diff options
Diffstat (limited to 'net/ipv6')
32 files changed, 1133 insertions, 861 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 6460eec..9601fd7 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -8,7 +8,8 @@ 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 netfilter.o + ip6_flowlabel.o ipv6_syms.o netfilter.o \ + inet6_connection_sock.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ xfrm6_output.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 76ff9f4..704fb73 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -137,6 +137,7 @@ static int addrconf_ifdown(struct net_device *dev, int how); static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); static void addrconf_dad_timer(unsigned long data); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); +static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(unsigned long data); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); @@ -379,8 +380,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) dev->type == ARPHRD_NONE || dev->type == ARPHRD_SIT) { printk(KERN_INFO - "Disabled Privacy Extensions on device %p(%s)\n", - dev, dev->name); + "%s: Disabled Privacy Extensions\n", + dev->name); ndev->cnf.use_tempaddr = -1; } else { in6_dev_hold(ndev); @@ -388,6 +389,9 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) } #endif + if (netif_carrier_ok(dev)) + ndev->if_flags |= IF_READY; + write_lock_bh(&addrconf_lock); dev->ip6_ptr = ndev; write_unlock_bh(&addrconf_lock); @@ -415,6 +419,7 @@ static struct inet6_dev * ipv6_find_idev(struct net_device *dev) if ((idev = ipv6_add_dev(dev)) == NULL) return NULL; } + if (dev->flags&IFF_UP) ipv6_mc_up(idev); return idev; @@ -634,8 +639,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } #endif - for (ifap = &idev->addr_list; (ifa=*ifap) != NULL; - ifap = &ifa->if_next) { + for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) { if (ifa == ifp) { *ifap = ifa->if_next; __in6_ifa_put(ifp); @@ -643,6 +647,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0) break; deleted = 1; + continue; } else if (ifp->flags & IFA_F_PERMANENT) { if (ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) { @@ -666,6 +671,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } } } + ifap = &ifa->if_next; } write_unlock_bh(&idev->lock); @@ -903,11 +909,18 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, score.addr_type = __ipv6_addr_type(&ifa->addr); - /* Rule 0: Candidate Source Address (section 4) + /* Rule 0: + * - Tentative Address (RFC2462 section 5.4) + * - A tentative address is not considered + * "assigned to an interface" in the traditional + * sense. + * - Candidate Source Address (section 4) * - In any case, anycast addresses, multicast * addresses, and the unspecified address MUST * NOT be included in a candidate set. */ + if (ifa->flags & IFA_F_TENTATIVE) + continue; if (unlikely(score.addr_type == IPV6_ADDR_ANY || score.addr_type & IPV6_ADDR_MULTICAST)) { LIMIT_NETDEBUG(KERN_DEBUG @@ -1182,7 +1195,7 @@ struct inet6_ifaddr * ipv6_get_ifaddr(struct in6_addr *addr, struct net_device * int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; - const struct in6_addr *sk2_rcv_saddr6 = tcp_v6_rcv_saddr(sk2); + const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); u32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; u32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); @@ -1215,10 +1228,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) /* Gets referenced address, destroys ifaddr */ -void addrconf_dad_failure(struct inet6_ifaddr *ifp) +void addrconf_dad_stop(struct inet6_ifaddr *ifp) { - if (net_ratelimit()) - printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name); if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); addrconf_del_timer(ifp); @@ -1244,6 +1255,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) ipv6_del_addr(ifp); } +void addrconf_dad_failure(struct inet6_ifaddr *ifp) +{ + if (net_ratelimit()) + printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name); + addrconf_dad_stop(ifp); +} /* Join to solicited addr multicast group. */ @@ -1596,9 +1613,17 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) not good. */ if (valid_lft >= 0x7FFFFFFF/HZ) - rt_expires = 0; + rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); else - rt_expires = jiffies + valid_lft * HZ; + rt_expires = valid_lft * HZ; + + /* + * We convert this (in jiffies) to clock_t later. + * Avoid arithmetic overflow there as well. + * Overflow can happen only if HZ < USER_HZ. + */ + if (HZ < USER_HZ && rt_expires > 0x7FFFFFFF / USER_HZ) + rt_expires = 0x7FFFFFFF / USER_HZ; if (pinfo->onlink) { struct rt6_info *rt; @@ -1610,12 +1635,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) ip6_del_rt(rt, NULL, NULL, NULL); rt = NULL; } else { - rt->rt6i_expires = rt_expires; + rt->rt6i_expires = jiffies + rt_expires; } } } else if (valid_lft) { addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, - dev, rt_expires, RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT); + dev, jiffies_to_clock_t(rt_expires), RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT); } if (rt) dst_release(&rt->u.dst); @@ -2125,9 +2150,42 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, { struct net_device *dev = (struct net_device *) data; struct inet6_dev *idev = __in6_dev_get(dev); + int run_pending = 0; switch(event) { case NETDEV_UP: + case NETDEV_CHANGE: + if (event == NETDEV_UP) { + if (!netif_carrier_ok(dev)) { + /* device is not ready yet. */ + printk(KERN_INFO + "ADDRCONF(NETDEV_UP): %s: " + "link is not ready\n", + dev->name); + break; + } + } else { + if (!netif_carrier_ok(dev)) { + /* device is still not ready. */ + break; + } + + if (idev) { + if (idev->if_flags & IF_READY) { + /* device is already configured. */ + break; + } + idev->if_flags |= IF_READY; + } + + printk(KERN_INFO + "ADDRCONF(NETDEV_CHANGE): %s: " + "link becomes ready\n", + dev->name); + + run_pending = 1; + } + switch(dev->type) { case ARPHRD_SIT: addrconf_sit_config(dev); @@ -2144,6 +2202,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; }; if (idev) { + if (run_pending) + addrconf_dad_run(idev); + /* If the MTU changed during the interface down, when the interface up, the changed MTU must be reflected in the idev as well as routers. @@ -2178,8 +2239,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ addrconf_ifdown(dev, event != NETDEV_DOWN); break; - case NETDEV_CHANGE: - break; + case NETDEV_CHANGENAME: #ifdef CONFIG_SYSCTL if (idev) { @@ -2260,7 +2320,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Step 3: clear flags for stateless addrconf */ if (how != 1) - idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD); + idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 4: clear address list */ #ifdef CONFIG_IPV6_PRIVACY @@ -2369,11 +2429,20 @@ out: /* * Duplicate Address Detection */ +static void addrconf_dad_kick(struct inet6_ifaddr *ifp) +{ + unsigned long rand_num; + struct inet6_dev *idev = ifp->idev; + + rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); + ifp->probes = idev->cnf.dad_transmits; + addrconf_mod_timer(ifp, AC_DAD, rand_num); +} + static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; - unsigned long rand_num; addrconf_join_solict(dev, &ifp->addr); @@ -2382,7 +2451,6 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) flags); net_srandom(ifp->addr.s6_addr32[3]); - rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); read_lock_bh(&idev->lock); if (ifp->dead) @@ -2399,9 +2467,19 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) return; } - ifp->probes = idev->cnf.dad_transmits; - addrconf_mod_timer(ifp, AC_DAD, rand_num); - + if (!(idev->if_flags & IF_READY)) { + spin_unlock_bh(&ifp->lock); + read_unlock_bh(&idev->lock); + /* + * If the defice is not ready: + * - keep it tentative if it is a permanent address. + * - otherwise, kill it. + */ + in6_ifa_hold(ifp); + addrconf_dad_stop(ifp); + return; + } + addrconf_dad_kick(ifp); spin_unlock_bh(&ifp->lock); out: read_unlock_bh(&idev->lock); @@ -2484,6 +2562,22 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) } } +static void addrconf_dad_run(struct inet6_dev *idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { + spin_lock_bh(&ifp->lock); + if (!(ifp->flags & IFA_F_TENTATIVE)) { + spin_unlock_bh(&ifp->lock); + continue; + } + spin_unlock_bh(&ifp->lock); + addrconf_dad_kick(ifp); + } + read_unlock_bh(&idev->lock); +} + #ifdef CONFIG_PROC_FS struct if6_iter_state { int bucket; @@ -2689,6 +2783,9 @@ restart: in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); read_unlock(&addrconf_hash_lock); + spin_lock(&ifpub->lock); + ifpub->regen_count = 0; + spin_unlock(&ifpub->lock); ipv6_create_tempaddr(ifpub, ifp); in6_ifa_put(ifpub); in6_ifa_put(ifp); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d954638..68afc53 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -167,6 +167,7 @@ lookup_protocol: sk->sk_reuse = 1; inet = inet_sk(sk); + inet->is_icsk = INET_PROTOSW_ICSK & answer_flags; if (SOCK_RAW == sock->type) { inet->num = protocol; @@ -389,6 +390,8 @@ int inet6_destroy_sock(struct sock *sk) return 0; } +EXPORT_SYMBOL_GPL(inet6_destroy_sock); + /* * This does both peername and sockname. */ @@ -431,7 +434,6 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; - int err = -EINVAL; switch(cmd) { @@ -450,16 +452,15 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long 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; + if (!sk->sk_prot->ioctl) + return -ENOIOCTLCMD; + return sk->sk_prot->ioctl(sk, cmd, arg); } /*NOTREACHED*/ return(0); } -struct proto_ops inet6_stream_ops = { +const struct proto_ops inet6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, @@ -480,7 +481,7 @@ struct proto_ops inet6_stream_ops = { .sendpage = tcp_sendpage }; -struct proto_ops inet6_dgram_ops = { +const struct proto_ops inet6_dgram_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, @@ -508,7 +509,7 @@ static struct net_proto_family inet6_family_ops = { }; /* Same as inet6_dgram_ops, sans udp_poll. */ -static struct proto_ops inet6_sockraw_ops = { +static const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, @@ -609,6 +610,79 @@ inet6_unregister_protosw(struct inet_protosw *p) } } +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) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index f362973..13cc7f8 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <net/xfrm.h> #include <asm/scatterlist.h> diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 40d9a19..6de8ee1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -36,6 +36,7 @@ #include <linux/random.