4 files changed, 1580 insertions, 77 deletions

diff --git a/drivers/net/vxlan/Makefile b/drivers/net/vxlan/Makefile
index d4c255499b72..91b8fec8b6cf 100644
--- a/drivers/net/vxlan/Makefile
+++ b/drivers/net/vxlan/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_VXLAN) += vxlan.o
 
-vxlan-objs := vxlan_core.o vxlan_multicast.o vxlan_vnifilter.o
+vxlan-objs := vxlan_core.o vxlan_multicast.o vxlan_vnifilter.o vxlan_mdb.o
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index b1b179effe2a..561fe1b314f5 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -71,53 +71,6 @@ static inline bool vxlan_collect_metadata(struct vxlan_sock *vs)
 	       ip_tunnel_collect_metadata();
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
-{
-	if (nla_len(nla) >= sizeof(struct in6_addr)) {
-		ip->sin6.sin6_addr = nla_get_in6_addr(nla);
-		ip->sa.sa_family = AF_INET6;
-		return 0;
-	} else if (nla_len(nla) >= sizeof(__be32)) {
-		ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
-		ip->sa.sa_family = AF_INET;
-		return 0;
-	} else {
-		return -EAFNOSUPPORT;
-	}
-}
-
-static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
-			      const union vxlan_addr *ip)
-{
-	if (ip->sa.sa_family == AF_INET6)
-		return nla_put_in6_addr(skb, attr, &ip->sin6.sin6_addr);
-	else
-		return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
-}
-
-#else /* !CONFIG_IPV6 */
-
-static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
-{
-	if (nla_len(nla) >= sizeof(struct in6_addr)) {
-		return -EAFNOSUPPORT;
-	} else if (nla_len(nla) >= sizeof(__be32)) {
-		ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
-		ip->sa.sa_family = AF_INET;
-		return 0;
-	} else {
-		return -EAFNOSUPPORT;
-	}
-}
-
-static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
-			      const union vxlan_addr *ip)
-{
-	return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
-}
-#endif
-
 /* Find VXLAN socket based on network namespace, address family, UDP port,
  * enabled unshareable flags and socket device binding (see l3mdev with
  * non-default VRF).
@@ -1863,7 +1816,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 		struct vxlan_fdb *f;
 		struct sk_buff	*reply;
 
-		if (!(n->nud_state & NUD_CONNECTED)) {
+		if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) {
 			neigh_release(n);
 			goto out;
 		}
@@ -2027,7 +1980,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 		struct vxlan_fdb *f;
 		struct sk_buff *reply;
 
-		if (!(n->nud_state & NUD_CONNECTED)) {
+		if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) {
 			neigh_release(n);
 			goto out;
 		}
@@ -2140,28 +2093,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
-				struct vxlan_metadata *md)
-{
-	struct vxlanhdr_gbp *gbp;
-
-	if (!md->gbp)
-		return;
-
-	gbp = (struct vxlanhdr_gbp *)vxh;
-	vxh->vx_flags |= VXLAN_HF_GBP;
-
-	if (md->gbp & VXLAN_GBP_DONT_LEARN)
-		gbp->dont_learn = 1;
-
-	if (md->gbp & VXLAN_GBP_POLICY_APPLIED)
-		gbp->policy_applied = 1;
-
-	gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
-}
-
-static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, u32 vxflags,
-			       __be16 protocol)
+static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol)
 {
 	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh;
 
@@ -2224,9 +2156,9 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
 	}
 
 	if (vxflags & VXLAN_F_GBP)
-		vxlan_build_gbp_hdr(vxh, vxflags, md);
+		vxlan_build_gbp_hdr(vxh, md);
 	if (vxflags & VXLAN_F_GPE) {
-		err = vxlan_build_gpe_hdr(vxh, vxflags, skb->protocol);
+		err = vxlan_build_gpe_hdr(vxh, skb->protocol);
 		if (err < 0)
 			return err;
 		inner_protocol = skb->protocol;
@@ -2442,9 +2374,8 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
