*
* 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
#include <asm/uaccess.h>
#include <asm/system.h>
+#include <linux/mroute6.h>
MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
-int sysctl_ipv6_bindv6only __read_mostly;
-
/* The inetsw6 table contains everything that inet6_create needs to
* build a new socket.
*/
int try_loading_module = 0;
int err;
- if (net != &init_net)
- return -EAFNOSUPPORT;
-
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
np->mcast_hops = -1;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->ipv6only = sysctl_ipv6_bindv6only;
+ np->ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
* using v6 API for ipv4.
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct net *net = sock_net(sk);
__be32 v4addr = 0;
unsigned short snum;
int addr_type = 0;
/* 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) {
+ if (inet_addr_type(net, v4addr) != RTN_LOCAL) {
err = -EADDRNOTAVAIL;
goto out;
}
err = -EINVAL;
goto out;
}
- dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
if (!dev) {
err = -ENODEV;
goto out;
*/
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST)) {
- if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) {
+ if (!ipv6_chk_addr(net, &addr->sin6_addr,
+ dev, 0)) {
if (dev)
dev_put(dev);
err = -EADDRNOTAVAIL;
EXPORT_SYMBOL(inet6_release);
-int inet6_destroy_sock(struct sock *sk)
+void inet6_destroy_sock(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
if ((opt = xchg(&np->opt, NULL)) != NULL)
sock_kfree_s(sk, opt, opt->tot_len);
-
- return 0;
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
switch(cmd)
{
case SIOCADDRT:
case SIOCDELRT:
- return(ipv6_route_ioctl(cmd,(void __user *)arg));
+ return(ipv6_route_ioctl(net, cmd, (void __user *)arg));
case SIOCSIFADDR:
- return addrconf_add_ifaddr((void __user *) arg);
+ return addrconf_add_ifaddr(net, (void __user *) arg);
case SIOCDIFADDR:
- return addrconf_del_ifaddr((void __user *) arg);
+ return addrconf_del_ifaddr(net, (void __user *) arg);
case SIOCSIFDSTADDR:
- return addrconf_set_dstaddr((void __user *) arg);
+ return addrconf_set_dstaddr(net, (void __user *) arg);
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
.owner = THIS_MODULE,
};
-/* Same as inet6_dgram_ops, sans udp_poll. */
-static const 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,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
-#endif
-};
-
-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)
+int inet6_register_protosw(struct inet_protosw *p)
{
struct list_head *lh;
struct inet_protosw *answer;
- int protocol = p->protocol;
struct list_head *last_perm;
+ int protocol = p->protocol;
+ int ret;
spin_lock_bh(&inetsw6_lock);
+ ret = -EINVAL;
if (p->type >= SOCK_MAX)
goto out_illegal;
/* If we are trying to override a permanent protocol, bail. */
answer = NULL;
+ ret = -EPERM;
last_perm = &inetsw6[p->type];
list_for_each(lh, &inetsw6[p->type]) {
answer = list_entry(lh, struct inet_protosw, list);
* system automatically returns to the old behavior.
*/
list_add_rcu(&p->list, last_perm);
+ ret = 0;
out:
spin_unlock_bh(&inetsw6_lock);
- return;
+ return ret;
out_permanent:
printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
+static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb,
+ int proto)
+{
+ struct inet6_protocol *ops = NULL;
+
+ for (;;) {
+ struct ipv6_opt_hdr *opth;
+ int len;
+
+ if (proto != NEXTHDR_HOP) {
+ ops = rcu_dereference(inet6_protos[proto]);
+
+ if (unlikely(!ops))
+ break;
+
+ if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
+ break;
+ }
+
+ if (unlikely(!pskb_may_pull(skb, 8)))
+ break;
+
+ opth = (void *)skb->data;
+ len = ipv6_optlen(opth);
+
+ if (unlikely(!pskb_may_pull(skb, len)))
+ break;
+
+ proto = opth->nexthdr;
+ __skb_pull(skb, len);
+ }
+
+ return ops;
+}
+
+static int ipv6_gso_send_check(struct sk_buff *skb)
+{
+ struct ipv6hdr *ipv6h;
+ struct inet6_protocol *ops;
