/*
* PF_INET6 socket protocol family
- * Linux INET6 implementation
+ * Linux INET6 implementation
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
+ * Pedro Roque <roque@di.fc.ul.pt>
*
* Adapted from linux/net/ipv4/af_inet.c
*
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>
-#include <linux/smp_lock.h>
#include <linux/netfilter_ipv6.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/udp.h>
+#include <net/udplite.h>
#include <net/tcp.h>
#include <net/ipip.h>
#include <net/protocol.h>
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
-int sysctl_ipv6_bindv6only;
-
-/* The inetsw table contains everything that inet_create needs to
+/* The inetsw6 table contains everything that inet6_create needs to
* build a new socket.
*/
static struct list_head inetsw6[SOCK_MAX];
return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
-static int inet6_create(struct socket *sock, int protocol)
+static int inet6_create(struct net *net, struct socket *sock, int protocol)
{
struct inet_sock *inet;
struct ipv6_pinfo *np;
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)
+ build_ehash_secret();
+
/* Look for the requested type/protocol pair. */
answer = NULL;
lookup_protocol:
BUG_TRAP(answer_prot->slab != NULL);
err = -ENOBUFS;
- sk = sk_alloc(PF_INET6, GFP_KERNEL, answer_prot, 1);
+ sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
sk->sk_reuse = 1;
inet = inet_sk(sk);
- inet->is_icsk = INET_PROTOSW_ICSK & answer_flags;
+ inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
if (SOCK_RAW == sock->type) {
inet->num = protocol;
np->mcast_hops = -1;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->ipv6only = sysctl_ipv6_bindv6only;
-
+ np->ipv6only = init_net.ipv6.sysctl.bindv6only;
+
/* Init the ipv4 part of the socket since we can have sockets
* using v6 API for ipv4.
*/
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
- /*
+ /*
* Increment only the relevant sk_prot->socks debug field, this changes
* the previous behaviour of incrementing both the equivalent to
* answer->prot->socks (inet6_sock_nr) and inet_sock_nr.
* the user to assign a number at socket
* creation time automatically shares.
*/
- inet->sport = ntohs(inet->num);
+ inet->sport = htons(inet->num);
sk->sk_prot->hash(sk);
}
if (sk->sk_prot->init) {
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
- __u32 v4addr = 0;
+ __be32 v4addr = 0;
unsigned short snum;
int addr_type = 0;
int err = 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(&init_net, v4addr) != RTN_LOCAL) {
err = -EADDRNOTAVAIL;
goto out;
}
*/
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);
+ dev = dev_get_by_index(&init_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(&init_net, &addr->sin6_addr,
+ dev, 0)) {
if (dev)
dev_put(dev);
err = -EADDRNOTAVAIL;
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);
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
- inet->sport = ntohs(inet->num);
+ inet->sport = htons(inet->num);
inet->dport = 0;
inet->daddr = 0;
out:
return err;
}
+EXPORT_SYMBOL(inet6_bind);
+
int inet6_release(struct socket *sock)
{
struct sock *sk = sock->sk;
return inet_release(sock);
}
+EXPORT_SYMBOL(inet6_release);
+
int inet6_destroy_sock(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
/*
* This does both peername and sockname.
*/
-
+
int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
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;
return(0);
}
+EXPORT_SYMBOL(inet6_getname);
+
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
- switch(cmd)
+ switch(cmd)
{
case SIOCGSTAMP:
return sock_get_timestamp(sk, (struct timeval __user *)arg);
+ case SIOCGSTAMPNS:
+ return sock_get_timestampns(sk, (struct timespec __user *)arg);
+
case SIOCADDRT:
case SIOCDELRT:
-
+
return(ipv6_route_ioctl(cmd,(void __user *)arg));
case SIOCSIFADDR:
return(0);
}
+EXPORT_SYMBOL(inet6_ioctl);
+
const struct proto_ops inet6_stream_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
.getsockopt = sock_common_getsockopt, /* ok */
- .sendmsg = inet_sendmsg, /* ok */
+ .sendmsg = tcp_sendmsg, /* ok */
.recvmsg = sock_common_recvmsg, /* ok */
.mmap = sock_no_mmap,
.sendpage = tcp_sendpage,
+ .splice_read = tcp_splice_read,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
.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);
/* 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
+ * 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);
+ ret = 0;
out:
spin_unlock_bh(&inetsw6_lock);
- return;
+ return ret;
out_permanent:
printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
goto out;
}
+EXPORT_SYMBOL(inet6_register_protosw);
+
void
inet6_unregister_protosw(struct inet_protosw *p)
{
}
}
+EXPORT_SYMBOL(inet6_unregister_protosw);
+
int inet6_sk_rebuild_header(struct sock *sk)
{
int err;
return err;
}
- __ip6_dst_store(sk, dst, NULL);
+ __ip6_dst_store(sk, dst, NULL, NULL);
}
return 0;