 	return 0;
 }
 
-static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
-			   __be32 default_vni, struct vxlan_rdst *rdst,
-			   bool did_rsc)
+void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
+		    __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc)
 {
 	struct dst_cache *dst_cache;
 	struct ip_tunnel_info *info;
@@ -2791,6 +2722,21 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 	}
 
+	if (vxlan->cfg.flags & VXLAN_F_MDB) {
+		struct vxlan_mdb_entry *mdb_entry;
+
+		rcu_read_lock();
+		mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni);
+		if (mdb_entry) {
+			netdev_tx_t ret;
+
+			ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb);
+			rcu_read_unlock();
+			return ret;
+		}
+		rcu_read_unlock();
+	}
+
 	eth = eth_hdr(skb);
 	f = vxlan_find_mac(vxlan, eth->h_dest, vni);
 	did_rsc = false;
@@ -2926,8 +2872,14 @@ static int vxlan_init(struct net_device *dev)
 	if (err)
 		goto err_free_percpu;
 
+	err = vxlan_mdb_init(vxlan);
+	if (err)
+		goto err_gro_cells_destroy;
+
 	return 0;
 
+err_gro_cells_destroy:
+	gro_cells_destroy(&vxlan->gro_cells);
 err_free_percpu:
 	free_percpu(dev->tstats);
 err_vnigroup_uninit:
@@ -2952,6 +2904,8 @@ static void vxlan_uninit(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
+	vxlan_mdb_fini(vxlan);
+
 	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
 		vxlan_vnigroup_uninit(vxlan);
 
@@ -3108,6 +3062,9 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_fdb_del		= vxlan_fdb_delete,
 	.ndo_fdb_dump		= vxlan_fdb_dump,
 	.ndo_fdb_get		= vxlan_fdb_get,
+	.ndo_mdb_add		= vxlan_mdb_add,
+	.ndo_mdb_del		= vxlan_mdb_del,
+	.ndo_mdb_dump		= vxlan_mdb_dump,
 	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
 };
 
diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c
new file mode 100644
index 000000000000..5e041622261a
--- /dev/null
+++ b/drivers/net/vxlan/vxlan_mdb.c
@@ -0,0 +1,1462 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/if_bridge.h>
+#include <linux/in.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/netlink.h>
+#include <net/vxlan.h>
+
+#include "vxlan_private.h"
+
+struct vxlan_mdb_entry_key {
+	union vxlan_addr src;
+	union vxlan_addr dst;
+	__be32 vni;
+};
+
+struct vxlan_mdb_entry {
+	struct rhash_head rhnode;
+	struct list_head remotes;
+	struct vxlan_mdb_entry_key key;
+	struct hlist_node mdb_node;
+	struct rcu_head rcu;
+};
+
+#define VXLAN_MDB_REMOTE_F_BLOCKED	BIT(0)
+
+struct vxlan_mdb_remote {
+	struct list_head list;
+	struct vxlan_rdst __rcu *rd;
+	u8 flags;
+	u8 filter_mode;
+	u8 rt_protocol;
+	struct hlist_head src_list;
+	struct rcu_head rcu;
+};
+
+#define VXLAN_SGRP_F_DELETE	BIT(0)
+
+struct vxlan_mdb_src_entry {
+	struct hlist_node node;
+	union vxlan_addr addr;
+	u8 flags;
+};
+
+struct vxlan_mdb_dump_ctx {
+	long reserved;
+	long entry_idx;
+	long remote_idx;
+};
+
+struct vxlan_mdb_config_src_entry {
+	union vxlan_addr addr;
+	struct list_head node;
+};
+
+struct vxlan_mdb_config {
+	struct vxlan_dev *vxlan;
+	struct vxlan_mdb_entry_key group;
+	struct list_head src_list;
+	union vxlan_addr remote_ip;
+	u32 remote_ifindex;
+	__be32 remote_vni;
+	__be16 remote_port;
+	u16 nlflags;
+	u8 flags;
+	u8 filter_mode;
+	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),
+	.key_len = sizeof(struct vxlan_mdb_entry_key),
+	.automatic_shrinking = true,
+};
+
+static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg,
+			   struct netlink_ext_ack *extack);
+static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg,
+			   struct netlink_ext_ack *extack);
+
+static void vxlan_br_mdb_entry_fill(const struct vxlan_dev *vxlan,
+				    const struct vxlan_mdb_entry *mdb_entry,
+				    const struct vxlan_mdb_remote *remote,
