br_netfilter.c

linux 内核源代码

		return NF_DROP;
	if (!setup_pre_routing(skb))
		return NF_DROP;

	NF_HOOK(PF_INET6, NF_IP6_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.
 * Replicate the checks that IPv4 does on packet reception.
 * Set skb->dev to the bridge device (i.e. parent of the
 * 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 *skb,
				      const struct net_device *in,
				      const struct net_device *out,
				      int (*okfn)(struct sk_buff *))
{
	struct iphdr *iph;
	__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) ||
	    IS_PPPOE_IPV6(skb)) {
#ifdef CONFIG_SYSCTL
		if (!brnf_call_ip6tables)
			return NF_ACCEPT;
#endif
		nf_bridge_pull_encap_header_rcsum(skb);
		return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn);
	}
#ifdef CONFIG_SYSCTL
	if (!brnf_call_iptables)
		return NF_ACCEPT;
#endif

	if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) &&
	    !IS_PPPOE_IP(skb))
		return NF_ACCEPT;

	nf_bridge_pull_encap_header_rcsum(skb);

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

	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 = ip_hdr(skb);
	if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0)
		goto inhdr_error;

	len = ntohs(iph->tot_len);
	if (skb->len < len || len < 4 * iph->ihl)
		goto inhdr_error;

	pskb_trim_rcsum(skb, len);

	nf_bridge_put(skb->nf_bridge);
	if (!nf_bridge_alloc(skb))
		return NF_DROP;
	if (!setup_pre_routing(skb))
		return NF_DROP;
	store_orig_dstaddr(skb);

	NF_HOOK(PF_INET, NF_IP_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;
}


/* PF_BRIDGE/LOCAL_IN ************************************************/
/* The packet is locally destined, which requires a real
 * dst_entry, so detach the fake one.  On the way up, the
 * packet would pass through PRE_ROUTING again (which already
 * 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 *skb,
				   const struct net_device *in,
				   const struct net_device *out,
				   int (*okfn)(struct sk_buff *))
{
	if (skb->dst == (struct dst_entry *)&__fake_rtable) {
		dst_release(skb->dst);
		skb->dst = NULL;
	}

	return NF_ACCEPT;
}

/* PF_BRIDGE/FORWARD *************************************************/
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)) {
		in = nf_bridge->physindev;
		if (nf_bridge->mask & BRNF_PKT_TYPE) {
			skb->pkt_type = PACKET_OTHERHOST;
			nf_bridge->mask ^= BRNF_PKT_TYPE;
		}
	} else {
		in = *((struct net_device **)(skb->cb));
	}
	nf_bridge_push_encap_header(skb);
	NF_HOOK_THRESH(PF_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 *skb,
				     const struct net_device *in,
				     const struct net_device *out,
				     int (*okfn)(struct sk_buff *))
{
	struct nf_bridge_info *nf_bridge;
	struct net_device *parent;
	int 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) ||
	    IS_PPPOE_IP(skb))
		pf = PF_INET;
	else
		pf = PF_INET6;

	nf_bridge_pull_encap_header(skb);

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

	/* The physdev module checks on this */
	nf_bridge->mask |= BRNF_BRIDGED;
	nf_bridge->physoutdev = skb->dev;

	NF_HOOK(pf, NF_IP_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 *skb,
				      const struct net_device *in,
				      const struct net_device *out,
				      int (*okfn)(struct sk_buff *))
{
	struct net_device **d = (struct net_device **)(skb->cb);

#ifdef CONFIG_SYSCTL
	if (!brnf_call_arptables)
		return NF_ACCEPT;
#endif

	if (skb->protocol != htons(ETH_P_ARP)) {
		if (!IS_VLAN_ARP(skb))
			return NF_ACCEPT;
		nf_bridge_pull_encap_header(skb);
	}

	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,
		(struct net_device *)out, br_nf_forward_finish);

	return NF_STOLEN;
}

/* PF_BRIDGE/LOCAL_OUT ***********************************************
 *
 * 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.
 *
 * 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.
 */
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 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;

	/* Bridged, take PF_BRIDGE/FORWARD.
	 * (see big note in front of br_nf_pre_routing_finish) */
	nf_bridge->physoutdev = skb->dev;
	realindev = nf_bridge->physindev;

	if (nf_bridge->mask & BRNF_PKT_TYPE) {
		skb->pkt_type = PACKET_OTHERHOST;
		nf_bridge->mask ^= BRNF_PKT_TYPE;
	}
	nf_bridge_push_encap_header(skb);

	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, realindev, skb->dev,
		br_forward_finish);
	return NF_STOLEN;
}

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);
}

/* PF_BRIDGE/POST_ROUTING ********************************************/
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 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_header(skb) < skb->head ||
	    skb_mac_header(skb) + ETH_HLEN > skb->data) {
		printk(KERN_CRIT "br_netfilter: Argh!! br_nf_post_routing: "
		       "bad mac.raw pointer.\n");
		goto print_error;
	}
#endif

	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) ||
	    IS_PPPOE_IP(skb))
		pf = PF_INET;
	else
		pf = PF_INET6;

#ifdef CONFIG_NETFILTER_DEBUG
	if (skb->dst == NULL) {
		printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n");
		goto print_error;
	}
#endif

	/* We assume any code from br_dev_queue_push_xmit onwards doesn't care
	 * about the value of skb->pkt_type. */
	if (skb->pkt_type == PACKET_OTHERHOST) {
		skb->pkt_type = PACKET_HOST;
		nf_bridge->mask |= BRNF_PKT_TYPE;
	}

	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,
		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_header(skb),
	       skb->data);
	dump_stack();
	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 *skb,
				   const struct net_device *in,
				   const struct net_device *out,
				   int (*okfn)(struct sk_buff *))
{
	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, },
};

#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 ret;

	ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);

	if (write && *(int *)(ctl->data))
		*(int *)(ctl->data) = 1;
	return ret;
}

static ctl_table brnf_table[] = {
	{
		.procname	= "bridge-nf-call-arptables",
		.data		= &brnf_call_arptables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-call-iptables",
		.data		= &brnf_call_iptables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-call-ip6tables",
		.data		= &brnf_call_ip6tables,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &brnf_sysctl_call_tables,
	},
	{
		.procname	= "bridge-nf-filter-vlan-tagged",
		.data		= &brnf_filter_vlan_tagged,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &brnf_sysctl_call_tables,
	},
	{
		.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_bridge_table[] = {
	{
		.ctl_name	= NET_BRIDGE,
		.procname	= "bridge",
		.mode		= 0555,
		.child		= brnf_table,
	},
	{ .ctl_name = 0 }
};

static ctl_table brnf_net_table[] = {
	{
		.ctl_name	= CTL_NET,
		.procname	= "net",
		.mode		= 0555,
		.child		= brnf_bridge_table,
	},
	{ .ctl_name = 0 }
};
#endif

int __init br_netfilter_init(void)
{
	int ret;

	ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
	if (ret < 0)
		return ret;
#ifdef CONFIG_SYSCTL
	brnf_sysctl_header = register_sysctl_table(brnf_net_table);
	if (brnf_sysctl_header == NULL) {
		printk(KERN_WARNING
		       "br_netfilter: can't register to sysctl.\n");
		nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
		return -ENOMEM;
	}
#endif
	printk(KERN_NOTICE "Bridge firewalling registered\n");
	return 0;
}

void br_netfilter_fini(void)
{
	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
#ifdef CONFIG_SYSCTL
	unregister_sysctl_table(brnf_sysctl_header);
#endif
}