7 files changed, 417 insertions, 214 deletions

diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index fd7ee03c59b3..a1cda5d4718d 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -12,6 +12,8 @@ bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
 
 bridge-$(subst m,y,$(CONFIG_BRIDGE_NETFILTER)) += br_nf_core.o
 
+br_netfilter-y := br_netfilter_hooks.o
+br_netfilter-$(subst m,y,$(CONFIG_IPV6)) += br_netfilter_ipv6.o
 obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o
 
 bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 7896cf143045..be84b7e5a3da 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -24,6 +24,7 @@
 #include <linux/atomic.h>
 #include <asm/unaligned.h>
 #include <linux/if_vlan.h>
+#include <net/switchdev.h>
 #include "br_private.h"
 
 static struct kmem_cache *br_fdb_cache __read_mostly;
@@ -130,11 +131,27 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr)
 	}
 }
 
+static void fdb_del_external_learn(struct net_bridge_fdb_entry *f)
+{
+	struct switchdev_obj obj = {
+		.id = SWITCHDEV_OBJ_PORT_FDB,
+		.u.fdb = {
+			.addr = f->addr.addr,
+			.vid = f->vlan_id,
+		},
+	};
+
+	switchdev_port_obj_del(f->dst->dev, &obj);
+}
+
 static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
 {
 	if (f->is_static)
 		fdb_del_hw_addr(br, f->addr.addr);
 
+	if (f->added_by_external_learn)
+		fdb_del_external_learn(f);
+
 	hlist_del_rcu(&f->hlist);
 	fdb_notify(br, f, RTM_DELNEIGH);
 	call_rcu(&f->rcu, fdb_rcu_free);
@@ -802,9 +819,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
@@ -871,13 +890,15 @@ out:
 	return err;
 }
 
-static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan)
+static int fdb_delete_by_addr_and_port(struct net_bridge_port *p,
+				       const u8 *addr, u16 vlan)
 {
+	struct net_bridge *br = p->br;
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
 	struct net_bridge_fdb_entry *fdb;
 
 	fdb = fdb_find(head, addr, vlan);
-	if (!fdb)
+	if (!fdb || fdb->dst != p)
 		return -ENOENT;
 
 	fdb_delete(br, fdb);
@@ -890,7 +911,7 @@ static int __br_fdb_delete(struct net_bridge_port *p,
 	int err;
 
 	spin_lock_bh(&p->br->hash_lock);
-	err = fdb_delete_by_addr(p->br, addr, vid);
+	err = fdb_delete_by_addr_and_port(p, addr, vid);
 	spin_unlock_bh(&p->br->hash_lock);
 
 	return err;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 0b38ee98024b..2e246a1a9b43 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1164,6 +1164,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1191,12 +1194,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter_hooks.c
index 46660a28feef..d89f4fac0bc5 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -34,6 +34,7 @@
 
 #include <net/ip.h>
 #include <net/ipv6.h>
+#include <net/addrconf.h>
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
 
@@ -115,16 +116,13 @@ struct brnf_frag_data {
 	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
 	u8 encap_size;
 	u8 size;
+	u16 vlan_tci;
+	__be16 vlan_proto;
 };
 
 static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
 #endif
 
-static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb)
-{
-	return skb->nf_bridge;
-}
-
 static void nf_bridge_info_free(struct sk_buff *skb)
 {
 	if (skb->nf_bridge) {
@@ -133,14 +131,6 @@ static void nf_bridge_info_free(struct sk_buff *skb)
 	}
 }
 
-static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
-{
-	struct net_bridge_port *port;
-
-	port = br_port_get_rcu(dev);
-	return port ? &port->br->fake_rtable : NULL;
-}
-
 static inline struct net_device *bridge_parent(const struct net_device *dev)
 {
 	struct net_bridge_port *port;
@@ -149,15 +139,6 @@ static inline struct net_device *bridge_parent(const struct net_device *dev)
 	return port ? port->br->dev : NULL;
 }
 
-static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb)
-{
-	skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC);
-	if (likely(skb->nf_bridge))
-		atomic_set(&(skb->nf_bridge->use), 1);
-
-	return skb->nf_bridge;
-}
-
 static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
@@ -175,7 +156,7 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 	return nf_bridge;
 }
 
-static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
+unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
 	case __cpu_to_be16(ETH_P_8021Q):
@@ -187,14 +168,6 @@ static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
 	}
 }
 