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <linux/icmpv6.h> static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) @@ -248,7 +249,7 @@ static u32 esp6_get_max_size(struct xfrm_state *x, int mtu) if (esp->conf.padlen) mtu = ALIGN(mtu, esp->conf.padlen); - return mtu + x->props.header_len + esp->auth.icv_full_len; + return mtu + x->props.header_len + esp->auth.icv_trunc_len; } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index be6faf3..113374d 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -413,6 +413,8 @@ ipv6_invert_rthdr(struct sock *sk, struct ipv6_rt_hdr *hdr) return opt; } +EXPORT_SYMBOL_GPL(ipv6_invert_rthdr); + /********************************** Hop-by-hop options. **********************************/ @@ -579,6 +581,8 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) return opt2; } +EXPORT_SYMBOL_GPL(ipv6_dup_options); + static int ipv6_renew_option(void *ohdr, struct ipv6_opt_hdr __user *newopt, int newoptlen, int inherit, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 34a3322..6ec6a2b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -328,8 +328,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, iif = skb->dev->ifindex; /* - * Must not send if we know that source is Anycast also. - * for now we don't know that. + * Must not send error if the source does not uniquely + * identify a single node (RFC2463 Section 2.4). + * We check unspecified / multicast addresses here, + * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n"); @@ -373,6 +375,16 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto out; + + /* + * We won't send icmp if the destination is known + * anycast. + */ + if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { + LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n"); + goto out_dst_release; + } + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c new file mode 100644 index 0000000..792f90f --- /dev/null +++ b/net/ipv6/inet6_connection_sock.c @@ -0,0 +1,199 @@ +/* + * 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. + * + * Support for INET6 connection oriented protocols. + * + * Authors: See the TCPv6 sources + * + * 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/in6.h> +#include <linux/ipv6.h> +#include <linux/jhash.h> + +#include <net/addrconf.h> +#include <net/inet_connection_sock.h> +#include <net/inet_ecn.h> +#include <net/inet_hashtables.h> +#include <net/ip6_route.h> +#include <net/sock.h> + +int inet6_csk_bind_conflict(const struct sock *sk, + const struct inet_bind_bucket *tb) +{ + const struct sock *sk2; + const struct hlist_node *node; + + /* We must walk the whole port owner list in this case. -DaveM */ + sk_for_each_bound(sk2, node, &tb->owners) { + if (sk != sk2 && + (!sk->sk_bound_dev_if || + !sk2->sk_bound_dev_if || + sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && + (!sk->sk_reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + ipv6_rcv_saddr_equal(sk, sk2)) + break; + } + + return node != NULL; +} + +EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); + +/* + * request_sock (formerly open request) hash tables. + */ +static u32 inet6_synq_hash(const struct in6_addr *raddr, const u16 rport, + const u32 rnd, const u16 synq_hsize) +{ + u32 a = raddr->s6_addr32[0]; + u32 b = raddr->s6_addr32[1]; + u32 c = raddr->s6_addr32[2]; + + a += JHASH_GOLDEN_RATIO; + b += JHASH_GOLDEN_RATIO; + c += rnd; + __jhash_mix(a, b, c); + + a += raddr->s6_addr32[3]; + b += (u32)rport; + __jhash_mix(a, b, c); + + return c & (synq_hsize - 1); +} + +struct request_sock *inet6_csk_search_req(const struct sock *sk, + struct request_sock ***prevp, + const __u16 rport, + const struct in6_addr *raddr, + const struct in6_addr *laddr, + const int iif) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; + struct request_sock *req, **prev; + + for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, + lopt->hash_rnd, + lopt->nr_table_entries)]; + (req = *prev) != NULL; + prev = &req->dl_next) { + const struct inet6_request_sock *treq = inet6_rsk(req); + + if (inet_rsk(req)->rmt_port == rport && + req->rsk_ops->family == AF_INET6 && + ipv6_addr_equal(&treq->rmt_addr, raddr) && + ipv6_addr_equal(&treq->loc_addr, laddr) && + (!treq->iif || treq->iif == iif)) { + BUG_TRAP(req->sk == NULL); + *prevp = prev; + return req; + } + } + + return NULL; +} + +EXPORT_SYMBOL_GPL(inet6_csk_search_req); + +void inet6_csk_reqsk_queue_hash_add(struct sock *sk, + struct request_sock *req, + const unsigned long timeout) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; + const u32 h = inet6_synq_hash(&inet6_rsk(req)->rmt_addr, + inet_rsk(req)->rmt_port, + lopt->hash_rnd, lopt->nr_table_entries); + + reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); + inet_csk_reqsk_queue_added(sk, timeout); +} + +EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); + +void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; + + sin6->sin6_family = AF_INET6; + ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); + sin6->sin6_port = inet_sk(sk)->dport; + /* We do not store received flowlabel for TCP */ + sin6->sin6_flowinfo = 0; + sin6->sin6_scope_id = 0; + if (sk->sk_bound_dev_if && + ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + sin6->sin6_scope_id = sk->sk_bound_dev_if; +} + +EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); + +int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) +{ + struct sock *sk = skb->sk; + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi fl; + struct dst_entry *dst; + struct in6_addr *final_p = NULL, final; + + 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; + IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); + fl.oif = sk->sk_bound_dev_if; + fl.fl_ip_sport = inet->sport; + fl.fl_ip_dport = inet->dport; + + 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; + } + + dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst == NULL) { + int err = ip6_dst_lookup(sk, &dst, &fl); + + if (err) { + sk->sk_err_soft = -err; + return err; + } + + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + sk->sk_route_caps = 0; + return err; + } + + ip6_dst_store(sk, dst, NULL); + sk->sk_route_caps = dst->dev->features & + ~(NETIF_F_IP_CSUM | NETIF_F_TSO); + } + + skb->dst = dst_clone(dst); + + /* Restore final destination back after routing done */ + ipv6_addr_copy(&fl.fl6_dst, &np->daddr); + + return ip6_xmit(sk, skb, &fl, np->opt, 0); +} + +EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 01d5f46..4154f3a 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -5,7 +5,8 @@ * * Generic INET6 transport hashtables * - * Authors: Lotsa people, from code originally in tcp + * Authors: Lotsa people, from code originally in tcp, generalised here + * by Arnaldo Carvalho de Melo <acme@mandriva.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -14,12 +15,13 @@ */ #include <linux/config.h> - #include <linux/module.h> +#include <linux/random.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> +#include <net/ip.h> struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, @@ -79,3 +81,180 @@ struct sock *inet6_lookup(struct inet_hashinfo *hashinfo, } EXPORT_SYMBOL_GPL(inet6_lookup); + +static int __inet6_check_established(struct inet_timewait_death_row *death_row, + struct sock *sk, const __u16 lport, + struct inet_timewait_sock **twp) +{ + struct inet_hashinfo *hinfo = death_row->hashinfo; + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); + const struct in6_addr *daddr = &np->rcv_saddr; + const struct in6_addr *saddr = &np->daddr; + const int dif = sk->sk_bound_dev_if; + const u32 ports = INET_COMBINED_PORTS(inet->dport, lport); + const unsigned int hash = inet6_ehashfn(daddr, inet->num, saddr, + inet->dport); + struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); + struct sock *sk2; + const struct hlist_node *node; + struct inet_timewait_sock *tw; + + prefetch(head->chain.first); + write_lock(&head->lock); + + /* Check TIME-WAIT sockets first. */ + sk_for_each(sk2, node, &(head + hinfo->ehash_size)->chain) { + const struct inet6_timewait_sock *tw6 = inet6_twsk(sk2); + + tw = inet_twsk(sk2); + + if(*((__u32 *)&(tw->tw_dport)) == ports && + sk2->sk_family == PF_INET6 && + ipv6_addr_equal(&tw6->tw_v6_daddr, saddr) && + ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) && + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) { + if (twsk_unique(sk, sk2, twp)) + goto unique; + else + goto not_unique; + } + } + tw = NULL; + + /* And established part... */ + sk_for_each(sk2, node, &head->chain) { + if (INET6_MATCH(sk2, hash, saddr, daddr, ports, dif)) + goto not_unique; + } + +unique: + BUG_TRAP(sk_unhashed(sk)); + __sk_add_node(sk, &head->chain); + sk->sk_hash = hash; + sock_prot_inc_use(sk->sk_prot); + write_unlock(&head->lock); + + if (twp != NULL) { + *twp = tw; + NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); + } else if (tw != NULL) { + /* Silly. Should hash-dance instead... */ + inet_twsk_deschedule(tw, death_row); + NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); + + inet_twsk_put(tw); + } + return 0; + +not_unique: + write_unlock(&head->lock); + return -EADDRNOTAVAIL; +} + +static inline u32 inet6_sk_port_offset(const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); + return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, + np->daddr.s6_addr32, + inet->dport); +} + +int inet6_hash_connect(struct inet_timewait_death_row *death_row, + struct sock *sk) +{ + struct inet_hashinfo *hinfo = death_row->hashinfo; + const unsigned short snum = inet_sk(sk)->num; + struct inet_bind_hashbucket *head; + struct inet_bind_bucket *tb; + int ret; + + if (snum == 0) { + const int low = sysctl_local_port_range[0]; + const int high = sysctl_local_port_range[1]; + const int range = high - low; + int i, port; + static u32 hint; + const u32 offset = hint + inet6_sk_port_offset(sk); + struct hlist_node *node; + struct inet_timewait_sock *tw = NULL; + + local_bh_disable(); + for (i = 1; i <= range; i++) { + port = low + (i + offset) % range; + head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)]; + spin_lock(&head->lock); + + /* Does not bother with rcv_saddr checks, + * because the established check is already + * unique enough. + */ + inet_bind_bucket_for_each(tb, node, &head->chain) { + if (tb->port == port) { + BUG_TRAP(!hlist_empty(&tb->owners)); + if (tb->fastreuse >= 0) + goto next_port; + if (!