br_netfilter.c

linux 内核源代码

/*
 *	Handle firewalling
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek               <[e-mail]>
 *	Bart De Schuymer (maintainer)	<[e-mail]>
 *
 *	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)
 *
 *	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/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 "br_private.h"
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#define skb_origaddr(skb)	 (((struct bridge_skb_cb *) \
				 (skb->nf_bridge->data))->daddr.ipv4)
#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_pppoe_tagged __read_mostly = 1;
#else
#define brnf_filter_vlan_tagged 1
#define brnf_filter_pppoe_tagged 1
#endif

static inline __be16 vlan_proto(const struct sk_buff *skb)
{
	return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
}

#define IS_VLAN_IP(skb) \
	(skb->protocol == htons(ETH_P_8021Q) && \
	 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) &&\
	 brnf_filter_vlan_tagged)

#define IS_VLAN_ARP(skb) \
	(skb->protocol == htons(ETH_P_8021Q) &&	\
	 vlan_proto(skb) == htons(ETH_P_ARP) &&	\
	 brnf_filter_vlan_tagged)

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)

/* We need these fake structures to make netfilter happy --
 * lots of places assume that skb->dst != NULL, which isn't
 * all that unreasonable.
 *
 * 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
};

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 net_device *bridge_parent(const struct net_device *dev)
{
	struct net_bridge_port *port = rcu_dereference(dev->br_port);

	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;

	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 = ETH_HLEN + nf_bridge_encap_header_len(skb);

	skb_copy_from_linear_data_offset(skb, -header_size,
					 skb->nf_bridge->data, header_size);
}

/*
 * When forwarding bridge frames, we save a copy of the original
 * header before processing.
 */
int nf_bridge_copy_header(struct sk_buff *skb)
{
	int err;
	int 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 *********************************************/
/* Undo the changes made for ip6tables PREROUTING and continue the
 * bridge PRE_ROUTING hook. */
static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = skb->nf_bridge;

	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;

	skb->dst = (struct dst_entry *)&__fake_rtable;
	dst_hold(skb->dst);

	skb->dev = nf_bridge->physindev;
	nf_bridge_push_encap_header(skb);
	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
		       br_handle_frame_finish, 1);

	return 0;
}

static void __br_dnat_complain(void)
{
	static unsigned long last_complaint;

	if (jiffies - last_complaint >= 5 * HZ) {
		printk(KERN_WARNING "Performing cross-bridge DNAT requires IP "
		       "forwarding to be enabled\n");
		last_complaint = jiffies;
	}
}

/* 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.
 *
 * There are two cases to consider:
 * 1. The packet was DNAT'ed to a device in the same bridge
 *    port group as it was received on. We can still bridge
 *    the packet.
 * 2. The packet was DNAT'ed to a different device, either
 *    a non-bridged device or another bridge port group.
 *    The packet will need to be routed.
 *
 * The correct way of distinguishing between these two cases is to
 * 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. 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.
 *
 * 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. 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:
 *
 * This can be because the destination address is martian, in which case
 * the packet will be dropped.
 * 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
 * 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)
 * --Bart, 20062711 (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) {
		struct dst_entry *dst = skb->dst;

		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 = ip_hdr(skb);
	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
	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 ((err = 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,
			};
			struct in_device *in_dev = in_dev_get(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;

			if (!ip_route_output_key(&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;
					goto bridged_dnat;
				}
				/* we are sure that forwarding is disabled, so printing
				 * this message is no problem. Note that the packet could
				 * still have a martian destination address, in which case
				 * the packet could be dropped even if forwarding were enabled */
				__br_dnat_complain();
				dst_release((struct dst_entry *)rt);
			}
free_skb:
			kfree_skb(skb);
			return 0;
		} else {
			if (skb->dst->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;
				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,
					       1);
				return 0;
			}
			memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
			skb->pkt_type = PACKET_HOST;
		}
	} else {
		skb->dst = (struct dst_entry *)&__fake_rtable;
		dst_hold(skb->dst);
	}

	skb->dev = nf_bridge->physindev;
	nf_bridge_push_encap_header(skb);
	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
		       br_handle_frame_finish, 1);

	return 0;
}

/* Some common code for IPv4/IPv6 */
static struct net_device *setup_pre_routing(struct sk_buff *skb)
{
	struct nf_bridge_info *nf_bridge = skb->nf_bridge;

	if (skb->pkt_type == PACKET_OTHERHOST) {
		skb->pkt_type = PACKET_HOST;
		nf_bridge->mask |= BRNF_PKT_TYPE;
	}

	nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING;
	nf_bridge->physindev = skb->dev;
	skb->dev = bridge_parent(skb->dev);

	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_PAD0:
			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(unsigned int hook,
					   struct sk_buff *skb,
					   const struct net_device *in,
					   const struct net_device *out,
					   int (*okfn)(struct sk_buff *))
{
	struct ipv6hdr *hdr;
	u32 pkt_len;

	if (skb->len < sizeof(struct ipv6hdr))
		goto inhdr_error;

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		goto inhdr_error;

	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 + sizeof(struct ipv6hdr) > skb->len)
			goto inhdr_error;
		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
			goto inhdr_error;
	}
	if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb))
		goto inhdr_error;

	nf_bridge_put(skb->nf_bridge);
	if (!nf_bridge_alloc(skb))