diff options
Diffstat (limited to 'net/bridge/br_netfilter.c')
| -rw-r--r-- | net/bridge/br_netfilter.c | 1216 |
1 files changed, 598 insertions, 618 deletions
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 05b3de88824..a615264cf01 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -3,15 +3,8 @@ * Linux ethernet bridge * * Authors: - * Lennert Buytenhek <buytenh@gnu.org> - * Bart De Schuymer (maintainer) <bdschuym@pandora.be> - * - * Changes: - * Apr 29 2003: physdev module support (bdschuym) - * Jun 19 2003: let arptables see bridged ARP traffic (bdschuym) - * Oct 06 2003: filter encapsulated IP/ARP VLAN traffic on untagged bridge - * (bdschuym) - * Sep 01 2004: add IPv6 filtering (bdschuym) + * 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 @@ -23,24 +16,27 @@ #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/route.h> #include <asm/uaccess.h> -#include <asm/checksum.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -48,71 +44,146 @@ #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 = 1; -static int brnf_call_ip6tables = 1; -static int brnf_call_arptables = 1; -static int brnf_filter_vlan_tagged = 1; +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 = 0; +static int brnf_filter_pppoe_tagged __read_mostly = 0; +static int brnf_pass_vlan_indev __read_mostly = 0; #else -#define brnf_filter_vlan_tagged 1 +#define brnf_call_iptables 1 +#define brnf_call_ip6tables 1 +#define brnf_call_arptables 1 +#define brnf_filter_vlan_tagged 0 +#define brnf_filter_pppoe_tagged 0 +#define brnf_pass_vlan_indev 0 #endif -int brnf_deferred_hooks; -EXPORT_SYMBOL_GPL(brnf_deferred_hooks); +#define IS_IP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) + +#define IS_IPV6(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) + +#define IS_ARP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) -static __be16 inline vlan_proto(const struct sk_buff *skb) +static inline __be16 vlan_proto(const struct sk_buff *skb) { - return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + if (vlan_tx_tag_present(skb)) + return skb->protocol; + else if (skb->protocol == htons(ETH_P_8021Q)) + return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + else + return 0; } #define IS_VLAN_IP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IP) && \ + (vlan_proto(skb) == htons(ETH_P_IP) && \ brnf_filter_vlan_tagged) #define IS_VLAN_IPV6(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IPV6) &&\ + (vlan_proto(skb) == htons(ETH_P_IPV6) && \ brnf_filter_vlan_tagged) #define IS_VLAN_ARP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_ARP) && \ + (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, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void fake_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} + +static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + return NULL; +} + +static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + return NULL; +} + +static unsigned int fake_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + +static struct dst_ops fake_dst_ops = { + .family = AF_INET, + .protocol = cpu_to_be16(ETH_P_IP), + .update_pmtu = fake_update_pmtu, + .redirect = fake_redirect, + .cow_metrics = fake_cow_metrics, + .neigh_lookup = fake_neigh_lookup, + .mtu = fake_mtu, +}; + +/* + * 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. + */ +static const u32 br_dst_default_metrics[RTAX_MAX] = { + [RTAX_MTU - 1] = 1500, }; -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, -}; +void br_netfilter_rtable_init(struct net_bridge *br) +{ + struct rtable *rt = &br->fake_rtable; + + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.dev = br->dev; + rt->dst.path = &rt->dst; + dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; + rt->dst.ops = &fake_dst_ops; +} + +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 = rcu_dereference(dev->br_port); + struct net_bridge_port *port; + port = br_port_get_rcu(dev); return port ? port->br->dev : NULL; } @@ -125,14 +196,148 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) 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; + + if (atomic_read(&nf_bridge->use) > 1) { + struct nf_bridge_info *tmp = nf_bridge_alloc(skb); + + 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 = 16; + int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); - if (skb->protocol == htons(ETH_P_8021Q)) - header_size = 18; + skb_copy_from_linear_data_offset(skb, -header_size, + skb->nf_bridge->data, header_size); +} - memcpy(skb->nf_bridge->data, skb->data - header_size, header_size); +static inline void nf_bridge_update_protocol(struct sk_buff *skb) +{ + if (skb->nf_bridge->mask & BRNF_8021Q) + skb->protocol = htons(ETH_P_8021Q); + else if (skb->nf_bridge->mask & BRNF_PPPoE) + skb->protocol = htons(ETH_P_PPP_SES); +} + +/* When handing a packet over to the IP layer + * check whether we have a skb that is in the + * expected format + */ + +static int br_parse_ip_options(struct sk_buff *skb) +{ + struct ip_options *opt; + const struct iphdr *iph; + struct net_device *dev = skb->dev; + u32 len; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto inhdr_error; + + iph = ip_hdr(skb); + opt = &(IPCB(skb)->opt); + + /* Basic sanity checks */ + if (iph->ihl < 5 || iph->version != 4) + goto inhdr_error; + + if (!pskb_may_pull(skb, iph->ihl*4)) + goto inhdr_error; + + iph = ip_hdr(skb); + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + goto inhdr_error; + + len = ntohs(iph->tot_len); + if (skb->len < len) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + goto drop; + } else if (len < (iph->ihl*4)) + goto inhdr_error; + + if (pskb_trim_rcsum(skb, len)) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + goto drop; + } + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (iph->ihl == 5) + return 0; + + opt->optlen = iph->ihl*4 - sizeof(struct iphdr); + if (ip_options_compile(dev_net(dev), opt, skb)) + goto inhdr_error; + + /* Check correct handling of SRR option */ + if (unlikely(opt->srr)) { + struct in_device *in_dev = __in_dev_get_rcu(dev); + if (in_dev && !IN_DEV_SOURCE_ROUTE(in_dev)) + goto drop; + + if (ip_options_rcv_srr(skb)) + goto drop; + } + + return 0; + +inhdr_error: + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); +drop: + return -1; +} + +/* Fill in the header for fragmented IP packets handled by + * the IPv4 connection tracking code. + */ +int nf_bridge_copy_header(struct sk_buff *skb) +{ + int err; + unsigned int header_size; + + nf_bridge_update_protocol(skb); + header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); + err = skb_cow_head(skb, header_size); + if (err) + return err; + + 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; } /* PF_BRIDGE/PRE_ROUTING *********************************************/ @@ -141,6 +346,7 @@ static inline void nf_bridge_save_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; @@ -148,34 +354,68 @@ 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; + } + skb_dst_set_noref(skb, &rt->dst); skb->dev = nf_bridge->physindev; - if (skb->protocol == htons(ETH_P_8021Q)) { - skb_push(skb, VLAN_HLEN); - skb->nh.raw -= VLAN_HLEN; - } - NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); return 0; } -static void __br_dnat_complain(void) +/* 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 sk_buff *skb) { - static unsigned long last_complaint; + struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct neighbour *neigh; + struct dst_entry *dst; - if (jiffies - last_complaint >= 5 * HZ) { - printk(KERN_WARNING "Performing cross-bridge DNAT requires IP " - "forwarding to be enabled\n"); - last_complaint = jiffies; + skb->dev = bridge_parent(skb->dev); + if (!skb->dev) + goto free_skb; + dst = skb_dst(skb); + neigh = dst_neigh_lookup_skb(dst, skb); + if (neigh) { + int ret; + + if (neigh->hh.hh_len) { + neigh_hh_bridge(&neigh->hh, skb); + skb->dev = nf_bridge->physindev; + ret = br_handle_frame_finish(skb); + } else { + /* the neighbour function below overwrites the complete + * MAC header, so we save the Ethernet source address and + * protocol number. + */ + skb_copy_from_linear_data_offset(skb, + -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, + ETH_HLEN-ETH_ALEN); + /* tell br_dev_xmit to continue with forwarding */ + nf_bridge->mask |= BRNF_BRIDGED_DNAT; + ret = neigh->output(neigh, skb); + } + neigh_release(neigh); + return ret; } +free_skb: + kfree_skb(skb); + return 0; } /* This requires some explaining. If DNAT has taken place, - * we will need to fix up the destination Ethernet address, - * and this is a tricky process. + * we will need to fix up the destination Ethernet address. * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -189,130 +429,118 @@ static void __br_dnat_complain(void) * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * - * 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() - * not much later. In that function it is assured that the iptables - * FORWARD chain is traversed for the packet. + * Let's first consider the case that ip_route_input() succeeds: * + * If the output device equals the