__inet6_check_established(death_row, + sk, port, + &tw)) + goto ok; + goto next_port; + } + } + + tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, + head, port); + if (!tb) { + spin_unlock(&head->lock); + break; + } + tb->fastreuse = -1; + goto ok; + + next_port: + spin_unlock(&head->lock); + } + local_bh_enable(); + + return -EADDRNOTAVAIL; + +ok: + hint += i; + + /* Head lock still held and bh's disabled */ + inet_bind_hash(sk, tb, port); + if (sk_unhashed(sk)) { + inet_sk(sk)->sport = htons(port); + __inet6_hash(hinfo, sk); + } + spin_unlock(&head->lock); + + if (tw) { + inet_twsk_deschedule(tw, death_row); + inet_twsk_put(tw); + } + + ret = 0; + goto out; + } + + head = &hinfo->bhash[inet_bhashfn(snum, hinfo->bhash_size)]; + tb = inet_csk(sk)->icsk_bind_hash; + spin_lock_bh(&head->lock); + + if (sk_head(&tb->owners) == sk && sk->sk_bind_node.next == NULL) { + __inet6_hash(hinfo, sk); + spin_unlock_bh(&head->lock); + return 0; + } else { + spin_unlock(&head->lock); + /* No definite answer... Walk to established hash table */ + ret = __inet6_check_established(death_row, sk, snum, NULL); +out: + local_bh_enable(); + return ret; + } +} + +EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1cf0276..89d12b4 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -200,6 +200,8 @@ struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, u32 label) return NULL; } +EXPORT_SYMBOL_GPL(fl6_sock_lookup); + void fl6_free_socklist(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8523c76..b4c4beb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -775,6 +775,8 @@ out_err_release: return err; } +EXPORT_SYMBOL_GPL(ip6_dst_lookup); + static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 55917fb..626dd39 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -47,6 +47,7 @@ #include <linux/rtnetlink.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 3620718..c63868d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -163,17 +163,17 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sk_refcnt_debug_dec(sk); if (sk->sk_protocol == IPPROTO_TCP) { - struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(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; + icsk->icsk_af_ops = &ipv4_specific; sk->sk_socket->ops = &inet_stream_ops; sk->sk_family = PF_INET; - tcp_sync_mss(sk, tp->pmtu_cookie); + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { local_bh_disable(); sock_prot_dec_use(sk->sk_prot); @@ -317,14 +317,15 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, } retv = 0; - if (sk->sk_type == SOCK_STREAM) { + if (inet_sk(sk)->is_icsk) { if (opt) { - struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(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); + icsk->icsk_ext_hdr_len = + opt->opt_flen + opt->opt_nflen; + icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } opt = xchg(&np->opt, opt); @@ -380,14 +381,15 @@ sticky_done: goto done; update: retv = 0; - if (sk->sk_type == SOCK_STREAM) { + if (inet_sk(sk)->is_icsk) { if (opt) { - struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(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); + icsk->icsk_ext_hdr_len = + opt->opt_flen + opt->opt_nflen; + icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } opt = xchg(&np->opt, opt); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index fd939da..1cf305a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -170,7 +170,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, #define MLDV2_QQIC(value) MLDV2_EXP(0x80, 4, 3, value) #define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value) -#define IPV6_MLD_MAX_MSF 10 +#define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF; @@ -224,6 +224,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr) mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = MCAST_EXCLUDE; + rwlock_init(&mc_lst->sflock); mc_lst->sflist = NULL; /* @@ -360,6 +361,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, struct ip6_sf_socklist *psl; int i, j, rv; int leavegroup = 0; + int pmclocked = 0; int err; if (pgsr->gsr_group.ss_family != AF_INET6 || @@ -403,6 +405,9 @@ int ip6_mc_source(int add, int omode, struct sock *sk, pmc->sfmode = omode; } + write_lock_bh(&pmc->sflock); + pmclocked = 1; + psl = pmc->sflist; if (!add) { if (!psl) @@ -475,6 +480,8 @@ int ip6_mc_source(int add, int omode, struct sock *sk, /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: + if (pmclocked) + write_unlock_bh(&pmc->sflock); read_unlock_bh(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); in6_dev_put(idev); @@ -510,6 +517,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) dev = idev->dev; err = 0; + read_lock_bh(&ipv6_sk_mc_lock); + if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; @@ -549,6 +558,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) newpsl = NULL; (void) ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); } + + write_lock_bh(&pmc->sflock); psl = pmc->sflist; if (psl) { (void) ip6_mc_del_src(idev, group, pmc->sfmode, @@ -558,8 +569,10 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) (void) ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sflist = newpsl; pmc->sfmode = gsf->gf_fmode; + write_unlock_bh(&pmc->sflock); err = 0; done: + read_unlock_bh(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); in6_dev_put(idev); dev_put(dev); @@ -592,6 +605,11 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, dev = idev->dev; err = -EADDRNOTAVAIL; + /* + * changes to the ipv6_mc_list require the socket lock and + * a read lock on ip6_sk_mc_lock. We have the socket lock, + * so reading the list is safe. + */ for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { if (pmc->ifindex != gsf->gf_interface) @@ -614,6 +632,10 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { return -EFAULT; } + /* changes to psl require the socket lock, a read lock on + * on ipv6_sk_mc_lock and a write lock on pmc->sflock. We + * have the socket lock, so reading here is safe. + */ for (i=0; i<copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; @@ -650,6 +672,7 @@ int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr, read_unlock(&ipv6_sk_mc_lock); return 1; } + read_lock(&mc->sflock); psl = mc->sflist; if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; @@ -665,6 +688,7 @@ int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr, if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = 0; } + read_unlock(&mc->sflock); read_unlock(&ipv6_sk_mc_lock); return rv; @@ -1068,7 +1092,8 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) ma->mca_flags |= MAF_TIMER_RUNNING; } -static void mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, +/* mark EXCLUDE-mode sources */ +static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, struct in6_addr *srcs) { struct ip6_sf_list *psf; @@ -1078,13 +1103,53 @@ static void mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, for (psf=pmc->mca_sources; psf; psf=psf->sf_next) { if (scount == nsrcs) break; - for (i=0; i<nsrcs; i++) + for (i=0; i<nsrcs; i++) { + /* skip inactive filters */ + if (pmc->mca_sfcount[MCAST_INCLUDE] || + pmc->mca_sfcount[MCAST_EXCLUDE] != + psf->sf_count[MCAST_EXCLUDE]) + continue; + if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { + scount++; + break; + } + } + } + pmc->mca_flags &= ~MAF_GSQUERY; + if (scount == nsrcs) /* all sources excluded */ + return 0; + return 1; +} + +static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, + struct in6_addr *srcs) +{ + struct ip6_sf_list *psf; + int i, scount; + + if (pmc->mca_sfmode == MCAST_EXCLUDE) + return mld_xmarksources(pmc, nsrcs, srcs); + + /* mark INCLUDE-mode sources */ + + scount = 0; + for (psf=pmc->mca_sources; psf; psf=psf->sf_next) { + if (scount == nsrcs) + break; + for (i=0; i<nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } + } + } + if (!scount) { + pmc->mca_flags &= ~MAF_GSQUERY; + return 0; } + pmc->mca_flags |= MAF_GSQUERY; + return 1; } int igmp6_event_query(struct sk_buff *skb) @@ -1167,7 +1232,7 @@ int igmp6_event_query(struct sk_buff *skb) /* mark sources to include, if group & source-specific */ if (mlh2->nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + - mlh2->nsrcs * sizeof(struct in6_addr))) { + ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) { in6_dev_put(idev); return -EINVAL; } @@ -1203,10 +1268,9 @@ int igmp6_event_query(struct sk_buff *skb) else ma->mca_flags &= ~MAF_GSQUERY; } - if (ma->mca_flags & MAF_GSQUERY) - mld_marksources(ma, ntohs(mlh2->nsrcs), - mlh2->srcs); - igmp6_group_queried(ma, max_delay); + if (!(ma->mca_flags & MAF_GSQUERY) || + mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) + igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); if (group_type != IPV6_ADDR_ANY) break; @@ -1281,7 +1345,18 @@ static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; - return !((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp); + if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { + if (pmc->mca_sfmode == MCAST_INCLUDE) + return 1; + /* don't include if this source is excluded + * in all filters + */ + if (psf->sf_count[MCAST_INCLUDE]) + return 0; + return pmc->mca_sfcount[MCAST_EXCLUDE] == + psf->sf_count[MCAST_EXCLUDE]; + } + return 0; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; @@ -1450,7 +1525,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_report *pmr; struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; - int scount, first, isquery, truncate; + int scount, stotal, first, isquery, truncate; if (pmc->mca_flags & MAF_NOREPORT) return skb; @@ -1460,25 +1535,13 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; + stotal = scount = 0; + psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; - if (!*psf_list) { - if (type == MLD2_ALLOW_NEW_SOURCES || - type == MLD2_BLOCK_OLD_SOURCES) - return skb; - if (pmc->mca_crcount || isquery) { - /* make sure we have room for group header and at - * least one source. - */ - if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)+ - sizeof(struct in6_addr)) { - mld_sendpack(skb); - skb = NULL; /* add_grhead will get a new one */ - } - skb = add_grhead(skb, pmc, type, &pgr); - } - return skb; - } + if (!