1 files changed, 140 insertions, 40 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2d8d8fcfa060..8d39071f32d7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -299,7 +299,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops)
 	if (rtnl_link_ops_get(ops->kind))
 		return -EEXIST;
 
-	if (!ops->dellink)
+	/* The check for setup is here because if ops
+	 * does not have that filled up, it is not possible
+	 * to use the ops for creating device. So do not
+	 * fill up dellink as well. That disables rtnl_dellink.
+	 */
+	if (ops->setup && !ops->dellink)
 		ops->dellink = unregister_netdevice_queue;
 
 	list_add_tail(&ops->list, &link_ops);
@@ -798,8 +803,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 		size += num_vfs *
 			(nla_total_size(sizeof(struct ifla_vf_mac)) +
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
-			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_rate)));
 		return size;
 	} else
 		return 0;
@@ -1065,6 +1070,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_info ivi;
 			struct ifla_vf_mac vf_mac;
 			struct ifla_vf_vlan vf_vlan;
+			struct ifla_vf_rate vf_rate;
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
@@ -1085,6 +1091,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				break;
 			vf_mac.vf =
 				vf_vlan.vf =
+				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
 				vf_linkstate.vf = ivi.vf;
@@ -1092,7 +1099,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
 			vf_vlan.qos = ivi.qos;
-			vf_tx_rate.rate = ivi.tx_rate;
+			vf_tx_rate.rate = ivi.max_tx_rate;
+			vf_rate.min_tx_rate = ivi.min_tx_rate;
+			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
@@ -1102,6 +1111,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			}
 			if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
 			    nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+			    nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
+				    &vf_rate) ||
 			    nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
 				    &vf_tx_rate) ||
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
@@ -1208,6 +1219,10 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 				    .len = sizeof(struct ifla_vf_tx_rate) },
 	[IFLA_VF_SPOOFCHK]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_link_state) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1234,6 +1249,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
@@ -1241,8 +1257,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1367,11 +1392,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 		}
 		case IFLA_VF_TX_RATE: {
 			struct ifla_vf_tx_rate *ivt;
+			struct ifla_vf_info ivf;
+			ivt = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_get_vf_config)
+				err = ops->ndo_get_vf_config(dev, ivt->vf,
+							     &ivf);
+			if (err)
+				break;
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivf.min_tx_rate,
+							   ivt->rate);
+			break;
+		}
+		case IFLA_VF_RATE: {
+			struct ifla_vf_rate *ivt;
 			ivt = nla_data(vf);
 			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivt->min_tx_rate,
+							   ivt->max_tx_rate);
 			break;
 		}
 		case IFLA_VF_SPOOFCHK: {
@@ -1739,12 +1782,11 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -ENODEV;
 
 	ops = dev->rtnl_link_ops;
-	if (!ops)
+	if (!ops || !ops->dellink)
 		return -EOPNOTSUPP;
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -1768,7 +1810,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 EXPORT_SYMBOL(rtnl_configure_link);
 
 struct net_device *rtnl_create_link(struct net *net,
-	char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[])
+	char *ifname, unsigned char name_assign_type,
+	const struct rtnl_link_ops *ops, struct nlattr *tb[])
 {
 	int err;
 	struct net_device *dev;
@@ -1786,8 +1829,8 @@ struct net_device *rtnl_create_link(struct net *net,
 		num_rx_queues = ops->get_num_rx_queues();
 
 	err = -ENOMEM;
-	dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup,
-			       num_tx_queues, num_rx_queues);
+	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
+			       ops->setup, num_tx_queues, num_rx_queues);
 	if (!dev)
 		goto err;
 
@@ -1852,6 +1895,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	char ifname[IFNAMSIZ];
 	struct nlattr *tb[IFLA_MAX+1];
 	struct nlattr *linkinfo[IFLA_INFO_MAX+1];
+	unsigned char name_assign_type = NET_NAME_USER;
 	int err;
 
 #ifdef CONFIG_MODULES
@@ -2001,14 +2045,19 @@ replay:
 			return -EOPNOTSUPP;
 		}
 
-		if (!ifname[0])
+		if (!ops->setup)
+			return -EOPNOTSUPP;
+
+		if (!ifname[0]) {
 			snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
+			name_assign_type = NET_NAME_ENUM;
+		}
 
 		dest_net = rtnl_link_get_net(net, tb);
 		if (IS_ERR(dest_net))
 			return PTR_ERR(dest_net);
 
