sa;
 
+	ret = ipoib_netlink_init();
+	if (ret)
+		goto err_client;
+
 	return 0;
 
+err_client:
+	ib_unregister_client(&ipoib_client);
+
 err_sa:
 	ib_sa_unregister_client(&ipoib_sa_client);
 	destroy_workqueue(ipoib_workqueue);
@@ -1723,6 +1743,7 @@ err_fs:
 
 static void __exit ipoib_cleanup_module(void)
 {
+	ipoib_netlink_fini();
 	ib_unregister_client(&ipoib_client);
 	ib_sa_unregister_client(&ipoib_sa_client);
 	ipoib_unregister_debugfs();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
new file mode 100644
index 000000000000..74685936c948
--- /dev/null
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. -  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/module.h>
+#include <net/rtnetlink.h>
+#include "ipoib.h"
+
+static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = {
+	[IFLA_IPOIB_PKEY]	= { .type = NLA_U16 },
+	[IFLA_IPOIB_MODE]	= { .type = NLA_U16 },
+	[IFLA_IPOIB_UMCAST]	= { .type = NLA_U16 },
+};
+
+static int ipoib_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	u16 val;
+
+	if (nla_put_u16(skb, IFLA_IPOIB_PKEY, priv->pkey))
+		goto nla_put_failure;
+
+	val = test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+	if (nla_put_u16(skb, IFLA_IPOIB_MODE, val))
+		goto nla_put_failure;
+
+	val = test_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+	if (nla_put_u16(skb, IFLA_IPOIB_UMCAST, val))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int ipoib_changelink(struct net_device *dev,
+			    struct nlattr *tb[], struct nlattr *data[])
+{
+	u16 mode, umcast;
+	int ret = 0;
+
+	if (data[IFLA_IPOIB_MODE]) {
+		mode  = nla_get_u16(data[IFLA_IPOIB_MODE]);
+		if (mode == IPOIB_MODE_DATAGRAM)
+			ret = ipoib_set_mode(dev, "datagram\n");
+		else if (mode == IPOIB_MODE_CONNECTED)
+			ret = ipoib_set_mode(dev, "connected\n");
+		else
+			ret = -EINVAL;
+
+		if (ret < 0)
+			goto out_err;
+	}
+
+	if (data[IFLA_IPOIB_UMCAST]) {
+		umcast = nla_get_u16(data[IFLA_IPOIB_UMCAST]);
+		ipoib_set_umcast(dev, umcast);
+	}
+
+out_err:
+	return ret;
+}
+
+static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
+			       struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_device *pdev;
+	struct ipoib_dev_priv *ppriv;
+	u16 child_pkey;
+	int err;
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+
+	pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	if (!pdev)
+		return -ENODEV;
+
+	ppriv = netdev_priv(pdev);
+
+	if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) {
+		ipoib_warn(ppriv, "child creation disallowed for child devices\n");
+		return -EINVAL;
+	}
+
+	if (!data || !data[IFLA_IPOIB_PKEY]) {
+		ipoib_dbg(ppriv, "no pkey specified, using parent pkey\n");
+		child_pkey  = ppriv->pkey;
+	} else
+		child_pkey  = nla_get_u16(data[IFLA_IPOIB_PKEY]);
+
+	err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
+
+	if (!err && data)
+		err = ipoib_changelink(dev, tb, data);
+	return err;
+}
+
+static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head *head)
+{
+	struct ipoib_dev_priv *priv, *ppriv;
+
+	priv = netdev_priv(dev);
+	ppriv = netdev_priv(priv->parent);
+
+	mutex_lock(&ppriv->vlan_mutex);
+	unregister_netdevice_queue(dev, head);
+	list_del(&priv->list);
+	mutex_unlock(&ppriv->vlan_mutex);
+}
+
+static size_t ipoib_get_size(const struct net_device *dev)
+{
+	return nla_total_size(2) +	/* IFLA_IPOIB_PKEY   */
+		nla_total_size(2) +	/* IFLA_IPOIB_MODE   */
+		nla_total_size(2);	/* IFLA_IPOIB_UMCAST */
+}
+
+static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
+	.kind		= "ipoib",
+	.maxtype	= IFLA_IPOIB_MAX,
+	.policy		= ipoib_policy,
+	.priv_size	= sizeof(struct ipoib_dev_priv),
+	.setup		= ipoib_setup,
+	.newlink	= ipoib_new_child_link,
+	.changelink	= ipoib_changelink,
+	.dellink	= ipoib_unregister_child_dev,
+	.get_size	= ipoib_get_size,
+	.fill_info	= ipoib_fill_info,
+};
+
+int __init ipoib_netlink_init(void)
+{
+	return rtnl_link_register(&ipoib_link_ops);
+}
+
+void __exit ipoib_netlink_fini(void)
+{
+	rtnl_link_unregister(&ipoib_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("ipoib");
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index d7e9740c7248..8292554bccb5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -49,47 +49,11 @@ static ssize_t show_parent(struct device *d, struct device_attribute *attr,
 }
 static DEVICE_ATTR(parent, S_IRUGO, show_parent, NULL);
 
