#include <linux/module.h>
+#include <linux/capability.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/netdevice.h>
#include <linux/icmpv6.h>
#include <linux/smp_lock.h>
+#include <linux/netfilter_ipv6.h>
#include <net/ip.h>
#include <net/ipv6.h>
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
-
-/* Per protocol sock slabcache */
-kmem_cache_t *tcp6_sk_cachep;
-kmem_cache_t *udp6_sk_cachep;
-kmem_cache_t *raw6_sk_cachep;
-
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
*/
static struct list_head inetsw6[SOCK_MAX];
-static spinlock_t inetsw6_lock = SPIN_LOCK_UNLOCKED;
-
-static void inet6_sock_destruct(struct sock *sk)
-{
- inet_sock_destruct(sk);
-
-#ifdef INET_REFCNT_DEBUG
- atomic_dec(&inet6_sock_nr);
-#endif
-}
-
-static __inline__ kmem_cache_t *inet6_sk_slab(int protocol)
-{
- kmem_cache_t* rc = tcp6_sk_cachep;
-
- if (protocol == IPPROTO_UDP)
- rc = udp6_sk_cachep;
- else if (protocol == IPPROTO_RAW)
- rc = raw6_sk_cachep;
- return rc;
-}
-
-static __inline__ int inet6_sk_size(int protocol)
-{
- int rc = sizeof(struct tcp6_sock);
-
- if (protocol == IPPROTO_UDP)
- rc = sizeof(struct udp6_sock);
- else if (protocol == IPPROTO_RAW)
- rc = sizeof(struct raw6_sock);
- return rc;
-}
+static DEFINE_SPINLOCK(inetsw6_lock);
static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
- struct ipv6_pinfo *rc = (&((struct tcp6_sock *)sk)->inet6);
+ const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
- if (sk->sk_protocol == IPPROTO_UDP)
- rc = (&((struct udp6_sock *)sk)->inet6);
- else if (sk->sk_protocol == IPPROTO_RAW)
- rc = (&((struct raw6_sock *)sk)->inet6);
- return rc;
+ return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
static int inet6_create(struct socket *sock, int protocol)
{
- struct inet_opt *inet;
+ struct inet_sock *inet;
struct ipv6_pinfo *np;
struct sock *sk;
- struct tcp6_sock* tcp6sk;
struct list_head *p;
struct inet_protosw *answer;
-
- sk = sk_alloc(PF_INET6, GFP_KERNEL, inet6_sk_size(protocol),
- inet6_sk_slab(protocol));
- if (sk == NULL)
- goto do_oom;
+ struct proto *answer_prot;
+ unsigned char answer_flags;
+ char answer_no_check;
+ int try_loading_module = 0;
+ int err;
/* Look for the requested type/protocol pair. */
answer = NULL;
+lookup_protocol:
+ err = -ESOCKTNOSUPPORT;
rcu_read_lock();
list_for_each_rcu(p, &inetsw6[sock->type]) {
answer = list_entry(p, struct inet_protosw, list);
if (IPPROTO_IP == answer->protocol)
break;
}
+ err = -EPROTONOSUPPORT;
answer = NULL;
}
- if (!answer)
- goto free_and_badtype;
+ if (!answer) {
+ if (try_loading_module < 2) {
+ rcu_read_unlock();
+ /*
+ * Be more specific, e.g. net-pf-10-proto-132-type-1
+ * (net-pf-PF_INET6-proto-IPPROTO_SCTP-type-SOCK_STREAM)
+ */
+ if (++try_loading_module == 1)
+ request_module("net-pf-%d-proto-%d-type-%d",
+ PF_INET6, protocol, sock->type);
+ /*
+ * Fall back to generic, e.g. net-pf-10-proto-132
+ * (net-pf-PF_INET6-proto-IPPROTO_SCTP)
+ */
+ else
+ request_module("net-pf-%d-proto-%d",
+ PF_INET6, protocol);
+ goto lookup_protocol;
+ } else
+ goto out_rcu_unlock;
+ }
+
+ err = -EPERM;
if (answer->capability > 0 && !capable(answer->capability))
- goto free_and_badperm;
- if (!protocol)
- goto free_and_noproto;
+ 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);
+
+ err = -ENOBUFS;
+ sk = sk_alloc(PF_INET6, GFP_KERNEL, answer_prot, 1);
+ if (sk == NULL)
+ goto out;
+
sock_init_data(sock, sk);
- sk_set_owner(sk, THIS_MODULE);
- sk->sk_prot = answer->prot;
- sk->sk_no_check = answer->no_check;
- if (INET_PROTOSW_REUSE & answer->flags)
+ err = 0;
+ sk->sk_no_check = answer_no_check;
+ if (INET_PROTOSW_REUSE & answer_flags)
sk->sk_reuse = 1;
- rcu_read_unlock();
inet = inet_sk(sk);
+ inet->is_icsk = INET_PROTOSW_ICSK & answer_flags;
if (SOCK_RAW == sock->type) {
inet->num = protocol;
inet->hdrincl = 1;
}
- sk->sk_destruct = inet6_sock_destruct;
- sk->sk_zapped = 0;
+ sk->sk_destruct = inet_sock_destruct;
sk->sk_family = PF_INET6;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = answer->prot->backlog_rcv;
- tcp6sk = (struct tcp6_sock *)sk;
- tcp6sk->pinet6 = np = inet6_sk_generic(sk);
+ inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
np->hop_limit = -1;
np->mcast_hops = -1;
np->mc_loop = 1;
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.