-static inline void nf_bridge_push_encap_header(struct sk_buff *skb)
-{
-	unsigned int len = nf_bridge_encap_header_len(skb);
-
-	skb_push(skb, len);
-	skb->network_header -= len;
-}
-
 static inline void nf_bridge_pull_encap_header(struct sk_buff *skb)
 {
 	unsigned int len = nf_bridge_encap_header_len(skb);
@@ -216,7 +189,7 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
  * expected format
  */
 
-static int br_parse_ip_options(struct sk_buff *skb)
+static int br_validate_ipv4(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	struct net_device *dev = skb->dev;
@@ -264,7 +237,7 @@ drop:
 	return -1;
 }
 
-static void nf_bridge_update_protocol(struct sk_buff *skb)
+void nf_bridge_update_protocol(struct sk_buff *skb)
 {
 	switch (skb->nf_bridge->orig_proto) {
 	case BRNF_PROTO_8021Q:
@@ -278,43 +251,12 @@ static void nf_bridge_update_protocol(struct sk_buff *skb)
 	}
 }
 
-/* PF_BRIDGE/PRE_ROUTING *********************************************/
-/* Undo the changes made for ip6tables PREROUTING and continue the
- * bridge PRE_ROUTING hook. */
-static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
-{
-	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
-	struct rtable *rt;
-
-	if (nf_bridge->pkt_otherhost) {
-		skb->pkt_type = PACKET_OTHERHOST;
-		nf_bridge->pkt_otherhost = false;
-	}
-	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
-
-	rt = bridge_parent_rtable(nf_bridge->physindev);
-	if (!rt) {
-		kfree_skb(skb);
-		return 0;
-	}
-	skb_dst_set_noref(skb, &rt->dst);
-
-	skb->dev = nf_bridge->physindev;
-	nf_bridge_update_protocol(skb);
-	nf_bridge_push_encap_header(skb);
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
-		       skb->dev, NULL,
-		       br_handle_frame_finish, 1);
-
-	return 0;
-}
-
 /* Obtain the correct destination MAC address, while preserving the original
  * source MAC address. If we already know this address, we just copy it. If we
  * don't, we use the neighbour framework to find out. In both cases, we make
  * sure that br_handle_frame_finish() is called afterwards.
  */
-static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
+int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 {
 	struct neighbour *neigh;
 	struct dst_entry *dst;
@@ -354,8 +296,9 @@ free_skb:
 	return 0;
 }
 
-static bool daddr_was_changed(const struct sk_buff *skb,
-			      const struct nf_bridge_info *nf_bridge)
+static inline bool
+br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
+			     const struct nf_bridge_info *nf_bridge)
 {
 	return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr;
 }
@@ -406,17 +349,15 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
-	int frag_max_size;
 
-	frag_max_size = IPCB(skb)->frag_max_size;
-	BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
+	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
 		skb->pkt_type = PACKET_OTHERHOST;
 		nf_bridge->pkt_otherhost = false;
 	}
-	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
-	if (daddr_was_changed(skb, nf_bridge)) {
+	nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING;
+	if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
 		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
 			struct in_device *in_dev = __in_dev_get_rcu(dev);
 
@@ -494,7 +435,7 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 }
 
 /* Some common code for IPv4/IPv6 */
-static struct net_device *setup_pre_routing(struct sk_buff *skb)
+struct net_device *setup_pre_routing(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
@@ -517,106 +458,6 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb)
 	return skb->dev;
 }
 
