X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fbridge%2Fbr_netfilter.c;h=268e2e7258881addf26214bb4418382ba3228c97;hb=81e675c227ec60a0bdcbb547dc530ebee23ff931;hp=1163c4f69899eef2ada2a8895f05c5564469a196;hpb=98e399f82ab3a6d863d1d4a7ea48925cc91c830e;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 1163c4f..268e2e7 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -29,6 +29,8 @@
 #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>
@@ -48,17 +50,19 @@
 
 #define skb_origaddr(skb)	 (((struct bridge_skb_cb *) \
 				 (skb->nf_bridge->data))->daddr.ipv4)
-#define store_orig_dstaddr(skb)	 (skb_origaddr(skb) = (skb)->nh.iph->daddr)
-#define dnat_took_place(skb)	 (skb_origaddr(skb) != (skb)->nh.iph->daddr)
+#define store_orig_dstaddr(skb)	 (skb_origaddr(skb) = ip_hdr(skb)->daddr)
+#define dnat_took_place(skb)	 (skb_origaddr(skb) != ip_hdr(skb)->daddr)
 
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
 static int brnf_call_ip6tables __read_mostly = 1;
 static int brnf_call_arptables __read_mostly = 1;
-static int brnf_filter_vlan_tagged __read_mostly = 1;
+static int brnf_filter_vlan_tagged __read_mostly = 0;
+static int brnf_filter_pppoe_tagged __read_mostly = 0;
 #else
-#define brnf_filter_vlan_tagged 1
+#define brnf_filter_vlan_tagged 0
+#define brnf_filter_pppoe_tagged 0
 #endif
 
 static inline __be16 vlan_proto(const struct sk_buff *skb)
@@ -81,30 +85,58 @@ static inline __be16 vlan_proto(const struct sk_buff *skb)
 	 vlan_proto(skb) == htons(ETH_P_ARP) &&	\
 	 brnf_filter_vlan_tagged)
 
-/* We need these fake structures to make netfilter happy --
- * lots of places assume that skb->dst != NULL, which isn't
- * all that unreasonable.
- *
+static inline __be16 pppoe_proto(const struct sk_buff *skb)
+{
+	return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+			    sizeof(struct pppoe_hdr)));
+}
+
+#define IS_PPPOE_IP(skb) \
+	(skb->protocol == htons(ETH_P_PPP_SES) && \
+	 pppoe_proto(skb) == htons(PPP_IP) && \
+	 brnf_filter_pppoe_tagged)
+
+#define IS_PPPOE_IPV6(skb) \
+	(skb->protocol == htons(ETH_P_PPP_SES) && \
+	 pppoe_proto(skb) == htons(PPP_IPV6) && \
+	 brnf_filter_pppoe_tagged)
+
+static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+}
+
+static struct dst_ops fake_dst_ops = {
+	.family =		AF_INET,
+	.protocol =		cpu_to_be16(ETH_P_IP),
+	.update_pmtu =		fake_update_pmtu,
+	.entries =		ATOMIC_INIT(0),
+};
+
+/*
+ * Initialize bogus route table used to keep netfilter happy.
  * Currently, we fill in the PMTU entry because netfilter
  * refragmentation needs it, and the rt_flags entry because
  * ipt_REJECT needs it.  Future netfilter modules might
- * require us to fill additional fields. */
-static struct net_device __fake_net_device = {
-	.hard_header_len	= ETH_HLEN
-};
+ * require us to fill additional fields.
+ */
+void br_netfilter_rtable_init(struct net_bridge *br)
+{
+	struct rtable *rt = &br->fake_rtable;
+
+	atomic_set(&rt->u.dst.__refcnt, 1);
+	rt->u.dst.dev = br->dev;
+	rt->u.dst.path = &rt->u.dst;
+	rt->u.dst.metrics[RTAX_MTU - 1] = 1500;
+	rt->u.dst.flags	= DST_NOXFRM;
+	rt->u.dst.ops = &fake_dst_ops;
+}
 
-static struct rtable __fake_rtable = {
-	.u = {
-		.dst = {
-			.__refcnt		= ATOMIC_INIT(1),
-			.dev			= &__fake_net_device,
-			.path			= &__fake_rtable.u.dst,
-			.metrics		= {[RTAX_MTU - 1] = 1500},
-			.flags			= DST_NOXFRM,
-		}
-	},
-	.rt_flags	= 0,
-};
+static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
+{
+	struct net_bridge_port *port = rcu_dereference(dev->br_port);
+
+	return port ? &port->br->fake_rtable : NULL;
+}
 
 static inline struct net_device *bridge_parent(const struct net_device *dev)
 {
@@ -122,14 +154,53 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb)
 	return skb->nf_bridge;
 }
 
-static inline void nf_bridge_save_header(struct sk_buff *skb)
+static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 {
-	int header_size = ETH_HLEN;
+	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
-	if (skb->protocol == htons(ETH_P_8021Q))
-		header_size += VLAN_HLEN;
+	if (atomic_read(&nf_bridge->use) > 1) {
+		struct nf_bridge_info *tmp = nf_bridge_alloc(skb);
 
-	memcpy(skb->nf_bridge->data, skb->data - header_size, header_size);
+		if (tmp) {
+			memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
+			atomic_set(&tmp->use, 1);
+			nf_bridge_put(nf_bridge);
+		}
+		nf_bridge = tmp;
+	}
+	return nf_bridge;
+}
+
+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);
+
+	skb_pull(skb, len);
+	skb->network_header += len;
+}
+
+static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
+{
+	unsigned int len = nf_bridge_encap_header_len(skb);
+
+	skb_pull_rcsum(skb, len);
+	skb->network_header += len;
+}
+
+static inline void nf_bridge_save_header(struct sk_buff *skb)
+{
+	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
+
+	skb_copy_from_linear_data_offset(skb, -header_size,
+					 skb->nf_bridge->data, header_size);
 }
 
 /*
@@ -139,19 +210,15 @@ static inline void nf_bridge_save_header(struct sk_buff *skb)
 int nf_bridge_copy_header(struct sk_buff *skb)
 {
 	int err;
-	int header_size = ETH_HLEN;
-
-	if (skb->protocol == htons(ETH_P_8021Q))
-		header_size += VLAN_HLEN;
+	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
 
-	err = skb_cow(skb, header_size);
+	err = skb_cow_head(skb, header_size);
 	if (err)
 		return err;
 
-	memcpy(skb->data - header_size, skb->nf_bridge->data, header_size);
-
-	if (skb->protocol == htons(ETH_P_8021Q))
-		__skb_push(skb, VLAN_HLEN);
+	skb_copy_to_linear_data_offset(skb, -header_size,
+				       skb->nf_bridge->data, header_size);
+	__skb_push(skb, nf_bridge_encap_header_len(skb));
 	return 0;
 }
 
@@ -161,6 +228,7 @@ int nf_bridge_copy_header(struct sk_buff *skb)
 static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct rtable *rt;
 
 	if (nf_bridge->mask & BRNF_PKT_TYPE) {
 		skb->pkt_type = PACKET_OTHERHOST;
@@ -168,14 +236,16 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 
-	skb->dst = (struct dst_entry *)&__fake_rtable;
-	dst_hold(skb->dst);
+	rt = bridge_parent_rtable(nf_bridge->physindev);
+	if (!rt) {
+		kfree_skb(skb);
+		return 0;
+	}
+	dst_hold(&rt->u.dst);
+	skb_dst_set(skb, &rt->u.dst);
 
 	skb->dev = nf_bridge->physindev;
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_push(skb, VLAN_HLEN);
-		skb->nh.raw -= VLAN_HLEN;
-	}
+	nf_bridge_push_encap_header(skb);
 	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
 		       br_handle_frame_finish, 1);
 
@@ -212,8 +282,9 @@ static void __br_dnat_complain(void)
  * Let us first consider the case that ip_route_input() succeeds:
  *
  * If skb->dst->dev equals the logical bridge device the packet
- * came in on, we can consider this bridging. We then call
- * skb->dst->output() which will make the packet enter br_nf_local_out()
+ * came in on, we can consider this bridging. The packet is passed
+ * through the neighbour output function to build a new destination
+ * MAC address, which will make the packet enter br_nf_local_out()
  * not much later. In that function it is assured that the iptables
  * FORWARD chain is traversed for the packet.
  *
@@ -250,23 +321,26 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 	skb->nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 
 	skb->dev = bridge_parent(skb->dev);
-	if (!skb->dev)
-		kfree_skb(skb);
-	else {
-		if (skb->protocol == htons(ETH_P_8021Q)) {
-			skb_pull(skb, VLAN_HLEN);
-			skb->nh.raw += VLAN_HLEN;
-		}
-		skb->dst->output(skb);
+	if (skb->dev) {
+		struct dst_entry *dst = skb_dst(skb);
+
+		nf_bridge_pull_encap_header(skb);
+
+		if (dst->hh)
+			return neigh_hh_output(dst->hh, skb);
+		else if (dst->neighbour)
+			return dst->neighbour->output(skb);
 	}
+	kfree_skb(skb);
 	return 0;
 }
 