+				    struct br_mdb_entry *e)
+{
+	const union vxlan_addr *dst = &mdb_entry->key.dst;
+
+	memset(e, 0, sizeof(*e));
+	e->ifindex = vxlan->dev->ifindex;
+	e->state = MDB_PERMANENT;
+
+	if (remote->flags & VXLAN_MDB_REMOTE_F_BLOCKED)
+		e->flags |= MDB_FLAGS_BLOCKED;
+
+	switch (dst->sa.sa_family) {
+	case AF_INET:
+		e->addr.u.ip4 = dst->sin.sin_addr.s_addr;
+		e->addr.proto = htons(ETH_P_IP);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		e->addr.u.ip6 = dst->sin6.sin6_addr;
+		e->addr.proto = htons(ETH_P_IPV6);
+		break;
+#endif
+	}
+}
+
+static int vxlan_mdb_entry_info_fill_srcs(struct sk_buff *skb,
+					  const struct vxlan_mdb_remote *remote)
+{
+	struct vxlan_mdb_src_entry *ent;
+	struct nlattr *nest;
+
+	if (hlist_empty(&remote->src_list))
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST);
+	if (!nest)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry(ent, &remote->src_list, node) {
+		struct nlattr *nest_ent;
+
+		nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY);
+		if (!nest_ent)
+			goto out_cancel_err;
+
+		if (vxlan_nla_put_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
+				       &ent->addr) ||
+		    nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, 0))
+			goto out_cancel_err;
+
+		nla_nest_end(skb, nest_ent);
+	}
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+out_cancel_err:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int vxlan_mdb_entry_info_fill(const struct vxlan_dev *vxlan,
+				     struct sk_buff *skb,
+				     const struct vxlan_mdb_entry *mdb_entry,
+				     const struct vxlan_mdb_remote *remote)
+{
+	struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+	struct br_mdb_entry e;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO);
+	if (!nest)
+		return -EMSGSIZE;
+
+	vxlan_br_mdb_entry_fill(vxlan, mdb_entry, remote, &e);
+
+	if (nla_put_nohdr(skb, sizeof(e), &e) ||
+	    nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, 0))
+		goto nest_err;
+
+	if (!vxlan_addr_any(&mdb_entry->key.src) &&
+	    vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_SOURCE, &mdb_entry->key.src))
+		goto nest_err;
+
+	if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, remote->rt_protocol) ||
+	    nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, remote->filter_mode) ||
+	    vxlan_mdb_entry_info_fill_srcs(skb, remote) ||
+	    vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_DST, &rd->remote_ip))
+		goto nest_err;
+
+	if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port &&
+	    nla_put_u16(skb, MDBA_MDB_EATTR_DST_PORT,
+			be16_to_cpu(rd->remote_port)))
+		goto nest_err;
+
+	if (rd->remote_vni != vxlan->default_dst.remote_vni &&
+	    nla_put_u32(skb, MDBA_MDB_EATTR_VNI, be32_to_cpu(rd->remote_vni)))
+		goto nest_err;
+
+	if (rd->remote_ifindex &&
+	    nla_put_u32(skb, MDBA_MDB_EATTR_IFINDEX, rd->remote_ifindex))
+		goto nest_err;
+
+	if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) &&
+	    mdb_entry->key.vni && nla_put_u32(skb, MDBA_MDB_EATTR_SRC_VNI,
+					      be32_to_cpu(mdb_entry->key.vni)))
+		goto nest_err;
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+nest_err:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int vxlan_mdb_entry_fill(const struct vxlan_dev *vxlan,
+				struct sk_buff *skb,
+				struct vxlan_mdb_dump_ctx *ctx,
+				const struct vxlan_mdb_entry *mdb_entry)
+{
+	int remote_idx = 0, s_remote_idx = ctx->remote_idx;
+	struct vxlan_mdb_remote *remote;
+	struct nlattr *nest;
+	int err = 0;
+
+	nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY);
+	if (!nest)
+		return -EMSGSIZE;
+
+	list_for_each_entry(remote, &mdb_entry->remotes, list) {
+		if (remote_idx < s_remote_idx)