if (np->rxopt.all) {
if ((opt->hop && (np->rxopt.bits.hopopts ||
np->rxopt.bits.ohopopts)) ||
- ((IPV6_FLOWINFO_MASK & *(u32*)skb->nh.raw) &&
+ ((IPV6_FLOWINFO_MASK &
+ *(__be32 *)skb_network_header(skb)) &&
np->rxopt.bits.rxflow) ||
(opt->srcrt && (np->rxopt.bits.srcrt ||
np->rxopt.bits.osrcrt)) ||
EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
-int
-snmp6_mib_init(void *ptr[2], size_t mibsize, size_t mibalign)
-{
- if (ptr == NULL)
- return -EINVAL;
-
- ptr[0] = __alloc_percpu(mibsize);
- if (!ptr[0])
- goto err0;
-
- ptr[1] = __alloc_percpu(mibsize);
- 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)
+ if (snmp_mib_init((void **)ipv6_statistics,
+ sizeof(struct ipstats_mib)) < 0)
goto err_ip_mib;
- if (snmp6_mib_init((void **)icmpv6_statistics, sizeof (struct icmpv6_mib),
- __alignof__(struct icmpv6_mib)) < 0)
+ if (snmp_mib_init((void **)icmpv6_statistics,
+ sizeof(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)
+ if (snmp_mib_init((void **)icmpv6msg_statistics,
+ sizeof(struct icmpv6msg_mib)) < 0)
+ goto err_icmpmsg_mib;
+ if (snmp_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib)) < 0)
goto err_udp_mib;
+ if (snmp_mib_init((void **)udplite_stats_in6,
+ sizeof (struct udp_mib)) < 0)
+ goto err_udplite_mib;
return 0;
+err_udplite_mib:
+ snmp_mib_free((void **)udp_stats_in6);
err_udp_mib:
- snmp6_mib_free((void **)icmpv6_statistics);
+ snmp_mib_free((void **)icmpv6msg_statistics);
+err_icmpmsg_mib:
+ snmp_mib_free((void **)icmpv6_statistics);
err_icmp_mib:
- snmp6_mib_free((void **)ipv6_statistics);
+ snmp_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);
+ snmp_mib_free((void **)ipv6_statistics);
+ snmp_mib_free((void **)icmpv6_statistics);
+ snmp_mib_free((void **)icmpv6msg_statistics);
+ snmp_mib_free((void **)udp_stats_in6);
+ snmp_mib_free((void **)udplite_stats_in6);
}
+static int inet6_net_init(struct net *net)
+{
+ 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;
+
+ return 0;
+}
+
+static void inet6_net_exit(struct net *net)
+{
+ return;
+}
+
+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;
- struct list_head *r;
+ struct list_head *r;
int err;
+ 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))
__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;
if (err)
goto out_unregister_tcp_proto;
- err = proto_register(&rawv6_prot, 1);
+ err = proto_register(&udplitev6_prot, 1);
if (err)
goto out_unregister_udp_proto;
+ err = proto_register(&rawv6_prot, 1);
+ if (err)
+ goto out_unregister_udplite_proto;
+
/* Register the socket-side information for inet6_create. */
for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
/* 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();
if (err)
goto out_unregister_sock;
-
+
/*
* ipngwg API draft makes clear that the correct semantics
* for TCP and UDP is to consider one TCP and UDP instance
* able to communicate via both network protocols.
*/
+ err = register_pernet_subsys(&inet6_net_ops);
+ if (err)
+ goto register_pernet_fail;
+
#ifdef CONFIG_SYSCTL
- ipv6_sysctl_register();
+ err = ipv6_sysctl_register();
+ if (err)
+ goto sysctl_fail;
#endif
err = icmpv6_init(&inet6_family_ops);
if (err)
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 (if6_proc_init())
goto proc_if6_fail;
#endif
- ip6_route_init();
- ip6_flowlabel_init();
+ err = ip6_route_init();
+ if (err)
+ goto ip6_route_fail;
+ err = ip6_flowlabel_init();
+ if (err)
+ goto ip6_flowlabel_fail;
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();
+ 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();
- 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;
out:
return err;
+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:
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();
icmp_fail:
#ifdef CONFIG_SYSCTL
ipv6_sysctl_unregister();
+sysctl_fail:
#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:
+ proto_unregister(&udplitev6_prot);
out_unregister_udp_proto:
proto_unregister(&udpv6_prot);
out_unregister_tcp_proto:
{
/* First of all disallow new sockets creation. */
sock_unregister(PF_INET6);
+ /* Disallow any further netlink messages */
+ rtnl_unregister_all(PF_INET6);
+
+ 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();
#ifdef CONFIG_PROC_FS
+
+ /* Cleanup code parts. */
if6_proc_exit();
ac6_proc_exit();
- ipv6_misc_proc_exit();
- udp6_proc_exit();
- tcp6_proc_exit();
- raw6_proc_exit();
+ ipv6_misc_proc_exit();
+ udplite6_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();
ipv6_netfilter_fini();
+ igmp6_cleanup();
ndisc_cleanup();
icmpv6_cleanup();
+ rawv6_exit();
#ifdef CONFIG_SYSCTL
- ipv6_sysctl_unregister();
+ ipv6_sysctl_unregister();
#endif
+ unregister_pernet_subsys(&inet6_net_ops);
cleanup_ipv6_mibs();
proto_unregister(&rawv6_prot);
+ proto_unregister(&udplitev6_prot);
proto_unregister(&udpv6_prot);
proto_unregister(&tcpv6_prot);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff