Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

net/ipv6/Kconfig

@@ -0,0 +1,79 @@
+#
+# IPv6 configuration
+# 
+config IPV6_PRIVACY
+	bool "IPv6: Privacy Extensions (RFC 3041) support"
+	depends on IPV6
+	---help---
+	  Privacy Extensions for Stateless Address Autoconfiguration in IPv6
+	  support.  With this option, additional periodically-alter 
+	  pseudo-random global-scope unicast address(es) will assigned to
+	  your interface(s).
+	
+	  By default, kernel do not generate temporary addresses.
+	  To use temporary addresses, do
+	
+	        echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr 
+
+	  See <file:Documentation/networking/ip-sysctl.txt> for details.
+
+config INET6_AH
+	tristate "IPv6: AH transformation"
+	depends on IPV6
+	select XFRM
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	---help---
+	  Support for IPsec AH.
+
+	  If unsure, say Y.
+
+config INET6_ESP
+	tristate "IPv6: ESP transformation"
+	depends on IPV6
+	select XFRM
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_DES
+	---help---
+	  Support for IPsec ESP.
+
+	  If unsure, say Y.
+
+config INET6_IPCOMP
+	tristate "IPv6: IPComp transformation"
+	depends on IPV6
+	select XFRM
+	select INET6_TUNNEL
+	select CRYPTO
+	select CRYPTO_DEFLATE
+	---help---
+	  Support for IP Payload Compression Protocol (IPComp) (RFC3173),
+	  typically needed for IPsec.
+
+	  If unsure, say Y.
+
+config INET6_TUNNEL
+	tristate "IPv6: tunnel transformation"
+	depends on IPV6
+	select XFRM
+	---help---
+	  Support for generic IPv6-in-IPv6 tunnel transformation, which is
+	  required by the IPv6-in-IPv6 tunneling module as well as tunnel mode
+	  IPComp.
+	  
+	  If unsure, say Y.
+
+config IPV6_TUNNEL
+	tristate "IPv6: IPv6-in-IPv6 tunnel"
+	depends on IPV6
+	select INET6_TUNNEL
+	---help---
+	  Support for IPv6-in-IPv6 tunnels described in RFC 2473.
+
+	  If unsure, say N.
+

net/ipv6/Makefile

@@ -0,0 +1,25 @@
+#
+# Makefile for the Linux TCP/IP (INET6) layer.
+#
+
+obj-$(CONFIG_IPV6) += ipv6.o
+
+ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \
+		route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \
+		protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+		exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \
+		ip6_flowlabel.o ipv6_syms.o
+
+ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
+	xfrm6_output.o
+ipv6-objs += $(ipv6-y)
+
+obj-$(CONFIG_INET6_AH) += ah6.o
+obj-$(CONFIG_INET6_ESP) += esp6.o
+obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o
+obj-$(CONFIG_INET6_TUNNEL) += xfrm6_tunnel.o 
+obj-$(CONFIG_NETFILTER)	+= netfilter/
+
+obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
+
+obj-y += exthdrs_core.o

net/ipv6/af_inet6.c

@@ -0,0 +1,867 @@
+/*
+ *	PF_INET6 socket protocol family
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>	
+ *
+ *	Adapted from linux/net/ipv4/af_inet.c
+ *
+ *	$Id: af_inet6.c,v 1.66 2002/02/01 22:01:04 davem Exp $
+ *
+ * 	Fixes:
+ *	piggy, Karl Knutson	:	Socket protocol table
+ * 	Hideaki YOSHIFUJI	:	sin6_scope_id support
+ * 	Arnaldo Melo		: 	check proc_net_create return, cleanups
+ *
+ *	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.
+ */
+
+
+#include <linux/module.h>
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/kernel.h>
+#include <linux/major.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+#include <linux/string.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/fcntl.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/init.h>
+
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/icmpv6.h>
+#include <linux/smp_lock.h>
+
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+#include <net/tcp.h>
+#include <net/ipip.h>
+#include <net/protocol.h>
+#include <net/inet_common.h>
+#include <net/transp_v6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#ifdef CONFIG_IPV6_TUNNEL
+#include <net/ip6_tunnel.h>
+#endif
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+
+MODULE_AUTHOR("Cast of dozens");
+MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
+MODULE_LICENSE("GPL");
+
+/* IPv6 procfs goodies... */
+
+#ifdef CONFIG_PROC_FS
+extern int raw6_proc_init(void);
+extern void raw6_proc_exit(void);
+extern int tcp6_proc_init(void);
+extern void tcp6_proc_exit(void);
+extern int udp6_proc_init(void);
+extern void udp6_proc_exit(void);
+extern int ipv6_misc_proc_init(void);
+extern void ipv6_misc_proc_exit(void);
+extern int ac6_proc_init(void);
+extern void ac6_proc_exit(void);
+extern int if6_proc_init(void);
+extern void if6_proc_exit(void);
+#endif
+
+int sysctl_ipv6_bindv6only;
+
+#ifdef INET_REFCNT_DEBUG
+atomic_t inet6_sock_nr;
+#endif
+
+/* The inetsw table contains everything that inet_create needs to
+ * build a new socket.
+ */
+static struct list_head inetsw6[SOCK_MAX];
+static DEFINE_SPINLOCK(inetsw6_lock);
+
+static void inet6_sock_destruct(struct sock *sk)
+{
+	inet_sock_destruct(sk);
+
+#ifdef INET_REFCNT_DEBUG
+	atomic_dec(&inet6_sock_nr);
+#endif
+}
+
+static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
+{
+	const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
+
+	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
+}
+
+static int inet6_create(struct socket *sock, int protocol)
+{
+	struct inet_sock *inet;
+	struct ipv6_pinfo *np;
+	struct sock *sk;
+	struct list_head *p;
+	struct inet_protosw *answer;
+	struct proto *answer_prot;
+	unsigned char answer_flags;
+	char answer_no_check;
+	int rc;
+
+	/* Look for the requested type/protocol pair. */
+	answer = NULL;
+	rcu_read_lock();
+	list_for_each_rcu(p, &inetsw6[sock->type]) {
+		answer = list_entry(p, struct inet_protosw, list);
+
+		/* Check the non-wild match. */
+		if (protocol == answer->protocol) {
+			if (protocol != IPPROTO_IP)
+				break;
+		} else {
+			/* Check for the two wild cases. */
+			if (IPPROTO_IP == protocol) {
+				protocol = answer->protocol;
+				break;
+			}
+			if (IPPROTO_IP == answer->protocol)
+				break;
+		}
+		answer = NULL;
+	}
+
+	rc = -ESOCKTNOSUPPORT;
+	if (!answer)
+		goto out_rcu_unlock;
+	rc = -EPERM;
+	if (answer->capability > 0 && !capable(answer->capability))
+		goto out_rcu_unlock;
+	rc = -EPROTONOSUPPORT;
+	if (!protocol)
+		goto out_rcu_unlock;
+
+	sock->ops = answer->ops;
+
+	answer_prot = answer->prot;
+	answer_no_check = answer->no_check;
+	answer_flags = answer->flags;
+	rcu_read_unlock();
+
+	BUG_TRAP(answer_prot->slab != NULL);
+
+	rc = -ENOBUFS;
+	sk = sk_alloc(PF_INET6, GFP_KERNEL, answer_prot, 1);
+	if (sk == NULL)
+		goto out;
+
+	sock_init_data(sock, sk);
+
+	rc = 0;
+	sk->sk_no_check = answer_no_check;
+	if (INET_PROTOSW_REUSE & answer_flags)
+		sk->sk_reuse = 1;
+
+	inet = inet_sk(sk);
+
+	if (SOCK_RAW == sock->type) {
+		inet->num = protocol;
+		if (IPPROTO_RAW == protocol)
+			inet->hdrincl = 1;
+	}
+
+	sk->sk_destruct		= inet6_sock_destruct;
+	sk->sk_family		= PF_INET6;
+	sk->sk_protocol		= protocol;
+
+	sk->sk_backlog_rcv	= answer->prot->backlog_rcv;
+
+	inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
+	np->hop_limit	= -1;
+	np->mcast_hops	= -1;
+	np->mc_loop	= 1;
+	np->pmtudisc	= IPV6_PMTUDISC_WANT;
+	np->ipv6only	= sysctl_ipv6_bindv6only;
+	
+	/* Init the ipv4 part of the socket since we can have sockets
+	 * using v6 API for ipv4.
+	 */
+	inet->uc_ttl	= -1;
+
+	inet->mc_loop	= 1;
+	inet->mc_ttl	= 1;
+	inet->mc_index	= 0;
+	inet->mc_list	= NULL;
+
+	if (ipv4_config.no_pmtu_disc)
+		inet->pmtudisc = IP_PMTUDISC_DONT;
+	else
+		inet->pmtudisc = IP_PMTUDISC_WANT;
+
+
+#ifdef INET_REFCNT_DEBUG
+	atomic_inc(&inet6_sock_nr);
+	atomic_inc(&inet_sock_nr);
+#endif
+	if (inet->num) {
+		/* It assumes that any protocol which allows
+		 * the user to assign a number at socket
+		 * creation time automatically shares.
+		 */
+		inet->sport = ntohs(inet->num);
+		sk->sk_prot->hash(sk);
+	}
+	if (sk->sk_prot->init) {
+		rc = sk->sk_prot->init(sk);
+		if (rc) {
+			sk_common_release(sk);
+			goto out;
+		}
+	}
+out:
+	return rc;
+out_rcu_unlock:
+	rcu_read_unlock();
+	goto out;
+}
+
+
+/* bind for INET6 API */
+int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sockaddr_in6 *addr=(struct sockaddr_in6 *)uaddr;
+	struct sock *sk = sock->sk;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	__u32 v4addr = 0;
+	unsigned short snum;
+	int addr_type = 0;
+	int err = 0;
+
+	/* If the socket has its own bind function then use it. */
+	if (sk->sk_prot->bind)
+		return sk->sk_prot->bind(sk, uaddr, addr_len);
+
+	if (addr_len < SIN6_LEN_RFC2133)
+		return -EINVAL;
+	addr_type = ipv6_addr_type(&addr->sin6_addr);
+	if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
+		return -EINVAL;
+
+	snum = ntohs(addr->sin6_port);
+	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
+		return -EACCES;
+
+	lock_sock(sk);
+
+	/* Check these errors (active socket, double bind). */
+	if (sk->sk_state != TCP_CLOSE || inet->num) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Check if the address belongs to the host. */
+	if (addr_type == IPV6_ADDR_MAPPED) {
+		v4addr = addr->sin6_addr.s6_addr32[3];
+		if (inet_addr_type(v4addr) != RTN_LOCAL) {
+			err = -EADDRNOTAVAIL;
+			goto out;
+		}
+	} else {
+		if (addr_type != IPV6_ADDR_ANY) {
+			struct net_device *dev = NULL;
+
+			if (addr_type & IPV6_ADDR_LINKLOCAL) {
+				if (addr_len >= sizeof(struct sockaddr_in6) &&
+				    addr->sin6_scope_id) {
+					/* Override any existing binding, if another one
+					 * is supplied by user.
+					 */
+					sk->sk_bound_dev_if = addr->sin6_scope_id;
+				}
+				
+				/* Binding to link-local address requires an interface */
+				if (!sk->sk_bound_dev_if) {
+					err = -EINVAL;
+					goto out;
+				}
+				dev = dev_get_by_index(sk->sk_bound_dev_if);
+				if (!dev) {
+					err = -ENODEV;
+					goto out;
+				}
+			}
+
+			/* ipv4 addr of the socket is invalid.  Only the
+			 * unspecified and mapped address have a v4 equivalent.
+			 */
+			v4addr = LOOPBACK4_IPV6;
+			if (!(addr_type & IPV6_ADDR_MULTICAST))	{
+				if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) {
+					if (dev)
+						dev_put(dev);
+					err = -EADDRNOTAVAIL;
+					goto out;
+				}
+			}
+			if (dev)
+				dev_put(dev);
+		}
+	}
+
+	inet->rcv_saddr = v4addr;
+	inet->saddr = v4addr;
+
+	ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+		
+	if (!(addr_type & IPV6_ADDR_MULTICAST))
+		ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+
+	/* Make sure we are allowed to bind here. */
+	if (sk->sk_prot->get_port(sk, snum)) {
+		inet_reset_saddr(sk);
+		err = -EADDRINUSE;
+		goto out;
+	}
+
+	if (addr_type != IPV6_ADDR_ANY)
+		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+	if (snum)
+		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
+	inet->sport = ntohs(inet->num);
+	inet->dport = 0;
+	inet->daddr = 0;
+out:
+	release_sock(sk);
+	return err;
+}
+
+int inet6_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (sk == NULL)
+		return -EINVAL;
+
+	/* Free mc lists */
+	ipv6_sock_mc_close(sk);
+
+	/* Free ac lists */
+	ipv6_sock_ac_close(sk);
+
+	return inet_release(sock);
+}
+
+int inet6_destroy_sock(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sk_buff *skb;
+	struct ipv6_txoptions *opt;
+
+	/*
+	 *	Release destination entry
+	 */
+
+	sk_dst_reset(sk);
+
+	/* Release rx options */
+
+	if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
+		kfree_skb(skb);
+
+	/* Free flowlabels */
+	fl6_free_socklist(sk);
+
+	/* Free tx options */
+
+	if ((opt = xchg(&np->opt, NULL)) != NULL)
+		sock_kfree_s(sk, opt, opt->tot_len);
+
+	return 0;
+}
+
+/*
+ *	This does both peername and sockname.
+ */
+ 
+int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
+		 int *uaddr_len, int peer)
+{
+	struct sockaddr_in6 *sin=(struct sockaddr_in6 *)uaddr;
+	struct sock *sk = sock->sk;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+  
+	sin->sin6_family = AF_INET6;
+	sin->sin6_flowinfo = 0;
+	sin->sin6_scope_id = 0;
+	if (peer) {
+		if (!inet->dport)
+			return -ENOTCONN;
+		if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
+		    peer == 1)
+			return -ENOTCONN;
+		sin->sin6_port = inet->dport;
+		ipv6_addr_copy(&sin->sin6_addr, &np->daddr);
+		if (np->sndflow)
+			sin->sin6_flowinfo = np->flow_label;
+	} else {
+		if (ipv6_addr_any(&np->rcv_saddr))
+			ipv6_addr_copy(&sin->sin6_addr, &np->saddr);
+		else
+			ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr);
+
+		sin->sin6_port = inet->sport;
+	}
+	if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
+		sin->sin6_scope_id = sk->sk_bound_dev_if;
+	*uaddr_len = sizeof(*sin);
+	return(0);
+}
+
+int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	struct sock *sk = sock->sk;
+	int err = -EINVAL;
+
+	switch(cmd) 
+	{
+	case SIOCGSTAMP:
+		return sock_get_timestamp(sk, (struct timeval __user *)arg);
+
+	case SIOCADDRT:
+	case SIOCDELRT:
+	  
+		return(ipv6_route_ioctl(cmd,(void __user *)arg));
+
+	case SIOCSIFADDR:
+		return addrconf_add_ifaddr((void __user *) arg);
+	case SIOCDIFADDR:
+		return addrconf_del_ifaddr((void __user *) arg);
+	case SIOCSIFDSTADDR:
+		return addrconf_set_dstaddr((void __user *) arg);
+	default:
+		if (!sk->sk_prot->ioctl ||
+		    (err = sk->sk_prot->ioctl(sk, cmd, arg)) == -ENOIOCTLCMD)
+			return(dev_ioctl(cmd,(void __user *) arg));		
+		return err;
+	}
+	/*NOTREACHED*/
+	return(0);
+}
+
+struct proto_ops inet6_stream_ops = {
+	.family =	PF_INET6,
+	.owner =	THIS_MODULE,
+	.release =	inet6_release,
+	.bind =		inet6_bind,
+	.connect =	inet_stream_connect,		/* ok		*/
+	.socketpair =	sock_no_socketpair,		/* a do nothing	*/
+	.accept =	inet_accept,			/* ok		*/
+	.getname =	inet6_getname, 
+	.poll =		tcp_poll,			/* ok		*/
+	.ioctl =	inet6_ioctl,			/* must change  */
+	.listen =	inet_listen,			/* ok		*/
+	.shutdown =	inet_shutdown,			/* ok		*/
+	.setsockopt =	sock_common_setsockopt,		/* ok		*/
+	.getsockopt =	sock_common_getsockopt,		/* ok		*/
+	.sendmsg =	inet_sendmsg,			/* ok		*/
+	.recvmsg =	sock_common_recvmsg,		/* ok		*/
+	.mmap =		sock_no_mmap,
+	.sendpage =	tcp_sendpage
+};
+
+struct proto_ops inet6_dgram_ops = {
+	.family =	PF_INET6,
+	.owner =	THIS_MODULE,
+	.release =	inet6_release,
+	.bind =		inet6_bind,
+	.connect =	inet_dgram_connect,		/* ok		*/
+	.socketpair =	sock_no_socketpair,		/* a do nothing	*/
+	.accept =	sock_no_accept,			/* a do nothing	*/
+	.getname =	inet6_getname, 
+	.poll =		udp_poll,			/* ok		*/
+	.ioctl =	inet6_ioctl,			/* must change  */
+	.listen =	sock_no_listen,			/* ok		*/
+	.shutdown =	inet_shutdown,			/* ok		*/
+	.setsockopt =	sock_common_setsockopt,		/* ok		*/
+	.getsockopt =	sock_common_getsockopt,		/* ok		*/
+	.sendmsg =	inet_sendmsg,			/* ok		*/
+	.recvmsg =	sock_common_recvmsg,		/* ok		*/
+	.mmap =		sock_no_mmap,
+	.sendpage =	sock_no_sendpage,
+};
+
+static struct net_proto_family inet6_family_ops = {
+	.family = PF_INET6,
+	.create = inet6_create,
+	.owner	= THIS_MODULE,
+};
+
+#ifdef CONFIG_SYSCTL
+extern void ipv6_sysctl_register(void);
+extern void ipv6_sysctl_unregister(void);
+#endif
+
+/* Same as inet6_dgram_ops, sans udp_poll.  */
+static struct proto_ops inet6_sockraw_ops = {
+	.family =	PF_INET6,
+	.owner =	THIS_MODULE,
+	.release =	inet6_release,
+	.bind =		inet6_bind,
+	.connect =	inet_dgram_connect,		/* ok		*/
+	.socketpair =	sock_no_socketpair,		/* a do nothing	*/
+	.accept =	sock_no_accept,			/* a do nothing	*/
+	.getname =	inet6_getname, 
+	.poll =		datagram_poll,			/* ok		*/
+	.ioctl =	inet6_ioctl,			/* must change  */
+	.listen =	sock_no_listen,			/* ok		*/
+	.shutdown =	inet_shutdown,			/* ok		*/
+	.setsockopt =	sock_common_setsockopt,		/* ok		*/
+	.getsockopt =	sock_common_getsockopt,		/* ok		*/
+	.sendmsg =	inet_sendmsg,			/* ok		*/
+	.recvmsg =	sock_common_recvmsg,		/* ok		*/
+	.mmap =		sock_no_mmap,
+	.sendpage =	sock_no_sendpage,
+};
+
+static struct inet_protosw rawv6_protosw = {
+	.type		= SOCK_RAW,
+	.protocol	= IPPROTO_IP,	/* wild card */
+	.prot		= &rawv6_prot,
+	.ops		= &inet6_sockraw_ops,
+	.capability	= CAP_NET_RAW,
+	.no_check	= UDP_CSUM_DEFAULT,
+	.flags		= INET_PROTOSW_REUSE,
+};
+
+void
+inet6_register_protosw(struct inet_protosw *p)
+{
+	struct list_head *lh;
+	struct inet_protosw *answer;
+	int protocol = p->protocol;
+	struct list_head *last_perm;
+
+	spin_lock_bh(&inetsw6_lock);
+
+	if (p->type >= SOCK_MAX)
+		goto out_illegal;
+
+	/* If we are trying to override a permanent protocol, bail. */
+	answer = NULL;
+	last_perm = &inetsw6[p->type];
+	list_for_each(lh, &inetsw6[p->type]) {
+		answer = list_entry(lh, struct inet_protosw, list);
+
+		/* Check only the non-wild match. */
+		if (INET_PROTOSW_PERMANENT & answer->flags) {
+			if (protocol == answer->protocol)
+				break;
+			last_perm = lh;
+		}
+
+		answer = NULL;
+	}
+	if (answer)
+		goto out_permanent;
+
+	/* Add the new entry after the last permanent entry if any, so that
+	 * the new entry does not override a permanent entry when matched with
+	 * a wild-card protocol. But it is allowed to override any existing
+	 * non-permanent entry.  This means that when we remove this entry, the 
+	 * system automatically returns to the old behavior.
+	 */
+	list_add_rcu(&p->list, last_perm);
+out:
+	spin_unlock_bh(&inetsw6_lock);
+	return;
+
+out_permanent:
+	printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
+	       protocol);
+	goto out;
+
+out_illegal:
+	printk(KERN_ERR
+	       "Ignoring attempt to register invalid socket type %d.\n",
+	       p->type);
+	goto out;
+}
+
+void
+inet6_unregister_protosw(struct inet_protosw *p)
+{
+	if (INET_PROTOSW_PERMANENT & p->flags) {
+		printk(KERN_ERR
+		       "Attempt to unregister permanent protocol %d.\n",
+		       p->protocol);
+	} else {
+		spin_lock_bh(&inetsw6_lock);
+		list_del_rcu(&p->list);
+		spin_unlock_bh(&inetsw6_lock);
+
+		synchronize_net();
+	}
+}
+
+int
+snmp6_mib_init(void *ptr[2], size_t mibsize, size_t mibalign)
+{
+	if (ptr == NULL)
+		return -EINVAL;
+
+	ptr[0] = __alloc_percpu(mibsize, mibalign);
+	if (!ptr[0])
+		goto err0;
+
+	ptr[1] = __alloc_percpu(mibsize, mibalign);
+	if (!ptr[1])
+		goto err1;
+
+	return 0;
+
+err1:
+	free_percpu(ptr[0]);
+	ptr[0] = NULL;
+err0:
+	return -ENOMEM;
+}
+
+void
+snmp6_mib_free(void *ptr[2])
+{
+	if (ptr == NULL)
+		return;
+	if (ptr[0])
+		free_percpu(ptr[0]);
+	if (ptr[1])
+		free_percpu(ptr[1]);
+	ptr[0] = ptr[1] = NULL;
+}
+
+static int __init init_ipv6_mibs(void)
+{
+	if (snmp6_mib_init((void **)ipv6_statistics, sizeof (struct ipstats_mib),
+			   __alignof__(struct ipstats_mib)) < 0)
+		goto err_ip_mib;
+	if (snmp6_mib_init((void **)icmpv6_statistics, sizeof (struct icmpv6_mib),
+			   __alignof__(struct icmpv6_mib)) < 0)
+		goto err_icmp_mib;
+	if (snmp6_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib),
+			   __alignof__(struct udp_mib)) < 0)
+		goto err_udp_mib;
+	return 0;
+
+err_udp_mib:
+	snmp6_mib_free((void **)icmpv6_statistics);
+err_icmp_mib:
+	snmp6_mib_free((void **)ipv6_statistics);
+err_ip_mib:
+	return -ENOMEM;
+	
+}
+
+static void cleanup_ipv6_mibs(void)
+{
+	snmp6_mib_free((void **)ipv6_statistics);
+	snmp6_mib_free((void **)icmpv6_statistics);
+	snmp6_mib_free((void **)udp_stats_in6);
+}
+
+extern int ipv6_misc_proc_init(void);
+
+static int __init inet6_init(void)
+{
+	struct sk_buff *dummy_skb;
+        struct list_head *r;
+	int err;
+
+#ifdef MODULE
+#if 0 /* FIXME --RR */
+	if (!mod_member_present(&__this_module, can_unload))
+	  return -EINVAL;
+
+	__this_module.can_unload = &ipv6_unload;
+#endif
+#endif
+
+	if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)) {
+		printk(KERN_CRIT "inet6_proto_init: size fault\n");
+		return -EINVAL;
+	}
+
+	err = proto_register(&tcpv6_prot, 1);
+	if (err)
+		goto out;
+
+	err = proto_register(&udpv6_prot, 1);
+	if (err)
+		goto out_unregister_tcp_proto;
+
+	err = proto_register(&rawv6_prot, 1);
+	if (err)
+		goto out_unregister_udp_proto;
+
+
+	/* Register the socket-side information for inet6_create.  */
+	for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
+		INIT_LIST_HEAD(r);
+
+	/* We MUST register RAW sockets before we create the ICMP6,
+	 * IGMP6, or NDISC control sockets.
+	 */
+	inet6_register_protosw(&rawv6_protosw);
+
+	/* Register the family here so that the init calls below will
+	 * be able to create sockets. (?? is this dangerous ??)
+	 */
+	(void) sock_register(&inet6_family_ops);
+
+	/* Initialise ipv6 mibs */
+	err = init_ipv6_mibs();
+	if (err)
+		goto out_unregister_raw_proto;
+	
+	/*
+	 *	ipngwg API draft makes clear that the correct semantics
+	 *	for TCP and UDP is to consider one TCP and UDP instance
+	 *	in a host availiable by both INET and INET6 APIs and
+	 *	able to communicate via both network protocols.
+	 */
+
+#ifdef CONFIG_SYSCTL
+	ipv6_sysctl_register();
+#endif
+	err = icmpv6_init(&inet6_family_ops);
+	if (err)
+		goto icmp_fail;
+	err = ndisc_init(&inet6_family_ops);
+	if (err)
+		goto ndisc_fail;
+	err = igmp6_init(&inet6_family_ops);
+	if (err)
+		goto igmp_fail;
+	/* Create /proc/foo6 entries. */
+#ifdef CONFIG_PROC_FS
+	err = -ENOMEM;
+	if (raw6_proc_init())
+		goto proc_raw6_fail;
+	if (tcp6_proc_init())
+		goto proc_tcp6_fail;
+	if (udp6_proc_init())
+		goto proc_udp6_fail;
+	if (ipv6_misc_proc_init())
+		goto proc_misc6_fail;
+
+	if (ac6_proc_init())
+		goto proc_anycast6_fail;
+	if (if6_proc_init())
+		goto proc_if6_fail;
+#endif
+	ipv6_packet_init();
+	ip6_route_init();
+	ip6_flowlabel_init();
+	err = addrconf_init();
+	if (err)
+		goto addrconf_fail;
+	sit_init();
+
+	/* Init v6 extension headers. */
+	ipv6_rthdr_init();
+	ipv6_frag_init();
+	ipv6_nodata_init();
+	ipv6_destopt_init();
+
+	/* Init v6 transport protocols. */
+	udpv6_init();
+	tcpv6_init();
+	err = 0;
+out:
+	return err;
+
+addrconf_fail:
+	ip6_flowlabel_cleanup();
+	ip6_route_cleanup();
+	ipv6_packet_cleanup();
+#ifdef CONFIG_PROC_FS
+	if6_proc_exit();
+proc_if6_fail:
+	ac6_proc_exit();
+proc_anycast6_fail:
+	ipv6_misc_proc_exit();
+proc_misc6_fail:
+	udp6_proc_exit();
+proc_udp6_fail:
+	tcp6_proc_exit();
+proc_tcp6_fail:
+	raw6_proc_exit();
+proc_raw6_fail:
+#endif
+	igmp6_cleanup();
+igmp_fail:
+	ndisc_cleanup();
+ndisc_fail:
+	icmpv6_cleanup();
+icmp_fail:
+#ifdef CONFIG_SYSCTL
+	ipv6_sysctl_unregister();
+#endif
+	cleanup_ipv6_mibs();
+out_unregister_raw_proto:
+	proto_unregister(&rawv6_prot);
+out_unregister_udp_proto:
+	proto_unregister(&udpv6_prot);
+out_unregister_tcp_proto:
+	proto_unregister(&tcpv6_prot);
+	goto out;
+}
+module_init(inet6_init);
+
+static void __exit inet6_exit(void)
+{
+	/* First of all disallow new sockets creation. */
+	sock_unregister(PF_INET6);
+#ifdef CONFIG_PROC_FS
+	if6_proc_exit();
+	ac6_proc_exit();
+ 	ipv6_misc_proc_exit();
+ 	udp6_proc_exit();
+ 	tcp6_proc_exit();
+ 	raw6_proc_exit();
+#endif
+	/* Cleanup code parts. */
+	sit_cleanup();
+	ip6_flowlabel_cleanup();
+	addrconf_cleanup();
+	ip6_route_cleanup();
+	ipv6_packet_cleanup();
+	igmp6_cleanup();
+	ndisc_cleanup();
+	icmpv6_cleanup();
+#ifdef CONFIG_SYSCTL
+	ipv6_sysctl_unregister();	
+#endif
+	cleanup_ipv6_mibs();
+	proto_unregister(&rawv6_prot);
+	proto_unregister(&udpv6_prot);
+	proto_unregister(&tcpv6_prot);
+}
+module_exit(inet6_exit);
+
+MODULE_ALIAS_NETPROTO(PF_INET6);

net/ipv6/ah6.c

@@ -0,0 +1,478 @@
+/*
+ * Copyright (C)2002 USAGI/WIDE Project
+ * 
+ * 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.
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Authors
+ *
+ *	Mitsuru KANDA @USAGI       : IPv6 Support 
+ * 	Kazunori MIYAZAWA @USAGI   :
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 	
+ * 	This file is derived from net/ipv4/ah.c.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/ah.h>
+#include <linux/crypto.h>
+#include <linux/pfkeyv2.h>
+#include <linux/string.h>
+#include <net/icmp.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+#include <asm/scatterlist.h>
+
+static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr)
+{
+	u8 *opt = (u8 *)opthdr;
+	int len = ipv6_optlen(opthdr);
+	int off = 0;
+	int optlen = 0;
+
+	off += 2;
+	len -= 2;
+
+	while (len > 0) {
+
+		switch (opt[off]) {
+
+		case IPV6_TLV_PAD0:
+			optlen = 1;
+			break;
+		default:
+			if (len < 2) 
+				goto bad;
+			optlen = opt[off+1]+2;
+			if (len < optlen)
+				goto bad;
+			if (opt[off] & 0x20)
+				memset(&opt[off+2], 0, opt[off+1]);
+			break;
+		}
+
+		off += optlen;
+		len -= optlen;
+	}
+	if (len == 0)
+		return 1;
+
+bad:
+	return 0;
+}
+
+/**
+ *	ipv6_rearrange_rthdr - rearrange IPv6 routing header
+ *	@iph: IPv6 header
+ *	@rthdr: routing header
+ *
+ *	Rearrange the destination address in @iph and the addresses in @rthdr
+ *	so that they appear in the order they will at the final destination.
+ *	See Appendix A2 of RFC 2402 for details.
+ */
+static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
+{
+	int segments, segments_left;
+	struct in6_addr *addrs;
+	struct in6_addr final_addr;
+
+	segments_left = rthdr->segments_left;
+	if (segments_left == 0)
+		return;
+	rthdr->segments_left = 0; 
+
+	/* The value of rthdr->hdrlen has been verified either by the system
+	 * call if it is locally generated, or by ipv6_rthdr_rcv() for incoming
+	 * packets.  So we can assume that it is even and that segments is
+	 * greater than or equal to segments_left.
+	 *
+	 * For the same reason we can assume that this option is of type 0.
+	 */
+	segments = rthdr->hdrlen >> 1;
+
+	addrs = ((struct rt0_hdr *)rthdr)->addr;
+	ipv6_addr_copy(&final_addr, addrs + segments - 1);
+
+	addrs += segments - segments_left;
+	memmove(addrs + 1, addrs, (segments_left - 1) * sizeof(*addrs));
+
+	ipv6_addr_copy(addrs, &iph->daddr);
+	ipv6_addr_copy(&iph->daddr, &final_addr);
+}
+
+static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len)
+{
+	union {
+		struct ipv6hdr *iph;
+		struct ipv6_opt_hdr *opth;
+		struct ipv6_rt_hdr *rth;
+		char *raw;
+	} exthdr = { .iph = iph };
+	char *end = exthdr.raw + len;
+	int nexthdr = iph->nexthdr;
+
+	exthdr.iph++;
+
+	while (exthdr.raw < end) {
+		switch (nexthdr) {
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			if (!zero_out_mutable_opts(exthdr.opth)) {
+				LIMIT_NETDEBUG(printk(
+					KERN_WARNING "overrun %sopts\n",
+					nexthdr == NEXTHDR_HOP ?
+						"hop" : "dest"));
+				return -EINVAL;
+			}
+			break;
+
+		case NEXTHDR_ROUTING:
+			ipv6_rearrange_rthdr(iph, exthdr.rth);
+			break;
+
+		default :
+			return 0;
+		}
+
+		nexthdr = exthdr.opth->nexthdr;
+		exthdr.raw += ipv6_optlen(exthdr.opth);
+	}
+
+	return 0;
+}
+
+static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+	int extlen;
+	struct ipv6hdr *top_iph;
+	struct ip_auth_hdr *ah;
+	struct ah_data *ahp;
+	u8 nexthdr;
+	char tmp_base[8];
+	struct {
+		struct in6_addr daddr;
+		char hdrs[0];
+	} *tmp_ext;
+
+	top_iph = (struct ipv6hdr *)skb->data;
+	top_iph->payload_len = htons(skb->len - sizeof(*top_iph));
+
+	nexthdr = *skb->nh.raw;
+	*skb->nh.raw = IPPROTO_AH;
+
+	/* When there are no extension headers, we only need to save the first
+	 * 8 bytes of the base IP header.
+	 */
+	memcpy(tmp_base, top_iph, sizeof(tmp_base));
+
+	tmp_ext = NULL;
+	extlen = skb->h.raw - (unsigned char *)(top_iph + 1);
+	if (extlen) {
+		extlen += sizeof(*tmp_ext);
+		tmp_ext = kmalloc(extlen, GFP_ATOMIC);
+		if (!tmp_ext) {
+			err = -ENOMEM;
+			goto error;
+		}
+		memcpy(tmp_ext, &top_iph->daddr, extlen);
+		err = ipv6_clear_mutable_options(top_iph,
+						 extlen - sizeof(*tmp_ext) +
+						 sizeof(*top_iph));
+		if (err)
+			goto error_free_iph;
+	}
+
+	ah = (struct ip_auth_hdr *)skb->h.raw;
+	ah->nexthdr = nexthdr;
+
+	top_iph->priority    = 0;
+	top_iph->flow_lbl[0] = 0;
+	top_iph->flow_lbl[1] = 0;
+	top_iph->flow_lbl[2] = 0;
+	top_iph->hop_limit   = 0;
+
+	ahp = x->data;
+	ah->hdrlen  = (XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + 
+				   ahp->icv_trunc_len) >> 2) - 2;
+
+	ah->reserved = 0;
+	ah->spi = x->id.spi;
+	ah->seq_no = htonl(++x->replay.oseq);
+	ahp->icv(ahp, skb, ah->auth_data);
+
+	err = 0;
+
+	memcpy(top_iph, tmp_base, sizeof(tmp_base));
+	if (tmp_ext) {
+		memcpy(&top_iph->daddr, tmp_ext, extlen);
+error_free_iph:
+		kfree(tmp_ext);
+	}
+
+error:
+	return err;
+}
+
+static int ah6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
+{
+	/*
+	 * Before process AH
+	 * [IPv6][Ext1][Ext2][AH][Dest][Payload]
+	 * |<-------------->| hdr_len
+	 *
+	 * To erase AH:
+	 * Keeping copy of cleared headers. After AH processing,
+	 * Moving the pointer of skb->nh.raw by using skb_pull as long as AH
+	 * header length. Then copy back the copy as long as hdr_len
+	 * If destination header following AH exists, copy it into after [Ext2].
+	 * 
+	 * |<>|[IPv6][Ext1][Ext2][Dest][Payload]
+	 * There is offset of AH before IPv6 header after the process.
+	 */
+
+	struct ipv6_auth_hdr *ah;
+	struct ah_data *ahp;
+	unsigned char *tmp_hdr = NULL;
+	u16 hdr_len;
+	u16 ah_hlen;
+	int nexthdr;
+
+	if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr)))
+		goto out;
+
+	/* We are going to _remove_ AH header to keep sockets happy,
+	 * so... Later this can change. */
+	if (skb_cloned(skb) &&
+	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		goto out;
+
+	hdr_len = skb->data - skb->nh.raw;
+	ah = (struct ipv6_auth_hdr*)skb->data;
+	ahp = x->data;
+	nexthdr = ah->nexthdr;
+	ah_hlen = (ah->hdrlen + 2) << 2;
+
+        if (ah_hlen != XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_full_len) &&
+            ah_hlen != XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len))
+                goto out;
+
+	if (!pskb_may_pull(skb, ah_hlen))
+		goto out;
+
+	tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC);
+	if (!tmp_hdr)
+		goto out;
+	memcpy(tmp_hdr, skb->nh.raw, hdr_len);
+	if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len))
+		goto out;
+	skb->nh.ipv6h->priority    = 0;
+	skb->nh.ipv6h->flow_lbl[0] = 0;
+	skb->nh.ipv6h->flow_lbl[1] = 0;
+	skb->nh.ipv6h->flow_lbl[2] = 0;
+	skb->nh.ipv6h->hop_limit   = 0;
+
+        {
+		u8 auth_data[MAX_AH_AUTH_LEN];
+
+		memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
+		memset(ah->auth_data, 0, ahp->icv_trunc_len);
+		skb_push(skb, skb->data - skb->nh.raw);
+		ahp->icv(ahp, skb, ah->auth_data);
+		if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) {
+			LIMIT_NETDEBUG(
+				printk(KERN_WARNING "ipsec ah authentication error\n"));
+			x->stats.integrity_failed++;
+			goto free_out;
+		}
+	}
+
+	skb->nh.raw = skb_pull(skb, ah_hlen);
+	memcpy(skb->nh.raw, tmp_hdr, hdr_len);
+	skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+	skb_pull(skb, hdr_len);
+	skb->h.raw = skb->data;
+
+
+	kfree(tmp_hdr);
+
+	return nexthdr;
+
+free_out:
+	kfree(tmp_hdr);
+out:
+	return -EINVAL;
+}
+
+static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, 
+                    int type, int code, int offset, __u32 info)
+{
+	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
+	struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset);
+	struct xfrm_state *x;
+
+	if (type != ICMPV6_DEST_UNREACH &&
+	    type != ICMPV6_PKT_TOOBIG)
+		return;
+
+	x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
+	if (!x)
+		return;
+
+	NETDEBUG(printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/"
+			"%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n",
+	       ntohl(ah->spi), NIP6(iph->daddr)));
+
+	xfrm_state_put(x);
+}
+
+static int ah6_init_state(struct xfrm_state *x, void *args)
+{
+	struct ah_data *ahp = NULL;
+	struct xfrm_algo_desc *aalg_desc;
+
+	if (!x->aalg)
+		goto error;
+
+	/* null auth can use a zero length key */
+	if (x->aalg->alg_key_len > 512)
+		goto error;
+
+	if (x->encap)
+		goto error;
+
+	ahp = kmalloc(sizeof(*ahp), GFP_KERNEL);
+	if (ahp == NULL)
+		return -ENOMEM;
+
+	memset(ahp, 0, sizeof(*ahp));
+
+	ahp->key = x->aalg->alg_key;
+	ahp->key_len = (x->aalg->alg_key_len+7)/8;
+	ahp->tfm = crypto_alloc_tfm(x->aalg->alg_name, 0);
+	if (!ahp->tfm)
+		goto error;
+	ahp->icv = ah_hmac_digest;
+	
+	/*
+	 * Lookup the algorithm description maintained by xfrm_algo,
+	 * verify crypto transform properties, and store information
+	 * we need for AH processing.  This lookup cannot fail here
+	 * after a successful crypto_alloc_tfm().
+	 */
+	aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
+	BUG_ON(!aalg_desc);
+
+	if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
+	    crypto_tfm_alg_digestsize(ahp->tfm)) {
+		printk(KERN_INFO "AH: %s digestsize %u != %hu\n",
+		       x->aalg->alg_name, crypto_tfm_alg_digestsize(ahp->tfm),
+		       aalg_desc->uinfo.auth.icv_fullbits/8);
+		goto error;
+	}
+	
+	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
+	ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8;
+	
+	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
+	
+	ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL);
+	if (!ahp->work_icv)
+		goto error;
+	
+	x->props.header_len = XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len);
+	if (x->props.mode)
+		x->props.header_len += sizeof(struct ipv6hdr);
+	x->data = ahp;
+
+	return 0;
+
+error:
+	if (ahp) {
+		if (ahp->work_icv)
+			kfree(ahp->work_icv);
+		if (ahp->tfm)
+			crypto_free_tfm(ahp->tfm);
+		kfree(ahp);
+	}
+	return -EINVAL;
+}
+
+static void ah6_destroy(struct xfrm_state *x)
+{
+	struct ah_data *ahp = x->data;
+
+	if (!ahp)
+		return;
+
+	if (ahp->work_icv) {
+		kfree(ahp->work_icv);
+		ahp->work_icv = NULL;
+	}
+	if (ahp->tfm) {
+		crypto_free_tfm(ahp->tfm);
+		ahp->tfm = NULL;
+	}
+	kfree(ahp);
+}
+
+static struct xfrm_type ah6_type =
+{
+	.description	= "AH6",
+	.owner		= THIS_MODULE,
+	.proto	     	= IPPROTO_AH,
+	.init_state	= ah6_init_state,
+	.destructor	= ah6_destroy,
+	.input		= ah6_input,
+	.output		= ah6_output
+};
+
+static struct inet6_protocol ah6_protocol = {
+	.handler	=	xfrm6_rcv,
+	.err_handler	=	ah6_err,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+static int __init ah6_init(void)
+{
+	if (xfrm_register_type(&ah6_type, AF_INET6) < 0) {
+		printk(KERN_INFO "ipv6 ah init: can't add xfrm type\n");
+		return -EAGAIN;
+	}
+
+	if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) {
+		printk(KERN_INFO "ipv6 ah init: can't add protocol\n");
+		xfrm_unregister_type(&ah6_type, AF_INET6);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+static void __exit ah6_fini(void)
+{
+	if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0)
+		printk(KERN_INFO "ipv6 ah close: can't remove protocol\n");
+
+	if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0)
+		printk(KERN_INFO "ipv6 ah close: can't remove xfrm type\n");
+
+}
+
+module_init(ah6_init);
+module_exit(ah6_fini);
+
+MODULE_LICENSE("GPL");

net/ipv6/anycast.c

@@ -0,0 +1,594 @@
+/*
+ *	Anycast support for IPv6
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	David L Stevens (dlstevens@us.ibm.com)
+ *
+ *	based heavily on net/ipv6/mcast.c
+ *
+ *	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.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/route.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/if_inet6.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+
+#include <net/checksum.h>
+
+static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr);
+
+/* Big ac list lock for all the sockets */
+static DEFINE_RWLOCK(ipv6_sk_ac_lock);
+
+static int
+ip6_onlink(struct in6_addr *addr, struct net_device *dev)
+{
+	struct inet6_dev	*idev;
+	struct inet6_ifaddr	*ifa;
+	int	onlink;
+
+	onlink = 0;
+	read_lock(&addrconf_lock);
+	idev = __in6_dev_get(dev);
+	if (idev) {
+		read_lock_bh(&idev->lock);
+		for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) {
+			onlink = ipv6_prefix_equal(addr, &ifa->addr,
+						   ifa->prefix_len);
+			if (onlink)
+				break;
+		}
+		read_unlock_bh(&idev->lock);
+	}
+	read_unlock(&addrconf_lock);
+	return onlink;
+}
+
+/*
+ *	socket join an anycast group
+ */
+
+int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev = NULL;
+	struct inet6_dev *idev;
+	struct ipv6_ac_socklist *pac;
+	int	ishost = !ipv6_devconf.forwarding;
+	int	err = 0;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+	if (ipv6_addr_is_multicast(addr))
+		return -EINVAL;
+	if (ipv6_chk_addr(addr, NULL, 0))
+		return -EINVAL;
+
+	pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);
+	if (pac == NULL)
+		return -ENOMEM;
+	pac->acl_next = NULL;
+	ipv6_addr_copy(&pac->acl_addr, addr);
+
+	if (ifindex == 0) {
+		struct rt6_info *rt;
+
+		rt = rt6_lookup(addr, NULL, 0, 0);
+		if (rt) {
+			dev = rt->rt6i_dev;
+			dev_hold(dev);
+			dst_release(&rt->u.dst);
+		} else if (ishost) {
+			err = -EADDRNOTAVAIL;
+			goto out_free_pac;
+		} else {
+			/* router, no matching interface: just pick one */
+
+			dev = dev_get_by_flags(IFF_UP, IFF_UP|IFF_LOOPBACK);
+		}
+	} else
+		dev = dev_get_by_index(ifindex);
+
+	if (dev == NULL) {
+		err = -ENODEV;
+		goto out_free_pac;
+	}
+
+	idev = in6_dev_get(dev);
+	if (!idev) {
+		if (ifindex)
+			err = -ENODEV;
+		else
+			err = -EADDRNOTAVAIL;
+		goto out_dev_put;
+	}
+	/* reset ishost, now that we have a specific device */
+	ishost = !idev->cnf.forwarding;
+	in6_dev_put(idev);
+
+	pac->acl_ifindex = dev->ifindex;
+
+	/* XXX
+	 * For hosts, allow link-local or matching prefix anycasts.
+	 * This obviates the need for propagating anycast routes while
+	 * still allowing some non-router anycast participation.
+	 */
+	if (!ip6_onlink(addr, dev)) {
+		if (ishost)
+			err = -EADDRNOTAVAIL;
+		if (err)
+			goto out_dev_put;
+	}
+
+	err = ipv6_dev_ac_inc(dev, addr);
+	if (err)
+		goto out_dev_put;
+
+	write_lock_bh(&ipv6_sk_ac_lock);
+	pac->acl_next = np->ipv6_ac_list;
+	np->ipv6_ac_list = pac;
+	write_unlock_bh(&ipv6_sk_ac_lock);
+
+	dev_put(dev);
+
+	return 0;
+
+out_dev_put:
+	dev_put(dev);
+out_free_pac:
+	sock_kfree_s(sk, pac, sizeof(*pac));
+	return err;
+}
+
+/*
+ *	socket leave an anycast group
+ */
+int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev;
+	struct ipv6_ac_socklist *pac, *prev_pac;
+
+	write_lock_bh(&ipv6_sk_ac_lock);
+	prev_pac = NULL;
+	for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
+		if ((ifindex == 0 || pac->acl_ifindex == ifindex) &&
+		     ipv6_addr_equal(&pac->acl_addr, addr))
+			break;
+		prev_pac = pac;
+	}
+	if (!pac) {
+		write_unlock_bh(&ipv6_sk_ac_lock);
+		return -ENOENT;
+	}
+	if (prev_pac)
+		prev_pac->acl_next = pac->acl_next;
+	else
+		np->ipv6_ac_list = pac->acl_next;
+
+	write_unlock_bh(&ipv6_sk_ac_lock);
+
+	dev = dev_get_by_index(pac->acl_ifindex);
+	if (dev) {
+		ipv6_dev_ac_dec(dev, &pac->acl_addr);
+		dev_put(dev);
+	}
+	sock_kfree_s(sk, pac, sizeof(*pac));
+	return 0;
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev = NULL;
+	struct ipv6_ac_socklist *pac;
+	int	prev_index;
+
+	write_lock_bh(&ipv6_sk_ac_lock);
+	pac = np->ipv6_ac_list;
+	np->ipv6_ac_list = NULL;
+	write_unlock_bh(&ipv6_sk_ac_lock);
+
+	prev_index = 0;
+	while (pac) {
+		struct ipv6_ac_socklist *next = pac->acl_next;
+
+		if (pac->acl_ifindex != prev_index) {
+			if (dev)
+				dev_put(dev);
+			dev = dev_get_by_index(pac->acl_ifindex);
+			prev_index = pac->acl_ifindex;
+		}
+		if (dev)
+			ipv6_dev_ac_dec(dev, &pac->acl_addr);
+		sock_kfree_s(sk, pac, sizeof(*pac));
+		pac = next;
+	}
+	if (dev)
+		dev_put(dev);
+}
+
+#if 0
+/* The function is not used, which is funny. Apparently, author
+ * supposed to use it to filter out datagrams inside udp/raw but forgot.
+ *
+ * It is OK, anycasts are not special comparing to delivery to unicasts.
+ */
+
+int inet6_ac_check(struct sock *sk, struct in6_addr *addr, int ifindex)
+{
+	struct ipv6_ac_socklist *pac;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	int	found;
+
+	found = 0;
+	read_lock(&ipv6_sk_ac_lock);
+	for (pac=np->ipv6_ac_list; pac; pac=pac->acl_next) {
+		if (ifindex && pac->acl_ifindex != ifindex)
+			continue;
+		found = ipv6_addr_equal(&pac->acl_addr, addr);
+		if (found)
+			break;
+	}
+	read_unlock(&ipv6_sk_ac_lock);
+
+	return found;
+}
+
+#endif
+
+static void aca_put(struct ifacaddr6 *ac)
+{
+	if (atomic_dec_and_test(&ac->aca_refcnt)) {
+		in6_dev_put(ac->aca_idev);
+		dst_release(&ac->aca_rt->u.dst);
+		kfree(ac);
+	}
+}
+
+/*
+ *	device anycast group inc (add if not found)
+ */
+int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr)
+{
+	struct ifacaddr6 *aca;
+	struct inet6_dev *idev;
+	struct rt6_info *rt;
+	int err;
+
+	idev = in6_dev_get(dev);
+
+	if (idev == NULL)
+		return -EINVAL;
+
+	write_lock_bh(&idev->lock);
+	if (idev->dead) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+		if (ipv6_addr_equal(&aca->aca_addr, addr)) {
+			aca->aca_users++;
+			err = 0;
+			goto out;
+		}
+	}
+
+	/*
+	 *	not found: create a new one.
+	 */
+
+	aca = kmalloc(sizeof(struct ifacaddr6), GFP_ATOMIC);
+
+	if (aca == NULL) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	rt = addrconf_dst_alloc(idev, addr, 1);
+	if (IS_ERR(rt)) {
+		kfree(aca);
+		err = PTR_ERR(rt);
+		goto out;
+	}
+
+	memset(aca, 0, sizeof(struct ifacaddr6));
+
+	ipv6_addr_copy(&aca->aca_addr, addr);
+	aca->aca_idev = idev;
+	aca->aca_rt = rt;
+	aca->aca_users = 1;
+	/* aca_tstamp should be updated upon changes */
+	aca->aca_cstamp = aca->aca_tstamp = jiffies;
+	atomic_set(&aca->aca_refcnt, 2);
+	spin_lock_init(&aca->aca_lock);
+
+	aca->aca_next = idev->ac_list;
+	idev->ac_list = aca;
+	write_unlock_bh(&idev->lock);
+
+	dst_hold(&rt->u.dst);
+	if (ip6_ins_rt(rt, NULL, NULL))
+		dst_release(&rt->u.dst);
+
+	addrconf_join_solict(dev, &aca->aca_addr);
+
+	aca_put(aca);
+	return 0;
+out:
+	write_unlock_bh(&idev->lock);
+	in6_dev_put(idev);
+	return err;
+}
+
+/*
+ *	device anycast group decrement
+ */
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr)
+{
+	struct ifacaddr6 *aca, *prev_aca;
+
+	write_lock_bh(&idev->lock);
+	prev_aca = NULL;
+	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+		if (ipv6_addr_equal(&aca->aca_addr, addr))
+			break;
+		prev_aca = aca;
+	}
+	if (!aca) {
+		write_unlock_bh(&idev->lock);
+		return -ENOENT;
+	}
+	if (--aca->aca_users > 0) {
+		write_unlock_bh(&idev->lock);
+		return 0;
+	}
+	if (prev_aca)
+		prev_aca->aca_next = aca->aca_next;
+	else
+		idev->ac_list = aca->aca_next;
+	write_unlock_bh(&idev->lock);
+	addrconf_leave_solict(idev, &aca->aca_addr);
+
+	dst_hold(&aca->aca_rt->u.dst);
+	if (ip6_del_rt(aca->aca_rt, NULL, NULL))
+		dst_free(&aca->aca_rt->u.dst);
+	else
+		dst_release(&aca->aca_rt->u.dst);
+
+	aca_put(aca);
+	return 0;
+}
+
+static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr)
+{
+	int ret;
+	struct inet6_dev *idev = in6_dev_get(dev);
+	if (idev == NULL)
+		return -ENODEV;
+	ret = __ipv6_dev_ac_dec(idev, addr);
+	in6_dev_put(idev);
+	return ret;
+}
+	
+/*
+ *	check if the interface has this anycast address
+ */
+static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr)
+{
+	struct inet6_dev *idev;
+	struct ifacaddr6 *aca;
+
+	idev = in6_dev_get(dev);
+	if (idev) {
+		read_lock_bh(&idev->lock);
+		for (aca = idev->ac_list; aca; aca = aca->aca_next)
+			if (ipv6_addr_equal(&aca->aca_addr, addr))
+				break;
+		read_unlock_bh(&idev->lock);
+		in6_dev_put(idev);
+		return aca != 0;
+	}
+	return 0;
+}
+
+/*
+ *	check if given interface (or any, if dev==0) has this anycast address
+ */
+int ipv6_chk_acast_addr(struct net_device *dev, struct in6_addr *addr)
+{
+	if (dev)
+		return ipv6_chk_acast_dev(dev, addr);
+	read_lock(&dev_base_lock);
+	for (dev=dev_base; dev; dev=dev->next)
+		if (ipv6_chk_acast_dev(dev, addr))
+			break;
+	read_unlock(&dev_base_lock);
+	return dev != 0;
+}
+
+
+#ifdef CONFIG_PROC_FS
+struct ac6_iter_state {
+	struct net_device *dev;
+	struct inet6_dev *idev;
+};
+
+#define ac6_seq_private(seq)	((struct ac6_iter_state *)(seq)->private)
+
+static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
+{
+	struct ifacaddr6 *im = NULL;
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	for (state->dev = dev_base, state->idev = NULL;
+	     state->dev;
+	     state->dev = state->dev->next) {
+		struct inet6_dev *idev;
+		idev = in6_dev_get(state->dev);
+		if (!idev)
+			continue;
+		read_lock_bh(&idev->lock);
+		im = idev->ac_list;
+		if (im) {
+			state->idev = idev;
+			break;
+		}
+		read_unlock_bh(&idev->lock);
+	}
+	return im;
+}
+
+static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im)
+{
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	im = im->aca_next;
+	while (!im) {
+		if (likely(state->idev != NULL)) {
+			read_unlock_bh(&state->idev->lock);
+			in6_dev_put(state->idev);
+		}
+		state->dev = state->dev->next;
+		if (!state->dev) {
+			state->idev = NULL;
+			break;
+		}
+		state->idev = in6_dev_get(state->dev);
+		if (!state->idev)
+			continue;
+		read_lock_bh(&state->idev->lock);
+		im = state->idev->ac_list;
+	}
+	return im;
+}
+
+static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos)
+{
+	struct ifacaddr6 *im = ac6_get_first(seq);
+	if (im)
+		while (pos && (im = ac6_get_next(seq, im)) != NULL)
+			--pos;
+	return pos ? NULL : im;
+}
+
+static void *ac6_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	read_lock(&dev_base_lock);
+	return ac6_get_idx(seq, *pos);
+}
+
+static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct ifacaddr6 *im;
+	im = ac6_get_next(seq, v);
+	++*pos;
+	return im;
+}
+
+static void ac6_seq_stop(struct seq_file *seq, void *v)
+{
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+	if (likely(state->idev != NULL)) {
+		read_unlock_bh(&state->idev->lock);
+		in6_dev_put(state->idev);
+	}
+	read_unlock(&dev_base_lock);
+}
+
+static int ac6_seq_show(struct seq_file *seq, void *v)
+{
+	struct ifacaddr6 *im = (struct ifacaddr6 *)v;
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	seq_printf(seq,
+		   "%-4d %-15s "
+		   "%04x%04x%04x%04x%04x%04x%04x%04x "
+		   "%5d\n",
+		   state->dev->ifindex, state->dev->name,
+		   NIP6(im->aca_addr),
+		   im->aca_users);
+	return 0;
+}
+
+static struct seq_operations ac6_seq_ops = {
+	.start	=	ac6_seq_start,
+	.next	=	ac6_seq_next,
+	.stop	=	ac6_seq_stop,
+	.show	=	ac6_seq_show,
+};
+
+static int ac6_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int rc = -ENOMEM;
+	struct ac6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+
+	if (!s)
+		goto out;
+
+	rc = seq_open(file, &ac6_seq_ops);
+	if (rc)
+		goto out_kfree;
+
+	seq = file->private_data;
+	seq->private = s;
+	memset(s, 0, sizeof(*s));
+out:
+	return rc;
+out_kfree:
+	kfree(s);
+	goto out;
+}
+
+static struct file_operations ac6_seq_fops = {
+	.owner		=	THIS_MODULE,
+	.open		=	ac6_seq_open,
+	.read		=	seq_read,
+	.llseek		=	seq_lseek,
+	.release	=	seq_release_private,
+};
+
+int __init ac6_proc_init(void)
+{
+	if (!proc_net_fops_create("anycast6", S_IRUGO, &ac6_seq_fops))
+		return -ENOMEM;
+
+	return 0;
+}
+
+void ac6_proc_exit(void)
+{
+	proc_net_remove("anycast6");
+}
+#endif
+

