X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Faf_inet6.c;h=3f9e86b15e0d867e1b85125b4521edbc0092054d;hb=3374cd1abd478f767aaedf2c21d109596ff0fe72;hp=90d2f723fc46f550a02962aad16bce7299e47770;hpb=c69bce20dda7f79160856a338298d65a284ba303;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 90d2f72..3f9e86b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -7,8 +7,6 @@ * * 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 @@ -38,6 +36,7 @@ #include #include #include +#include #include #include @@ -52,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -61,19 +61,34 @@ #include #include +#include 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. */ static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); +struct ipv6_params ipv6_defaults = { + .disable_ipv6 = 0, + .autoconf = 1, +}; + +static int disable_ipv6_mod = 0; + +module_param_named(disable, disable_ipv6_mod, int, 0444); +MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); + +module_param_named(disable_ipv6, ipv6_defaults.disable_ipv6, int, 0444); +MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); + +module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); +MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); + static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); @@ -81,12 +96,12 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } -static int inet6_create(struct net *net, struct socket *sock, int protocol) +static int inet6_create(struct net *net, struct socket *sock, int protocol, + int kern) { 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; @@ -94,22 +109,18 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol) 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: err = -ESOCKTNOSUPPORT; rcu_read_lock(); - list_for_each_rcu(p, &inetsw6[sock->type]) { - answer = list_entry(p, struct inet_protosw, list); + list_for_each_entry_rcu(answer, &inetsw6[sock->type], list) { + err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) @@ -124,10 +135,9 @@ lookup_protocol: break; } err = -EPROTONOSUPPORT; - answer = NULL; } - if (!answer) { + if (err) { if (try_loading_module < 2) { rcu_read_unlock(); /* @@ -150,7 +160,7 @@ lookup_protocol: } err = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; @@ -159,7 +169,7 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - BUG_TRAP(answer_prot->slab != NULL); + WARN_ON(answer_prot->slab == NULL); err = -ENOBUFS; sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot); @@ -177,7 +187,7 @@ lookup_protocol: inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -190,10 +200,10 @@ lookup_protocol: inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk); np->hop_limit = -1; - np->mcast_hops = -1; + np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; 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. @@ -220,12 +230,12 @@ lookup_protocol: */ sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically shares. */ - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { @@ -250,6 +260,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) 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; @@ -272,15 +283,32 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) lock_sock(sk); /* Check these errors (active socket, double bind). */ - if (sk->sk_state != TCP_CLOSE || inet->num) { + if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + int chk_addr_ret; + + /* Binding to v4-mapped address on a v6-only socket + * makes no sense + */ + if (np->ipv6only) { + err = -EINVAL; + goto out; + } + + /* Reproduce AF_INET checks to make the bindings consitant */ v4addr = addr->sin6_addr.s6_addr32[3]; - if (inet_addr_type(v4addr) != RTN_LOCAL) { + chk_addr_ret = inet_addr_type(net, v4addr); + if (!sysctl_ip_nonlocal_bind && + !(inet->freebind || inet->transparent) && + v4addr != htonl(INADDR_ANY) && + chk_addr_ret != RTN_LOCAL && + chk_addr_ret != RTN_MULTICAST && + chk_addr_ret != RTN_BROADCAST) { err = -EADDRNOTAVAIL; goto out; } @@ -288,6 +316,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; + rcu_read_lock(); if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { @@ -300,12 +329,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; - goto out; + goto out_unlock; } - dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; - goto out; + goto out_unlock; } } @@ -314,20 +343,18 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); + if (!ipv6_chk_addr(net, &addr->sin6_addr, + dev, 0)) { err = -EADDRNOTAVAIL; - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); + rcu_read_unlock(); } } - inet->rcv_saddr = v4addr; - inet->saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); @@ -341,16 +368,22 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - if (addr_type != IPV6_ADDR_ANY) + if (addr_type != IPV6_ADDR_ANY) { sk->sk_userlocks |= SOCK_BINDADDR_LOCK; + if (addr_type != IPV6_ADDR_MAPPED) + np->ipv6only = 1; + } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->dport = 0; - inet->daddr = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_dport = 0; + inet->inet_daddr = 0; out: release_sock(sk); return err; +out_unlock: + rcu_read_unlock(); + goto out; } EXPORT_SYMBOL(inet6_bind); @@ -373,7 +406,7 @@ int inet6_release(struct socket *sock) 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; @@ -391,8 +424,6 @@ int inet6_destroy_sock(struct sock *sk) if ((opt = xchg(&np->opt, NULL)) != NULL) sock_kfree_s(sk, opt, opt->tot_len); - - return 0; } EXPORT_SYMBOL_GPL(inet6_destroy_sock); @@ -413,12 +444,12 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (peer) { - if (!inet->dport) + if (!inet->inet_dport) return -ENOTCONN; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1) return -ENOTCONN; - sin->sin6_port = inet->dport; + sin->sin6_port = inet->inet_dport; ipv6_addr_copy(&sin->sin6_addr, &np->daddr); if (np->sndflow) sin->sin6_flowinfo = np->flow_label; @@ -428,7 +459,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); - sin->sin6_port = inet->sport; + sin->sin6_port = inet->inet_sport; } if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; @@ -441,6 +472,7 @@ EXPORT_SYMBOL(inet6_getname); 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) { @@ -453,14 +485,14 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) 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; @@ -523,63 +555,29 @@ const struct proto_ops inet6_dgram_ops = { #endif }; -static struct net_proto_family inet6_family_ops = { +static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .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); @@ -603,9 +601,10 @@ inet6_register_protosw(struct inet_protosw *p) * 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", @@ -658,8 +657,9 @@ int inet6_sk_rebuild_header(struct sock *sk) 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; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { @@ -677,7 +677,7 @@ int inet6_sk_rebuild_header(struct sock *sk) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; return err; } @@ -712,62 +712,370 @@ int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb) EXPORT_SYMBOL_GPL(ipv6_opt_accepted); -static int __init init_ipv6_mibs(void) +static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) +{ + const 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 proto; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + const 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 = rcu_dereference(inet6_protos[ + 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; + const struct inet6_protocol *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + + 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); + + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + rcu_read_lock(); + ops = rcu_dereference(inet6_protos[proto]); + 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)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } + } + +out: + return segs; +} + +struct ipv6_gro_cb { + struct napi_gro_cb napi; + int proto; +}; + +#define IPV6_GRO_CB(skb) ((struct ipv6_gro_cb *)(skb)->cb) + +static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct inet6_protocol *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct ipv6hdr *iph; + unsigned int nlen; + unsigned int hlen; + unsigned int off; + int flush = 1; + int proto; + __wsum csum; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } + + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + + flush += ntohs(iph->payload_len) != skb_gro_len(skb); + + rcu_read_lock(); + proto = iph->nexthdr; + ops = rcu_dereference(inet6_protos[proto]); + if (!ops || !ops->gro_receive) { + __pskb_pull(skb, skb_gro_offset(skb)); + proto = ipv6_gso_pull_exthdrs(skb, proto); + skb_gro_pull(skb, -skb_transport_offset(skb)); + skb_reset_transport_header(skb); + __skb_push(skb, skb_gro_offset(skb)); + + if (!ops || !ops->gro_receive) + goto out_unlock; + + iph = ipv6_hdr(skb); + } + + IPV6_GRO_CB(skb)->proto = proto; + + flush--; + nlen = skb_network_header_len(skb); + + for (p = *head; p; p = p->next) { + struct ipv6hdr *iph2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = ipv6_hdr(p); + + /* All fields must match except length. */ + if (nlen != skb_network_header_len(p) || + memcmp(iph, iph2, offsetof(struct ipv6hdr, payload_len)) || + memcmp(&iph->nexthdr, &iph2->nexthdr, + nlen - offsetof(struct ipv6hdr, nexthdr))) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + + csum = skb->csum; + skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + + pp = ops->gro_receive(head, skb); + + skb->csum = csum; + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int ipv6_gro_complete(struct sk_buff *skb) +{ + const struct inet6_protocol *ops; + struct ipv6hdr *iph = ipv6_hdr(skb); + int err = -ENOSYS; + + iph->payload_len = htons(skb->len - skb_network_offset(skb) - + sizeof(*iph)); + + rcu_read_lock(); + ops = rcu_dereference(inet6_protos[IPV6_GRO_CB(skb)->proto]); + if (WARN_ON(!ops || !ops->gro_complete)) + goto out_unlock; + + err = ops->gro_complete(skb); + +out_unlock: + rcu_read_unlock(); + + return err; +} + +static struct packet_type ipv6_packet_type __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), + .func = ipv6_rcv, + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, +}; + +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 __net_init ipv6_init_mibs(struct net *net) { - if (snmp_mib_init((void **)ipv6_statistics, + if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6, + sizeof (struct udp_mib)) < 0) + return -ENOMEM; + if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6, + sizeof (struct udp_mib)) < 0) + goto err_udplite_mib; + if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics, sizeof(struct ipstats_mib)) < 0) goto err_ip_mib; - if (snmp_mib_init((void **)icmpv6_statistics, + if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics, sizeof(struct icmpv6_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void **)icmpv6msg_statistics, + if (snmp_mib_init((void __percpu **)net->mib.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: - snmp_mib_free((void **)icmpv6msg_statistics); err_icmpmsg_mib: - snmp_mib_free((void **)icmpv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); err_icmp_mib: - snmp_mib_free((void **)ipv6_statistics); + snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); err_ip_mib: + snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); +err_udplite_mib: + snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); return -ENOMEM; +} +static void ipv6_cleanup_mibs(struct net *net) +{ + snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); + snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); + snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics); } -static void cleanup_ipv6_mibs(void) +static int __net_init inet6_net_init(struct net *net) { - 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); + int err = 0; + + net->ipv6.sysctl.bindv6only = 0; + net->ipv6.sysctl.icmpv6_time = 1*HZ; + + err = ipv6_init_mibs(net); + if (err) + return err; +#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; +#endif + return err; + +#ifdef CONFIG_PROC_FS +proc_ac6_fail: + tcp6_proc_exit(net); +proc_tcp6_fail: + udp6_proc_exit(net); +out: + ipv6_cleanup_mibs(net); + return err; +#endif } +static void __net_exit inet6_net_exit(struct net *net) +{ +#ifdef CONFIG_PROC_FS + udp6_proc_exit(net); + tcp6_proc_exit(net); + ac6_proc_exit(net); +#endif + ipv6_cleanup_mibs(net); +} + +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; - int err; + int err = 0; 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; + /* Register the socket-side information for inet6_create. */ + for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) + INIT_LIST_HEAD(r); - __this_module.can_unload = &ipv6_unload; -#endif -#endif + if (disable_ipv6_mod) { + printk(KERN_INFO + "IPv6: Loaded, but administratively disabled, " + "reboot required to enable\n"); + goto out; + } err = proto_register(&tcpv6_prot, 1); if (err) @@ -786,27 +1094,25 @@ static int __init inet6_init(void) goto out_unregister_udplite_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); + 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(); +#ifdef CONFIG_SYSCTL + err = ipv6_static_sysctl_register(); if (err) - goto out_unregister_sock; - + goto static_sysctl_fail; +#endif /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance @@ -814,16 +1120,19 @@ static int __init inet6_init(void) * 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(); @@ -834,61 +1143,85 @@ static int __init inet6_init(void) 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 @@ -898,15 +1231,20 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: + ip6_mr_cleanup(); +ipmr_fail: icmpv6_cleanup(); icmp_fail: + unregister_pernet_subsys(&inet6_net_ops); +register_pernet_fail: #ifdef CONFIG_SYSCTL - ipv6_sysctl_unregister(); + ipv6_static_sysctl_unregister(); +static_sysctl_fail: #endif - 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: @@ -921,14 +1259,25 @@ module_init(inet6_init); static void __exit inet6_exit(void) { + if (disable_ipv6_mod) + return; + /* First of all disallow new sockets creation. */ sock_unregister(PF_INET6); /* 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(); @@ -936,25 +1285,27 @@ static void __exit inet6_exit(void) /* 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(); + rawv6_exit(); + + unregister_pernet_subsys(&inet6_net_ops); #ifdef CONFIG_SYSCTL - ipv6_sysctl_unregister(); + ipv6_static_sysctl_unregister(); #endif - cleanup_ipv6_mibs(); proto_unregister(&rawv6_prot); proto_unregister(&udplitev6_prot); proto_unregister(&udpv6_prot); proto_unregister(&tcpv6_prot); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } module_exit(inet6_exit);