+ int err = -EINVAL;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+ goto out;
+
+ ipv6h = ipv6_hdr(skb);
+ __skb_pull(skb, sizeof(*ipv6h));
+ err = -EPROTONOSUPPORT;
+
+ rcu_read_lock();
+ ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (likely(ops && ops->gso_send_check)) {
+ skb_reset_transport_header(skb);
+ err = ops->gso_send_check(skb);
+ }
+ rcu_read_unlock();
+
+out:
+ return err;
+}
+
+static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ struct ipv6hdr *ipv6h;
+ struct inet6_protocol *ops;
+
+ if (!(features & NETIF_F_V6_CSUM))
+ features &= ~NETIF_F_SG;
+
+ if (unlikely(skb_shinfo(skb)->gso_type &
+ ~(SKB_GSO_UDP |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_TCPV6 |
+ 0)))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+ goto out;
+
+ ipv6h = ipv6_hdr(skb);
+ __skb_pull(skb, sizeof(*ipv6h));
+ segs = ERR_PTR(-EPROTONOSUPPORT);
+
+ rcu_read_lock();
+ ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (likely(ops && ops->gso_segment)) {
+ skb_reset_transport_header(skb);
+ segs = ops->gso_segment(skb, features);
+ }
+ rcu_read_unlock();
+
+ if (unlikely(IS_ERR(segs)))
+ goto out;
+
+ for (skb = segs; skb; skb = skb->next) {
+ ipv6h = ipv6_hdr(skb);
+ ipv6h->payload_len = htons(skb->len - skb->mac_len -
+ sizeof(*ipv6h));
+ }
+
+out:
+ return segs;
+}
+
+static struct packet_type ipv6_packet_type = {
+ .type = __constant_htons(ETH_P_IPV6),
+ .func = ipv6_rcv,
+ .gso_send_check = ipv6_gso_send_check,
+ .gso_segment = ipv6_gso_segment,
+};
+
+static int __init ipv6_packet_init(void)
+{
+ dev_add_pack(&ipv6_packet_type);
+ return 0;
+}
+
+static void ipv6_packet_cleanup(void)
+{
+ dev_remove_pack(&ipv6_packet_type);
+}
+
static int __init init_ipv6_mibs(void)
{
if (snmp_mib_init((void **)ipv6_statistics,
snmp_mib_free((void **)udplite_stats_in6);
}
+static int inet6_net_init(struct net *net)
+{
+ int err = 0;
+
+ net->ipv6.sysctl.bindv6only = 0;
+ net->ipv6.sysctl.flush_delay = 0;
+ net->ipv6.sysctl.ip6_rt_max_size = 4096;
+ net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
+ net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
+ net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
+ net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
+ net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
+ net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
+ net->ipv6.sysctl.icmpv6_time = 1*HZ;
+
+#ifdef CONFIG_PROC_FS
+ err = udp6_proc_init(net);
+ if (err)
+ goto out;
+ err = tcp6_proc_init(net);
+ if (err)
+ goto proc_tcp6_fail;
+ err = ac6_proc_init(net);
+ if (err)
+ goto proc_ac6_fail;
+out:
+#endif
+ return err;
+
+#ifdef CONFIG_PROC_FS
+proc_ac6_fail:
+ tcp6_proc_exit(net);
+proc_tcp6_fail:
+ udp6_proc_exit(net);
+ goto out;
+#endif
+}
+
+static void inet6_net_exit(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+ udp6_proc_exit(net);
+ tcp6_proc_exit(net);
+ ac6_proc_exit(net);
+#endif
+}
+
+static struct pernet_operations inet6_net_ops = {
+ .init = inet6_net_init,
+ .exit = inet6_net_exit,
+};
+
static int __init inet6_init(void)
{
struct sk_buff *dummy_skb;
BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb));
-#ifdef MODULE
-#if 0 /* FIXME --RR */
- if (!mod_member_present(&__this_module, can_unload))
- return -EINVAL;
-
- __this_module.can_unload = &ipv6_unload;
-#endif
-#endif
-
err = proto_register(&tcpv6_prot, 1);
if (err)
goto out;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
*/
- inet6_register_protosw(&rawv6_protosw);
+ err = rawv6_init();
+ if (err)
+ goto out_unregister_raw_proto;
/* Register the family here so that the init calls below will
* be able to create sockets. (?? is this dangerous ??)
*/
err = sock_register(&inet6_family_ops);
if (err)
- goto out_unregister_raw_proto;
+ goto out_sock_register_fail;
/* Initialise ipv6 mibs */
err = init_ipv6_mibs();
* able to communicate via both network protocols.
*/
-#ifdef CONFIG_SYSCTL
- ipv6_sysctl_register();
-#endif
- err = icmpv6_init(&inet6_family_ops);
+ err = register_pernet_subsys(&inet6_net_ops);
+ if (err)
+ goto register_pernet_fail;
+ err = icmpv6_init();
if (err)
goto icmp_fail;
- err = ndisc_init(&inet6_family_ops);
+ err = ip6_mr_init();
+ if (err)
+ goto ipmr_fail;
+ err = ndisc_init();
if (err)
goto ndisc_fail;
- err = igmp6_init(&inet6_family_ops);
+ err = igmp6_init();
if (err)
goto igmp_fail;
err = ipv6_netfilter_init();
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 (udplite6_proc_init())
goto proc_udplite6_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
err = ip6_route_init();
if (err)
goto ip6_route_fail;
- ip6_flowlabel_init();
+ err = ip6_flowlabel_init();
+ if (err)
+ goto ip6_flowlabel_fail;
err = addrconf_init();
if (err)
goto addrconf_fail;
/* Init v6 extension headers. */
- ipv6_rthdr_init();
- ipv6_frag_init();
- ipv6_nodata_init();
- ipv6_destopt_init();
+ err = ipv6_exthdrs_init();
+ if (err)
+ goto ipv6_exthdrs_fail;
+
+ err = ipv6_frag_init();
+ if (err)
+ goto ipv6_frag_fail;
/* Init v6 transport protocols. */
- udpv6_init();
- udplitev6_init();
- tcpv6_init();
+ err = udpv6_init();
+ if (err)
+ goto udpv6_fail;
- ipv6_packet_init();
- err = 0;
+ err = udplitev6_init();
+ if (err)
+ goto udplitev6_fail;
+
+ err = tcpv6_init();
+ if (err)
+ goto tcpv6_fail;
+
+ err = ipv6_packet_init();
+ if (err)
+ goto ipv6_packet_fail;
+
+#ifdef CONFIG_SYSCTL
+ err = ipv6_sysctl_register();
+ if (err)
+ goto sysctl_fail;
+#endif
out:
return err;
+#ifdef CONFIG_SYSCTL
+sysctl_fail:
+ ipv6_packet_cleanup();
+#endif
+ipv6_packet_fail:
+ tcpv6_exit();
+tcpv6_fail:
+ udplitev6_exit();
+udplitev6_fail:
+ udpv6_exit();
+udpv6_fail:
+ ipv6_frag_exit();
+ipv6_frag_fail:
+ ipv6_exthdrs_exit();
+ipv6_exthdrs_fail:
+ addrconf_cleanup();
addrconf_fail:
ip6_flowlabel_cleanup();
+ip6_flowlabel_fail:
ip6_route_cleanup();
ip6_route_fail:
#ifdef CONFIG_PROC_FS
if6_proc_exit();
proc_if6_fail:
- ac6_proc_exit();
-proc_anycast6_fail:
ipv6_misc_proc_exit();
proc_misc6_fail:
udplite6_proc_exit();
proc_udplite6_fail:
- udp6_proc_exit();
-proc_udp6_fail:
- tcp6_proc_exit();
-proc_tcp6_fail:
raw6_proc_exit();
proc_raw6_fail:
#endif
igmp_fail:
ndisc_cleanup();
ndisc_fail:
+ ip6_mr_cleanup();
+ipmr_fail:
icmpv6_cleanup();
icmp_fail:
-#ifdef CONFIG_SYSCTL
- ipv6_sysctl_unregister();
-#endif
+ unregister_pernet_subsys(&inet6_net_ops);
+register_pernet_fail:
cleanup_ipv6_mibs();
out_unregister_sock:
sock_unregister(PF_INET6);
rtnl_unregister_all(PF_INET6);
+out_sock_register_fail:
+ rawv6_exit();
out_unregister_raw_proto:
proto_unregister(&rawv6_prot);
out_unregister_udplite_proto:
/* Disallow any further netlink messages */
rtnl_unregister_all(PF_INET6);
+#ifdef CONFIG_SYSCTL
+ ipv6_sysctl_unregister();
+#endif
+ udpv6_exit();
+ udplitev6_exit();
+ tcpv6_exit();
+
/* Cleanup code parts. */
ipv6_packet_cleanup();
-
+ ipv6_frag_exit();
+ ipv6_exthdrs_exit();
addrconf_cleanup();
ip6_flowlabel_cleanup();
ip6_route_cleanup();
/* Cleanup code parts. */
if6_proc_exit();
- ac6_proc_exit();
ipv6_misc_proc_exit();
udplite6_proc_exit();
- udp6_proc_exit();
- tcp6_proc_exit();
raw6_proc_exit();
#endif
ipv6_netfilter_fini();
igmp6_cleanup();
ndisc_cleanup();
+ ip6_mr_cleanup();
icmpv6_cleanup();
-#ifdef CONFIG_SYSCTL
- ipv6_sysctl_unregister();
-#endif
+ rawv6_exit();
+
+ unregister_pernet_subsys(&inet6_net_ops);
cleanup_ipv6_mibs();
proto_unregister(&rawv6_prot);
proto_unregister(&udplitev6_prot);