net/ipv6/datagram.c

@@ -0,0 +1,600 @@
+/*
+ *	common UDP/RAW code
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>	
+ *
+ *	$Id: datagram.c,v 1.24 2002/02/01 22:01:04 davem Exp $
+ *
+ *	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.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/route.h>
+
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+#include <net/transp_v6.h>
+#include <net/ip6_route.h>
+
+#include <linux/errqueue.h>
+#include <asm/uaccess.h>
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
+	struct inet_sock      	*inet = inet_sk(sk);
+	struct ipv6_pinfo      	*np = inet6_sk(sk);
+	struct in6_addr		*daddr, *final_p = NULL, final;
+	struct dst_entry	*dst;
+	struct flowi		fl;
+	struct ip6_flowlabel	*flowlabel = NULL;
+	int			addr_type;
+	int			err;
+
+	if (usin->sin6_family == AF_INET) {
+		if (__ipv6_only_sock(sk))
+			return -EAFNOSUPPORT;
+		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		goto ipv4_connected;
+	}
+
+	if (addr_len < SIN6_LEN_RFC2133)
+	  	return -EINVAL;
+
+	if (usin->sin6_family != AF_INET6) 
+	  	return -EAFNOSUPPORT;
+
+	memset(&fl, 0, sizeof(fl));
+	if (np->sndflow) {
+		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
+			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+			if (flowlabel == NULL)
+				return -EINVAL;
+			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+		}
+	}
+
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+
+	if (addr_type == IPV6_ADDR_ANY) {
+		/*
+		 *	connect to self
+		 */
+		usin->sin6_addr.s6_addr[15] = 0x01;
+	}
+
+	daddr = &usin->sin6_addr;
+
+	if (addr_type == IPV6_ADDR_MAPPED) {
+		struct sockaddr_in sin;
+
+		if (__ipv6_only_sock(sk)) {
+			err = -ENETUNREACH;
+			goto out;
+		}
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = daddr->s6_addr32[3];
+		sin.sin_port = usin->sin6_port;
+
+		err = ip4_datagram_connect(sk, 
+					   (struct sockaddr*) &sin, 
+					   sizeof(sin));
+
+ipv4_connected:
+		if (err)
+			goto out;
+		
+		ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr);
+
+		if (ipv6_addr_any(&np->saddr)) {
+			ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff),
+				      inet->saddr);
+		}
+
+		if (ipv6_addr_any(&np->rcv_saddr)) {
+			ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff),
+				      inet->rcv_saddr);
+		}
+		goto out;
+	}
+
+	if (addr_type&IPV6_ADDR_LINKLOCAL) {
+		if (addr_len >= sizeof(struct sockaddr_in6) &&
+		    usin->sin6_scope_id) {
+			if (sk->sk_bound_dev_if &&
+			    sk->sk_bound_dev_if != usin->sin6_scope_id) {
+				err = -EINVAL;
+				goto out;
+			}
+			sk->sk_bound_dev_if = usin->sin6_scope_id;
+			if (!sk->sk_bound_dev_if &&
+			    (addr_type & IPV6_ADDR_MULTICAST))
+				fl.oif = np->mcast_oif;
+		}
+
+		/* Connect to link-local address requires an interface */
+		if (!sk->sk_bound_dev_if) {
+			err = -EINVAL;
+			goto out;
+		}
+	}
+
+	ipv6_addr_copy(&np->daddr, daddr);
+	np->flow_label = fl.fl6_flowlabel;
+
+	inet->dport = usin->sin6_port;
+
+	/*
+	 *	Check for a route to destination an obtain the
+	 *	destination cache for it.
+	 */
+
+	fl.proto = sk->sk_protocol;
+	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
+	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
+	fl.oif = sk->sk_bound_dev_if;
+	fl.fl_ip_dport = inet->dport;
+	fl.fl_ip_sport = inet->sport;
+
+	if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST))
+		fl.oif = np->mcast_oif;
+
+	if (flowlabel) {
+		if (flowlabel->opt && flowlabel->opt->srcrt) {
+			struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt;
+			ipv6_addr_copy(&final, &fl.fl6_dst);
+			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
+			final_p = &final;
+		}
+	} else if (np->opt && np->opt->srcrt) {
+		struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
+		ipv6_addr_copy(&final, &fl.fl6_dst);
+		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
+		final_p = &final;
+	}
+
+	err = ip6_dst_lookup(sk, &dst, &fl);
+	if (err)
+		goto out;
+	if (final_p)
+		ipv6_addr_copy(&fl.fl6_dst, final_p);
+
+	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
+		dst_release(dst);
+		goto out;
+	}
+
+	/* source address lookup done in ip6_dst_lookup */
+
+	if (ipv6_addr_any(&np->saddr))
+		ipv6_addr_copy(&np->saddr, &fl.fl6_src);
+
+	if (ipv6_addr_any(&np->rcv_saddr)) {
+		ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
+		inet->rcv_saddr = LOOPBACK4_IPV6;
+	}
+
+	ip6_dst_store(sk, dst,
+		      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
+		      &np->daddr : NULL);
+
+	sk->sk_state = TCP_ESTABLISHED;
+out:
+	fl6_sock_release(flowlabel);
+	return err;
+}
+
+void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
+		     u16 port, u32 info, u8 *payload)
+{
+	struct ipv6_pinfo *np  = inet6_sk(sk);
+	struct icmp6hdr *icmph = (struct icmp6hdr *)skb->h.raw;
+	struct sock_exterr_skb *serr;
+
+	if (!np->recverr)
+		return;
+
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	serr = SKB_EXT_ERR(skb);
+	serr->ee.ee_errno = err;
+	serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+	serr->ee.ee_type = icmph->icmp6_type; 
+	serr->ee.ee_code = icmph->icmp6_code;
+	serr->ee.ee_pad = 0;
+	serr->ee.ee_info = info;
+	serr->ee.ee_data = 0;
+	serr->addr_offset = (u8*)&(((struct ipv6hdr*)(icmph+1))->daddr) - skb->nh.raw;
+	serr->port = port;
+
+	skb->h.raw = payload;
+	__skb_pull(skb, payload - skb->data);
+
+	if (sock_queue_err_skb(sk, skb))
+		kfree_skb(skb);
+}
+
+void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sock_exterr_skb *serr;
+	struct ipv6hdr *iph;
+	struct sk_buff *skb;
+
+	if (!np->recverr)
+		return;
+
+	skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	iph = (struct ipv6hdr*)skb_put(skb, sizeof(struct ipv6hdr));
+	skb->nh.ipv6h = iph;
+	ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+
+	serr = SKB_EXT_ERR(skb);
+	serr->ee.ee_errno = err;
+	serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
+	serr->ee.ee_type = 0; 
+	serr->ee.ee_code = 0;
+	serr->ee.ee_pad = 0;
+	serr->ee.ee_info = info;
+	serr->ee.ee_data = 0;
+	serr->addr_offset = (u8*)&iph->daddr - skb->nh.raw;
+	serr->port = fl->fl_ip_dport;
+
+	skb->h.raw = skb->tail;
+	__skb_pull(skb, skb->tail - skb->data);
+
+	if (sock_queue_err_skb(sk, skb))
+		kfree_skb(skb);
+}
+
+/* 
+ *	Handle MSG_ERRQUEUE
+ */
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sock_exterr_skb *serr;
+	struct sk_buff *skb, *skb2;
+	struct sockaddr_in6 *sin;
+	struct {
+		struct sock_extended_err ee;
+		struct sockaddr_in6	 offender;
+	} errhdr;
+	int err;
+	int copied;
+
+	err = -EAGAIN;
+	skb = skb_dequeue(&sk->sk_error_queue);
+	if (skb == NULL)
+		goto out;
+
+	copied = skb->len;
+	if (copied > len) {
+		msg->msg_flags |= MSG_TRUNC;
+		copied = len;
+	}
+	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	if (err)
+		goto out_free_skb;
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	serr = SKB_EXT_ERR(skb);
+
+	sin = (struct sockaddr_in6 *)msg->msg_name;
+	if (sin) {
+		sin->sin6_family = AF_INET6;
+		sin->sin6_flowinfo = 0;
+		sin->sin6_port = serr->port; 
+		sin->sin6_scope_id = 0;
+		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+			ipv6_addr_copy(&sin->sin6_addr,
+			  (struct in6_addr *)(skb->nh.raw + serr->addr_offset));
+			if (np->sndflow)
+				sin->sin6_flowinfo = *(u32*)(skb->nh.raw + serr->addr_offset - 24) & IPV6_FLOWINFO_MASK;
+			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
+				sin->sin6_scope_id = IP6CB(skb)->iif;
+		} else {
+			ipv6_addr_set(&sin->sin6_addr, 0, 0,
+				      htonl(0xffff),
+				      *(u32*)(skb->nh.raw + serr->addr_offset));
+		}
+	}
+
+	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
+	sin = &errhdr.offender;
+	sin->sin6_family = AF_UNSPEC;
+	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
+		sin->sin6_family = AF_INET6;
+		sin->sin6_flowinfo = 0;
+		sin->sin6_scope_id = 0;
+		if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+			ipv6_addr_copy(&sin->sin6_addr, &skb->nh.ipv6h->saddr);
+			if (np->rxopt.all)
+				datagram_recv_ctl(sk, msg, skb);
+			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
+				sin->sin6_scope_id = IP6CB(skb)->iif;
+		} else {
+			struct inet_sock *inet = inet_sk(sk);
+
+			ipv6_addr_set(&sin->sin6_addr, 0, 0,
+				      htonl(0xffff),
+				      skb->nh.iph->saddr);
+			if (inet->cmsg_flags)
+				ip_cmsg_recv(msg, skb);
+		}
+	}
+
+	put_cmsg(msg, SOL_IPV6, IPV6_RECVERR, sizeof(errhdr), &errhdr);
+
+	/* Now we could try to dump offended packet options */
+
+	msg->msg_flags |= MSG_ERRQUEUE;
+	err = copied;
+
+	/* Reset and regenerate socket error */
+	spin_lock_irq(&sk->sk_error_queue.lock);
+	sk->sk_err = 0;
+	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
+		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
+		spin_unlock_irq(&sk->sk_error_queue.lock);
+		sk->sk_error_report(sk);
+	} else {
+		spin_unlock_irq(&sk->sk_error_queue.lock);
+	}
+
+out_free_skb:	
+	kfree_skb(skb);
+out:
+	return err;
+}
+
+
+
+int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct inet6_skb_parm *opt = IP6CB(skb);
+
+	if (np->rxopt.bits.rxinfo) {
+		struct in6_pktinfo src_info;
+
+		src_info.ipi6_ifindex = opt->iif;
+		ipv6_addr_copy(&src_info.ipi6_addr, &skb->nh.ipv6h->daddr);
+		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+	}
+
+	if (np->rxopt.bits.rxhlim) {
+		int hlim = skb->nh.ipv6h->hop_limit;
+		put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
+	}
+
+	if (np->rxopt.bits.rxflow && (*(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK)) {
+		u32 flowinfo = *(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK;
+		put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
+	}
+	if (np->rxopt.bits.hopopts && opt->hop) {
+		u8 *ptr = skb->nh.raw + opt->hop;
+		put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
+	}
+	if (np->rxopt.bits.dstopts && opt->dst0) {
+		u8 *ptr = skb->nh.raw + opt->dst0;
+		put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, (ptr[1]+1)<<3, ptr);
+	}
+	if (np->rxopt.bits.srcrt && opt->srcrt) {
+		struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(skb->nh.raw + opt->srcrt);
+		put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, (rthdr->hdrlen+1) << 3, rthdr);
+	}
+	if (np->rxopt.bits.dstopts && opt->dst1) {
+		u8 *ptr = skb->nh.raw + opt->dst1;
+		put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, (ptr[1]+1)<<3, ptr);
+	}
+	return 0;
+}
+
+int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
+		      struct ipv6_txoptions *opt,
+		      int *hlimit)
+{
+	struct in6_pktinfo *src_info;
+	struct cmsghdr *cmsg;
+	struct ipv6_rt_hdr *rthdr;
+	struct ipv6_opt_hdr *hdr;
+	int len;
+	int err = 0;
+
+	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+		int addr_type;
+		struct net_device *dev = NULL;
+
+		if (!CMSG_OK(msg, cmsg)) {
+			err = -EINVAL;
+			goto exit_f;
+		}
+
+		if (cmsg->cmsg_level != SOL_IPV6)
+			continue;
+
+		switch (cmsg->cmsg_type) {
+ 		case IPV6_PKTINFO:
+ 			if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+			
+			if (src_info->ipi6_ifindex) {
+				if (fl->oif && src_info->ipi6_ifindex != fl->oif)
+					return -EINVAL;
+				fl->oif = src_info->ipi6_ifindex;
+			}
+
+			addr_type = ipv6_addr_type(&src_info->ipi6_addr);
+
+			if (addr_type == IPV6_ADDR_ANY)
+				break;
+			
+			if (addr_type & IPV6_ADDR_LINKLOCAL) {
+				if (!src_info->ipi6_ifindex)
+					return -EINVAL;
+				else {
+					dev = dev_get_by_index(src_info->ipi6_ifindex);
+					if (!dev)
+						return -ENODEV;
+				}
+			}
+			if (!ipv6_chk_addr(&src_info->ipi6_addr, dev, 0)) {
+				if (dev)
+					dev_put(dev);
+				err = -EINVAL;
+				goto exit_f;
+			}
+			if (dev)
+				dev_put(dev);
+
+			ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr);
+			break;
+
+		case IPV6_FLOWINFO:
+                        if (cmsg->cmsg_len < CMSG_LEN(4)) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) {
+				if ((fl->fl6_flowlabel^*(u32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) {
+					err = -EINVAL;
+					goto exit_f;
+				}
+			}
+			fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(u32 *)CMSG_DATA(cmsg);
+			break;
+
+		case IPV6_HOPOPTS:
+                        if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg);
+			len = ((hdr->hdrlen + 1) << 3);
+			if (cmsg->cmsg_len < CMSG_LEN(len)) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+			if (!capable(CAP_NET_RAW)) {
+				err = -EPERM;
+				goto exit_f;
+			}
+			opt->opt_nflen += len;
+			opt->hopopt = hdr;
+			break;
+
+		case IPV6_DSTOPTS:
+                        if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg);
+			len = ((hdr->hdrlen + 1) << 3);
+			if (cmsg->cmsg_len < CMSG_LEN(len)) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+			if (!capable(CAP_NET_RAW)) {
+				err = -EPERM;
+				goto exit_f;
+			}
+			if (opt->dst1opt) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+			opt->opt_flen += len;
+			opt->dst1opt = hdr;
+			break;
+
+		case IPV6_RTHDR:
+                        if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg);
+
+			/*
+			 *	TYPE 0
+			 */
+			if (rthdr->type) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			len = ((rthdr->hdrlen + 1) << 3);
+
+                        if (cmsg->cmsg_len < CMSG_LEN(len)) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			/* segments left must also match */
+			if ((rthdr->hdrlen >> 1) != rthdr->segments_left) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			opt->opt_nflen += len;
+			opt->srcrt = rthdr;
+
+			if (opt->dst1opt) {
+				int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3);
+
+				opt->opt_nflen += dsthdrlen;
+				opt->dst0opt = opt->dst1opt;
+				opt->dst1opt = NULL;
+				opt->opt_flen -= dsthdrlen;
+			}
+
+			break;
+
+		case IPV6_HOPLIMIT:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
+			*hlimit = *(int *)CMSG_DATA(cmsg);
+			break;
+
+		default:
+			LIMIT_NETDEBUG(
+				printk(KERN_DEBUG "invalid cmsg type: %d\n", cmsg->cmsg_type));
+			err = -EINVAL;
+			break;
+		};
+	}
+
+exit_f:
+	return err;
+}

net/ipv6/esp6.c

@@ -0,0 +1,424 @@
+/*
+ * Copyright (C)2002 USAGI/WIDE Project
+ * 
+ * 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.
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Authors
+ *
+ *	Mitsuru KANDA @USAGI       : IPv6 Support 
+ * 	Kazunori MIYAZAWA @USAGI   :
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 	
+ * 	This file is derived from net/ipv4/esp.c
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/esp.h>
+#include <asm/scatterlist.h>
+#include <linux/crypto.h>
+#include <linux/pfkeyv2.h>
+#include <linux/random.h>
+#include <net/icmp.h>
+#include <net/ipv6.h>
+#include <linux/icmpv6.h>
+
+static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+	int hdr_len;
+	struct ipv6hdr *top_iph;
+	struct ipv6_esp_hdr *esph;
+	struct crypto_tfm *tfm;
+	struct esp_data *esp;
+	struct sk_buff *trailer;
+	int blksize;
+	int clen;
+	int alen;
+	int nfrags;
+
+	esp = x->data;
+	hdr_len = skb->h.raw - skb->data +
+		  sizeof(*esph) + esp->conf.ivlen;
+
+	/* Strip IP+ESP header. */
+	__skb_pull(skb, hdr_len);
+
+	/* Now skb is pure payload to encrypt */
+	err = -ENOMEM;
+
+	/* Round to block size */
+	clen = skb->len;
+
+	alen = esp->auth.icv_trunc_len;
+	tfm = esp->conf.tfm;
+	blksize = (crypto_tfm_alg_blocksize(tfm) + 3) & ~3;
+	clen = (clen + 2 + blksize-1)&~(blksize-1);
+	if (esp->conf.padlen)
+		clen = (clen + esp->conf.padlen-1)&~(esp->conf.padlen-1);
+
+	if ((nfrags = skb_cow_data(skb, clen-skb->len+alen, &trailer)) < 0) {
+		goto error;
+	}
+
+	/* Fill padding... */
+	do {
+		int i;
+		for (i=0; i<clen-skb->len - 2; i++)
+			*(u8*)(trailer->tail + i) = i+1;
+	} while (0);
+	*(u8*)(trailer->tail + clen-skb->len - 2) = (clen - skb->len)-2;
+	pskb_put(skb, trailer, clen - skb->len);
+
+	top_iph = (struct ipv6hdr *)__skb_push(skb, hdr_len);
+	esph = (struct ipv6_esp_hdr *)skb->h.raw;
+	top_iph->payload_len = htons(skb->len + alen - sizeof(*top_iph));
+	*(u8*)(trailer->tail - 1) = *skb->nh.raw;
+	*skb->nh.raw = IPPROTO_ESP;
+
+	esph->spi = x->id.spi;
+	esph->seq_no = htonl(++x->replay.oseq);
+
+	if (esp->conf.ivlen)
+		crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
+
+	do {
+		struct scatterlist *sg = &esp->sgbuf[0];
+
+		if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
+			sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
+			if (!sg)
+				goto error;
+		}
+		skb_to_sgvec(skb, sg, esph->enc_data+esp->conf.ivlen-skb->data, clen);
+		crypto_cipher_encrypt(tfm, sg, sg, clen);
+		if (unlikely(sg != &esp->sgbuf[0]))
+			kfree(sg);
+	} while (0);
+
+	if (esp->conf.ivlen) {
+		memcpy(esph->enc_data, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
+		crypto_cipher_get_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
+	}
+
+	if (esp->auth.icv_full_len) {
+		esp->auth.icv(esp, skb, (u8*)esph-skb->data,
+			sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen+clen, trailer->tail);
+		pskb_put(skb, trailer, alen);
+	}
+
+	err = 0;
+
+error:
+	return err;
+}
+
+static int esp6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
+{
+	struct ipv6hdr *iph;
+	struct ipv6_esp_hdr *esph;
+	struct esp_data *esp = x->data;
+	struct sk_buff *trailer;
+	int blksize = crypto_tfm_alg_blocksize(esp->conf.tfm);
+	int alen = esp->auth.icv_trunc_len;
+	int elen = skb->len - sizeof(struct ipv6_esp_hdr) - esp->conf.ivlen - alen;
+
+	int hdr_len = skb->h.raw - skb->nh.raw;
+	int nfrags;
+	unsigned char *tmp_hdr = NULL;
+	int ret = 0;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6_esp_hdr))) {
+		ret = -EINVAL;
+		goto out_nofree;
+	}
+
+	if (elen <= 0 || (elen & (blksize-1))) {
+		ret = -EINVAL;
+		goto out_nofree;
+	}
+
+	tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC);
+	if (!tmp_hdr) {
+		ret = -ENOMEM;
+		goto out_nofree;
+	}
+	memcpy(tmp_hdr, skb->nh.raw, hdr_len);
+
+	/* If integrity check is required, do this. */
+        if (esp->auth.icv_full_len) {
+		u8 sum[esp->auth.icv_full_len];
+		u8 sum1[alen];
+
+		esp->auth.icv(esp, skb, 0, skb->len-alen, sum);
+
+		if (skb_copy_bits(skb, skb->len-alen, sum1, alen))
+			BUG();
+
+		if (unlikely(memcmp(sum, sum1, alen))) {
+			x->stats.integrity_failed++;
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	if ((nfrags = skb_cow_data(skb, 0, &trailer)) < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	esph = (struct ipv6_esp_hdr*)skb->data;
+	iph = skb->nh.ipv6h;
+
+	/* Get ivec. This can be wrong, check against another impls. */
+	if (esp->conf.ivlen)
+		crypto_cipher_set_iv(esp->conf.tfm, esph->enc_data, crypto_tfm_alg_ivsize(esp->conf.tfm));
+
+        {
+		u8 nexthdr[2];
+		struct scatterlist *sg = &esp->sgbuf[0];
+		u8 padlen;
+
+		if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
+			sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
+			if (!sg) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+		skb_to_sgvec(skb, sg, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen, elen);
+		crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
+		if (unlikely(sg != &esp->sgbuf[0]))
+			kfree(sg);
+
+		if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
+			BUG();
+
+		padlen = nexthdr[0];
+		if (padlen+2 >= elen) {
+			LIMIT_NETDEBUG(
+				printk(KERN_WARNING "ipsec esp packet is garbage padlen=%d, elen=%d\n", padlen+2, elen));
+			ret = -EINVAL;
+			goto out;
+		}
+		/* ... check padding bits here. Silly. :-) */ 
+
+		pskb_trim(skb, skb->len - alen - padlen - 2);
+		skb->h.raw = skb_pull(skb, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen);
+		skb->nh.raw += sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen;
+		memcpy(skb->nh.raw, tmp_hdr, hdr_len);
+		skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+		ret = nexthdr[1];
+	}
+
+out:
+	kfree(tmp_hdr);
+out_nofree:
+	return ret;
+}
+
+static u32 esp6_get_max_size(struct xfrm_state *x, int mtu)
+{
+	struct esp_data *esp = x->data;
+	u32 blksize = crypto_tfm_alg_blocksize(esp->conf.tfm);
+
+	if (x->props.mode) {
+		mtu = (mtu + 2 + blksize-1)&~(blksize-1);
+	} else {
+		/* The worst case. */
+		mtu += 2 + blksize;
+	}
+	if (esp->conf.padlen)
+		mtu = (mtu + esp->conf.padlen-1)&~(esp->conf.padlen-1);
+
+	return mtu + x->props.header_len + esp->auth.icv_full_len;
+}
+
+static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+                     int type, int code, int offset, __u32 info)
+{
+	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
+	struct ipv6_esp_hdr *esph = (struct ipv6_esp_hdr*)(skb->data+offset);
+	struct xfrm_state *x;
+
+	if (type != ICMPV6_DEST_UNREACH && 
+	    type != ICMPV6_PKT_TOOBIG)
+		return;
+
+	x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
+	if (!x)
+		return;
+	printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/"
+			"%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", 
+			ntohl(esph->spi), NIP6(iph->daddr));
+	xfrm_state_put(x);
+}
+
+static void esp6_destroy(struct xfrm_state *x)
+{
+	struct esp_data *esp = x->data;
+
+	if (!esp)
+		return;
+
+	if (esp->conf.tfm) {
+		crypto_free_tfm(esp->conf.tfm);
+		esp->conf.tfm = NULL;
+	}
+	if (esp->conf.ivec) {
+		kfree(esp->conf.ivec);
+		esp->conf.ivec = NULL;
+	}
+	if (esp->auth.tfm) {
+		crypto_free_tfm(esp->auth.tfm);
+		esp->auth.tfm = NULL;
+	}
+	if (esp->auth.work_icv) {
+		kfree(esp->auth.work_icv);
+		esp->auth.work_icv = NULL;
+	}
+	kfree(esp);
+}
+
+static int esp6_init_state(struct xfrm_state *x, void *args)
+{
+	struct esp_data *esp = NULL;
+
+	/* null auth and encryption can have zero length keys */
+	if (x->aalg) {
+		if (x->aalg->alg_key_len > 512)
+			goto error;
+	}
+	if (x->ealg == NULL)
+		goto error;
+
+	if (x->encap)
+		goto error;
+
+	esp = kmalloc(sizeof(*esp), GFP_KERNEL);
+	if (esp == NULL)
+		return -ENOMEM;
+
+	memset(esp, 0, sizeof(*esp));
+
+	if (x->aalg) {
+		struct xfrm_algo_desc *aalg_desc;
+
+		esp->auth.key = x->aalg->alg_key;
+		esp->auth.key_len = (x->aalg->alg_key_len+7)/8;
+		esp->auth.tfm = crypto_alloc_tfm(x->aalg->alg_name, 0);
+		if (esp->auth.tfm == NULL)
+			goto error;
+		esp->auth.icv = esp_hmac_digest;
+ 
+		aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
+		BUG_ON(!aalg_desc);
+ 
+		if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
+			crypto_tfm_alg_digestsize(esp->auth.tfm)) {
+				printk(KERN_INFO "ESP: %s digestsize %u != %hu\n",
+					x->aalg->alg_name,
+					crypto_tfm_alg_digestsize(esp->auth.tfm),
+					aalg_desc->uinfo.auth.icv_fullbits/8);
+				goto error;
+		}
+ 
+		esp->auth.icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
+		esp->auth.icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8;
+ 
+		esp->auth.work_icv = kmalloc(esp->auth.icv_full_len, GFP_KERNEL);
+		if (!esp->auth.work_icv)
+			goto error;
+	}
+	esp->conf.key = x->ealg->alg_key;
+	esp->conf.key_len = (x->ealg->alg_key_len+7)/8;
+	if (x->props.ealgo == SADB_EALG_NULL)
+		esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_ECB);
+	else
+		esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_CBC);
+	if (esp->conf.tfm == NULL)
+		goto error;
+	esp->conf.ivlen = crypto_tfm_alg_ivsize(esp->conf.tfm);
+	esp->conf.padlen = 0;
+	if (esp->conf.ivlen) {
+		esp->conf.ivec = kmalloc(esp->conf.ivlen, GFP_KERNEL);
+		if (unlikely(esp->conf.ivec == NULL))
+			goto error;
+		get_random_bytes(esp->conf.ivec, esp->conf.ivlen);
+	}
+	if (crypto_cipher_setkey(esp->conf.tfm, esp->conf.key, esp->conf.key_len))
+		goto error;
+	x->props.header_len = sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen;
+	if (x->props.mode)
+		x->props.header_len += sizeof(struct ipv6hdr);
+	x->data = esp;
+	return 0;
+
+error:
+	x->data = esp;
+	esp6_destroy(x);
+	x->data = NULL;
+	return -EINVAL;
+}
+
+static struct xfrm_type esp6_type =
+{
+	.description	= "ESP6",
+	.owner	     	= THIS_MODULE,
+	.proto	     	= IPPROTO_ESP,
+	.init_state	= esp6_init_state,
+	.destructor	= esp6_destroy,
+	.get_max_size	= esp6_get_max_size,
+	.input		= esp6_input,
+	.output		= esp6_output
+};
+
+static struct inet6_protocol esp6_protocol = {
+	.handler 	=	xfrm6_rcv,
+	.err_handler	=	esp6_err,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+static int __init esp6_init(void)
+{
+	if (xfrm_register_type(&esp6_type, AF_INET6) < 0) {
+		printk(KERN_INFO "ipv6 esp init: can't add xfrm type\n");
+		return -EAGAIN;
+	}
+	if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) {
+		printk(KERN_INFO "ipv6 esp init: can't add protocol\n");
+		xfrm_unregister_type(&esp6_type, AF_INET6);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+static void __exit esp6_fini(void)
+{
+	if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0)
+		printk(KERN_INFO "ipv6 esp close: can't remove protocol\n");
+	if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0)
+		printk(KERN_INFO "ipv6 esp close: can't remove xfrm type\n");
+}
+
+module_init(esp6_init);
+module_exit(esp6_fini);
+
+MODULE_LICENSE("GPL");

net/ipv6/exthdrs.c

@@ -0,0 +1,575 @@
+/*
+ *	Extension Header handling for IPv6
+ *	Linux INET6 implementation
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>
+ *	Andi Kleen		<ak@muc.de>
+ *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
+ *
+ *	$Id: exthdrs.c,v 1.13 2001/06/19 15:58:56 davem Exp $
+ *
+ *	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.
+ */
+
+/* Changes:
+ *	yoshfuji		: ensure not to overrun while parsing 
+ *				  tlv options.
+ *	Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs().
+ *	YOSHIFUJI Hideaki @USAGI  Register inbound extension header
+ *				  handlers as inet6_protocol{}.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+
+#include <asm/uaccess.h>
+
+/*
+ *	Parsing tlv encoded headers.
+ *
+ *	Parsing function "func" returns 1, if parsing succeed
+ *	and 0, if it failed.
+ *	It MUST NOT touch skb->h.
+ */
+
+struct tlvtype_proc {
+	int	type;
+	int	(*func)(struct sk_buff *skb, int offset);
+};
+
+/*********************
+  Generic functions
+ *********************/
+
+/* An unknown option is detected, decide what to do */
+
+static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff)
+{
+	switch ((skb->nh.raw[optoff] & 0xC0) >> 6) {
+	case 0: /* ignore */
+		return 1;
+
+	case 1: /* drop packet */
+		break;
+
+	case 3: /* Send ICMP if not a multicast address and drop packet */
+		/* Actually, it is redundant check. icmp_send
+		   will recheck in any case.
+		 */
+		if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr))
+			break;
+	case 2: /* send ICMP PARM PROB regardless and drop packet */
+		icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff);
+		return 0;
+	};
+
+	kfree_skb(skb);
+	return 0;
+}
+
+/* Parse tlv encoded option header (hop-by-hop or destination) */
+
+static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb)
+{
+	struct tlvtype_proc *curr;
+	int off = skb->h.raw - skb->nh.raw;
+	int len = ((skb->h.raw[1]+1)<<3);
+
+	if ((skb->h.raw + len) - skb->data > skb_headlen(skb))
+		goto bad;
+
+	off += 2;
+	len -= 2;
+
+	while (len > 0) {
+		int optlen = skb->nh.raw[off+1]+2;
+
+		switch (skb->nh.raw[off]) {
+		case IPV6_TLV_PAD0:
+			optlen = 1;
+			break;
+
+		case IPV6_TLV_PADN:
+			break;
+
+		default: /* Other TLV code so scan list */
+			if (optlen > len)
+				goto bad;
+			for (curr=procs; curr->type >= 0; curr++) {
+				if (curr->type == skb->nh.raw[off]) {
+					/* type specific length/alignment 
+					   checks will be performed in the 
+					   func(). */
+					if (curr->func(skb, off) == 0)
+						return 0;
+					break;
+				}
+			}
+			if (curr->type < 0) {
+				if (ip6_tlvopt_unknown(skb, off) == 0)
+					return 0;
+			}
+			break;
+		}
+		off += optlen;
+		len -= optlen;
+	}
+	if (len == 0)
+		return 1;
+bad:
+	kfree_skb(skb);
+	return 0;
+}
+
+/*****************************
+  Destination options header.
+ *****************************/
+
+static struct tlvtype_proc tlvprocdestopt_lst[] = {
+	/* No destination options are defined now */
+	{-1,			NULL}
+};
+
+static int ipv6_destopt_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *skbp;
+	struct inet6_skb_parm *opt = IP6CB(skb);
+
+	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) ||
+	    !pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		kfree_skb(skb);
+		return -1;
+	}
+
+	opt->dst1 = skb->h.raw - skb->nh.raw;
+
+	if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) {
+		skb->h.raw += ((skb->h.raw[1]+1)<<3);
+		*nhoffp = opt->dst1;
+		return 1;
+	}
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+	return -1;
+}
+
+static struct inet6_protocol destopt_protocol = {
+	.handler	=	ipv6_destopt_rcv,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+void __init ipv6_destopt_init(void)
+{
+	if (inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS) < 0)
+		printk(KERN_ERR "ipv6_destopt_init: Could not register protocol\n");
+}
+
+/********************************
+  NONE header. No data in packet.
+ ********************************/
+
+static int ipv6_nodata_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *skbp;
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static struct inet6_protocol nodata_protocol = {
+	.handler	=	ipv6_nodata_rcv,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+void __init ipv6_nodata_init(void)
+{
+	if (inet6_add_protocol(&nodata_protocol, IPPROTO_NONE) < 0)
+		printk(KERN_ERR "ipv6_nodata_init: Could not register protocol\n");
+}
+
+/********************************
+  Routing header.
+ ********************************/
+
+static int ipv6_rthdr_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *skbp;
+	struct inet6_skb_parm *opt = IP6CB(skb);
+	struct in6_addr *addr;
+	struct in6_addr daddr;
+	int n, i;
+
+	struct ipv6_rt_hdr *hdr;
+	struct rt0_hdr *rthdr;
+
+	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) ||
+	    !pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		kfree_skb(skb);
+		return -1;
+	}
+
+	hdr = (struct ipv6_rt_hdr *) skb->h.raw;
+
+	if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr) ||
+	    skb->pkt_type != PACKET_HOST) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+		kfree_skb(skb);
+		return -1;
+	}
+
+looped_back:
+	if (hdr->segments_left == 0) {
+		opt->srcrt = skb->h.raw - skb->nh.raw;
+		skb->h.raw += (hdr->hdrlen + 1) << 3;
+		opt->dst0 = opt->dst1;
+		opt->dst1 = 0;
+		*nhoffp = (&hdr->nexthdr) - skb->nh.raw;
+		return 1;
+	}
+
+	if (hdr->type != IPV6_SRCRT_TYPE_0) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb->nh.raw);
+		return -1;
+	}
+	
+	if (hdr->hdrlen & 0x01) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw);
+		return -1;
+	}
+
+	/*
+	 *	This is the routing header forwarding algorithm from
+	 *	RFC 2460, page 16.
+	 */
+
+	n = hdr->hdrlen >> 1;
+
+	if (hdr->segments_left > n) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->segments_left) - skb->nh.raw);
+		return -1;
+	}
+
+	/* We are about to mangle packet header. Be careful!
+	   Do not damage packets queued somewhere.
+	 */
+	if (skb_cloned(skb)) {
+		struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC);
+		kfree_skb(skb);
+		/* the copy is a forwarded packet */
+		if (skb2 == NULL) {
+			IP6_INC_STATS_BH(IPSTATS_MIB_OUTDISCARDS);	
+			return -1;
+		}
+		*skbp = skb = skb2;
+		opt = IP6CB(skb2);
+		hdr = (struct ipv6_rt_hdr *) skb2->h.raw;
+	}
+
+	if (skb->ip_summed == CHECKSUM_HW)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	i = n - --hdr->segments_left;
+
+	rthdr = (struct rt0_hdr *) hdr;
+	addr = rthdr->addr;
+	addr += i - 1;
+
+	if (ipv6_addr_is_multicast(addr)) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+		kfree_skb(skb);
+		return -1;
+	}
+
+	ipv6_addr_copy(&daddr, addr);
+	ipv6_addr_copy(addr, &skb->nh.ipv6h->daddr);
+	ipv6_addr_copy(&skb->nh.ipv6h->daddr, &daddr);
+
+	dst_release(xchg(&skb->dst, NULL));
+	ip6_route_input(skb);
+	if (skb->dst->error) {
+		skb_push(skb, skb->data - skb->nh.raw);
+		dst_input(skb);
+		return -1;
+	}
+
+	if (skb->dst->dev->flags&IFF_LOOPBACK) {
+		if (skb->nh.ipv6h->hop_limit <= 1) {
+			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+			icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+				    0, skb->dev);
+			kfree_skb(skb);
+			return -1;
+		}
+		skb->nh.ipv6h->hop_limit--;
+		goto looped_back;
+	}
+
+	skb_push(skb, skb->data - skb->nh.raw);
+	dst_input(skb);
+	return -1;
+}
+
+static struct inet6_protocol rthdr_protocol = {
+	.handler	=	ipv6_rthdr_rcv,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+void __init ipv6_rthdr_init(void)
+{
+	if (inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING) < 0)
+		printk(KERN_ERR "ipv6_rthdr_init: Could not register protocol\n");
+};
+
+/*
+   This function inverts received rthdr.
+   NOTE: specs allow to make it automatically only if
+   packet authenticated.
+
+   I will not discuss it here (though, I am really pissed off at
+   this stupid requirement making rthdr idea useless)
+
+   Actually, it creates severe problems  for us.
+   Embryonic requests has no associated sockets,
+   so that user have no control over it and
+   cannot not only to set reply options, but
+   even to know, that someone wants to connect
+   without success. :-(
+
+   For now we need to test the engine, so that I created
+   temporary (or permanent) backdoor.
+   If listening socket set IPV6_RTHDR to 2, then we invert header.
+                                                   --ANK (980729)
+ */
+
+struct ipv6_txoptions *
+ipv6_invert_rthdr(struct sock *sk, struct ipv6_rt_hdr *hdr)
+{
+	/* Received rthdr:
+
+	   [ H1 -> H2 -> ... H_prev ]  daddr=ME
+
+	   Inverted result:
+	   [ H_prev -> ... -> H1 ] daddr =sender
+
+	   Note, that IP output engine will rewrite this rthdr
+	   by rotating it left by one addr.
+	 */
+
+	int n, i;
+	struct rt0_hdr *rthdr = (struct rt0_hdr*)hdr;
+	struct rt0_hdr *irthdr;
+	struct ipv6_txoptions *opt;
+	int hdrlen = ipv6_optlen(hdr);
+
+	if (hdr->segments_left ||
+	    hdr->type != IPV6_SRCRT_TYPE_0 ||
+	    hdr->hdrlen & 0x01)
+		return NULL;
+
+	n = hdr->hdrlen >> 1;
+	opt = sock_kmalloc(sk, sizeof(*opt) + hdrlen, GFP_ATOMIC);
+	if (opt == NULL)
+		return NULL;
+	memset(opt, 0, sizeof(*opt));
+	opt->tot_len = sizeof(*opt) + hdrlen;
+	opt->srcrt = (void*)(opt+1);
+	opt->opt_nflen = hdrlen;
+
+	memcpy(opt->srcrt, hdr, sizeof(*hdr));
+	irthdr = (struct rt0_hdr*)opt->srcrt;
+	/* Obsolete field, MBZ, when originated by us */
+	irthdr->bitmap = 0;
+	opt->srcrt->segments_left = n;
+	for (i=0; i<n; i++)
+		memcpy(irthdr->addr+i, rthdr->addr+(n-1-i), 16);
+	return opt;
+}
+
+/**********************************
+  Hop-by-hop options.
+ **********************************/
+
+/* Router Alert as of RFC 2711 */
+
+static int ipv6_hop_ra(struct sk_buff *skb, int optoff)
+{
+	if (skb->nh.raw[optoff+1] == 2) {
+		IP6CB(skb)->ra = optoff;
+		return 1;
+	}
+	LIMIT_NETDEBUG(
+		 printk(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", skb->nh.raw[optoff+1]));
+	kfree_skb(skb);
+	return 0;
+}
+
+/* Jumbo payload */
+
+static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
+{
+	u32 pkt_len;
+
+	if (skb->nh.raw[optoff+1] != 4 || (optoff&3) != 2) {
+		LIMIT_NETDEBUG(
+			 printk(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", skb->nh.raw[optoff+1]));
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		goto drop;
+	}
+
+	pkt_len = ntohl(*(u32*)(skb->nh.raw+optoff+2));
+	if (pkt_len <= IPV6_MAXPLEN) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2);
+		return 0;
+	}
+	if (skb->nh.ipv6h->payload_len) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff);
+		return 0;
+	}
+
+	if (pkt_len > skb->len - sizeof(struct ipv6hdr)) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS);
+		goto drop;
+	}
+	if (pkt_len + sizeof(struct ipv6hdr) < skb->len) {
+		__pskb_trim(skb, pkt_len + sizeof(struct ipv6hdr));
+		if (skb->ip_summed == CHECKSUM_HW)
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+	return 1;
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
+static struct tlvtype_proc tlvprochopopt_lst[] = {
+	{
+		.type	= IPV6_TLV_ROUTERALERT,
+		.func	= ipv6_hop_ra,
+	},
+	{
+		.type	= IPV6_TLV_JUMBO,
+		.func	= ipv6_hop_jumbo,
+	},
+	{ -1, }
+};
+
+int ipv6_parse_hopopts(struct sk_buff *skb, int nhoff)
+{
+	IP6CB(skb)->hop = sizeof(struct ipv6hdr);
+	if (ip6_parse_tlv(tlvprochopopt_lst, skb))
+		return sizeof(struct ipv6hdr);
+	return -1;
+}
+
+/*
+ *	Creating outbound headers.
+ *
+ *	"build" functions work when skb is filled from head to tail (datagram)
+ *	"push"	functions work when headers are added from tail to head (tcp)
+ *
+ *	In both cases we assume, that caller reserved enough room
+ *	for headers.
+ */
+
+static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
+			    struct ipv6_rt_hdr *opt,
+			    struct in6_addr **addr_p)
+{
+	struct rt0_hdr *phdr, *ihdr;
+	int hops;
+
+	ihdr = (struct rt0_hdr *) opt;
+	
+	phdr = (struct rt0_hdr *) skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3);
+	memcpy(phdr, ihdr, sizeof(struct rt0_hdr));
+
+	hops = ihdr->rt_hdr.hdrlen >> 1;
+
+	if (hops > 1)
+		memcpy(phdr->addr, ihdr->addr + 1,
+		       (hops - 1) * sizeof(struct in6_addr));
+
+	ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p);
+	*addr_p = ihdr->addr;
+
+	phdr->rt_hdr.nexthdr = *proto;
+	*proto = NEXTHDR_ROUTING;
+}
+
+static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt)
+{
+	struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt));
+
+	memcpy(h, opt, ipv6_optlen(opt));
+	h->nexthdr = *proto;
+	*proto = type;
+}
+
+void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
+			  u8 *proto,
+			  struct in6_addr **daddr)
+{
+	if (opt->srcrt)
+		ipv6_push_rthdr(skb, proto, opt->srcrt, daddr);
+	if (opt->dst0opt)
+		ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt);
+	if (opt->hopopt)
+		ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt);
+}
+
+void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto)
+{
+	if (opt->dst1opt)
+		ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt);
+}
+
+struct ipv6_txoptions *
+ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
+{
+	struct ipv6_txoptions *opt2;
+
+	opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
+	if (opt2) {
+		long dif = (char*)opt2 - (char*)opt;
+		memcpy(opt2, opt, opt->tot_len);
+		if (opt2->hopopt)
+			*((char**)&opt2->hopopt) += dif;
+		if (opt2->dst0opt)
+			*((char**)&opt2->dst0opt) += dif;
+		if (opt2->dst1opt)
+			*((char**)&opt2->dst1opt) += dif;
+		if (opt2->srcrt)
+			*((char**)&opt2->srcrt) += dif;
+	}
+	return opt2;
+}

net/ipv6/exthdrs_core.c

@@ -0,0 +1,109 @@
+/*
+ * IPv6 library code, needed by static components when full IPv6 support is
+ * not configured or static.
+ */
+#include <net/ipv6.h>
+
+/* 
+ * find out if nexthdr is a well-known extension header or a protocol
+ */
+
+int ipv6_ext_hdr(u8 nexthdr)
+{
+	/* 
+	 * find out if nexthdr is an extension header or a protocol
+	 */
+	return ( (nexthdr == NEXTHDR_HOP)	||
+		 (nexthdr == NEXTHDR_ROUTING)	||
+		 (nexthdr == NEXTHDR_FRAGMENT)	||
+		 (nexthdr == NEXTHDR_AUTH)	||
+		 (nexthdr == NEXTHDR_NONE)	||
+		 (nexthdr == NEXTHDR_DEST) );
+}
+
+/*
+ * Skip any extension headers. This is used by the ICMP module.
+ *
+ * Note that strictly speaking this conflicts with RFC 2460 4.0:
+ * ...The contents and semantics of each extension header determine whether 
+ * or not to proceed to the next header.  Therefore, extension headers must
+ * be processed strictly in the order they appear in the packet; a
+ * receiver must not, for example, scan through a packet looking for a
+ * particular kind of extension header and process that header prior to
+ * processing all preceding ones.
+ * 
+ * We do exactly this. This is a protocol bug. We can't decide after a
+ * seeing an unknown discard-with-error flavour TLV option if it's a 
+ * ICMP error message or not (errors should never be send in reply to
+ * ICMP error messages).
+ * 
+ * But I see no other way to do this. This might need to be reexamined
+ * when Linux implements ESP (and maybe AUTH) headers.
+ * --AK
+ *
+ * This function parses (probably truncated) exthdr set "hdr"
+ * of length "len". "nexthdrp" initially points to some place,
+ * where type of the first header can be found.
+ *
+ * It skips all well-known exthdrs, and returns pointer to the start
+ * of unparsable area i.e. the first header with unknown type.
+ * If it is not NULL *nexthdr is updated by type/protocol of this header.
+ *
+ * NOTES: - if packet terminated with NEXTHDR_NONE it returns NULL.
+ *        - it may return pointer pointing beyond end of packet,
+ *	    if the last recognized header is truncated in the middle.
+ *        - if packet is truncated, so that all parsed headers are skipped,
+ *	    it returns NULL.
+ *	  - First fragment header is skipped, not-first ones
+ *	    are considered as unparsable.
+ *	  - ESP is unparsable for now and considered like
+ *	    normal payload protocol.
+ *	  - Note also special handling of AUTH header. Thanks to IPsec wizards.
+ *
+ * --ANK (980726)
+ */
+
+int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, int len)
+{
+	u8 nexthdr = *nexthdrp;
+
+	while (ipv6_ext_hdr(nexthdr)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+		int hdrlen;
+
+		if (len < (int)sizeof(struct ipv6_opt_hdr))
+			return -1;
+		if (nexthdr == NEXTHDR_NONE)
+			return -1;
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (hp == NULL)
+			BUG();
+		if (nexthdr == NEXTHDR_FRAGMENT) {
+			unsigned short _frag_off, *fp;
+			fp = skb_header_pointer(skb,
+						start+offsetof(struct frag_hdr,
+							       frag_off),
+						sizeof(_frag_off),
+						&_frag_off);
+			if (fp == NULL)
+				return -1;
+
+			if (ntohs(*fp) & ~0x7)
+				break;
+			hdrlen = 8;
+		} else if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hp->hdrlen+2)<<2; 
+		else
+			hdrlen = ipv6_optlen(hp); 
+
+		nexthdr = hp->nexthdr;
+		len -= hdrlen;
+		start += hdrlen;
+	}
+
+	*nexthdrp = nexthdr;
+	return start;
+}
+
+EXPORT_SYMBOL(ipv6_ext_hdr);
+EXPORT_SYMBOL(ipv6_skip_exthdr);