 static int br_nf_pre_routing_finish(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	struct iphdr *iph = skb->nh.iph;
+	struct iphdr *iph = ip_hdr(skb);
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct rtable *rt;
 	int err;
 
 	if (nf_bridge->mask & BRNF_PKT_TYPE) {
@@ -276,7 +350,6 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 	if (dnat_took_place(skb)) {
 		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
-			struct rtable *rt;
 			struct flowi fl = {
 				.nl_u = {
 					.ip4_u = {
@@ -286,7 +359,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 				},
 				.proto = 0,
 			};
-			struct in_device *in_dev = in_dev_get(dev);
+			struct in_device *in_dev = __in_dev_get_rcu(dev);
 
 			/* If err equals -EHOSTUNREACH the error is due to a
 			 * martian destination or due to the fact that
@@ -298,11 +371,11 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 			if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
 				goto free_skb;
 
-			if (!ip_route_output_key(&rt, &fl)) {
+			if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
 				/* - Bridged-and-DNAT'ed traffic doesn't
 				 *   require ip_forwarding. */
 				if (((struct dst_entry *)rt)->dev == dev) {
-					skb->dst = (struct dst_entry *)rt;
+					skb_dst_set(skb, (struct dst_entry *)rt);
 					goto bridged_dnat;
 				}
 				/* we are sure that forwarding is disabled, so printing
@@ -316,17 +389,13 @@ free_skb:
 			kfree_skb(skb);
 			return 0;
 		} else {
-			if (skb->dst->dev == dev) {
+			if (skb_dst(skb)->dev == dev) {
 bridged_dnat:
 				/* Tell br_nf_local_out this is a
 				 * bridged frame */
 				nf_bridge->mask |= BRNF_BRIDGED_DNAT;
 				skb->dev = nf_bridge->physindev;
-				if (skb->protocol ==
-				    htons(ETH_P_8021Q)) {
-					skb_push(skb, VLAN_HLEN);
-					skb->nh.raw -= VLAN_HLEN;
-				}
+				nf_bridge_push_encap_header(skb);
 				NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING,
 					       skb, skb->dev, NULL,
 					       br_nf_pre_routing_finish_bridge,
@@ -337,15 +406,17 @@ bridged_dnat:
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
-		skb->dst = (struct dst_entry *)&__fake_rtable;
-		dst_hold(skb->dst);
+		rt = bridge_parent_rtable(nf_bridge->physindev);
+		if (!rt) {
+			kfree_skb(skb);
+			return 0;
+		}
+		dst_hold(&rt->u.dst);
+		skb_dst_set(skb, &rt->u.dst);
 	}
 
 	skb->dev = nf_bridge->physindev;
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_push(skb, VLAN_HLEN);
-		skb->nh.raw -= VLAN_HLEN;
-	}
+	nf_bridge_push_encap_header(skb);
 	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
 		       br_handle_frame_finish, 1);
 
@@ -372,9 +443,10 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb)
 /* 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 *) (skb->nh.ipv6h + 1);
+	unsigned char *raw = (u8 *)(ipv6_hdr(skb) + 1);
 	u32 pkt_len;
-	int off = raw - skb->nh.raw;
+	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))
@@ -384,9 +456,9 @@ static int check_hbh_len(struct sk_buff *skb)
 	len -= 2;
 
 	while (len > 0) {
-		int optlen = skb->nh.raw[off + 1] + 2;
+		int optlen = nh[off + 1] + 2;
 
-		switch (skb->nh.raw[off]) {
+		switch (nh[off]) {
 		case IPV6_TLV_PAD0:
 			optlen = 1;
 			break;
@@ -395,17 +467,18 @@ static int check_hbh_len(struct sk_buff *skb)
 			break;
 
 		case IPV6_TLV_JUMBO:
-			if (skb->nh.raw[off + 1] != 4 || (off & 3) != 2)
+			if (nh[off + 1] != 4 || (off & 3) != 2)
 				goto bad;
-			pkt_len = ntohl(*(__be32 *) (skb->nh.raw + off + 2));
+			pkt_len = ntohl(*(__be32 *) (nh + off + 2));
 			if (pkt_len <= IPV6_MAXPLEN ||
-			    skb->nh.ipv6h->payload_len)
+			    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)
@@ -439,7 +512,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto inhdr_error;
 