+			goto skip;
+
+		err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote);
+		if (err)
+			break;
+skip:
+		remote_idx++;
+	}
+
+	ctx->remote_idx = err ? remote_idx : 0;
+	nla_nest_end(skb, nest);
+	return err;
+}
+
+static int vxlan_mdb_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb,
+			  struct vxlan_mdb_dump_ctx *ctx)
+{
+	int entry_idx = 0, s_entry_idx = ctx->entry_idx;
+	struct vxlan_mdb_entry *mdb_entry;
+	struct nlattr *nest;
+	int err = 0;
+
+	nest = nla_nest_start_noflag(skb, MDBA_MDB);
+	if (!nest)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry(mdb_entry, &vxlan->mdb_list, mdb_node) {
+		if (entry_idx < s_entry_idx)
+			goto skip;
+
+		err = vxlan_mdb_entry_fill(vxlan, skb, ctx, mdb_entry);
+		if (err)
+			break;
+skip:
+		entry_idx++;
+	}
+
+	ctx->entry_idx = err ? entry_idx : 0;
+	nla_nest_end(skb, nest);
+	return err;
+}
+
+int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb,
+		   struct netlink_callback *cb)
+{
+	struct vxlan_mdb_dump_ctx *ctx = (void *)cb->ctx;
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct br_port_msg *bpm;
+	struct nlmsghdr *nlh;
+	int err;
+
+	ASSERT_RTNL();
+
+	NL_ASSERT_DUMP_CTX_FITS(struct vxlan_mdb_dump_ctx);
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+			cb->nlh->nlmsg_seq, RTM_NEWMDB, sizeof(*bpm),
+			NLM_F_MULTI);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	bpm = nlmsg_data(nlh);
+	memset(bpm, 0, sizeof(*bpm));
+	bpm->family = AF_BRIDGE;
+	bpm->ifindex = dev->ifindex;
+
+	err = vxlan_mdb_fill(vxlan, skb, ctx);
+
+	nlmsg_end(skb, nlh);
+
+	cb->seq = vxlan->mdb_seq;
+	nl_dump_check_consistent(cb, nlh);
+
+	return err;
+}
+
+static const struct nla_policy
+vxlan_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = {
+	[MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY,
+						  sizeof(struct in_addr),
+						  sizeof(struct in6_addr)),
+};
+
+static const struct nla_policy
+vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = {
+	[MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol),
+};
+
+static struct netlink_range_validation vni_range = {
+	.max = VXLAN_N_VID - 1,
+};
+
+static const struct nla_policy vxlan_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+					      sizeof(struct in_addr),
+					      sizeof(struct in6_addr)),
+	[MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE,
+						  MCAST_INCLUDE),
+	[MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_pol),
+	[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_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
+	[MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+};
+
+static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto,
+				      struct netlink_ext_ack *extack)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		if (nla_len(attr) != sizeof(struct in_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length");
+			return false;
+		}
+		if (ipv4_is_multicast(nla_get_in_addr(attr))) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed");
+			return false;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6): {
+		struct in6_addr src;
+
+		if (nla_len(attr) != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length");
+			return false;
+		}
+		src = nla_get_in6_addr(attr);
+		if (ipv6_addr_is_multicast(&src)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed");
+			return false;
+		}
+		break;
+	}
+#endif
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address");
+		return false;
+	}
+
+	return true;
+}
+
+static void vxlan_mdb_config_group_set(struct vxlan_mdb_config *cfg,
+				       const struct br_mdb_entry *entry,
+				       const struct nlattr *source_attr)
+{
+	struct vxlan_mdb_entry_key *group = &cfg->group;