*psf_list) + goto empty_source; + pmr = skb ? (struct mld2_report *)skb->h.raw : NULL; /* EX and TO_EX get a fresh packet, if needed */ @@ -1491,7 +1554,6 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } } first = 1; - scount = 0; psf_prev = NULL; for (psf=*psf_list; psf; psf=psf_next) { struct in6_addr *psrc; @@ -1525,7 +1587,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } psrc = (struct in6_addr *)skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; - scount++; + scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { psf->sf_crcount--; @@ -1540,6 +1602,21 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } psf_prev = psf; } + +empty_source: + if (!stotal) { + if (type == MLD2_ALLOW_NEW_SOURCES || + type == MLD2_BLOCK_OLD_SOURCES) + return skb; + if (pmc->mca_crcount || isquery) { + /* make sure we have room for group header */ + if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { + mld_sendpack(skb); + skb = NULL; /* add_grhead will get a new one */ + } + skb = add_grhead(skb, pmc, type, &pgr); + } + } if (pgr) pgr->grec_nsrcs = htons(scount); @@ -1621,11 +1698,11 @@ static void mld_send_cr(struct inet6_dev *idev) skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->mca_crcount) { - pmc->mca_crcount--; if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } + pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb); mld_clear_zeros(&pmc->mca_sources); @@ -1659,12 +1736,12 @@ static void mld_send_cr(struct inet6_dev *idev) /* filter mode changes */ if (pmc->mca_crcount) { - pmc->mca_crcount--; if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); + pmc->mca_crcount--; } spin_unlock_bh(&pmc->mca_lock); } @@ -2023,6 +2100,9 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, { int err; + /* callers have the socket lock and a write lock on ipv6_sk_mc_lock, + * so no other readers or writers of iml or its sflist + */ if (iml->sflist == 0) { /* any-source empty exclude case */ return ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 060d612..04912f9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -211,7 +211,7 @@ config IP6_NF_TARGET_REJECT config IP6_NF_TARGET_NFQUEUE tristate "NFQUEUE Target Support" - depends on IP_NF_IPTABLES + depends on IP6_NF_IPTABLES help This Target replaced the old obsolete QUEUE target. diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 95d4692..925b42d4 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -15,6 +15,7 @@ * - new extension header parser code */ #include <linux/config.h> +#include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> @@ -86,11 +87,6 @@ static DECLARE_MUTEX(ip6t_mutex); context stops packets coming through and allows user context to read the counters or update the rules. - To be cache friendly on SMP, we arrange them like so: - [ n-entries ] - ... cache-align padding ... - [ n-entries ] - Hence the start of any table is given by get_table() below. */ /* The table itself */ @@ -108,33 +104,29 @@ struct ip6t_table_info unsigned int underflow[NF_IP6_NUMHOOKS]; /* ip6t_entry tables: one per CPU */ - char entries[0] ____cacheline_aligned; + void *entries[NR_CPUS]; }; static LIST_HEAD(ip6t_target); static LIST_HEAD(ip6t_match); static LIST_HEAD(ip6t_tables); +#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) #define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) -#ifdef CONFIG_SMP -#define TABLE_OFFSET(t,p) (SMP_ALIGN((t)->size)*(p)) -#else -#define TABLE_OFFSET(t,p) 0 -#endif - #if 0 #define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0) #define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; }) #define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0) #endif -static int ip6_masked_addrcmp(struct in6_addr addr1, struct in6_addr mask, - struct in6_addr addr2) +int +ip6_masked_addrcmp(const struct in6_addr *addr1, const struct in6_addr *mask, + const struct in6_addr *addr2) { int i; for( i = 0; i < 16; i++){ - if((addr1.s6_addr[i] & mask.s6_addr[i]) != - (addr2.s6_addr[i] & mask.s6_addr[i])) + if((addr1->s6_addr[i] & mask->s6_addr[i]) != + (addr2->s6_addr[i] & mask->s6_addr[i])) return 1; } return 0; @@ -168,10 +160,10 @@ ip6_packet_match(const struct sk_buff *skb, #define FWINV(bool,invflg) ((bool) ^ !!(ip6info->invflags & invflg)) - if (FWINV(ip6_masked_addrcmp(ipv6->saddr,ip6info->smsk,ip6info->src), - IP6T_INV_SRCIP) - || FWINV(ip6_masked_addrcmp(ipv6->daddr,ip6info->dmsk,ip6info->dst), - IP6T_INV_DSTIP)) { + if (FWINV(ip6_masked_addrcmp(&ipv6->saddr, &ip6info->smsk, + &ip6info->src), IP6T_INV_SRCIP) + || FWINV(ip6_masked_addrcmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -214,69 +206,21 @@ ip6_packet_match(const struct sk_buff *skb, /* look for the desired protocol header */ if((ip6info->flags & IP6T_F_PROTO)) { - u_int8_t currenthdr = ipv6->nexthdr; - struct ipv6_opt_hdr _hdr, *hp; - u_int16_t ptr; /* Header offset in skb */ - u_int16_t hdrlen; /* Header */ - u_int16_t _fragoff = 0, *fp = NULL; - - ptr = IPV6_HDR_LEN; - - while (ip6t_ext_hdr(currenthdr)) { - /* Is there enough space for the next ext header? */ - if (skb->len - ptr < IPV6_OPTHDR_LEN) - return 0; - - /* NONE or ESP: there isn't protocol part */ - /* If we want to count these packets in '-p all', - * we will change the return 0 to 1*/ - if ((currenthdr == IPPROTO_NONE) || - (currenthdr == IPPROTO_ESP)) - break; + int protohdr; + unsigned short _frag_off; - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - BUG_ON(hp == NULL); - - /* Size calculation */ - if (currenthdr == IPPROTO_FRAGMENT) { - fp = skb_header_pointer(skb, - ptr+offsetof(struct frag_hdr, - frag_off), - sizeof(_fragoff), - &_fragoff); - if (fp == NULL) - return 0; - - _fragoff = ntohs(*fp) & ~0x7; - hdrlen = 8; - } else if (currenthdr == IPPROTO_AH) - hdrlen = (hp->hdrlen+2)<<2; - else - hdrlen = ipv6_optlen(hp); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - /* ptr is too large */ - if ( ptr > skb->len ) - return 0; - if (_fragoff) { - if (ip6t_ext_hdr(currenthdr)) - return 0; - break; - } - } - - *protoff = ptr; - *fragoff = _fragoff; + protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off); + if (protohdr < 0) + return 0; - /* currenthdr contains the protocol header */ + *fragoff = _frag_off; dprintf("Packet protocol %hi ?= %s%hi.\n", - currenthdr, + protohdr, ip6info->invflags & IP6T_INV_PROTO ? "!":"", ip6info->proto); - if (ip6info->proto == currenthdr) { + if (ip6info->proto == protohdr) { if(ip6info->invflags & IP6T_INV_PROTO) { return 0; } @@ -376,8 +320,7 @@ ip6t_do_table(struct sk_buff **pskb, read_lock_bh(&table->lock); IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - table_base = (void *)table->private->entries - + TABLE_OFFSET(table->private, smp_processor_id()); + table_base = (void *)table->private->entries[smp_processor_id()]; e = get_entry(table_base, table->private->hook_entry[hook]); #ifdef CONFIG_NETFILTER_DEBUG @@ -649,7 +592,8 @@ unconditional(const struct ip6t_ip6 *ipv6) /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) +mark_source_chains(struct ip6t_table_info *newinfo, + unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -658,7 +602,7 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) for (hook = 0; hook < NF_IP6_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e - = (struct ip6t_entry *)(newinfo->entries + pos); + = (struct ip6t_entry *)(entry0 + pos); if (!(valid_hooks & (1 << hook))) continue; @@ -708,13 +652,13 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) goto next; e = (struct ip6t_entry *) - (newinfo->entries + pos); + (entry0 + pos); } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = (struct ip6t_entry *) - (newinfo->entries + pos + size); + (entry0 + pos + size); e->counters.pcnt = pos; pos += size; } else { @@ -731,7 +675,7 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) newpos = pos + e->next_offset; } e = (struct ip6t_entry *) - (newinfo->entries + newpos); + (entry0 + newpos); e->counters.pcnt = pos; pos = newpos; } @@ -941,6 +885,7 @@ static int translate_table(const char *name, unsigned int valid_hooks, struct ip6t_table_info *newinfo, + void *entry0, unsigned int size, unsigned int number, const unsigned int *hook_entries, @@ -961,11 +906,11 @@ translate_table(const char *name, duprintf("translate_table: size %u\n", newinfo->size); i = 0; /* Walk through entries, checking offsets. */ - ret = IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, + ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, check_entry_size_and_hooks, newinfo, - newinfo->entries, - newinfo->entries + size, + entry0, + entry0 + size, hook_entries, underflows, &i); if (ret != 0) return ret; @@ -993,27 +938,24 @@ translate_table(const char *name, } } - if (!mark_source_chains(newinfo, valid_hooks)) + if (!mark_source_chains(newinfo, valid_hooks, entry0)) return -ELOOP; /* Finally, each sanity check must pass */ i = 0; - ret = IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, + ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, check_entry, name, size, &i); if (ret != 0) { - IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, + IP6T_ENTRY_ITERATE(entry0, newinfo->size, cleanup_entry, &i); return ret; } /* And one copy for every other CPU */ for_each_cpu(i) { - if (i == 0) - continue; - memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i, - newinfo->entries, - SMP_ALIGN(newinfo->size)); + if (newinfo->entries[i] && newinfo->entries[i] != entry0) + memcpy(newinfo->entries[i], entry0, newinfo->size); } return ret; @@ -1029,15 +971,12 @@ replace_table(struct ip6t_table *table, #ifdef CONFIG_NETFILTER_DEBUG { - struct ip6t_entry *table_base; - unsigned int i; + int cpu; - for_each_cpu(i) { - table_base = - (void *)newinfo->entries - + TABLE_OFFSET(newinfo, i); - - table_base->comefrom = 0xdead57ac; + for_each_cpu(cpu) { + struct ip6t_entry *table_base = newinfo->entries[cpu]; + if (table_base) + table_base->comefrom = 0xdead57ac; } } #endif @@ -1072,16 +1011,44 @@ add_entry_to_counter(const struct ip6t_entry *e, return 0; } +static inline int +set_entry_to_counter(const struct ip6t_entry *e, + struct ip6t_counters total[], + unsigned int *i) +{ + SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); + + (*i)++; + return 0; +} + static void get_counters(const struct ip6t_table_info *t, struct ip6t_counters counters[]) { unsigned int cpu; unsigned int i; + unsigned int curcpu; + + /* Instead of clearing (by a previous call to memset()) + * the counters and using adds, we set the counters + * with data used by 'current' CPU + * We dont care about preemption here. + */ + curcpu = raw_smp_processor_id(); + + i = 0; + IP6T_ENTRY_ITERATE(t->entries[curcpu], + t->size, + set_entry_to_counter, + counters, + &i); for_each_cpu(cpu) { + if (cpu == curcpu) + continue; i = 0; - IP6T_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu), + IP6T_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, @@ -1098,6 +1065,7 @@ copy_entries_to_user(unsigned int total_size, struct ip6t_entry *e; struct ip6t_counters *counters; int ret = 0; + void *loc_cpu_entry; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -1109,13 +1077,13 @@ copy_entries_to_user(unsigned int total_size, return -ENOMEM; /* First, sum counters... */ - memset(counters, 0, countersize); write_lock_bh(&table->lock); get_counters(table->private, counters); write_unlock_bh(&table->lock); - /* ... then copy entire thing from CPU 0... */ - if (copy_to_user(userptr, table->private->entries, total_size) != 0) { + /* choose the copy that is on ourc node/cpu */ + loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; goto free_counters; } @@ -1127,7 +1095,7 @@ copy_entries_to_user(unsigned int total_size, struct ip6t_entry_match *m; struct ip6t_entry_target *t; - e = (struct ip6t_entry *)(table->private->entries + off); + e = (struct ip6t_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], @@ -1196,6 +1164,46 @@ get_entries(const struct ip6t_get_entries *entries, return ret; } +static void free_table_info(struct ip6t_table_info *info) +{ + int cpu; + for_each_cpu(cpu) { + if (info->size <= PAGE_SIZE) + kfree(info->entries[cpu]); + else + vfree(info->entries[cpu]); + } + kfree(info); +} + +static struct ip6t_table_info *alloc_table_info(unsigned int size) +{ + struct ip6t_table_info *newinfo; + int cpu; + + newinfo = kzalloc(sizeof(struct ip6t_table_info), GFP_KERNEL); + if (!newinfo) + return NULL; + + newinfo->size = size; + + for_each_cpu(cpu) { + if (size <= PAGE_SIZE) + newinfo->entries[cpu] = kmalloc_node(size, + GFP_KERNEL, + cpu_to_node(cpu)); + else + newinfo->entries[cpu] = vmalloc_node(size, + cpu_to_node(cpu)); + if (newinfo->entries[cpu] == NULL) { + free_table_info(newinfo); + return NULL; + } + } + + return newinfo; +} + static int do_replace(void __user *user, unsigned int len) { @@ -1204,6 +1212,7 @@ do_replace(void __user *user, unsigned int len) struct ip6t_table *t; struct ip6t_table_info *newinfo, *oldinfo; struct ip6t_counters *counters; + void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; @@ -1212,13 +1221,13 @@ do_replace(void __user *user, unsigned int len) if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) return -ENOMEM; - newinfo = vmalloc(sizeof(struct ip6t_table_info) - + SMP_ALIGN(tmp.size) * - (highest_possible_processor_id()+1)); + newinfo = alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; - if (copy_from_user(newinfo->entries, user + sizeof(tmp), + /* choose the copy that is on our node/cpu */ + loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; + if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; @@ -1229,10 +1238,9 @@ do_replace(void __user *user, unsigned int len) ret = -ENOMEM; goto free_newinfo; } - memset(counters, 0, tmp.num_counters * sizeof(struct ip6t_counters)); ret = translate_table(tmp.name, tmp.valid_hooks, - newinfo, tmp.size, tmp.num_entries, + newinfo, loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); if (ret != 0) goto free_newinfo_counters; @@ -1271,8 +1279,9 @@ do_replace(void __user *user, unsigned int len) /* Get the old counters. */ get_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ - IP6T_ENTRY_ITERATE(oldinfo->entries, oldinfo->size, cleanup_entry,NULL); - vfree(oldinfo); + loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; + IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); + free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, sizeof(struct ip6t_counters) * tmp.num_counters) != 0) ret = -EFAULT; @@ -1284,11 +1293,11 @@ do_replace(void __user *user, unsigned int len) module_put(t->me); up(&ip6t_mutex); free_newinfo_counters_untrans: - IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, cleanup_entry,NULL); + IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL); free_newinfo_counters: vfree(counters); free_newinfo: - vfree(newinfo); + free_table_info(newinfo); return ret; } @@ -1321,6 +1330,7 @@ do_add_counters(void __user *user, unsigned int len) struct ip6t_counters_info tmp, *paddc; struct ip6t_table *t; int ret = 0; + void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; @@ -1350,7 +1360,9 @@ do_add_counters(void __user *user, unsigned int len) } i = 0; - IP6T_ENTRY_ITERATE(t->private->entries, + /* Choose the copy that is on our node */ + loc_cpu_entry = t->private->entries[smp_processor_id()]; + IP6T_ENTRY_ITERATE(loc_cpu_entry, t->private->size, add_counter_to_entry, paddc->counters, @@ -1543,28 +1555,29 @@ int ip6t_register_table(struct ip6t_table *table, struct ip6t_table_info *newinfo; static struct ip6t_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; + void *loc_cpu_entry; - newinfo = vmalloc(sizeof(struct ip6t_table_info) - + SMP_ALIGN(repl->size) * - (highest_possible_processor_id()+1)); + newinfo = alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; - memcpy(newinfo->entries, repl->entries, repl->size); + /* choose the copy on our node/cpu */ + loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; + memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(table->name, table->valid_hooks, - newinfo, repl->size, + newinfo, loc_cpu_entry, repl->size, repl->num_entries, repl->hook_entry, repl->underflow); if (ret != 0) { - vfree(newinfo); + free_table_info(newinfo); return ret; } ret = down_interruptible(&ip6t_mutex); if (ret != 0) { - vfree(newinfo); + free_table_info(newinfo); return ret; } @@ -1593,20 +1606,23 @@ int ip6t_register_table(struct ip6t_table *table, return ret; free_unlock: - vfree(newinfo); + free_table_info(newinfo); goto unlock; } void ip6t_unregister_table(struct ip6t_table *table) { + void *loc_cpu_entry; + down(&ip6t_mutex); LIST_DELETE(&ip6t_tables, table); up(&ip6t_mutex); /* Decrease module usage counts and free resources */ - IP6T_ENTRY_ITERATE(table->private->entries, table->private->size, + loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + IP6T_ENTRY_ITERATE(loc_cpu_entry, table->private->size, cleanup_entry, NULL); - vfree(table->private); + free_table_info(table->private); } /* Returns 1 if the port is matched by the range, 0 otherwise */ @@ -2035,26 +2051,39 @@ static void __exit fini(void) } /* - * find specified header up to transport protocol header. - * If found target header, the offset to the header is set to *offset - * and return 0. otherwise, return -1. + * find the offset to specified header or the protocol number of last header + * if target < 0. "last header" is transport protocol header, ESP, or + * "No next header". + * + * If target header is found, its offset is set in *offset and return protocol + * number. Otherwise, return -1. + * + * Note that non-1st fragment is special case that "the protocol number + * of last header" is "next header" field in Fragment header. In this case, + * *offset is meaningless and fragment offset is stored in *fragoff if fragoff + * isn't NULL. * - * Notes: - non-1st Fragment Header isn't skipped. - * - ESP header isn't skipped. - * - The target header may be trancated. */ -int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, u8 target) +int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, + int target, unsigned short *fragoff) { unsigned int start = (u8*)(skb->nh.ipv6h + 1) - skb->data; u8 nexthdr = skb->nh.ipv6h->nexthdr; unsigned int len = skb->len - start; + if (fragoff) + *fragoff = 0; + while (nexthdr != target) { struct ipv6_opt_hdr _hdr, *hp; unsigned int hdrlen; - if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) + if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { + if (target < 0) + break; return -1; + } + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); if (hp == NULL) return -1; @@ -2068,8 +2097,17 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, u8 target) if (fp == NULL) return -1; - if (ntohs(*fp) & ~0x7) + _frag_off = ntohs(*fp) & ~0x7; + if (_frag_off) { + if (target < 0 && + ((!ipv6_ext_hdr(hp->nexthdr)) || + nexthdr == NEXTHDR_NONE)) { + if (fragoff) + *fragoff = _frag_off; + return hp->nexthdr; + } return -1; + } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) hdrlen = (hp->hdrlen + 2) << 2; @@ -2082,7 +2120,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, u8 target) } *offset = start; - return 0; + return nexthdr; } EXPORT_SYMBOL(ip6t_register_table); @@ -2094,6 +2132,7 @@ EXPORT_SYMBOL(ip6t_register_target); EXPORT_SYMBOL(ip6t_unregister_target); EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); +EXPORT_SYMBOL(ip6_masked_addrcmp); module_init(init); module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 0cd1d1b..ae4653b 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/skbuff.h> +#include <linux/if_arp.h> #include <linux/ip.h> #include <linux/spinlock.h> #include <linux/icmpv6.h> diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index dde3779..f5c1a7ff 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/ip.h> #include <linux/ipv6.h> #include <linux/types.h> #include <net/checksum.h> @@ -53,7 +54,7 @@ match(const struct sk_buff *skb, unsigned int ptr; unsigned int hdrlen = 0; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL) < 0) return 0; ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c index c450a63..48cf5f9 100644 --- a/net/ipv6/netfilter/ip6t_dst.c +++ b/net/ipv6/netfilter/ip6t_dst.c @@ -71,9 +71,9 @@ match(const struct sk_buff *skb, unsigned int optlen; #if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0) #else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0) #endif return 0; diff --git a/net/ipv6/netfilter/ip6t_esp.c b/net/ipv6/netfilter/ip6t_esp.c index 24bc0cd..e1828f6 100644 --- a/net/ipv6/netfilter/ip6t_esp.c +++ b/net/ipv6/netfilter/ip6t_esp.