-		dev = rtnl_create_link(dest_net, ifname, ops, tb);
+		dev = rtnl_create_link(dest_net, ifname, name_assign_type, ops, tb);
 		if (IS_ERR(dev)) {
 			err = PTR_ERR(dev);
 			goto out;
@@ -2019,11 +2068,15 @@ replay:
 		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
 			/* Drivers should call free_netdev() in ->destructor
-			 * and unregister it on failure so that device could be
-			 * finally freed in rtnl_unlock.
+			 * and unregister it on failure after registration
+			 * so that device could be finally freed in rtnl_unlock.
 			 */
-			if (err < 0)
+			if (err < 0) {
+				/* If device is not registered at all, free it now */
+				if (dev->reg_state == NETREG_UNINITIALIZED)
+					free_netdev(dev);
 				goto out;
+			}
 		} else {
 			err = register_netdevice(dev);
 			if (err < 0) {
@@ -2095,9 +2148,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -2335,22 +2392,20 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 		     struct net_device *dev,
 		     const unsigned char *addr)
 {
-	int err = -EOPNOTSUPP;
+	int err = -EINVAL;
 
 	/* If aging addresses are supported device will need to
 	 * implement its own handler for this.
 	 */
 	if (!(ndm->ndm_state & NUD_PERMANENT)) {
 		pr_info("%s: FDB only supports static addresses\n", dev->name);
-		return -EINVAL;
+		return err;
 	}
 
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
 		err = dev_uc_del(dev, addr);
 	else if (is_multicast_ether_addr(addr))
 		err = dev_mc_del(dev, addr);
-	else
-		err = -EINVAL;
 
 	return err;
 }
@@ -2464,6 +2519,7 @@ skip:
 int ndo_dflt_fdb_dump(struct sk_buff *skb,
 		      struct netlink_callback *cb,
 		      struct net_device *dev,
+		      struct net_device *filter_dev,
 		      int idx)
 {
 	int err;
@@ -2481,28 +2537,72 @@ EXPORT_SYMBOL(ndo_dflt_fdb_dump);
 
 static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	int idx = 0;
-	struct net *net = sock_net(skb->sk);
 	struct net_device *dev;
+	struct nlattr *tb[IFLA_MAX+1];
+	struct net_device *bdev = NULL;
+	struct net_device *br_dev = NULL;
+	const struct net_device_ops *ops = NULL;
+	const struct net_device_ops *cops = NULL;
+	struct ifinfomsg *ifm = nlmsg_data(cb->nlh);
+	struct net *net = sock_net(skb->sk);
+	int brport_idx = 0;
+	int br_idx = 0;
+	int idx = 0;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->priv_flags & IFF_BRIDGE_PORT) {
-			struct net_device *br_dev;
-			const struct net_device_ops *ops;
+	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
+			ifla_policy) == 0) {
+		if (tb[IFLA_MASTER])
+			br_idx = nla_get_u32(tb[IFLA_MASTER]);
+	}
+
+	brport_idx = ifm->ifi_index;
+
+	if (br_idx) {
+		br_dev = __dev_get_by_index(net, br_idx);
+		if (!br_dev)
+			return -ENODEV;
+
+		ops = br_dev->netdev_ops;
+		bdev = br_dev;
+	}
+
+	for_each_netdev(net, dev) {
+		if (brport_idx && (dev->ifindex != brport_idx))
+			continue;
 
-			br_dev = netdev_master_upper_dev_get(dev);
-			ops = br_dev->netdev_ops;
-			if (ops->ndo_fdb_dump)
-				idx = ops->ndo_fdb_dump(skb, cb, dev, idx);
+		if (!br_idx) { /* user did not specify a specific bridge */
+			if (dev->priv_flags & IFF_BRIDGE_PORT) {
+				br_dev = netdev_master_upper_dev_get(dev);
+				cops = br_dev->netdev_ops;
+			}
+
+			bdev = dev;
+		} else {
+			if (dev != br_dev &&
+			    !(dev->priv_flags & IFF_BRIDGE_PORT))
+				continue;
+
+			if (br_dev != netdev_master_upper_dev_get(dev) &&
+			    !(dev->priv_flags & IFF_EBRIDGE))
+				continue;
+
+			bdev = br_dev;
+			cops = ops;
 		}
 
+		if (dev->priv_flags & IFF_BRIDGE_PORT) {
+			if (cops && cops->ndo_fdb_dump)
+				idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev,
+							 idx);
+		}
+
+		idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
 		if (dev->netdev_ops->ndo_fdb_dump)
-			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
-		else
-			idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
+			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, bdev, dev,
+							    idx);
+
+		cops = NULL;
 	}
-	rcu_read_unlock();
 
 	cb->args[0] = idx;
 	return skb->len;