-	hdr = skb->nh.ipv6h;
+	hdr = ipv6_hdr(skb);
 
 	if (hdr->version != 6)
 		goto inhdr_error;
@@ -461,7 +534,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
 	if (!setup_pre_routing(skb))
 		return NF_DROP;
 
-	NF_HOOK(PF_INET6, NF_IP6_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
 		br_nf_pre_routing_finish_ipv6);
 
 	return NF_STOLEN;
@@ -476,27 +549,24 @@ inhdr_error:
  * receiving device) to make netfilter happy, the REDIRECT
  * target in particular.  Save the original destination IP
  * address to be able to detect DNAT afterwards. */
-static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
 	struct iphdr *iph;
-	__u32 len;
-	struct sk_buff *skb = *pskb;
+	__u32 len = nf_bridge_encap_header_len(skb);
+
+	if (unlikely(!pskb_may_pull(skb, len)))
+		goto out;
 
-	if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb)) {
+	if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+	    IS_PPPOE_IPV6(skb)) {
 #ifdef CONFIG_SYSCTL
 		if (!brnf_call_ip6tables)
 			return NF_ACCEPT;
 #endif
-		if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
-			goto out;
-
-		if (skb->protocol == htons(ETH_P_8021Q)) {
-			skb_pull_rcsum(skb, VLAN_HLEN);
-			skb->nh.raw += VLAN_HLEN;
-		}
+		nf_bridge_pull_encap_header_rcsum(skb);
 		return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn);
 	}
 #ifdef CONFIG_SYSCTL
@@ -504,28 +574,23 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb,
 		return NF_ACCEPT;
 #endif
 
-	if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb))
+	if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) &&
+	    !IS_PPPOE_IP(skb))
 		return NF_ACCEPT;
 
-	if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
-		goto out;
-
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_pull_rcsum(skb, VLAN_HLEN);
-		skb->nh.raw += VLAN_HLEN;
-	}
+	nf_bridge_pull_encap_header_rcsum(skb);
 
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto inhdr_error;
 
-	iph = skb->nh.iph;
+	iph = ip_hdr(skb);
 	if (iph->ihl < 5 || iph->version != 4)
 		goto inhdr_error;
 
 	if (!pskb_may_pull(skb, 4 * iph->ihl))
 		goto inhdr_error;
 
-	iph = skb->nh.iph;
+	iph = ip_hdr(skb);
 	if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0)
 		goto inhdr_error;
 
@@ -542,7 +607,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb,
 		return NF_DROP;
 	store_orig_dstaddr(skb);
 
-	NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
 		br_nf_pre_routing_finish);
 
 	return NF_STOLEN;
@@ -561,17 +626,15 @@ out:
  * took place when the packet entered the bridge), but we
  * register an IPv4 PRE_ROUTING 'sabotage' hook that will
  * prevent this from happening. */
-static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
 {
-	struct sk_buff *skb = *pskb;
+	struct rtable *rt = skb_rtable(skb);
 
-	if (skb->dst == (struct dst_entry *)&__fake_rtable) {
-		dst_release(skb->dst);
-		skb->dst = NULL;
-	}
+	if (rt && rt == bridge_parent_rtable(in))
+		skb_dst_drop(skb);
 
 	return NF_ACCEPT;
 }
@@ -591,10 +654,7 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	} else {
 		in = *((struct net_device **)(skb->cb));
 	}
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_push(skb, VLAN_HLEN);
-		skb->nh.raw -= VLAN_HLEN;
-	}
+	nf_bridge_push_encap_header(skb);
 	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, in,
 		       skb->dev, br_forward_finish, 1);
 	return 0;
@@ -605,32 +665,37 @@ static int br_nf_forward_finish(struct sk_buff *skb)
  * but we are still able to filter on the 'real' indev/outdev
  * because of the physdev module. For ARP, indev and outdev are the
  * bridge ports. */
-static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
 				     const struct net_device *in,
 				     const struct net_device *out,
 				     int (*okfn)(struct sk_buff *))
 {
-	struct sk_buff *skb = *pskb;
 	struct nf_bridge_info *nf_bridge;
 	struct net_device *parent;
-	int pf;
+	u_int8_t pf;
 
 	if (!skb->nf_bridge)
 		return NF_ACCEPT;
 