+ *
+ * This allows better debug granularity as we'll know exactly how many
+ * UDPv6, TCPv6, etc socks were allocated, not the sum of all IPv6
+ * transport protocol socks. -acme
+ */
+ sk_refcnt_debug_inc(sk);
-
-#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
sk->sk_prot->hash(sk);
}
if (sk->sk_prot->init) {
- int err = sk->sk_prot->init(sk);
- if (err != 0) {
+ err = sk->sk_prot->init(sk);
+ if (err) {
sk_common_release(sk);
- return err;
+ goto out;
}
}
- return 0;
-
-free_and_badtype:
- rcu_read_unlock();
- sk_free(sk);
- return -ESOCKTNOSUPPORT;
-free_and_badperm:
- rcu_read_unlock();
- sk_free(sk);
- return -EPERM;
-free_and_noproto:
+out:
+ return err;
+out_rcu_unlock:
rcu_read_unlock();
- sk_free(sk);
- return -EPROTONOSUPPORT;
-do_oom:
- return -ENOBUFS;
+ goto out;
}
{
struct sockaddr_in6 *addr=(struct sockaddr_in6 *)uaddr;
struct sock *sk = sock->sk;
- struct inet_opt *inet = inet_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
__u32 v4addr = 0;
unsigned short snum;
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)
return 0;
}
+EXPORT_SYMBOL_GPL(inet6_destroy_sock);
+
/*
* This does both peername and sockname.
*/
{
struct sockaddr_in6 *sin=(struct sockaddr_in6 *)uaddr;
struct sock *sk = sock->sk;
- struct inet_opt *inet = inet_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
sin->sin6_family = AF_INET6;
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
- int err = -EINVAL;
switch(cmd)
{
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;
+ if (!sk->sk_prot->ioctl)
+ return -ENOIOCTLCMD;
+ return sk->sk_prot->ioctl(sk, cmd, arg);
}
/*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
+const 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,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
};
-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 = 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,
+const 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,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
};
static struct net_proto_family inet6_family_ops = {
.owner = THIS_MODULE,
};
-#ifdef CONFIG_SYSCTL
-extern void ipv6_sysctl_register(void);
-extern void ipv6_sysctl_unregister(void);
+/* 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_dgram_ops,
+ .ops = &inet6_sockraw_ops,
.capability = CAP_NET_RAW,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
}
}
+int inet6_sk_rebuild_header(struct sock *sk)
+{
+ int err;
+ struct dst_entry *dst;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ dst = __sk_dst_check(sk, np->dst_cookie);
+
+ if (dst == NULL) {
+ struct inet_sock *inet = inet_sk(sk);
+ struct in6_addr *final_p = NULL, final;
+ struct flowi fl;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.proto = sk->sk_protocol;
+ ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
+ ipv6_addr_copy(&fl.fl6_src, &np->saddr);
+ fl.fl6_flowlabel = np->flow_label;
+ fl.oif = sk->sk_bound_dev_if;
+ fl.fl_ip_dport = inet->dport;
+ fl.fl_ip_sport = inet->sport;
+
+ 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) {
+ sk->sk_route_caps = 0;
+ return err;
+ }
+ if (final_p)
+ ipv6_addr_copy(&fl.fl6_dst, final_p);
+
+ if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
+ sk->sk_err_soft = -err;
+ return err;
+ }
+
+ ip6_dst_store(sk, dst, NULL);
+ sk->sk_route_caps = dst->dev->features &
+ ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+ }
+
+ return 0;
+}
+
+EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header);
+
+int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct inet6_skb_parm *opt = IP6CB(skb);
