3 files changed, 196 insertions, 57 deletions

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 412c3c0b6990..386cbe4d3327 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2379,7 +2379,17 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		else
 			udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 #if IS_ENABLED(CONFIG_IPV6)
-		key.label = vxlan->cfg.label;
+		switch (vxlan->cfg.label_policy) {
+		case VXLAN_LABEL_FIXED:
+			key.label = vxlan->cfg.label;
+			break;
+		case VXLAN_LABEL_INHERIT:
+			key.label = ip_tunnel_get_flowlabel(old_iph, skb);
+			break;
+		default:
+			DEBUG_NET_WARN_ON_ONCE(1);
+			goto drop;
+		}
 #endif
 	} else {
 		if (!info) {
@@ -2845,6 +2855,7 @@ static int vxlan_init(struct net_device *dev)
 	if (err)
 		goto err_gro_cells_destroy;
 
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 err_gro_cells_destroy:
@@ -3225,6 +3236,7 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_fdb_get		= vxlan_fdb_get,
 	.ndo_mdb_add		= vxlan_mdb_add,
 	.ndo_mdb_del		= vxlan_mdb_del,
+	.ndo_mdb_del_bulk	= vxlan_mdb_del_bulk,
 	.ndo_mdb_dump		= vxlan_mdb_dump,
 	.ndo_mdb_get		= vxlan_mdb_get,
 	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
@@ -3242,7 +3254,7 @@ static const struct net_device_ops vxlan_netdev_raw_ops = {
 };
 
 /* Info for udev, that this is a virtual tunnel endpoint */
-static struct device_type vxlan_type = {
+static const struct device_type vxlan_type = {
 	.name = "vxlan",
 };
 
@@ -3366,6 +3378,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_DF]		= { .type = NLA_U8 },
 	[IFLA_VXLAN_VNIFILTER]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_LOCALBYPASS]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[IFLA_VXLAN_LABEL_POLICY]       = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX),
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -3740,6 +3753,12 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf,
 		return -EINVAL;
 	}
 
+	if (conf->label_policy && !use_ipv6) {
+		NL_SET_ERR_MSG(extack,
+			       "Label policy only applies to IPv6 VXLAN devices");
+		return -EINVAL;
+	}
+
 	if (conf->remote_ifindex) {
 		struct net_device *lowerdev;
 
@@ -4082,6 +4101,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_VXLAN_LABEL])
 		conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
 			     IPV6_FLOWLABEL_MASK;
+	if (data[IFLA_VXLAN_LABEL_POLICY])
+		conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]);
 
 	if (data[IFLA_VXLAN_LEARNING]) {
 		err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING,
@@ -4398,6 +4419,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_DF */
 		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
+		nla_total_size(sizeof(__u32)) +  /* IFLA_VXLAN_LABEL_POLICY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
@@ -4471,6 +4493,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
 	    nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
 	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
+	    nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 		       !!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_PROXY,
@@ -4804,55 +4827,43 @@ static __net_init int vxlan_init_net(struct net *net)
 					 NULL);
 }
 
-static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn,
+					     struct list_head *dev_to_kill)
 {
-	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan, *next;
-	struct net_device *dev, *aux;
-
-	for_each_netdev_safe(net, dev, aux)
-		if (dev->rtnl_link_ops == &vxlan_link_ops)
-			unregister_netdevice_queue(dev, head);
-
-	list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) {
-		/* If vxlan->dev is in the same netns, it has already been added
-		 * to the list by the previous loop.
-		 */
-		if (!net_eq(dev_net(vxlan->dev), net))
-			unregister_netdevice_queue(vxlan->dev, head);
-	}
 
+	list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next)
+		vxlan_dellink(vxlan->dev, dev_to_kill);
 }
 
-static void __net_exit vxlan_exit_batch_net(struct list_head *net_list)
+static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list,
+					     struct list_head *dev_to_kill)
 {
 	struct net *net;
-	LIST_HEAD(list);
-	unsigned int h;
 
+	ASSERT_RTNL();
 	list_for_each_entry(net, net_list, exit_list) {
 		struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 
-		unregister_nexthop_notifier(net, &vn->nexthop_notifier_block);
-	}
-	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list)
-		vxlan_destroy_tunnels(net, &list);
+		__unregister_nexthop_notifier(net, &vn->nexthop_notifier_block);
 
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+		vxlan_destroy_tunnels(vn, dev_to_kill);
+	}
+}
 
-	list_for_each_entry(net, net_list, exit_list) {
-		struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+static void __net_exit vxlan_exit_net(struct net *net)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	unsigned int h;
 
-		for (h = 0; h < PORT_HASH_SIZE; ++h)
-			WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h]));
-	}
+	for (h = 0; h < PORT_HASH_SIZE; ++h)
+		WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h]));
 }
 
 static struct pernet_operations vxlan_net_ops = {
 	.init = vxlan_init_net,
-	.exit_batch = vxlan_exit_batch_net,
+	.exit_batch_rtnl = vxlan_exit_batch_rtnl,
+	.exit = vxlan_exit_net,
 	.id   = &vxlan_net_id,
 	.size = sizeof(struct vxlan_net),
 };
diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c
index eb4c580b5cee..60eb95a06d55 100644
--- a/drivers/net/vxlan/vxlan_mdb.c
+++ b/drivers/net/vxlan/vxlan_mdb.c
@@ -74,6 +74,14 @@ struct vxlan_mdb_config {
 	u8 rt_protocol;
 };
 
+struct vxlan_mdb_flush_desc {
+	union vxlan_addr remote_ip;
+	__be32 src_vni;
+	__be32 remote_vni;
+	__be16 remote_port;
+	u8 rt_protocol;
+};
+
 static const struct rhashtable_params vxlan_mdb_rht_params = {
 	.head_offset = offsetof(struct vxlan_mdb_entry, rhnode),
 	.key_offset = offsetof(struct vxlan_mdb_entry, key),
@@ -1306,6 +1314,145 @@ int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+static const struct nla_policy
+vxlan_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
+	[MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY,
+					   sizeof(struct in_addr),
+					   sizeof(struct in6_addr)),
+	[MDBE_ATTR_DST_PORT] = { .type = NLA_U16 },
+	[MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT),
+};
+
+static int vxlan_mdb_flush_desc_init(struct vxlan_dev *vxlan,
+				     struct vxlan_mdb_flush_desc *desc,
+				     struct nlattr *tb[],
+				     struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	if (entry->ifindex && entry->ifindex != vxlan->dev->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid port net device");
+		return -EINVAL;
+	}
+
+	if (entry->vid) {
+		NL_SET_ERR_MSG_MOD(extack, "VID must not be specified");
+		return -EINVAL;
+	}
+
+	if (!tb[MDBA_SET_ENTRY_ATTRS])
+		return 0;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_SET_ENTRY_ATTRS],
+			       vxlan_mdbe_attrs_del_bulk_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) {
+		u8 state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]);
+
+		if ((state_mask & MDB_PERMANENT) && !(entry->state & MDB_PERMANENT)) {
+			NL_SET_ERR_MSG_MOD(extack, "Only permanent MDB entries are supported");
+			return -EINVAL;
+		}
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST])
+		vxlan_nla_get_addr(&desc->remote_ip, mdbe_attrs[MDBE_ATTR_DST]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST_PORT])
+		desc->remote_port =
+			cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT]));
+
+	if (mdbe_attrs[MDBE_ATTR_VNI])
+		desc->remote_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI]));
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_VNI])
+		desc->src_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI]));
+
+	return 0;
+}
+
+static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
+				    struct vxlan_mdb_entry *mdb_entry,
+				    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_remote *remote, *tmp;
+
+	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) {
+		struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+		__be32 remote_vni;
+
+		if (desc->remote_ip.sa.sa_family &&
+		    !vxlan_addr_equal(&desc->remote_ip, &rd->remote_ip))
+			continue;
+
+		/* Encapsulation is performed with source VNI if remote VNI
+		 * is not set.
+		 */
+		remote_vni = rd->remote_vni ? : mdb_entry->key.vni;
+		if (desc->remote_vni && desc->remote_vni != remote_vni)
+			continue;
+
+		if (desc->remote_port && desc->remote_port != rd->remote_port)
+			continue;
+
+		if (desc->rt_protocol &&
+		    desc->rt_protocol != remote->rt_protocol)
+			continue;
+
+		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
+	}
+}
+
+static void vxlan_mdb_flush(struct vxlan_dev *vxlan,
+			    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_entry *mdb_entry;
+	struct hlist_node *tmp;
+
+	/* The removal of an entry cannot trigger the removal of another entry
+	 * since entries are always added to the head of the list.
+	 */
+	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
+		if (desc->src_vni && desc->src_vni != mdb_entry->key.vni)
+			continue;
+
+		vxlan_mdb_remotes_flush(vxlan, mdb_entry, desc);
+		/* Entry will only be removed if its remotes list is empty. */
+		vxlan_mdb_entry_put(vxlan, mdb_entry);
+	}
+}
+
+int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		       struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_mdb_flush_desc desc = {};
+	int err;
+
+	ASSERT_RTNL();
+
+	err = vxlan_mdb_flush_desc_init(vxlan, &desc, tb, extack);
+	if (err)
+		return err;
+
+	vxlan_mdb_flush(vxlan, &desc);
+
+	return 0;
+}
+
 static const struct nla_policy vxlan_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
 	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
 					      sizeof(struct in_addr),
@@ -1575,29 +1722,6 @@ static void vxlan_mdb_check_empty(void *ptr, void *arg)
 	WARN_ON_ONCE(1);
 }
 
-static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
-				    struct vxlan_mdb_entry *mdb_entry)
-{
-	struct vxlan_mdb_remote *remote, *tmp;
-
-	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list)
-		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
-}
-
-static void vxlan_mdb_entries_flush(struct vxlan_dev *vxlan)
-{
-	struct vxlan_mdb_entry *mdb_entry;
-	struct hlist_node *tmp;
-
-	/* The removal of an entry cannot trigger the removal of another entry
-	 * since entries are always added to the head of the list.
-	 */
-	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
-		vxlan_mdb_remotes_flush(vxlan, mdb_entry);
-		vxlan_mdb_entry_put(vxlan, mdb_entry);
-	}
-}
-
 int vxlan_mdb_init(struct vxlan_dev *vxlan)
 {
 	int err;
@@ -1613,7 +1737,9 @@ int vxlan_mdb_init(struct vxlan_dev *vxlan)
 
 void vxlan_mdb_fini(struct vxlan_dev *vxlan)
 {
-	vxlan_mdb_entries_flush(vxlan);
+	struct vxlan_mdb_flush_desc desc = {};
+
+	vxlan_mdb_flush(vxlan, &desc);
 	WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB);
 	rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty,
 				    NULL);
diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h
index db679c380955..b35d96b78843 100644
--- a/drivers/net/vxlan/vxlan_private.h
+++ b/drivers/net/vxlan/vxlan_private.h
@@ -235,6 +235,8 @@ int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags,
 		  struct netlink_ext_ack *extack);
 int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 		  struct netlink_ext_ack *extack);
+int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		       struct netlink_ext_ack *extack);
 int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid,
 		  u32 seq, struct netlink_ext_ack *extack);
 struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,