+	/* Need exclusive nf_bridge_info since we might have multiple
+	 * different physoutdevs. */
+	if (!nf_bridge_unshare(skb))
+		return NF_DROP;
+
 	parent = bridge_parent(out);
 	if (!parent)
 		return NF_DROP;
 
-	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb))
+	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
+	    IS_PPPOE_IP(skb))
 		pf = PF_INET;
-	else
+	else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+		 IS_PPPOE_IPV6(skb))
 		pf = PF_INET6;
+	else
+		return NF_ACCEPT;
 
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_pull(*pskb, VLAN_HLEN);
-		(*pskb)->nh.raw += VLAN_HLEN;
-	}
+	nf_bridge_pull_encap_header(skb);
 
 	nf_bridge = skb->nf_bridge;
 	if (skb->pkt_type == PACKET_OTHERHOST) {
@@ -642,18 +707,17 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb,
 	nf_bridge->mask |= BRNF_BRIDGED;
 	nf_bridge->physoutdev = skb->dev;
 
-	NF_HOOK(pf, NF_IP_FORWARD, skb, bridge_parent(in), parent,
+	NF_HOOK(pf, NF_INET_FORWARD, skb, bridge_parent(in), parent,
 		br_nf_forward_finish);
 
 	return NF_STOLEN;
 }
 
-static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	struct sk_buff *skb = *pskb;
 	struct net_device **d = (struct net_device **)(skb->cb);
 
 #ifdef CONFIG_SYSCTL
@@ -664,19 +728,16 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb,
 	if (skb->protocol != htons(ETH_P_ARP)) {
 		if (!IS_VLAN_ARP(skb))
 			return NF_ACCEPT;
-		skb_pull(*pskb, VLAN_HLEN);
-		(*pskb)->nh.raw += VLAN_HLEN;
+		nf_bridge_pull_encap_header(skb);
 	}
 
-	if (skb->nh.arph->ar_pln != 4) {
-		if (IS_VLAN_ARP(skb)) {
-			skb_push(*pskb, VLAN_HLEN);
-			(*pskb)->nh.raw -= VLAN_HLEN;
-		}
+	if (arp_hdr(skb)->ar_pln != 4) {
+		if (IS_VLAN_ARP(skb))
+			nf_bridge_push_encap_header(skb);
 		return NF_ACCEPT;
 	}
 	*d = (struct net_device *)in;
-	NF_HOOK(NF_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
+	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
 		(struct net_device *)out, br_nf_forward_finish);
 
 	return NF_STOLEN;
@@ -694,18 +755,22 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb,
  * NF_BR_PRI_FIRST, so no relevant PF_BRIDGE/INPUT functions have been nor
  * will be executed.
  */
-static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff *skb,
 				    const struct net_device *in,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
 	struct net_device *realindev;
-	struct sk_buff *skb = *pskb;
 	struct nf_bridge_info *nf_bridge;
 
 	if (!skb->nf_bridge)
 		return NF_ACCEPT;
 
+	/* Need exclusive nf_bridge_info since we might have multiple
+	 * different physoutdevs. */
+	if (!nf_bridge_unshare(skb))
+		return NF_DROP;
+
 	nf_bridge = skb->nf_bridge;
 	if (!(nf_bridge->mask & BRNF_BRIDGED_DNAT))
 		return NF_ACCEPT;
@@ -719,36 +784,40 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb,
 		skb->pkt_type = PACKET_OTHERHOST;
 		nf_bridge->mask ^= BRNF_PKT_TYPE;
 	}
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_push(skb, VLAN_HLEN);
-		skb->nh.raw -= VLAN_HLEN;
-	}
+	nf_bridge_push_encap_header(skb);
 
 	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, realindev, skb->dev,
 		br_forward_finish);
 	return NF_STOLEN;
 }
 