-/* We only check the length. A bridge shouldn't do any hop-by-hop stuff anyway */
-static int check_hbh_len(struct sk_buff *skb)
-{
-	unsigned char *raw = (u8 *)(ipv6_hdr(skb) + 1);
-	u32 pkt_len;
-	const unsigned char *nh = skb_network_header(skb);
-	int off = raw - nh;
-	int len = (raw[1] + 1) << 3;
-
-	if ((raw + len) - skb->data > skb_headlen(skb))
-		goto bad;
-
-	off += 2;
-	len -= 2;
-
-	while (len > 0) {
-		int optlen = nh[off + 1] + 2;
-
-		switch (nh[off]) {
-		case IPV6_TLV_PAD1:
-			optlen = 1;
-			break;
-
-		case IPV6_TLV_PADN:
-			break;
-
-		case IPV6_TLV_JUMBO:
-			if (nh[off + 1] != 4 || (off & 3) != 2)
-				goto bad;
-			pkt_len = ntohl(*(__be32 *) (nh + off + 2));
-			if (pkt_len <= IPV6_MAXPLEN ||
-			    ipv6_hdr(skb)->payload_len)
-				goto bad;
-			if (pkt_len > skb->len - sizeof(struct ipv6hdr))
-				goto bad;
-			if (pskb_trim_rcsum(skb,
-					    pkt_len + sizeof(struct ipv6hdr)))
-				goto bad;
-			nh = skb_network_header(skb);
-			break;
-		default:
-			if (optlen > len)
-				goto bad;
-			break;
-		}
-		off += optlen;
-		len -= optlen;
-	}
-	if (len == 0)
-		return 0;
-bad:
-	return -1;
-
-}
-
-/* Replicate the checks that IPv6 does on packet reception and pass the packet
- * to ip6tables, which doesn't support NAT, so things are fairly simple. */
-static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
-					   struct sk_buff *skb,
-					   const struct nf_hook_state *state)
-{
-	const struct ipv6hdr *hdr;
-	u32 pkt_len;
-
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_DROP;
-
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-		return NF_DROP;
-
-	hdr = ipv6_hdr(skb);
-
-	if (hdr->version != 6)
-		return NF_DROP;
-
-	pkt_len = ntohs(hdr->payload_len);
-
-	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
-		if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
-			return NF_DROP;
-		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
-			return NF_DROP;
-	}
-	if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb))
-		return NF_DROP;
-
-	nf_bridge_put(skb->nf_bridge);
-	if (!nf_bridge_alloc(skb))
-		return NF_DROP;
-	if (!setup_pre_routing(skb))
-		return NF_DROP;
-
-	skb->protocol = htons(ETH_P_IPV6);
-	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb,
-		skb->dev, NULL,
-		br_nf_pre_routing_finish_ipv6);
-
-	return NF_STOLEN;
-}
-
 /* Direct IPv6 traffic to br_nf_pre_routing_ipv6.
  * Replicate the checks that IPv4 does on packet reception.
  * Set skb->dev to the bridge device (i.e. parent of the
@@ -656,7 +497,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 
 	nf_bridge_pull_encap_header_rcsum(skb);
 
-	if (br_parse_ip_options(skb))
+	if (br_validate_ipv4(skb))
 		return NF_DROP;
 
 	nf_bridge_put(skb->nf_bridge);
@@ -700,12 +541,12 @@ static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb)
 	struct net_device *in;
 
 	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
-		int frag_max_size;
 
-		if (skb->protocol == htons(ETH_P_IP)) {
-			frag_max_size = IPCB(skb)->frag_max_size;
-			BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
-		}
+		if (skb->protocol == htons(ETH_P_IP))
+			nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
+
+		if (skb->protocol == htons(ETH_P_IPV6))
+			nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
 		in = nf_bridge->physindev;
 		if (nf_bridge->pkt_otherhost) {
@@ -768,12 +609,15 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	}
 
 	if (pf == NFPROTO_IPV4) {
-		int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size;
-
-		if (br_parse_ip_options(skb))
+		if (br_validate_ipv4(skb))
 			return NF_DROP;
+		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
+	}
 
-		IPCB(skb)->frag_max_size = frag_max;
+	if (pf == NFPROTO_IPV6) {
+		if (br_validate_ipv6(skb))
+			return NF_DROP;
+		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
 	}
 
 	nf_bridge->physoutdev = skb->dev;
@@ -823,7 +667,7 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 	return NF_STOLEN;
 }
 
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	struct brnf_frag_data *data;
@@ -837,12 +681,18 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
 		return 0;
 	}
 
+	if (data->vlan_tci) {
+		skb->vlan_tci = data->vlan_tci;
+		skb->vlan_proto = data->vlan_proto;
+	}
+
 	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
 	__skb_push(skb, data->encap_size);
 
 	nf_bridge_info_free(skb);
 	return br_dev_queue_push_xmit(sk, skb);
 }
+#endif
 
 static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb,
 			     int (*output)(struct sock *, struct sk_buff *))
@@ -863,54 +713,82 @@ static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb,
 	return ip_do_fragment(sk, skb, output);
 }
 