net/ipv6/icmp.c

@@ -0,0 +1,822 @@
+/*
+ *	Internet Control Message Protocol (ICMPv6)
+ *	Linux INET6 implementation
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>
+ *
+ *	$Id: icmp.c,v 1.38 2002/02/08 03:57:19 davem Exp $
+ *
+ *	Based on net/ipv4/icmp.c
+ *
+ *	RFC 1885
+ *
+ *	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.
+ */
+
+/*
+ *	Changes:
+ *
+ *	Andi Kleen		:	exception handling
+ *	Andi Kleen			add rate limits. never reply to a icmp.
+ *					add more length checks and other fixes.
+ *	yoshfuji		:	ensure to sent parameter problem for
+ *					fragments.
+ *	YOSHIFUJI Hideaki @USAGI:	added sysctl for icmp rate limit.
+ *	Randy Dunlap and
+ *	YOSHIFUJI Hideaki @USAGI:	Per-interface statistics support
+ *	Kazunori MIYAZAWA @USAGI:       change output process to use ip6_append_data
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+#endif
+
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/icmpv6.h>
+
+#include <net/ip.h>
+#include <net/sock.h>
+
+#include <net/ipv6.h>
+#include <net/ip6_checksum.h>
+#include <net/protocol.h>
+#include <net/raw.h>
+#include <net/rawv6.h>
+#include <net/transp_v6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/icmp.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+
+DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics);
+
+/*
+ *	The ICMP socket(s). This is the most convenient way to flow control
+ *	our ICMP output as well as maintain a clean interface throughout
+ *	all layers. All Socketless IP sends will soon be gone.
+ *
+ *	On SMP we have one ICMP socket per-cpu.
+ */
+static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL;
+#define icmpv6_socket	__get_cpu_var(__icmpv6_socket)
+
+static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp);
+
+static struct inet6_protocol icmpv6_protocol = {
+	.handler	=	icmpv6_rcv,
+	.flags		=	INET6_PROTO_FINAL,
+};
+
+static __inline__ int icmpv6_xmit_lock(void)
+{
+	local_bh_disable();
+
+	if (unlikely(!spin_trylock(&icmpv6_socket->sk->sk_lock.slock))) {
+		/* This can happen if the output path (f.e. SIT or
+		 * ip6ip6 tunnel) signals dst_link_failure() for an
+		 * outgoing ICMP6 packet.
+		 */
+		local_bh_enable();
+		return 1;
+	}
+	return 0;
+}
+
+static __inline__ void icmpv6_xmit_unlock(void)
+{
+	spin_unlock_bh(&icmpv6_socket->sk->sk_lock.slock);
+}
+
+/* 
+ * Slightly more convenient version of icmpv6_send.
+ */
+void icmpv6_param_prob(struct sk_buff *skb, int code, int pos)
+{
+	icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
+	kfree_skb(skb);
+}
+
+/*
+ * Figure out, may we reply to this packet with icmp error.
+ *
+ * We do not reply, if:
+ *	- it was icmp error message.
+ *	- it is truncated, so that it is known, that protocol is ICMPV6
+ *	  (i.e. in the middle of some exthdr)
+ *
+ *	--ANK (980726)
+ */
+
+static int is_ineligible(struct sk_buff *skb)
+{
+	int ptr = (u8*)(skb->nh.ipv6h+1) - skb->data;
+	int len = skb->len - ptr;
+	__u8 nexthdr = skb->nh.ipv6h->nexthdr;
+
+	if (len < 0)
+		return 1;
+
+	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, len);
+	if (ptr < 0)
+		return 0;
+	if (nexthdr == IPPROTO_ICMPV6) {
+		u8 _type, *tp;
+		tp = skb_header_pointer(skb,
+			ptr+offsetof(struct icmp6hdr, icmp6_type),
+			sizeof(_type), &_type);
+		if (tp == NULL ||
+		    !(*tp & ICMPV6_INFOMSG_MASK))
+			return 1;
+	}
+	return 0;
+}
+
+static int sysctl_icmpv6_time = 1*HZ; 
+
+/* 
+ * Check the ICMP output rate limit 
+ */
+static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
+				     struct flowi *fl)
+{
+	struct dst_entry *dst;
+	int res = 0;
+
+	/* Informational messages are not limited. */
+	if (type & ICMPV6_INFOMSG_MASK)
+		return 1;
+
+	/* Do not limit pmtu discovery, it would break it. */
+	if (type == ICMPV6_PKT_TOOBIG)
+		return 1;
+
+	/* 
+	 * Look up the output route.
+	 * XXX: perhaps the expire for routing entries cloned by
+	 * this lookup should be more aggressive (not longer than timeout).
+	 */
+	dst = ip6_route_output(sk, fl);
+	if (dst->error) {
+		IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
+	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
+		res = 1;
+	} else {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		int tmo = sysctl_icmpv6_time;
+
+		/* Give more bandwidth to wider prefixes. */
+		if (rt->rt6i_dst.plen < 128)
+			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
+
+		res = xrlim_allow(dst, tmo);
+	}
+	dst_release(dst);
+	return res;
+}
+
+/*
+ *	an inline helper for the "simple" if statement below
+ *	checks if parameter problem report is caused by an
+ *	unrecognized IPv6 option that has the Option Type 
+ *	highest-order two bits set to 10
+ */
+
+static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset)
+{
+	u8 _optval, *op;
+
+	offset += skb->nh.raw - skb->data;
+	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
+	if (op == NULL)
+		return 1;
+	return (*op & 0xC0) == 0x80;
+}
+
+static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len)
+{
+	struct sk_buff *skb;
+	struct icmp6hdr *icmp6h;
+	int err = 0;
+
+	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
+		goto out;
+
+	icmp6h = (struct icmp6hdr*) skb->h.raw;
+	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
+	icmp6h->icmp6_cksum = 0;
+
+	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+		skb->csum = csum_partial((char *)icmp6h,
+					sizeof(struct icmp6hdr), skb->csum);
+		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
+						      &fl->fl6_dst,
+						      len, fl->proto,
+						      skb->csum);
+	} else {
+		u32 tmp_csum = 0;
+
+		skb_queue_walk(&sk->sk_write_queue, skb) {
+			tmp_csum = csum_add(tmp_csum, skb->csum);
+		}
+
+		tmp_csum = csum_partial((char *)icmp6h,
+					sizeof(struct icmp6hdr), tmp_csum);
+		tmp_csum = csum_ipv6_magic(&fl->fl6_src,
+					   &fl->fl6_dst,
+					   len, fl->proto, tmp_csum);
+		icmp6h->icmp6_cksum = tmp_csum;
+	}
+	if (icmp6h->icmp6_cksum == 0)
+		icmp6h->icmp6_cksum = -1;
+	ip6_push_pending_frames(sk);
+out:
+	return err;
+}
+
+struct icmpv6_msg {
+	struct sk_buff	*skb;
+	int		offset;
+};
+
+static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
+{
+	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
+	struct sk_buff *org_skb = msg->skb;
+	__u32 csum = 0;
+
+	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
+				      to, len, csum);
+	skb->csum = csum_block_add(skb->csum, csum, odd);
+	return 0;
+}
+
+/*
+ *	Send an ICMP message in response to a packet in error
+ */
+void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, 
+		 struct net_device *dev)
+{
+	struct inet6_dev *idev = NULL;
+	struct ipv6hdr *hdr = skb->nh.ipv6h;
+	struct sock *sk = icmpv6_socket->sk;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct in6_addr *saddr = NULL;
+	struct dst_entry *dst;
+	struct icmp6hdr tmp_hdr;
+	struct flowi fl;
+	struct icmpv6_msg msg;
+	int iif = 0;
+	int addr_type = 0;
+	int len;
+	int hlimit;
+	int err = 0;
+
+	if ((u8*)hdr < skb->head || (u8*)(hdr+1) > skb->tail)
+		return;
+
+	/*
+	 *	Make sure we respect the rules 
+	 *	i.e. RFC 1885 2.4(e)
+	 *	Rule (e.1) is enforced by not using icmpv6_send
+	 *	in any code that processes icmp errors.
+	 */
+	addr_type = ipv6_addr_type(&hdr->daddr);
+
+	if (ipv6_chk_addr(&hdr->daddr, skb->dev, 0))
+		saddr = &hdr->daddr;
+
+	/*
+	 *	Dest addr check
+	 */
+
+	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
+		if (type != ICMPV6_PKT_TOOBIG &&
+		    !(type == ICMPV6_PARAMPROB && 
+		      code == ICMPV6_UNK_OPTION && 
+		      (opt_unrec(skb, info))))
+			return;
+
+		saddr = NULL;
+	}
+
+	addr_type = ipv6_addr_type(&hdr->saddr);
+
+	/*
+	 *	Source addr check
+	 */
+
+	if (addr_type & IPV6_ADDR_LINKLOCAL)
+		iif = skb->dev->ifindex;
+
+	/*
+	 *	Must not send if we know that source is Anycast also.
+	 *	for now we don't know that.
+	 */
+	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
+		LIMIT_NETDEBUG(
+			printk(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n"));
+		return;
+	}
+
+	/* 
+	 *	Never answer to a ICMP packet.
+	 */
+	if (is_ineligible(skb)) {
+		LIMIT_NETDEBUG(
+			printk(KERN_DEBUG "icmpv6_send: no reply to icmp error\n")); 
+		return;
+	}
+
+	memset(&fl, 0, sizeof(fl));
+	fl.proto = IPPROTO_ICMPV6;
+	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
+	if (saddr)
+		ipv6_addr_copy(&fl.fl6_src, saddr);
+	fl.oif = iif;
+	fl.fl_icmp_type = type;
+	fl.fl_icmp_code = code;
+
+	if (icmpv6_xmit_lock())
+		return;
+
+	if (!icmpv6_xrlim_allow(sk, type, &fl))
+		goto out;
+
+	tmp_hdr.icmp6_type = type;
+	tmp_hdr.icmp6_code = code;
+	tmp_hdr.icmp6_cksum = 0;
+	tmp_hdr.icmp6_pointer = htonl(info);
+
+	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
+		fl.oif = np->mcast_oif;
+
+	err = ip6_dst_lookup(sk, &dst, &fl);
+	if (err)
+		goto out;
+	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+		goto out_dst_release;
+
+	if (ipv6_addr_is_multicast(&fl.fl6_dst))
+		hlimit = np->mcast_hops;
+	else
+		hlimit = np->hop_limit;
+	if (hlimit < 0)
+		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
+	if (hlimit < 0)
+		hlimit = ipv6_get_hoplimit(dst->dev);
+
+	msg.skb = skb;
+	msg.offset = skb->nh.raw - skb->data;
+
+	len = skb->len - msg.offset;
+	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
+	if (len < 0) {
+		LIMIT_NETDEBUG(
+			printk(KERN_DEBUG "icmp: len problem\n"));
+		goto out_dst_release;
+	}
+
+	idev = in6_dev_get(skb->dev);
+
+	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
+			      len + sizeof(struct icmp6hdr),
+			      sizeof(struct icmp6hdr),
+			      hlimit, NULL, &fl, (struct rt6_info*)dst,
+			      MSG_DONTWAIT);
+	if (err) {
+		ip6_flush_pending_frames(sk);
+		goto out_put;
+	}
+	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, len + sizeof(struct icmp6hdr));
+
+	if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB)
+		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_OUTDESTUNREACHS, type - ICMPV6_DEST_UNREACH);
+	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS);
+
+out_put:
+	if (likely(idev != NULL))
+		in6_dev_put(idev);
+out_dst_release:
+	dst_release(dst);
+out:
+	icmpv6_xmit_unlock();
+}
+
+static void icmpv6_echo_reply(struct sk_buff *skb)
+{
+	struct sock *sk = icmpv6_socket->sk;
+	struct inet6_dev *idev;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct in6_addr *saddr = NULL;
+	struct icmp6hdr *icmph = (struct icmp6hdr *) skb->h.raw;
+	struct icmp6hdr tmp_hdr;
+	struct flowi fl;
+	struct icmpv6_msg msg;
+	struct dst_entry *dst;
+	int err = 0;
+	int hlimit;
+
+	saddr = &skb->nh.ipv6h->daddr;
+
+	if (!ipv6_unicast_destination(skb))
+		saddr = NULL;
+
+	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
+	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
+
+	memset(&fl, 0, sizeof(fl));
+	fl.proto = IPPROTO_ICMPV6;
+	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
+	if (saddr)
+		ipv6_addr_copy(&fl.fl6_src, saddr);
+	fl.oif = skb->dev->ifindex;
+	fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
+
+	if (icmpv6_xmit_lock())
+		return;
+
+	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
+		fl.oif = np->mcast_oif;
+
+	err = ip6_dst_lookup(sk, &dst, &fl);
+	if (err)
+		goto out;
+	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+		goto out_dst_release;
+
+	if (ipv6_addr_is_multicast(&fl.fl6_dst))
+		hlimit = np->mcast_hops;
+	else
+		hlimit = np->hop_limit;
+	if (hlimit < 0)
+		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
+	if (hlimit < 0)
+		hlimit = ipv6_get_hoplimit(dst->dev);
+
+	idev = in6_dev_get(skb->dev);
+
+	msg.skb = skb;
+	msg.offset = 0;
+
+	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
+				sizeof(struct icmp6hdr), hlimit, NULL, &fl,
+				(struct rt6_info*)dst, MSG_DONTWAIT);
+
+	if (err) {
+		ip6_flush_pending_frames(sk);
+		goto out_put;
+	}
+	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, skb->len + sizeof(struct icmp6hdr));
+
+        ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTECHOREPLIES);
+        ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS);
+
+out_put: 
+	if (likely(idev != NULL))
+		in6_dev_put(idev);
+out_dst_release:
+	dst_release(dst);
+out: 
+	icmpv6_xmit_unlock();
+}
+
+static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
+{
+	struct in6_addr *saddr, *daddr;
+	struct inet6_protocol *ipprot;
+	struct sock *sk;
+	int inner_offset;
+	int hash;
+	u8 nexthdr;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		return;
+
+	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
+	if (ipv6_ext_hdr(nexthdr)) {
+		/* now skip over extension headers */
+		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, skb->len - sizeof(struct ipv6hdr));
+		if (inner_offset<0)
+			return;
+	} else {
+		inner_offset = sizeof(struct ipv6hdr);
+	}
+
+	/* Checkin header including 8 bytes of inner protocol header. */
+	if (!pskb_may_pull(skb, inner_offset+8))
+		return;
+
+	saddr = &skb->nh.ipv6h->saddr;
+	daddr = &skb->nh.ipv6h->daddr;
+
+	/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
+	   Without this we will not able f.e. to make source routed
+	   pmtu discovery.
+	   Corresponding argument (opt) to notifiers is already added.
+	   --ANK (980726)
+	 */
+
+	hash = nexthdr & (MAX_INET_PROTOS - 1);
+
+	rcu_read_lock();
+	ipprot = rcu_dereference(inet6_protos[hash]);
+	if (ipprot && ipprot->err_handler)
+		ipprot->err_handler(skb, NULL, type, code, inner_offset, info);
+	rcu_read_unlock();
+
+	read_lock(&raw_v6_lock);
+	if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) {
+		while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr))) {
+			rawv6_err(sk, skb, NULL, type, code, inner_offset, info);
+			sk = sk_next(sk);
+		}
+	}
+	read_unlock(&raw_v6_lock);
+}
+  
+/*
+ *	Handle icmp messages
+ */
+
+static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *pskb;
+	struct net_device *dev = skb->dev;
+	struct inet6_dev *idev = __in6_dev_get(dev);
+	struct in6_addr *saddr, *daddr;
+	struct ipv6hdr *orig_hdr;
+	struct icmp6hdr *hdr;
+	int type;
+
+	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INMSGS);
+
+	saddr = &skb->nh.ipv6h->saddr;
+	daddr = &skb->nh.ipv6h->daddr;
+
+	/* Perform checksum. */
+	if (skb->ip_summed == CHECKSUM_HW) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
+				    skb->csum)) {
+			LIMIT_NETDEBUG(
+				printk(KERN_DEBUG "ICMPv6 hw checksum failed\n"));
+			skb->ip_summed = CHECKSUM_NONE;
+		}
+	}
+	if (skb->ip_summed == CHECKSUM_NONE) {
+		if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
+				    skb_checksum(skb, 0, skb->len, 0))) {
+			LIMIT_NETDEBUG(
+				printk(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n",
+				       NIP6(*saddr), NIP6(*daddr)));
+			goto discard_it;
+		}
+	}
+
+	if (!pskb_pull(skb, sizeof(struct icmp6hdr)))
+		goto discard_it;
+
+	hdr = (struct icmp6hdr *) skb->h.raw;
+
+	type = hdr->icmp6_type;
+
+	if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB)
+		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INDESTUNREACHS, type - ICMPV6_DEST_UNREACH);
+	else if (type >= ICMPV6_ECHO_REQUEST && type <= NDISC_REDIRECT)
+		ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INECHOS, type - ICMPV6_ECHO_REQUEST);
+
+	switch (type) {
+	case ICMPV6_ECHO_REQUEST:
+		icmpv6_echo_reply(skb);
+		break;
+
+	case ICMPV6_ECHO_REPLY:
+		/* we couldn't care less */
+		break;
+
+	case ICMPV6_PKT_TOOBIG:
+		/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
+		   standard destination cache. Seems, only "advanced"
+		   destination cache will allow to solve this problem
+		   --ANK (980726)
+		 */
+		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+			goto discard_it;
+		hdr = (struct icmp6hdr *) skb->h.raw;
+		orig_hdr = (struct ipv6hdr *) (hdr + 1);
+		rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
+				   ntohl(hdr->icmp6_mtu));
+
+		/*
+		 *	Drop through to notify
+		 */
+
+	case ICMPV6_DEST_UNREACH:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
+		break;
+
+	case NDISC_ROUTER_SOLICITATION:
+	case NDISC_ROUTER_ADVERTISEMENT:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+	case NDISC_REDIRECT:
+		ndisc_rcv(skb);
+		break;
+
+	case ICMPV6_MGM_QUERY:
+		igmp6_event_query(skb);
+		break;
+
+	case ICMPV6_MGM_REPORT:
+		igmp6_event_report(skb);
+		break;
+
+	case ICMPV6_MGM_REDUCTION:
+	case ICMPV6_NI_QUERY:
+	case ICMPV6_NI_REPLY:
+	case ICMPV6_MLD2_REPORT:
+	case ICMPV6_DHAAD_REQUEST:
+	case ICMPV6_DHAAD_REPLY:
+	case ICMPV6_MOBILE_PREFIX_SOL:
+	case ICMPV6_MOBILE_PREFIX_ADV:
+		break;
+
+	default:
+		LIMIT_NETDEBUG(
+			printk(KERN_DEBUG "icmpv6: msg of unknown type\n"));
+
+		/* informational */
+		if (type & ICMPV6_INFOMSG_MASK)
+			break;
+
+		/* 
+		 * error of unknown type. 
+		 * must pass to upper level 
+		 */
+
+		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
+	};
+	kfree_skb(skb);
+	return 0;
+
+discard_it:
+	ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INERRORS);
+	kfree_skb(skb);
+	return 0;
+}
+
+int __init icmpv6_init(struct net_proto_family *ops)
+{
+	struct sock *sk;
+	int err, i, j;
+
+	for (i = 0; i < NR_CPUS; i++) {
+		if (!cpu_possible(i))
+			continue;
+
+		err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6,
+				       &per_cpu(__icmpv6_socket, i));
+		if (err < 0) {
+			printk(KERN_ERR
+			       "Failed to initialize the ICMP6 control socket "
+			       "(err %d).\n",
+			       err);
+			goto fail;
+		}
+
+		sk = per_cpu(__icmpv6_socket, i)->sk;
+		sk->sk_allocation = GFP_ATOMIC;
+
+		/* Enough space for 2 64K ICMP packets, including
+		 * sk_buff struct overhead.
+		 */
+		sk->sk_sndbuf =
+			(2 * ((64 * 1024) + sizeof(struct sk_buff)));
+
+		sk->sk_prot->unhash(sk);
+	}
+
+
+	if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) {
+		printk(KERN_ERR "Failed to register ICMP6 protocol\n");
+		err = -EAGAIN;
+		goto fail;
+	}
+
+	return 0;
+
+ fail:
+	for (j = 0; j < i; j++) {
+		if (!cpu_possible(j))
+			continue;
+		sock_release(per_cpu(__icmpv6_socket, j));
+	}
+
+	return err;
+}
+
+void icmpv6_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++) {
+		if (!cpu_possible(i))
+			continue;
+		sock_release(per_cpu(__icmpv6_socket, i));
+	}
+	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
+}
+
+static struct icmp6_err {
+	int err;
+	int fatal;
+} tab_unreach[] = {
+	{	/* NOROUTE */
+		.err	= ENETUNREACH,
+		.fatal	= 0,
+	},
+	{	/* ADM_PROHIBITED */
+		.err	= EACCES,
+		.fatal	= 1,
+	},
+	{	/* Was NOT_NEIGHBOUR, now reserved */
+		.err	= EHOSTUNREACH,
+		.fatal	= 0,
+	},
+	{	/* ADDR_UNREACH	*/
+		.err	= EHOSTUNREACH,
+		.fatal	= 0,
+	},
+	{	/* PORT_UNREACH	*/
+		.err	= ECONNREFUSED,
+		.fatal	= 1,
+	},
+};
+
+int icmpv6_err_convert(int type, int code, int *err)
+{
+	int fatal = 0;
+
+	*err = EPROTO;
+
+	switch (type) {
+	case ICMPV6_DEST_UNREACH:
+		fatal = 1;
+		if (code <= ICMPV6_PORT_UNREACH) {
+			*err  = tab_unreach[code].err;
+			fatal = tab_unreach[code].fatal;
+		}
+		break;
+
+	case ICMPV6_PKT_TOOBIG:
+		*err = EMSGSIZE;
+		break;
+		
+	case ICMPV6_PARAMPROB:
+		*err = EPROTO;
+		fatal = 1;
+		break;
+
+	case ICMPV6_TIME_EXCEED:
+		*err = EHOSTUNREACH;
+		break;
+	};
+
+	return fatal;
+}
+
+#ifdef CONFIG_SYSCTL
+ctl_table ipv6_icmp_table[] = {
+	{
+		.ctl_name	= NET_IPV6_ICMP_RATELIMIT,
+		.procname	= "ratelimit",
+		.data		= &sysctl_icmpv6_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{ .ctl_name = 0 },
+};
+#endif
+

net/ipv6/ip6_flowlabel.c

@@ -0,0 +1,706 @@
+/*
+ *	ip6_flowlabel.c		IPv6 flowlabel manager.
+ *
+ *	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.
+ *
+ *	Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/in6.h>
+#include <linux/route.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+#include <net/sock.h>
+
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+#include <net/protocol.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/rawv6.h>
+#include <net/icmp.h>
+#include <net/transp_v6.h>
+
+#include <asm/uaccess.h>
+
+#define FL_MIN_LINGER	6	/* Minimal linger. It is set to 6sec specified
+				   in old IPv6 RFC. Well, it was reasonable value.
+				 */
+#define FL_MAX_LINGER	60	/* Maximal linger timeout */
+
+/* FL hash table */
+
+#define FL_MAX_PER_SOCK	32
+#define FL_MAX_SIZE	4096
+#define FL_HASH_MASK	255
+#define FL_HASH(l)	(ntohl(l)&FL_HASH_MASK)
+
+static atomic_t fl_size = ATOMIC_INIT(0);
+static struct ip6_flowlabel *fl_ht[FL_HASH_MASK+1];
+
+static void ip6_fl_gc(unsigned long dummy);
+static struct timer_list ip6_fl_gc_timer = TIMER_INITIALIZER(ip6_fl_gc, 0, 0);
+
+/* FL hash table lock: it protects only of GC */
+
+static DEFINE_RWLOCK(ip6_fl_lock);
+
+/* Big socket sock */
+
+static DEFINE_RWLOCK(ip6_sk_fl_lock);
+
+
+static __inline__ struct ip6_flowlabel * __fl_lookup(u32 label)
+{
+	struct ip6_flowlabel *fl;
+
+	for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) {
+		if (fl->label == label)
+			return fl;
+	}
+	return NULL;
+}
+
+static struct ip6_flowlabel * fl_lookup(u32 label)
+{
+	struct ip6_flowlabel *fl;
+
+	read_lock_bh(&ip6_fl_lock);
+	fl = __fl_lookup(label);
+	if (fl)
+		atomic_inc(&fl->users);
+	read_unlock_bh(&ip6_fl_lock);
+	return fl;
+}
+
+
+static void fl_free(struct ip6_flowlabel *fl)
+{
+	if (fl)
+		kfree(fl->opt);
+	kfree(fl);
+}
+
+static void fl_release(struct ip6_flowlabel *fl)
+{
+	write_lock_bh(&ip6_fl_lock);
+
+	fl->lastuse = jiffies;
+	if (atomic_dec_and_test(&fl->users)) {
+		unsigned long ttd = fl->lastuse + fl->linger;
+		if (time_after(ttd, fl->expires))
+			fl->expires = ttd;
+		ttd = fl->expires;
+		if (fl->opt && fl->share == IPV6_FL_S_EXCL) {
+			struct ipv6_txoptions *opt = fl->opt;
+			fl->opt = NULL;
+			kfree(opt);
+		}
+		if (!timer_pending(&ip6_fl_gc_timer) ||
+		    time_after(ip6_fl_gc_timer.expires, ttd))
+			mod_timer(&ip6_fl_gc_timer, ttd);
+	}
+
+	write_unlock_bh(&ip6_fl_lock);
+}
+
+static void ip6_fl_gc(unsigned long dummy)
+{
+	int i;
+	unsigned long now = jiffies;
+	unsigned long sched = 0;
+
+	write_lock(&ip6_fl_lock);
+
+	for (i=0; i<=FL_HASH_MASK; i++) {
+		struct ip6_flowlabel *fl, **flp;
+		flp = &fl_ht[i];
+		while ((fl=*flp) != NULL) {
+			if (atomic_read(&fl->users) == 0) {
+				unsigned long ttd = fl->lastuse + fl->linger;
+				if (time_after(ttd, fl->expires))
+					fl->expires = ttd;
+				ttd = fl->expires;
+				if (time_after_eq(now, ttd)) {
+					*flp = fl->next;
+					fl_free(fl);
+					atomic_dec(&fl_size);
+					continue;
+				}
+				if (!sched || time_before(ttd, sched))
+					sched = ttd;
+			}
+			flp = &fl->next;
+		}
+	}
+	if (!sched && atomic_read(&fl_size))
+		sched = now + FL_MAX_LINGER;
+	if (sched) {
+		ip6_fl_gc_timer.expires = sched;
+		add_timer(&ip6_fl_gc_timer);
+	}
+	write_unlock(&ip6_fl_lock);
+}
+
+static int fl_intern(struct ip6_flowlabel *fl, __u32 label)
+{
+	fl->label = label & IPV6_FLOWLABEL_MASK;
+
+	write_lock_bh(&ip6_fl_lock);
+	if (label == 0) {
+		for (;;) {
+			fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK;
+			if (fl->label) {
+				struct ip6_flowlabel *lfl;
+				lfl = __fl_lookup(fl->label);
+				if (lfl == NULL)
+					break;
+			}
+		}
+	}
+
+	fl->lastuse = jiffies;
+	fl->next = fl_ht[FL_HASH(fl->label)];
+	fl_ht[FL_HASH(fl->label)] = fl;
+	atomic_inc(&fl_size);
+	write_unlock_bh(&ip6_fl_lock);
+	return 0;
+}
+
+
+
+/* Socket flowlabel lists */
+
+struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, u32 label)
+{
+	struct ipv6_fl_socklist *sfl;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	label &= IPV6_FLOWLABEL_MASK;
+
+	for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) {
+		struct ip6_flowlabel *fl = sfl->fl;
+		if (fl->label == label) {
+			fl->lastuse = jiffies;
+			atomic_inc(&fl->users);
+			return fl;
+		}
+	}
+	return NULL;
+}
+
+void fl6_free_socklist(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_fl_socklist *sfl;
+
+	while ((sfl = np->ipv6_fl_list) != NULL) {
+		np->ipv6_fl_list = sfl->next;
+		fl_release(sfl->fl);
+		kfree(sfl);
+	}
+}
+
+/* Service routines */
+
+
+/*
+   It is the only difficult place. flowlabel enforces equal headers
+   before and including routing header, however user may supply options
+   following rthdr.
+ */
+
+struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
+					 struct ip6_flowlabel * fl,
+					 struct ipv6_txoptions * fopt)
+{
+	struct ipv6_txoptions * fl_opt = fl->opt;
+
+	if (fopt == NULL || fopt->opt_flen == 0)
+		return fl_opt;
+
+	if (fl_opt != NULL) {
+		opt_space->hopopt = fl_opt->hopopt;
+		opt_space->dst0opt = fl_opt->dst0opt;
+		opt_space->srcrt = fl_opt->srcrt;
+		opt_space->opt_nflen = fl_opt->opt_nflen;
+	} else {
+		if (fopt->opt_nflen == 0)
+			return fopt;
+		opt_space->hopopt = NULL;
+		opt_space->dst0opt = NULL;
+		opt_space->srcrt = NULL;
+		opt_space->opt_nflen = 0;
+	}
+	opt_space->dst1opt = fopt->dst1opt;
+	opt_space->auth = fopt->auth;
+	opt_space->opt_flen = fopt->opt_flen;
+	return opt_space;
+}
+
+static unsigned long check_linger(unsigned long ttl)
+{
+	if (ttl < FL_MIN_LINGER)
+		return FL_MIN_LINGER*HZ;
+	if (ttl > FL_MAX_LINGER && !capable(CAP_NET_ADMIN))
+		return 0;
+	return ttl*HZ;
+}
+
+static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned long expires)
+{
+	linger = check_linger(linger);
+	if (!linger)
+		return -EPERM;
+	expires = check_linger(expires);
+	if (!expires)
+		return -EPERM;
+	fl->lastuse = jiffies;
+	if (time_before(fl->linger, linger))
+		fl->linger = linger;
+	if (time_before(expires, fl->linger))
+		expires = fl->linger;
+	if (time_before(fl->expires, fl->lastuse + expires))
+		fl->expires = fl->lastuse + expires;
+	return 0;
+}
+
+static struct ip6_flowlabel *
+fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *err_p)
+{
+	struct ip6_flowlabel *fl;
+	int olen;
+	int addr_type;
+	int err;
+
+	err = -ENOMEM;
+	fl = kmalloc(sizeof(*fl), GFP_KERNEL);
+	if (fl == NULL)
+		goto done;
+	memset(fl, 0, sizeof(*fl));
+
+	olen = optlen - CMSG_ALIGN(sizeof(*freq));
+	if (olen > 0) {
+		struct msghdr msg;
+		struct flowi flowi;
+		int junk;
+
+		err = -ENOMEM;
+		fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL);
+		if (fl->opt == NULL)
+			goto done;
+
+		memset(fl->opt, 0, sizeof(*fl->opt));
+		fl->opt->tot_len = sizeof(*fl->opt) + olen;
+		err = -EFAULT;
+		if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen))
+			goto done;
+
+		msg.msg_controllen = olen;
+		msg.msg_control = (void*)(fl->opt+1);
+		flowi.oif = 0;
+
+		err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk);
+		if (err)
+			goto done;
+		err = -EINVAL;
+		if (fl->opt->opt_flen)
+			goto done;
+		if (fl->opt->opt_nflen == 0) {
+			kfree(fl->opt);
+			fl->opt = NULL;
+		}
+	}
+
+	fl->expires = jiffies;
+	err = fl6_renew(fl, freq->flr_linger, freq->flr_expires);
+	if (err)
+		goto done;
+	fl->share = freq->flr_share;
+	addr_type = ipv6_addr_type(&freq->flr_dst);
+	if ((addr_type&IPV6_ADDR_MAPPED)
+	    || addr_type == IPV6_ADDR_ANY)
+		goto done;
+	ipv6_addr_copy(&fl->dst, &freq->flr_dst);
+	atomic_set(&fl->users, 1);
+	switch (fl->share) {
+	case IPV6_FL_S_EXCL:
+	case IPV6_FL_S_ANY:
+		break;
+	case IPV6_FL_S_PROCESS:
+		fl->owner = current->pid;
+		break;
+	case IPV6_FL_S_USER:
+		fl->owner = current->euid;
+		break;
+	default:
+		err = -EINVAL;
+		goto done;
+	}
+	return fl;
+
+done:
+	fl_free(fl);
+	*err_p = err;
+	return NULL;
+}
+
+static int mem_check(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_fl_socklist *sfl;
+	int room = FL_MAX_SIZE - atomic_read(&fl_size);
+	int count = 0;
+
+	if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
+		return 0;
+
+	for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next)
+		count++;
+
+	if (room <= 0 ||
+	    ((count >= FL_MAX_PER_SOCK ||
+	     (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4)
+	     && !capable(CAP_NET_ADMIN)))
+		return -ENOBUFS;
+
+	return 0;
+}
+
+static int ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2)
+{
+	if (h1 == h2)
+		return 0;
+	if (h1 == NULL || h2 == NULL)
+		return 1;
+	if (h1->hdrlen != h2->hdrlen)
+		return 1;
+	return memcmp(h1+1, h2+1, ((h1->hdrlen+1)<<3) - sizeof(*h1));
+}
+
+static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2)
+{
+	if (o1 == o2)
+		return 0;
+	if (o1 == NULL || o2 == NULL)
+		return 1;
+	if (o1->opt_nflen != o2->opt_nflen)
+		return 1;
+	if (ipv6_hdr_cmp(o1->hopopt, o2->hopopt))
+		return 1;
+	if (ipv6_hdr_cmp(o1->dst0opt, o2->dst0opt))
+		return 1;
+	if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt))
+		return 1;
+	return 0;
+}
+
+int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
+{
+	int err;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct in6_flowlabel_req freq;
+	struct ipv6_fl_socklist *sfl1=NULL;
+	struct ipv6_fl_socklist *sfl, **sflp;
+	struct ip6_flowlabel *fl;
+
+	if (optlen < sizeof(freq))
+		return -EINVAL;
+
+	if (copy_from_user(&freq, optval, sizeof(freq)))
+		return -EFAULT;
+
+	switch (freq.flr_action) {
+	case IPV6_FL_A_PUT:
+		write_lock_bh(&ip6_sk_fl_lock);
+		for (sflp = &np->ipv6_fl_list; (sfl=*sflp)!=NULL; sflp = &sfl->next) {
+			if (sfl->fl->label == freq.flr_label) {
+				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
+					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
+				*sflp = sfl->next;
+				write_unlock_bh(&ip6_sk_fl_lock);
+				fl_release(sfl->fl);
+				kfree(sfl);
+				return 0;
+			}
+		}
+		write_unlock_bh(&ip6_sk_fl_lock);
+		return -ESRCH;
+
+	case IPV6_FL_A_RENEW:
+		read_lock_bh(&ip6_sk_fl_lock);
+		for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) {
+			if (sfl->fl->label == freq.flr_label) {
+				err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires);
+				read_unlock_bh(&ip6_sk_fl_lock);
+				return err;
+			}
+		}
+		read_unlock_bh(&ip6_sk_fl_lock);
+
+		if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) {
+			fl = fl_lookup(freq.flr_label);
+			if (fl) {
+				err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
+				fl_release(fl);
+				return err;
+			}
+		}
+		return -ESRCH;
+
+	case IPV6_FL_A_GET:
+		if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
+			return -EINVAL;
+
+		fl = fl_create(&freq, optval, optlen, &err);
+		if (fl == NULL)
+			return err;
+		sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
+
+		if (freq.flr_label) {
+			struct ip6_flowlabel *fl1 = NULL;
+
+			err = -EEXIST;
+			read_lock_bh(&ip6_sk_fl_lock);
+			for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) {
+				if (sfl->fl->label == freq.flr_label) {
+					if (freq.flr_flags&IPV6_FL_F_EXCL) {
+						read_unlock_bh(&ip6_sk_fl_lock);
+						goto done;
+					}
+					fl1 = sfl->fl;
+					atomic_inc(&fl->users);
+					break;
+				}
+			}
+			read_unlock_bh(&ip6_sk_fl_lock);
+
+			if (fl1 == NULL)
+				fl1 = fl_lookup(freq.flr_label);
+			if (fl1) {
+				err = -EEXIST;
+				if (freq.flr_flags&IPV6_FL_F_EXCL)
+					goto release;
+				err = -EPERM;
+				if (fl1->share == IPV6_FL_S_EXCL ||
+				    fl1->share != fl->share ||
+				    fl1->owner != fl->owner)
+					goto release;
+
+				err = -EINVAL;
+				if (!ipv6_addr_equal(&fl1->dst, &fl->dst) ||
+				    ipv6_opt_cmp(fl1->opt, fl->opt))
+					goto release;
+
+				err = -ENOMEM;
+				if (sfl1 == NULL)
+					goto release;
+				if (fl->linger > fl1->linger)
+					fl1->linger = fl->linger;
+				if ((long)(fl->expires - fl1->expires) > 0)
+					fl1->expires = fl->expires;
+				write_lock_bh(&ip6_sk_fl_lock);
+				sfl1->fl = fl1;
+				sfl1->next = np->ipv6_fl_list;
+				np->ipv6_fl_list = sfl1;
+				write_unlock_bh(&ip6_sk_fl_lock);
+				fl_free(fl);
+				return 0;
+
+release:
+				fl_release(fl1);
+				goto done;
+			}
+		}
+		err = -ENOENT;
+		if (!(freq.flr_flags&IPV6_FL_F_CREATE))
+			goto done;
+
+		err = -ENOMEM;
+		if (sfl1 == NULL || (err = mem_check(sk)) != 0)
+			goto done;
+
+		err = fl_intern(fl, freq.flr_label);
+		if (err)
+			goto done;
+
+		/* Do not check for fault */
+		if (!freq.flr_label)
+			copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
+				     &fl->label, sizeof(fl->label));
+
+		sfl1->fl = fl;
+		sfl1->next = np->ipv6_fl_list;
+		np->ipv6_fl_list = sfl1;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+
+done:
+	fl_free(fl);
+	kfree(sfl1);
+	return err;
+}
+
+#ifdef CONFIG_PROC_FS
+
+struct ip6fl_iter_state {
+	int bucket;
+};
+
+#define ip6fl_seq_private(seq)	((struct ip6fl_iter_state *)(seq)->private)
+
+static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq)
+{
+	struct ip6_flowlabel *fl = NULL;
+	struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
+
+	for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) {
+		if (fl_ht[state->bucket]) {
+			fl = fl_ht[state->bucket];
+			break;
+		}
+	}
+	return fl;
+}
+
+static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flowlabel *fl)
+{
+	struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
+
+	fl = fl->next;
+	while (!fl) {
+		if (++state->bucket <= FL_HASH_MASK)
+			fl = fl_ht[state->bucket];
+	}
+	return fl;
+}
+
+static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos)
+{
+	struct ip6_flowlabel *fl = ip6fl_get_first(seq);
+	if (fl)
+		while (pos && (fl = ip6fl_get_next(seq, fl)) != NULL)
+			--pos;
+	return pos ? NULL : fl;
+}
+
+static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	read_lock_bh(&ip6_fl_lock);
+	return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+}
+
+static void *ip6fl_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct ip6_flowlabel *fl;
+
+	if (v == SEQ_START_TOKEN)
+		fl = ip6fl_get_first(seq);
+	else
+		fl = ip6fl_get_next(seq, v);
+	++*pos;
+	return fl;
+}
+
+static void ip6fl_seq_stop(struct seq_file *seq, void *v)
+{
+	read_unlock_bh(&ip6_fl_lock);
+}
+
+static void ip6fl_fl_seq_show(struct seq_file *seq, struct ip6_flowlabel *fl)
+{
+	while(fl) {
+		seq_printf(seq,
+			   "%05X %-1d %-6d %-6d %-6ld %-8ld "
+			   "%02x%02x%02x%02x%02x%02x%02x%02x "
+			   "%-4d\n",
+			   (unsigned)ntohl(fl->label),
+			   fl->share,
+			   (unsigned)fl->owner,
+			   atomic_read(&fl->users),
+			   fl->linger/HZ,
+			   (long)(fl->expires - jiffies)/HZ,
+			   NIP6(fl->dst),
+			   fl->opt ? fl->opt->opt_nflen : 0);
+		fl = fl->next;
+	}
+}
+
+static int ip6fl_seq_show(struct seq_file *seq, void *v)
+{
+	if (v == SEQ_START_TOKEN)
+		seq_puts(seq, "Label S Owner  Users  Linger Expires  "
+			      "Dst                              Opt\n");
+	else
+		ip6fl_fl_seq_show(seq, v);
+	return 0;
+}
+
+static struct seq_operations ip6fl_seq_ops = {
+	.start	=	ip6fl_seq_start,
+	.next	=	ip6fl_seq_next,
+	.stop	=	ip6fl_seq_stop,
+	.show	=	ip6fl_seq_show,
+};
+
+static int ip6fl_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int rc = -ENOMEM;
+	struct ip6fl_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+
+	if (!s)
+		goto out;
+
+	rc = seq_open(file, &ip6fl_seq_ops);
+	if (rc)
+		goto out_kfree;
+
+	seq = file->private_data;
+	seq->private = s;
+	memset(s, 0, sizeof(*s));
+out:
+	return rc;
+out_kfree:
+	kfree(s);
+	goto out;
+}
+
+static struct file_operations ip6fl_seq_fops = {
+	.owner		=	THIS_MODULE,
+	.open		=	ip6fl_seq_open,
+	.read		=	seq_read,
+	.llseek		=	seq_lseek,
+	.release	=	seq_release_private,
+};
+#endif
+
+
+void ip6_flowlabel_init(void)
+{
+#ifdef CONFIG_PROC_FS
+	proc_net_fops_create("ip6_flowlabel", S_IRUGO, &ip6fl_seq_fops);
+#endif
+}
+
+void ip6_flowlabel_cleanup(void)
+{
+	del_timer(&ip6_fl_gc_timer);
+#ifdef CONFIG_PROC_FS
+	proc_net_remove("ip6_flowlabel");
+#endif
+}

net/ipv6/ip6_input.c

@@ -0,0 +1,269 @@
+/*
+ *	IPv6 input
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>
+ *	Ian P. Morris		<I.P.Morris@soton.ac.uk>
+ *
+ *	$Id: ip6_input.c,v 1.19 2000/12/13 18:31:50 davem Exp $
+ *
+ *	Based in linux/net/ipv4/ip_input.c
+ *
+ *	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.
+ */
+/* Changes
+ *
+ * 	Mitsuru KANDA @USAGI and
+ * 	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+
+
+
+static inline int ip6_rcv_finish( struct sk_buff *skb) 
+{
+	if (skb->dst == NULL)
+		ip6_route_input(skb);
+
+	return dst_input(skb);
+}
+
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
+{
+	struct ipv6hdr *hdr;
+	u32 		pkt_len;
+
+	if (skb->pkt_type == PACKET_OTHERHOST)
+		goto drop;
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_INRECEIVES);
+
+	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
+		goto out;
+	}
+
+	/*
+	 * Store incoming device index. When the packet will
+	 * be queued, we cannot refer to skb->dev anymore.
+	 *
+	 * BTW, when we send a packet for our own local address on a
+	 * non-loopback interface (e.g. ethX), it is being delivered
+	 * via the loopback interface (lo) here; skb->dev = &loopback_dev.
+	 * It, however, should be considered as if it is being
+	 * arrived via the sending interface (ethX), because of the
+	 * nature of scoping architecture. --yoshfuji
+	 */
+	IP6CB(skb)->iif = skb->dst ? ((struct rt6_info *)skb->dst)->rt6i_idev->dev->ifindex : dev->ifindex;
+
+	if (skb->len < sizeof(struct ipv6hdr))
+		goto err;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+		goto drop;
+	}
+
+	hdr = skb->nh.ipv6h;
+
+	if (hdr->version != 6)
+		goto err;
+
+	pkt_len = ntohs(hdr->payload_len);
+
+	/* pkt_len may be zero if Jumbo payload option is present */
+	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
+		if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+			goto truncated;
+		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
+			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+			goto drop;
+		}
+		hdr = skb->nh.ipv6h;
+	}
+
+	if (hdr->nexthdr == NEXTHDR_HOP) {
+		skb->h.raw = (u8*)(hdr+1);
+		if (ipv6_parse_hopopts(skb, offsetof(struct ipv6hdr, nexthdr)) < 0) {
+			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+			return 0;
+		}
+		hdr = skb->nh.ipv6h;
+	}
+
+	return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish);
+truncated:
+	IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS);
+err:
+	IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+drop:
+	kfree_skb(skb);
+out:
+	return 0;
+}
+
+/*
+ *	Deliver the packet to the host
+ */
+
+
+static inline int ip6_input_finish(struct sk_buff *skb)
+{
+	struct inet6_protocol *ipprot;
+	struct sock *raw_sk;
+	unsigned int nhoff;
+	int nexthdr;
+	u8 hash;
+
+	skb->h.raw = skb->nh.raw + sizeof(struct ipv6hdr);
+
+	/*
+	 *	Parse extension headers
+	 */
+
+	nexthdr = skb->nh.ipv6h->nexthdr;
+	nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	/* Skip hop-by-hop options, they are already parsed. */
+	if (nexthdr == NEXTHDR_HOP) {
+		nhoff = sizeof(struct ipv6hdr);
+		nexthdr = skb->h.raw[0];
+		skb->h.raw += (skb->h.raw[1]+1)<<3;
+	}
+
+	rcu_read_lock();
+resubmit:
+	if (!pskb_pull(skb, skb->h.raw - skb->data))
+		goto discard;
+	nexthdr = skb->nh.raw[nhoff];
+
+	raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]);
+	if (raw_sk)
+		ipv6_raw_deliver(skb, nexthdr);
+
+	hash = nexthdr & (MAX_INET_PROTOS - 1);
+	if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {
+		int ret;
+		
+		if (ipprot->flags & INET6_PROTO_FINAL) {
+			struct ipv6hdr *hdr;	
+
+			skb_postpull_rcsum(skb, skb->nh.raw,
+					   skb->h.raw - skb->nh.raw);
+			hdr = skb->nh.ipv6h;
+			if (ipv6_addr_is_multicast(&hdr->daddr) &&
+			    !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
+			    &hdr->saddr) &&
+			    !ipv6_is_mld(skb, nexthdr))
+				goto discard;
+		}
+		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
+		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) 
+			goto discard;
+		
+		ret = ipprot->handler(&skb, &nhoff);
+		if (ret > 0)
+			goto resubmit;
+		else if (ret == 0)
+			IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
+	} else {
+		if (!raw_sk) {
+			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				IP6_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS);
+				icmpv6_param_prob(skb, ICMPV6_UNK_NEXTHDR, nhoff);
+			}
+		} else {
+			IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
+			kfree_skb(skb);
+		}
+	}
+	rcu_read_unlock();
+	return 0;
+
+discard:
+	IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
+	rcu_read_unlock();
+	kfree_skb(skb);
+	return 0;
+}
+
+
+int ip6_input(struct sk_buff *skb)
+{
+	return NF_HOOK(PF_INET6,NF_IP6_LOCAL_IN, skb, skb->dev, NULL, ip6_input_finish);
+}
+
+int ip6_mc_input(struct sk_buff *skb)
+{
+	struct ipv6hdr *hdr;
+	int deliver;
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS);
+
+	hdr = skb->nh.ipv6h;
+	deliver = likely(!(skb->dev->flags & (IFF_PROMISC|IFF_ALLMULTI))) ||
+	    ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+
+	/*
+	 *	IPv6 multicast router mode isnt currently supported.
+	 */
+#if 0
+	if (ipv6_config.multicast_route) {
+		int addr_type;
+
+		addr_type = ipv6_addr_type(&hdr->daddr);
+
+		if (!(addr_type & (IPV6_ADDR_LOOPBACK | IPV6_ADDR_LINKLOCAL))) {
+			struct sk_buff *skb2;
+			struct dst_entry *dst;
+
+			dst = skb->dst;
+			
+			if (deliver) {
+				skb2 = skb_clone(skb, GFP_ATOMIC);
+				dst_output(skb2);
+			} else {
+				dst_output(skb);
+				return 0;
+			}
+		}
+	}
+#endif
+
+	if (likely(deliver)) {
+		ip6_input(skb);
+		return 0;
+	}
+	/* discard */
+	kfree_skb(skb);
+
+	return 0;
+}

net/ipv6/ipcomp6.c

@@ -0,0 +1,524 @@
+/*
+ * IP Payload Compression Protocol (IPComp) for IPv6 - RFC3173
+ *
+ * Copyright (C)2003 USAGI/WIDE Project
+ *
+ * Author	Mitsuru KANDA  <mk@linux-ipv6.org>
+ *
+ * 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.
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+/* 
+ * [Memo]
+ *
+ * Outbound:
+ *  The compression of IP datagram MUST be done before AH/ESP processing, 
+ *  fragmentation, and the addition of Hop-by-Hop/Routing header. 
+ *
+ * Inbound:
+ *  The decompression of IP datagram MUST be done after the reassembly, 
+ *  AH/ESP processing.
+ */
+#include <linux/config.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/ipcomp.h>
+#include <asm/scatterlist.h>
+#include <asm/semaphore.h>
+#include <linux/crypto.h>
+#include <linux/pfkeyv2.h>
+#include <linux/random.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <linux/list.h>
+#include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
+#include <net/icmp.h>
+#include <net/ipv6.h>
+#include <linux/ipv6.h>
+#include <linux/icmpv6.h>
+
+struct ipcomp6_tfms {
+	struct list_head list;
+	struct crypto_tfm **tfms;
+	int users;
+};
+
+static DECLARE_MUTEX(ipcomp6_resource_sem);
+static void **ipcomp6_scratches;
+static int ipcomp6_scratch_users;
+static LIST_HEAD(ipcomp6_tfms_list);
+
+static int ipcomp6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
+{
+	int err = 0;
+	u8 nexthdr = 0;
+	int hdr_len = skb->h.raw - skb->nh.raw;
+	unsigned char *tmp_hdr = NULL;
+	struct ipv6hdr *iph;
+	int plen, dlen;
+	struct ipcomp_data *ipcd = x->data;
+	u8 *start, *scratch;
+	struct crypto_tfm *tfm;
+	int cpu;
+
+	if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+		skb_linearize(skb, GFP_ATOMIC) != 0) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Remove ipcomp header and decompress original payload */
+	iph = skb->nh.ipv6h;
+	tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC);
+	if (!tmp_hdr)
+		goto out;
+	memcpy(tmp_hdr, iph, hdr_len);
+	nexthdr = *(u8 *)skb->data;
+	skb_pull(skb, sizeof(struct ipv6_comp_hdr)); 
+	skb->nh.raw += sizeof(struct ipv6_comp_hdr);
+	memcpy(skb->nh.raw, tmp_hdr, hdr_len);
+	iph = skb->nh.ipv6h;
+	iph->payload_len = htons(ntohs(iph->payload_len) - sizeof(struct ipv6_comp_hdr));
+	skb->h.raw = skb->data;
+
+	/* decompression */
+	plen = skb->len;
+	dlen = IPCOMP_SCRATCH_SIZE;
+	start = skb->data;
+
+	cpu = get_cpu();
+	scratch = *per_cpu_ptr(ipcomp6_scratches, cpu);
+	tfm = *per_cpu_ptr(ipcd->tfms, cpu);
+
+	err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen);
+	if (err) {
+		err = -EINVAL;
+		goto out_put_cpu;
+	}
+
+	if (dlen < (plen + sizeof(struct ipv6_comp_hdr))) {
+		err = -EINVAL;
+		goto out_put_cpu;
+	}
+
+	err = pskb_expand_head(skb, 0, dlen - plen, GFP_ATOMIC);
+	if (err) {
+		goto out_put_cpu;
+	}
+
+	skb_put(skb, dlen - plen);
+	memcpy(skb->data, scratch, dlen);
+
+	iph = skb->nh.ipv6h;
+	iph->payload_len = htons(skb->len);
+	
+out_put_cpu:
+	put_cpu();
+out:
+	if (tmp_hdr)
+		kfree(tmp_hdr);
+	if (err)
+		goto error_out;
+	return nexthdr;
+error_out:
+	return err;
+}
+
+static int ipcomp6_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+	struct ipv6hdr *top_iph;
+	int hdr_len;
+	struct ipv6_comp_hdr *ipch;
+	struct ipcomp_data *ipcd = x->data;
+	int plen, dlen;
+	u8 *start, *scratch;
+	struct crypto_tfm *tfm;
+	int cpu;
+
+	hdr_len = skb->h.raw - skb->data;
+
+	/* check whether datagram len is larger than threshold */
+	if ((skb->len - hdr_len) < ipcd->threshold) {
+		goto out_ok;
+	}
+
+	if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+		skb_linearize(skb, GFP_ATOMIC) != 0) {
+		goto out_ok;
+	}
+
+	/* compression */
+	plen = skb->len - hdr_len;
+	dlen = IPCOMP_SCRATCH_SIZE;
+	start = skb->h.raw;
+
+	cpu = get_cpu();
+	scratch = *per_cpu_ptr(ipcomp6_scratches, cpu);
+	tfm = *per_cpu_ptr(ipcd->tfms, cpu);
+
+	err = crypto_comp_compress(tfm, start, plen, scratch, &dlen);
+	if (err || (dlen + sizeof(struct ipv6_comp_hdr)) >= plen) {
+		put_cpu();
+		goto out_ok;
+	}
+	memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen);
+	put_cpu();
+	pskb_trim(skb, hdr_len + dlen + sizeof(struct ip_comp_hdr));
+
+	/* insert ipcomp header and replace datagram */
+	top_iph = (struct ipv6hdr *)skb->data;
+
+	top_iph->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
+	ipch = (struct ipv6_comp_hdr *)start;
+	ipch->nexthdr = *skb->nh.raw;
+	ipch->flags = 0;
+	ipch->cpi = htons((u16 )ntohl(x->id.spi));
+	*skb->nh.raw = IPPROTO_COMP;
+
+out_ok:
+	return 0;
+}
+
+static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		                int type, int code, int offset, __u32 info)
+{
+	u32 spi;
+	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
+	struct ipv6_comp_hdr *ipcomph = (struct ipv6_comp_hdr*)(skb->data+offset);
+	struct xfrm_state *x;
+
+	if (type != ICMPV6_DEST_UNREACH && type != ICMPV6_PKT_TOOBIG)
+		return;
+
+	spi = ntohl(ntohs(ipcomph->cpi));
+	x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
+	if (!x)
+		return;
+
+	printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/"
+			"%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n",
+			spi, NIP6(iph->daddr));
+	xfrm_state_put(x);
+}
+
+static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
+{
+	struct xfrm_state *t = NULL;
+
+	t = xfrm_state_alloc();
+	if (!t)
+		goto out;
+
+	t->id.proto = IPPROTO_IPV6;
+	t->id.spi = xfrm6_tunnel_alloc_spi((xfrm_address_t *)&x->props.saddr);
+	memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr));
+	memcpy(&t->sel, &x->sel, sizeof(t->sel));
+	t->props.family = AF_INET6;
+	t->props.mode = 1;
+	memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
+
+	t->type = xfrm_get_type(IPPROTO_IPV6, t->props.family);
+	if (t->type == NULL)
+		goto error;
+
+	if (t->type->init_state(t, NULL))
+		goto error;
+
+	t->km.state = XFRM_STATE_VALID;
+	atomic_set(&t->tunnel_users, 1);
+
+out:
+	return t;
+
+error:
+	xfrm_state_put(t);
+	goto out;
+}
+
+static int ipcomp6_tunnel_attach(struct xfrm_state *x)
+{
+	int err = 0;
+	struct xfrm_state *t = NULL;
+	u32 spi;
+
+	spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr);
+	if (spi)
+		t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr,
+					      spi, IPPROTO_IPV6, AF_INET6);
+	if (!t) {
+		t = ipcomp6_tunnel_create(x);
+		if (!t) {
+			err = -EINVAL;
+			goto out;
+		}
+		xfrm_state_insert(t);
+		xfrm_state_hold(t);
+	}
+	x->tunnel = t;
+	atomic_inc(&t->tunnel_users);
+
+out:
+	return err;
+}
+
+static void ipcomp6_free_scratches(void)
+{
+	int i;
+	void **scratches;
+
+	if (--ipcomp6_scratch_users)
+		return;
+
+	scratches = ipcomp6_scratches;
+	if (!scratches)
+		return;
+
+	for_each_cpu(i) {
+		void *scratch = *per_cpu_ptr(scratches, i);
+		if (scratch)
+			vfree(scratch);
+	}
+
+	free_percpu(scratches);
+}
+
+static void **ipcomp6_alloc_scratches(void)
+{
+	int i;
+	void **scratches;
+
+	if (ipcomp6_scratch_users++)
+		return ipcomp6_scratches;
+
+	scratches = alloc_percpu(void *);
+	if (!scratches)
+		return NULL;
+
+	ipcomp6_scratches = scratches;
+
+	for_each_cpu(i) {
+		void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE);
+		if (!scratch)
+			return NULL;
+		*per_cpu_ptr(scratches, i) = scratch;
+	}
+
+	return scratches;
+}
+
+static void ipcomp6_free_tfms(struct crypto_tfm **tfms)
+{
+	struct ipcomp6_tfms *pos;
+	int cpu;
+
+	list_for_each_entry(pos, &ipcomp6_tfms_list, list) {
+		if (pos->tfms == tfms)
+			break;
+	}
+
+	BUG_TRAP(pos);
+
+	if (--pos->users)
+		return;
+
+	list_del(&pos->list);
+	kfree(pos);
+
+	if (!tfms)
+		return;
+
+	for_each_cpu(cpu) {
+		struct crypto_tfm *tfm = *per_cpu_ptr(tfms, cpu);
+		if (tfm)
+			crypto_free_tfm(tfm);
+	}
+	free_percpu(tfms);
+}
+
+static struct crypto_tfm **ipcomp6_alloc_tfms(const char *alg_name)
+{
+	struct ipcomp6_tfms *pos;
+	struct crypto_tfm **tfms;
+	int cpu;
+
+	/* This can be any valid CPU ID so we don't need locking. */
+	cpu = smp_processor_id();
+
+	list_for_each_entry(pos, &ipcomp6_tfms_list, list) {
+		struct crypto_tfm *tfm;
+
+		tfms = pos->tfms;
+		tfm = *per_cpu_ptr(tfms, cpu);
+
+		if (!strcmp(crypto_tfm_alg_name(tfm), alg_name)) {
+			pos->users++;
+			return tfms;
+		}
+	}
+
+	pos = kmalloc(sizeof(*pos), GFP_KERNEL);
+	if (!pos)
+		return NULL;
+
+	pos->users = 1;
+	INIT_LIST_HEAD(&pos->list);
+	list_add(&pos->list, &ipcomp6_tfms_list);
+
+	pos->tfms = tfms = alloc_percpu(struct crypto_tfm *);
+	if (!tfms)
+		goto error;
+
+	for_each_cpu(cpu) {
+		struct crypto_tfm *tfm = crypto_alloc_tfm(alg_name, 0);
+		if (!tfm)
+			goto error;
+		*per_cpu_ptr(tfms, cpu) = tfm;
+	}
+
+	return tfms;
+
+error:
+	ipcomp6_free_tfms(tfms);
+	return NULL;
+}
+
+static void ipcomp6_free_data(struct ipcomp_data *ipcd)
+{
+	if (ipcd->tfms)
+		ipcomp6_free_tfms(ipcd->tfms);
+	ipcomp6_free_scratches();
+}
+
+static void ipcomp6_destroy(struct xfrm_state *x)
+{
+	struct ipcomp_data *ipcd = x->data;
+	if (!ipcd)
+		return;
+	xfrm_state_delete_tunnel(x);
+	down(&ipcomp6_resource_sem);
+	ipcomp6_free_data(ipcd);
+	up(&ipcomp6_resource_sem);
+	kfree(ipcd);
+
+	xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr);
+}
+
+static int ipcomp6_init_state(struct xfrm_state *x, void *args)
+{
+	int err;
+	struct ipcomp_data *ipcd;
+	struct xfrm_algo_desc *calg_desc;
+
+	err = -EINVAL;
+	if (!x->calg)
+		goto out;
+
+	if (x->encap)
+		goto out;
+
+	err = -ENOMEM;
+	ipcd = kmalloc(sizeof(*ipcd), GFP_KERNEL);
+	if (!ipcd)
+		goto out;
+
+	memset(ipcd, 0, sizeof(*ipcd));
+	x->props.header_len = 0;
+	if (x->props.mode)
+		x->props.header_len += sizeof(struct ipv6hdr);
+	
+	down(&ipcomp6_resource_sem);
+	if (!ipcomp6_alloc_scratches())
+		goto error;
+
+	ipcd->tfms = ipcomp6_alloc_tfms(x->calg->alg_name);
+	if (!ipcd->tfms)
+		goto error;
+	up(&ipcomp6_resource_sem);
+
+	if (x->props.mode) {
+		err = ipcomp6_tunnel_attach(x);
+		if (err)
+			goto error_tunnel;
+	}
+
+	calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0);
+	BUG_ON(!calg_desc);
+	ipcd->threshold = calg_desc->uinfo.comp.threshold;
+	x->data = ipcd;
+	err = 0;
+out:
+	return err;
+error_tunnel:
+	down(&ipcomp6_resource_sem);
+error:
+	ipcomp6_free_data(ipcd);
+	up(&ipcomp6_resource_sem);
+	kfree(ipcd);
+
+	goto out;
+}
+
+static struct xfrm_type ipcomp6_type = 
+{
+	.description	= "IPCOMP6",
+	.owner		= THIS_MODULE,
+	.proto		= IPPROTO_COMP,
+	.init_state	= ipcomp6_init_state,
+	.destructor	= ipcomp6_destroy,
+	.input		= ipcomp6_input,
+	.output		= ipcomp6_output,
+};
+
+static struct inet6_protocol ipcomp6_protocol = 
+{
+	.handler	= xfrm6_rcv,
+	.err_handler	= ipcomp6_err,
+	.flags		= INET6_PROTO_NOPOLICY,
+};
+
+static int __init ipcomp6_init(void)
+{
+	if (xfrm_register_type(&ipcomp6_type, AF_INET6) < 0) {
+		printk(KERN_INFO "ipcomp6 init: can't add xfrm type\n");
+		return -EAGAIN;
+	}
+	if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) {
+		printk(KERN_INFO "ipcomp6 init: can't add protocol\n");
+		xfrm_unregister_type(&ipcomp6_type, AF_INET6);
+		return -EAGAIN;
+	}
+	return 0;
+}
+
+static void __exit ipcomp6_fini(void)
+{
+	if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) 
+		printk(KERN_INFO "ipv6 ipcomp close: can't remove protocol\n");
+	if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0)
+		printk(KERN_INFO "ipv6 ipcomp close: can't remove xfrm type\n");
+}
+
+module_init(ipcomp6_init);
+module_exit(ipcomp6_fini);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) for IPv6 - RFC3173");
+MODULE_AUTHOR("Mitsuru KANDA <mk@linux-ipv6.org>");
+
+

net/ipv6/ipv6_sockglue.c

@@ -0,0 +1,704 @@
+/*
+ *	IPv6 BSD socket options interface
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>	
+ *
+ *	Based on linux/net/ipv4/ip_sockglue.c
+ *
+ *	$Id: ipv6_sockglue.c,v 1.41 2002/02/01 22:01:04 davem Exp $
+ *
+ *	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.
+ *
+ *	FIXME: Make the setsockopt code POSIX compliant: That is
+ *
+ *	o	Return -EINVAL for setsockopt of short lengths
+ *	o	Truncate getsockopt returns
+ *	o	Return an optlen of the truncated length if need be
+ *
+ *	Changes:
+ *	David L Stevens <dlstevens@us.ibm.com>:
+ *		- added multicast source filtering API for MLDv2
+ */
+
+#include <linux/module.h>
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/init.h>
+#include <linux/sysctl.h>
+#include <linux/netfilter.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/inet_common.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include <asm/uaccess.h>
+
+DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics);
+
+static struct packet_type ipv6_packet_type = {
+	.type = __constant_htons(ETH_P_IPV6), 
+	.func = ipv6_rcv,
+};
+
+struct ip6_ra_chain *ip6_ra_chain;
+DEFINE_RWLOCK(ip6_ra_lock);
+
+int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *))
+{
+	struct ip6_ra_chain *ra, *new_ra, **rap;
+
+	/* RA packet may be delivered ONLY to IPPROTO_RAW socket */
+	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW)
+		return -EINVAL;
+
+	new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
+
+	write_lock_bh(&ip6_ra_lock);
+	for (rap = &ip6_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
+		if (ra->sk == sk) {
+			if (sel>=0) {
+				write_unlock_bh(&ip6_ra_lock);
+				if (new_ra)
+					kfree(new_ra);
+				return -EADDRINUSE;
+			}
+
+			*rap = ra->next;
+			write_unlock_bh(&ip6_ra_lock);
+
+			if (ra->destructor)
+				ra->destructor(sk);
+			sock_put(sk);
+			kfree(ra);
+			return 0;
+		}
+	}
+	if (new_ra == NULL) {
+		write_unlock_bh(&ip6_ra_lock);
+		return -ENOBUFS;
+	}
+	new_ra->sk = sk;
+	new_ra->sel = sel;
+	new_ra->destructor = destructor;
+	new_ra->next = ra;
+	*rap = new_ra;
+	sock_hold(sk);
+	write_unlock_bh(&ip6_ra_lock);
+	return 0;
+}
+
+extern int ip6_mc_source(int add, int omode, struct sock *sk,
+	struct group_source_req *pgsr);
+extern int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
+extern int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
+	struct group_filter __user *optval, int __user *optlen);
+
+
+int ipv6_setsockopt(struct sock *sk, int level, int optname,
+		    char __user *optval, int optlen)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	int val, valbool;
+	int retv = -ENOPROTOOPT;
+
+	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
+		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+
+	if(level!=SOL_IPV6)
+		goto out;
+
+	if (optval == NULL)
+		val=0;
+	else if (get_user(val, (int __user *) optval))
+		return -EFAULT;
+
+	valbool = (val!=0);
+
+	lock_sock(sk);
+
+	switch (optname) {
+
+	case IPV6_ADDRFORM:
+		if (val == PF_INET) {
+			struct ipv6_txoptions *opt;
+			struct sk_buff *pktopt;
+
+			if (sk->sk_protocol != IPPROTO_UDP &&
+			    sk->sk_protocol != IPPROTO_TCP)
+				break;
+
+			if (sk->sk_state != TCP_ESTABLISHED) {
+				retv = -ENOTCONN;
+				break;
+			}
+
+			if (ipv6_only_sock(sk) ||
+			    !(ipv6_addr_type(&np->daddr) & IPV6_ADDR_MAPPED)) {
+				retv = -EADDRNOTAVAIL;
+				break;
+			}
+
+			fl6_free_socklist(sk);
+			ipv6_sock_mc_close(sk);
+
+			if (sk->sk_protocol == IPPROTO_TCP) {
+				struct tcp_sock *tp = tcp_sk(sk);
+
+				local_bh_disable();
+				sock_prot_dec_use(sk->sk_prot);
+				sock_prot_inc_use(&tcp_prot);
+				local_bh_enable();
+				sk->sk_prot = &tcp_prot;
+				tp->af_specific = &ipv4_specific;
+				sk->sk_socket->ops = &inet_stream_ops;
+				sk->sk_family = PF_INET;
+				tcp_sync_mss(sk, tp->pmtu_cookie);
+			} else {
+				local_bh_disable();
+				sock_prot_dec_use(sk->sk_prot);
+				sock_prot_inc_use(&udp_prot);
+				local_bh_enable();
+				sk->sk_prot = &udp_prot;
+				sk->sk_socket->ops = &inet_dgram_ops;
+				sk->sk_family = PF_INET;
+			}
+			opt = xchg(&np->opt, NULL);
+			if (opt)
+				sock_kfree_s(sk, opt, opt->tot_len);
+			pktopt = xchg(&np->pktoptions, NULL);
+			if (pktopt)
+				kfree_skb(pktopt);
+
+			sk->sk_destruct = inet_sock_destruct;
+#ifdef INET_REFCNT_DEBUG
+			atomic_dec(&inet6_sock_nr);
+#endif
+			module_put(THIS_MODULE);
+			retv = 0;
+			break;
+		}
+		goto e_inval;
+
+	case IPV6_V6ONLY:
+		if (inet_sk(sk)->num)
+			goto e_inval;
+		np->ipv6only = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_PKTINFO:
+		np->rxopt.bits.rxinfo = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_HOPLIMIT:
+		np->rxopt.bits.rxhlim = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_RTHDR:
+		if (val < 0 || val > 2)
+			goto e_inval;
+		np->rxopt.bits.srcrt = val;
+		retv = 0;
+		break;
+
+	case IPV6_HOPOPTS:
+		np->rxopt.bits.hopopts = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_DSTOPTS:
+		np->rxopt.bits.dstopts = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_FLOWINFO:
+		np->rxopt.bits.rxflow = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_PKTOPTIONS:
+	{
+		struct ipv6_txoptions *opt = NULL;
+		struct msghdr msg;
+		struct flowi fl;
+		int junk;
+
+		fl.fl6_flowlabel = 0;
+		fl.oif = sk->sk_bound_dev_if;
+
+		if (optlen == 0)
+			goto update;
+
+		/* 1K is probably excessive
+		 * 1K is surely not enough, 2K per standard header is 16K.
+		 */
+		retv = -EINVAL;
+		if (optlen > 64*1024)
+			break;
+
+		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
+		retv = -ENOBUFS;
+		if (opt == NULL)
+			break;
+
+		memset(opt, 0, sizeof(*opt));
+		opt->tot_len = sizeof(*opt) + optlen;
+		retv = -EFAULT;
+		if (copy_from_user(opt+1, optval, optlen))
+			goto done;
+
+		msg.msg_controllen = optlen;
+		msg.msg_control = (void*)(opt+1);
+
+		retv = datagram_send_ctl(&msg, &fl, opt, &junk);
+		if (retv)
+			goto done;
+update:
+		retv = 0;
+		if (sk->sk_type == SOCK_STREAM) {
+			if (opt) {
+				struct tcp_sock *tp = tcp_sk(sk);
+				if (!((1 << sk->sk_state) &
+				      (TCPF_LISTEN | TCPF_CLOSE))
+				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
+					tp->ext_header_len = opt->opt_flen + opt->opt_nflen;
+					tcp_sync_mss(sk, tp->pmtu_cookie);
+				}
+			}
+			opt = xchg(&np->opt, opt);
+			sk_dst_reset(sk);
+		} else {
+			write_lock(&sk->sk_dst_lock);
+			opt = xchg(&np->opt, opt);
+			write_unlock(&sk->sk_dst_lock);
+			sk_dst_reset(sk);
+		}
+
+done:
+		if (opt)
+			sock_kfree_s(sk, opt, opt->tot_len);
+		break;
+	}
+	case IPV6_UNICAST_HOPS:
+		if (val > 255 || val < -1)
+			goto e_inval;
+		np->hop_limit = val;
+		retv = 0;
+		break;
+
+	case IPV6_MULTICAST_HOPS:
+		if (sk->sk_type == SOCK_STREAM)
+			goto e_inval;
+		if (val > 255 || val < -1)
+			goto e_inval;
+		np->mcast_hops = val;
+		retv = 0;
+		break;
+
+	case IPV6_MULTICAST_LOOP:
+		np->mc_loop = valbool;
+		retv = 0;
+		break;
+
+	case IPV6_MULTICAST_IF:
+		if (sk->sk_type == SOCK_STREAM)
+			goto e_inval;
+		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
+			goto e_inval;
+
+		if (__dev_get_by_index(val) == NULL) {
+			retv = -ENODEV;
+			break;
+		}
+		np->mcast_oif = val;
+		retv = 0;
+		break;
+	case IPV6_ADD_MEMBERSHIP:
+	case IPV6_DROP_MEMBERSHIP:
+	{
+		struct ipv6_mreq mreq;
+
+		retv = -EFAULT;
+		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
+			break;
+
+		if (optname == IPV6_ADD_MEMBERSHIP)
+			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
+		else
+			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
+		break;
+	}
+	case IPV6_JOIN_ANYCAST:
+	case IPV6_LEAVE_ANYCAST:
+	{
+		struct ipv6_mreq mreq;
+
+		if (optlen != sizeof(struct ipv6_mreq))
+			goto e_inval;
+
+		retv = -EFAULT;
+		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
+			break;
+
+		if (optname == IPV6_JOIN_ANYCAST)
+			retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
+		else
+			retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
+		break;
+	}
+	case MCAST_JOIN_GROUP:
+	case MCAST_LEAVE_GROUP:
+	{
+		struct group_req greq;
+		struct sockaddr_in6 *psin6;
+
+		retv = -EFAULT;
+		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
+			break;
+		if (greq.gr_group.ss_family != AF_INET6) {
+			retv = -EADDRNOTAVAIL;
+			break;
+		}
+		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
+		if (optname == MCAST_JOIN_GROUP)
+			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
+				&psin6->sin6_addr);
+		else
+			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
+				&psin6->sin6_addr);
+		break;
+	}
+	case MCAST_JOIN_SOURCE_GROUP:
+	case MCAST_LEAVE_SOURCE_GROUP:
+	case MCAST_BLOCK_SOURCE:
+	case MCAST_UNBLOCK_SOURCE:
+	{
+		struct group_source_req greqs;
+		int omode, add;
+
+		if (optlen != sizeof(struct group_source_req))
+			goto e_inval;
+		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
+			retv = -EFAULT;
+			break;
+		}
+		if (greqs.gsr_group.ss_family != AF_INET6 ||
+		    greqs.gsr_source.ss_family != AF_INET6) {
+			retv = -EADDRNOTAVAIL;
+			break;
+		}
+		if (optname == MCAST_BLOCK_SOURCE) {
+			omode = MCAST_EXCLUDE;
+			add = 1;
+		} else if (optname == MCAST_UNBLOCK_SOURCE) {
+			omode = MCAST_EXCLUDE;
+			add = 0;
+		} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
+			struct sockaddr_in6 *psin6;
+
+			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
+			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
+				&psin6->sin6_addr);
+			if (retv)
+				break;
+			omode = MCAST_INCLUDE;
+			add = 1;
+		} else /*IP_DROP_SOURCE_MEMBERSHIP */ {
+			omode = MCAST_INCLUDE;
+			add = 0;
+		}
+		retv = ip6_mc_source(add, omode, sk, &greqs);
+		break;
+	}
+	case MCAST_MSFILTER:
+	{
+		extern int sysctl_optmem_max;
+		extern int sysctl_mld_max_msf;
+		struct group_filter *gsf;
+
+		if (optlen < GROUP_FILTER_SIZE(0))
+			goto e_inval;
+		if (optlen > sysctl_optmem_max) {
+			retv = -ENOBUFS;
+			break;
+		}
+		gsf = (struct group_filter *)kmalloc(optlen,GFP_KERNEL);
+		if (gsf == 0) {
+			retv = -ENOBUFS;
+			break;
+		}
+		retv = -EFAULT;
+		if (copy_from_user(gsf, optval, optlen)) {
+			kfree(gsf);
+			break;
+		}
+		/* numsrc >= (4G-140)/128 overflow in 32 bits */
+		if (gsf->gf_numsrc >= 0x1ffffffU ||
+		    gsf->gf_numsrc > sysctl_mld_max_msf) {
+			kfree(gsf);
+			retv = -ENOBUFS;
+			break;
+		}
+		if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
+			kfree(gsf);
+			retv = -EINVAL;
+			break;
+		}
+		retv = ip6_mc_msfilter(sk, gsf);
+		kfree(gsf);
+
+		break;
+	}
+	case IPV6_ROUTER_ALERT:
+		retv = ip6_ra_control(sk, val, NULL);
+		break;
+	case IPV6_MTU_DISCOVER:
+		if (val<0 || val>2)
+			goto e_inval;
+		np->pmtudisc = val;
+		retv = 0;
+		break;
+	case IPV6_MTU:
+		if (val && val < IPV6_MIN_MTU)
+			goto e_inval;
+		np->frag_size = val;
+		retv = 0;
+		break;
+	case IPV6_RECVERR:
+		np->recverr = valbool;
+		if (!val)
+			skb_queue_purge(&sk->sk_error_queue);
+		retv = 0;
+		break;
+	case IPV6_FLOWINFO_SEND:
+		np->sndflow = valbool;
+		retv = 0;
+		break;
+	case IPV6_FLOWLABEL_MGR:
+		retv = ipv6_flowlabel_opt(sk, optval, optlen);
+		break;
+	case IPV6_IPSEC_POLICY:
+	case IPV6_XFRM_POLICY:
+		retv = xfrm_user_policy(sk, optname, optval, optlen);
+		break;
+
+#ifdef CONFIG_NETFILTER
+	default:
+		retv = nf_setsockopt(sk, PF_INET6, optname, optval, 
+					    optlen);
+		break;
+#endif
+
+	}
+	release_sock(sk);
+
+out:
+	return retv;
+
+e_inval:
+	release_sock(sk);
+	return -EINVAL;
+}
+
+int ipv6_getsockopt(struct sock *sk, int level, int optname,
+		    char __user *optval, int __user *optlen)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	int len;
+	int val;
+
+	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
+		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+	if(level!=SOL_IPV6)
+		return -ENOPROTOOPT;
+	if (get_user(len, optlen))
+		return -EFAULT;
+	switch (optname) {
+	case IPV6_ADDRFORM:
+		if (sk->sk_protocol != IPPROTO_UDP &&
+		    sk->sk_protocol != IPPROTO_TCP)
+			return -EINVAL;
+		if (sk->sk_state != TCP_ESTABLISHED)
+			return -ENOTCONN;
+		val = sk->sk_family;
+		break;
+	case MCAST_MSFILTER:
+	{
+		struct group_filter gsf;
+		int err;
+
+		if (len < GROUP_FILTER_SIZE(0))
+			return -EINVAL;
+		if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
+			return -EFAULT;
+		lock_sock(sk);
+		err = ip6_mc_msfget(sk, &gsf,
+			(struct group_filter __user *)optval, optlen);
+		release_sock(sk);
+		return err;
+	}
+
+	case IPV6_PKTOPTIONS:
+	{
+		struct msghdr msg;
+		struct sk_buff *skb;
+
+		if (sk->sk_type != SOCK_STREAM)
+			return -ENOPROTOOPT;
+
+		msg.msg_control = optval;
+		msg.msg_controllen = len;
+		msg.msg_flags = 0;
+
+		lock_sock(sk);
+		skb = np->pktoptions;
+		if (skb)
+			atomic_inc(&skb->users);
+		release_sock(sk);
+
+		if (skb) {
+			int err = datagram_recv_ctl(sk, &msg, skb);
+			kfree_skb(skb);
+			if (err)
+				return err;
+		} else {
+			if (np->rxopt.bits.rxinfo) {
+				struct in6_pktinfo src_info;
+				src_info.ipi6_ifindex = np->mcast_oif;
+				ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr);
+				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+			}
+			if (np->rxopt.bits.rxhlim) {
+				int hlim = np->mcast_hops;
+				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
+			}
+		}
+		len -= msg.msg_controllen;
+		return put_user(len, optlen);
+	}
+	case IPV6_MTU:
+	{
+		struct dst_entry *dst;
+		val = 0;	
+		lock_sock(sk);
+		dst = sk_dst_get(sk);
+		if (dst) {
+			val = dst_mtu(dst);
+			dst_release(dst);
+		}
+		release_sock(sk);
+		if (!val)
+			return -ENOTCONN;
+		break;
+	}
+
+	case IPV6_V6ONLY:
+		val = np->ipv6only;
+		break;
+
+	case IPV6_PKTINFO:
+		val = np->rxopt.bits.rxinfo;
+		break;
+
+	case IPV6_HOPLIMIT:
+		val = np->rxopt.bits.rxhlim;
+		break;
+
+	case IPV6_RTHDR:
+		val = np->rxopt.bits.srcrt;
+		break;
+
+	case IPV6_HOPOPTS:
+		val = np->rxopt.bits.hopopts;
+		break;
+
+	case IPV6_DSTOPTS:
+		val = np->rxopt.bits.dstopts;
+		break;
+
+	case IPV6_FLOWINFO:
+		val = np->rxopt.bits.rxflow;
+		break;
+
+	case IPV6_UNICAST_HOPS:
+		val = np->hop_limit;
+		break;
+
+	case IPV6_MULTICAST_HOPS:
+		val = np->mcast_hops;
+		break;
+
+	case IPV6_MULTICAST_LOOP:
+		val = np->mc_loop;
+		break;
+
+	case IPV6_MULTICAST_IF:
+		val = np->mcast_oif;
+		break;
+
+	case IPV6_MTU_DISCOVER:
+		val = np->pmtudisc;
+		break;
+
+	case IPV6_RECVERR:
+		val = np->recverr;
+		break;
+
+	case IPV6_FLOWINFO_SEND:
+		val = np->sndflow;
+		break;
+
+	default:
+#ifdef CONFIG_NETFILTER
+		lock_sock(sk);
+		val = nf_getsockopt(sk, PF_INET6, optname, optval, 
+				    &len);
+		release_sock(sk);
+		if (val >= 0)
+			val = put_user(len, optlen);
+		return val;
+#else
+		return -EINVAL;
+#endif
+	}
+	len = min_t(unsigned int, sizeof(int), len);
+	if(put_user(len, optlen))
+		return -EFAULT;
+	if(copy_to_user(optval,&val,len))
+		return -EFAULT;
+	return 0;
+}
+
+void __init ipv6_packet_init(void)
+{
+	dev_add_pack(&ipv6_packet_type);
+}
+
+void ipv6_packet_cleanup(void)
+{
+	dev_remove_pack(&ipv6_packet_type);
+}

net/ipv6/ipv6_syms.c

@@ -0,0 +1,41 @@
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <net/protocol.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#include <net/xfrm.h>
+
+EXPORT_SYMBOL(ipv6_addr_type);
+EXPORT_SYMBOL(icmpv6_send);
+EXPORT_SYMBOL(icmpv6_statistics);
+EXPORT_SYMBOL(icmpv6_err_convert);
+EXPORT_SYMBOL(ndisc_mc_map);
+EXPORT_SYMBOL(register_inet6addr_notifier);
+EXPORT_SYMBOL(unregister_inet6addr_notifier);
+EXPORT_SYMBOL(ip6_route_output);
+#ifdef CONFIG_NETFILTER
+EXPORT_SYMBOL(ip6_route_me_harder);
+#endif
+EXPORT_SYMBOL(addrconf_lock);
+EXPORT_SYMBOL(ipv6_setsockopt);
+EXPORT_SYMBOL(ipv6_getsockopt);
+EXPORT_SYMBOL(inet6_register_protosw);
+EXPORT_SYMBOL(inet6_unregister_protosw);
+EXPORT_SYMBOL(inet6_add_protocol);
+EXPORT_SYMBOL(inet6_del_protocol);
+EXPORT_SYMBOL(ip6_xmit);
+EXPORT_SYMBOL(inet6_release);
+EXPORT_SYMBOL(inet6_bind);
+EXPORT_SYMBOL(inet6_getname);
+EXPORT_SYMBOL(inet6_ioctl);
+EXPORT_SYMBOL(ipv6_get_saddr);
+EXPORT_SYMBOL(ipv6_chk_addr);
+EXPORT_SYMBOL(in6_dev_finish_destroy);
+#ifdef CONFIG_XFRM
+EXPORT_SYMBOL(xfrm6_rcv);
+#endif
+EXPORT_SYMBOL(rt6_lookup);
+EXPORT_SYMBOL(fl6_sock_lookup);
+EXPORT_SYMBOL(ipv6_push_nfrag_opts);

net/ipv6/netfilter/Kconfig

@@ -0,0 +1,242 @@
+#
+# IP netfilter configuration
+#
+
+menu "IPv6: Netfilter Configuration (EXPERIMENTAL)"
+	depends on INET && IPV6 && NETFILTER && EXPERIMENTAL
+
+#tristate 'Connection tracking (required for masq/NAT)' CONFIG_IP6_NF_CONNTRACK
+#if [ "$CONFIG_IP6_NF_CONNTRACK" != "n" ]; then
+#  dep_tristate '  FTP protocol support' CONFIG_IP6_NF_FTP $CONFIG_IP6_NF_CONNTRACK
+#fi
+config IP6_NF_QUEUE
+	tristate "Userspace queueing via NETLINK"
+	---help---
+
+	  This option adds a queue handler to the kernel for IPv6
+	  packets which lets us to receive the filtered packets
+	  with QUEUE target using libiptc as we can do with
+	  the IPv4 now.
+
+	  (C) Fernando Anton 2001
+	  IPv64 Project - Work based in IPv64 draft by Arturo Azcorra.
+	  Universidad Carlos III de Madrid
+	  Universidad Politecnica de Alcala de Henares
+	  email: <fanton@it.uc3m.es>.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_IPTABLES
+	tristate "IP6 tables support (required for filtering/masq/NAT)"
+	help
+	  ip6tables is a general, extensible packet identification framework.
+	  Currently only the packet filtering and packet mangling subsystem
+	  for IPv6 use this, but connection tracking is going to follow.
+	  Say 'Y' or 'M' here if you want to use either of those.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+# The simple matches.
+config IP6_NF_MATCH_LIMIT
+	tristate "limit match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  limit matching allows you to control the rate at which a rule can be
+	  matched: mainly useful in combination with the LOG target ("LOG
+	  target support", below) and to avoid some Denial of Service attacks.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_MAC
+	tristate "MAC address match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  mac matching allows you to match packets based on the source
+	  Ethernet address of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_RT
+	tristate "Routing header match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  rt matching allows you to match packets based on the routing
+	  header of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_OPTS
+	tristate "Hop-by-hop and Dst opts header match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  This allows one to match packets based on the hop-by-hop
+	  and destination options headers of a packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_FRAG
+	tristate "Fragmentation header match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  frag matching allows you to match packets based on the fragmentation
+	  header of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_HL
+	tristate "HL match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  HL matching allows you to match packets based on the hop
+	  limit of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_MULTIPORT
+	tristate "Multiple port match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  Multiport matching allows you to match TCP or UDP packets based on
+	  a series of source or destination ports: normally a rule can only
+	  match a single range of ports.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_OWNER
+	tristate "Owner match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  Packet owner matching allows you to match locally-generated packets
+	  based on who created them: the user, group, process or session.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+#  dep_tristate '  MAC address match support' CONFIG_IP6_NF_MATCH_MAC $CONFIG_IP6_NF_IPTABLES
+config IP6_NF_MATCH_MARK
+	tristate "netfilter MARK match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  Netfilter mark matching allows you to match packets based on the
+	  `nfmark' value in the packet.  This can be set by the MARK target
+	  (see below).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_IPV6HEADER
+	tristate "IPv6 Extension Headers Match"
+	depends on IP6_NF_IPTABLES
+	help
+	  This module allows one to match packets based upon
+	  the ipv6 extension headers.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_AHESP
+	tristate "AH/ESP match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  This module allows one to match AH and ESP packets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_LENGTH
+	tristate "Packet Length match support"
+	depends on IP6_NF_IPTABLES
+	help
+	  This option allows you to match the length of a packet against a
+	  specific value or range of values.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_EUI64
+	tristate "EUI64 address check"
+	depends on IP6_NF_IPTABLES
+	help
+	  This module performs checking on the IPv6 source address
+	  Compares the last 64 bits with the EUI64 (delivered
+	  from the MAC address) address
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_PHYSDEV
+	tristate "Physdev match support"
+	depends on IP6_NF_IPTABLES && BRIDGE_NETFILTER
+	help
+	  Physdev packet matching matches against the physical bridge ports
+	  the IP packet arrived on or will leave by.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+#  dep_tristate '  Multiple port match support' CONFIG_IP6_NF_MATCH_MULTIPORT $CONFIG_IP6_NF_IPTABLES
+#  dep_tristate '  TOS match support' CONFIG_IP6_NF_MATCH_TOS $CONFIG_IP6_NF_IPTABLES
+#  if [ "$CONFIG_IP6_NF_CONNTRACK" != "n" ]; then
+#    dep_tristate '  Connection state match support' CONFIG_IP6_NF_MATCH_STATE $CONFIG_IP6_NF_CONNTRACK $CONFIG_IP6_NF_IPTABLES 
+#  fi
+#  if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+#    dep_tristate '  Unclean match support (EXPERIMENTAL)' CONFIG_IP6_NF_MATCH_UNCLEAN $CONFIG_IP6_NF_IPTABLES
+#    dep_tristate '  Owner match support (EXPERIMENTAL)' CONFIG_IP6_NF_MATCH_OWNER $CONFIG_IP6_NF_IPTABLES
+#  fi
+# The targets
+config IP6_NF_FILTER
+	tristate "Packet filtering"
+	depends on IP6_NF_IPTABLES
+	help
+	  Packet filtering defines a table `filter', which has a series of
+	  rules for simple packet filtering at local input, forwarding and
+	  local output.  See the man page for iptables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_LOG
+	tristate "LOG target support"
+	depends on IP6_NF_FILTER
+	help
+	  This option adds a `LOG' target, which allows you to create rules in
+	  any iptables table which records the packet header to the syslog.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+#  if [ "$CONFIG_IP6_NF_FILTER" != "n" ]; then
+#    dep_tristate '    REJECT target support' CONFIG_IP6_NF_TARGET_REJECT $CONFIG_IP6_NF_FILTER
+#    if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+#      dep_tristate '    MIRROR target support (EXPERIMENTAL)' CONFIG_IP6_NF_TARGET_MIRROR $CONFIG_IP6_NF_FILTER
+#    fi
+#  fi
+config IP6_NF_MANGLE
+	tristate "Packet mangling"
+	depends on IP6_NF_IPTABLES
+	help
+	  This option adds a `mangle' table to iptables: see the man page for
+	  iptables(8).  This table is used for various packet alterations
+	  which can effect how the packet is routed.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+#    dep_tristate '    TOS target support' CONFIG_IP6_NF_TARGET_TOS $CONFIG_IP_NF_MANGLE
+config IP6_NF_TARGET_MARK
+	tristate "MARK target support"
+	depends on IP6_NF_MANGLE
+	help
+	  This option adds a `MARK' target, which allows you to create rules
+	  in the `mangle' table which alter the netfilter mark (nfmark) field
+	  associated with the packet packet prior to routing. This can change
+	  the routing method (see `Use netfilter MARK value as routing
+	  key') and can also be used by other subsystems to change their
+	  behavior.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+#dep_tristate '  LOG target support' CONFIG_IP6_NF_TARGET_LOG $CONFIG_IP6_NF_IPTABLES
+config IP6_NF_RAW
+	tristate  'raw table support (required for TRACE)'
+	depends on IP6_NF_IPTABLES
+	help
+	  This option adds a `raw' table to ip6tables. This table is the very
+	  first in the netfilter framework and hooks in at the PREROUTING
+	  and OUTPUT chains.
+	
+	  If you want to compile it as a module, say M here and read
+	  <file:Documentation/modules.txt>.  If unsure, say `N'.
+
+endmenu
+

net/ipv6/netfilter/Makefile

@@ -0,0 +1,26 @@
+#
+# Makefile for the netfilter modules on top of IPv6.
+#
+
+# Link order matters here.
+obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o
+obj-$(CONFIG_IP6_NF_MATCH_LIMIT) += ip6t_limit.o
+obj-$(CONFIG_IP6_NF_MATCH_MARK) += ip6t_mark.o
+obj-$(CONFIG_IP6_NF_MATCH_LENGTH) += ip6t_length.o
+obj-$(CONFIG_IP6_NF_MATCH_MAC) += ip6t_mac.o
+obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
+obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o
+obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o
+obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o
+obj-$(CONFIG_IP6_NF_MATCH_AHESP) += ip6t_esp.o ip6t_ah.o
+obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
+obj-$(CONFIG_IP6_NF_MATCH_MULTIPORT) += ip6t_multiport.o
+obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o
+obj-$(CONFIG_IP6_NF_MATCH_PHYSDEV) += ip6t_physdev.o
+obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
+obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
+obj-$(CONFIG_IP6_NF_TARGET_MARK) += ip6t_MARK.o
+obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o
+obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o
+obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
+obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o

net/ipv6/netfilter/ip6_queue.c

@@ -0,0 +1,741 @@
+/*
+ * This is a module which is used for queueing IPv6 packets and
+ * communicating with userspace via netlink.
+ *
+ * (C) 2001 Fernando Anton, this code is GPL.
+ *     IPv64 Project - Work based in IPv64 draft by Arturo Azcorra.
+ *     Universidad Carlos III de Madrid - Leganes (Madrid) - Spain
+ *     Universidad Politecnica de Alcala de Henares - Alcala de H. (Madrid) - Spain
+ *     email: fanton@it.uc3m.es
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 2001-11-06: First try. Working with ip_queue.c for IPv4 and trying
+ *             to adapt it to IPv6
+ *             HEAVILY based in ipqueue.c by James Morris. It's just
+ *             a little modified version of it, so he's nearly the
+ *             real coder of this.
+ *             Few changes needed, mainly the hard_routing code and
+ *             the netlink socket protocol (we're NETLINK_IP6_FW).
+ * 2002-06-25: Code cleanup. [JM: ported cleanup over from ip_queue.c]
+ * 2005-02-04: Added /proc counter for dropped packets; fixed so
+ *             packets aren't delivered to user space if they're going
+ *             to be dropped.
+ */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/ipv6.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/netlink.h>
+#include <linux/spinlock.h>
+#include <linux/sysctl.h>
+#include <linux/proc_fs.h>
+#include <net/sock.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <linux/netfilter_ipv4/ip_queue.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+#define IPQ_QMAX_DEFAULT 1024
+#define IPQ_PROC_FS_NAME "ip6_queue"
+#define NET_IPQ_QMAX 2088
+#define NET_IPQ_QMAX_NAME "ip6_queue_maxlen"
+
+struct ipq_rt_info {
+	struct in6_addr daddr;
+	struct in6_addr saddr;
+};
+
+struct ipq_queue_entry {
+	struct list_head list;
+	struct nf_info *info;
+	struct sk_buff *skb;
+	struct ipq_rt_info rt_info;
+};
+
+typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long);
+
+static unsigned char copy_mode = IPQ_COPY_NONE;
+static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT;
+static DEFINE_RWLOCK(queue_lock);
+static int peer_pid;
+static unsigned int copy_range;
+static unsigned int queue_total;
+static unsigned int queue_dropped = 0;
+static unsigned int queue_user_dropped = 0;
+static struct sock *ipqnl;
+static LIST_HEAD(queue_list);
+static DECLARE_MUTEX(ipqnl_sem);
+
+static void
+ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
+{
+	nf_reinject(entry->skb, entry->info, verdict);
+	kfree(entry);
+}
+
+static inline void
+__ipq_enqueue_entry(struct ipq_queue_entry *entry)
+{
+       list_add(&entry->list, &queue_list);
+       queue_total++;
+}
+
+/*
+ * Find and return a queued entry matched by cmpfn, or return the last
+ * entry if cmpfn is NULL.
+ */
+static inline struct ipq_queue_entry *
+__ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
+{
+	struct list_head *p;
+
+	list_for_each_prev(p, &queue_list) {
+		struct ipq_queue_entry *entry = (struct ipq_queue_entry *)p;
+		
+		if (!cmpfn || cmpfn(entry, data))
+			return entry;
+	}
+	return NULL;
+}
+
+static inline void
+__ipq_dequeue_entry(struct ipq_queue_entry *entry)
+{
+	list_del(&entry->list);
+	queue_total--;
+}
+
+static inline struct ipq_queue_entry *
+__ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
+{
+	struct ipq_queue_entry *entry;
+
+	entry = __ipq_find_entry(cmpfn, data);
+	if (entry == NULL)
+		return NULL;
+
+	__ipq_dequeue_entry(entry);
+	return entry;
+}
+
+
+static inline void
+__ipq_flush(int verdict)
+{
+	struct ipq_queue_entry *entry;
+	
+	while ((entry = __ipq_find_dequeue_entry(NULL, 0)))
+		ipq_issue_verdict(entry, verdict);
+}
+
+static inline int
+__ipq_set_mode(unsigned char mode, unsigned int range)
+{
+	int status = 0;
+	
+	switch(mode) {
+	case IPQ_COPY_NONE:
+	case IPQ_COPY_META:
+		copy_mode = mode;
+		copy_range = 0;
+		break;
+		
+	case IPQ_COPY_PACKET:
+		copy_mode = mode;
+		copy_range = range;
+		if (copy_range > 0xFFFF)
+			copy_range = 0xFFFF;
+		break;
+		
+	default:
+		status = -EINVAL;
+
+	}
+	return status;
+}
+
+static inline void
+__ipq_reset(void)
+{
+	peer_pid = 0;
+	net_disable_timestamp();
+	__ipq_set_mode(IPQ_COPY_NONE, 0);
+	__ipq_flush(NF_DROP);
+}
+
+static struct ipq_queue_entry *
+ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
+{
+	struct ipq_queue_entry *entry;
+	
+	write_lock_bh(&queue_lock);
+	entry = __ipq_find_dequeue_entry(cmpfn, data);
+	write_unlock_bh(&queue_lock);
+	return entry;
+}
+
+static void
+ipq_flush(int verdict)
+{
+	write_lock_bh(&queue_lock);
+	__ipq_flush(verdict);
+	write_unlock_bh(&queue_lock);
+}
+
+static struct sk_buff *
+ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp)
+{
+	unsigned char *old_tail;
+	size_t size = 0;
+	size_t data_len = 0;
+	struct sk_buff *skb;
+	struct ipq_packet_msg *pmsg;
+	struct nlmsghdr *nlh;
+
+	read_lock_bh(&queue_lock);
+	
+	switch (copy_mode) {
+	case IPQ_COPY_META:
+	case IPQ_COPY_NONE:
+		size = NLMSG_SPACE(sizeof(*pmsg));
+		data_len = 0;
+		break;
+	
+	case IPQ_COPY_PACKET:
+		if (copy_range == 0 || copy_range > entry->skb->len)
+			data_len = entry->skb->len;
+		else
+			data_len = copy_range;
+		
+		size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
+		break;
+	
+	default:
+		*errp = -EINVAL;
+		read_unlock_bh(&queue_lock);
+		return NULL;
+	}
+
+	read_unlock_bh(&queue_lock);
+
+	skb = alloc_skb(size, GFP_ATOMIC);
+	if (!skb)
+		goto nlmsg_failure;
+		
+	old_tail= skb->tail;
+	nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh));
+	pmsg = NLMSG_DATA(nlh);
+	memset(pmsg, 0, sizeof(*pmsg));
+
+	pmsg->packet_id       = (unsigned long )entry;
+	pmsg->data_len        = data_len;
+	pmsg->timestamp_sec   = entry->skb->stamp.tv_sec;
+	pmsg->timestamp_usec  = entry->skb->stamp.tv_usec;
+	pmsg->mark            = entry->skb->nfmark;
+	pmsg->hook            = entry->info->hook;
+	pmsg->hw_protocol     = entry->skb->protocol;
+	
+	if (entry->info->indev)
+		strcpy(pmsg->indev_name, entry->info->indev->name);
+	else
+		pmsg->indev_name[0] = '\0';
+	
+	if (entry->info->outdev)
+		strcpy(pmsg->outdev_name, entry->info->outdev->name);
+	else
+		pmsg->outdev_name[0] = '\0';
+	
+	if (entry->info->indev && entry->skb->dev) {
+		pmsg->hw_type = entry->skb->dev->type;
+		if (entry->skb->dev->hard_header_parse)
+			pmsg->hw_addrlen =
+				entry->skb->dev->hard_header_parse(entry->skb,
+				                                   pmsg->hw_addr);
+	}
+	
+	if (data_len)
+		if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len))
+			BUG();
+		
+	nlh->nlmsg_len = skb->tail - old_tail;
+	return skb;
+
+nlmsg_failure:
+	if (skb)
+		kfree_skb(skb);
+	*errp = -EINVAL;
+	printk(KERN_ERR "ip6_queue: error creating packet message\n");
+	return NULL;
+}
+
+static int
+ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info, void *data)
+{
+	int status = -EINVAL;
+	struct sk_buff *nskb;
+	struct ipq_queue_entry *entry;
+
+	if (copy_mode == IPQ_COPY_NONE)
+		return -EAGAIN;
+
+	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	if (entry == NULL) {
+		printk(KERN_ERR "ip6_queue: OOM in ipq_enqueue_packet()\n");
+		return -ENOMEM;
+	}
+
+	entry->info = info;
+	entry->skb = skb;
+
+	if (entry->info->hook == NF_IP_LOCAL_OUT) {
+		struct ipv6hdr *iph = skb->nh.ipv6h;
+
+		entry->rt_info.daddr = iph->daddr;
+		entry->rt_info.saddr = iph->saddr;
+	}
+
+	nskb = ipq_build_packet_message(entry, &status);
+	if (nskb == NULL)
+		goto err_out_free;
+		
+	write_lock_bh(&queue_lock);
+	
+	if (!peer_pid)
+		goto err_out_free_nskb; 
+
+	if (queue_total >= queue_maxlen) {
+                queue_dropped++;
+		status = -ENOSPC;
+		if (net_ratelimit())
+		        printk (KERN_WARNING "ip6_queue: fill at %d entries, "
+				"dropping packet(s).  Dropped: %d\n", queue_total,
+				queue_dropped);
+		goto err_out_free_nskb;
+	}
+
+ 	/* netlink_unicast will either free the nskb or attach it to a socket */ 
+	status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT);
+	if (status < 0) {
+ 	        queue_user_dropped++;
+		goto err_out_unlock;
+	}
+	
+	__ipq_enqueue_entry(entry);
+
+	write_unlock_bh(&queue_lock);
+	return status;
+	
+err_out_free_nskb:
+	kfree_skb(nskb); 
+	
+err_out_unlock:
+	write_unlock_bh(&queue_lock);
+
+err_out_free:
+	kfree(entry);
+	return status;
+}
+
+static int
+ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
+{
+	int diff;
+	struct ipv6hdr *user_iph = (struct ipv6hdr *)v->payload;
+
+	if (v->data_len < sizeof(*user_iph))
+		return 0;
+	diff = v->data_len - e->skb->len;
+	if (diff < 0)
+		skb_trim(e->skb, v->data_len);
+	else if (diff > 0) {
+		if (v->data_len > 0xFFFF)
+			return -EINVAL;
+		if (diff > skb_tailroom(e->skb)) {
+			struct sk_buff *newskb;
+			
+			newskb = skb_copy_expand(e->skb,
+			                         skb_headroom(e->skb),
+			                         diff,
+			                         GFP_ATOMIC);
+			if (newskb == NULL) {
+				printk(KERN_WARNING "ip6_queue: OOM "
+				      "in mangle, dropping packet\n");
+				return -ENOMEM;
+			}
+			if (e->skb->sk)
+				skb_set_owner_w(newskb, e->skb->sk);
+			kfree_skb(e->skb);
+			e->skb = newskb;
+		}
+		skb_put(e->skb, diff);
+	}
+	if (!skb_ip_make_writable(&e->skb, v->data_len))
+		return -ENOMEM;
+	memcpy(e->skb->data, v->payload, v->data_len);
+	e->skb->nfcache |= NFC_ALTERED;
+
+	/*
+	 * Extra routing may needed on local out, as the QUEUE target never
+	 * returns control to the table.
+         * Not a nice way to cmp, but works
+	 */
+	if (e->info->hook == NF_IP_LOCAL_OUT) {
+		struct ipv6hdr *iph = e->skb->nh.ipv6h;
+		if (!ipv6_addr_equal(&iph->daddr, &e->rt_info.daddr) ||
+		    !ipv6_addr_equal(&iph->saddr, &e->rt_info.saddr))
+			return ip6_route_me_harder(e->skb);
+	}
+	return 0;
+}
+
+static inline int
+id_cmp(struct ipq_queue_entry *e, unsigned long id)
+{
+	return (id == (unsigned long )e);
+}
+
+static int
+ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
+{
+	struct ipq_queue_entry *entry;
+
+	if (vmsg->value > NF_MAX_VERDICT)
+		return -EINVAL;
+
+	entry = ipq_find_dequeue_entry(id_cmp, vmsg->id);
+	if (entry == NULL)
+		return -ENOENT;
+	else {
+		int verdict = vmsg->value;
+		
+		if (vmsg->data_len && vmsg->data_len == len)
+			if (ipq_mangle_ipv6(vmsg, entry) < 0)
+				verdict = NF_DROP;
+		
+		ipq_issue_verdict(entry, verdict);
+		return 0;
+	}
+}
+
+static int
+ipq_set_mode(unsigned char mode, unsigned int range)
+{
+	int status;
+
+	write_lock_bh(&queue_lock);
+	status = __ipq_set_mode(mode, range);
+	write_unlock_bh(&queue_lock);
+	return status;
+}
+
+static int
+ipq_receive_peer(struct ipq_peer_msg *pmsg,
+                 unsigned char type, unsigned int len)
+{
+	int status = 0;
+
+	if (len < sizeof(*pmsg))
+		return -EINVAL;
+
+	switch (type) {
+	case IPQM_MODE:
+		status = ipq_set_mode(pmsg->msg.mode.value,
+		                      pmsg->msg.mode.range);
+		break;
+		
+	case IPQM_VERDICT:
+		if (pmsg->msg.verdict.value > NF_MAX_VERDICT)
+			status = -EINVAL;
+		else
+			status = ipq_set_verdict(&pmsg->msg.verdict,
+			                         len - sizeof(*pmsg));
+			break;
+	default:
+		status = -EINVAL;
+	}
+	return status;
+}
+
+static int
+dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
+{
+	if (entry->info->indev)
+		if (entry->info->indev->ifindex == ifindex)
+			return 1;
+			
+	if (entry->info->outdev)
+		if (entry->info->outdev->ifindex == ifindex)
+			return 1;
+
+	return 0;
+}
+
+static void
+ipq_dev_drop(int ifindex)
+{
+	struct ipq_queue_entry *entry;
+	
+	while ((entry = ipq_find_dequeue_entry(dev_cmp, ifindex)) != NULL)
+		ipq_issue_verdict(entry, NF_DROP);
+}
+
+#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)
+
+static inline void
+ipq_rcv_skb(struct sk_buff *skb)
+{
+	int status, type, pid, flags, nlmsglen, skblen;
+	struct nlmsghdr *nlh;
+
+	skblen = skb->len;
+	if (skblen < sizeof(*nlh))
+		return;
+
+	nlh = (struct nlmsghdr *)skb->data;
+	nlmsglen = nlh->nlmsg_len;
+	if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen)
+		return;
+
+	pid = nlh->nlmsg_pid;
+	flags = nlh->nlmsg_flags;
+	
+	if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI)
+		RCV_SKB_FAIL(-EINVAL);
+		
+	if (flags & MSG_TRUNC)
+		RCV_SKB_FAIL(-ECOMM);
+		
+	type = nlh->nlmsg_type;
+	if (type < NLMSG_NOOP || type >= IPQM_MAX)
+		RCV_SKB_FAIL(-EINVAL);
+		
+	if (type <= IPQM_BASE)
+		return;
+	
+	if (security_netlink_recv(skb))
+		RCV_SKB_FAIL(-EPERM);	
+
+	write_lock_bh(&queue_lock);
+	
+	if (peer_pid) {
+		if (peer_pid != pid) {
+			write_unlock_bh(&queue_lock);
+			RCV_SKB_FAIL(-EBUSY);
+		}
+	} else {
+		net_enable_timestamp();
+		peer_pid = pid;
+	}
+		
+	write_unlock_bh(&queue_lock);
+	
+	status = ipq_receive_peer(NLMSG_DATA(nlh), type,
+	                          skblen - NLMSG_LENGTH(0));
+	if (status < 0)
+		RCV_SKB_FAIL(status);
+		
+	if (flags & NLM_F_ACK)
+		netlink_ack(skb, nlh, 0);
+        return;
+}
+
+static void
+ipq_rcv_sk(struct sock *sk, int len)
+{
+	do {
+		struct sk_buff *skb;
+
+		if (down_trylock(&ipqnl_sem))
+			return;
+			
+		while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+			ipq_rcv_skb(skb);
+			kfree_skb(skb);
+		}
+		
+		up(&ipqnl_sem);
+
+	} while (ipqnl && ipqnl->sk_receive_queue.qlen);
+}
+
+static int
+ipq_rcv_dev_event(struct notifier_block *this,
+                  unsigned long event, void *ptr)
+{
+	struct net_device *dev = ptr;
+
+	/* Drop any packets associated with the downed device */
+	if (event == NETDEV_DOWN)
+		ipq_dev_drop(dev->ifindex);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ipq_dev_notifier = {
+	.notifier_call	= ipq_rcv_dev_event,
+};
+
+static int
+ipq_rcv_nl_event(struct notifier_block *this,
+                 unsigned long event, void *ptr)
+{
+	struct netlink_notify *n = ptr;
+
+	if (event == NETLINK_URELEASE &&
+	    n->protocol == NETLINK_IP6_FW && n->pid) {
+		write_lock_bh(&queue_lock);
+		if (n->pid == peer_pid)
+			__ipq_reset();
+		write_unlock_bh(&queue_lock);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ipq_nl_notifier = {
+	.notifier_call	= ipq_rcv_nl_event,
+};
+
+static struct ctl_table_header *ipq_sysctl_header;
+
+static ctl_table ipq_table[] = {
+	{
+		.ctl_name	= NET_IPQ_QMAX,
+		.procname	= NET_IPQ_QMAX_NAME,
+		.data		= &queue_maxlen,
+		.maxlen		= sizeof(queue_maxlen),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+ 	{ .ctl_name = 0 }
+};
+
+static ctl_table ipq_dir_table[] = {
+	{
+		.ctl_name	= NET_IPV6,
+		.procname	= "ipv6",
+		.mode		= 0555,
+		.child		= ipq_table
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table ipq_root_table[] = {
+	{
+		.ctl_name	= CTL_NET,
+		.procname	= "net",
+		.mode		= 0555,
+		.child		= ipq_dir_table
+	},
+	{ .ctl_name = 0 }
+};
+
+static int
+ipq_get_info(char *buffer, char **start, off_t offset, int length)
+{
+	int len;
+
+	read_lock_bh(&queue_lock);
+	
+	len = sprintf(buffer,
+	              "Peer PID          : %d\n"
+	              "Copy mode         : %hu\n"
+	              "Copy range        : %u\n"
+	              "Queue length      : %u\n"
+	              "Queue max. length : %u\n"
+		      "Queue dropped     : %u\n"
+		      "Netfilter dropped : %u\n",
+	              peer_pid,
+	              copy_mode,
+	              copy_range,
+	              queue_total,
+	              queue_maxlen,
+		      queue_dropped,
+		      queue_user_dropped);
+
+	read_unlock_bh(&queue_lock);
+	
+	*start = buffer + offset;
+	len -= offset;
+	if (len > length)
+		len = length;
+	else if (len < 0)
+		len = 0;
+	return len;
+}
+
+static int
+init_or_cleanup(int init)
+{
+	int status = -ENOMEM;
+	struct proc_dir_entry *proc;
+	
+	if (!init)
+		goto cleanup;
+
+	netlink_register_notifier(&ipq_nl_notifier);
+	ipqnl = netlink_kernel_create(NETLINK_IP6_FW, ipq_rcv_sk);
+	if (ipqnl == NULL) {
+		printk(KERN_ERR "ip6_queue: failed to create netlink socket\n");
+		goto cleanup_netlink_notifier;
+	}
+
+	proc = proc_net_create(IPQ_PROC_FS_NAME, 0, ipq_get_info);
+	if (proc)
+		proc->owner = THIS_MODULE;
+	else {
+		printk(KERN_ERR "ip6_queue: failed to create proc entry\n");
+		goto cleanup_ipqnl;
+	}
+	
+	register_netdevice_notifier(&ipq_dev_notifier);
+	ipq_sysctl_header = register_sysctl_table(ipq_root_table, 0);
+	
+	status = nf_register_queue_handler(PF_INET6, ipq_enqueue_packet, NULL);
+	if (status < 0) {
+		printk(KERN_ERR "ip6_queue: failed to register queue handler\n");
+		goto cleanup_sysctl;
+	}
+	return status;
+
+cleanup:
+	nf_unregister_queue_handler(PF_INET6);
+	synchronize_net();
+	ipq_flush(NF_DROP);
+	
+cleanup_sysctl:
+	unregister_sysctl_table(ipq_sysctl_header);
+	unregister_netdevice_notifier(&ipq_dev_notifier);
+	proc_net_remove(IPQ_PROC_FS_NAME);
+	
+cleanup_ipqnl:
+	sock_release(ipqnl->sk_socket);
+	down(&ipqnl_sem);
+	up(&ipqnl_sem);
+	
+cleanup_netlink_notifier:
+	netlink_unregister_notifier(&ipq_nl_notifier);
+	return status;
+}
+
+static int __init init(void)
+{
+	
+	return init_or_cleanup(1);
+}
+
+static void __exit fini(void)
+{
+	init_or_cleanup(0);
+}
+
+MODULE_DESCRIPTION("IPv6 packet queue handler");
+MODULE_LICENSE("GPL");
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_LOG.c