-int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+		     u16 pkey, int type)
 {
-	struct ipoib_dev_priv *ppriv, *priv;
-	char intf_name[IFNAMSIZ];
 	int result;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	ppriv = netdev_priv(pdev);
-
-	if (!rtnl_trylock())
-		return restart_syscall();
-	mutex_lock(&ppriv->vlan_mutex);
-
-	/*
-	 * First ensure this isn't a duplicate. We check the parent device and
-	 * then all of the child interfaces to make sure the Pkey doesn't match.
-	 */
-	if (ppriv->pkey == pkey) {
-		result = -ENOTUNIQ;
-		priv = NULL;
-		goto err;
-	}
-
-	list_for_each_entry(priv, &ppriv->child_intfs, list) {
-		if (priv->pkey == pkey) {
-			result = -ENOTUNIQ;
-			priv = NULL;
-			goto err;
-		}
-	}
-
-	snprintf(intf_name, sizeof intf_name, "%s.%04x",
-		 ppriv->dev->name, pkey);
-	priv = ipoib_intf_alloc(intf_name);
-	if (!priv) {
-		result = -ENOMEM;
-		goto err;
-	}
-
 	priv->max_ib_mtu = ppriv->max_ib_mtu;
 	/* MTU will be reset when mcast join happens */
 	priv->dev->mtu   = IPOIB_UD_MTU(priv->max_ib_mtu);
@@ -124,24 +88,27 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 	ipoib_create_debug_files(priv->dev);
 
-	if (ipoib_cm_add_mode_attr(priv->dev))
-		goto sysfs_failed;
-	if (ipoib_add_pkey_attr(priv->dev))
-		goto sysfs_failed;
-	if (ipoib_add_umcast_attr(priv->dev))
-		goto sysfs_failed;
-
-	if (device_create_file(&priv->dev->dev, &dev_attr_parent))
-		goto sysfs_failed;
+	/* RTNL childs don't need proprietary sysfs entries */
+	if (type == IPOIB_LEGACY_CHILD) {
+		if (ipoib_cm_add_mode_attr(priv->dev))
+			goto sysfs_failed;
+		if (ipoib_add_pkey_attr(priv->dev))
+			goto sysfs_failed;
+		if (ipoib_add_umcast_attr(priv->dev))
+			goto sysfs_failed;
+
+		if (device_create_file(&priv->dev->dev, &dev_attr_parent))
+			goto sysfs_failed;
+	}
 
+	priv->child_type  = type;
+	priv->dev->iflink = ppriv->dev->ifindex;
 	list_add_tail(&priv->list, &ppriv->child_intfs);
 
-	mutex_unlock(&ppriv->vlan_mutex);
-	rtnl_unlock();
-
 	return 0;
 
 sysfs_failed:
+	result = -ENOMEM;
 	ipoib_delete_debug_files(priv->dev);
 	unregister_netdevice(priv->dev);
 
@@ -149,11 +116,60 @@ register_failed:
 	ipoib_dev_cleanup(priv->dev);
 
 err:
+	return result;
+}
+
+int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+{
+	struct ipoib_dev_priv *ppriv, *priv;
+	char intf_name[IFNAMSIZ];
+	struct ipoib_dev_priv *tpriv;
+	int result;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	ppriv = netdev_priv(pdev);
+
+	snprintf(intf_name, sizeof intf_name, "%s.%04x",
+		 ppriv->dev->name, pkey);
+	priv = ipoib_intf_alloc(intf_name);
+	if (!priv)
+		return -ENOMEM;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	mutex_lock(&ppriv->vlan_mutex);
+
+	/*
+	 * First ensure this isn't a duplicate. We check the parent device and
+	 * then all of the legacy child interfaces to make sure the Pkey
+	 * doesn't match.
+	 */
+	if (ppriv->pkey == pkey) {
+		result = -ENOTUNIQ;
+		goto out;
+	}
+
+	list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
+		if (tpriv->pkey == pkey &&
+		    tpriv->child_type == IPOIB_LEGACY_CHILD) {
+			result = -ENOTUNIQ;
+			goto out;
+		}
+	}
+
+	result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD);
+
+out:
 	mutex_unlock(&ppriv->vlan_mutex);
-	rtnl_unlock();
-	if (priv)
+
+	if (result)
 		free_netdev(priv->dev);
 
+	rtnl_unlock();
+
 	return result;
 }
 
@@ -171,9 +187,9 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 		return restart_syscall();
 	mutex_lock(&ppriv->vlan_mutex);
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
-		if (priv->pkey == pkey) {
+		if (priv->pkey == pkey &&
+		    priv->child_type == IPOIB_LEGACY_CHILD) {
 			unregister_netdevice(priv->dev);
-			ipoib_dev_cleanup(priv->dev);
 			list_del(&priv->list);
 			dev = priv->dev;
 			break;