+static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
+{
+	if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE)
+		return PPPOE_SES_HLEN;
+	return 0;
+}
+
 static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 {
-	int ret;
-	int frag_max_size;
+	struct nf_bridge_info *nf_bridge;
 	unsigned int mtu_reserved;
 
-	if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) {
+	mtu_reserved = nf_bridge_mtu_reduction(skb);
+
+	if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) {
 		nf_bridge_info_free(skb);
 		return br_dev_queue_push_xmit(sk, skb);
 	}
 
-	mtu_reserved = nf_bridge_mtu_reduction(skb);
+	nf_bridge = nf_bridge_info_get(skb);
+
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 	/* This is wrong! We should preserve the original fragment
 	 * boundaries by preserving frag_list rather than refragmenting.
 	 */
-	if (skb->len + mtu_reserved > skb->dev->mtu) {
+	if (skb->protocol == htons(ETH_P_IP)) {
 		struct brnf_frag_data *data;
 
-		frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
-		if (br_parse_ip_options(skb))
-			/* Drop invalid packet */
+		if (br_validate_ipv4(skb))
 			return NF_DROP;
-		IPCB(skb)->frag_max_size = frag_max_size;
+
+		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
 
 		nf_bridge_update_protocol(skb);
 
 		data = this_cpu_ptr(&brnf_frag_data_storage);
+
+		data->vlan_tci = skb->vlan_tci;
+		data->vlan_proto = skb->vlan_proto;
 		data->encap_size = nf_bridge_encap_header_len(skb);
 		data->size = ETH_HLEN + data->encap_size;
 
 		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
 						 data->size);
 
-		ret = br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit);
-	} else {
-		nf_bridge_info_free(skb);
-		ret = br_dev_queue_push_xmit(sk, skb);
+		return br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit);
 	}
+#endif
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
+		struct brnf_frag_data *data;
 