@@ -0,0 +1,509 @@
+/*
+ * This is a module which is used for logging packets.
+ */
+
+/* (C) 2001 Jan Rekorajski <baggins@pld.org.pl>
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/spinlock.h>
+#include <linux/icmpv6.h>
+#include <net/udp.h>
+#include <net/tcp.h>
+#include <net/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>");
+MODULE_DESCRIPTION("IP6 tables LOG target module");
+MODULE_LICENSE("GPL");
+
+static unsigned int nflog = 1;
+module_param(nflog, int, 0400);
+MODULE_PARM_DESC(nflog, "register as internal netfilter logging module");
+ 
+struct in_device;
+#include <net/route.h>
+#include <linux/netfilter_ipv6/ip6t_LOG.h>
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/* Use lock to serialize, so printks don't overlap */
+static DEFINE_SPINLOCK(log_lock);
+
+/* One level of recursion won't kill us */
+static void dump_packet(const struct ip6t_log_info *info,
+			const struct sk_buff *skb, unsigned int ip6hoff,
+			int recurse)
+{
+	u_int8_t currenthdr;
+	int fragment;
+	struct ipv6hdr _ip6h, *ih;
+	unsigned int ptr;
+	unsigned int hdrlen = 0;
+
+	ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h);
+	if (ih == NULL) {
+		printk("TRUNCATED");
+		return;
+	}
+
+	/* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000" */
+	printk("SRC=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->saddr));
+	printk("DST=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->daddr));
+
+	/* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */
+	printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ",
+	       ntohs(ih->payload_len) + sizeof(struct ipv6hdr),
+	       (ntohl(*(u_int32_t *)ih) & 0x0ff00000) >> 20,
+	       ih->hop_limit,
+	       (ntohl(*(u_int32_t *)ih) & 0x000fffff));
+
+	fragment = 0;
+	ptr = ip6hoff + sizeof(struct ipv6hdr);
+	currenthdr = ih->nexthdr;
+	while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+		if (hp == NULL) {
+			printk("TRUNCATED");
+			return;
+		}
+
+		/* Max length: 48 "OPT (...) " */
+		if (info->logflags & IP6T_LOG_IPOPT)
+			printk("OPT ( ");
+
+		switch (currenthdr) {
+		case IPPROTO_FRAGMENT: {
+			struct frag_hdr _fhdr, *fh;
+
+			printk("FRAG:");
+			fh = skb_header_pointer(skb, ptr, sizeof(_fhdr),
+						&_fhdr);
+			if (fh == NULL) {
+				printk("TRUNCATED ");
+				return;
+			}
+
+			/* Max length: 6 "65535 " */
+			printk("%u ", ntohs(fh->frag_off) & 0xFFF8);
+
+			/* Max length: 11 "INCOMPLETE " */
+			if (fh->frag_off & htons(0x0001))
+				printk("INCOMPLETE ");
+
+			printk("ID:%08x ", ntohl(fh->identification));
+
+			if (ntohs(fh->frag_off) & 0xFFF8)
+				fragment = 1;
+
+			hdrlen = 8;
+
+			break;
+		}
+		case IPPROTO_DSTOPTS:
+		case IPPROTO_ROUTING:
+		case IPPROTO_HOPOPTS:
+			if (fragment) {
+				if (info->logflags & IP6T_LOG_IPOPT)
+					printk(")");
+				return;
+			}
+			hdrlen = ipv6_optlen(hp);
+			break;
+		/* Max Length */
+		case IPPROTO_AH:
+			if (info->logflags & IP6T_LOG_IPOPT) {
+				struct ip_auth_hdr _ahdr, *ah;
+
+				/* Max length: 3 "AH " */
+				printk("AH ");
+
+				if (fragment) {
+					printk(")");
+					return;
+				}
+
+				ah = skb_header_pointer(skb, ptr, sizeof(_ahdr),
+							&_ahdr);
+				if (ah == NULL) {
+					/*
+					 * Max length: 26 "INCOMPLETE [65535 	
+					 *  bytes] )"
+					 */
+					printk("INCOMPLETE [%u bytes] )",
+					       skb->len - ptr);
+					return;
+				}
+
+				/* Length: 15 "SPI=0xF1234567 */
+				printk("SPI=0x%x ", ntohl(ah->spi));
+
+			}
+
+			hdrlen = (hp->hdrlen+2)<<2;
+			break;
+		case IPPROTO_ESP:
+			if (info->logflags & IP6T_LOG_IPOPT) {
+				struct ip_esp_hdr _esph, *eh;
+
+				/* Max length: 4 "ESP " */
+				printk("ESP ");
+
+				if (fragment) {
+					printk(")");
+					return;
+				}
+
+				/*
+				 * Max length: 26 "INCOMPLETE [65535 bytes] )"
+				 */
+				eh = skb_header_pointer(skb, ptr, sizeof(_esph),
+							&_esph);
+				if (eh == NULL) {
+					printk("INCOMPLETE [%u bytes] )",
+					       skb->len - ptr);
+					return;
+				}
+
+				/* Length: 16 "SPI=0xF1234567 )" */
+				printk("SPI=0x%x )", ntohl(eh->spi) );
+
+			}
+			return;
+		default:
+			/* Max length: 20 "Unknown Ext Hdr 255" */
+			printk("Unknown Ext Hdr %u", currenthdr);
+			return;
+		}
+		if (info->logflags & IP6T_LOG_IPOPT)
+			printk(") ");
+
+		currenthdr = hp->nexthdr;
+		ptr += hdrlen;
+	}
+
+	switch (currenthdr) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		/* Max length: 10 "PROTO=TCP " */
+		printk("PROTO=TCP ");
+
+		if (fragment)
+			break;
+
+		/* Max length: 25 "INCOMPLETE [65535 bytes] " */
+		th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph);
+		if (th == NULL) {
+			printk("INCOMPLETE [%u bytes] ", skb->len - ptr);
+			return;
+		}
+
+		/* Max length: 20 "SPT=65535 DPT=65535 " */
+		printk("SPT=%u DPT=%u ",
+		       ntohs(th->source), ntohs(th->dest));
+		/* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */
+		if (info->logflags & IP6T_LOG_TCPSEQ)
+			printk("SEQ=%u ACK=%u ",
+			       ntohl(th->seq), ntohl(th->ack_seq));
+		/* Max length: 13 "WINDOW=65535 " */
+		printk("WINDOW=%u ", ntohs(th->window));
+		/* Max length: 9 "RES=0x3C " */
+		printk("RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22));
+		/* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */
+		if (th->cwr)
+			printk("CWR ");
+		if (th->ece)
+			printk("ECE ");
+		if (th->urg)
+			printk("URG ");
+		if (th->ack)
+			printk("ACK ");
+		if (th->psh)
+			printk("PSH ");
+		if (th->rst)
+			printk("RST ");
+		if (th->syn)
+			printk("SYN ");
+		if (th->fin)
+			printk("FIN ");
+		/* Max length: 11 "URGP=65535 " */
+		printk("URGP=%u ", ntohs(th->urg_ptr));
+
+		if ((info->logflags & IP6T_LOG_TCPOPT)
+		    && th->doff * 4 > sizeof(struct tcphdr)) {
+			u_int8_t _opt[60 - sizeof(struct tcphdr)], *op;
+			unsigned int i;
+			unsigned int optsize = th->doff * 4
+					       - sizeof(struct tcphdr);
+
+			op = skb_header_pointer(skb,
+						ptr + sizeof(struct tcphdr),
+						optsize, _opt);
+			if (op == NULL) {
+				printk("OPT (TRUNCATED)");
+				return;
+			}
+
+			/* Max length: 127 "OPT (" 15*4*2chars ") " */
+			printk("OPT (");
+			for (i =0; i < optsize; i++)
+				printk("%02X", op[i]);
+			printk(") ");
+		}
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		/* Max length: 10 "PROTO=UDP " */
+		printk("PROTO=UDP ");
+
+		if (fragment)
+			break;
+
+		/* Max length: 25 "INCOMPLETE [65535 bytes] " */
+		uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph);
+		if (uh == NULL) {
+			printk("INCOMPLETE [%u bytes] ", skb->len - ptr);
+			return;
+		}
+
+		/* Max length: 20 "SPT=65535 DPT=65535 " */
+		printk("SPT=%u DPT=%u LEN=%u ",
+		       ntohs(uh->source), ntohs(uh->dest),
+		       ntohs(uh->len));
+		break;
+	}
+	case IPPROTO_ICMPV6: {
+		struct icmp6hdr _icmp6h, *ic;
+
+		/* Max length: 13 "PROTO=ICMPv6 " */
+		printk("PROTO=ICMPv6 ");
+
+		if (fragment)
+			break;
+
+		/* Max length: 25 "INCOMPLETE [65535 bytes] " */
+		ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h);
+		if (ic == NULL) {
+			printk("INCOMPLETE [%u bytes] ", skb->len - ptr);
+			return;
+		}
+
+		/* Max length: 18 "TYPE=255 CODE=255 " */
+		printk("TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code);
+
+		switch (ic->icmp6_type) {
+		case ICMPV6_ECHO_REQUEST:
+		case ICMPV6_ECHO_REPLY:
+			/* Max length: 19 "ID=65535 SEQ=65535 " */
+			printk("ID=%u SEQ=%u ",
+				ntohs(ic->icmp6_identifier),
+				ntohs(ic->icmp6_sequence));
+			break;
+		case ICMPV6_MGM_QUERY:
+		case ICMPV6_MGM_REPORT:
+		case ICMPV6_MGM_REDUCTION:
+			break;
+
+		case ICMPV6_PARAMPROB:
+			/* Max length: 17 "POINTER=ffffffff " */
+			printk("POINTER=%08x ", ntohl(ic->icmp6_pointer));
+			/* Fall through */
+		case ICMPV6_DEST_UNREACH:
+		case ICMPV6_PKT_TOOBIG:
+		case ICMPV6_TIME_EXCEED:
+			/* Max length: 3+maxlen */
+			if (recurse) {
+				printk("[");
+				dump_packet(info, skb, ptr + sizeof(_icmp6h),
+					    0);
+				printk("] ");
+			}
+
+			/* Max length: 10 "MTU=65535 " */
+			if (ic->icmp6_type == ICMPV6_PKT_TOOBIG)
+				printk("MTU=%u ", ntohl(ic->icmp6_mtu));
+		}
+		break;
+	}
+	/* Max length: 10 "PROTO=255 " */
+	default:
+		printk("PROTO=%u ", currenthdr);
+	}
+
+	/* Max length: 15 "UID=4294967295 " */
+	if ((info->logflags & IP6T_LOG_UID) && recurse && skb->sk) {
+		read_lock_bh(&skb->sk->sk_callback_lock);
+		if (skb->sk->sk_socket && skb->sk->sk_socket->file)
+			printk("UID=%u ", skb->sk->sk_socket->file->f_uid);
+		read_unlock_bh(&skb->sk->sk_callback_lock);
+	}
+}
+
+static void
+ip6t_log_packet(unsigned int hooknum,
+		const struct sk_buff *skb,
+		const struct net_device *in,
+		const struct net_device *out,
+		const struct ip6t_log_info *loginfo,
+		const char *level_string,
+		const char *prefix)
+{
+	struct ipv6hdr *ipv6h = skb->nh.ipv6h;
+
+	spin_lock_bh(&log_lock);
+	printk(level_string);
+	printk("%sIN=%s OUT=%s ",
+		prefix == NULL ? loginfo->prefix : prefix,
+		in ? in->name : "",
+		out ? out->name : "");
+	if (in && !out) {
+		/* MAC logging for input chain only. */
+		printk("MAC=");
+		if (skb->dev && skb->dev->hard_header_len && skb->mac.raw != (void*)ipv6h) {
+			if (skb->dev->type != ARPHRD_SIT){
+			  int i;
+			  unsigned char *p = skb->mac.raw;
+			  for (i = 0; i < skb->dev->hard_header_len; i++,p++)
+				printk("%02x%c", *p,
+			       		i==skb->dev->hard_header_len - 1
+			       		? ' ':':');
+			} else {
+			  int i;
+			  unsigned char *p = skb->mac.raw;
+			  if ( p - (ETH_ALEN*2+2) > skb->head ){
+			    p -= (ETH_ALEN+2);
+			    for (i = 0; i < (ETH_ALEN); i++,p++)
+				printk("%02x%s", *p,
+					i == ETH_ALEN-1 ? "->" : ":");
+			    p -= (ETH_ALEN*2);
+			    for (i = 0; i < (ETH_ALEN); i++,p++)
+				printk("%02x%c", *p,
+					i == ETH_ALEN-1 ? ' ' : ':');
+			  }
+			  
+			  if ((skb->dev->addr_len == 4) &&
+			      skb->dev->hard_header_len > 20){
+			    printk("TUNNEL=");
+			    p = skb->mac.raw + 12;
+			    for (i = 0; i < 4; i++,p++)
+				printk("%3d%s", *p,
+					i == 3 ? "->" : ".");
+			    for (i = 0; i < 4; i++,p++)
+				printk("%3d%c", *p,
+					i == 3 ? ' ' : '.');
+			  }
+			}
+		} else
+			printk(" ");
+	}
+
+	dump_packet(loginfo, skb, (u8*)skb->nh.ipv6h - skb->data, 1);
+	printk("\n");
+	spin_unlock_bh(&log_lock);
+}
+
+static unsigned int
+ip6t_log_target(struct sk_buff **pskb,
+		const struct net_device *in,
+		const struct net_device *out,
+		unsigned int hooknum,
+		const void *targinfo,
+		void *userinfo)
+{
+	const struct ip6t_log_info *loginfo = targinfo;
+	char level_string[4] = "< >";
+
+	level_string[1] = '0' + (loginfo->level % 8);
+	ip6t_log_packet(hooknum, *pskb, in, out, loginfo, level_string, NULL);
+
+	return IP6T_CONTINUE;
+}
+
+static void
+ip6t_logfn(unsigned int hooknum,
+	   const struct sk_buff *skb,
+	   const struct net_device *in,
+	   const struct net_device *out,
+	   const char *prefix)
+{
+	struct ip6t_log_info loginfo = {
+		.level = 0,
+		.logflags = IP6T_LOG_MASK,
+		.prefix = ""
+	};
+
+	ip6t_log_packet(hooknum, skb, in, out, &loginfo, KERN_WARNING, prefix);
+}
+
+static int ip6t_log_checkentry(const char *tablename,
+			       const struct ip6t_entry *e,
+			       void *targinfo,
+			       unsigned int targinfosize,
+			       unsigned int hook_mask)
+{
+	const struct ip6t_log_info *loginfo = targinfo;
+
+	if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_log_info))) {
+		DEBUGP("LOG: targinfosize %u != %u\n",
+		       targinfosize, IP6T_ALIGN(sizeof(struct ip6t_log_info)));
+		return 0;
+	}
+
+	if (loginfo->level >= 8) {
+		DEBUGP("LOG: level %u >= 8\n", loginfo->level);
+		return 0;
+	}
+
+	if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') {
+		DEBUGP("LOG: prefix term %i\n",
+		       loginfo->prefix[sizeof(loginfo->prefix)-1]);
+		return 0;
+	}
+
+	return 1;
+}
+
+static struct ip6t_target ip6t_log_reg = {
+	.name 		= "LOG",
+	.target 	= ip6t_log_target, 
+	.checkentry	= ip6t_log_checkentry, 
+	.me 		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	if (ip6t_register_target(&ip6t_log_reg))
+		return -EINVAL;
+	if (nflog)
+		nf_log_register(PF_INET6, &ip6t_logfn);
+
+	return 0;
+}
+
+static void __exit fini(void)
+{
+	if (nflog)
+		nf_log_unregister(PF_INET6, &ip6t_logfn);
+	ip6t_unregister_target(&ip6t_log_reg);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_MARK.c

@@ -0,0 +1,78 @@
+/* This is a module which is used for setting the NFMARK field of an skb. */
+
+/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <net/checksum.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_MARK.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+
+static unsigned int
+target(struct sk_buff **pskb,
+       const struct net_device *in,
+       const struct net_device *out,
+       unsigned int hooknum,
+       const void *targinfo,
+       void *userinfo)
+{
+	const struct ip6t_mark_target_info *markinfo = targinfo;
+
+	if((*pskb)->nfmark != markinfo->mark) {
+		(*pskb)->nfmark = markinfo->mark;
+		(*pskb)->nfcache |= NFC_ALTERED;
+	}
+	return IP6T_CONTINUE;
+}
+
+static int
+checkentry(const char *tablename,
+	   const struct ip6t_entry *e,
+           void *targinfo,
+           unsigned int targinfosize,
+           unsigned int hook_mask)
+{
+	if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_mark_target_info))) {
+		printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n",
+		       targinfosize,
+		       IP6T_ALIGN(sizeof(struct ip6t_mark_target_info)));
+		return 0;
+	}
+
+	if (strcmp(tablename, "mangle") != 0) {
+		printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename);
+		return 0;
+	}
+
+	return 1;
+}
+
+static struct ip6t_target ip6t_mark_reg
+= { { NULL, NULL }, "MARK", target, checkentry, NULL, THIS_MODULE };
+
+static int __init init(void)
+{
+	printk(KERN_DEBUG "registering ipv6 mark target\n");
+	if (ip6t_register_target(&ip6t_mark_reg))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_target(&ip6t_mark_reg);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_ah.c

@@ -0,0 +1,208 @@
+/* Kernel module to match AH parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_ah.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 AH match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/* Returns 1 if the spi is matched by the range, 0 otherwise */
+static inline int
+spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert)
+{
+	int r=0;
+	DEBUGP("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ',
+	       min,spi,max);
+	r = (spi >= min && spi <= max) ^ invert;
+	DEBUGP(" result %s\n",r? "PASS\n" : "FAILED\n");
+	return r;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	struct ip_auth_hdr *ah = NULL, _ah;
+	const struct ip6t_ah *ahinfo = matchinfo;
+	unsigned int temp;
+	int len;
+	u8 nexthdr;
+	unsigned int ptr;
+	unsigned int hdrlen = 0;
+
+	/*DEBUGP("IPv6 AH entered\n");*/
+	/* if (opt->auth == 0) return 0;
+	* It does not filled on output */
+
+	/* type of the 1st exthdr */
+	nexthdr = skb->nh.ipv6h->nexthdr;
+	/* pointer to the 1st exthdr */
+	ptr = sizeof(struct ipv6hdr);
+	/* available length */
+	len = skb->len - ptr;
+	temp = 0;
+
+	while (ip6t_ext_hdr(nexthdr)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		DEBUGP("ipv6_ah header iteration \n");
+
+		/* Is there enough space for the next ext header? */
+		if (len < sizeof(struct ipv6_opt_hdr))
+			return 0;
+		/* No more exthdr -> evaluate */
+		if (nexthdr == NEXTHDR_NONE)
+			break;
+		/* ESP -> evaluate */
+		if (nexthdr == NEXTHDR_ESP)
+			break;
+
+		hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+		BUG_ON(hp == NULL);
+
+		/* Calculate the header length */
+		if (nexthdr == NEXTHDR_FRAGMENT)
+			hdrlen = 8;
+		else if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hp->hdrlen+2)<<2;
+		else
+			hdrlen = ipv6_optlen(hp);
+
+		/* AH -> evaluate */
+		if (nexthdr == NEXTHDR_AUTH) {
+			temp |= MASK_AH;
+			break;
+		}
+
+		
+		/* set the flag */
+		switch (nexthdr) {
+		case NEXTHDR_HOP:
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_FRAGMENT:
+		case NEXTHDR_AUTH:
+		case NEXTHDR_DEST:
+			break;
+		default:
+			DEBUGP("ipv6_ah match: unknown nextheader %u\n",nexthdr);
+			return 0;
+		}
+
+		nexthdr = hp->nexthdr;
+		len -= hdrlen;
+		ptr += hdrlen;
+		if (ptr > skb->len) {
+			DEBUGP("ipv6_ah: new pointer too large! \n");
+			break;
+		}
+	}
+
+	/* AH header not found */
+	if (temp != MASK_AH)
+		return 0;
+
+	if (len < sizeof(struct ip_auth_hdr)){
+		*hotdrop = 1;
+		return 0;
+	}
+
+	ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah);
+	BUG_ON(ah == NULL);
+
+	DEBUGP("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen);
+	DEBUGP("RES %04X ", ah->reserved);
+	DEBUGP("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi));
+
+	DEBUGP("IPv6 AH spi %02X ",
+	       (spi_match(ahinfo->spis[0], ahinfo->spis[1],
+	                  ntohl(ah->spi),
+	                  !!(ahinfo->invflags & IP6T_AH_INV_SPI))));
+	DEBUGP("len %02X %04X %02X ",
+	       ahinfo->hdrlen, hdrlen,
+	       (!ahinfo->hdrlen ||
+	        (ahinfo->hdrlen == hdrlen) ^
+	        !!(ahinfo->invflags & IP6T_AH_INV_LEN)));
+	DEBUGP("res %02X %04X %02X\n",
+	       ahinfo->hdrres, ah->reserved,
+	       !(ahinfo->hdrres && ah->reserved));
+
+	return (ah != NULL)
+	       &&
+	       (spi_match(ahinfo->spis[0], ahinfo->spis[1],
+	                  ntohl(ah->spi),
+	                  !!(ahinfo->invflags & IP6T_AH_INV_SPI)))
+	       &&
+	       (!ahinfo->hdrlen ||
+	        (ahinfo->hdrlen == hdrlen) ^
+	        !!(ahinfo->invflags & IP6T_AH_INV_LEN))
+	       &&
+	       !(ahinfo->hdrres && ah->reserved);
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+          const struct ip6t_ip6 *ip,
+          void *matchinfo,
+          unsigned int matchinfosize,
+          unsigned int hook_mask)
+{
+	const struct ip6t_ah *ahinfo = matchinfo;
+
+	if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_ah))) {
+		DEBUGP("ip6t_ah: matchsize %u != %u\n",
+		       matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_ah)));
+		return 0;
+	}
+	if (ahinfo->invflags & ~IP6T_AH_INV_MASK) {
+		DEBUGP("ip6t_ah: unknown flags %X\n", ahinfo->invflags);
+		return 0;
+	}
+	return 1;
+}
+
+static struct ip6t_match ah_match = {
+	.name		= "ah",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&ah_match);
+}
+
+static void __exit cleanup(void)
+{
+	ip6t_unregister_match(&ah_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6t_dst.c

@@ -0,0 +1,298 @@
+/* Kernel module to match Hop-by-Hop and Destination parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <asm/byteorder.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_opts.h>
+
+#define HOPBYHOP	0
+
+MODULE_LICENSE("GPL");
+#if HOPBYHOP
+MODULE_DESCRIPTION("IPv6 HbH match");
+#else
+MODULE_DESCRIPTION("IPv6 DST match");
+#endif
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/*
+ * (Type & 0xC0) >> 6
+ * 	0	-> ignorable
+ * 	1	-> must drop the packet
+ * 	2	-> send ICMP PARM PROB regardless and drop packet
+ * 	3	-> Send ICMP if not a multicast address and drop packet
+ *  (Type & 0x20) >> 5
+ *  	0	-> invariant
+ *  	1	-> can change the routing
+ *  (Type & 0x1F) Type
+ *      0	-> Pad1 (only 1 byte!)
+ *      1	-> PadN LENGTH info (total length = length + 2)
+ *      C0 | 2	-> JUMBO 4 x x x x ( xxxx > 64k )
+ *      5	-> RTALERT 2 x x
+ */
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+       struct ipv6_opt_hdr _optsh, *oh;
+       const struct ip6t_opts *optinfo = matchinfo;
+       unsigned int temp;
+       unsigned int len;
+       u8 nexthdr;
+       unsigned int ptr;
+       unsigned int hdrlen = 0;
+       unsigned int ret = 0;
+       u8 _opttype, *tp = NULL;
+       u8 _optlen, *lp = NULL;
+       unsigned int optlen;
+       
+       /* type of the 1st exthdr */
+       nexthdr = skb->nh.ipv6h->nexthdr;
+       /* pointer to the 1st exthdr */
+       ptr = sizeof(struct ipv6hdr);
+       /* available length */
+       len = skb->len - ptr;
+       temp = 0;
+
+        while (ip6t_ext_hdr(nexthdr)) {
+               struct ipv6_opt_hdr _hdr, *hp;
+
+              DEBUGP("ipv6_opts header iteration \n");
+
+              /* Is there enough space for the next ext header? */
+                if (len < (int)sizeof(struct ipv6_opt_hdr))
+                        return 0;
+              /* No more exthdr -> evaluate */
+                if (nexthdr == NEXTHDR_NONE) {
+                     break;
+              }
+              /* ESP -> evaluate */
+                if (nexthdr == NEXTHDR_ESP) {
+                     break;
+              }
+
+	      hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+	      BUG_ON(hp == NULL);
+
+              /* Calculate the header length */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                        hdrlen = 8;
+                } else if (nexthdr == NEXTHDR_AUTH)
+                        hdrlen = (hp->hdrlen+2)<<2;
+                else
+                        hdrlen = ipv6_optlen(hp);
+
+              /* OPTS -> evaluate */
+#if HOPBYHOP
+                if (nexthdr == NEXTHDR_HOP) {
+                     temp |= MASK_HOPOPTS;
+#else
+                if (nexthdr == NEXTHDR_DEST) {
+                     temp |= MASK_DSTOPTS;
+#endif
+                     break;
+              }
+
+
+              /* set the flag */
+              switch (nexthdr){
+                     case NEXTHDR_HOP:
+                     case NEXTHDR_ROUTING:
+                     case NEXTHDR_FRAGMENT:
+                     case NEXTHDR_AUTH:
+                     case NEXTHDR_DEST:
+                            break;
+                     default:
+                            DEBUGP("ipv6_opts match: unknown nextheader %u\n",nexthdr);
+                            return 0;
+                            break;
+              }
+
+                nexthdr = hp->nexthdr;
+                len -= hdrlen;
+                ptr += hdrlen;
+		if ( ptr > skb->len ) {
+			DEBUGP("ipv6_opts: new pointer is too large! \n");
+			break;
+		}
+        }
+
+       /* OPTIONS header not found */
+#if HOPBYHOP
+       if ( temp != MASK_HOPOPTS ) return 0;
+#else
+       if ( temp != MASK_DSTOPTS ) return 0;
+#endif
+
+       if (len < (int)sizeof(struct ipv6_opt_hdr)){
+	       *hotdrop = 1;
+       		return 0;
+       }
+
+       if (len < hdrlen){
+	       /* Packet smaller than it's length field */
+       		return 0;
+       }
+
+       oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
+       BUG_ON(oh == NULL);
+
+       DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen);
+
+       DEBUGP("len %02X %04X %02X ",
+       		optinfo->hdrlen, hdrlen,
+       		(!(optinfo->flags & IP6T_OPTS_LEN) ||
+                           ((optinfo->hdrlen == hdrlen) ^
+                           !!(optinfo->invflags & IP6T_OPTS_INV_LEN))));
+
+       ret = (oh != NULL)
+       		&&
+	      	(!(optinfo->flags & IP6T_OPTS_LEN) ||
+                           ((optinfo->hdrlen == hdrlen) ^
+                           !!(optinfo->invflags & IP6T_OPTS_INV_LEN)));
+
+       ptr += 2;
+       hdrlen -= 2;
+       if ( !(optinfo->flags & IP6T_OPTS_OPTS) ){
+	       return ret;
+	} else if (optinfo->flags & IP6T_OPTS_NSTRICT) {
+		DEBUGP("Not strict - not implemented");
+	} else {
+		DEBUGP("Strict ");
+		DEBUGP("#%d ",optinfo->optsnr);
+		for(temp=0; temp<optinfo->optsnr; temp++){
+			/* type field exists ? */
+			if (hdrlen < 1)
+				break;
+			tp = skb_header_pointer(skb, ptr, sizeof(_opttype),
+						&_opttype);
+			if (tp == NULL)
+				break;
+
+			/* Type check */
+			if (*tp != (optinfo->opts[temp] & 0xFF00)>>8){
+				DEBUGP("Tbad %02X %02X\n",
+				       *tp,
+				       (optinfo->opts[temp] & 0xFF00)>>8);
+				return 0;
+			} else {
+				DEBUGP("Tok ");
+			}
+			/* Length check */
+			if (*tp) {
+				u16 spec_len;
+
+				/* length field exists ? */
+				if (hdrlen < 2)
+					break;
+				lp = skb_header_pointer(skb, ptr + 1,
+							sizeof(_optlen),
+							&_optlen);
+				if (lp == NULL)
+					break;
+				spec_len = optinfo->opts[temp] & 0x00FF;
+
+				if (spec_len != 0x00FF && spec_len != *lp) {
+					DEBUGP("Lbad %02X %04X\n", *lp,
+					       spec_len);
+					return 0;
+				}
+				DEBUGP("Lok ");
+				optlen = *lp + 2;
+			} else {
+				DEBUGP("Pad1\n");
+				optlen = 1;
+			}
+
+			/* Step to the next */
+			DEBUGP("len%04X \n", optlen);
+
+			if ((ptr > skb->len - optlen || hdrlen < optlen) &&
+			    (temp < optinfo->optsnr - 1)) {
+				DEBUGP("new pointer is too large! \n");
+				break;
+			}
+			ptr += optlen;
+			hdrlen -= optlen;
+		}
+		if (temp == optinfo->optsnr)
+			return ret;
+		else return 0;
+	}
+
+	return 0;
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+          const struct ip6t_ip6 *ip,
+          void *matchinfo,
+          unsigned int matchinfosize,
+          unsigned int hook_mask)
+{
+       const struct ip6t_opts *optsinfo = matchinfo;
+
+       if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) {
+              DEBUGP("ip6t_opts: matchsize %u != %u\n",
+                      matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts)));
+              return 0;
+       }
+       if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) {
+              DEBUGP("ip6t_opts: unknown flags %X\n",
+                      optsinfo->invflags);
+              return 0;
+       }
+
+       return 1;
+}
+
+static struct ip6t_match opts_match = {
+#if HOPBYHOP
+	.name		= "hbh",
+#else
+	.name		= "dst",
+#endif
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+       return ip6t_register_match(&opts_match);
+}
+
+static void __exit cleanup(void)
+{
+       ip6t_unregister_match(&opts_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6t_esp.c

@@ -0,0 +1,181 @@
+/* Kernel module to match ESP parameters. */
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_esp.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 ESP match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/* Returns 1 if the spi is matched by the range, 0 otherwise */
+static inline int
+spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert)
+{
+	int r=0;
+	DEBUGP("esp spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ',
+	       min,spi,max);
+	r=(spi >= min && spi <= max) ^ invert;
+	DEBUGP(" result %s\n",r? "PASS\n" : "FAILED\n");
+	return r;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	struct ip_esp_hdr _esp, *eh = NULL;
+	const struct ip6t_esp *espinfo = matchinfo;
+	unsigned int temp;
+	int len;
+	u8 nexthdr;
+	unsigned int ptr;
+
+	/* Make sure this isn't an evil packet */
+	/*DEBUGP("ipv6_esp entered \n");*/
+
+	/* type of the 1st exthdr */
+	nexthdr = skb->nh.ipv6h->nexthdr;
+	/* pointer to the 1st exthdr */
+	ptr = sizeof(struct ipv6hdr);
+	/* available length */
+	len = skb->len - ptr;
+	temp = 0;
+
+	while (ip6t_ext_hdr(nexthdr)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+		int hdrlen;
+
+		DEBUGP("ipv6_esp header iteration \n");
+
+		/* Is there enough space for the next ext header? */
+		if (len < sizeof(struct ipv6_opt_hdr))
+			return 0;
+		/* No more exthdr -> evaluate */
+		if (nexthdr == NEXTHDR_NONE)
+			break;
+		/* ESP -> evaluate */
+		if (nexthdr == NEXTHDR_ESP) {
+			temp |= MASK_ESP;
+			break;
+		}
+
+		hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+		BUG_ON(hp == NULL);
+
+		/* Calculate the header length */
+		if (nexthdr == NEXTHDR_FRAGMENT)
+			hdrlen = 8;
+		else if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hp->hdrlen+2)<<2;
+		else
+			hdrlen = ipv6_optlen(hp);
+
+		/* set the flag */
+		switch (nexthdr) {
+		case NEXTHDR_HOP:
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_FRAGMENT:
+		case NEXTHDR_AUTH:
+		case NEXTHDR_DEST:
+			break;
+		default:
+			DEBUGP("ipv6_esp match: unknown nextheader %u\n",nexthdr);
+			return 0;
+		}
+
+		nexthdr = hp->nexthdr;
+		len -= hdrlen;
+		ptr += hdrlen;
+		if (ptr > skb->len) {
+			DEBUGP("ipv6_esp: new pointer too large! \n");
+			break;
+		}
+	}
+
+	/* ESP header not found */
+	if (temp != MASK_ESP)
+		return 0;
+
+	if (len < sizeof(struct ip_esp_hdr)) {
+		*hotdrop = 1;
+		return 0;
+	}
+
+	eh = skb_header_pointer(skb, ptr, sizeof(_esp), &_esp);
+	BUG_ON(eh == NULL);
+
+	DEBUGP("IPv6 ESP SPI %u %08X\n", ntohl(eh->spi), ntohl(eh->spi));
+
+	return (eh != NULL)
+		&& spi_match(espinfo->spis[0], espinfo->spis[1],
+			      ntohl(eh->spi),
+			      !!(espinfo->invflags & IP6T_ESP_INV_SPI));
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+	   const struct ip6t_ip6 *ip,
+	   void *matchinfo,
+	   unsigned int matchinfosize,
+	   unsigned int hook_mask)
+{
+	const struct ip6t_esp *espinfo = matchinfo;
+
+	if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_esp))) {
+		DEBUGP("ip6t_esp: matchsize %u != %u\n",
+			 matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_esp)));
+		return 0;
+	}
+	if (espinfo->invflags & ~IP6T_ESP_INV_MASK) {
+		DEBUGP("ip6t_esp: unknown flags %X\n",
+			 espinfo->invflags);
+		return 0;
+	}
+	return 1;
+}
+
+static struct ip6t_match esp_match = {
+	.name		= "esp",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&esp_match);
+}
+
+static void __exit cleanup(void)
+{
+	ip6t_unregister_match(&esp_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6t_eui64.c

@@ -0,0 +1,101 @@
+/* Kernel module to match EUI64 address parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_DESCRIPTION("IPv6 EUI64 address checking match");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+
+    unsigned char eui64[8];
+    int i=0;
+
+     if ( !(skb->mac.raw >= skb->head
+                && (skb->mac.raw + ETH_HLEN) <= skb->data)
+                && offset != 0) {
+                        *hotdrop = 1;
+                        return 0;
+                }
+    
+    memset(eui64, 0, sizeof(eui64));
+
+    if (eth_hdr(skb)->h_proto == ntohs(ETH_P_IPV6)) {
+      if (skb->nh.ipv6h->version == 0x6) { 
+         memcpy(eui64, eth_hdr(skb)->h_source, 3);
+         memcpy(eui64 + 5, eth_hdr(skb)->h_source + 3, 3);
+	 eui64[3]=0xff;
+	 eui64[4]=0xfe;
+	 eui64[0] |= 0x02;
+
+	 i=0;
+	 while ((skb->nh.ipv6h->saddr.s6_addr[8+i] ==
+			 eui64[i]) && (i<8)) i++;
+
+	 if ( i == 8 )
+	 	return 1;
+      }
+    }
+
+    return 0;
+}
+
+static int
+ip6t_eui64_checkentry(const char *tablename,
+		   const struct ip6t_ip6 *ip,
+		   void *matchinfo,
+		   unsigned int matchsize,
+		   unsigned int hook_mask)
+{
+	if (hook_mask
+	    & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) |
+		(1 << NF_IP6_FORWARD))) {
+		printk("ip6t_eui64: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n");
+		return 0;
+	}
+
+	if (matchsize != IP6T_ALIGN(sizeof(int)))
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match eui64_match = {
+	.name		= "eui64",
+	.match		= &match,
+	.checkentry	= &ip6t_eui64_checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&eui64_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&eui64_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_frag.c

@@ -0,0 +1,229 @@
+/* Kernel module to match FRAG parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_frag.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 FRAG match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/* Returns 1 if the id is matched by the range, 0 otherwise */
+static inline int
+id_match(u_int32_t min, u_int32_t max, u_int32_t id, int invert)
+{
+       int r=0;
+       DEBUGP("frag id_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ',
+              min,id,max);
+       r=(id >= min && id <= max) ^ invert;
+       DEBUGP(" result %s\n",r? "PASS" : "FAILED");
+       return r;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+       struct frag_hdr _frag, *fh = NULL;
+       const struct ip6t_frag *fraginfo = matchinfo;
+       unsigned int temp;
+       int len;
+       u8 nexthdr;
+       unsigned int ptr;
+       unsigned int hdrlen = 0;
+
+       /* type of the 1st exthdr */
+       nexthdr = skb->nh.ipv6h->nexthdr;
+       /* pointer to the 1st exthdr */
+       ptr = sizeof(struct ipv6hdr);
+       /* available length */
+       len = skb->len - ptr;
+       temp = 0;
+
+        while (ip6t_ext_hdr(nexthdr)) {
+               struct ipv6_opt_hdr _hdr, *hp;
+
+              DEBUGP("ipv6_frag header iteration \n");
+
+              /* Is there enough space for the next ext header? */
+                if (len < (int)sizeof(struct ipv6_opt_hdr))
+                        return 0;
+              /* No more exthdr -> evaluate */
+                if (nexthdr == NEXTHDR_NONE) {
+                     break;
+              }
+              /* ESP -> evaluate */
+                if (nexthdr == NEXTHDR_ESP) {
+                     break;
+              }
+
+	      hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+	      BUG_ON(hp == NULL);
+
+              /* Calculate the header length */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                        hdrlen = 8;
+                } else if (nexthdr == NEXTHDR_AUTH)
+                        hdrlen = (hp->hdrlen+2)<<2;
+                else
+                        hdrlen = ipv6_optlen(hp);
+
+              /* FRAG -> evaluate */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                     temp |= MASK_FRAGMENT;
+                     break;
+              }
+
+
+              /* set the flag */
+              switch (nexthdr){
+                     case NEXTHDR_HOP:
+                     case NEXTHDR_ROUTING:
+                     case NEXTHDR_FRAGMENT:
+                     case NEXTHDR_AUTH:
+                     case NEXTHDR_DEST:
+                            break;
+                     default:
+                            DEBUGP("ipv6_frag match: unknown nextheader %u\n",nexthdr);
+                            return 0;
+                            break;
+              }
+
+                nexthdr = hp->nexthdr;
+                len -= hdrlen;
+                ptr += hdrlen;
+		if ( ptr > skb->len ) {
+			DEBUGP("ipv6_frag: new pointer too large! \n");
+			break;
+		}
+        }
+
+       /* FRAG header not found */
+       if ( temp != MASK_FRAGMENT ) return 0;
+
+       if (len < sizeof(struct frag_hdr)){
+	       *hotdrop = 1;
+       		return 0;
+       }
+
+       fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag);
+       BUG_ON(fh == NULL);
+
+       DEBUGP("INFO %04X ", fh->frag_off);
+       DEBUGP("OFFSET %04X ", ntohs(fh->frag_off) & ~0x7);
+       DEBUGP("RES %02X %04X", fh->reserved, ntohs(fh->frag_off) & 0x6);
+       DEBUGP("MF %04X ", fh->frag_off & htons(IP6_MF));
+       DEBUGP("ID %u %08X\n", ntohl(fh->identification),
+	      ntohl(fh->identification));
+
+       DEBUGP("IPv6 FRAG id %02X ",
+       		(id_match(fraginfo->ids[0], fraginfo->ids[1],
+                           ntohl(fh->identification),
+                           !!(fraginfo->invflags & IP6T_FRAG_INV_IDS))));
+       DEBUGP("res %02X %02X%04X %02X ", 
+       		(fraginfo->flags & IP6T_FRAG_RES), fh->reserved,
+		ntohs(fh->frag_off) & 0x6,
+       		!((fraginfo->flags & IP6T_FRAG_RES)
+			&& (fh->reserved || (ntohs(fh->frag_off) & 0x06))));
+       DEBUGP("first %02X %02X %02X ", 
+       		(fraginfo->flags & IP6T_FRAG_FST),
+		ntohs(fh->frag_off) & ~0x7,
+       		!((fraginfo->flags & IP6T_FRAG_FST)
+			&& (ntohs(fh->frag_off) & ~0x7)));
+       DEBUGP("mf %02X %02X %02X ", 
+       		(fraginfo->flags & IP6T_FRAG_MF),
+		ntohs(fh->frag_off) & IP6_MF,
+       		!((fraginfo->flags & IP6T_FRAG_MF)
+			&& !((ntohs(fh->frag_off) & IP6_MF))));
+       DEBUGP("last %02X %02X %02X\n", 
+       		(fraginfo->flags & IP6T_FRAG_NMF),
+		ntohs(fh->frag_off) & IP6_MF,
+       		!((fraginfo->flags & IP6T_FRAG_NMF)
+			&& (ntohs(fh->frag_off) & IP6_MF)));
+
+       return (fh != NULL)
+       		&&
+       		(id_match(fraginfo->ids[0], fraginfo->ids[1],
+			  ntohl(fh->identification),
+                           !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)))
+		&&
+		!((fraginfo->flags & IP6T_FRAG_RES)
+			&& (fh->reserved || (ntohs(fh->frag_off) & 0x6)))
+		&&
+		!((fraginfo->flags & IP6T_FRAG_FST)
+			&& (ntohs(fh->frag_off) & ~0x7))
+		&&
+		!((fraginfo->flags & IP6T_FRAG_MF)
+			&& !(ntohs(fh->frag_off) & IP6_MF))
+		&&
+		!((fraginfo->flags & IP6T_FRAG_NMF)
+			&& (ntohs(fh->frag_off) & IP6_MF));
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+          const struct ip6t_ip6 *ip,
+          void *matchinfo,
+          unsigned int matchinfosize,
+          unsigned int hook_mask)
+{
+       const struct ip6t_frag *fraginfo = matchinfo;
+
+       if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_frag))) {
+              DEBUGP("ip6t_frag: matchsize %u != %u\n",
+                      matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_frag)));
+              return 0;
+       }
+       if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) {
+              DEBUGP("ip6t_frag: unknown flags %X\n",
+                      fraginfo->invflags);
+              return 0;
+       }
+
+       return 1;
+}
+
+static struct ip6t_match frag_match = {
+	.name		= "frag",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+       return ip6t_register_match(&frag_match);
+}
+
+static void __exit cleanup(void)
+{
+       ip6t_unregister_match(&frag_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6t_hbh.c