+
+	switch (entry->addr.proto) {
+	case htons(ETH_P_IP):
+		group->dst.sa.sa_family = AF_INET;
+		group->dst.sin.sin_addr.s_addr = entry->addr.u.ip4;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		group->dst.sa.sa_family = AF_INET6;
+		group->dst.sin6.sin6_addr = entry->addr.u.ip6;
+		break;
+#endif
+	}
+
+	if (source_attr)
+		vxlan_nla_get_addr(&group->src, source_attr);
+}
+
+static bool vxlan_mdb_is_star_g(const struct vxlan_mdb_entry_key *group)
+{
+	return !vxlan_addr_any(&group->dst) && vxlan_addr_any(&group->src);
+}
+
+static bool vxlan_mdb_is_sg(const struct vxlan_mdb_entry_key *group)
+{
+	return !vxlan_addr_any(&group->dst) && !vxlan_addr_any(&group->src);
+}
+
+static int vxlan_mdb_config_src_entry_init(struct vxlan_mdb_config *cfg,
+					   __be16 proto,
+					   const struct nlattr *src_entry,
+					   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[MDBE_SRCATTR_MAX + 1];
+	struct vxlan_mdb_config_src_entry *src;
+	int err;
+
+	err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry,
+			       vxlan_mdbe_src_list_entry_pol, extack);
+	if (err)
+		return err;
+
+	if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS))
+		return -EINVAL;
+
+	if (!vxlan_mdb_is_valid_source(tb[MDBE_SRCATTR_ADDRESS], proto,
+				       extack))
+		return -EINVAL;
+
+	src = kzalloc(sizeof(*src), GFP_KERNEL);
+	if (!src)
+		return -ENOMEM;
+
+	err = vxlan_nla_get_addr(&src->addr, tb[MDBE_SRCATTR_ADDRESS]);
+	if (err)
+		goto err_free_src;
+
+	list_add_tail(&src->node, &cfg->src_list);
+
+	return 0;
+
+err_free_src:
+	kfree(src);
+	return err;
+}
+
+static void
+vxlan_mdb_config_src_entry_fini(struct vxlan_mdb_config_src_entry *src)
+{
+	list_del(&src->node);
+	kfree(src);
+}
+
+static int vxlan_mdb_config_src_list_init(struct vxlan_mdb_config *cfg,
+					  __be16 proto,
+					  const struct nlattr *src_list,
+					  struct netlink_ext_ack *extack)
+{
+	struct vxlan_mdb_config_src_entry *src, *tmp;
+	struct nlattr *src_entry;
+	int rem, err;
+
+	nla_for_each_nested(src_entry, src_list, rem) {
+		err = vxlan_mdb_config_src_entry_init(cfg, proto, src_entry,
+						      extack);
+		if (err)
+			goto err_src_entry_init;
+	}
+
+	return 0;
+
+err_src_entry_init:
+	list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node)
+		vxlan_mdb_config_src_entry_fini(src);
+	return err;
+}
+
+static void vxlan_mdb_config_src_list_fini(struct vxlan_mdb_config *cfg)
+{
+	struct vxlan_mdb_config_src_entry *src, *tmp;
+
+	list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node)
+		vxlan_mdb_config_src_entry_fini(src);
+}
+
+static int vxlan_mdb_config_attrs_init(struct vxlan_mdb_config *cfg,
+				       const struct br_mdb_entry *entry,
+				       const struct nlattr *set_attrs,
+				       struct netlink_ext_ack *extack)
+{
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, set_attrs,
+			       vxlan_mdbe_attrs_pol, extack);
+	if (err)
+		return err;
+
+	if (NL_REQ_ATTR_CHECK(extack, set_attrs, mdbe_attrs, MDBE_ATTR_DST)) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing remote destination IP address");
+		return -EINVAL;
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_SOURCE] &&
+	    !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE],
+				       entry->addr.proto, extack))
+		return -EINVAL;
+
+	vxlan_mdb_config_group_set(cfg, entry, mdbe_attrs[MDBE_ATTR_SOURCE]);
+
+	/* rtnetlink code only validates that IPv4 group address is
+	 * multicast.
+	 */
+	if (!vxlan_addr_is_multicast(&cfg->group.dst) &&
+	    !vxlan_addr_any(&cfg->group.dst)) {
+		NL_SET_ERR_MSG_MOD(extack, "Group address is not multicast");
+		return -EINVAL;
+	}
+
+	if (vxlan_addr_any(&cfg->group.dst) &&