+#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE)
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
-	if (skb->protocol == htons(ETH_P_IP) &&
+	if (skb->nfct != NULL &&
+	    (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) &&
 	    skb->len > skb->dev->mtu &&
 	    !skb_is_gso(skb))
 		return ip_fragment(skb, br_dev_queue_push_xmit);
 	else
 		return br_dev_queue_push_xmit(skb);
 }
+#else
+static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+{
+        return br_dev_queue_push_xmit(skb);
+}
+#endif
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
-static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
 				       int (*okfn)(struct sk_buff *))
 {
-	struct sk_buff *skb = *pskb;
-	struct nf_bridge_info *nf_bridge = (*pskb)->nf_bridge;
+	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct net_device *realoutdev = bridge_parent(skb->dev);
-	int pf;
+	u_int8_t pf;
 
 #ifdef CONFIG_NETFILTER_DEBUG
 	/* Be very paranoid. This probably won't happen anymore, but let's
@@ -764,16 +833,23 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb,
 	if (!nf_bridge)
 		return NF_ACCEPT;
 
+	if (!(nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT)))
+		return NF_ACCEPT;
+
 	if (!realoutdev)
 		return NF_DROP;
 
-	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb))
+	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
+	    IS_PPPOE_IP(skb))
 		pf = PF_INET;
-	else
+	else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+		 IS_PPPOE_IPV6(skb))
 		pf = PF_INET6;
+	else
+		return NF_ACCEPT;
 
 #ifdef CONFIG_NETFILTER_DEBUG
-	if (skb->dst == NULL) {
+	if (skb_dst(skb) == NULL) {
 		printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n");
 		goto print_error;
 	}
@@ -786,18 +862,10 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb,
 		nf_bridge->mask |= BRNF_PKT_TYPE;
 	}
 
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		skb_pull(skb, VLAN_HLEN);
-		skb->nh.raw += VLAN_HLEN;
-	}
-
+	nf_bridge_pull_encap_header(skb);
 	nf_bridge_save_header(skb);
 
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
-	if (nf_bridge->netoutdev)
-		realoutdev = nf_bridge->netoutdev;
-#endif
-	NF_HOOK(pf, NF_IP_POST_ROUTING, skb, NULL, realoutdev,
+	NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev,
 		br_nf_dev_queue_xmit);
 
 	return NF_STOLEN;
@@ -819,13 +887,13 @@ print_error:
 /* IP/SABOTAGE *****************************************************/
 /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING
  * for the second time. */
-static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff **pskb,
+static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
 {
-	if ((*pskb)->nf_bridge &&
-	    !((*pskb)->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
+	if (skb->nf_bridge &&
+	    !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
 		return NF_STOP;
 	}
 
@@ -836,57 +904,73 @@ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff **pskb,
  * PF_BRIDGE/NF_BR_LOCAL_OUT functions don't get bridged traffic as input.
  * For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
  * ip_refrag() can return NF_STOLEN. */
-static struct nf_hook_ops br_nf_ops[] = {
-	{ .hook = br_nf_pre_routing,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_PRE_ROUTING,
-	  .priority = NF_BR_PRI_BRNF, },
-	{ .hook = br_nf_local_in,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_LOCAL_IN,
-	  .priority = NF_BR_PRI_BRNF, },
-	{ .hook = br_nf_forward_ip,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_FORWARD,
-	  .priority = NF_BR_PRI_BRNF - 1, },
-	{ .hook = br_nf_forward_arp,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_FORWARD,
-	  .priority = NF_BR_PRI_BRNF, },
-	{ .hook = br_nf_local_out,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_LOCAL_OUT,
-	  .priority = NF_BR_PRI_FIRST, },
-	{ .hook = br_nf_post_routing,
-	  .owner = THIS_MODULE,
-	  .pf = PF_BRIDGE,
-	  .hooknum = NF_BR_POST_ROUTING,
-	  .priority = NF_BR_PRI_LAST, },
-	{ .hook = ip_sabotage_in,
-	  .owner = THIS_MODULE,
-	  .pf = PF_INET,
-	  .hooknum = NF_IP_PRE_ROUTING,
-	  .priority = NF_IP_PRI_FIRST, },
-	{ .hook = ip_sabotage_in,
-	  .owner = THIS_MODULE,
-	  .pf = PF_INET6,
-	  .hooknum = NF_IP6_PRE_ROUTING,
-	  .priority = NF_IP6_PRI_FIRST, },
+static struct nf_hook_ops br_nf_ops[] __read_mostly = {
+	{
+		.hook = br_nf_pre_routing,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_PRE_ROUTING,
+		.priority = NF_BR_PRI_BRNF,
+	},
+	{
+		.hook = br_nf_local_in,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_LOCAL_IN,
+		.priority = NF_BR_PRI_BRNF,
+	},
+	{
+		.hook = br_nf_forward_ip,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_FORWARD,
+		.priority = NF_BR_PRI_BRNF - 1,
+	},
+	{
+		.hook = br_nf_forward_arp,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_FORWARD,
+		.priority = NF_BR_PRI_BRNF,
+	},
+	{
+		.hook = br_nf_local_out,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_LOCAL_OUT,
+		.priority = NF_BR_PRI_FIRST,
+	},
+	{
+		.hook = br_nf_post_routing,
+		.owner = THIS_MODULE,
+		.pf = PF_BRIDGE,
+		.hooknum = NF_BR_POST_ROUTING,
+		.priority = NF_BR_PRI_LAST,
+	},
+	{
+		.hook = ip_sabotage_in,
+		.owner = THIS_MODULE,
+		.pf = PF_INET,
+		.hooknum = NF_INET_PRE_ROUTING,
+		.priority = NF_IP_PRI_FIRST,
+	},
+	{
+		.hook = ip_sabotage_in,
+		.owner = THIS_MODULE,
+		.pf = PF_INET6,
+		.hooknum = NF_INET_PRE_ROUTING,
+		.priority = NF_IP6_PRI_FIRST,
+	},
 };
 