-	return ret;
-}
-#else
-static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
-{
+		if (br_validate_ipv6(skb))
+			return NF_DROP;
+
+		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
+
+		nf_bridge_update_protocol(skb);
+
+		data = this_cpu_ptr(&brnf_frag_data_storage);
+		data->encap_size = nf_bridge_encap_header_len(skb);
+		data->size = ETH_HLEN + data->encap_size;
+
+		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
+						 data->size);
+
+		if (v6ops)
+			return v6ops->fragment(sk, skb, br_nf_push_frag_xmit);
+		else
+			return -EMSGSIZE;
+	}
+#endif
 	nf_bridge_info_free(skb);
 	return br_dev_queue_push_xmit(sk, skb);
 }
-#endif
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
 static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
new file mode 100644
index 000000000000..6d12d2675c80
--- /dev/null
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -0,0 +1,245 @@
+/*
+ *	Handle firewalling
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *	Bart De Schuymer		<bdschuym@pandora.be>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Lennert dedicates this file to Kerstin Wurdinger.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_arp.h>
+#include <linux/in_route.h>
+#include <linux/inetdevice.h>
+
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <net/route.h>
+#include <net/netfilter/br_netfilter.h>
+
+#include <asm/uaccess.h>
+#include "br_private.h"
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+#endif
+
+/* We only check the length. A bridge shouldn't do any hop-by-hop stuff
+ * anyway
+ */
+static int br_nf_check_hbh_len(struct sk_buff *skb)
+{
+	unsigned char *raw = (u8 *)(ipv6_hdr(skb) + 1);
+	u32 pkt_len;
+	const unsigned char *nh = skb_network_header(skb);
+	int off = raw - nh;
+	int len = (raw[1] + 1) << 3;
+
+	if ((raw + len) - skb->data > skb_headlen(skb))
+		goto bad;
+
+	off += 2;
+	len -= 2;
+
+	while (len > 0) {
+		int optlen = nh[off + 1] + 2;
+
+		switch (nh[off]) {
+		case IPV6_TLV_PAD1:
+			optlen = 1;
+			break;
+
+		case IPV6_TLV_PADN:
+			break;
+
+		case IPV6_TLV_JUMBO:
+			if (nh[off + 1] != 4 || (off & 3) != 2)
+				goto bad;
+			pkt_len = ntohl(*(__be32 *)(nh + off + 2));
+			if (pkt_len <= IPV6_MAXPLEN ||
+			    ipv6_hdr(skb)->payload_len)
+				goto bad;
+			if (pkt_len > skb->len - sizeof(struct ipv6hdr))
+				goto bad;
+			if (pskb_trim_rcsum(skb,
+					    pkt_len + sizeof(struct ipv6hdr)))
+				goto bad;
+			nh = skb_network_header(skb);
+			break;
+		default:
+			if (optlen > len)
+				goto bad;
+			break;
+		}
+		off += optlen;
+		len -= optlen;
+	}
+	if (len == 0)
+		return 0;
+bad:
+	return -1;
+}
+
+int br_validate_ipv6(struct sk_buff *skb)
+{
+	const struct ipv6hdr *hdr;
+	struct net_device *dev = skb->dev;
+	struct inet6_dev *idev = in6_dev_get(skb->dev);
+	u32 pkt_len;
+	u8 ip6h_len = sizeof(struct ipv6hdr);
+
+	if (!pskb_may_pull(skb, ip6h_len))
+		goto inhdr_error;
+
+	if (skb->len < ip6h_len)
+		goto drop;
+
+	hdr = ipv6_hdr(skb);
+
+	if (hdr->version != 6)
+		goto inhdr_error;
+
+	pkt_len = ntohs(hdr->payload_len);
+
+	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
+		if (pkt_len + ip6h_len > skb->len) {
+			IP6_INC_STATS_BH(dev_net(dev), idev,
+					 IPSTATS_MIB_INTRUNCATEDPKTS);
+			goto drop;
+		}
+		if (pskb_trim_rcsum(skb, pkt_len + ip6h_len)) {
+			IP6_INC_STATS_BH(dev_net(dev), idev,
+					 IPSTATS_MIB_INDISCARDS);
+			goto drop;
+		}
+	}
+	if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb))
+		goto drop;
+
+	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+	/* No IP options in IPv6 header; however it should be
+	 * checked if some next headers need special treatment
+	 */
+	return 0;
+
+inhdr_error:
+	IP6_INC_STATS_BH(dev_net(dev), idev, IPSTATS_MIB_INHDRERRORS);
+drop:
+	return -1;
+}
+
+static inline bool
+br_nf_ipv6_daddr_was_changed(const struct sk_buff *skb,
+			     const struct nf_bridge_info *nf_bridge)
+{
+	return memcmp(&nf_bridge->ipv6_daddr, &ipv6_hdr(skb)->daddr,
+		      sizeof(ipv6_hdr(skb)->daddr)) != 0;
+}
+
+/* PF_BRIDGE/PRE_ROUTING: Undo the changes made for ip6tables
+ * PREROUTING and continue the bridge PRE_ROUTING hook. See comment
+ * for br_nf_pre_routing_finish(), same logic is used here but
+ * equivalent IPv6 function ip6_route_input() called indirectly.
+ */
+static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
+{
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	struct rtable *rt;
+	struct net_device *dev = skb->dev;
+	const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
+
+	nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
+
+	if (nf_bridge->pkt_otherhost) {
+		skb->pkt_type = PACKET_OTHERHOST;
+		nf_bridge->pkt_otherhost = false;
+	}
+	nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING;
+	if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) {
+		skb_dst_drop(skb);
+		v6ops->route_input(skb);
+
+		if (skb_dst(skb)->error) {
+			kfree_skb(skb);
+			return 0;
+		}
+
+		if (skb_dst(skb)->dev == dev) {
+			skb->dev = nf_bridge->physindev;
+			nf_bridge_update_protocol(skb);
+			nf_bridge_push_encap_header(skb);
+			NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
+				       sk, skb, skb->dev, NULL,
+				       br_nf_pre_routing_finish_bridge,
+				       1);
+			return 0;
+		}
+		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
+		skb->pkt_type = PACKET_HOST;
+	} else {
+		rt = bridge_parent_rtable(nf_bridge->physindev);
+		if (!rt) {
+			kfree_skb(skb);
+			return 0;
+		}
+		skb_dst_set_noref(skb, &rt->dst);
+	}
+
+	skb->dev = nf_bridge->physindev;
+	nf_bridge_update_protocol(skb);
+	nf_bridge_push_encap_header(skb);
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
+		       skb->dev, NULL,
+		       br_handle_frame_finish, 1);
+
+	return 0;
+}
+
+/* Replicate the checks that IPv6 does on packet reception and pass the packet
+ * to ip6tables.
+ */
+unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct nf_hook_state *state)
+{
+	struct nf_bridge_info *nf_bridge;
+
+	if (br_validate_ipv6(skb))
+		return NF_DROP;
+
+	nf_bridge_put(skb->nf_bridge);
+	if (!nf_bridge_alloc(skb))
+		return NF_DROP;
+	if (!setup_pre_routing(skb))
+		return NF_DROP;
+
+	nf_bridge = nf_bridge_info_get(skb);
+	nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr;
+
+	skb->protocol = htons(ETH_P_IPV6);
+	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb,
+		skb->dev, NULL,
+		br_nf_pre_routing_finish_ipv6);
+
+	return NF_STOLEN;
+}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 1f36fa70639b..5dccced71269 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -18,6 +18,7 @@
 #include <linux/netpoll.h>
 #include <linux/u64_stats_sync.h>
 #include <net/route.h>
+#include <net/ip6_fib.h>
 #include <linux/if_vlan.h>
 