+	    mdbe_attrs[MDBE_ATTR_SOURCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Source cannot be specified for the all-zeros entry");
+		return -EINVAL;
+	}
+
+	if (vxlan_mdb_is_sg(&cfg->group))
+		cfg->filter_mode = MCAST_INCLUDE;
+
+	if (mdbe_attrs[MDBE_ATTR_GROUP_MODE]) {
+		if (!vxlan_mdb_is_star_g(&cfg->group)) {
+			NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries");
+			return -EINVAL;
+		}
+		cfg->filter_mode = nla_get_u8(mdbe_attrs[MDBE_ATTR_GROUP_MODE]);
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_LIST]) {
+		if (!vxlan_mdb_is_star_g(&cfg->group)) {
+			NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries");
+			return -EINVAL;
+		}
+		if (!mdbe_attrs[MDBE_ATTR_GROUP_MODE]) {
+			NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode");
+			return -EINVAL;
+		}
+		err = vxlan_mdb_config_src_list_init(cfg, entry->addr.proto,
+						     mdbe_attrs[MDBE_ATTR_SRC_LIST],
+						     extack);
+		if (err)
+			return err;
+	}
+
+	if (vxlan_mdb_is_star_g(&cfg->group) && list_empty(&cfg->src_list) &&
+	    cfg->filter_mode == MCAST_INCLUDE) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list");
+		return -EINVAL;
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		cfg->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	err = vxlan_nla_get_addr(&cfg->remote_ip, mdbe_attrs[MDBE_ATTR_DST]);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid remote destination address");
+		goto err_src_list_fini;
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_DST_PORT])
+		cfg->remote_port =
+			cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT]));
+
+	if (mdbe_attrs[MDBE_ATTR_VNI])
+		cfg->remote_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI]));
+
+	if (mdbe_attrs[MDBE_ATTR_IFINDEX]) {
+		cfg->remote_ifindex =
+			nla_get_s32(mdbe_attrs[MDBE_ATTR_IFINDEX]);
+		if (!__dev_get_by_index(cfg->vxlan->net, cfg->remote_ifindex)) {
+			NL_SET_ERR_MSG_MOD(extack, "Outgoing interface not found");
+			err = -EINVAL;
+			goto err_src_list_fini;
+		}
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_VNI])
+		cfg->group.vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI]));
+
+	return 0;
+
+err_src_list_fini:
+	vxlan_mdb_config_src_list_fini(cfg);
+	return err;
+}
+
+static int vxlan_mdb_config_init(struct vxlan_mdb_config *cfg,
+				 struct net_device *dev, struct nlattr *tb[],
+				 u16 nlmsg_flags,
+				 struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	memset(cfg, 0, sizeof(*cfg));
+	cfg->vxlan = vxlan;
+	cfg->group.vni = vxlan->default_dst.remote_vni;
+	INIT_LIST_HEAD(&cfg->src_list);
+	cfg->nlflags = nlmsg_flags;
+	cfg->filter_mode = MCAST_EXCLUDE;
+	cfg->rt_protocol = RTPROT_STATIC;
+	cfg->remote_vni = vxlan->default_dst.remote_vni;
+	cfg->remote_port = vxlan->cfg.dst_port;
+
+	if (entry->ifindex != dev->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "Port net device must be the VXLAN net device");
+		return -EINVAL;
+	}
+
+	/* State is not part of the entry key and can be ignored on deletion
+	 * requests.
+	 */
+	if ((nlmsg_flags & (NLM_F_CREATE | NLM_F_REPLACE)) &&
+	    entry->state != MDB_PERMANENT) {
+		NL_SET_ERR_MSG_MOD(extack, "MDB entry must be permanent");
+		return -EINVAL;
+	}
+
+	if (entry->flags) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid MDB entry flags");
+		return -EINVAL;
+	}
+
+	if (entry->vid) {
+		NL_SET_ERR_MSG_MOD(extack, "VID must not be specified");
+		return -EINVAL;
+	}
+
+	if (entry->addr.proto != htons(ETH_P_IP) &&
+	    entry->addr.proto != htons(ETH_P_IPV6)) {
+		NL_SET_ERR_MSG_MOD(extack, "Group address must be an IPv4 / IPv6 address");
+		return -EINVAL;
+	}
+
+	if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY_ATTRS)) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY_ATTRS attribute");
+		return -EINVAL;
+	}
+
+	return vxlan_mdb_config_attrs_init(cfg, entry, tb[MDBA_SET_ENTRY_ATTRS],
+					   extack);
+}
+
+static void vxlan_mdb_config_fini(struct vxlan_mdb_config *cfg)
+{
+	vxlan_mdb_config_src_list_fini(cfg);
+}
+
+static struct vxlan_mdb_entry *
+vxlan_mdb_entry_lookup(struct vxlan_dev *vxlan,
+		       const struct vxlan_mdb_entry_key *group)
+{
+	return rhashtable_lookup_fast(&vxlan->mdb_tbl, group,
+				      vxlan_mdb_rht_params);
+}
+
+static struct vxlan_mdb_remote *
+vxlan_mdb_remote_lookup(const struct vxlan_mdb_entry *mdb_entry,
+			const union vxlan_addr *addr)
+{
+	struct vxlan_mdb_remote *remote;
+
+	list_for_each_entry(remote, &mdb_entry->remotes, list) {
+		struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+
+		if (vxlan_addr_equal(addr, &rd->remote_ip))
+			return remote;
+	}
+
+	return NULL;
+}
+
+static void vxlan_mdb_rdst_free(struct rcu_head *head)
+{
+	struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu);
+
+	dst_cache_destroy(&rd->dst_cache);
+	kfree(rd);
+}
+
+static int vxlan_mdb_remote_rdst_init(const struct vxlan_mdb_config *cfg,
+				      struct vxlan_mdb_remote *remote)
+{
+	struct vxlan_rdst *rd;
+	int err;
+
+	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+
+	err = dst_cache_init(&rd->dst_cache, GFP_KERNEL);
+	if (err)
+		goto err_free_rdst;
+
+	rd->remote_ip = cfg->remote_ip;
+	rd->remote_port = cfg->remote_port;
+	rd->remote_vni = cfg->remote_vni;
+	rd->remote_ifindex = cfg->remote_ifindex;
+	rcu_assign_pointer(remote->rd, rd);
+
+	return 0;
+
+err_free_rdst:
+	kfree(rd);
+	return err;
+}
+
+static void vxlan_mdb_remote_rdst_fini(struct vxlan_rdst *rd)
+{
+	call_rcu(&rd->rcu, vxlan_mdb_rdst_free);
+}
+
+static int vxlan_mdb_remote_init(const struct vxlan_mdb_config *cfg,
+				 struct vxlan_mdb_remote *remote)
+{
+	int err;
+
+	err = vxlan_mdb_remote_rdst_init(cfg, remote);
+	if (err)
+		return err;
+
+	remote->flags = cfg->flags;
+	remote->filter_mode = cfg->filter_mode;
+	remote->rt_protocol = cfg->rt_protocol;
+	INIT_HLIST_HEAD(&remote->src_list);
+
+	return 0;
+}
+
+static void vxlan_mdb_remote_fini(struct vxlan_dev *vxlan,
+				  struct vxlan_mdb_remote *remote)
+{
+	WARN_ON_ONCE(!hlist_empty(&remote->src_list));
+	vxlan_mdb_remote_rdst_fini(rtnl_dereference(remote->rd));
+}
+
+static struct vxlan_mdb_src_entry *
+vxlan_mdb_remote_src_entry_lookup(const struct vxlan_mdb_remote *remote,
+				  const union vxlan_addr *addr)
+{
+	struct vxlan_mdb_src_entry *ent;
+
+	hlist_for_each_entry(ent, &remote->src_list, node) {
+		if (vxlan_addr_equal(&ent->addr, addr))
+			return ent;
+	}
+
+	return NULL;
+}
+
+static struct vxlan_mdb_src_entry *
+vxlan_mdb_remote_src_entry_add(struct vxlan_mdb_remote *remote,
+			       const union vxlan_addr *addr)
+{
+	struct vxlan_mdb_src_entry *ent;
+
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return NULL;
+
+	ent->addr = *addr;
+	hlist_add_head(&ent->node, &remote->src_list);
+
+	return ent;
+}
+
+static void
+vxlan_mdb_remote_src_entry_del(struct vxlan_mdb_src_entry *ent)
+{
+	hlist_del(&ent->node);
+	kfree(ent);
+}
+
+static int
+vxlan_mdb_remote_src_fwd_add(const struct vxlan_mdb_config *cfg,
+			     const union vxlan_addr *addr,
+			     struct netlink_ext_ack *extack)
+{
+	struct vxlan_mdb_config sg_cfg;
+
+	memset(&sg_cfg, 0, sizeof(sg_cfg));
+	sg_cfg.vxlan = cfg->vxlan;
+	sg_cfg.group.src = *addr;
+	sg_cfg.group.dst = cfg->group.dst;
+	sg_cfg.group.vni = cfg->group.vni;
+	INIT_LIST_HEAD(&sg_cfg.src_list);
+	sg_cfg.remote_ip = cfg->remote_ip;
+	sg_cfg.remote_ifindex = cfg->remote_ifindex;
+	sg_cfg.remote_vni = cfg->remote_vni;
+	sg_cfg.remote_port = cfg->remote_port;
+	sg_cfg.nlflags = cfg->nlflags;