logical bridge device the packet + * came in on, we can consider this bridging. The corresponding MAC + * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will - * later be passed up to the IP stack to be routed. + * later be passed up to the IP stack to be routed. For a redirected + * packet, ip_route_input() will give back the localhost as output device, + * which differs from the bridge device. * - * Let us now consider the case that ip_route_input() fails: + * Let's now consider the case that ip_route_input() fails: * - * After a "echo '0' > /proc/sys/net/ipv4/ip_forward" ip_route_input() - * will fail, while __ip_route_output_key() will return success. The source - * address for __ip_route_output_key() is set to zero, so __ip_route_output_key + * This can be because the destination address is martian, in which case + * the packet will be dropped. + * If IP forwarding is disabled, ip_route_input() will fail, while + * ip_route_output_key() can return success. The source + * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care - * if IP forwarding is allowed. We send a warning message to the users's - * log telling her to put IP forwarding on. - * - * ip_route_input() will also fail if there is no route available. - * In that case we just drop the packet. - * - * --Lennert, 20020411 - * --Bart, 20020416 (updated) - * --Bart, 20021007 (updated) */ -static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) -{ - if (skb->pkt_type == PACKET_OTHERHOST) { - skb->pkt_type = PACKET_HOST; - skb->nf_bridge->mask |= BRNF_PKT_TYPE; - } - 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); - } - return 0; -} - + * if IP forwarding is enabled. If the output device equals the logical bridge + * device, we proceed as if ip_route_input() succeeded. If it differs from the + * logical bridge port or if ip_route_output_key() fails we drop the packet. + */ 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) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->mask ^= BRNF_PKT_TYPE; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (dnat_took_place(skb)) { - if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev)) { - struct rtable *rt; - struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .saddr = 0, - .tos = RT_TOS(iph->tos) }, - }, - .proto = 0, - }; - - if (!ip_route_output_key(&rt, &fl)) { + if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, 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 + * forwarding is disabled. For most martian packets, + * ip_route_output_key() will fail. It won't fail for 2 types of + * martian destinations: loopback destinations and destination + * 0.0.0.0. In both cases the packet will be dropped because the + * destination is the loopback device and not the bridge. */ + if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) + goto free_skb; + + rt = ip_route_output(dev_net(dev), iph->daddr, 0, + RT_TOS(iph->tos), 0); + if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't - * require ip_forwarding. - * - Deal with redirected traffic. */ - if (((struct dst_entry *)rt)->dev == dev || - rt->rt_type == RTN_LOCAL) { - skb->dst = (struct dst_entry *)rt; + * require ip_forwarding. */ + if (rt->dst.dev == dev) { + skb_dst_set(skb, &rt->dst); goto bridged_dnat; } - __br_dnat_complain(); - dst_release((struct dst_entry *)rt); + ip_rt_put(rt); } +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_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, + NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; } - memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); 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; + } + skb_dst_set_noref(skb, &rt->dst); } skb->dev = nf_bridge->physindev; - if (skb->protocol == htons(ETH_P_8021Q)) { - skb_push(skb, VLAN_HLEN); - skb->nh.raw -= VLAN_HLEN; - } - NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); return 0; } +static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev) +{ + struct net_device *vlan, *br; + + br = bridge_parent(dev); + if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb)) + return br; + + vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto, + vlan_tx_tag_get(skb) & VLAN_VID_MASK); + + return vlan ? vlan : br; +} + /* Some common code for IPv4/IPv6 */ static struct net_device *setup_pre_routing(struct sk_buff *skb) { @@ -325,17 +553,24 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; - skb->dev = bridge_parent(skb->dev); + skb->dev = brnf_get_logical_dev(skb, skb->dev); + if (skb->protocol == htons(ETH_P_8021Q)) + nf_bridge->mask |= BRNF_8021Q; + else if (skb->protocol == htons(ETH_P_PPP_SES)) + nf_bridge->mask |= BRNF_PPPoE; + /* Must drop socket now because of tproxy. */ + skb_orphan(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 *) (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)) @@ -345,10 +580,10 @@ 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]) { - case IPV6_TLV_PAD0: + switch (nh[off]) { + case IPV6_TLV_PAD1: optlen = 1; break; @@ -356,17 +591,18 @@ 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(*(u32 *) (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) @@ -385,36 +621,36 @@ bad: /* 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(unsigned int hook, +static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; u32 pkt_len; if (skb->len < sizeof(struct ipv6hdr)) - goto inhdr_error; + return NF_DROP; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto inhdr_error; + return NF_DROP; - hdr = skb->nh.ipv6h; + hdr = ipv6_hdr(skb); if (hdr->version != 6) - goto inhdr_error; + return NF_DROP; pkt_len = ntohs(hdr->payload_len); if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + sizeof(struct ipv6hdr) > skb->len) - goto inhdr_error; + return NF_DROP; if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) - goto inhdr_error; + return NF_DROP; } if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb)) - goto inhdr_error; + return NF_DROP; nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) @@ -422,13 +658,11 @@ 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, + skb->protocol = htons(ETH_P_IPV6); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); return NF_STOLEN; - -inhdr_error: - return NF_DROP; } /* Direct IPv6 traffic to br_nf_pre_routing_ipv6. @@ -437,64 +671,42 @@ 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(const struct nf_hook_ops *ops, + 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; - - if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb)) { -#ifdef CONFIG_SYSCTL - if (!brnf_call_ip6tables) - return NF_ACCEPT; -#endif - if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) - goto out; + struct net_bridge_port *p; + struct net_bridge *br; + __u32 len = nf_bridge_encap_header_len(skb); - if (skb->protocol == htons(ETH_P_8021Q)) { - skb_pull_rcsum(skb, VLAN_HLEN); - skb->nh.raw += VLAN_HLEN; - } - return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn); - } -#ifdef CONFIG_SYSCTL - if (!brnf_call_iptables) - return NF_ACCEPT; -#endif + if (unlikely(!pskb_may_pull(skb, len))) + return NF_DROP; - if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb)) - return NF_ACCEPT; + p = br_port_get_rcu(in); + if (p == NULL) + return NF_DROP; + br = p->br; - if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) - goto out; + if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) { + if (!brnf_call_ip6tables && !br->nf_call_ip6tables) + return NF_ACCEPT; - 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(ops, skb, in, out, okfn); } - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto inhdr_error; - - iph = skb->nh.iph; - if (iph->ihl < 5 || iph->version != 4) - goto inhdr_error; - - if (!pskb_may_pull(skb, 4 * iph->ihl)) - goto inhdr_error; + if (!brnf_call_iptables && !br->nf_call_iptables) + return NF_ACCEPT; - iph = skb->nh.iph; - if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0) - goto inhdr_error; + if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb)) + return NF_ACCEPT; - len = ntohs(iph->tot_len); - if (skb->len < len || len < 4 * iph->ihl) - goto inhdr_error; + nf_bridge_pull_encap_header_rcsum(skb); - pskb_trim_rcsum(skb, len); + if (br_parse_ip_options(skb)) + return NF_DROP; nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) @@ -502,16 +714,12 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, if (!setup_pre_routing(skb)) return NF_DROP; store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); - NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish); return NF_STOLEN; - -inhdr_error: -// IP_INC_STATS_BH(IpInHdrErrors); -out: - return NF_DROP; } @@ -522,18 +730,13 @@ 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(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct sk_buff *skb = *pskb; - - if (skb->dst == (struct dst_entry *)&__fake_rtable) { - dst_release(skb->dst); - skb->dst = NULL; - } - + br_drop_fake_rtable(skb); return NF_ACCEPT; } @@ -543,55 +746,59 @@ static int br_nf_forward_finish(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *in; - if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) { + if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { in = nf_bridge->physindev; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->mask ^= BRNF_PKT_TYPE; } + nf_bridge_update_protocol(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_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, in, + nf_bridge_push_encap_header(skb); + + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in, skb->dev, br_forward_finish, 1); return 0; } + /* This is the 'purely bridged' case. For IP, we pass the packet to * netfilter with indev and outdev set to the bridge device, * 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(const struct nf_hook_ops *ops, + 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)) - pf = PF_INET; + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) + pf = NFPROTO_IPV4; + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) + pf = NFPROTO_IPV6; else - pf = PF_INET6; + 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) { @@ -599,215 +806,106 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, nf_bridge->mask |= BRNF_PKT_TYPE; } + if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) + return NF_DROP; + /* The physdev module checks on this */ nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; + if (pf == NFPROTO_IPV4) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_IP_FORWARD, skb, bridge_parent(in), parent, + NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, 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(const struct nf_hook_ops *ops, + 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_bridge_port *p; + struct net_bridge *br; struct net_device **d = (struct net_device **)(skb->cb); -#ifdef CONFIG_SYSCTL - if (!brnf_call_arptables) + p = br_port_get_rcu(out); + if (p == NULL) + return NF_ACCEPT; + br = p->br; + + if (!brnf_call_arptables && !br->nf_call_arptables) return NF_ACCEPT; -#endif - if (skb->protocol != htons(ETH_P_ARP)) { + if (!IS_ARP(skb)) { 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; } -/* PF_BRIDGE/LOCAL_OUT ***********************************************/ -static int br_nf_local_out_finish(struct sk_buff *skb) -{ - if (skb->protocol == htons(ETH_P_8021Q)) { - skb_push(skb, VLAN_HLEN); - skb->nh.raw -= VLAN_HLEN; - } - - NF_HOOK_THRESH(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, - br_forward_finish, NF_BR_PRI_FIRST + 1); - - return 0; -} - -/* This function sees both locally originated IP packets and forwarded - * IP packets (in both cases the destination device is a bridge - * device). It also sees bridged-and-DNAT'ed packets. - * To be able to filter on the physical bridge devices (with the physdev - * module), we steal packets destined to a bridge device away from the - * PF_INET/FORWARD and PF_INET/OUTPUT hook functions, and give them back later, - * when we have determined the real output device. This is done in here. - * - * If (nf_bridge->mask & BRNF_BRIDGED_DNAT) then the packet is bridged - * and we fake the PF_BRIDGE/FORWARD hook. The function br_nf_forward() - * will then fake the PF_INET/FORWARD hook. br_nf_local_out() has priority - * NF_BR_PRI_FIRST, so no relevant PF_BRIDGE/INPUT functions have been nor - * will be executed. - * Otherwise, if nf_bridge->physindev is NULL, the bridge-nf code never touched - * this packet before, and so the packet was locally originated. We fake - * the PF_INET/LOCAL_OUT hook. - * Finally, if nf_bridge->physindev isn't NULL, then the packet was IP routed, - * so we fake the PF_INET/FORWARD hook. ip_sabotage_out() makes sure - * even routed packets that didn't arrive on a bridge interface have their - * nf_bridge->physindev set. */ -static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - struct net_device *realindev, *realoutdev; - struct sk_buff *skb = *pskb; - struct nf_bridge_info *nf_bridge; - int pf; - - if (!skb->nf_bridge) - return NF_ACCEPT; - - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) - pf = PF_INET; - else - pf = PF_INET6; - -#ifdef CONFIG_NETFILTER_DEBUG - /* Sometimes we get packets with NULL ->dst here (for example, - * running a dhcp client daemon triggers this). This should now - * be fixed, but let's keep the check around. */ - if (skb->dst == NULL) { - printk(KERN_CRIT "br_netfilter: skb->dst == NULL."); - return NF_ACCEPT; - } -#endif - - nf_bridge = skb->nf_bridge; - nf_bridge->physoutdev = skb->dev; - realindev = nf_bridge->physindev; - - /* Bridged, take PF_BRIDGE/FORWARD. - * (see big note in front of br_nf_pre_routing_finish) */ - if (nf_bridge->mask & BRNF_BRIDGED_DNAT) { - if (nf_bridge->mask & BRNF_PKT_TYPE) { - 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_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, realindev, - skb->dev, br_forward_finish); - goto out; - } - realoutdev = bridge_parent(skb->dev); - if (!realoutdev) - return NF_DROP; - -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - /* iptables should match -o br0.x */ - if (nf_bridge->netoutdev) - realoutdev = nf_bridge->netoutdev; -#endif - if (skb->protocol == htons(ETH_P_8021Q)) { - skb_pull(skb, VLAN_HLEN); - (*pskb)->nh.raw += VLAN_HLEN; - } - /* IP forwarded traffic has a physindev, locally - * generated traffic hasn't. */ - if (realindev != NULL) { - if (!(nf_bridge->mask & BRNF_DONT_TAKE_PARENT)) { - struct net_device *parent = bridge_parent(realindev); - if (parent) - realindev = parent; - } + int ret; - NF_HOOK_THRESH(pf, NF_IP_FORWARD, skb, realindev, - realoutdev, br_nf_local_out_finish, - NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD + 1); - } else { - NF_HOOK_THRESH(pf, NF_IP_LOCAL_OUT, skb, realindev, - realoutdev, br_nf_local_out_finish, - NF_IP_PRI_BRIDGE_SABOTAGE_LOCAL_OUT + 1); - } + if (skb->protocol == htons(ETH_P_IP) && + skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && + !skb_is_gso(skb)) { + if (br_parse_ip_options(skb)) + /* Drop invalid packet */ + return NF_DROP; + ret = ip_fragment(skb, br_dev_queue_push_xmit); + } else + ret = br_dev_queue_push_xmit(skb); -out: - return NF_STOLEN; + return ret; } - +#else static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - if (skb->protocol == htons(ETH_P_IP) && - 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); + 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(const struct nf_hook_ops *ops, + 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; - -#ifdef CONFIG_NETFILTER_DEBUG - /* Be very paranoid. This probably won't happen anymore, but let's - * keep the check just to be sure... */ - if (skb->mac.raw < skb->head || skb->mac.raw + ETH_HLEN > skb->data) { - printk(KERN_CRIT "br_netfilter: Argh!! br_nf_post_routing: " - "bad mac.raw pointer."); - goto print_error; - } -#endif + u_int8_t pf; - if (!nf_bridge) + if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) return NF_ACCEPT; if (!realoutdev) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) - pf = PF_INET; + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) + pf = NFPROTO_IPV4; + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) + pf = NFPROTO_IPV6; else - pf = PF_INET6; - -#ifdef CONFIG_NETFILTER_DEBUG - if (skb->dst == NULL) { - printk(KERN_CRIT "br_netfilter: skb->dst == NULL."); - goto print_error; - } -#endif + return NF_ACCEPT; /* We assume any code from br_dev_queue_push_xmit onwards doesn't care * about the value of skb->pkt_type. */ @@ -816,301 +914,183 @@ 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 (pf == NFPROTO_IPV4) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); -#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; - -#ifdef CONFIG_NETFILTER_DEBUG -print_error: - if (skb->dev != NULL) { - printk("[%s]", skb->dev->name); - if (realoutdev) - printk("[%s]", realoutdev->name); - } - printk(" head:%p, raw:%p, data:%p\n", skb->head, skb->mac.raw, - skb->data); - return NF_ACCEPT; -#endif } /* 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(const struct nf_hook_ops *ops, + 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)) { - return NF_STOP; - } - - return NF_ACCEPT; -} - -/* Postpone execution of PF_INET(6)/FORWARD, PF_INET(6)/LOCAL_OUT - * and PF_INET(6)/POST_ROUTING until we have done the forwarding - * decision in the bridge code and have determined nf_bridge->physoutdev. */ -static unsigned int ip_sabotage_out(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *skb = *pskb; - - if ((out->hard_start_xmit == br_dev_xmit && - okfn != br_nf_forward_finish && - okfn != br_nf_local_out_finish && okfn != br_nf_dev_queue_xmit) -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - || ((out->priv_flags & IFF_802_1Q_VLAN) && - VLAN_DEV_INFO(out)->real_dev->hard_start_xmit == br_dev_xmit) -#endif - ) { - struct nf_bridge_info *nf_bridge; - - if (!skb->nf_bridge) { -#ifdef CONFIG_SYSCTL - /* This code is executed while in the IP(v6) stack, - the version should be 4 or 6. We can't use - skb->protocol because that isn't set on - PF_INET(6)/LOCAL_OUT. */ - struct iphdr *ip = skb->nh.iph; - - if (ip->version == 4 && !brnf_call_iptables) - return NF_ACCEPT; - else if (ip->version == 6 && !brnf_call_ip6tables) - return NF_ACCEPT; - else if (!brnf_deferred_hooks) - return NF_ACCEPT; -#endif - if (hook == NF_IP_POST_ROUTING) - return NF_ACCEPT; - if (!nf_bridge_alloc(skb)) - return NF_DROP; - } - - nf_bridge = skb->nf_bridge; - - /* This frame will arrive on PF_BRIDGE/LOCAL_OUT and we - * will need the indev then. For a brouter, the real indev - * can be a bridge port, so we make sure br_nf_local_out() - * doesn't use the bridge parent of the indev by using - * the BRNF_DONT_TAKE_PARENT mask. */ - if (hook == NF_IP_FORWARD && nf_bridge->physindev == NULL) { - nf_bridge->mask |= BRNF_DONT_TAKE_PARENT; - nf_bridge->physindev = (struct net_device *)in; - } -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - /* the iptables outdev is br0.x, not br0 */ - if (out->priv_flags & IFF_802_1Q_VLAN) - nf_bridge->netoutdev = (struct net_device *)out; -#endif + if (skb->nf_bridge && + !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { return NF_STOP; } return NF_ACCEPT; } -/* For br_nf_local_out we need (prio = NF_BR_PRI_FIRST), to insure that innocent - * 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, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_FORWARD, - .priority = NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_FORWARD, - .priority = NF_IP6_PRI_BRIDGE_SABOTAGE_FORWARD, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_BRIDGE_SABOTAGE_LOCAL_OUT, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_BRIDGE_SABOTAGE_LOCAL_OUT, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_FIRST, }, - { .hook = ip_sabotage_out, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_POST_ROUTING, - .priority = NF_IP6_PRI_FIRST, }, +/* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because + * br_dev_queue_push_xmit is called afterwards */ +static struct nf_hook_ops br_nf_ops[] __read_mostly = { + { + .hook = br_nf_pre_routing, + .owner = THIS_MODULE, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_PRE_ROUTING, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_local_in, + .owner = THIS_MODULE, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_forward_ip, + .owner = THIS_MODULE, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_FORWARD, + .priority = NF_BR_PRI_BRNF - 1, + }, + { + .hook = br_nf_forward_arp, + .owner = THIS_MODULE, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_FORWARD, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_post_routing, + .owner = THIS_MODULE, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_POST_ROUTING, + .priority = NF_BR_PRI_LAST, + }, + { + .hook = ip_sabotage_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_FIRST, + }, + { + .hook = ip_sabotage_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .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, - void __user * buffer, size_t * lenp, loff_t * ppos) +int brnf_sysctl_call_tables(struct 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; return ret; } -static ctl_table brnf_table[] = { +static struct 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, + .procname = "bridge-nf-pass-vlan-input-dev", + .data = &brnf_pass_vlan_indev, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = brnf_sysctl_call_tables, }, - { .ctl_name = 0 } + { } }; #endif -int br_netfilter_init(void) +int __init br_netfilter_init(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(br_nf_ops); i++) { - int ret; - - if ((ret = nf_register_hook(&br_nf_ops[i])) >= 0) - continue; + int ret; - while (i--) - nf_unregister_hook(&br_nf_ops[i]); + ret = dst_entries_init(&fake_dst_ops); + if (ret < 0) + return ret; + ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + if (ret < 0) { + dst_entries_destroy(&fake_dst_ops); return ret; } - #ifdef CONFIG_SYSCTL - brnf_sysctl_header = register_sysctl_table(brnf_net_table, 0); + brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table); if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); - for (i = 0; i < ARRAY_SIZE(br_nf_ops); i++) - nf_unregister_hook(&br_nf_ops[i]); - return -EFAULT; + nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + dst_entries_destroy(&fake_dst_ops); + return -ENOMEM; } #endif - printk(KERN_NOTICE "Bridge firewalling registered\n"); - return 0; } void br_netfilter_fini(void) { - int i; - - for (i = ARRAY_SIZE(br_nf_ops) - 1; i >= 0; i--) - nf_unregister_hook(&br_nf_ops[i]); + nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(brnf_sysctl_header); + unregister_net_sysctl_table(brnf_sysctl_header); #endif + dst_entries_destroy(&fake_dst_ops); } |