+
+ if (np->rxopt.all) {
+ if ((opt->hop && (np->rxopt.bits.hopopts ||
+ np->rxopt.bits.ohopopts)) ||
+ ((IPV6_FLOWINFO_MASK & *(u32*)skb->nh.raw) &&
+ np->rxopt.bits.rxflow) ||
+ (opt->srcrt && (np->rxopt.bits.srcrt ||
+ np->rxopt.bits.osrcrt)) ||
+ ((opt->dst1 || opt->dst0) &&
+ (np->rxopt.bits.dstopts || np->rxopt.bits.odstopts)))
+ return 1;
+ }
+ return 0;
+}
+
+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, mibalign);
+ ptr[0] = __alloc_percpu(mibsize);
if (!ptr[0])
goto err0;
- ptr[1] = __alloc_percpu(mibsize, mibalign);
+ ptr[1] = __alloc_percpu(mibsize);
if (!ptr[1])
goto err1;
{
if (ptr == NULL)
return;
- free_percpu(ptr[0]);
- free_percpu(ptr[1]);
+ if (ptr[0])
+ free_percpu(ptr[0]);
+ if (ptr[1])
+ free_percpu(ptr[1]);
ptr[0] = ptr[1] = NULL;
}
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;
#endif
#endif
- if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb))
- {
+ if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)) {
printk(KERN_CRIT "inet6_proto_init: size fault\n");
return -EINVAL;
}
- /* allocate our sock slab caches */
- tcp6_sk_cachep = kmem_cache_create("tcp6_sock",
- sizeof(struct tcp6_sock), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- udp6_sk_cachep = kmem_cache_create("udp6_sock",
- sizeof(struct udp6_sock), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- raw6_sk_cachep = kmem_cache_create("raw6_sock",
- sizeof(struct raw6_sock), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!tcp6_sk_cachep || !udp6_sk_cachep || !raw6_sk_cachep)
- printk(KERN_CRIT "%s: Can't create protocol sock SLAB "
- "caches!\n", __FUNCTION__);
+
+ 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)
/* 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);
+ err = sock_register(&inet6_family_ops);
+ if (err)
+ goto out_unregister_raw_proto;
/* Initialise ipv6 mibs */
err = init_ipv6_mibs();
if (err)
- goto init_mib_fail;
+ goto out_unregister_sock;
/*
* ipngwg API draft makes clear that the correct semantics
err = igmp6_init(&inet6_family_ops);
if (err)
goto igmp_fail;
+ err = ipv6_netfilter_init();
+ if (err)
+ goto netfilter_fail;
/* Create /proc/foo6 entries. */
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
if (if6_proc_init())
goto proc_if6_fail;
#endif
- ipv6_packet_init();
ip6_route_init();
ip6_flowlabel_init();
- addrconf_init();
+ err = addrconf_init();
+ if (err)
+ goto addrconf_fail;
sit_init();
/* Init v6 extension headers. */
udpv6_init();
tcpv6_init();
- return 0;
+ ipv6_packet_init();
+ err = 0;
+out:
+ return err;
+addrconf_fail:
+ ip6_flowlabel_cleanup();
+ ip6_route_cleanup();
#ifdef CONFIG_PROC_FS
+ if6_proc_exit();
proc_if6_fail:
ac6_proc_exit();
proc_anycast6_fail:
proc_tcp6_fail:
raw6_proc_exit();
proc_raw6_fail:
- igmp6_cleanup();
#endif
+ ipv6_netfilter_fini();
+netfilter_fail:
+ igmp6_cleanup();
igmp_fail:
ndisc_cleanup();
ndisc_fail:
ipv6_sysctl_unregister();
#endif
cleanup_ipv6_mibs();
-init_mib_fail:
- return err;
+out_unregister_sock:
+ sock_unregister(PF_INET6);
+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);
ip6_route_cleanup();
ipv6_packet_cleanup();
igmp6_cleanup();
+ ipv6_netfilter_fini();
ndisc_cleanup();
icmpv6_cleanup();
#ifdef CONFIG_SYSCTL
ipv6_sysctl_unregister();
#endif
cleanup_ipv6_mibs();
- kmem_cache_destroy(tcp6_sk_cachep);
- kmem_cache_destroy(udp6_sk_cachep);
- kmem_cache_destroy(raw6_sk_cachep);
+ proto_unregister(&rawv6_prot);
+ proto_unregister(&udpv6_prot);
+ proto_unregister(&tcpv6_prot);
}
module_exit(inet6_exit);
git://git.onelab.eu / linux-2.6.git / blobdiff