+	sg_cfg.filter_mode = MCAST_INCLUDE;
+	if (cfg->filter_mode == MCAST_EXCLUDE)
+		sg_cfg.flags = VXLAN_MDB_REMOTE_F_BLOCKED;
+	sg_cfg.rt_protocol = cfg->rt_protocol;
+
+	return __vxlan_mdb_add(&sg_cfg, extack);
+}
+
+static void
+vxlan_mdb_remote_src_fwd_del(struct vxlan_dev *vxlan,
+			     const struct vxlan_mdb_entry_key *group,
+			     const struct vxlan_mdb_remote *remote,
+			     const union vxlan_addr *addr)
+{
+	struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+	struct vxlan_mdb_config sg_cfg;
+
+	memset(&sg_cfg, 0, sizeof(sg_cfg));
+	sg_cfg.vxlan = vxlan;
+	sg_cfg.group.src = *addr;
+	sg_cfg.group.dst = group->dst;
+	sg_cfg.group.vni = group->vni;
+	INIT_LIST_HEAD(&sg_cfg.src_list);
+	sg_cfg.remote_ip = rd->remote_ip;
+
+	__vxlan_mdb_del(&sg_cfg, NULL);
+}
+
+static int
+vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg,
+			 struct vxlan_mdb_remote *remote,
+			 const struct vxlan_mdb_config_src_entry *src,
+			 struct netlink_ext_ack *extack)
+{
+	struct vxlan_mdb_src_entry *ent;
+	int err;
+
+	ent = vxlan_mdb_remote_src_entry_lookup(remote, &src->addr);
+	if (!ent) {
+		ent = vxlan_mdb_remote_src_entry_add(remote, &src->addr);
+		if (!ent)
+			return -ENOMEM;
+	} else if (!(cfg->nlflags & NLM_F_REPLACE)) {
+		NL_SET_ERR_MSG_MOD(extack, "Source entry already exists");
+		return -EEXIST;
+	}
+
+	err = vxlan_mdb_remote_src_fwd_add(cfg, &ent->addr, extack);
+	if (err)
+		goto err_src_del;
+
+	/* Clear flags in case source entry was marked for deletion as part of
+	 * replace flow.
+	 */
+	ent->flags = 0;
+
+	return 0;
+
+err_src_del:
+	vxlan_mdb_remote_src_entry_del(ent);
+	return err;
+}
+
+static void vxlan_mdb_remote_src_del(struct vxlan_dev *vxlan,
+				     const struct vxlan_mdb_entry_key *group,
+				     const struct vxlan_mdb_remote *remote,
+				     struct vxlan_mdb_src_entry *ent)
+{
+	vxlan_mdb_remote_src_fwd_del(vxlan, group, remote, &ent->addr);
+	vxlan_mdb_remote_src_entry_del(ent);
+}
+
+static int vxlan_mdb_remote_srcs_add(const struct vxlan_mdb_config *cfg,
+				     struct vxlan_mdb_remote *remote,
+				     struct netlink_ext_ack *extack)
+{
+	struct vxlan_mdb_config_src_entry *src;
+	struct vxlan_mdb_src_entry *ent;
+	struct hlist_node *tmp;
+	int err;
+
+	list_for_each_entry(src, &cfg->src_list, node) {
+		err = vxlan_mdb_remote_src_add(cfg, remote, src, extack);
+		if (err)
+			goto err_src_del;
+	}
+
+	return 0;
+
+err_src_del:
+	hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node)
+		vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, ent);
+	return err;
+}
+
+static void vxlan_mdb_remote_srcs_del(struct vxlan_dev *vxlan,
+				      const struct vxlan_mdb_entry_key *group,
+				      struct vxlan_mdb_remote *remote)
+{
+	struct vxlan_mdb_src_entry *ent;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node)
+		vxlan_mdb_remote_src_del(vxlan, group, remote, ent);
+}
+
+static size_t
+vxlan_mdb_nlmsg_src_list_size(const struct vxlan_mdb_entry_key *group,
+			      const struct vxlan_mdb_remote *remote)
+{
+	struct vxlan_mdb_src_entry *ent;
+	size_t nlmsg_size;
+
+	if (hlist_empty(&remote->src_list))
+		return 0;
+
+	/* MDBA_MDB_EATTR_SRC_LIST */
+	nlmsg_size = nla_total_size(0);
+
+	hlist_for_each_entry(ent, &remote->src_list, node) {
+			      /* MDBA_MDB_SRCLIST_ENTRY */
+		nlmsg_size += nla_total_size(0) +
+			      /* MDBA_MDB_SRCATTR_ADDRESS */
+			      nla_total_size(vxlan_addr_size(&group->dst)) +
+			      /* MDBA_MDB_SRCATTR_TIMER */
+			      nla_total_size(sizeof(u8));
+	}
+
+	return nlmsg_size;
+}
+
+static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan,
+				   const struct vxlan_mdb_entry *mdb_entry,
+				   const struct vxlan_mdb_remote *remote)
+{