 #ifdef CONFIG_SYSCTL
 static
-int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp,
+int brnf_sysctl_call_tables(ctl_table * ctl, int write,
 			    void __user * buffer, size_t * lenp, loff_t * ppos)
 {
 	int ret;
 
-	ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
 
 	if (write && *(int *)(ctl->data))
 		*(int *)(ctl->data) = 1;
@@ -895,58 +979,47 @@ int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp,
 
 static ctl_table brnf_table[] = {
 	{
-		.ctl_name	= NET_BRIDGE_NF_CALL_ARPTABLES,
 		.procname	= "bridge-nf-call-arptables",
 		.data		= &brnf_call_arptables,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &brnf_sysctl_call_tables,
+		.proc_handler	= brnf_sysctl_call_tables,
 	},
 	{
-		.ctl_name	= NET_BRIDGE_NF_CALL_IPTABLES,
 		.procname	= "bridge-nf-call-iptables",
 		.data		= &brnf_call_iptables,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &brnf_sysctl_call_tables,
+		.proc_handler	= brnf_sysctl_call_tables,
 	},
 	{
-		.ctl_name	= NET_BRIDGE_NF_CALL_IP6TABLES,
 		.procname	= "bridge-nf-call-ip6tables",
 		.data		= &brnf_call_ip6tables,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &brnf_sysctl_call_tables,
+		.proc_handler	= brnf_sysctl_call_tables,
 	},
 	{
-		.ctl_name	= NET_BRIDGE_NF_FILTER_VLAN_TAGGED,
 		.procname	= "bridge-nf-filter-vlan-tagged",
 		.data		= &brnf_filter_vlan_tagged,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &brnf_sysctl_call_tables,
+		.proc_handler	= brnf_sysctl_call_tables,
 	},
-	{ .ctl_name = 0 }
-};
-
-static ctl_table brnf_bridge_table[] = {
 	{
-		.ctl_name	= NET_BRIDGE,
-		.procname	= "bridge",
-		.mode		= 0555,
-		.child		= brnf_table,
+		.procname	= "bridge-nf-filter-pppoe-tagged",
+		.data		= &brnf_filter_pppoe_tagged,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= brnf_sysctl_call_tables,
 	},
-	{ .ctl_name = 0 }
+	{ }
 };
 
-static ctl_table brnf_net_table[] = {
-	{
-		.ctl_name	= CTL_NET,
-		.procname	= "net",
-		.mode		= 0555,
-		.child		= brnf_bridge_table,
-	},
-	{ .ctl_name = 0 }
+static struct ctl_path brnf_path[] = {
+	{ .procname = "net", },
+	{ .procname = "bridge", },
+	{ }
 };
 #endif
 
@@ -958,7 +1031,7 @@ int __init br_netfilter_init(void)
 	if (ret < 0)
 		return ret;
 #ifdef CONFIG_SYSCTL
-	brnf_sysctl_header = register_sysctl_table(brnf_net_table);
+	brnf_sysctl_header = register_sysctl_paths(brnf_path, brnf_table);
 	if (brnf_sysctl_header == NULL) {
 		printk(KERN_WARNING
 		       "br_netfilter: can't register to sysctl.\n");