@@ -0,0 +1,298 @@
+/* Kernel module to match Hop-by-Hop and Destination parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <asm/byteorder.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_opts.h>
+
+#define HOPBYHOP	1
+
+MODULE_LICENSE("GPL");
+#if HOPBYHOP
+MODULE_DESCRIPTION("IPv6 HbH match");
+#else
+MODULE_DESCRIPTION("IPv6 DST match");
+#endif
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/*
+ * (Type & 0xC0) >> 6
+ * 	0	-> ignorable
+ * 	1	-> must drop the packet
+ * 	2	-> send ICMP PARM PROB regardless and drop packet
+ * 	3	-> Send ICMP if not a multicast address and drop packet
+ *  (Type & 0x20) >> 5
+ *  	0	-> invariant
+ *  	1	-> can change the routing
+ *  (Type & 0x1F) Type
+ *      0	-> Pad1 (only 1 byte!)
+ *      1	-> PadN LENGTH info (total length = length + 2)
+ *      C0 | 2	-> JUMBO 4 x x x x ( xxxx > 64k )
+ *      5	-> RTALERT 2 x x
+ */
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+       struct ipv6_opt_hdr _optsh, *oh;
+       const struct ip6t_opts *optinfo = matchinfo;
+       unsigned int temp;
+       unsigned int len;
+       u8 nexthdr;
+       unsigned int ptr;
+       unsigned int hdrlen = 0;
+       unsigned int ret = 0;
+       u8 _opttype, *tp = NULL;
+       u8 _optlen, *lp = NULL;
+       unsigned int optlen;
+       
+       /* type of the 1st exthdr */
+       nexthdr = skb->nh.ipv6h->nexthdr;
+       /* pointer to the 1st exthdr */
+       ptr = sizeof(struct ipv6hdr);
+       /* available length */
+       len = skb->len - ptr;
+       temp = 0;
+
+        while (ip6t_ext_hdr(nexthdr)) {
+               struct ipv6_opt_hdr _hdr, *hp;
+
+              DEBUGP("ipv6_opts header iteration \n");
+
+              /* Is there enough space for the next ext header? */
+                if (len < (int)sizeof(struct ipv6_opt_hdr))
+                        return 0;
+              /* No more exthdr -> evaluate */
+                if (nexthdr == NEXTHDR_NONE) {
+                     break;
+              }
+              /* ESP -> evaluate */
+                if (nexthdr == NEXTHDR_ESP) {
+                     break;
+              }
+
+	      hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+	      BUG_ON(hp == NULL);
+
+              /* Calculate the header length */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                        hdrlen = 8;
+                } else if (nexthdr == NEXTHDR_AUTH)
+                        hdrlen = (hp->hdrlen+2)<<2;
+                else
+                        hdrlen = ipv6_optlen(hp);
+
+              /* OPTS -> evaluate */
+#if HOPBYHOP
+                if (nexthdr == NEXTHDR_HOP) {
+                     temp |= MASK_HOPOPTS;
+#else
+                if (nexthdr == NEXTHDR_DEST) {
+                     temp |= MASK_DSTOPTS;
+#endif
+                     break;
+              }
+
+
+              /* set the flag */
+              switch (nexthdr){
+                     case NEXTHDR_HOP:
+                     case NEXTHDR_ROUTING:
+                     case NEXTHDR_FRAGMENT:
+                     case NEXTHDR_AUTH:
+                     case NEXTHDR_DEST:
+                            break;
+                     default:
+                            DEBUGP("ipv6_opts match: unknown nextheader %u\n",nexthdr);
+                            return 0;
+                            break;
+              }
+
+                nexthdr = hp->nexthdr;
+                len -= hdrlen;
+                ptr += hdrlen;
+		if ( ptr > skb->len ) {
+			DEBUGP("ipv6_opts: new pointer is too large! \n");
+			break;
+		}
+        }
+
+       /* OPTIONS header not found */
+#if HOPBYHOP
+       if ( temp != MASK_HOPOPTS ) return 0;
+#else
+       if ( temp != MASK_DSTOPTS ) return 0;
+#endif
+
+       if (len < (int)sizeof(struct ipv6_opt_hdr)){
+	       *hotdrop = 1;
+       		return 0;
+       }
+
+       if (len < hdrlen){
+	       /* Packet smaller than it's length field */
+       		return 0;
+       }
+
+       oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
+       BUG_ON(oh == NULL);
+
+       DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen);
+
+       DEBUGP("len %02X %04X %02X ",
+       		optinfo->hdrlen, hdrlen,
+       		(!(optinfo->flags & IP6T_OPTS_LEN) ||
+                           ((optinfo->hdrlen == hdrlen) ^
+                           !!(optinfo->invflags & IP6T_OPTS_INV_LEN))));
+
+       ret = (oh != NULL)
+       		&&
+	      	(!(optinfo->flags & IP6T_OPTS_LEN) ||
+                           ((optinfo->hdrlen == hdrlen) ^
+                           !!(optinfo->invflags & IP6T_OPTS_INV_LEN)));
+
+       ptr += 2;
+       hdrlen -= 2;
+       if ( !(optinfo->flags & IP6T_OPTS_OPTS) ){
+	       return ret;
+	} else if (optinfo->flags & IP6T_OPTS_NSTRICT) {
+		DEBUGP("Not strict - not implemented");
+	} else {
+		DEBUGP("Strict ");
+		DEBUGP("#%d ",optinfo->optsnr);
+		for(temp=0; temp<optinfo->optsnr; temp++){
+			/* type field exists ? */
+			if (hdrlen < 1)
+				break;
+			tp = skb_header_pointer(skb, ptr, sizeof(_opttype),
+						&_opttype);
+			if (tp == NULL)
+				break;
+
+			/* Type check */
+			if (*tp != (optinfo->opts[temp] & 0xFF00)>>8){
+				DEBUGP("Tbad %02X %02X\n",
+				       *tp,
+				       (optinfo->opts[temp] & 0xFF00)>>8);
+				return 0;
+			} else {
+				DEBUGP("Tok ");
+			}
+			/* Length check */
+			if (*tp) {
+				u16 spec_len;
+
+				/* length field exists ? */
+				if (hdrlen < 2)
+					break;
+				lp = skb_header_pointer(skb, ptr + 1,
+							sizeof(_optlen),
+							&_optlen);
+				if (lp == NULL)
+					break;
+				spec_len = optinfo->opts[temp] & 0x00FF;
+
+				if (spec_len != 0x00FF && spec_len != *lp) {
+					DEBUGP("Lbad %02X %04X\n", *lp,
+					       spec_len);
+					return 0;
+				}
+				DEBUGP("Lok ");
+				optlen = *lp + 2;
+			} else {
+				DEBUGP("Pad1\n");
+				optlen = 1;
+			}
+
+			/* Step to the next */
+			DEBUGP("len%04X \n", optlen);
+
+			if ((ptr > skb->len - optlen || hdrlen < optlen) &&
+			    (temp < optinfo->optsnr - 1)) {
+				DEBUGP("new pointer is too large! \n");
+				break;
+			}
+			ptr += optlen;
+			hdrlen -= optlen;
+		}
+		if (temp == optinfo->optsnr)
+			return ret;
+		else return 0;
+	}
+
+	return 0;
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+          const struct ip6t_ip6 *ip,
+          void *matchinfo,
+          unsigned int matchinfosize,
+          unsigned int hook_mask)
+{
+       const struct ip6t_opts *optsinfo = matchinfo;
+
+       if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) {
+              DEBUGP("ip6t_opts: matchsize %u != %u\n",
+                      matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts)));
+              return 0;
+       }
+       if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) {
+              DEBUGP("ip6t_opts: unknown flags %X\n",
+                      optsinfo->invflags);
+              return 0;
+       }
+
+       return 1;
+}
+
+static struct ip6t_match opts_match = {
+#if HOPBYHOP
+	.name		= "hbh",
+#else
+	.name		= "dst",
+#endif
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+       return ip6t_register_match(&opts_match);
+}
+
+static void __exit cleanup(void)
+{
+       ip6t_unregister_match(&opts_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6t_hl.c

@@ -0,0 +1,80 @@
+/* Hop Limit matching module */
+
+/* (C) 2001-2002 Maciej Soltysiak <solt@dns.toxicfilms.tv>
+ * Based on HW's ttl module
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter_ipv6/ip6t_hl.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>");
+MODULE_DESCRIPTION("IP tables Hop Limit matching module");
+MODULE_LICENSE("GPL");
+
+static int match(const struct sk_buff *skb, const struct net_device *in,
+		 const struct net_device *out, const void *matchinfo,
+		 int offset, unsigned int protoff,
+		 int *hotdrop)
+{
+	const struct ip6t_hl_info *info = matchinfo;
+	const struct ipv6hdr *ip6h = skb->nh.ipv6h;
+
+	switch (info->mode) {
+		case IP6T_HL_EQ:
+			return (ip6h->hop_limit == info->hop_limit);
+			break;
+		case IP6T_HL_NE:
+			return (!(ip6h->hop_limit == info->hop_limit));
+			break;
+		case IP6T_HL_LT:
+			return (ip6h->hop_limit < info->hop_limit);
+			break;
+		case IP6T_HL_GT:
+			return (ip6h->hop_limit > info->hop_limit);
+			break;
+		default:
+			printk(KERN_WARNING "ip6t_hl: unknown mode %d\n", 
+				info->mode);
+			return 0;
+	}
+
+	return 0;
+}
+
+static int checkentry(const char *tablename, const struct ip6t_ip6 *ip,
+		      void *matchinfo, unsigned int matchsize,
+		      unsigned int hook_mask)
+{
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_hl_info)))
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match hl_match = {
+	.name		= "hl",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&hl_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&hl_match);
+
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_ipv6header.c

@@ -0,0 +1,167 @@
+/* ipv6header match - matches IPv6 packets based
+   on whether they contain certain headers */
+
+/* Original idea: Brad Chapman 
+ * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_ipv6header.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 headers match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+static int
+ipv6header_match(const struct sk_buff *skb,
+		 const struct net_device *in,
+		 const struct net_device *out,
+		 const void *matchinfo,
+		 int offset,
+		 unsigned int protoff,
+		 int *hotdrop)
+{
+	const struct ip6t_ipv6header_info *info = matchinfo;
+	unsigned int temp;
+	int len;
+	u8 nexthdr;
+	unsigned int ptr;
+
+	/* Make sure this isn't an evil packet */
+
+	/* type of the 1st exthdr */
+	nexthdr = skb->nh.ipv6h->nexthdr;
+	/* pointer to the 1st exthdr */
+	ptr = sizeof(struct ipv6hdr);
+	/* available length */
+	len = skb->len - ptr;
+	temp = 0;
+
+        while (ip6t_ext_hdr(nexthdr)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+        	int hdrlen;
+
+		/* Is there enough space for the next ext header? */
+                if (len < (int)sizeof(struct ipv6_opt_hdr))
+                        return 0;
+		/* No more exthdr -> evaluate */
+                if (nexthdr == NEXTHDR_NONE) {
+			temp |= MASK_NONE;
+			break;
+		}
+		/* ESP -> evaluate */
+                if (nexthdr == NEXTHDR_ESP) {
+			temp |= MASK_ESP;
+			break;
+		}
+
+		hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+		BUG_ON(hp == NULL);
+
+		/* Calculate the header length */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                        hdrlen = 8;
+                } else if (nexthdr == NEXTHDR_AUTH)
+                        hdrlen = (hp->hdrlen+2)<<2;
+                else
+                        hdrlen = ipv6_optlen(hp);
+
+		/* set the flag */
+		switch (nexthdr){
+			case NEXTHDR_HOP:
+				temp |= MASK_HOPOPTS;
+				break;
+			case NEXTHDR_ROUTING:
+				temp |= MASK_ROUTING;
+				break;
+			case NEXTHDR_FRAGMENT:
+				temp |= MASK_FRAGMENT;
+				break;
+			case NEXTHDR_AUTH:
+				temp |= MASK_AH;
+				break;
+			case NEXTHDR_DEST:
+				temp |= MASK_DSTOPTS;
+				break;
+			default:
+				return 0;
+				break;
+		}
+
+                nexthdr = hp->nexthdr;
+                len -= hdrlen;
+                ptr += hdrlen;
+		if (ptr > skb->len)
+			break;
+        }
+
+	if ( (nexthdr != NEXTHDR_NONE ) && (nexthdr != NEXTHDR_ESP) )
+		temp |= MASK_PROTO;
+
+	if (info->modeflag)
+		return !((temp ^ info->matchflags ^ info->invflags)
+			 & info->matchflags);
+	else {
+		if (info->invflags)
+			return temp != info->matchflags;
+		else
+			return temp == info->matchflags;
+	}
+}
+
+static int
+ipv6header_checkentry(const char *tablename,
+		      const struct ip6t_ip6 *ip,
+		      void *matchinfo,
+		      unsigned int matchsize,
+		      unsigned int hook_mask)
+{
+	const struct ip6t_ipv6header_info *info = matchinfo;
+
+	/* Check for obvious errors */
+	/* This match is valid in all hooks! */
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_ipv6header_info)))
+		return 0;
+
+	/* invflags is 0 or 0xff in hard mode */
+	if ((!info->modeflag) && info->invflags != 0x00
+			      && info->invflags != 0xFF)
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match ip6t_ipv6header_match = {
+	.name		= "ipv6header",
+	.match		= &ipv6header_match,
+	.checkentry	= &ipv6header_checkentry,
+	.destroy	= NULL,
+	.me		= THIS_MODULE,
+};
+
+static int  __init ipv6header_init(void)
+{
+	return ip6t_register_match(&ip6t_ipv6header_match);
+}
+
+static void __exit ipv6header_exit(void)
+{
+	ip6t_unregister_match(&ip6t_ipv6header_match);
+}
+
+module_init(ipv6header_init);
+module_exit(ipv6header_exit);
+

net/ipv6/netfilter/ip6t_length.c

@@ -0,0 +1,66 @@
+/* Length Match - IPv6 Port */
+
+/* (C) 1999-2001 James Morris <jmorros@intercode.com.au>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter_ipv6/ip6t_length.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
+MODULE_DESCRIPTION("IPv6 packet length match");
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	const struct ip6t_length_info *info = matchinfo;
+	u_int16_t pktlen = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr);
+	
+	return (pktlen >= info->min && pktlen <= info->max) ^ info->invert;
+}
+
+static int
+checkentry(const char *tablename,
+           const struct ip6t_ip6 *ip,
+           void *matchinfo,
+           unsigned int matchsize,
+           unsigned int hook_mask)
+{
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_length_info)))
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match length_match = {
+	.name		= "length",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&length_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&length_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_limit.c

@@ -0,0 +1,147 @@
+/* Kernel module to control the rate
+ *
+ * 2 September 1999: Changed from the target RATE to the match
+ *                   `limit', removed logging.  Did I mention that
+ *                   Alexey is a fucking genius?
+ *                   Rusty Russell (rusty@rustcorp.com.au).  */
+
+/* (C) 1999 J<>r<EFBFBD>me de Vivie <devivie@info.enserb.u-bordeaux.fr>
+ * (C) 1999 Herv<72> Eychenne <eychenne@info.enserb.u-bordeaux.fr>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_limit.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>");
+MODULE_DESCRIPTION("rate limiting within ip6tables");
+
+/* The algorithm used is the Simple Token Bucket Filter (TBF)
+ * see net/sched/sch_tbf.c in the linux source tree
+ */
+
+static DEFINE_SPINLOCK(limit_lock);
+
+/* Rusty: This is my (non-mathematically-inclined) understanding of
+   this algorithm.  The `average rate' in jiffies becomes your initial
+   amount of credit `credit' and the most credit you can ever have
+   `credit_cap'.  The `peak rate' becomes the cost of passing the
+   test, `cost'.
+
+   `prev' tracks the last packet hit: you gain one credit per jiffy.
+   If you get credit balance more than this, the extra credit is
+   discarded.  Every time the match passes, you lose `cost' credits;
+   if you don't have that many, the test fails.
+
+   See Alexey's formal explanation in net/sched/sch_tbf.c.
+
+   To avoid underflow, we multiply by 128 (ie. you get 128 credits per
+   jiffy).  Hence a cost of 2^32-1, means one pass per 32768 seconds
+   at 1024HZ (or one every 9 hours).  A cost of 1 means 12800 passes
+   per second at 100HZ.  */
+
+#define CREDITS_PER_JIFFY 128
+
+static int
+ip6t_limit_match(const struct sk_buff *skb,
+		const struct net_device *in,
+		const struct net_device *out,
+		const void *matchinfo,
+		int offset,
+		unsigned int protoff,
+		int *hotdrop)
+{
+	struct ip6t_rateinfo *r = ((struct ip6t_rateinfo *)matchinfo)->master;
+	unsigned long now = jiffies;
+
+	spin_lock_bh(&limit_lock);
+	r->credit += (now - xchg(&r->prev, now)) * CREDITS_PER_JIFFY;
+	if (r->credit > r->credit_cap)
+		r->credit = r->credit_cap;
+
+	if (r->credit >= r->cost) {
+		/* We're not limited. */
+		r->credit -= r->cost;
+		spin_unlock_bh(&limit_lock);
+		return 1;
+	}
+
+       	spin_unlock_bh(&limit_lock);
+	return 0;
+}
+
+/* Precision saver. */
+static u_int32_t
+user2credits(u_int32_t user)
+{
+	/* If multiplying would overflow... */
+	if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY))
+		/* Divide first. */
+		return (user / IP6T_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY;
+
+	return (user * HZ * CREDITS_PER_JIFFY) / IP6T_LIMIT_SCALE;
+}
+
+static int
+ip6t_limit_checkentry(const char *tablename,
+		     const struct ip6t_ip6 *ip,
+		     void *matchinfo,
+		     unsigned int matchsize,
+		     unsigned int hook_mask)
+{
+	struct ip6t_rateinfo *r = matchinfo;
+
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_rateinfo)))
+		return 0;
+
+	/* Check for overflow. */
+	if (r->burst == 0
+	    || user2credits(r->avg * r->burst) < user2credits(r->avg)) {
+		printk("Call rusty: overflow in ip6t_limit: %u/%u\n",
+		       r->avg, r->burst);
+		return 0;
+	}
+
+	/* User avg in seconds * IP6T_LIMIT_SCALE: convert to jiffies *
+	   128. */
+	r->prev = jiffies;
+	r->credit = user2credits(r->avg * r->burst);	 /* Credits full. */
+	r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */
+	r->cost = user2credits(r->avg);
+
+	/* For SMP, we only want to use one set of counters. */
+	r->master = r;
+
+	return 1;
+}
+
+static struct ip6t_match ip6t_limit_reg = {
+	.name		= "limit",
+	.match		= ip6t_limit_match,
+	.checkentry	= ip6t_limit_checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	if (ip6t_register_match(&ip6t_limit_reg))
+		return -EINVAL;
+	return 0;
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&ip6t_limit_reg);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_mac.c

@@ -0,0 +1,80 @@
+/* Kernel module to match MAC address parameters. */
+
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+
+#include <linux/netfilter_ipv6/ip6t_mac.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MAC address matching module for IPv6");
+MODULE_AUTHOR("Netfilter Core Teaam <coreteam@netfilter.org>");
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+    const struct ip6t_mac_info *info = matchinfo;
+
+    /* Is mac pointer valid? */
+    return (skb->mac.raw >= skb->head
+	    && (skb->mac.raw + ETH_HLEN) <= skb->data
+	    /* If so, compare... */
+	    && ((memcmp(eth_hdr(skb)->h_source, info->srcaddr, ETH_ALEN)
+		== 0) ^ info->invert));
+}
+
+static int
+ip6t_mac_checkentry(const char *tablename,
+		   const struct ip6t_ip6 *ip,
+		   void *matchinfo,
+		   unsigned int matchsize,
+		   unsigned int hook_mask)
+{
+	if (hook_mask
+	    & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN)
+		| (1 << NF_IP6_FORWARD))) {
+		printk("ip6t_mac: only valid for PRE_ROUTING, LOCAL_IN or"
+		       " FORWARD\n");
+		return 0;
+	}
+
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mac_info)))
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match mac_match = {
+	.name		= "mac",
+	.match		= &match,
+	.checkentry	= &ip6t_mac_checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&mac_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&mac_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_mark.c

@@ -0,0 +1,66 @@
+/* Kernel module to match NFMARK values. */
+
+/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter_ipv6/ip6t_mark.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables mark match");
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	const struct ip6t_mark_info *info = matchinfo;
+
+	return ((skb->nfmark & info->mask) == info->mark) ^ info->invert;
+}
+
+static int
+checkentry(const char *tablename,
+           const struct ip6t_ip6 *ip,
+           void *matchinfo,
+           unsigned int matchsize,
+           unsigned int hook_mask)
+{
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mark_info)))
+		return 0;
+
+	return 1;
+}
+
+static struct ip6t_match mark_match = {
+	.name		= "mark",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&mark_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&mark_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_multiport.c

@@ -0,0 +1,125 @@
+/* Kernel module to match one of a list of TCP/UDP ports: ports are in
+   the same place so we can treat them as equal. */
+
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/udp.h>
+#include <linux/skbuff.h>
+#include <linux/in.h>
+
+#include <linux/netfilter_ipv6/ip6t_multiport.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables match for multiple ports");
+
+#if 0
+#define duprintf(format, args...) printk(format , ## args)
+#else
+#define duprintf(format, args...)
+#endif
+
+/* Returns 1 if the port is matched by the test, 0 otherwise. */
+static inline int
+ports_match(const u_int16_t *portlist, enum ip6t_multiport_flags flags,
+	    u_int8_t count, u_int16_t src, u_int16_t dst)
+{
+	unsigned int i;
+	for (i=0; i<count; i++) {
+		if (flags != IP6T_MULTIPORT_DESTINATION
+		    && portlist[i] == src)
+			return 1;
+
+		if (flags != IP6T_MULTIPORT_SOURCE
+		    && portlist[i] == dst)
+			return 1;
+	}
+
+	return 0;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	u16 _ports[2], *pptr;
+	const struct ip6t_multiport *multiinfo = matchinfo;
+
+	/* Must not be a fragment. */
+	if (offset)
+		return 0;
+
+	/* Must be big enough to read ports (both UDP and TCP have
+	   them at the start). */
+	pptr = skb_header_pointer(skb, protoff, sizeof(_ports), &_ports[0]);
+	if (pptr == NULL) {
+		/* We've been asked to examine this packet, and we
+		 * can't.  Hence, no choice but to drop.
+		 */
+		duprintf("ip6t_multiport:"
+			 " Dropping evil offset=0 tinygram.\n");
+		*hotdrop = 1;
+		return 0;
+	}
+
+	return ports_match(multiinfo->ports,
+			   multiinfo->flags, multiinfo->count,
+			   ntohs(pptr[0]), ntohs(pptr[1]));
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+	   const struct ip6t_ip6 *ip,
+	   void *matchinfo,
+	   unsigned int matchsize,
+	   unsigned int hook_mask)
+{
+	const struct ip6t_multiport *multiinfo = matchinfo;
+
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_multiport)))
+		return 0;
+
+	/* Must specify proto == TCP/UDP, no unknown flags or bad count */
+	return (ip->proto == IPPROTO_TCP || ip->proto == IPPROTO_UDP)
+		&& !(ip->invflags & IP6T_INV_PROTO)
+		&& matchsize == IP6T_ALIGN(sizeof(struct ip6t_multiport))
+		&& (multiinfo->flags == IP6T_MULTIPORT_SOURCE
+		    || multiinfo->flags == IP6T_MULTIPORT_DESTINATION
+		    || multiinfo->flags == IP6T_MULTIPORT_EITHER)
+		&& multiinfo->count <= IP6T_MULTI_PORTS;
+}
+
+static struct ip6t_match multiport_match = {
+	.name		= "multiport",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&multiport_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&multiport_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_owner.c

@@ -0,0 +1,174 @@
+/* Kernel module to match various things tied to sockets associated with
+   locally generated outgoing packets. */
+
+/* (C) 2000-2001 Marc Boucher <marc@mbsi.ca>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <net/sock.h>
+
+#include <linux/netfilter_ipv6/ip6t_owner.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>");
+MODULE_DESCRIPTION("IP6 tables owner matching module");
+MODULE_LICENSE("GPL");
+
+static int
+match_pid(const struct sk_buff *skb, pid_t pid)
+{
+	struct task_struct *p;
+	struct files_struct *files;
+	int i;
+
+	read_lock(&tasklist_lock);
+	p = find_task_by_pid(pid);
+	if (!p)
+		goto out;
+	task_lock(p);
+	files = p->files;
+	if(files) {
+		spin_lock(&files->file_lock);
+		for (i=0; i < files->max_fds; i++) {
+			if (fcheck_files(files, i) == skb->sk->sk_socket->file) {
+				spin_unlock(&files->file_lock);
+				task_unlock(p);
+				read_unlock(&tasklist_lock);
+				return 1;
+			}
+		}
+		spin_unlock(&files->file_lock);
+	}
+	task_unlock(p);
+out:
+	read_unlock(&tasklist_lock);
+	return 0;
+}
+
+static int
+match_sid(const struct sk_buff *skb, pid_t sid)
+{
+	struct task_struct *g, *p;
+	struct file *file = skb->sk->sk_socket->file;
+	int i, found=0;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		struct files_struct *files;
+		if (p->signal->session != sid)
+			continue;
+
+		task_lock(p);
+		files = p->files;
+		if (files) {
+			spin_lock(&files->file_lock);
+			for (i=0; i < files->max_fds; i++) {
+				if (fcheck_files(files, i) == file) {
+					found = 1;
+					break;
+				}
+			}
+			spin_unlock(&files->file_lock);
+		}
+		task_unlock(p);
+		if (found)
+			goto out;
+	} while_each_thread(g, p);
+out:
+	read_unlock(&tasklist_lock);
+
+	return found;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	const struct ip6t_owner_info *info = matchinfo;
+
+	if (!skb->sk || !skb->sk->sk_socket || !skb->sk->sk_socket->file)
+		return 0;
+
+	if(info->match & IP6T_OWNER_UID) {
+		if((skb->sk->sk_socket->file->f_uid != info->uid) ^
+		    !!(info->invert & IP6T_OWNER_UID))
+			return 0;
+	}
+
+	if(info->match & IP6T_OWNER_GID) {
+		if((skb->sk->sk_socket->file->f_gid != info->gid) ^
+		    !!(info->invert & IP6T_OWNER_GID))
+			return 0;
+	}
+
+	if(info->match & IP6T_OWNER_PID) {
+		if (!match_pid(skb, info->pid) ^
+		    !!(info->invert & IP6T_OWNER_PID))
+			return 0;
+	}
+
+	if(info->match & IP6T_OWNER_SID) {
+		if (!match_sid(skb, info->sid) ^
+		    !!(info->invert & IP6T_OWNER_SID))
+			return 0;
+	}
+
+	return 1;
+}
+
+static int
+checkentry(const char *tablename,
+           const struct ip6t_ip6 *ip,
+           void *matchinfo,
+           unsigned int matchsize,
+           unsigned int hook_mask)
+{
+        if (hook_mask
+            & ~((1 << NF_IP6_LOCAL_OUT) | (1 << NF_IP6_POST_ROUTING))) {
+                printk("ip6t_owner: only valid for LOCAL_OUT or POST_ROUTING.\n");
+                return 0;
+        }
+
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_owner_info)))
+		return 0;
+#ifdef CONFIG_SMP
+	/* files->file_lock can not be used in a BH */
+	if (((struct ip6t_owner_info *)matchinfo)->match
+	    & (IP6T_OWNER_PID|IP6T_OWNER_SID)) {
+		printk("ip6t_owner: pid and sid matching is broken on SMP.\n");
+		return 0;
+	}
+#endif
+	return 1;
+}
+
+static struct ip6t_match owner_match = {
+	.name		= "owner",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&owner_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&owner_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_physdev.c

@@ -0,0 +1,135 @@
+/* Kernel module to match the bridge port in and
+ * out device for IP packets coming into contact with a bridge. */
+
+/* (C) 2001-2003 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 version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter_ipv6/ip6t_physdev.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_bridge.h>
+#define MATCH   1
+#define NOMATCH 0
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
+MODULE_DESCRIPTION("iptables bridge physical device match module");
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+	int i;
+	static const char nulldevname[IFNAMSIZ];
+	const struct ip6t_physdev_info *info = matchinfo;
+	unsigned int ret;
+	const char *indev, *outdev;
+	struct nf_bridge_info *nf_bridge;
+
+	/* Not a bridged IP packet or no info available yet:
+	 * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if
+	 * the destination device will be a bridge. */
+	if (!(nf_bridge = skb->nf_bridge)) {
+		/* Return MATCH if the invert flags of the used options are on */
+		if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) &&
+		    !(info->invert & IP6T_PHYSDEV_OP_BRIDGED))
+			return NOMATCH;
+		if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN) &&
+		    !(info->invert & IP6T_PHYSDEV_OP_ISIN))
+			return NOMATCH;
+		if ((info->bitmask & IP6T_PHYSDEV_OP_ISOUT) &&
+		    !(info->invert & IP6T_PHYSDEV_OP_ISOUT))
+			return NOMATCH;
+		if ((info->bitmask & IP6T_PHYSDEV_OP_IN) &&
+		    !(info->invert & IP6T_PHYSDEV_OP_IN))
+			return NOMATCH;
+		if ((info->bitmask & IP6T_PHYSDEV_OP_OUT) &&
+		    !(info->invert & IP6T_PHYSDEV_OP_OUT))
+			return NOMATCH;
+		return MATCH;
+	}
+
+	/* This only makes sense in the FORWARD and POSTROUTING chains */
+	if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) &&
+	    (!!(nf_bridge->mask & BRNF_BRIDGED) ^
+	    !(info->invert & IP6T_PHYSDEV_OP_BRIDGED)))
+		return NOMATCH;
+
+	if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN &&
+	    (!nf_bridge->physindev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISIN))) ||
+	    (info->bitmask & IP6T_PHYSDEV_OP_ISOUT &&
+	    (!nf_bridge->physoutdev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISOUT))))
+		return NOMATCH;
+
+	if (!(info->bitmask & IP6T_PHYSDEV_OP_IN))
+		goto match_outdev;
+	indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname;
+	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) {
+		ret |= (((const unsigned int *)indev)[i]
+			^ ((const unsigned int *)info->physindev)[i])
+			& ((const unsigned int *)info->in_mask)[i];
+	}
+
+	if ((ret == 0) ^ !(info->invert & IP6T_PHYSDEV_OP_IN))
+		return NOMATCH;
+
+match_outdev:
+	if (!(info->bitmask & IP6T_PHYSDEV_OP_OUT))
+		return MATCH;
+	outdev = nf_bridge->physoutdev ?
+		 nf_bridge->physoutdev->name : nulldevname;
+	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) {
+		ret |= (((const unsigned int *)outdev)[i]
+			^ ((const unsigned int *)info->physoutdev)[i])
+			& ((const unsigned int *)info->out_mask)[i];
+	}
+
+	return (ret != 0) ^ !(info->invert & IP6T_PHYSDEV_OP_OUT);
+}
+
+static int
+checkentry(const char *tablename,
+		       const struct ip6t_ip6 *ip,
+		       void *matchinfo,
+		       unsigned int matchsize,
+		       unsigned int hook_mask)
+{
+	const struct ip6t_physdev_info *info = matchinfo;
+
+	if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_physdev_info)))
+		return 0;
+	if (!(info->bitmask & IP6T_PHYSDEV_OP_MASK) ||
+	    info->bitmask & ~IP6T_PHYSDEV_OP_MASK)
+		return 0;
+	return 1;
+}
+
+static struct ip6t_match physdev_match = {
+	.name		= "physdev",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+	return ip6t_register_match(&physdev_match);
+}
+
+static void __exit fini(void)
+{
+	ip6t_unregister_match(&physdev_match);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6t_rt.c

@@ -0,0 +1,301 @@
+/* Kernel module to match ROUTING parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <asm/byteorder.h>
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_rt.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 RT match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+/* Returns 1 if the id is matched by the range, 0 otherwise */
+static inline int
+segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, int invert)
+{
+       int r=0;
+       DEBUGP("rt segsleft_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ',
+              min,id,max);
+       r=(id >= min && id <= max) ^ invert;
+       DEBUGP(" result %s\n",r? "PASS" : "FAILED");
+       return r;
+}
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      unsigned int protoff,
+      int *hotdrop)
+{
+       struct ipv6_rt_hdr _route, *rh = NULL;
+       const struct ip6t_rt *rtinfo = matchinfo;
+       unsigned int temp;
+       unsigned int len;
+       u8 nexthdr;
+       unsigned int ptr;
+       unsigned int hdrlen = 0;
+       unsigned int ret = 0;
+       struct in6_addr *ap, _addr;
+
+       /* type of the 1st exthdr */
+       nexthdr = skb->nh.ipv6h->nexthdr;
+       /* pointer to the 1st exthdr */
+       ptr = sizeof(struct ipv6hdr);
+       /* available length */
+       len = skb->len - ptr;
+       temp = 0;
+
+        while (ip6t_ext_hdr(nexthdr)) {
+               struct ipv6_opt_hdr _hdr, *hp;
+
+              DEBUGP("ipv6_rt header iteration \n");
+
+              /* Is there enough space for the next ext header? */
+                if (len < (int)sizeof(struct ipv6_opt_hdr))
+                        return 0;
+              /* No more exthdr -> evaluate */
+                if (nexthdr == NEXTHDR_NONE) {
+                     break;
+              }
+              /* ESP -> evaluate */
+                if (nexthdr == NEXTHDR_ESP) {
+                     break;
+              }
+
+	      hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+	      BUG_ON(hp == NULL);
+
+              /* Calculate the header length */
+                if (nexthdr == NEXTHDR_FRAGMENT) {
+                        hdrlen = 8;
+                } else if (nexthdr == NEXTHDR_AUTH)
+                        hdrlen = (hp->hdrlen+2)<<2;
+                else
+                        hdrlen = ipv6_optlen(hp);
+
+              /* ROUTING -> evaluate */
+                if (nexthdr == NEXTHDR_ROUTING) {
+                     temp |= MASK_ROUTING;
+                     break;
+              }
+
+
+              /* set the flag */
+              switch (nexthdr){
+                     case NEXTHDR_HOP:
+                     case NEXTHDR_ROUTING:
+                     case NEXTHDR_FRAGMENT:
+                     case NEXTHDR_AUTH:
+                     case NEXTHDR_DEST:
+                            break;
+                     default:
+                            DEBUGP("ipv6_rt match: unknown nextheader %u\n",nexthdr);
+                            return 0;
+                            break;
+              }
+
+                nexthdr = hp->nexthdr;
+                len -= hdrlen;
+                ptr += hdrlen;
+		if ( ptr > skb->len ) {
+			DEBUGP("ipv6_rt: new pointer is too large! \n");
+			break;
+		}
+        }
+
+       /* ROUTING header not found */
+       if ( temp != MASK_ROUTING ) return 0;
+
+       if (len < (int)sizeof(struct ipv6_rt_hdr)){
+	       *hotdrop = 1;
+       		return 0;
+       }
+
+       if (len < hdrlen){
+	       /* Pcket smaller than its length field */
+       		return 0;
+       }
+
+       rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route);
+       BUG_ON(rh == NULL);
+
+       DEBUGP("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen);
+       DEBUGP("TYPE %04X ", rh->type);
+       DEBUGP("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left);
+
+       DEBUGP("IPv6 RT segsleft %02X ",
+       		(segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
+                           rh->segments_left,
+                           !!(rtinfo->invflags & IP6T_RT_INV_SGS))));
+       DEBUGP("type %02X %02X %02X ",
+       		rtinfo->rt_type, rh->type, 
+       		(!(rtinfo->flags & IP6T_RT_TYP) ||
+                           ((rtinfo->rt_type == rh->type) ^
+                           !!(rtinfo->invflags & IP6T_RT_INV_TYP))));
+       DEBUGP("len %02X %04X %02X ",
+       		rtinfo->hdrlen, hdrlen,
+       		(!(rtinfo->flags & IP6T_RT_LEN) ||
+                           ((rtinfo->hdrlen == hdrlen) ^
+                           !!(rtinfo->invflags & IP6T_RT_INV_LEN))));
+       DEBUGP("res %02X %02X %02X ", 
+       		(rtinfo->flags & IP6T_RT_RES), ((struct rt0_hdr *)rh)->bitmap,
+       		!((rtinfo->flags & IP6T_RT_RES) && (((struct rt0_hdr *)rh)->bitmap)));
+
+       ret = (rh != NULL)
+       		&&
+       		(segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
+                           rh->segments_left,
+                           !!(rtinfo->invflags & IP6T_RT_INV_SGS)))
+		&&
+	      	(!(rtinfo->flags & IP6T_RT_LEN) ||
+                           ((rtinfo->hdrlen == hdrlen) ^
+                           !!(rtinfo->invflags & IP6T_RT_INV_LEN)))
+		&&
+       		(!(rtinfo->flags & IP6T_RT_TYP) ||
+                           ((rtinfo->rt_type == rh->type) ^
+                           !!(rtinfo->invflags & IP6T_RT_INV_TYP)));
+
+	if (ret && (rtinfo->flags & IP6T_RT_RES)) {
+		u_int32_t *bp, _bitmap;
+		bp = skb_header_pointer(skb,
+					ptr + offsetof(struct rt0_hdr, bitmap),
+					sizeof(_bitmap), &_bitmap);
+
+		ret = (*bp == 0);
+	}
+
+	DEBUGP("#%d ",rtinfo->addrnr);
+       if ( !(rtinfo->flags & IP6T_RT_FST) ){
+	       return ret;
+	} else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) {
+		DEBUGP("Not strict ");
+		if ( rtinfo->addrnr > (unsigned int)((hdrlen-8)/16) ){
+			DEBUGP("There isn't enough space\n");
+			return 0;
+		} else {
+			unsigned int i = 0;
+
+			DEBUGP("#%d ",rtinfo->addrnr);
+			for(temp=0; temp<(unsigned int)((hdrlen-8)/16); temp++){
+				ap = skb_header_pointer(skb,
+							ptr
+							+ sizeof(struct rt0_hdr)
+							+ temp * sizeof(_addr),
+							sizeof(_addr),
+							&_addr);
+
+				BUG_ON(ap == NULL);
+
+				if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) {
+					DEBUGP("i=%d temp=%d;\n",i,temp);
+					i++;
+				}
+				if (i==rtinfo->addrnr) break;
+			}
+			DEBUGP("i=%d #%d\n", i, rtinfo->addrnr);
+			if (i == rtinfo->addrnr)
+				return ret;
+			else return 0;
+		}
+	} else {
+		DEBUGP("Strict ");
+		if ( rtinfo->addrnr > (unsigned int)((hdrlen-8)/16) ){
+			DEBUGP("There isn't enough space\n");
+			return 0;
+		} else {
+			DEBUGP("#%d ",rtinfo->addrnr);
+			for(temp=0; temp<rtinfo->addrnr; temp++){
+				ap = skb_header_pointer(skb,
+							ptr
+							+ sizeof(struct rt0_hdr)
+							+ temp * sizeof(_addr),
+							sizeof(_addr),
+							&_addr);
+				BUG_ON(ap == NULL);
+
+				if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp]))
+					break;
+			}
+			DEBUGP("temp=%d #%d\n", temp, rtinfo->addrnr);
+			if ((temp == rtinfo->addrnr) && (temp == (unsigned int)((hdrlen-8)/16)))
+				return ret;
+			else return 0;
+		}
+	}
+
+	return 0;
+}
+
+/* Called when user tries to insert an entry of this type. */
+static int
+checkentry(const char *tablename,
+          const struct ip6t_ip6 *ip,
+          void *matchinfo,
+          unsigned int matchinfosize,
+          unsigned int hook_mask)
+{
+       const struct ip6t_rt *rtinfo = matchinfo;
+
+       if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_rt))) {
+              DEBUGP("ip6t_rt: matchsize %u != %u\n",
+                      matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_rt)));
+              return 0;
+       }
+       if (rtinfo->invflags & ~IP6T_RT_INV_MASK) {
+              DEBUGP("ip6t_rt: unknown flags %X\n",
+                      rtinfo->invflags);
+              return 0;
+       }
+       if ( (rtinfo->flags & (IP6T_RT_RES|IP6T_RT_FST_MASK)) && 
+		       (!(rtinfo->flags & IP6T_RT_TYP) || 
+		       (rtinfo->rt_type != 0) || 
+		       (rtinfo->invflags & IP6T_RT_INV_TYP)) ) {
+	      DEBUGP("`--rt-type 0' required before `--rt-0-*'");
+              return 0;
+       }
+
+       return 1;
+}
+
+static struct ip6t_match rt_match = {
+	.name		= "rt",
+	.match		= &match,
+	.checkentry	= &checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init init(void)
+{
+       return ip6t_register_match(&rt_match);
+}
+
+static void __exit cleanup(void)
+{
+       ip6t_unregister_match(&rt_match);
+}
+
+module_init(init);
+module_exit(cleanup);

net/ipv6/netfilter/ip6table_filter.c

@@ -0,0 +1,214 @@
+/*
+ * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x.
+ *
+ * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables filter table");
+
+#define FILTER_VALID_HOOKS ((1 << NF_IP6_LOCAL_IN) | (1 << NF_IP6_FORWARD) | (1 << NF_IP6_LOCAL_OUT))
+
+/* Standard entry. */
+struct ip6t_standard
+{
+	struct ip6t_entry entry;
+	struct ip6t_standard_target target;
+};
+
+struct ip6t_error_target
+{
+	struct ip6t_entry_target target;
+	char errorname[IP6T_FUNCTION_MAXNAMELEN];
+};
+
+struct ip6t_error
+{
+	struct ip6t_entry entry;
+	struct ip6t_error_target target;
+};
+
+static struct
+{
+	struct ip6t_replace repl;
+	struct ip6t_standard entries[3];
+	struct ip6t_error term;
+} initial_table __initdata
+= { { "filter", FILTER_VALID_HOOKS, 4,
+      sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error),
+      { [NF_IP6_LOCAL_IN] = 0,
+	[NF_IP6_FORWARD] = sizeof(struct ip6t_standard),
+	[NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 },
+      { [NF_IP6_LOCAL_IN] = 0,
+	[NF_IP6_FORWARD] = sizeof(struct ip6t_standard),
+	[NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 },
+      0, NULL, { } },
+    {
+	    /* LOCAL_IN */
+	    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* FORWARD */
+	    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* LOCAL_OUT */
+	    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } }
+    },
+    /* ERROR */
+    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+	0,
+	sizeof(struct ip6t_entry),
+	sizeof(struct ip6t_error),
+	0, { 0, 0 }, { } },
+      { { { { IP6T_ALIGN(sizeof(struct ip6t_error_target)), IP6T_ERROR_TARGET } },
+	  { } },
+	"ERROR"
+      }
+    }
+};
+
+static struct ip6t_table packet_filter = {
+	.name		= "filter",
+	.valid_hooks	= FILTER_VALID_HOOKS,
+	.lock		= RW_LOCK_UNLOCKED,
+	.me		= THIS_MODULE,
+};
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6t_hook(unsigned int hook,
+	 struct sk_buff **pskb,
+	 const struct net_device *in,
+	 const struct net_device *out,
+	 int (*okfn)(struct sk_buff *))
+{
+	return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL);
+}
+
+static unsigned int
+ip6t_local_out_hook(unsigned int hook,
+		   struct sk_buff **pskb,
+		   const struct net_device *in,
+		   const struct net_device *out,
+		   int (*okfn)(struct sk_buff *))
+{
+#if 0
+	/* root is playing with raw sockets. */
+	if ((*pskb)->len < sizeof(struct iphdr)
+	    || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) {
+		if (net_ratelimit())
+			printk("ip6t_hook: happy cracking.\n");
+		return NF_ACCEPT;
+	}
+#endif
+
+	return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL);
+}
+
+static struct nf_hook_ops ip6t_ops[] = {
+	{
+		.hook		= ip6t_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_LOCAL_IN,
+		.priority	= NF_IP6_PRI_FILTER,
+	},
+	{
+		.hook		= ip6t_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_FORWARD,
+		.priority	= NF_IP6_PRI_FILTER,
+	},
+	{
+		.hook		= ip6t_local_out_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_FILTER,
+	},
+};
+
+/* Default to forward because I got too much mail already. */
+static int forward = NF_ACCEPT;
+module_param(forward, bool, 0000);
+
+static int __init init(void)
+{
+	int ret;
+
+	if (forward < 0 || forward > NF_MAX_VERDICT) {
+		printk("iptables forward must be 0 or 1\n");
+		return -EINVAL;
+	}
+
+	/* Entry 1 is the FORWARD hook */
+	initial_table.entries[1].target.verdict = -forward - 1;
+
+	/* Register table */
+	ret = ip6t_register_table(&packet_filter, &initial_table.repl);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	ret = nf_register_hook(&ip6t_ops[0]);
+	if (ret < 0)
+		goto cleanup_table;
+
+	ret = nf_register_hook(&ip6t_ops[1]);
+	if (ret < 0)
+		goto cleanup_hook0;
+
+	ret = nf_register_hook(&ip6t_ops[2]);
+	if (ret < 0)
+		goto cleanup_hook1;
+
+	return ret;
+
+ cleanup_hook1:
+	nf_unregister_hook(&ip6t_ops[1]);
+ cleanup_hook0:
+	nf_unregister_hook(&ip6t_ops[0]);
+ cleanup_table:
+	ip6t_unregister_table(&packet_filter);
+
+	return ret;
+}
+
+static void __exit fini(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++)
+		nf_unregister_hook(&ip6t_ops[i]);
+
+	ip6t_unregister_table(&packet_filter);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6table_mangle.c