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/ip.h> #include <linux/ipv6.h> #include <linux/types.h> #include <net/checksum.h> @@ -55,7 +56,7 @@ match(const struct sk_buff *skb, /* Make sure this isn't an evil packet */ /*DEBUGP("ipv6_esp entered \n");*/ - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ESP) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ESP, NULL) < 0) return 0; eh = skb_header_pointer(skb, ptr, sizeof(_esp), &_esp); diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 085d5f8..d1549b2 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -52,7 +52,7 @@ match(const struct sk_buff *skb, const struct ip6t_frag *fraginfo = matchinfo; unsigned int ptr; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL) < 0) return 0; fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag); diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 1d09485..e3bc8e2 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -71,9 +71,9 @@ match(const struct sk_buff *skb, unsigned int optlen; #if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0) #else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0) #endif return 0; diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index beb2fd5..c1e770e 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -58,7 +58,7 @@ match(const struct sk_buff *skb, unsigned int ret = 0; struct in6_addr *ap, _addr; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING) < 0) + if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL) < 0) return 0; rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 753a3ae..704fbbe 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -401,6 +401,48 @@ static ctl_table nf_ct_net_table[] = { }; #endif +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static int ipv6_tuple_to_nfattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + NFA_PUT(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4, + &tuple->src.u3.ip6); + NFA_PUT(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4, + &tuple->dst.u3.ip6); + return 0; + +nfattr_failure: + return -1; +} + +static const size_t cta_min_ip[CTA_IP_MAX] = { + [CTA_IP_V6_SRC-1] = sizeof(u_int32_t)*4, + [CTA_IP_V6_DST-1] = sizeof(u_int32_t)*4, +}; + +static int ipv6_nfattr_to_tuple(struct nfattr *tb[], + struct nf_conntrack_tuple *t) +{ + if (!tb[CTA_IP_V6_SRC-1] || !tb[CTA_IP_V6_DST-1]) + return -EINVAL; + + if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip)) + return -EINVAL; + + memcpy(&t->src.u3.ip6, NFA_DATA(tb[CTA_IP_V6_SRC-1]), + sizeof(u_int32_t) * 4); + memcpy(&t->dst.u3.ip6, NFA_DATA(tb[CTA_IP_V6_DST-1]), + sizeof(u_int32_t) * 4); + + return 0; +} +#endif + struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, .name = "ipv6", @@ -409,6 +451,11 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .print_tuple = ipv6_print_tuple, .print_conntrack = ipv6_print_conntrack, .prepare = ipv6_prepare, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = ipv6_tuple_to_nfattr, + .nfattr_to_tuple = ipv6_nfattr_to_tuple, +#endif .get_features = ipv6_get_features, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index c0f1da5..09945c3 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -57,19 +57,19 @@ static int icmpv6_pkt_to_tuple(const struct sk_buff *skb, return 1; } +/* Add 1; spaces filled with 0. */ +static u_int8_t invmap[] = { + [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, + [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_QUERY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_REPLY +1 +}; + static int icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { - /* Add 1; spaces filled with 0. */ - static u_int8_t invmap[] = { - [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, - [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, - [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_QUERY + 1, - [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_REPLY +1 - }; - - __u8 type = orig->dst.u.icmp.type - 128; - if (type >= sizeof(invmap) || !invmap[type]) + int type = orig->dst.u.icmp.type - 128; + if (type < 0 || type >= sizeof(invmap) || !invmap[type]) return 0; tuple->src.u.icmp.id = orig->src.u.icmp.id; @@ -129,12 +129,12 @@ static int icmpv6_new(struct nf_conn *conntrack, [ICMPV6_ECHO_REQUEST - 128] = 1, [ICMPV6_NI_QUERY - 128] = 1 }; + int type = conntrack->tuplehash[0].tuple.dst.u.icmp.type - 128; - if (conntrack->tuplehash[0].tuple.dst.u.icmp.type - 128 >= sizeof(valid_new) - || !valid_new[conntrack->tuplehash[0].tuple.dst.u.icmp.type - 128]) { + if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { /* Can't create a new ICMPv6 `conn' with this. */ - DEBUGP("icmp: can't create new conn with type %u\n", - conntrack->tuplehash[0].tuple.dst.u.icmp.type); + DEBUGP("icmpv6: can't create new conn with type %u\n", + type + 128); NF_CT_DUMP_TUPLE(&conntrack->tuplehash[0].tuple); return 0; } @@ -185,7 +185,7 @@ icmpv6_error_message(struct sk_buff *skb, return -NF_ACCEPT; } - inproto = nf_ct_find_proto(PF_INET6, inprotonum); + inproto = __nf_ct_proto_find(PF_INET6, inprotonum); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuple(skb, inip6off, inprotoff, PF_INET6, inprotonum, @@ -255,6 +255,60 @@ skipped: return icmpv6_error_message(skb, dataoff, ctinfo, hooknum); } +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +static int icmpv6_tuple_to_nfattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + NFA_PUT(skb, CTA_PROTO_ICMPV6_ID, sizeof(u_int16_t), + &t->src.u.icmp.id); + NFA_PUT(skb, CTA_PROTO_ICMPV6_TYPE, sizeof(u_int8_t), + &t->dst.u.icmp.type); + NFA_PUT(skb, CTA_PROTO_ICMPV6_CODE, sizeof(u_int8_t), + &t->dst.u.icmp.code); + + return 0; + +nfattr_failure: + return -1; +} + +static const size_t cta_min_proto[CTA_PROTO_MAX] = { + [CTA_PROTO_ICMPV6_TYPE-1] = sizeof(u_int8_t), + [CTA_PROTO_ICMPV6_CODE-1] = sizeof(u_int8_t), + [CTA_PROTO_ICMPV6_ID-1] = sizeof(u_int16_t) +}; + +static int icmpv6_nfattr_to_tuple(struct nfattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMPV6_TYPE-1] + || !tb[CTA_PROTO_ICMPV6_CODE-1] + || !tb[CTA_PROTO_ICMPV6_ID-1]) + return -EINVAL; + + if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto)) + return -EINVAL; + + tuple->dst.u.icmp.type = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMPV6_TYPE-1]); + tuple->dst.u.icmp.code = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMPV6_CODE-1]); + tuple->src.u.icmp.id = + *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_ICMPV6_ID-1]); + + if (tuple->dst.u.icmp.type < 128 + || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) + || !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + + return 0; +} +#endif + struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6 = { .l3proto = PF_INET6, @@ -267,6 +321,11 @@ struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6 = .packet = icmpv6_packet, .new = icmpv6_new, .error = icmpv6_error, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = icmpv6_tuple_to_nfattr, + .nfattr_to_tuple = icmpv6_nfattr_to_tuple, +#endif }; EXPORT_SYMBOL(nf_conntrack_protocol_icmpv6); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index c2c52af..f3e5ffb 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -98,7 +98,7 @@ struct nf_ct_frag6_queue #define FRAG6Q_HASHSZ 64 static struct nf_ct_frag6_queue *nf_ct_frag6_hash[FRAG6Q_HASHSZ]; -static rwlock_t nf_ct_frag6_lock = RW_LOCK_UNLOCKED; +static DEFINE_RWLOCK(nf_ct_frag6_lock); static u32 nf_ct_frag6_hash_rnd; static LIST_HEAD(nf_ct_frag6_lru_list); int nf_ct_frag6_nqueues = 0; @@ -371,7 +371,7 @@ nf_ct_frag6_create(unsigned int hash, u32 id, struct in6_addr *src, struct init_timer(&fq->timer); fq->timer.function = nf_ct_frag6_expire; fq->timer.data = (long) fq; - fq->lock = SPIN_LOCK_UNLOCKED; + spin_lock_init(&fq->lock); atomic_set(&fq->refcnt, 1); return nf_ct_frag6_intern(hash, fq); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a66900c..66f1d12 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -32,6 +32,7 @@ #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +#include <linux/skbuff.h> #include <asm/uaccess.h> #include <asm/ioctls.h> #include <asm/bug.h> @@ -433,25 +434,14 @@ out: return err; csum_copy_err: - /* Clear queue. */ - if (flags&MSG_PEEK) { - int clear = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); - clear = 1; - } - spin_unlock_bh(&sk->sk_receive_queue.lock); - if (clear) - kfree_skb(skb); - } + skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; /* FIXME: increment a raw6 drops counter here */ - goto out_free; + goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a7a537b..66140f1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -413,11 +413,14 @@ static struct rt6_info *rt6_cow(struct rt6_info *ort, struct in6_addr *daddr, rt = ip6_rt_copy(ort); if (rt) { - ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); - - if (!(rt->rt6i_flags&RTF_GATEWAY)) + if (!(rt->rt6i_flags&RTF_GATEWAY)) { + if (rt->rt6i_dst.plen != 128 && + ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)) + rt->rt6i_flags |= RTF_ANYCAST; ipv6_addr_copy(&rt->rt6i_gateway, daddr); + } + ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; rt->u.dst.flags |= DST_HOST; @@ -829,7 +832,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } rt->u.dst.obsolete = -1; - rt->rt6i_expires = clock_t_to_jiffies(rtmsg->rtmsg_info); + rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info); if (nlh && (r = NLMSG_DATA(nlh))) { rt->rt6i_protocol = r->rtm_protocol; } else { @@ -1413,7 +1416,9 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->u.dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; - if (!anycast) + if (anycast) + rt->rt6i_flags |= RTF_ANYCAST; + else rt->rt6i_flags |= RTF_LOCAL; rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); if (rt->rt6i_nexthop == NULL) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c3123c9..577d497 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -33,6 +33,7 @@ #include <asm/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> +#include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> @@ -720,7 +721,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); - dev->mtu = 1500 - sizeof(struct iphdr); + dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr); dev->flags = IFF_NOARP; dev->iflink = 0; dev->addr_len = 4; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 62c0e5b..2947bc5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -48,6 +48,7 @@ #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> +#include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> @@ -59,6 +60,7 @@ #include <net/addrconf.h> #include <net/snmp.h> #include <net/dsfield.h> +#include <net/timewait_sock.h> #include <asm/uaccess.h> @@ -67,224 +69,33 @@ static void tcp_v6_send_reset(struct sk_buff *skb); static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); -static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, +static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok); -static struct tcp_func ipv6_mapped; -static struct tcp_func ipv6_specific; +static struct inet_connection_sock_af_ops ipv6_mapped; +static struct inet_connection_sock_af_ops ipv6_specific; -static inline int tcp_v6_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb) -{ - const struct sock *sk2; - const struct hlist_node *node; - - /* We must walk the whole port owner list in this case. -DaveM */ - sk_for_each_bound(sk2, node, &tb->owners) { - if (sk != sk2 && - (!sk->sk_bound_dev_if || - !