 #define BR_HASH_BITS 8
@@ -214,7 +215,10 @@ struct net_bridge
 	spinlock_t			hash_lock;
 	struct hlist_head		hash[BR_HASH_SIZE];
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	struct rtable 			fake_rtable;
+	union {
+		struct rtable		fake_rtable;
+		struct rt6_info		fake_rt6_info;
+	};
 	bool				nf_call_iptables;
 	bool				nf_call_ip6tables;
 	bool				nf_call_arptables;
@@ -304,7 +308,6 @@ struct br_input_skb_cb {
 	int mrouters_only;
 #endif
 
-	u16 frag_max_size;
 	bool proxyarp_replied;
 
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 13013fe8db24..17fc358a5432 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -2,6 +2,7 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
+#include <net/switchdev.h>
 
 #include "br_private.h"
 
@@ -36,6 +37,36 @@ static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags)
 		clear_bit(vid, v->untagged_bitmap);
 }
 
+static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
+			  u16 vid, u16 flags)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int err;
+
+	/* If driver uses VLAN ndo ops, use 8021q to install vid
+	 * on device, otherwise try switchdev ops to install vid.
+	 */
+
+	if (ops->ndo_vlan_rx_add_vid) {
+		err = vlan_vid_add(dev, br->vlan_proto, vid);
+	} else {
+		struct switchdev_obj vlan_obj = {
+			.id = SWITCHDEV_OBJ_PORT_VLAN,
+			.u.vlan = {
+				.flags = flags,
+				.vid_start = vid,
+				.vid_end = vid,
+			},
+		};
+
+		err = switchdev_port_obj_add(dev, &vlan_obj);
+		if (err == -EOPNOTSUPP)
+			err = 0;
+	}
+
+	return err;
+}
+
 static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 {
 	struct net_bridge_port *p = NULL;
@@ -62,7 +93,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 		 * This ensures tagged traffic enters the bridge when
 		 * promiscuous mode is disabled by br_manage_promisc().
 		 */
-		err = vlan_vid_add(dev, br->vlan_proto, vid);
+		err = __vlan_vid_add(dev, br, vid, flags);
 		if (err)
 			return err;
 	}
@@ -86,6 +117,30 @@ out_filt:
 	return err;
 }
 
+static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br,
+			   u16 vid)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	/* If driver uses VLAN ndo ops, use 8021q to delete vid
+	 * on device, otherwise try switchdev ops to delete vid.
+	 */
+
+	if (ops->ndo_vlan_rx_kill_vid) {
+		vlan_vid_del(dev, br->vlan_proto, vid);
+	} else {
+		struct switchdev_obj vlan_obj = {
+			.id = SWITCHDEV_OBJ_PORT_VLAN,
+			.u.vlan = {
+				.vid_start = vid,
+				.vid_end = vid,
+			},
+		};
+
+		switchdev_port_obj_del(dev, &vlan_obj);
+	}
+}
+
 static int __vlan_del(struct net_port_vlans *v, u16 vid)
 {
 	if (!test_bit(vid, v->vlan_bitmap))
@@ -96,7 +151,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid)
 
 	if (v->port_idx) {
 		struct net_bridge_port *p = v->parent.port;
-		vlan_vid_del(p->dev, p->br->vlan_proto, vid);
+		__vlan_vid_del(p->dev, p->br, vid);
 	}
 
 	clear_bit(vid, v->vlan_bitmap);