@@ -0,0 +1,287 @@
+/*
+ * IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6
+ *
+ * Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org>
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Extended to all five netfilter hooks by Brad Chapman & Harald Welte
+ */
+#include <linux/module.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables mangle table");
+
+#define MANGLE_VALID_HOOKS ((1 << NF_IP6_PRE_ROUTING) | \
+			    (1 << NF_IP6_LOCAL_IN) | \
+			    (1 << NF_IP6_FORWARD) | \
+			    (1 << NF_IP6_LOCAL_OUT) | \
+			    (1 << NF_IP6_POST_ROUTING))
+
+#if 0
+#define DEBUGP(x, args...)	printk(KERN_DEBUG x, ## args)
+#else
+#define DEBUGP(x, args...)
+#endif
+
+/* Standard entry. */
+struct ip6t_standard
+{
+	struct ip6t_entry entry;
+	struct ip6t_standard_target target;
+};
+
+struct ip6t_error_target
+{
+	struct ip6t_entry_target target;
+	char errorname[IP6T_FUNCTION_MAXNAMELEN];
+};
+
+struct ip6t_error
+{
+	struct ip6t_entry entry;
+	struct ip6t_error_target target;
+};
+
+static struct
+{
+	struct ip6t_replace repl;
+	struct ip6t_standard entries[5];
+	struct ip6t_error term;
+} initial_table __initdata
+= { { "mangle", MANGLE_VALID_HOOKS, 6,
+      sizeof(struct ip6t_standard) * 5 + sizeof(struct ip6t_error),
+      { [NF_IP6_PRE_ROUTING] 	= 0,
+	[NF_IP6_LOCAL_IN]	= sizeof(struct ip6t_standard),
+	[NF_IP6_FORWARD]	= sizeof(struct ip6t_standard) * 2,
+	[NF_IP6_LOCAL_OUT] 	= sizeof(struct ip6t_standard) * 3,
+	[NF_IP6_POST_ROUTING]	= sizeof(struct ip6t_standard) * 4},
+      { [NF_IP6_PRE_ROUTING] 	= 0,
+	[NF_IP6_LOCAL_IN]	= sizeof(struct ip6t_standard),
+	[NF_IP6_FORWARD]	= sizeof(struct ip6t_standard) * 2,
+	[NF_IP6_LOCAL_OUT] 	= sizeof(struct ip6t_standard) * 3,
+	[NF_IP6_POST_ROUTING]	= sizeof(struct ip6t_standard) * 4},
+      0, NULL, { } },
+    {
+	    /* PRE_ROUTING */
+            { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* LOCAL_IN */
+            { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* FORWARD */
+            { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* LOCAL_OUT */
+            { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } },
+	    /* POST_ROUTING */
+	    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+		0,
+		sizeof(struct ip6t_entry),
+		sizeof(struct ip6t_standard),
+		0, { 0, 0 }, { } },
+	      { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } },
+		-NF_ACCEPT - 1 } }
+    },
+    /* ERROR */
+    { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 },
+	0,
+	sizeof(struct ip6t_entry),
+	sizeof(struct ip6t_error),
+	0, { 0, 0 }, { } },
+      { { { { IP6T_ALIGN(sizeof(struct ip6t_error_target)), IP6T_ERROR_TARGET } },
+	  { } },
+	"ERROR"
+      }
+    }
+};
+
+static struct ip6t_table packet_mangler = {
+	.name		= "mangle",
+	.valid_hooks	= MANGLE_VALID_HOOKS,
+	.lock		= RW_LOCK_UNLOCKED,
+	.me		= THIS_MODULE,
+};
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6t_route_hook(unsigned int hook,
+	 struct sk_buff **pskb,
+	 const struct net_device *in,
+	 const struct net_device *out,
+	 int (*okfn)(struct sk_buff *))
+{
+	return ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+}
+
+static unsigned int
+ip6t_local_hook(unsigned int hook,
+		   struct sk_buff **pskb,
+		   const struct net_device *in,
+		   const struct net_device *out,
+		   int (*okfn)(struct sk_buff *))
+{
+
+	unsigned long nfmark;
+	unsigned int ret;
+	struct in6_addr saddr, daddr;
+	u_int8_t hop_limit;
+	u_int32_t flowlabel;
+
+#if 0
+	/* root is playing with raw sockets. */
+	if ((*pskb)->len < sizeof(struct iphdr)
+	    || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) {
+		if (net_ratelimit())
+			printk("ip6t_hook: happy cracking.\n");
+		return NF_ACCEPT;
+	}
+#endif
+
+	/* save source/dest address, nfmark, hoplimit, flowlabel, priority,  */
+	memcpy(&saddr, &(*pskb)->nh.ipv6h->saddr, sizeof(saddr));
+	memcpy(&daddr, &(*pskb)->nh.ipv6h->daddr, sizeof(daddr));
+	nfmark = (*pskb)->nfmark;
+	hop_limit = (*pskb)->nh.ipv6h->hop_limit;
+
+	/* flowlabel and prio (includes version, which shouldn't change either */
+	flowlabel = *((u_int32_t *) (*pskb)->nh.ipv6h);
+
+	ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+
+	if (ret != NF_DROP && ret != NF_STOLEN 
+		&& (memcmp(&(*pskb)->nh.ipv6h->saddr, &saddr, sizeof(saddr))
+		    || memcmp(&(*pskb)->nh.ipv6h->daddr, &daddr, sizeof(daddr))
+		    || (*pskb)->nfmark != nfmark
+		    || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) {
+
+		/* something which could affect routing has changed */
+
+		DEBUGP("ip6table_mangle: we'd need to re-route a packet\n");
+	}
+
+	return ret;
+}
+
+static struct nf_hook_ops ip6t_ops[] = {
+	{
+		.hook		= ip6t_route_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_MANGLE,
+	},
+	{
+		.hook		= ip6t_local_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_LOCAL_IN,
+		.priority	= NF_IP6_PRI_MANGLE,
+	},
+	{
+		.hook		= ip6t_route_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_FORWARD,
+		.priority	= NF_IP6_PRI_MANGLE,
+	},
+	{
+		.hook		= ip6t_local_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_MANGLE,
+	},
+	{
+		.hook		= ip6t_route_hook,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET6,
+		.hooknum	= NF_IP6_POST_ROUTING,
+		.priority	= NF_IP6_PRI_MANGLE,
+	},
+};
+
+static int __init init(void)
+{
+	int ret;
+
+	/* Register table */
+	ret = ip6t_register_table(&packet_mangler, &initial_table.repl);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	ret = nf_register_hook(&ip6t_ops[0]);
+	if (ret < 0)
+		goto cleanup_table;
+
+	ret = nf_register_hook(&ip6t_ops[1]);
+	if (ret < 0)
+		goto cleanup_hook0;
+
+	ret = nf_register_hook(&ip6t_ops[2]);
+	if (ret < 0)
+		goto cleanup_hook1;
+
+	ret = nf_register_hook(&ip6t_ops[3]);
+	if (ret < 0)
+		goto cleanup_hook2;
+
+	ret = nf_register_hook(&ip6t_ops[4]);
+	if (ret < 0)
+		goto cleanup_hook3;
+
+	return ret;
+
+ cleanup_hook3:
+        nf_unregister_hook(&ip6t_ops[3]);
+ cleanup_hook2:
+	nf_unregister_hook(&ip6t_ops[2]);
+ cleanup_hook1:
+	nf_unregister_hook(&ip6t_ops[1]);
+ cleanup_hook0:
+	nf_unregister_hook(&ip6t_ops[0]);
+ cleanup_table:
+	ip6t_unregister_table(&packet_mangler);
+
+	return ret;
+}
+
+static void __exit fini(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++)
+		nf_unregister_hook(&ip6t_ops[i]);
+
+	ip6t_unregister_table(&packet_mangler);
+}
+
+module_init(init);
+module_exit(fini);

net/ipv6/netfilter/ip6table_raw.c

@@ -0,0 +1,182 @@
+/*
+ * IPv6 raw table, a port of the IPv4 raw table to IPv6
+ *
+ * Copyright (C) 2003 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ */
+#include <linux/module.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+#define RAW_VALID_HOOKS ((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_OUT))
+
+#if 0
+#define DEBUGP(x, args...)	printk(KERN_DEBUG x, ## args)
+#else
+#define DEBUGP(x, args...)
+#endif
+
+/* Standard entry. */
+struct ip6t_standard
+{
+	struct ip6t_entry entry;
+	struct ip6t_standard_target target;
+};
+
+struct ip6t_error_target
+{
+	struct ip6t_entry_target target;
+	char errorname[IP6T_FUNCTION_MAXNAMELEN];
+};
+
+struct ip6t_error
+{
+	struct ip6t_entry entry;
+	struct ip6t_error_target target;
+};
+
+static struct
+{
+	struct ip6t_replace repl;
+	struct ip6t_standard entries[2];
+	struct ip6t_error term;
+} initial_table __initdata = {
+	.repl = {
+		.name = "raw",
+		.valid_hooks = RAW_VALID_HOOKS,
+		.num_entries = 3,
+		.size = sizeof(struct ip6t_standard) * 2 + sizeof(struct ip6t_error),
+		.hook_entry = {
+			[NF_IP6_PRE_ROUTING] = 0,
+			[NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard)
+		},
+		.underflow = {
+			[NF_IP6_PRE_ROUTING] = 0,
+			[NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard)
+		},
+	},
+	.entries = {
+		/* PRE_ROUTING */
+		{
+			.entry = {
+				.target_offset = sizeof(struct ip6t_entry),
+				.next_offset = sizeof(struct ip6t_standard),
+			},
+			.target = {
+				.target = {
+					.u = {
+						.target_size = IP6T_ALIGN(sizeof(struct ip6t_standard_target)),
+					},
+				},
+				.verdict = -NF_ACCEPT - 1,
+			},
+		},
+
+		/* LOCAL_OUT */
+		{
+			.entry = {
+				.target_offset = sizeof(struct ip6t_entry),
+				.next_offset = sizeof(struct ip6t_standard),
+			},
+			.target = {
+				.target = {
+					.u = {
+						.target_size = IP6T_ALIGN(sizeof(struct ip6t_standard_target)),
+					},
+				},
+				.verdict = -NF_ACCEPT - 1,
+			},
+		},
+	},
+	/* ERROR */
+	.term = {
+		.entry = {
+			.target_offset = sizeof(struct ip6t_entry),
+			.next_offset = sizeof(struct ip6t_error),
+		},
+		.target = {
+			.target = {
+				.u = {
+					.user = {
+						.target_size = IP6T_ALIGN(sizeof(struct ip6t_error_target)),
+						.name = IP6T_ERROR_TARGET,
+					},
+				},
+			},
+			.errorname = "ERROR",
+		},
+	}
+};
+
+static struct ip6t_table packet_raw = { 
+	.name = "raw", 
+	.valid_hooks = RAW_VALID_HOOKS, 
+	.lock = RW_LOCK_UNLOCKED, 
+	.me = THIS_MODULE
+};
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6t_hook(unsigned int hook,
+	 struct sk_buff **pskb,
+	 const struct net_device *in,
+	 const struct net_device *out,
+	 int (*okfn)(struct sk_buff *))
+{
+	return ip6t_do_table(pskb, hook, in, out, &packet_raw, NULL);
+}
+
+static struct nf_hook_ops ip6t_ops[] = { 
+	{
+	  .hook = ip6t_hook, 
+	  .pf = PF_INET6,
+	  .hooknum = NF_IP6_PRE_ROUTING,
+	  .priority = NF_IP6_PRI_FIRST
+	},
+	{
+	  .hook = ip6t_hook, 
+	  .pf = PF_INET6, 
+	  .hooknum = NF_IP6_LOCAL_OUT,
+	  .priority = NF_IP6_PRI_FIRST
+	},
+};
+
+static int __init init(void)
+{
+	int ret;
+
+	/* Register table */
+	ret = ip6t_register_table(&packet_raw, &initial_table.repl);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	ret = nf_register_hook(&ip6t_ops[0]);
+	if (ret < 0)
+		goto cleanup_table;
+
+	ret = nf_register_hook(&ip6t_ops[1]);
+	if (ret < 0)
+		goto cleanup_hook0;
+
+	return ret;
+
+ cleanup_hook0:
+	nf_unregister_hook(&ip6t_ops[0]);
+ cleanup_table:
+	ip6t_unregister_table(&packet_raw);
+
+	return ret;
+}
+
+static void __exit fini(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++)
+		nf_unregister_hook(&ip6t_ops[i]);
+
+	ip6t_unregister_table(&packet_raw);
+}
+
+module_init(init);
+module_exit(fini);
+MODULE_LICENSE("GPL");

net/ipv6/proc.c

@@ -0,0 +1,303 @@
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		This file implements the various access functions for the
+ *		PROC file system.  This is very similar to the IPv4 version,
+ *		except it reports the sockets in the INET6 address family.
+ *
+ * Version:	$Id: proc.c,v 1.17 2002/02/01 22:01:04 davem Exp $
+ *
+ * Authors:	David S. Miller (davem@caip.rutgers.edu)
+ * 		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *
+ *		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.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/stddef.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/transp_v6.h>
+#include <net/ipv6.h>
+
+#ifdef CONFIG_PROC_FS
+static struct proc_dir_entry *proc_net_devsnmp6;
+
+static int fold_prot_inuse(struct proto *proto)
+{
+	int res = 0;
+	int cpu;
+
+	for (cpu=0; cpu<NR_CPUS; cpu++)
+		res += proto->stats[cpu].inuse;
+
+	return res;
+}
+
+static int sockstat6_seq_show(struct seq_file *seq, void *v)
+{
+	seq_printf(seq, "TCP6: inuse %d\n",
+		       fold_prot_inuse(&tcpv6_prot));
+	seq_printf(seq, "UDP6: inuse %d\n",
+		       fold_prot_inuse(&udpv6_prot));
+	seq_printf(seq, "RAW6: inuse %d\n",
+		       fold_prot_inuse(&rawv6_prot));
+	seq_printf(seq, "FRAG6: inuse %d memory %d\n",
+		       ip6_frag_nqueues, atomic_read(&ip6_frag_mem));
+	return 0;
+}
+
+static struct snmp_mib snmp6_ipstats_list[] = {
+/* ipv6 mib according to RFC 2465 */
+	SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INRECEIVES),
+	SNMP_MIB_ITEM("Ip6InHdrErrors", IPSTATS_MIB_INHDRERRORS),
+	SNMP_MIB_ITEM("Ip6InTooBigErrors", IPSTATS_MIB_INTOOBIGERRORS),
+	SNMP_MIB_ITEM("Ip6InNoRoutes", IPSTATS_MIB_INNOROUTES),
+	SNMP_MIB_ITEM("Ip6InAddrErrors", IPSTATS_MIB_INADDRERRORS),
+	SNMP_MIB_ITEM("Ip6InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS),
+	SNMP_MIB_ITEM("Ip6InTruncatedPkts", IPSTATS_MIB_INTRUNCATEDPKTS),
+	SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS),
+	SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS),
+	SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS),
+	SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS),
+	SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS),
+	SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES),
+	SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT),
+	SNMP_MIB_ITEM("Ip6ReasmReqds", IPSTATS_MIB_REASMREQDS),
+	SNMP_MIB_ITEM("Ip6ReasmOKs", IPSTATS_MIB_REASMOKS),
+	SNMP_MIB_ITEM("Ip6ReasmFails", IPSTATS_MIB_REASMFAILS),
+	SNMP_MIB_ITEM("Ip6FragOKs", IPSTATS_MIB_FRAGOKS),
+	SNMP_MIB_ITEM("Ip6FragFails", IPSTATS_MIB_FRAGFAILS),
+	SNMP_MIB_ITEM("Ip6FragCreates", IPSTATS_MIB_FRAGCREATES),
+	SNMP_MIB_ITEM("Ip6InMcastPkts", IPSTATS_MIB_INMCASTPKTS),
+	SNMP_MIB_ITEM("Ip6OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS),
+	SNMP_MIB_SENTINEL
+};
+
+static struct snmp_mib snmp6_icmp6_list[] = {
+/* icmpv6 mib according to RFC 2466
+
+   Exceptions:  {In|Out}AdminProhibs are removed, because I see
+                no good reasons to account them separately
+		of another dest.unreachs.
+		OutErrs is zero identically.
+		OutEchos too.
+		OutRouterAdvertisements too.
+		OutGroupMembQueries too.
+ */
+	SNMP_MIB_ITEM("Icmp6InMsgs", ICMP6_MIB_INMSGS),
+	SNMP_MIB_ITEM("Icmp6InErrors", ICMP6_MIB_INERRORS),
+	SNMP_MIB_ITEM("Icmp6InDestUnreachs", ICMP6_MIB_INDESTUNREACHS),
+	SNMP_MIB_ITEM("Icmp6InPktTooBigs", ICMP6_MIB_INPKTTOOBIGS),
+	SNMP_MIB_ITEM("Icmp6InTimeExcds", ICMP6_MIB_INTIMEEXCDS),
+	SNMP_MIB_ITEM("Icmp6InParmProblems", ICMP6_MIB_INPARMPROBLEMS),
+	SNMP_MIB_ITEM("Icmp6InEchos", ICMP6_MIB_INECHOS),
+	SNMP_MIB_ITEM("Icmp6InEchoReplies", ICMP6_MIB_INECHOREPLIES),
+	SNMP_MIB_ITEM("Icmp6InGroupMembQueries", ICMP6_MIB_INGROUPMEMBQUERIES),
+	SNMP_MIB_ITEM("Icmp6InGroupMembResponses", ICMP6_MIB_INGROUPMEMBRESPONSES),
+	SNMP_MIB_ITEM("Icmp6InGroupMembReductions", ICMP6_MIB_INGROUPMEMBREDUCTIONS),
+	SNMP_MIB_ITEM("Icmp6InRouterSolicits", ICMP6_MIB_INROUTERSOLICITS),
+	SNMP_MIB_ITEM("Icmp6InRouterAdvertisements", ICMP6_MIB_INROUTERADVERTISEMENTS),
+	SNMP_MIB_ITEM("Icmp6InNeighborSolicits", ICMP6_MIB_INNEIGHBORSOLICITS),
+	SNMP_MIB_ITEM("Icmp6InNeighborAdvertisements", ICMP6_MIB_INNEIGHBORADVERTISEMENTS),
+	SNMP_MIB_ITEM("Icmp6InRedirects", ICMP6_MIB_INREDIRECTS),
+	SNMP_MIB_ITEM("Icmp6OutMsgs", ICMP6_MIB_OUTMSGS),
+	SNMP_MIB_ITEM("Icmp6OutDestUnreachs", ICMP6_MIB_OUTDESTUNREACHS),
+	SNMP_MIB_ITEM("Icmp6OutPktTooBigs", ICMP6_MIB_OUTPKTTOOBIGS),
+	SNMP_MIB_ITEM("Icmp6OutTimeExcds", ICMP6_MIB_OUTTIMEEXCDS),
+	SNMP_MIB_ITEM("Icmp6OutParmProblems", ICMP6_MIB_OUTPARMPROBLEMS),
+	SNMP_MIB_ITEM("Icmp6OutEchoReplies", ICMP6_MIB_OUTECHOREPLIES),
+	SNMP_MIB_ITEM("Icmp6OutRouterSolicits", ICMP6_MIB_OUTROUTERSOLICITS),
+	SNMP_MIB_ITEM("Icmp6OutNeighborSolicits", ICMP6_MIB_OUTNEIGHBORSOLICITS),
+	SNMP_MIB_ITEM("Icmp6OutNeighborAdvertisements", ICMP6_MIB_OUTNEIGHBORADVERTISEMENTS),
+	SNMP_MIB_ITEM("Icmp6OutRedirects", ICMP6_MIB_OUTREDIRECTS),
+	SNMP_MIB_ITEM("Icmp6OutGroupMembResponses", ICMP6_MIB_OUTGROUPMEMBRESPONSES),
+	SNMP_MIB_ITEM("Icmp6OutGroupMembReductions", ICMP6_MIB_OUTGROUPMEMBREDUCTIONS),
+	SNMP_MIB_SENTINEL
+};
+
+static struct snmp_mib snmp6_udp6_list[] = {
+	SNMP_MIB_ITEM("Udp6InDatagrams", UDP_MIB_INDATAGRAMS),
+	SNMP_MIB_ITEM("Udp6NoPorts", UDP_MIB_NOPORTS),
+	SNMP_MIB_ITEM("Udp6InErrors", UDP_MIB_INERRORS),
+	SNMP_MIB_ITEM("Udp6OutDatagrams", UDP_MIB_OUTDATAGRAMS),
+	SNMP_MIB_SENTINEL
+};
+
+static unsigned long
+fold_field(void *mib[], int offt)
+{
+        unsigned long res = 0;
+        int i;
+ 
+        for (i = 0; i < NR_CPUS; i++) {
+                if (!cpu_possible(i))
+                        continue;
+                res += *(((unsigned long *)per_cpu_ptr(mib[0], i)) + offt);
+                res += *(((unsigned long *)per_cpu_ptr(mib[1], i)) + offt);
+        }
+        return res;
+}
+
+static inline void
+snmp6_seq_show_item(struct seq_file *seq, void **mib, struct snmp_mib *itemlist)
+{
+	int i;
+	for (i=0; itemlist[i].name; i++)
+		seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, 
+				fold_field(mib, itemlist[i].entry));
+}
+
+static int snmp6_seq_show(struct seq_file *seq, void *v)
+{
+	struct inet6_dev *idev = (struct inet6_dev *)seq->private;
+
+	if (idev) {
+		seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
+		snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list);
+	} else {
+		snmp6_seq_show_item(seq, (void **)ipv6_statistics, snmp6_ipstats_list);
+		snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list);
+		snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list);
+	}
+	return 0;
+}
+
+static int sockstat6_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sockstat6_seq_show, NULL);
+}
+
+static struct file_operations sockstat6_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = sockstat6_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+static int snmp6_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, snmp6_seq_show, PDE(inode)->data);
+}
+
+static struct file_operations snmp6_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = snmp6_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+int snmp6_register_dev(struct inet6_dev *idev)
+{
+	struct proc_dir_entry *p;
+
+	if (!idev || !idev->dev)
+		return -EINVAL;
+
+	if (!proc_net_devsnmp6)
+		return -ENOENT;
+
+	p = create_proc_entry(idev->dev->name, S_IRUGO, proc_net_devsnmp6);
+	if (!p)
+		return -ENOMEM;
+
+	p->data = idev;
+	p->proc_fops = &snmp6_seq_fops;
+
+	idev->stats.proc_dir_entry = p;
+	return 0;
+}
+
+int snmp6_unregister_dev(struct inet6_dev *idev)
+{
+	if (!proc_net_devsnmp6)
+		return -ENOENT;
+	if (!idev || !idev->stats.proc_dir_entry)
+		return -EINVAL;
+	remove_proc_entry(idev->stats.proc_dir_entry->name,
+			  proc_net_devsnmp6);
+	return 0;
+}
+
+int __init ipv6_misc_proc_init(void)
+{
+	int rc = 0;
+
+	if (!proc_net_fops_create("snmp6", S_IRUGO, &snmp6_seq_fops))
+		goto proc_snmp6_fail;
+
+	proc_net_devsnmp6 = proc_mkdir("dev_snmp6", proc_net);
+	if (!proc_net_devsnmp6)
+		goto proc_dev_snmp6_fail;
+
+	if (!proc_net_fops_create("sockstat6", S_IRUGO, &sockstat6_seq_fops))
+		goto proc_sockstat6_fail;
+out:
+	return rc;
+
+proc_sockstat6_fail:
+	proc_net_remove("dev_snmp6");
+proc_dev_snmp6_fail:
+	proc_net_remove("snmp6");
+proc_snmp6_fail:
+	rc = -ENOMEM;
+	goto out;
+}
+
+void ipv6_misc_proc_exit(void)
+{
+	proc_net_remove("sockstat6");
+	proc_net_remove("dev_snmp6");
+	proc_net_remove("snmp6");
+}
+
+#else	/* CONFIG_PROC_FS */
+
+
+int snmp6_register_dev(struct inet6_dev *idev)
+{
+	return 0;
+}
+
+int snmp6_unregister_dev(struct inet6_dev *idev)
+{
+	return 0;
+}
+#endif	/* CONFIG_PROC_FS */
+
+int snmp6_alloc_dev(struct inet6_dev *idev)
+{
+	int err = -ENOMEM;
+
+	if (!idev || !idev->dev)
+		return -EINVAL;
+
+	if (snmp6_mib_init((void **)idev->stats.icmpv6, sizeof(struct icmpv6_mib),
+			   __alignof__(struct icmpv6_mib)) < 0)
+		goto err_icmp;
+
+	return 0;
+
+err_icmp:
+	return err;
+}
+
+int snmp6_free_dev(struct inet6_dev *idev)
+{
+	snmp6_mib_free((void **)idev->stats.icmpv6);
+	return 0;
+}
+
+

net/ipv6/protocol.c

@@ -0,0 +1,86 @@
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		PF_INET6 protocol dispatch tables.
+ *
+ * Version:	$Id: protocol.c,v 1.10 2001/05/18 02:25:49 davem Exp $
+ *
+ * Authors:	Pedro Roque	<roque@di.fc.ul.pt>
+ *
+ *		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.
+ */
+
+/*
+ *      Changes:
+ *
+ *      Vince Laviano (vince@cs.stanford.edu)       16 May 2001
+ *      - Removed unused variable 'inet6_protocol_base'
+ *      - Modified inet6_del_protocol() to correctly maintain copy bit.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+
+struct inet6_protocol *inet6_protos[MAX_INET_PROTOS];
+static DEFINE_SPINLOCK(inet6_proto_lock);
+
+
+int inet6_add_protocol(struct inet6_protocol *prot, unsigned char protocol)
+{
+	int ret, hash = protocol & (MAX_INET_PROTOS - 1);
+
+	spin_lock_bh(&inet6_proto_lock);
+
+	if (inet6_protos[hash]) {
+		ret = -1;
+	} else {
+		inet6_protos[hash] = prot;
+		ret = 0;
+	}
+
+	spin_unlock_bh(&inet6_proto_lock);
+
+	return ret;
+}
+
+/*
+ *	Remove a protocol from the hash tables.
+ */
+ 
+int inet6_del_protocol(struct inet6_protocol *prot, unsigned char protocol)
+{
+	int ret, hash = protocol & (MAX_INET_PROTOS - 1);
+
+	spin_lock_bh(&inet6_proto_lock);
+
+	if (inet6_protos[hash] != prot) {
+		ret = -1;
+	} else {
+		inet6_protos[hash] = NULL;
+		ret = 0;
+	}
+
+	spin_unlock_bh(&inet6_proto_lock);
+
+	synchronize_net();
+
+	return ret;
+}

net/ipv6/reassembly.c

@@ -0,0 +1,771 @@
+/*
+ *	IPv6 fragment reassembly
+ *	Linux INET6 implementation 
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>	
+ *
+ *	$Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
+ *
+ *	Based on: net/ipv4/ip_fragment.c
+ *
+ *	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.
+ */
+
+/* 
+ *	Fixes:	
+ *	Andi Kleen	Make it work with multiple hosts.
+ *			More RFC compliance.
+ *
+ *      Horst von Brand Add missing #include <linux/string.h>
+ *	Alexey Kuznetsov	SMP races, threading, cleanup.
+ *	Patrick McHardy		LRU queue of frag heads for evictor.
+ *	Mitsuru KANDA @USAGI	Register inet6_protocol{}.
+ *	David Stevens and
+ *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
+ *				calculate ICV correctly.
+ */
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/jiffies.h>
+#include <linux/net.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/icmpv6.h>
+#include <linux/random.h>
+#include <linux/jhash.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+
+int sysctl_ip6frag_high_thresh = 256*1024;
+int sysctl_ip6frag_low_thresh = 192*1024;
+
+int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT;
+
+struct ip6frag_skb_cb
+{
+	struct inet6_skb_parm	h;
+	int			offset;
+};
+
+#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))
+
+
+/*
+ *	Equivalent of ipv4 struct ipq
+ */
+
+struct frag_queue
+{
+	struct frag_queue	*next;
+	struct list_head lru_list;		/* lru list member	*/
+
+	__u32			id;		/* fragment id		*/
+	struct in6_addr		saddr;
+	struct in6_addr		daddr;
+
+	spinlock_t		lock;
+	atomic_t		refcnt;
+	struct timer_list	timer;		/* expire timer		*/
+	struct sk_buff		*fragments;
+	int			len;
+	int			meat;
+	int			iif;
+	struct timeval		stamp;
+	unsigned int		csum;
+	__u8			last_in;	/* has first/last segment arrived? */
+#define COMPLETE		4
+#define FIRST_IN		2
+#define LAST_IN			1
+	__u16			nhoffset;
+	struct frag_queue	**pprev;
+};
+
+/* Hash table. */
+
+#define IP6Q_HASHSZ	64
+
+static struct frag_queue *ip6_frag_hash[IP6Q_HASHSZ];
+static DEFINE_RWLOCK(ip6_frag_lock);
+static u32 ip6_frag_hash_rnd;
+static LIST_HEAD(ip6_frag_lru_list);
+int ip6_frag_nqueues = 0;
+
+static __inline__ void __fq_unlink(struct frag_queue *fq)
+{
+	if(fq->next)
+		fq->next->pprev = fq->pprev;
+	*fq->pprev = fq->next;
+	list_del(&fq->lru_list);
+	ip6_frag_nqueues--;
+}
+
+static __inline__ void fq_unlink(struct frag_queue *fq)
+{
+	write_lock(&ip6_frag_lock);
+	__fq_unlink(fq);
+	write_unlock(&ip6_frag_lock);
+}
+
+static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
+			       struct in6_addr *daddr)
+{
+	u32 a, b, c;
+
+	a = saddr->s6_addr32[0];
+	b = saddr->s6_addr32[1];
+	c = saddr->s6_addr32[2];
+
+	a += JHASH_GOLDEN_RATIO;
+	b += JHASH_GOLDEN_RATIO;
+	c += ip6_frag_hash_rnd;
+	__jhash_mix(a, b, c);
+
+	a += saddr->s6_addr32[3];
+	b += daddr->s6_addr32[0];
+	c += daddr->s6_addr32[1];
+	__jhash_mix(a, b, c);
+
+	a += daddr->s6_addr32[2];
+	b += daddr->s6_addr32[3];
+	c += id;
+	__jhash_mix(a, b, c);
+
+	return c & (IP6Q_HASHSZ - 1);
+}
+
+static struct timer_list ip6_frag_secret_timer;
+int sysctl_ip6frag_secret_interval = 10 * 60 * HZ;
+
+static void ip6_frag_secret_rebuild(unsigned long dummy)
+{
+	unsigned long now = jiffies;
+	int i;
+
+	write_lock(&ip6_frag_lock);
+	get_random_bytes(&ip6_frag_hash_rnd, sizeof(u32));
+	for (i = 0; i < IP6Q_HASHSZ; i++) {
+		struct frag_queue *q;
+
+		q = ip6_frag_hash[i];
+		while (q) {
+			struct frag_queue *next = q->next;
+			unsigned int hval = ip6qhashfn(q->id,
+						       &q->saddr,
+						       &q->daddr);
+
+			if (hval != i) {
+				/* Unlink. */
+				if (q->next)
+					q->next->pprev = q->pprev;
+				*q->pprev = q->next;
+
+				/* Relink to new hash chain. */
+				if ((q->next = ip6_frag_hash[hval]) != NULL)
+					q->next->pprev = &q->next;
+				ip6_frag_hash[hval] = q;
+				q->pprev = &ip6_frag_hash[hval];
+			}
+
+			q = next;
+		}
+	}
+	write_unlock(&ip6_frag_lock);
+
+	mod_timer(&ip6_frag_secret_timer, now + sysctl_ip6frag_secret_interval);
+}
+
+atomic_t ip6_frag_mem = ATOMIC_INIT(0);
+
+/* Memory Tracking Functions. */
+static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
+{
+	if (work)
+		*work -= skb->truesize;
+	atomic_sub(skb->truesize, &ip6_frag_mem);
+	kfree_skb(skb);
+}
+
+static inline void frag_free_queue(struct frag_queue *fq, int *work)
+{
+	if (work)
+		*work -= sizeof(struct frag_queue);
+	atomic_sub(sizeof(struct frag_queue), &ip6_frag_mem);
+	kfree(fq);
+}
+
+static inline struct frag_queue *frag_alloc_queue(void)
+{
+	struct frag_queue *fq = kmalloc(sizeof(struct frag_queue), GFP_ATOMIC);
+
+	if(!fq)
+		return NULL;
+	atomic_add(sizeof(struct frag_queue), &ip6_frag_mem);
+	return fq;
+}
+
+/* Destruction primitives. */
+
+/* Complete destruction of fq. */
+static void ip6_frag_destroy(struct frag_queue *fq, int *work)
+{
+	struct sk_buff *fp;
+
+	BUG_TRAP(fq->last_in&COMPLETE);
+	BUG_TRAP(del_timer(&fq->timer) == 0);
+
+	/* Release all fragment data. */
+	fp = fq->fragments;
+	while (fp) {
+		struct sk_buff *xp = fp->next;
+
+		frag_kfree_skb(fp, work);
+		fp = xp;
+	}
+
+	frag_free_queue(fq, work);
+}
+
+static __inline__ void fq_put(struct frag_queue *fq, int *work)
+{
+	if (atomic_dec_and_test(&fq->refcnt))
+		ip6_frag_destroy(fq, work);
+}
+
+/* Kill fq entry. It is not destroyed immediately,
+ * because caller (and someone more) holds reference count.
+ */
+static __inline__ void fq_kill(struct frag_queue *fq)
+{
+	if (del_timer(&fq->timer))
+		atomic_dec(&fq->refcnt);
+
+	if (!(fq->last_in & COMPLETE)) {
+		fq_unlink(fq);
+		atomic_dec(&fq->refcnt);
+		fq->last_in |= COMPLETE;
+	}
+}
+
+static void ip6_evictor(void)
+{
+	struct frag_queue *fq;
+	struct list_head *tmp;
+	int work;
+
+	work = atomic_read(&ip6_frag_mem) - sysctl_ip6frag_low_thresh;
+	if (work <= 0)
+		return;
+
+	while(work > 0) {
+		read_lock(&ip6_frag_lock);
+		if (list_empty(&ip6_frag_lru_list)) {
+			read_unlock(&ip6_frag_lock);
+			return;
+		}
+		tmp = ip6_frag_lru_list.next;
+		fq = list_entry(tmp, struct frag_queue, lru_list);
+		atomic_inc(&fq->refcnt);
+		read_unlock(&ip6_frag_lock);
+
+		spin_lock(&fq->lock);
+		if (!(fq->last_in&COMPLETE))
+			fq_kill(fq);
+		spin_unlock(&fq->lock);
+
+		fq_put(fq, &work);
+		IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	}
+}
+
+static void ip6_frag_expire(unsigned long data)
+{
+	struct frag_queue *fq = (struct frag_queue *) data;
+
+	spin_lock(&fq->lock);
+
+	if (fq->last_in & COMPLETE)
+		goto out;
+
+	fq_kill(fq);
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT);
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+
+	/* Send error only if the first segment arrived. */
+	if (fq->last_in&FIRST_IN && fq->fragments) {
+		struct net_device *dev = dev_get_by_index(fq->iif);
+
+		/*
+		   But use as source device on which LAST ARRIVED
+		   segment was received. And do not use fq->dev
+		   pointer directly, device might already disappeared.
+		 */
+		if (dev) {
+			fq->fragments->dev = dev;
+			icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0,
+				    dev);
+			dev_put(dev);
+		}
+	}
+out:
+	spin_unlock(&fq->lock);
+	fq_put(fq, NULL);
+}
+
+/* Creation primitives. */
+
+
+static struct frag_queue *ip6_frag_intern(unsigned int hash,
+					  struct frag_queue *fq_in)
+{
+	struct frag_queue *fq;
+
+	write_lock(&ip6_frag_lock);
+#ifdef CONFIG_SMP
+	for (fq = ip6_frag_hash[hash]; fq; fq = fq->next) {
+		if (fq->id == fq_in->id && 
+		    ipv6_addr_equal(&fq_in->saddr, &fq->saddr) &&
+		    ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) {
+			atomic_inc(&fq->refcnt);
+			write_unlock(&ip6_frag_lock);
+			fq_in->last_in |= COMPLETE;
+			fq_put(fq_in, NULL);
+			return fq;
+		}
+	}
+#endif
+	fq = fq_in;
+
+	if (!mod_timer(&fq->timer, jiffies + sysctl_ip6frag_time))
+		atomic_inc(&fq->refcnt);
+
+	atomic_inc(&fq->refcnt);
+	if((fq->next = ip6_frag_hash[hash]) != NULL)
+		fq->next->pprev = &fq->next;
+	ip6_frag_hash[hash] = fq;
+	fq->pprev = &ip6_frag_hash[hash];
+	INIT_LIST_HEAD(&fq->lru_list);
+	list_add_tail(&fq->lru_list, &ip6_frag_lru_list);
+	ip6_frag_nqueues++;
+	write_unlock(&ip6_frag_lock);
+	return fq;
+}
+
+
+static struct frag_queue *
+ip6_frag_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr *dst)
+{
+	struct frag_queue *fq;
+
+	if ((fq = frag_alloc_queue()) == NULL)
+		goto oom;
+
+	memset(fq, 0, sizeof(struct frag_queue));
+
+	fq->id = id;
+	ipv6_addr_copy(&fq->saddr, src);
+	ipv6_addr_copy(&fq->daddr, dst);
+
+	init_timer(&fq->timer);
+	fq->timer.function = ip6_frag_expire;
+	fq->timer.data = (long) fq;
+	spin_lock_init(&fq->lock);
+	atomic_set(&fq->refcnt, 1);
+
+	return ip6_frag_intern(hash, fq);
+
+oom:
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	return NULL;
+}
+
+static __inline__ struct frag_queue *
+fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
+{
+	struct frag_queue *fq;
+	unsigned int hash = ip6qhashfn(id, src, dst);
+
+	read_lock(&ip6_frag_lock);
+	for(fq = ip6_frag_hash[hash]; fq; fq = fq->next) {
+		if (fq->id == id && 
+		    ipv6_addr_equal(src, &fq->saddr) &&
+		    ipv6_addr_equal(dst, &fq->daddr)) {
+			atomic_inc(&fq->refcnt);
+			read_unlock(&ip6_frag_lock);
+			return fq;
+		}
+	}
+	read_unlock(&ip6_frag_lock);
+
+	return ip6_frag_create(hash, id, src, dst);
+}
+
+
+static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, 
+			   struct frag_hdr *fhdr, int nhoff)
+{
+	struct sk_buff *prev, *next;
+	int offset, end;
+
+	if (fq->last_in & COMPLETE)
+		goto err;
+
+	offset = ntohs(fhdr->frag_off) & ~0x7;
+	end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
+			((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));
+
+	if ((unsigned int)end > IPV6_MAXPLEN) {
+		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+ 		icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw);
+ 		return;
+	}
+
+ 	if (skb->ip_summed == CHECKSUM_HW)
+ 		skb->csum = csum_sub(skb->csum,
+ 				     csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0));
+
+	/* Is this the final fragment? */
+	if (!(fhdr->frag_off & htons(IP6_MF))) {
+		/* If we already have some bits beyond end
+		 * or have different end, the segment is corrupted.
+		 */
+		if (end < fq->len ||
+		    ((fq->last_in & LAST_IN) && end != fq->len))
+			goto err;
+		fq->last_in |= LAST_IN;
+		fq->len = end;
+	} else {
+		/* Check if the fragment is rounded to 8 bytes.
+		 * Required by the RFC.
+		 */
+		if (end & 0x7) {
+			/* RFC2460 says always send parameter problem in
+			 * this case. -DaveM
+			 */
+			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, 
+					  offsetof(struct ipv6hdr, payload_len));
+			return;
+		}
+		if (end > fq->len) {
+			/* Some bits beyond end -> corruption. */
+			if (fq->last_in & LAST_IN)
+				goto err;
+			fq->len = end;
+		}
+	}
+
+	if (end == offset)
+		goto err;
+
+	/* Point into the IP datagram 'data' part. */
+	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
+		goto err;
+	if (end-offset < skb->len) {
+		if (pskb_trim(skb, end - offset))
+			goto err;
+		if (skb->ip_summed != CHECKSUM_UNNECESSARY)
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
+	/* Find out which fragments are in front and at the back of us
+	 * in the chain of fragments so far.  We must know where to put
+	 * this fragment, right?
+	 */
+	prev = NULL;
+	for(next = fq->fragments; next != NULL; next = next->next) {
+		if (FRAG6_CB(next)->offset >= offset)
+			break;	/* bingo! */
+		prev = next;
+	}
+
+	/* We found where to put this one.  Check for overlap with
+	 * preceding fragment, and, if needed, align things so that
+	 * any overlaps are eliminated.
+	 */
+	if (prev) {
+		int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
+
+		if (i > 0) {
+			offset += i;
+			if (end <= offset)
+				goto err;
+			if (!pskb_pull(skb, i))
+				goto err;
+			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
+				skb->ip_summed = CHECKSUM_NONE;
+		}
+	}
+
+	/* Look for overlap with succeeding segments.
+	 * If we can merge fragments, do it.
+	 */
+	while (next && FRAG6_CB(next)->offset < end) {
+		int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
+
+		if (i < next->len) {
+			/* Eat head of the next overlapped fragment
+			 * and leave the loop. The next ones cannot overlap.
+			 */
+			if (!pskb_pull(next, i))
+				goto err;
+			FRAG6_CB(next)->offset += i;	/* next fragment */
+			fq->meat -= i;
+			if (next->ip_summed != CHECKSUM_UNNECESSARY)
+				next->ip_summed = CHECKSUM_NONE;
+			break;
+		} else {
+			struct sk_buff *free_it = next;
+
+			/* Old fragment is completely overridden with
+			 * new one drop it.
+			 */
+			next = next->next;
+
+			if (prev)
+				prev->next = next;
+			else
+				fq->fragments = next;
+
+			fq->meat -= free_it->len;
+			frag_kfree_skb(free_it, NULL);
+		}
+	}
+
+	FRAG6_CB(skb)->offset = offset;
+
+	/* Insert this fragment in the chain of fragments. */
+	skb->next = next;
+	if (prev)
+		prev->next = skb;
+	else
+		fq->fragments = skb;
+
+	if (skb->dev)
+		fq->iif = skb->dev->ifindex;
+	skb->dev = NULL;
+	fq->stamp = skb->stamp;
+	fq->meat += skb->len;
+	atomic_add(skb->truesize, &ip6_frag_mem);
+
+	/* The first fragment.
+	 * nhoffset is obtained from the first fragment, of course.
+	 */
+	if (offset == 0) {
+		fq->nhoffset = nhoff;
+		fq->last_in |= FIRST_IN;
+	}
+	write_lock(&ip6_frag_lock);
+	list_move_tail(&fq->lru_list, &ip6_frag_lru_list);
+	write_unlock(&ip6_frag_lock);
+	return;
+
+err:
+	IP6_INC_STATS(IPSTATS_MIB_REASMFAILS);
+	kfree_skb(skb);
+}
+
+/*
+ *	Check if this packet is complete.
+ *	Returns NULL on failure by any reason, and pointer
+ *	to current nexthdr field in reassembled frame.
+ *
+ *	It is called with locked fq, and caller must check that
+ *	queue is eligible for reassembly i.e. it is not COMPLETE,
+ *	the last and the first frames arrived and all the bits are here.
+ */
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
+			  unsigned int *nhoffp,
+			  struct net_device *dev)
+{
+	struct sk_buff *fp, *head = fq->fragments;
+	int    payload_len;
+	unsigned int nhoff;
+
+	fq_kill(fq);
+
+	BUG_TRAP(head != NULL);
+	BUG_TRAP(FRAG6_CB(head)->offset == 0);
+
+	/* Unfragmented part is taken from the first segment. */
+	payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
+	if (payload_len > IPV6_MAXPLEN)
+		goto out_oversize;
+
+	/* Head of list must not be cloned. */
+	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
+		goto out_oom;
+
+	/* If the first fragment is fragmented itself, we split
+	 * it to two chunks: the first with data and paged part
+	 * and the second, holding only fragments. */
+	if (skb_shinfo(head)->frag_list) {
+		struct sk_buff *clone;
+		int i, plen = 0;
+
+		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
+			goto out_oom;
+		clone->next = head->next;
+		head->next = clone;
+		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+		skb_shinfo(head)->frag_list = NULL;
+		for (i=0; i<skb_shinfo(head)->nr_frags; i++)
+			plen += skb_shinfo(head)->frags[i].size;
+		clone->len = clone->data_len = head->data_len - plen;
+		head->data_len -= clone->len;
+		head->len -= clone->len;
+		clone->csum = 0;
+		clone->ip_summed = head->ip_summed;
+		atomic_add(clone->truesize, &ip6_frag_mem);
+	}
+
+	/* We have to remove fragment header from datagram and to relocate
+	 * header in order to calculate ICV correctly. */
+	nhoff = fq->nhoffset;
+	head->nh.raw[nhoff] = head->h.raw[0];
+	memmove(head->head + sizeof(struct frag_hdr), head->head, 
+		(head->data - head->head) - sizeof(struct frag_hdr));
+	head->mac.raw += sizeof(struct frag_hdr);
+	head->nh.raw += sizeof(struct frag_hdr);
+
+	skb_shinfo(head)->frag_list = head->next;
+	head->h.raw = head->data;
+	skb_push(head, head->data - head->nh.raw);
+	atomic_sub(head->truesize, &ip6_frag_mem);
+
+	for (fp=head->next; fp; fp = fp->next) {
+		head->data_len += fp->len;
+		head->len += fp->len;
+		if (head->ip_summed != fp->ip_summed)
+			head->ip_summed = CHECKSUM_NONE;
+		else if (head->ip_summed == CHECKSUM_HW)
+			head->csum = csum_add(head->csum, fp->csum);
+		head->truesize += fp->truesize;
+		atomic_sub(fp->truesize, &ip6_frag_mem);
+	}
+
+	head->next = NULL;
+	head->dev = dev;
+	head->stamp = fq->stamp;
+	head->nh.ipv6h->payload_len = htons(payload_len);
+
+	*skb_in = head;
+
+	/* Yes, and fold redundant checksum back. 8) */
+	if (head->ip_summed == CHECKSUM_HW)
+		head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+	fq->fragments = NULL;
+	*nhoffp = nhoff;
+	return 1;
+
+out_oversize:
+	if (net_ratelimit())
+		printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
+	goto out_fail;
+out_oom:
+	if (net_ratelimit())
+		printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
+out_fail:
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	return -1;
+}
+
+static int ipv6_frag_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *skbp; 
+	struct net_device *dev = skb->dev;
+	struct frag_hdr *fhdr;
+	struct frag_queue *fq;
+	struct ipv6hdr *hdr;
+
+	hdr = skb->nh.ipv6h;
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);
+
+	/* Jumbo payload inhibits frag. header */
+	if (hdr->payload_len==0) {
+		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
+		return -1;
+	}
+	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
+		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
+		return -1;
+	}
+
+	hdr = skb->nh.ipv6h;
+	fhdr = (struct frag_hdr *)skb->h.raw;
+
+	if (!(fhdr->frag_off & htons(0xFFF9))) {
+		/* It is not a fragmented frame */
+		skb->h.raw += sizeof(struct frag_hdr);
+		IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+
+		*nhoffp = (u8*)fhdr - skb->nh.raw;
+		return 1;
+	}
+
+	if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
+		ip6_evictor();
+
+	if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) {
+		int ret = -1;
+
+		spin_lock(&fq->lock);
+
+		ip6_frag_queue(fq, skb, fhdr, *nhoffp);
+
+		if (fq->last_in == (FIRST_IN|LAST_IN) &&
+		    fq->meat == fq->len)
+			ret = ip6_frag_reasm(fq, skbp, nhoffp, dev);
+
+		spin_unlock(&fq->lock);
+		fq_put(fq, NULL);
+		return ret;
+	}
+
+	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	kfree_skb(skb);
+	return -1;
+}
+
+static struct inet6_protocol frag_protocol =
+{
+	.handler	=	ipv6_frag_rcv,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+void __init ipv6_frag_init(void)
+{
+	if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
+		printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n");
+
+	ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
+				   (jiffies ^ (jiffies >> 6)));
+
+	init_timer(&ip6_frag_secret_timer);
+	ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
+	ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
+	add_timer(&ip6_frag_secret_timer);
+}

net/ipv6/sit.c

@@ -0,0 +1,833 @@
+/*
+ *	IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT)
+ *	Linux INET6 implementation
+ *
+ *	Authors:
+ *	Pedro Roque		<roque@di.fc.ul.pt>	
+ *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
+ *
+ *	$Id: sit.c,v 1.53 2001/09/25 05:09:53 davem Exp $
+ *
+ *	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.
+ *
+ *	Changes:
+ * Roger Venning <r.venning@telstra.com>:	6to4 support
+ * Nate Thompson <nate@thebog.net>:		6to4 support
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/sched.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/icmp.h>
+#include <asm/uaccess.h>
+#include <linux/init.h>
+#include <linux/netfilter_ipv4.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/icmp.h>
+#include <net/ipip.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/dsfield.h>
+
+/*
+   This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
+
+   For comments look at net/ipv4/ip_gre.c --ANK
+ */
+
+#define HASH_SIZE  16
+#define HASH(addr) ((addr^(addr>>4))&0xF)
+
+static int ipip6_fb_tunnel_init(struct net_device *dev);
+static int ipip6_tunnel_init(struct net_device *dev);
+static void ipip6_tunnel_setup(struct net_device *dev);
+
+static struct net_device *ipip6_fb_tunnel_dev;
+
+static struct ip_tunnel *tunnels_r_l[HASH_SIZE];
+static struct ip_tunnel *tunnels_r[HASH_SIZE];
+static struct ip_tunnel *tunnels_l[HASH_SIZE];
+static struct ip_tunnel *tunnels_wc[1];
+static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunnels_r_l };
+
+static DEFINE_RWLOCK(ipip6_lock);
+
+static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local)
+{
+	unsigned h0 = HASH(remote);
+	unsigned h1 = HASH(local);
+	struct ip_tunnel *t;
+
+	for (t = tunnels_r_l[h0^h1]; t; t = t->next) {
+		if (local == t->parms.iph.saddr &&
+		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
+			return t;
+	}
+	for (t = tunnels_r[h0]; t; t = t->next) {
+		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
+			return t;
+	}
+	for (t = tunnels_l[h1]; t; t = t->next) {
+		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
+			return t;
+	}
+	if ((t = tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
+		return t;
+	return NULL;
+}
+
+static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t)
+{
+	u32 remote = t->parms.iph.daddr;
+	u32 local = t->parms.iph.saddr;
+	unsigned h = 0;
+	int prio = 0;
+
+	if (remote) {
+		prio |= 2;
+		h ^= HASH(remote);
+	}
+	if (local) {
+		prio |= 1;
+		h ^= HASH(local);
+	}
+	return &tunnels[prio][h];
+}
+
+static void ipip6_tunnel_unlink(struct ip_tunnel *t)
+{
+	struct ip_tunnel **tp;
+
+	for (tp = ipip6_bucket(t); *tp; tp = &(*tp)->next) {
+		if (t == *tp) {
+			write_lock_bh(&ipip6_lock);
+			*tp = t->next;
+			write_unlock_bh(&ipip6_lock);
+			break;
+		}
+	}
+}
+
+static void ipip6_tunnel_link(struct ip_tunnel *t)
+{
+	struct ip_tunnel **tp = ipip6_bucket(t);
+
+	t->next = *tp;
+	write_lock_bh(&ipip6_lock);
+	*tp = t;
+	write_unlock_bh(&ipip6_lock);
+}
+
+static struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create)
+{
+	u32 remote = parms->iph.daddr;
+	u32 local = parms->iph.saddr;
+	struct ip_tunnel *t, **tp, *nt;
+	struct net_device *dev;
+	unsigned h = 0;
+	int prio = 0;
+	char name[IFNAMSIZ];
+
+	if (remote) {
+		prio |= 2;
+		h ^= HASH(remote);
+	}
+	if (local) {
+		prio |= 1;
+		h ^= HASH(local);
+	}
+	for (tp = &tunnels[prio][h]; (t = *tp) != NULL; tp = &t->next) {
+		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
+			return t;
+	}
+	if (!create)
+		goto failed;
+
+	if (parms->name[0])
+		strlcpy(name, parms->name, IFNAMSIZ);
+	else {
+		int i;
+		for (i=1; i<100; i++) {
+			sprintf(name, "sit%d", i);
+			if (__dev_get_by_name(name) == NULL)
+				break;
+		}
+		if (i==100)
+			goto failed;
+	}
+
+	dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup);
+	if (dev == NULL)
+		return NULL;
+
+	nt = dev->priv;
+	dev->init = ipip6_tunnel_init;
+	nt->parms = *parms;
+
+	if (register_netdevice(dev) < 0) {
+		free_netdev(dev);
+		goto failed;
+	}
+
+	dev_hold(dev);
+
+	ipip6_tunnel_link(nt);
+	/* Do not decrement MOD_USE_COUNT here. */
+	return nt;
+
+failed:
+	return NULL;
+}
+
+static void ipip6_tunnel_uninit(struct net_device *dev)
+{
+	if (dev == ipip6_fb_tunnel_dev) {
+		write_lock_bh(&ipip6_lock);
+		tunnels_wc[0] = NULL;
+		write_unlock_bh(&ipip6_lock);
+		dev_put(dev);
+	} else {
+		ipip6_tunnel_unlink((struct ip_tunnel*)dev->priv);
+		dev_put(dev);
+	}
+}
+
+
+static void ipip6_err(struct sk_buff *skb, u32 info)
+{
+#ifndef I_WISH_WORLD_WERE_PERFECT
+
+/* It is not :-( All the routers (except for Linux) return only
+   8 bytes of packet payload. It means, that precise relaying of
+   ICMP in the real Internet is absolutely infeasible.
+ */
+	struct iphdr *iph = (struct iphdr*)skb->data;
+	int type = skb->h.icmph->type;
+	int code = skb->h.icmph->code;
+	struct ip_tunnel *t;
+
+	switch (type) {
+	default:
+	case ICMP_PARAMETERPROB:
+		return;
+
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+		case ICMP_PORT_UNREACH:
+			/* Impossible event. */
+			return;
+		case ICMP_FRAG_NEEDED:
+			/* Soft state for pmtu is maintained by IP core. */
+			return;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			   rfc2003 contains "deep thoughts" about NET_UNREACH,
+			   I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			return;
+		break;
+	}
+
+	read_lock(&ipip6_lock);
+	t = ipip6_tunnel_lookup(iph->daddr, iph->saddr);
+	if (t == NULL || t->parms.iph.daddr == 0)
+		goto out;
+	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
+		goto out;
+
+	if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+		t->err_count++;
+	else
+		t->err_count = 1;
+	t->err_time = jiffies;
+out:
+	read_unlock(&ipip6_lock);
+	return;
+#else
+	struct iphdr *iph = (struct iphdr*)dp;
+	int hlen = iph->ihl<<2;
+	struct ipv6hdr *iph6;
+	int type = skb->h.icmph->type;
+	int code = skb->h.icmph->code;
+	int rel_type = 0;
+	int rel_code = 0;
+	int rel_info = 0;
+	struct sk_buff *skb2;
+	struct rt6_info *rt6i;
+
+	if (len < hlen + sizeof(struct ipv6hdr))
+		return;
+	iph6 = (struct ipv6hdr*)(dp + hlen);
+
+	switch (type) {
+	default:
+		return;
+	case ICMP_PARAMETERPROB:
+		if (skb->h.icmph->un.gateway < hlen)
+			return;
+
+		/* So... This guy found something strange INSIDE encapsulated
+		   packet. Well, he is fool, but what can we do ?
+		 */
+		rel_type = ICMPV6_PARAMPROB;
+		rel_info = skb->h.icmph->un.gateway - hlen;
+		break;
+
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+		case ICMP_PORT_UNREACH:
+			/* Impossible event. */
+			return;
+		case ICMP_FRAG_NEEDED:
+			/* Too complicated case ... */
+			return;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			   rfc2003 contains "deep thoughts" about NET_UNREACH,
+			   I believe, it is just ether pollution. --ANK
+			 */
+			rel_type = ICMPV6_DEST_UNREACH;
+			rel_code = ICMPV6_ADDR_UNREACH;
+			break;
+		}
+		break;
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			return;
+		rel_type = ICMPV6_TIME_EXCEED;
+		rel_code = ICMPV6_EXC_HOPLIMIT;
+		break;
+	}
+
+	/* Prepare fake skb to feed it to icmpv6_send */
+	skb2 = skb_clone(skb, GFP_ATOMIC);
+	if (skb2 == NULL)
+		return;
+	dst_release(skb2->dst);
+	skb2->dst = NULL;
+	skb_pull(skb2, skb->data - (u8*)iph6);
+	skb2->nh.raw = skb2->data;
+
+	/* Try to guess incoming interface */
+	rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0);
+	if (rt6i && rt6i->rt6i_dev) {
+		skb2->dev = rt6i->rt6i_dev;
+
+		rt6i = rt6_lookup(&iph6->daddr, &iph6->saddr, NULL, 0);
+
+		if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) {
+			struct ip_tunnel * t = (struct ip_tunnel*)rt6i->rt6i_dev->priv;
+			if (rel_type == ICMPV6_TIME_EXCEED && t->parms.iph.ttl) {
+				rel_type = ICMPV6_DEST_UNREACH;
+				rel_code = ICMPV6_ADDR_UNREACH;
+			}
+			icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev);
+		}
+	}
+	kfree_skb(skb2);
+	return;
+#endif
+}
+
+static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
+{
+	if (INET_ECN_is_ce(iph->tos))
+		IP6_ECN_set_ce(skb->nh.ipv6h);
+}
+
+static int ipip6_rcv(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	struct ip_tunnel *tunnel;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		goto out;
+
+	iph = skb->nh.iph;
+
+	read_lock(&ipip6_lock);
+	if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
+		secpath_reset(skb);
+		skb->mac.raw = skb->nh.raw;
+		skb->nh.raw = skb->data;
+		memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
+		skb->protocol = htons(ETH_P_IPV6);
+		skb->pkt_type = PACKET_HOST;
+		tunnel->stat.rx_packets++;
+		tunnel->stat.rx_bytes += skb->len;
+		skb->dev = tunnel->dev;
+		dst_release(skb->dst);
+		skb->dst = NULL;
+		nf_reset(skb);
+		ipip6_ecn_decapsulate(iph, skb);
+		netif_rx(skb);
+		read_unlock(&ipip6_lock);
+		return 0;
+	}
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0);
+	kfree_skb(skb);
+	read_unlock(&ipip6_lock);
+out:
+	return 0;
+}
+
+/* Returns the embedded IPv4 address if the IPv6 address
+   comes from 6to4 (RFC 3056) addr space */
+
+static inline u32 try_6to4(struct in6_addr *v6dst)
+{
+	u32 dst = 0;
+
+	if (v6dst->s6_addr16[0] == htons(0x2002)) {
+	        /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
+		memcpy(&dst, &v6dst->s6_addr16[1], 4);
+	}
+	return dst;
+}
+
+/*
+ *	This function assumes it is being called from dev_queue_xmit()
+ *	and that skb is filled properly by that function.
+ */
+
+static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
+	struct net_device_stats *stats = &tunnel->stat;
+	struct iphdr  *tiph = &tunnel->parms.iph;
+	struct ipv6hdr *iph6 = skb->nh.ipv6h;
+	u8     tos = tunnel->parms.iph.tos;
+	struct rtable *rt;     			/* Route to the other host */
+	struct net_device *tdev;			/* Device to other host */
+	struct iphdr  *iph;			/* Our new IP header */
+	int    max_headroom;			/* The extra header space needed */
+	u32    dst = tiph->daddr;
+	int    mtu;
+	struct in6_addr *addr6;	
+	int addr_type;
+
+	if (tunnel->recursion++) {
+		tunnel->stat.collisions++;
+		goto tx_error;
+	}
+
+	if (skb->protocol != htons(ETH_P_IPV6))
+		goto tx_error;
+
+	if (!dst)
+		dst = try_6to4(&iph6->daddr);
+
+	if (!dst) {
+		struct neighbour *neigh = NULL;
+
+		if (skb->dst)
+			neigh = skb->dst->neighbour;
+
+		if (neigh == NULL) {
+			if (net_ratelimit())
+				printk(KERN_DEBUG "sit: nexthop == NULL\n");
+			goto tx_error;
+		}
+
+		addr6 = (struct in6_addr*)&neigh->primary_key;
+		addr_type = ipv6_addr_type(addr6);
+
+		if (addr_type == IPV6_ADDR_ANY) {
+			addr6 = &skb->nh.ipv6h->daddr;
+			addr_type = ipv6_addr_type(addr6);
+		}
+
+		if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
+			goto tx_error_icmp;
+
+		dst = addr6->s6_addr32[3];
+	}
+
+	{
+		struct flowi fl = { .nl_u = { .ip4_u =
+					      { .daddr = dst,
+						.saddr = tiph->saddr,
+						.tos = RT_TOS(tos) } },
+				    .oif = tunnel->parms.link,
+				    .proto = IPPROTO_IPV6 };
+		if (ip_route_output_key(&rt, &fl)) {
+			tunnel->stat.tx_carrier_errors++;
+			goto tx_error_icmp;
+		}
+	}
+	if (rt->rt_type != RTN_UNICAST) {
+		ip_rt_put(rt);
+		tunnel->stat.tx_carrier_errors++;
+		goto tx_error_icmp;
+	}
+	tdev = rt->u.dst.dev;
+
+	if (tdev == dev) {
+		ip_rt_put(rt);
+		tunnel->stat.collisions++;
+		goto tx_error;
+	}
+
+	if (tiph->frag_off)
+		mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
+	else
+		mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
+
+	if (mtu < 68) {
+		tunnel->stat.collisions++;
+		ip_rt_put(rt);
+		goto tx_error;
+	}
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+	if (tunnel->parms.iph.daddr && skb->dst)
+		skb->dst->ops->update_pmtu(skb->dst, mtu);
+
+	if (skb->len > mtu) {
+		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+		ip_rt_put(rt);
+		goto tx_error;
+	}
+
+	if (tunnel->err_count > 0) {
+		if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+			tunnel->err_count--;
+			dst_link_failure(skb);
+		} else
+			tunnel->err_count = 0;
+	}
+
+	/*
+	 * Okay, now see if we can stuff it in the buffer as-is.
+	 */
+	max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
+
+	if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
+		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (!new_skb) {
+			ip_rt_put(rt);
+  			stats->tx_dropped++;
+			dev_kfree_skb(skb);
+			tunnel->recursion--;
+			return 0;
+		}
+		if (skb->sk)
+			skb_set_owner_w(new_skb, skb->sk);
+		dev_kfree_skb(skb);
+		skb = new_skb;
+		iph6 = skb->nh.ipv6h;
+	}
+
+	skb->h.raw = skb->nh.raw;
+	skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+	dst_release(skb->dst);
+	skb->dst = &rt->u.dst;
+
+	/*
+	 *	Push down and install the IPIP header.
+	 */
+
+	iph 			=	skb->nh.iph;
+	iph->version		=	4;
+	iph->ihl		=	sizeof(struct iphdr)>>2;
+	if (mtu > IPV6_MIN_MTU)
+		iph->frag_off	=	htons(IP_DF);
+	else
+		iph->frag_off	=	0;
+
+	iph->protocol		=	IPPROTO_IPV6;
+	iph->tos		=	INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
+	iph->daddr		=	rt->rt_dst;
+	iph->saddr		=	rt->rt_src;
+
+	if ((iph->ttl = tiph->ttl) == 0)
+		iph->ttl	=	iph6->hop_limit;
+
+	nf_reset(skb);
+
+	IPTUNNEL_XMIT();
+	tunnel->recursion--;
+	return 0;
+
+tx_error_icmp:
+	dst_link_failure(skb);
+tx_error:
+	stats->tx_errors++;
+	dev_kfree_skb(skb);
+	tunnel->recursion--;
+	return 0;
+}
+
+static int
+ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	int err = 0;
+	struct ip_tunnel_parm p;
+	struct ip_tunnel *t;
+
+	switch (cmd) {
+	case SIOCGETTUNNEL:
+		t = NULL;
+		if (dev == ipip6_fb_tunnel_dev) {
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
+				err = -EFAULT;
+				break;
+			}
+			t = ipip6_tunnel_locate(&p, 0);
+		}
+		if (t == NULL)
+			t = (struct ip_tunnel*)dev->priv;
+		memcpy(&p, &t->parms, sizeof(p));
+		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+			err = -EFAULT;
+		break;
+
+	case SIOCADDTUNNEL:
+	case SIOCCHGTUNNEL:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		err = -EFAULT;
+		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+			goto done;
+
+		err = -EINVAL;
+		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 ||
+		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
+			goto done;
+		if (p.iph.ttl)
+			p.iph.frag_off |= htons(IP_DF);
+
+		t = ipip6_tunnel_locate(&p, cmd == SIOCADDTUNNEL);
+
+		if (dev != ipip6_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+			if (t != NULL) {
+				if (t->dev != dev) {
+					err = -EEXIST;
+					break;
+				}
+			} else {
+				if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
+				    (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
+					err = -EINVAL;
+					break;
+				}
+				t = (struct ip_tunnel*)dev->priv;
+				ipip6_tunnel_unlink(t);
+				t->parms.iph.saddr = p.iph.saddr;
+				t->parms.iph.daddr = p.iph.daddr;
+				memcpy(dev->dev_addr, &p.iph.saddr, 4);
+				memcpy(dev->broadcast, &p.iph.daddr, 4);
+				ipip6_tunnel_link(t);
+				netdev_state_change(dev);
+			}
+		}
+
+		if (t) {
+			err = 0;
+			if (cmd == SIOCCHGTUNNEL) {
+				t->parms.iph.ttl = p.iph.ttl;
+				t->parms.iph.tos = p.iph.tos;
+			}
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
+				err = -EFAULT;
+		} else
+			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		break;
+
+	case SIOCDELTUNNEL:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		if (dev == ipip6_fb_tunnel_dev) {
+			err = -EFAULT;
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+				goto done;
+			err = -ENOENT;
+			if ((t = ipip6_tunnel_locate(&p, 0)) == NULL)
+				goto done;
+			err = -EPERM;
+			if (t == ipip6_fb_tunnel_dev->priv)
+				goto done;
+			dev = t->dev;
+		}
+		err = unregister_netdevice(dev);
+		break;
+
+	default:
+		err = -EINVAL;
+	}
+
+done:
+	return err;
+}
+
+static struct net_device_stats *ipip6_tunnel_get_stats(struct net_device *dev)
+{
+	return &(((struct ip_tunnel*)dev->priv)->stat);
+}
+
+static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
+		return -EINVAL;
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static void ipip6_tunnel_setup(struct net_device *dev)
+{
+	SET_MODULE_OWNER(dev);
+	dev->uninit		= ipip6_tunnel_uninit;
+	dev->destructor 	= free_netdev;
+	dev->hard_start_xmit	= ipip6_tunnel_xmit;
+	dev->get_stats		= ipip6_tunnel_get_stats;
+	dev->do_ioctl		= ipip6_tunnel_ioctl;
+	dev->change_mtu		= ipip6_tunnel_change_mtu;
+
+	dev->type		= ARPHRD_SIT;
+	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
+	dev->mtu		= 1500 - sizeof(struct iphdr);
+	dev->flags		= IFF_NOARP;
+	dev->iflink		= 0;
+	dev->addr_len		= 4;
+}
+
+static int ipip6_tunnel_init(struct net_device *dev)
+{
+	struct net_device *tdev = NULL;
+	struct ip_tunnel *tunnel;
+	struct iphdr *iph;
+
+	tunnel = (struct ip_tunnel*)dev->priv;
+	iph = &tunnel->parms.iph;
+
+	tunnel->dev = dev;
+	strcpy(tunnel->parms.name, dev->name);
+
+	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
+	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+
+	if (iph->daddr) {
+		struct flowi fl = { .nl_u = { .ip4_u =
+					      { .daddr = iph->daddr,
+						.saddr = iph->saddr,
+						.tos = RT_TOS(iph->tos) } },
+				    .oif = tunnel->parms.link,
+				    .proto = IPPROTO_IPV6 };
+		struct rtable *rt;
+		if (!ip_route_output_key(&rt, &fl)) {
+			tdev = rt->u.dst.dev;
+			ip_rt_put(rt);
+		}
+		dev->flags |= IFF_POINTOPOINT;
+	}
+
+	if (!tdev && tunnel->parms.link)
+		tdev = __dev_get_by_index(tunnel->parms.link);
+
+	if (tdev) {
+		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
+		dev->mtu = tdev->mtu - sizeof(struct iphdr);
+		if (dev->mtu < IPV6_MIN_MTU)
+			dev->mtu = IPV6_MIN_MTU;
+	}
+	dev->iflink = tunnel->parms.link;
+
+	return 0;
+}
+
+int __init ipip6_fb_tunnel_init(struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = dev->priv;
+	struct iphdr *iph = &tunnel->parms.iph;
+
+	tunnel->dev = dev;
+	strcpy(tunnel->parms.name, dev->name);
+
+	iph->version		= 4;
+	iph->protocol		= IPPROTO_IPV6;
+	iph->ihl		= 5;
+	iph->ttl		= 64;
+
+	dev_hold(dev);
+	tunnels_wc[0]		= tunnel;
+	return 0;
+}
+
+static struct net_protocol sit_protocol = {
+	.handler	=	ipip6_rcv,
+	.err_handler	=	ipip6_err,
+};
+
+void __exit sit_cleanup(void)
+{
+	inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
+	unregister_netdev(ipip6_fb_tunnel_dev);
+}
+
+int __init sit_init(void)
+{
+	int err;
+
+	printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n");
+
+	if (inet_add_protocol(&sit_protocol, IPPROTO_IPV6) < 0) {
+		printk(KERN_INFO "sit init: Can't add protocol\n");
+		return -EAGAIN;
+	}
+
+	ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", 
+					   ipip6_tunnel_setup);
+	if (!ipip6_fb_tunnel_dev) {
+		err = -ENOMEM;
+		goto err1;
+	}
+
+	ipip6_fb_tunnel_dev->init = ipip6_fb_tunnel_init;
+
+	if ((err =  register_netdev(ipip6_fb_tunnel_dev)))
+		goto err2;
+
+ out:
+	return err;
+ err2:
+	free_netdev(ipip6_fb_tunnel_dev);
+ err1:
+	inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
+	goto out;
+}