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && - (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; - } - - return node != NULL; -} - -/* Grrr, addr_type already calculated by caller, but I don't want - * to add some silly "cookie" argument to this method just for that. - * But it doesn't matter, the recalculation is in the rarest path - * this function ever takes. - */ static int tcp_v6_get_port(struct sock *sk, unsigned short snum) { - struct inet_bind_hashbucket *head; - struct inet_bind_bucket *tb; - struct hlist_node *node; - int ret; - - local_bh_disable(); - if (snum == 0) { - int low = sysctl_local_port_range[0]; - int high = sysctl_local_port_range[1]; - int remaining = (high - low) + 1; - int rover = net_random() % (high - low) + low; - - do { - head = &tcp_hashinfo.bhash[inet_bhashfn(rover, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->port == rover) - goto next; - break; - next: - spin_unlock(&head->lock); - if (++rover > high) - rover = low; - } while (--remaining > 0); - - /* Exhausted local port range during search? It is not - * possible for us to be holding one of the bind hash - * locks if this test triggers, because if 'remaining' - * drops to zero, we broke out of the do/while loop at - * the top level, not from the 'break;' statement. - */ - ret = 1; - if (unlikely(remaining <= 0)) - goto fail; - - /* OK, here is the one we will use. */ - snum = rover; - } else { - head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->port == snum) - goto tb_found; - } - tb = NULL; - goto tb_not_found; -tb_found: - if (tb && !hlist_empty(&tb->owners)) { - if (tb->fastreuse > 0 && sk->sk_reuse && - sk->sk_state != TCP_LISTEN) { - goto success; - } else { - ret = 1; - if (tcp_v6_bind_conflict(sk, tb)) - goto fail_unlock; - } - } -tb_not_found: - ret = 1; - if (tb == NULL) { - tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, snum); - if (tb == NULL) - goto fail_unlock; - } - if (hlist_empty(&tb->owners)) { - if (sk->sk_reuse && sk->sk_state != TCP_LISTEN) - tb->fastreuse = 1; - else - tb->fastreuse = 0; - } else if (tb->fastreuse && - (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) - tb->fastreuse = 0; - -success: - if (!inet_csk(sk)->icsk_bind_hash) - inet_bind_hash(sk, tb, snum); - BUG_TRAP(inet_csk(sk)->icsk_bind_hash == tb); - ret = 0; - -fail_unlock: - spin_unlock(&head->lock); -fail: - local_bh_enable(); - return ret; -} - -static __inline__ void __tcp_v6_hash(struct sock *sk) -{ - struct hlist_head *list; - rwlock_t *lock; - - BUG_TRAP(sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - list = &tcp_hashinfo.listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &tcp_hashinfo.lhash_lock; - inet_listen_wlock(&tcp_hashinfo); - } else { - unsigned int hash; - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - hash &= (tcp_hashinfo.ehash_size - 1); - list = &tcp_hashinfo.ehash[hash].chain; - lock = &tcp_hashinfo.ehash[hash].lock; - write_lock(lock); - } - - __sk_add_node(sk, list); - sock_prot_inc_use(sk->sk_prot); - write_unlock(lock); + return inet_csk_get_port(&tcp_hashinfo, sk, snum, + inet6_csk_bind_conflict); } - static void tcp_v6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->af_specific == &ipv6_mapped) { + if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { tcp_prot.hash(sk); return; } local_bh_disable(); - __tcp_v6_hash(sk); + __inet6_hash(&tcp_hashinfo, sk); local_bh_enable(); } } -/* - * Open request hash tables. - */ - -static u32 tcp_v6_synq_hash(const struct in6_addr *raddr, const u16 rport, const u32 rnd) -{ - u32 a, b, c; - - a = raddr->s6_addr32[0]; - b = raddr->s6_addr32[1]; - c = raddr->s6_addr32[2]; - - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; - c += rnd; - __jhash_mix(a, b, c); - - a += raddr->s6_addr32[3]; - b += (u32) rport; - __jhash_mix(a, b, c); - - return c & (TCP_SYNQ_HSIZE - 1); -} - -static struct request_sock *tcp_v6_search_req(const struct sock *sk, - struct request_sock ***prevp, - __u16 rport, - struct in6_addr *raddr, - struct in6_addr *laddr, - int iif) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; - - for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; - (req = *prev) != NULL; - prev = &req->dl_next) { - const struct tcp6_request_sock *treq = tcp6_rsk(req); - - if (inet_rsk(req)->rmt_port == rport && - req->rsk_ops->family == AF_INET6 && - ipv6_addr_equal(&treq->rmt_addr, raddr) && - ipv6_addr_equal(&treq->loc_addr, laddr) && - (!treq->iif || treq->iif == iif)) { - BUG_TRAP(req->sk == NULL); - *prevp = prev; - return req; - } - } - - return NULL; -} - static __inline__ u16 tcp_v6_check(struct tcphdr *th, int len, struct in6_addr *saddr, struct in6_addr *daddr, @@ -308,195 +119,12 @@ static __u32 tcp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) } } -static int __tcp_v6_check_established(struct sock *sk, const __u16 lport, - struct inet_timewait_sock **twp) -{ - struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - const struct in6_addr *daddr = &np->rcv_saddr; - const struct in6_addr *saddr = &np->daddr; - const int dif = sk->sk_bound_dev_if; - const u32 ports = INET_COMBINED_PORTS(inet->dport, lport); - unsigned int hash = inet6_ehashfn(daddr, inet->num, saddr, inet->dport); - struct inet_ehash_bucket *head = inet_ehash_bucket(&tcp_hashinfo, hash); - struct sock *sk2; - const struct hlist_node *node; - struct inet_timewait_sock *tw; - - prefetch(head->chain.first); - write_lock(&head->lock); - - /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &(head + tcp_hashinfo.ehash_size)->chain) { - const struct tcp6_timewait_sock *tcp6tw = tcp6_twsk(sk2); - - tw = inet_twsk(sk2); - - if(*((__u32 *)&(tw->tw_dport)) == ports && - sk2->sk_family == PF_INET6 && - ipv6_addr_equal(&tcp6tw->tw_v6_daddr, saddr) && - ipv6_addr_equal(&tcp6tw->tw_v6_rcv_saddr, daddr) && - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) { - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk2); - struct tcp_sock *tp = tcp_sk(sk); - - if (tcptw->tw_ts_recent_stamp && - (!twp || - (sysctl_tcp_tw_reuse && - xtime.tv_sec - tcptw->tw_ts_recent_stamp > 1))) { - /* See comment in tcp_ipv4.c */ - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (!tp->write_seq) - tp->write_seq = 1; - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; - sock_hold(sk2); - goto unique; - } else - goto not_unique; - } - } - tw = NULL; - - /* And established part... */ - sk_for_each(sk2, node, &head->chain) { - if (INET6_MATCH(sk2, hash, saddr, daddr, ports, dif)) - goto not_unique; - } - -unique: - BUG_TRAP(sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); - sk->sk_hash = hash; - sock_prot_inc_use(sk->sk_prot); - write_unlock(&head->lock); - - if (twp) { - *twp = tw; - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw) { - /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw, &tcp_death_row); - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - - inet_twsk_put(tw); - } - return 0; - -not_unique: - write_unlock(&head->lock); - return -EADDRNOTAVAIL; -} - -static inline u32 tcpv6_port_offset(const struct sock *sk) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - - return secure_tcpv6_port_ephemeral(np->rcv_saddr.s6_addr32, - np->daddr.s6_addr32, - inet->dport); -} - -static int tcp_v6_hash_connect(struct sock *sk) -{ - unsigned short snum = inet_sk(sk)->num; - struct inet_bind_hashbucket *head; - struct inet_bind_bucket *tb; - int ret; - - if (!snum) { - int low = sysctl_local_port_range[0]; - int high = sysctl_local_port_range[1]; - int range = high - low; - int i; - int port; - static u32 hint; - u32 offset = hint + tcpv6_port_offset(sk); - struct hlist_node *node; - struct inet_timewait_sock *tw = NULL; - - local_bh_disable(); - for (i = 1; i <= range; i++) { - port = low + (i + offset) % range; - head = &tcp_hashinfo.bhash[inet_bhashfn(port, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - - /* Does not bother with rcv_saddr checks, - * because the established check is already - * unique enough. - */ - inet_bind_bucket_for_each(tb, node, &head->chain) { - if (tb->port == port) { - BUG_TRAP(!hlist_empty(&tb->owners)); - if (tb->fastreuse >= 0) - goto next_port; - if (!__tcp_v6_check_established(sk, - port, - &tw)) - goto ok; - goto next_port; - } - } - - tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, port); - if (!tb) { - spin_unlock(&head->lock); - break; - } - tb->fastreuse = -1; - goto ok; - - next_port: - spin_unlock(&head->lock); - } - local_bh_enable(); - - return -EADDRNOTAVAIL; - -ok: - hint += i; - - /* Head lock still held and bh's disabled */ - inet_bind_hash(sk, tb, port); - if (sk_unhashed(sk)) { - inet_sk(sk)->sport = htons(port); - __tcp_v6_hash(sk); - } - spin_unlock(&head->lock); - - if (tw) { - inet_twsk_deschedule(tw, &tcp_death_row); - inet_twsk_put(tw); - } - - ret = 0; - goto out; - } - - head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - - if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - __tcp_v6_hash(sk); - spin_unlock_bh(&head->lock); - return 0; - } else { - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ - ret = __tcp_v6_check_established(sk, snum, NULL); -out: - local_bh_enable(); - return ret; - } -} - static int tcp_v6_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 inet_sock *inet = inet_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p = NULL, final; @@ -571,7 +199,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, */ if (addr_type == IPV6_ADDR_MAPPED) { - u32 exthdrlen = tp->ext_header_len; + u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); @@ -583,14 +211,14 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; - tp->af_specific = &ipv6_mapped; + icsk->icsk_af_ops = &ipv6_mapped; sk->sk_backlog_rcv = tcp_v4_do_rcv; err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { - tp->ext_header_len = exthdrlen; - tp->af_specific = &ipv6_specific; + icsk->icsk_ext_hdr_len = exthdrlen; + icsk->icsk_af_ops = &ipv6_specific; sk->sk_backlog_rcv = tcp_v6_do_rcv; goto failure; } else { @@ -643,16 +271,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); - tp->ext_header_len = 0; + icsk->icsk_ext_hdr_len = 0; if (np->opt) - tp->ext_header_len = np->opt->opt_flen + np->opt->opt_nflen; + icsk->icsk_ext_hdr_len = (np->opt->opt_flen + + np->opt->opt_nflen); tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); - err = tcp_v6_hash_connect(sk); + err = inet6_hash_connect(&tcp_death_row, sk); if (err) goto late_failure; @@ -758,7 +387,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } else dst_hold(dst); - if (tp->pmtu_cookie > dst_mtu(dst)) { + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ @@ -775,8 +404,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sock_owned_by_user(sk)) goto out; - req = tcp_v6_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); + req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, + &hdr->saddr, inet6_iif(skb)); if (!req) goto out; @@ -822,7 +451,7 @@ out: static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { - struct tcp6_request_sock *treq = tcp6_rsk(req); + struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; struct ipv6_txoptions *opt = NULL; @@ -888,8 +517,8 @@ done: static void tcp_v6_reqsk_destructor(struct request_sock *req) { - if (tcp6_rsk(req)->pktopts) - kfree_skb(tcp6_rsk(req)->pktopts); + if (inet6_rsk(req)->pktopts) + kfree_skb(inet6_rsk(req)->pktopts); } static struct request_sock_ops tcp6_request_sock_ops = { @@ -901,26 +530,15 @@ static struct request_sock_ops tcp6_request_sock_ops = { .send_reset = tcp_v6_send_reset }; -static 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; -} - +static struct timewait_sock_ops tcp6_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp6_timewait_sock), + .twsk_unique = tcp_twsk_unique, +}; -static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, - struct sk_buff *skb) +static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); + struct tcphdr *th = skb->h.th; if (skb->ip_summed == CHECKSUM_HW) { th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); @@ -992,13 +610,12 @@ static void tcp_v6_send_reset(struct sk_buff *skb) /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { - if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) + if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, buff, &fl, NULL, 0); + TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(TCP_MIB_OUTRSTS); return; - - ip6_xmit(NULL, buff, &fl, NULL, 0); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(TCP_MIB_OUTRSTS); - return; + } } kfree_skb(buff); @@ -1057,11 +674,11 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 fl.fl_ip_sport = t1->source; if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { - if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) + if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, buff, &fl, NULL, 0); + TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); return; - ip6_xmit(NULL, buff, &fl, NULL, 0); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); - return; + } } kfree_skb(buff); @@ -1092,8 +709,9 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) struct sock *nsk; /* Find possible connection requests. */ - req = tcp_v6_search_req(sk, &prev, th->source, &skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr, inet6_iif(skb)); + req = inet6_csk_search_req(sk, &prev, th->source, + &skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, inet6_iif(skb)); if (req) return tcp_check_req(sk, skb, req, prev); @@ -1117,23 +735,12 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) return sk; } -static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - const u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); - - reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, TCP_TIMEOUT_INIT); - inet_csk_reqsk_queue_added(sk, TCP_TIMEOUT_INIT); -} - - /* FIXME: this is substantially similar to the ipv4 code. * Can some kind of merge be done? -- erics */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp6_request_sock *treq; + struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); @@ -1158,7 +765,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&tcp6_request_sock_ops); + req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) goto drop; @@ -1171,7 +778,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); - treq = tcp6_rsk(req); + treq = inet6_rsk(req); ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr); ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr); TCP_ECN_create_request(req, skb->h.th); @@ -1197,8 +804,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (tcp_v6_send_synack(sk, req, NULL)) goto drop; - tcp_v6_synq_add(sk, req); - + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; drop: @@ -1213,7 +819,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { - struct tcp6_request_sock *treq = tcp6_rsk(req); + struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; @@ -1248,7 +854,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); - newtp->af_specific = &ipv6_mapped; + inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; @@ -1262,10 +868,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ /* It is tricky place. Until this moment IPv4 tcp - worked with IPv6 af_tcp.af_specific. + worked with IPv6 icsk.icsk_af_ops. Sync it now. */ - tcp_sync_mss(newsk, newtp->pmtu_cookie); + tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } @@ -1372,10 +978,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, sock_kfree_s(sk, opt, opt->tot_len); } - newtp->ext_header_len = 0; + inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt) - newtp->ext_header_len = newnp->opt->opt_nflen + - newnp->opt->opt_flen; + inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + + newnp->opt->opt_flen); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric(dst, RTAX_ADVMSS); @@ -1383,7 +989,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; - __tcp_v6_hash(newsk); + __inet6_hash(&tcp_hashinfo, newsk); inet_inherit_port(&tcp_hashinfo, sk, newsk); return newsk; @@ -1680,139 +1286,16 @@ do_time_wait: goto discard_it; } -static int tcp_v6_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 = IPPROTO_TCP; - 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; -} - -static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok) -{ - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi fl; - struct dst_entry *dst; - struct in6_addr *final_p = NULL, final; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl6_flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_sport = inet->sport; - fl.fl_ip_dport = inet->dport; - - 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; - } - - dst = __sk_dst_check(sk, np->dst_cookie); - - if (dst == NULL) { - int err = ip6_dst_lookup(sk, &dst, &fl); - - if (err) { - sk->sk_err_soft = -err; - return err; - } - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { - sk->sk_route_caps = 0; - return err; - } - - ip6_dst_store(sk, dst, NULL); - sk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); - } - - skb->dst = dst_clone(dst); - - /* Restore final destination back after routing done */ - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - - return ip6_xmit(sk, skb, &fl, np->opt, 0); -} - -static void v6_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; - - sin6->sin6_family = AF_INET6; - ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); - sin6->sin6_port = inet_sk(sk)->dport; - /* We do not store received flowlabel for TCP */ - sin6->sin6_flowinfo = 0; - sin6->sin6_scope_id = 0; - if (sk->sk_bound_dev_if && - ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin6->sin6_scope_id = sk->sk_bound_dev_if; -} - static int tcp_v6_remember_stamp(struct sock *sk) { /* Alas, not yet... */ return 0; } -static struct tcp_func ipv6_specific = { - .queue_xmit = tcp_v6_xmit, +static struct inet_connection_sock_af_ops ipv6_specific = { + .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, - .rebuild_header = tcp_v6_rebuild_header, + .rebuild_header = inet6_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .remember_stamp = tcp_v6_remember_stamp, @@ -1820,7 +1303,7 @@ static struct tcp_func ipv6_specific = { .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, - .addr2sockaddr = v6_addr2sockaddr, + .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6) }; @@ -1828,7 +1311,7 @@ static struct tcp_func ipv6_specific = { * TCP over IPv4 via INET6 API */ -static struct tcp_func ipv6_mapped = { +static struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1839,7 +1322,7 @@ static struct tcp_func ipv6_mapped = { .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, - .addr2sockaddr = v6_addr2sockaddr, + .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6) }; @@ -1878,8 +1361,9 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_state = TCP_CLOSE; - tp->af_specific = &ipv6_specific; + icsk->icsk_af_ops = &ipv6_specific; icsk->icsk_ca_ops = &tcp_init_congestion_ops; + icsk->icsk_sync_mss = tcp_sync_mss; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); @@ -1901,14 +1385,13 @@ static int tcp_v6_destroy_sock(struct sock *sk) static void get_openreq6(struct seq_file *seq, struct sock *sk, struct request_sock *req, int i, int uid) { - struct in6_addr *dest, *src; int ttd = req->expires - jiffies; + struct in6_addr *src = &inet6_rsk(req)->loc_addr; + struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; if (ttd < 0) ttd = 0; - src = &tcp6_rsk(req)->loc_addr; - dest = &tcp6_rsk(req)->rmt_addr; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", @@ -1989,14 +1472,14 @@ static void get_timewait6_sock(struct seq_file *seq, { struct in6_addr *dest, *src; __u16 destp, srcp; - struct tcp6_timewait_sock *tcp6tw = tcp6_twsk((struct sock *)tw); + struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); int ttd = tw->tw_ttd - jiffies; if (ttd < 0) ttd = 0; - dest = &tcp6tw->tw_v6_daddr; - src = &tcp6tw->tw_v6_rcv_saddr; + dest = &tw6->tw_v6_daddr; + src = &tw6->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); @@ -2094,7 +1577,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), - .twsk_obj_size = sizeof(struct tcp6_timewait_sock), + .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, }; @@ -2111,7 +1594,8 @@ static struct inet_protosw tcpv6_protosw = { .ops = &inet6_stream_ops, .capability = -1, .no_check = 0, - .flags = INET_PROTOSW_PERMANENT, + .flags = INET_PROTOSW_PERMANENT | + INET_PROTOSW_ICSK, }; void __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5cc8731..d8538dc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -36,6 +36,7 @@ #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/init.h> +#include <linux/skbuff.h> #include <asm/uaccess.h> #include <net/sock.h> @@ -300,20 +301,7 @@ out: return err; csum_copy_err: - /* Clear queue. */ - if (flags&MSG_PEEK) { - int clear = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); - clear = 1; - } - spin_unlock_bh(&sk->sk_receive_queue.lock); - if (clear) - kfree_skb(skb); - } - - skb_free_datagram(sk, skb); + skb_kill_datagram(sk, skb, flags); if (flags & MSG_DONTWAIT) { UDP6_INC_STATS_USER(UDP_MIB_INERRORS); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cf1d91e..69bd957 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -214,6 +214,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) case IPPROTO_UDP: case IPPROTO_TCP: case IPPROTO_SCTP: + case IPPROTO_DCCP: if (pskb_may_pull(skb, skb->nh.raw + offset + 4 - skb->data)) { u16 *ports = (u16 *)exthdr; |