net/ipv6/sysctl_net_ipv6.c

@@ -0,0 +1,125 @@
+/*
+ * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem.
+ *
+ * Changes:
+ * YOSHIFUJI Hideaki @USAGI:	added icmp sysctl table.
+ */
+
+#include <linux/mm.h>
+#include <linux/sysctl.h>
+#include <linux/config.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <net/ndisc.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+
+extern ctl_table ipv6_route_table[];
+extern ctl_table ipv6_icmp_table[];
+
+#ifdef CONFIG_SYSCTL
+
+static ctl_table ipv6_table[] = {
+	{
+		.ctl_name	= NET_IPV6_ROUTE,
+		.procname	= "route",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= ipv6_route_table
+	},
+	{
+		.ctl_name	= NET_IPV6_ICMP,
+		.procname	= "icmp",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= ipv6_icmp_table
+	},
+	{
+		.ctl_name	= NET_IPV6_BINDV6ONLY,
+		.procname	= "bindv6only",
+		.data		= &sysctl_ipv6_bindv6only,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_IPV6_IP6FRAG_HIGH_THRESH,
+		.procname	= "ip6frag_high_thresh",
+		.data		= &sysctl_ip6frag_high_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_IPV6_IP6FRAG_LOW_THRESH,
+		.procname	= "ip6frag_low_thresh",
+		.data		= &sysctl_ip6frag_low_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_IPV6_IP6FRAG_TIME,
+		.procname	= "ip6frag_time",
+		.data		= &sysctl_ip6frag_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+		.strategy	= &sysctl_jiffies,
+	},
+	{
+		.ctl_name	= NET_IPV6_IP6FRAG_SECRET_INTERVAL,
+		.procname	= "ip6frag_secret_interval",
+		.data		= &sysctl_ip6frag_secret_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+		.strategy	= &sysctl_jiffies
+	},
+	{
+		.ctl_name	= NET_IPV6_MLD_MAX_MSF,
+		.procname	= "mld_max_msf",
+		.data		= &sysctl_mld_max_msf,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table_header *ipv6_sysctl_header;
+
+static ctl_table ipv6_net_table[] = {
+	{
+		.ctl_name	= NET_IPV6,
+		.procname	= "ipv6",
+		.mode		= 0555,
+		.child		= ipv6_table
+	},
+        { .ctl_name = 0 }
+};
+
+static ctl_table ipv6_root_table[] = {
+	{
+		.ctl_name	= CTL_NET,
+		.procname	= "net",
+		.mode		= 0555,
+		.child		= ipv6_net_table
+	},
+        { .ctl_name = 0 }
+};
+
+void ipv6_sysctl_register(void)
+{
+	ipv6_sysctl_header = register_sysctl_table(ipv6_root_table, 0);
+}
+
+void ipv6_sysctl_unregister(void)
+{
+	unregister_sysctl_table(ipv6_sysctl_header);
+}
+
+#endif /* CONFIG_SYSCTL */
+
+
+

net/ipv6/xfrm6_input.c

@@ -0,0 +1,150 @@
+/*
+ * xfrm6_input.c: based on net/ipv4/xfrm4_input.c
+ *
+ * Authors:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *	YOSHIFUJI Hideaki @USAGI
+ *		IPv6 support
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+
+static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
+{
+	struct ipv6hdr *outer_iph = skb->nh.ipv6h;
+	struct ipv6hdr *inner_iph = skb->h.ipv6h;
+
+	if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
+		IP6_ECN_set_ce(inner_iph);
+}
+
+int xfrm6_rcv_spi(struct sk_buff **pskb, unsigned int *nhoffp, u32 spi)
+{
+	struct sk_buff *skb = *pskb;
+	int err;
+	u32 seq;
+	struct sec_decap_state xfrm_vec[XFRM_MAX_DEPTH];
+	struct xfrm_state *x;
+	int xfrm_nr = 0;
+	int decaps = 0;
+	int nexthdr;
+	unsigned int nhoff;
+
+	nhoff = *nhoffp;
+	nexthdr = skb->nh.raw[nhoff];
+
+	seq = 0;
+	if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0)
+		goto drop;
+	
+	do {
+		struct ipv6hdr *iph = skb->nh.ipv6h;
+
+		if (xfrm_nr == XFRM_MAX_DEPTH)
+			goto drop;
+
+		x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, nexthdr, AF_INET6);
+		if (x == NULL)
+			goto drop;
+		spin_lock(&x->lock);
+		if (unlikely(x->km.state != XFRM_STATE_VALID))
+			goto drop_unlock;
+
+		if (x->props.replay_window && xfrm_replay_check(x, seq))
+			goto drop_unlock;
+
+		if (xfrm_state_check_expire(x))
+			goto drop_unlock;
+
+		nexthdr = x->type->input(x, &(xfrm_vec[xfrm_nr].decap), skb);
+		if (nexthdr <= 0)
+			goto drop_unlock;
+
+		skb->nh.raw[nhoff] = nexthdr;
+
+		if (x->props.replay_window)
+			xfrm_replay_advance(x, seq);
+
+		x->curlft.bytes += skb->len;
+		x->curlft.packets++;
+
+		spin_unlock(&x->lock);
+
+		xfrm_vec[xfrm_nr++].xvec = x;
+
+		if (x->props.mode) { /* XXX */
+			if (nexthdr != IPPROTO_IPV6)
+				goto drop;
+			if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+				goto drop;
+			if (skb_cloned(skb) &&
+			    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+				goto drop;
+			if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+				ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h);
+			if (!(x->props.flags & XFRM_STATE_NOECN))
+				ipip6_ecn_decapsulate(skb);
+			skb->mac.raw = memmove(skb->data - skb->mac_len,
+					       skb->mac.raw, skb->mac_len);
+			skb->nh.raw = skb->data;
+			decaps = 1;
+			break;
+		}
+
+		if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) < 0)
+			goto drop;
+	} while (!err);
+
+	/* Allocate new secpath or COW existing one. */
+	if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
+		struct sec_path *sp;
+		sp = secpath_dup(skb->sp);
+		if (!sp)
+			goto drop;
+		if (skb->sp)
+			secpath_put(skb->sp);
+		skb->sp = sp;
+	}
+
+	if (xfrm_nr + skb->sp->len > XFRM_MAX_DEPTH)
+		goto drop;
+
+	memcpy(skb->sp->x+skb->sp->len, xfrm_vec, xfrm_nr*sizeof(struct sec_decap_state));
+	skb->sp->len += xfrm_nr;
+	skb->ip_summed = CHECKSUM_NONE;
+
+	if (decaps) {
+		if (!(skb->dev->flags&IFF_LOOPBACK)) {
+			dst_release(skb->dst);
+			skb->dst = NULL;
+		}
+		netif_rx(skb);
+		return -1;
+	} else {
+		return 1;
+	}
+
+drop_unlock:
+	spin_unlock(&x->lock);
+	xfrm_state_put(x);
+drop:
+	while (--xfrm_nr >= 0)
+		xfrm_state_put(xfrm_vec[xfrm_nr].xvec);
+	kfree_skb(skb);
+	return -1;
+}
+
+EXPORT_SYMBOL(xfrm6_rcv_spi);
+
+int xfrm6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
+{
+	return xfrm6_rcv_spi(pskb, nhoffp, 0);
+}

net/ipv6/xfrm6_output.c

@@ -0,0 +1,143 @@
+/*
+ * xfrm6_output.c - Common IPsec encapsulation code for IPv6.
+ * Copyright (C) 2002 USAGI/WIDE Project
+ * Copyright (c) 2004 Herbert Xu <herbert@gondor.apana.org.au>
+ * 
+ * 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.
+ */
+
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/icmpv6.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+
+/* Add encapsulation header.
+ *
+ * In transport mode, the IP header and mutable extension headers will be moved
+ * forward to make space for the encapsulation header.
+ *
+ * In tunnel mode, the top IP header will be constructed per RFC 2401.
+ * The following fields in it shall be filled in by x->type->output:
+ *	payload_len
+ *
+ * On exit, skb->h will be set to the start of the encapsulation header to be
+ * filled in by x->type->output and skb->nh will be set to the nextheader field
+ * of the extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header.  The value of skb->data will always
+ * point to the top IP header.
+ */
+static void xfrm6_encap(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb->dst;
+	struct xfrm_state *x = dst->xfrm;
+	struct ipv6hdr *iph, *top_iph;
+	int dsfield;
+
+	skb_push(skb, x->props.header_len);
+	iph = skb->nh.ipv6h;
+
+	if (!x->props.mode) {
+		u8 *prevhdr;
+		int hdr_len;
+
+		hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
+		skb->nh.raw = prevhdr - x->props.header_len;
+		skb->h.raw = skb->data + hdr_len;
+		memmove(skb->data, iph, hdr_len);
+		return;
+	}
+
+	skb->nh.raw = skb->data;
+	top_iph = skb->nh.ipv6h;
+	skb->nh.raw = &top_iph->nexthdr;
+	skb->h.ipv6h = top_iph + 1;
+
+	top_iph->version = 6;
+	top_iph->priority = iph->priority;
+	top_iph->flow_lbl[0] = iph->flow_lbl[0];
+	top_iph->flow_lbl[1] = iph->flow_lbl[1];
+	top_iph->flow_lbl[2] = iph->flow_lbl[2];
+	dsfield = ipv6_get_dsfield(top_iph);
+	dsfield = INET_ECN_encapsulate(dsfield, dsfield);
+	if (x->props.flags & XFRM_STATE_NOECN)
+		dsfield &= ~INET_ECN_MASK;
+	ipv6_change_dsfield(top_iph, 0, dsfield);
+	top_iph->nexthdr = IPPROTO_IPV6; 
+	top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
+	ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
+	ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+}
+
+static int xfrm6_tunnel_check_size(struct sk_buff *skb)
+{
+	int mtu, ret = 0;
+	struct dst_entry *dst = skb->dst;
+
+	mtu = dst_mtu(dst);
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+
+	if (skb->len > mtu) {
+		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+		ret = -EMSGSIZE;
+	}
+
+	return ret;
+}
+
+int xfrm6_output(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb->dst;
+	struct xfrm_state *x = dst->xfrm;
+	int err;
+	
+	if (skb->ip_summed == CHECKSUM_HW) {
+		err = skb_checksum_help(skb, 0);
+		if (err)
+			goto error_nolock;
+	}
+
+	if (x->props.mode) {
+		err = xfrm6_tunnel_check_size(skb);
+		if (err)
+			goto error_nolock;
+	}
+
+	spin_lock_bh(&x->lock);
+	err = xfrm_state_check(x, skb);
+	if (err)
+		goto error;
+
+	xfrm6_encap(skb);
+
+	err = x->type->output(x, skb);
+	if (err)
+		goto error;
+
+	x->curlft.bytes += skb->len;
+	x->curlft.packets++;
+
+	spin_unlock_bh(&x->lock);
+
+	skb->nh.raw = skb->data;
+	
+	if (!(skb->dst = dst_pop(dst))) {
+		err = -EHOSTUNREACH;
+		goto error_nolock;
+	}
+	err = NET_XMIT_BYPASS;
+
+out_exit:
+	return err;
+error:
+	spin_unlock_bh(&x->lock);
+error_nolock:
+	kfree_skb(skb);
+	goto out_exit;
+}

net/ipv6/xfrm6_policy.c

@@ -0,0 +1,295 @@
+/*
+ * xfrm6_policy.c: based on xfrm4_policy.c
+ *
+ * Authors:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ * 	YOSHIFUJI Hideaki
+ * 		Split up af-specific portion
+ * 
+ */
+
+#include <linux/config.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+
+static struct dst_ops xfrm6_dst_ops;
+static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
+
+static struct xfrm_type_map xfrm6_type_map = { .lock = RW_LOCK_UNLOCKED };
+
+static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
+{
+	int err = 0;
+	*dst = (struct xfrm_dst*)ip6_route_output(NULL, fl);
+	if (!*dst)
+		err = -ENETUNREACH;
+	return err;
+}
+
+static struct dst_entry *
+__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
+{
+	struct dst_entry *dst;
+
+	/* Still not clear if we should set fl->fl6_{src,dst}... */
+	read_lock_bh(&policy->lock);
+	for (dst = policy->bundles; dst; dst = dst->next) {
+		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
+		struct in6_addr fl_dst_prefix, fl_src_prefix;
+
+		ipv6_addr_prefix(&fl_dst_prefix,
+				 &fl->fl6_dst,
+				 xdst->u.rt6.rt6i_dst.plen);
+		ipv6_addr_prefix(&fl_src_prefix,
+				 &fl->fl6_src,
+				 xdst->u.rt6.rt6i_src.plen);
+		if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
+		    ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
+		    xfrm_bundle_ok(xdst, fl, AF_INET6)) {
+			dst_clone(dst);
+			break;
+		}
+	}
+	read_unlock_bh(&policy->lock);
+	return dst;
+}
+
+/* Allocate chain of dst_entry's, attach known xfrm's, calculate
+ * all the metrics... Shortly, bundle a bundle.
+ */
+
+static int
+__xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx,
+		      struct flowi *fl, struct dst_entry **dst_p)
+{
+	struct dst_entry *dst, *dst_prev;
+	struct rt6_info *rt0 = (struct rt6_info*)(*dst_p);
+	struct rt6_info *rt  = rt0;
+	struct in6_addr *remote = &fl->fl6_dst;
+	struct in6_addr *local  = &fl->fl6_src;
+	struct flowi fl_tunnel = {
+		.nl_u = {
+			.ip6_u = {
+				.saddr = *local,
+				.daddr = *remote
+			}
+		}
+	};
+	int i;
+	int err = 0;
+	int header_len = 0;
+	int trailer_len = 0;
+
+	dst = dst_prev = NULL;
+	dst_hold(&rt->u.dst);
+
+	for (i = 0; i < nx; i++) {
+		struct dst_entry *dst1 = dst_alloc(&xfrm6_dst_ops);
+		struct xfrm_dst *xdst;
+		int tunnel = 0;
+
+		if (unlikely(dst1 == NULL)) {
+			err = -ENOBUFS;
+			dst_release(&rt->u.dst);
+			goto error;
+		}
+
+		if (!dst)
+			dst = dst1;
+		else {
+			dst_prev->child = dst1;
+			dst1->flags |= DST_NOHASH;
+			dst_clone(dst1);
+		}
+
+		xdst = (struct xfrm_dst *)dst1;
+		xdst->route = &rt->u.dst;
+
+		dst1->next = dst_prev;
+		dst_prev = dst1;
+		if (xfrm[i]->props.mode) {
+			remote = (struct in6_addr*)&xfrm[i]->id.daddr;
+			local  = (struct in6_addr*)&xfrm[i]->props.saddr;
+			tunnel = 1;
+		}
+		header_len += xfrm[i]->props.header_len;
+		trailer_len += xfrm[i]->props.trailer_len;
+
+		if (tunnel) {
+			ipv6_addr_copy(&fl_tunnel.fl6_dst, remote);
+			ipv6_addr_copy(&fl_tunnel.fl6_src, local);
+			err = xfrm_dst_lookup((struct xfrm_dst **) &rt,
+					      &fl_tunnel, AF_INET6);
+			if (err)
+				goto error;
+		} else
+			dst_hold(&rt->u.dst);
+	}
+
+	dst_prev->child = &rt->u.dst;
+	dst->path = &rt->u.dst;
+
+	*dst_p = dst;
+	dst = dst_prev;
+
+	dst_prev = *dst_p;
+	i = 0;
+	for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) {
+		struct xfrm_dst *x = (struct xfrm_dst*)dst_prev;
+
+		dst_prev->xfrm = xfrm[i++];
+		dst_prev->dev = rt->u.dst.dev;
+		if (rt->u.dst.dev)
+			dev_hold(rt->u.dst.dev);
+		dst_prev->obsolete	= -1;
+		dst_prev->flags	       |= DST_HOST;
+		dst_prev->lastuse	= jiffies;
+		dst_prev->header_len	= header_len;
+		dst_prev->trailer_len	= trailer_len;
+		memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics));
+
+		/* Copy neighbour for reachability confirmation */
+		dst_prev->neighbour	= neigh_clone(rt->u.dst.neighbour);
+		dst_prev->input		= rt->u.dst.input;
+		dst_prev->output	= xfrm6_output;
+		/* Sheit... I remember I did this right. Apparently,
+		 * it was magically lost, so this code needs audit */
+		x->u.rt6.rt6i_flags    = rt0->rt6i_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL);
+		x->u.rt6.rt6i_metric   = rt0->rt6i_metric;
+		x->u.rt6.rt6i_node     = rt0->rt6i_node;
+		x->u.rt6.rt6i_gateway  = rt0->rt6i_gateway;
+		memcpy(&x->u.rt6.rt6i_gateway, &rt0->rt6i_gateway, sizeof(x->u.rt6.rt6i_gateway)); 
+		x->u.rt6.rt6i_dst      = rt0->rt6i_dst;
+		x->u.rt6.rt6i_src      = rt0->rt6i_src;	
+		header_len -= x->u.dst.xfrm->props.header_len;
+		trailer_len -= x->u.dst.xfrm->props.trailer_len;
+	}
+
+	xfrm_init_pmtu(dst);
+	return 0;
+
+error:
+	if (dst)
+		dst_free(dst);
+	return err;
+}
+
+static inline void
+_decode_session6(struct sk_buff *skb, struct flowi *fl)
+{
+	u16 offset = sizeof(struct ipv6hdr);
+	struct ipv6hdr *hdr = skb->nh.ipv6h;
+	struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+	u8 nexthdr = skb->nh.ipv6h->nexthdr;
+
+	memset(fl, 0, sizeof(struct flowi));
+	ipv6_addr_copy(&fl->fl6_dst, &hdr->daddr);
+	ipv6_addr_copy(&fl->fl6_src, &hdr->saddr);
+
+	while (pskb_may_pull(skb, skb->nh.raw + offset + 1 - skb->data)) {
+		switch (nexthdr) {
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			offset += ipv6_optlen(exthdr);
+			nexthdr = exthdr->nexthdr;
+			exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+			break;
+
+		case IPPROTO_UDP:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+			if (pskb_may_pull(skb, skb->nh.raw + offset + 4 - skb->data)) {
+				u16 *ports = (u16 *)exthdr;
+
+				fl->fl_ip_sport = ports[0];
+				fl->fl_ip_dport = ports[1];
+			}
+			fl->proto = nexthdr;
+			return;
+
+		case IPPROTO_ICMPV6:
+			if (pskb_may_pull(skb, skb->nh.raw + offset + 2 - skb->data)) {
+				u8 *icmp = (u8 *)exthdr;
+
+				fl->fl_icmp_type = icmp[0];
+				fl->fl_icmp_code = icmp[1];
+			}
+			fl->proto = nexthdr;
+			return;
+
+		/* XXX Why are there these headers? */
+		case IPPROTO_AH:
+		case IPPROTO_ESP:
+		case IPPROTO_COMP:
+		default:
+			fl->fl_ipsec_spi = 0;
+			fl->proto = nexthdr;
+			return;
+		};
+	}
+}
+
+static inline int xfrm6_garbage_collect(void)
+{
+	read_lock(&xfrm6_policy_afinfo.lock);
+	xfrm6_policy_afinfo.garbage_collect();
+	read_unlock(&xfrm6_policy_afinfo.lock);
+	return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2);
+}
+
+static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	struct dst_entry *path = xdst->route;
+
+	path->ops->update_pmtu(path, mtu);
+}
+
+static struct dst_ops xfrm6_dst_ops = {
+	.family =		AF_INET6,
+	.protocol =		__constant_htons(ETH_P_IPV6),
+	.gc =			xfrm6_garbage_collect,
+	.update_pmtu =		xfrm6_update_pmtu,
+	.gc_thresh =		1024,
+	.entry_size =		sizeof(struct xfrm_dst),
+};
+
+static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
+	.family =		AF_INET6,
+	.lock = 		RW_LOCK_UNLOCKED,
+	.type_map = 		&xfrm6_type_map,
+	.dst_ops =		&xfrm6_dst_ops,
+	.dst_lookup =		xfrm6_dst_lookup,
+	.find_bundle =		__xfrm6_find_bundle,
+	.bundle_create =	__xfrm6_bundle_create,
+	.decode_session =	_decode_session6,
+};
+
+static void __init xfrm6_policy_init(void)
+{
+	xfrm_policy_register_afinfo(&xfrm6_policy_afinfo);
+}
+
+static void xfrm6_policy_fini(void)
+{
+	xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo);
+}
+
+void __init xfrm6_init(void)
+{
+	xfrm6_policy_init();
+	xfrm6_state_init();
+}
+
+void xfrm6_fini(void)
+{
+	//xfrm6_input_fini();
+	xfrm6_policy_fini();
+	xfrm6_state_fini();
+}

net/ipv6/xfrm6_state.c

@@ -0,0 +1,136 @@
+/*
+ * xfrm6_state.c: based on xfrm4_state.c
+ *
+ * Authors:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ * 	YOSHIFUJI Hideaki @USAGI
+ * 		Split up af-specific portion
+ * 	
+ */
+
+#include <net/xfrm.h>
+#include <linux/pfkeyv2.h>
+#include <linux/ipsec.h>
+#include <net/ipv6.h>
+
+static struct xfrm_state_afinfo xfrm6_state_afinfo;
+
+static void
+__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
+		     struct xfrm_tmpl *tmpl,
+		     xfrm_address_t *daddr, xfrm_address_t *saddr)
+{
+	/* Initialize temporary selector matching only
+	 * to current session. */
+	ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst);
+	ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src);
+	x->sel.dport = xfrm_flowi_dport(fl);
+	x->sel.dport_mask = ~0;
+	x->sel.sport = xfrm_flowi_sport(fl);
+	x->sel.sport_mask = ~0;
+	x->sel.prefixlen_d = 128;
+	x->sel.prefixlen_s = 128;
+	x->sel.proto = fl->proto;
+	x->sel.ifindex = fl->oif;
+	x->id = tmpl->id;
+	if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
+		memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
+	memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
+	if (ipv6_addr_any((struct in6_addr*)&x->props.saddr))
+		memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
+	x->props.mode = tmpl->mode;
+	x->props.reqid = tmpl->reqid;
+	x->props.family = AF_INET6;
+}
+
+static struct xfrm_state *
+__xfrm6_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto)
+{
+	unsigned h = __xfrm6_spi_hash(daddr, spi, proto);
+	struct xfrm_state *x;
+
+	list_for_each_entry(x, xfrm6_state_afinfo.state_byspi+h, byspi) {
+		if (x->props.family == AF_INET6 &&
+		    spi == x->id.spi &&
+		    ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) &&
+		    proto == x->id.proto) {
+			xfrm_state_hold(x);
+			return x;
+		}
+	}
+	return NULL;
+}
+
+static struct xfrm_state *
+__xfrm6_find_acq(u8 mode, u32 reqid, u8 proto, 
+		 xfrm_address_t *daddr, xfrm_address_t *saddr, 
+		 int create)
+{
+	struct xfrm_state *x, *x0;
+	unsigned h = __xfrm6_dst_hash(daddr);
+
+	x0 = NULL;
+
+	list_for_each_entry(x, xfrm6_state_afinfo.state_bydst+h, bydst) {
+		if (x->props.family == AF_INET6 &&
+		    ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) &&
+		    mode == x->props.mode &&
+		    proto == x->id.proto &&
+		    ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)x->props.saddr.a6) &&
+		    reqid == x->props.reqid &&
+		    x->km.state == XFRM_STATE_ACQ &&
+		    !x->id.spi) {
+			    x0 = x;
+			    break;
+		    }
+	}
+	if (!x0 && create && (x0 = xfrm_state_alloc()) != NULL) {
+		ipv6_addr_copy((struct in6_addr *)x0->sel.daddr.a6,
+			       (struct in6_addr *)daddr);
+		ipv6_addr_copy((struct in6_addr *)x0->sel.saddr.a6,
+			       (struct in6_addr *)saddr);
+		x0->sel.prefixlen_d = 128;
+		x0->sel.prefixlen_s = 128;
+		ipv6_addr_copy((struct in6_addr *)x0->props.saddr.a6,
+			       (struct in6_addr *)saddr);
+		x0->km.state = XFRM_STATE_ACQ;
+		ipv6_addr_copy((struct in6_addr *)x0->id.daddr.a6,
+			       (struct in6_addr *)daddr);
+		x0->id.proto = proto;
+		x0->props.family = AF_INET6;
+		x0->props.mode = mode;
+		x0->props.reqid = reqid;
+		x0->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES;
+		xfrm_state_hold(x0);
+		x0->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ;
+		add_timer(&x0->timer);
+		xfrm_state_hold(x0);
+		list_add_tail(&x0->bydst, xfrm6_state_afinfo.state_bydst+h);
+		wake_up(&km_waitq);
+	}
+	if (x0)
+		xfrm_state_hold(x0);
+	return x0;
+}
+
+static struct xfrm_state_afinfo xfrm6_state_afinfo = {
+	.family			= AF_INET6,
+	.lock			= RW_LOCK_UNLOCKED,
+	.init_tempsel		= __xfrm6_init_tempsel,
+	.state_lookup		= __xfrm6_state_lookup,
+	.find_acq		= __xfrm6_find_acq,
+};
+
+void __init xfrm6_state_init(void)
+{
+	xfrm_state_register_afinfo(&xfrm6_state_afinfo);
+}
+
+void xfrm6_state_fini(void)
+{
+	xfrm_state_unregister_afinfo(&xfrm6_state_afinfo);
+}
+

net/ipv6/xfrm6_tunnel.c

@@ -0,0 +1,543 @@
+/*
+ * Copyright (C)2003,2004 USAGI/WIDE Project
+ *
+ * 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.
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Authors	Mitsuru KANDA  <mk@linux-ipv6.org>
+ * 		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *
+ * Based on net/ipv4/xfrm4_tunnel.c
+ *
+ */
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/xfrm.h>
+#include <linux/list.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <linux/ipv6.h>
+#include <linux/icmpv6.h>
+
+#ifdef CONFIG_IPV6_XFRM6_TUNNEL_DEBUG
+# define X6TDEBUG	3
+#else
+# define X6TDEBUG	1
+#endif
+
+#define X6TPRINTK(fmt, args...)		printk(fmt, ## args)
+#define X6TNOPRINTK(fmt, args...)	do { ; } while(0)
+
+#if X6TDEBUG >= 1
+# define X6TPRINTK1	X6TPRINTK
+#else
+# define X6TPRINTK1	X6TNOPRINTK
+#endif
+
+#if X6TDEBUG >= 3
+# define X6TPRINTK3	X6TPRINTK
+#else
+# define X6TPRINTK3	X6TNOPRINTK
+#endif
+
+/*
+ * xfrm_tunnel_spi things are for allocating unique id ("spi") 
+ * per xfrm_address_t.
+ */
+struct xfrm6_tunnel_spi {
+	struct hlist_node list_byaddr;
+	struct hlist_node list_byspi;
+	xfrm_address_t addr;
+	u32 spi;
+	atomic_t refcnt;
+#ifdef XFRM6_TUNNEL_SPI_MAGIC
+	u32 magic;
+#endif
+};
+
+#ifdef CONFIG_IPV6_XFRM6_TUNNEL_DEBUG
+# define XFRM6_TUNNEL_SPI_MAGIC 0xdeadbeef
+#endif
+
+static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock);
+
+static u32 xfrm6_tunnel_spi;
+
+#define XFRM6_TUNNEL_SPI_MIN	1
+#define XFRM6_TUNNEL_SPI_MAX	0xffffffff
+
+static kmem_cache_t *xfrm6_tunnel_spi_kmem;
+
+#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256
+#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256
+
+static struct hlist_head xfrm6_tunnel_spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE];
+static struct hlist_head xfrm6_tunnel_spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE];
+
+#ifdef XFRM6_TUNNEL_SPI_MAGIC
+static int x6spi_check_magic(const struct xfrm6_tunnel_spi *x6spi,
+			     const char *name)
+{
+	if (unlikely(x6spi->magic != XFRM6_TUNNEL_SPI_MAGIC)) {
+		X6TPRINTK3(KERN_DEBUG "%s(): x6spi object "
+				      "at %p has corrupted magic %08x "
+				      "(should be %08x)\n",
+			   name, x6spi, x6spi->magic, XFRM6_TUNNEL_SPI_MAGIC);
+		return -1;
+	}
+	return 0;
+}
+#else
+static int inline x6spi_check_magic(const struct xfrm6_tunnel_spi *x6spi,
+				    const char *name)
+{
+	return 0;
+}
+#endif
+
+#define X6SPI_CHECK_MAGIC(x6spi) x6spi_check_magic((x6spi), __FUNCTION__)
+
+
+static unsigned inline xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr)
+{
+	unsigned h;
+
+	X6TPRINTK3(KERN_DEBUG "%s(addr=%p)\n", __FUNCTION__, addr);
+
+	h = addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3];
+	h ^= h >> 16;
+	h ^= h >> 8;
+	h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1;
+
+	X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, h);
+
+	return h;
+}
+
+static unsigned inline xfrm6_tunnel_spi_hash_byspi(u32 spi)
+{
+	return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE;
+}
+
+
+static int xfrm6_tunnel_spi_init(void)
+{
+	int i;
+
+	X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__);
+
+	xfrm6_tunnel_spi = 0;
+	xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi",
+						  sizeof(struct xfrm6_tunnel_spi),
+						  0, SLAB_HWCACHE_ALIGN,
+						  NULL, NULL);
+	if (!xfrm6_tunnel_spi_kmem) {
+		X6TPRINTK1(KERN_ERR
+			   "%s(): failed to allocate xfrm6_tunnel_spi_kmem\n",
+		           __FUNCTION__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
+		INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byaddr[i]);
+	for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++)
+		INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byspi[i]);
+	return 0;
+}
+
+static void xfrm6_tunnel_spi_fini(void)
+{
+	int i;
+
+	X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__);
+
+	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) {
+		if (!hlist_empty(&xfrm6_tunnel_spi_byaddr[i]))
+			goto err;
+	}
+	for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) {
+		if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i]))
+			goto err;
+	}
+	kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
+	xfrm6_tunnel_spi_kmem = NULL;
+	return;
+err:
+	X6TPRINTK1(KERN_ERR "%s(): table is not empty\n", __FUNCTION__);
+	return;
+}
+
+static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
+{
+	struct xfrm6_tunnel_spi *x6spi;
+	struct hlist_node *pos;
+
+	X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr);
+
+	hlist_for_each_entry(x6spi, pos,
+			     &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
+			     list_byaddr) {
+		if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) {
+			X6SPI_CHECK_MAGIC(x6spi);
+			X6TPRINTK3(KERN_DEBUG "%s() = %p(%u)\n", __FUNCTION__, x6spi, x6spi->spi);
+			return x6spi;
+		}
+	}
+
+	X6TPRINTK3(KERN_DEBUG "%s() = NULL(0)\n", __FUNCTION__);
+	return NULL;
+}
+
+u32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
+{
+	struct xfrm6_tunnel_spi *x6spi;
+	u32 spi;
+
+	X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr);
+
+	read_lock_bh(&xfrm6_tunnel_spi_lock);
+	x6spi = __xfrm6_tunnel_spi_lookup(saddr);
+	spi = x6spi ? x6spi->spi : 0;
+	read_unlock_bh(&xfrm6_tunnel_spi_lock);
+	return spi;
+}
+
+EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup);
+
+static u32 __xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
+{
+	u32 spi;
+	struct xfrm6_tunnel_spi *x6spi;
+	struct hlist_node *pos;
+	unsigned index;
+
+	X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr);
+
+	if (xfrm6_tunnel_spi < XFRM6_TUNNEL_SPI_MIN ||
+	    xfrm6_tunnel_spi >= XFRM6_TUNNEL_SPI_MAX)
+		xfrm6_tunnel_spi = XFRM6_TUNNEL_SPI_MIN;
+	else
+		xfrm6_tunnel_spi++;
+
+	for (spi = xfrm6_tunnel_spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) {
+		index = xfrm6_tunnel_spi_hash_byspi(spi);
+		hlist_for_each_entry(x6spi, pos, 
+				     &xfrm6_tunnel_spi_byspi[index], 
+				     list_byspi) {
+			if (x6spi->spi == spi)
+				goto try_next_1;
+		}
+		xfrm6_tunnel_spi = spi;
+		goto alloc_spi;
+try_next_1:;
+	}
+	for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tunnel_spi; spi++) {
+		index = xfrm6_tunnel_spi_hash_byspi(spi);
+		hlist_for_each_entry(x6spi, pos, 
+				     &xfrm6_tunnel_spi_byspi[index], 
+				     list_byspi) {
+			if (x6spi->spi == spi)
+				goto try_next_2;
+		}
+		xfrm6_tunnel_spi = spi;
+		goto alloc_spi;
+try_next_2:;
+	}
+	spi = 0;
+	goto out;
+alloc_spi:
+	X6TPRINTK3(KERN_DEBUG "%s(): allocate new spi for "
+			      "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", 
+			      __FUNCTION__, 
+			      NIP6(*(struct in6_addr *)saddr));
+	x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, SLAB_ATOMIC);
+	if (!x6spi) {
+		X6TPRINTK1(KERN_ERR "%s(): kmem_cache_alloc() failed\n", 
+			   __FUNCTION__);
+		goto out;
+	}
+#ifdef XFRM6_TUNNEL_SPI_MAGIC
+	x6spi->magic = XFRM6_TUNNEL_SPI_MAGIC;
+#endif
+	memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr));
+	x6spi->spi = spi;
+	atomic_set(&x6spi->refcnt, 1);
+
+	hlist_add_head(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]);
+
+	index = xfrm6_tunnel_spi_hash_byaddr(saddr);
+	hlist_add_head(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]);
+	X6SPI_CHECK_MAGIC(x6spi);
+out:
+	X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, spi);
+	return spi;
+}
+
+u32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
+{
+	struct xfrm6_tunnel_spi *x6spi;
+	u32 spi;
+
+	X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr);
+
+	write_lock_bh(&xfrm6_tunnel_spi_lock);
+	x6spi = __xfrm6_tunnel_spi_lookup(saddr);
+	if (x6spi) {
+		atomic_inc(&x6spi->refcnt);
+		spi = x6spi->spi;
+	} else
+		spi = __xfrm6_tunnel_alloc_spi(saddr);
+	write_unlock_bh(&xfrm6_tunnel_spi_lock);
+
+	X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, spi);
+
+	return spi;
+}
+
+EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi);
+
+void xfrm6_tunnel_free_spi(xfrm_address_t *saddr)
+{
+	struct xfrm6_tunnel_spi *x6spi;
+	struct hlist_node *pos, *n;
+
+	X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr);
+
+	write_lock_bh(&xfrm6_tunnel_spi_lock);
+
+	hlist_for_each_entry_safe(x6spi, pos, n, 
+				  &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
+				  list_byaddr)
+	{
+		if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) {
+			X6TPRINTK3(KERN_DEBUG "%s(): x6spi object "
+					      "for %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x "
+					      "found at %p\n",
+				   __FUNCTION__, 
+				   NIP6(*(struct in6_addr *)saddr),
+				   x6spi);
+			X6SPI_CHECK_MAGIC(x6spi);
+			if (atomic_dec_and_test(&x6spi->refcnt)) {
+				hlist_del(&x6spi->list_byaddr);
+				hlist_del(&x6spi->list_byspi);
+				kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi);
+				break;
+			}
+		}
+	}
+	write_unlock_bh(&xfrm6_tunnel_spi_lock);
+}
+
+EXPORT_SYMBOL(xfrm6_tunnel_free_spi);
+
+static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipv6hdr *top_iph;
+
+	top_iph = (struct ipv6hdr *)skb->data;
+	top_iph->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
+	return 0;
+}
+
+static int xfrm6_tunnel_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
+{
+	return 0;
+}
+
+static struct xfrm6_tunnel *xfrm6_tunnel_handler;
+static DECLARE_MUTEX(xfrm6_tunnel_sem);
+
+int xfrm6_tunnel_register(struct xfrm6_tunnel *handler)
+{
+	int ret;
+
+	down(&xfrm6_tunnel_sem);
+	ret = 0;
+	if (xfrm6_tunnel_handler != NULL)
+		ret = -EINVAL;
+	if (!ret)
+		xfrm6_tunnel_handler = handler;
+	up(&xfrm6_tunnel_sem);
+
+	return ret;
+}
+
+EXPORT_SYMBOL(xfrm6_tunnel_register);
+
+int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler)
+{
+	int ret;
+
+	down(&xfrm6_tunnel_sem);
+	ret = 0;
+	if (xfrm6_tunnel_handler != handler)
+		ret = -EINVAL;
+	if (!ret)
+		xfrm6_tunnel_handler = NULL;
+	up(&xfrm6_tunnel_sem);
+
+	synchronize_net();
+
+	return ret;
+}
+
+EXPORT_SYMBOL(xfrm6_tunnel_deregister);
+
+static int xfrm6_tunnel_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
+{
+	struct sk_buff *skb = *pskb;
+	struct xfrm6_tunnel *handler = xfrm6_tunnel_handler;
+	struct ipv6hdr *iph = skb->nh.ipv6h;
+	u32 spi;
+
+	/* device-like_ip6ip6_handler() */
+	if (handler && handler->handler(pskb, nhoffp) == 0)
+		return 0;
+
+	spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr);
+	return xfrm6_rcv_spi(pskb, nhoffp, spi);
+}
+
+static void xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			     int type, int code, int offset, __u32 info)
+{
+	struct xfrm6_tunnel *handler = xfrm6_tunnel_handler;
+
+	/* call here first for device-like ip6ip6 err handling */
+	if (handler) {
+		handler->err_handler(skb, opt, type, code, offset, info);
+		return;
+	}
+
+	/* xfrm6_tunnel native err handling */
+	switch (type) {
+	case ICMPV6_DEST_UNREACH: 
+		switch (code) {
+		case ICMPV6_NOROUTE: 
+		case ICMPV6_ADM_PROHIBITED:
+		case ICMPV6_NOT_NEIGHBOUR:
+		case ICMPV6_ADDR_UNREACH:
+		case ICMPV6_PORT_UNREACH:
+		default:
+			X6TPRINTK3(KERN_DEBUG
+				   "xfrm6_tunnel: Destination Unreach.\n");
+			break;
+		}
+		break;
+	case ICMPV6_PKT_TOOBIG:
+			X6TPRINTK3(KERN_DEBUG 
+				   "xfrm6_tunnel: Packet Too Big.\n");
+		break;
+	case ICMPV6_TIME_EXCEED:
+		switch (code) {
+		case ICMPV6_EXC_HOPLIMIT:
+			X6TPRINTK3(KERN_DEBUG
+				   "xfrm6_tunnel: Too small Hoplimit.\n");
+			break;
+		case ICMPV6_EXC_FRAGTIME:
+		default: 
+			break;
+		}
+		break;
+	case ICMPV6_PARAMPROB:
+		switch (code) {
+		case ICMPV6_HDR_FIELD: break;
+		case ICMPV6_UNK_NEXTHDR: break;
+		case ICMPV6_UNK_OPTION: break;
+		}
+		break;
+	default:
+		break;
+	}
+	return;
+}
+
+static int xfrm6_tunnel_init_state(struct xfrm_state *x, void *args)
+{
+	if (!x->props.mode)
+		return -EINVAL;
+
+	if (x->encap)
+		return -EINVAL;
+
+	x->props.header_len = sizeof(struct ipv6hdr);
+
+	return 0;
+}
+
+static void xfrm6_tunnel_destroy(struct xfrm_state *x)
+{
+	xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr);
+}
+
+static struct xfrm_type xfrm6_tunnel_type = {
+	.description	= "IP6IP6",
+	.owner          = THIS_MODULE,
+	.proto		= IPPROTO_IPV6,
+	.init_state	= xfrm6_tunnel_init_state,
+	.destructor	= xfrm6_tunnel_destroy,
+	.input		= xfrm6_tunnel_input,
+	.output		= xfrm6_tunnel_output,
+};
+
+static struct inet6_protocol xfrm6_tunnel_protocol = {
+	.handler	= xfrm6_tunnel_rcv,
+	.err_handler	= xfrm6_tunnel_err, 
+	.flags          = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
+};
+
+static int __init xfrm6_tunnel_init(void)
+{
+	X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__);
+
+	if (xfrm_register_type(&xfrm6_tunnel_type, AF_INET6) < 0) {
+		X6TPRINTK1(KERN_ERR
+			   "xfrm6_tunnel init: can't add xfrm type\n");
+		return -EAGAIN;
+	}
+	if (inet6_add_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6) < 0) {
+		X6TPRINTK1(KERN_ERR
+			   "xfrm6_tunnel init(): can't add protocol\n");
+		xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
+		return -EAGAIN;
+	}
+	if (xfrm6_tunnel_spi_init() < 0) {
+		X6TPRINTK1(KERN_ERR
+			   "xfrm6_tunnel init: failed to initialize spi\n");
+		inet6_del_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6);
+		xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
+		return -EAGAIN;
+	}
+	return 0;
+}
+
+static void __exit xfrm6_tunnel_fini(void)
+{
+	X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__);
+
+	xfrm6_tunnel_spi_fini();
+	if (inet6_del_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6) < 0)
+		X6TPRINTK1(KERN_ERR 
+			   "xfrm6_tunnel close: can't remove protocol\n");
+	if (xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6) < 0)
+		X6TPRINTK1(KERN_ERR
+			   "xfrm6_tunnel close: can't remove xfrm type\n");
+}
+
+module_init(xfrm6_tunnel_init);
+module_exit(xfrm6_tunnel_fini);
+MODULE_LICENSE("GPL");