diff options
Diffstat (limited to 'net/ipv6')
29 files changed, 723 insertions, 432 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 324fac3b6c16..e048ec62d109 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -243,7 +243,7 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev) /* Check if a route is valid prefix route */ static inline int addrconf_is_prefix_route(const struct rt6_info *rt) { - return ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0); + return (rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0; } static void addrconf_del_timer(struct inet6_ifaddr *ifp) @@ -836,7 +836,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; - unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp; + unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp, age; unsigned long regen_advance; int tmp_plen; int ret = 0; @@ -886,12 +886,13 @@ retry: goto out; } memcpy(&addr.s6_addr[8], idev->rndid, 8); + age = (jiffies - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, ifp->valid_lft, - idev->cnf.temp_valid_lft); + idev->cnf.temp_valid_lft + age); tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, - idev->cnf.temp_prefered_lft - + idev->cnf.temp_prefered_lft + age - idev->cnf.max_desync_factor); tmp_plen = ifp->prefix_len; max_addresses = idev->cnf.max_addresses; @@ -1426,8 +1427,10 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; - if (addrconf_dad_end(ifp)) + if (addrconf_dad_end(ifp)) { + in6_ifa_put(ifp); return; + } if (net_ratelimit()) printk(KERN_INFO "%s: IPv6 duplicate address %pI6c detected!\n", @@ -1544,7 +1547,7 @@ static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) return 0; } -int __ipv6_isatap_ifid(u8 *eui, __be32 addr) +static int __ipv6_isatap_ifid(u8 *eui, __be32 addr) { if (addr == 0) return -1; @@ -1560,7 +1563,6 @@ int __ipv6_isatap_ifid(u8 *eui, __be32 addr) memcpy(eui + 4, &addr, 4); return 0; } -EXPORT_SYMBOL(__ipv6_isatap_ifid); static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) { @@ -2022,10 +2024,11 @@ ok: ipv6_ifa_notify(0, ift); } - if (create && in6_dev->cnf.use_tempaddr > 0) { + if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) { /* * When a new public address is created as described in [ADDRCONF], - * also create a new temporary address. + * also create a new temporary address. Also create a temporary + * address if it's enabled but no temporary address currently exists. */ read_unlock_bh(&in6_dev->lock); ipv6_create_tempaddr(ifp, NULL); @@ -2964,7 +2967,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) start sending router solicitations. */ - if (ifp->idev->cnf.forwarding == 0 && + if ((ifp->idev->cnf.forwarding == 0 || + ifp->idev->cnf.forwarding == 2) && ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 8175f802651b..c8993e5a337c 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -518,10 +518,9 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) static inline int ip6addrlbl_msgsize(void) { - return (NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + nla_total_size(16) /* IFAL_ADDRESS */ - + nla_total_size(4) /* IFAL_LABEL */ - ); + + nla_total_size(4); /* IFAL_LABEL */ } static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 56b9bf2516f4..54e8e42f7a88 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -343,7 +343,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!ipv6_chk_addr(net, &addr->sin6_addr, + if (!inet->transparent && + !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; goto out_unlock; @@ -467,7 +468,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; *uaddr_len = sizeof(*sin); - return(0); + return 0; } EXPORT_SYMBOL(inet6_getname); @@ -488,7 +489,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCADDRT: case SIOCDELRT: - return(ipv6_route_ioctl(net, cmd, (void __user *)arg)); + return ipv6_route_ioctl(net, cmd, (void __user *)arg); case SIOCSIFADDR: return addrconf_add_ifaddr(net, (void __user *) arg); @@ -502,7 +503,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return sk->sk_prot->ioctl(sk, cmd, arg); } /*NOTREACHED*/ - return(0); + return 0; } EXPORT_SYMBOL(inet6_ioctl); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index ef371aa01ac5..320bdb877eed 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -577,6 +577,25 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } + if (np->rxopt.bits.rxorigdstaddr) { + struct sockaddr_in6 sin6; + u16 *ports = (u16 *) skb_transport_header(skb); + + if (skb_transport_offset(skb) + 4 <= skb->len) { + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ + + sin6.sin6_family = AF_INET6; + ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr); + sin6.sin6_port = ports[1]; + sin6.sin6_flowinfo = 0; + sin6.sin6_scope_id = 0; + + put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); + } + } return 0; } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index e1caa5d526c2..14ed0a955b56 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -13,12 +13,12 @@ int ipv6_ext_hdr(u8 nexthdr) /* * find out if nexthdr is an extension header or a protocol */ - return ( (nexthdr == NEXTHDR_HOP) || + return (nexthdr == NEXTHDR_HOP) || (nexthdr == NEXTHDR_ROUTING) || (nexthdr == NEXTHDR_FRAGMENT) || (nexthdr == NEXTHDR_AUTH) || (nexthdr == NEXTHDR_NONE) || - (nexthdr == NEXTHDR_DEST) ); + (nexthdr == NEXTHDR_DEST); } /* diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b1108ede18e1..d829874d8946 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -34,11 +34,10 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, { struct fib_lookup_arg arg = { .lookup_ptr = lookup, + .flags = FIB_LOOKUP_NOREF, }; fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg); - if (arg.rule) - fib_rule_put(arg.rule); if (arg.result) return arg.result; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b6a585909d35..de382114609b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1500,15 +1500,18 @@ static void fib6_gc_timer_cb(unsigned long arg) static int __net_init fib6_net_init(struct net *net) { + size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ, - sizeof(*net->ipv6.fib_table_hash), - GFP_KERNEL); + /* Avoid false sharing : Use at least a full cache line */ + size = max_t(size_t, size, L1_CACHE_BYTES); + + net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 980912ed7a38..99157b4cd56e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -637,7 +637,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } mtu -= hlen + sizeof(struct frag_hdr); - if (skb_has_frags(skb)) { + if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; @@ -878,8 +878,8 @@ static inline int ip6_rt_check(struct rt6key *rt_key, struct in6_addr *fl_addr, struct in6_addr *addr_cache) { - return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && - (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache))); + return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && + (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0fd027f3f47e..2a59610c2a58 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -75,7 +75,7 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static void ip6_tnl_dev_init(struct net_device *dev); +static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static int ip6_tnl_net_id __read_mostly; @@ -83,15 +83,42 @@ struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ - struct ip6_tnl *tnls_r_l[HASH_SIZE]; - struct ip6_tnl *tnls_wc[1]; - struct ip6_tnl **tnls[2]; + struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; + struct ip6_tnl __rcu *tnls_wc[1]; + struct ip6_tnl __rcu **tnls[2]; }; +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ip6_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ip6_tnl_lock); static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { @@ -138,8 +165,8 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) static struct ip6_tnl * ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -167,7 +194,7 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) * Return: head of IPv6 tunnel list **/ -static struct ip6_tnl ** +static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) { struct in6_addr *remote = &p->raddr; @@ -190,12 +217,10 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms); + struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); - spin_lock_bh(&ip6_tnl_lock); - t->next = *tp; + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ip6_tnl_lock); } /** @@ -206,18 +231,25 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp; - - for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ip6_tnl_lock); - *tp = t->next; - spin_unlock_bh(&ip6_tnl_lock); + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = ip6_tnl_bucket(ip6n, &t->parms); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } } +static void ip6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + /** * ip6_tnl_create() - create a new tunnel * @p: tunnel parameters @@ -256,7 +288,9 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; - ip6_tnl_dev_init(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto failed_free; if ((err = register_netdevice(dev)) < 0) goto failed_free; @@ -266,7 +300,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) return t; failed_free: - free_netdev(dev); + ip6_dev_free(dev); failed: return NULL; } @@ -290,10 +324,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, { struct in6_addr *remote = &p->raddr; struct in6_addr *local = &p->laddr; + struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = *ip6_tnl_bucket(ip6n, p); t; t = t->next) { + for (tp = ip6_tnl_bucket(ip6n, p); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) return t; @@ -318,13 +355,10 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - if (dev == ip6n->fb_tnl_dev) { - spin_lock_bh(&ip6_tnl_lock); - ip6n->tnls_wc[0] = NULL; - spin_unlock_bh(&ip6_tnl_lock); - } else { + if (dev == ip6n->fb_tnl_dev) + rcu_assign_pointer(ip6n->tnls_wc[0], NULL); + else ip6_tnl_unlink(ip6n, t); - } ip6_tnl_dst_reset(t); dev_put(dev); } @@ -702,6 +736,8 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { + struct pcpu_tstats *tstats; + if (t->parms.proto != ipproto && t->parms.proto != 0) { rcu_read_unlock(); goto discard; @@ -724,10 +760,16 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); - skb_tunnel_rx(skb, t->dev); + tstats = this_cpu_ptr(t->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, t->dev); dscp_ecn_decapsulate(t, ipv6h, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -934,8 +976,10 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, err = ip6_local_out(skb); if (net_xmit_eval(err) == 0) { - stats->tx_bytes += pkt_len; - stats->tx_packets++; + struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats); + + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; } else { stats->tx_errors++; stats->tx_aborted_errors++; @@ -1240,6 +1284,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) t = netdev_priv(dev); ip6_tnl_unlink(ip6n, t); + synchronize_net(); err = ip6_tnl_change(t, &p); ip6_tnl_link(ip6n, t); netdev_state_change(dev); @@ -1300,12 +1345,14 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { - .ndo_uninit = ip6_tnl_dev_uninit, + .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, - .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_do_ioctl = ip6_tnl_ioctl, .ndo_change_mtu = ip6_tnl_change_mtu, + .ndo_get_stats = ip6_get_stats, }; + /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel @@ -1317,7 +1364,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); @@ -1325,6 +1372,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } @@ -1333,12 +1381,17 @@ static void ip6_tnl_dev_setup(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static inline void +static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + t->dev = dev; strcpy(t->parms.name, dev->name); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } /** @@ -1346,11 +1399,15 @@ ip6_tnl_dev_init_gen(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static void ip6_tnl_dev_init(struct net_device *dev) +static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - ip6_tnl_dev_init_gen(dev); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; ip6_tnl_link_config(t); + return 0; } /** @@ -1360,25 +1417,29 @@ static void ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev) +static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; - ip6_tnl_dev_init_gen(dev); t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6n->tnls_wc[0] = t; + rcu_assign_pointer(ip6n->tnls_wc[0], t); + return 0; } -static struct xfrm6_tunnel ip4ip6_handler = { +static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, .priority = 1, }; -static struct xfrm6_tunnel ip6ip6_handler = { +static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, .priority = 1, @@ -1391,14 +1452,14 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) LIST_HEAD(list); for (h = 0; h < HASH_SIZE; h++) { - t = ip6n->tnls_r_l[h]; + t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t != NULL) { unregister_netdevice_queue(t->dev, &list); - t = t->next; + t = rtnl_dereference(t->next); } } - t = ip6n->tnls_wc[0]; + t = rtnl_dereference(ip6n->tnls_wc[0]); unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1419,7 +1480,9 @@ static int __net_init ip6_tnl_init_net(struct net *net) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); - ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) @@ -1427,7 +1490,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) return 0; err_register: - free_netdev(ip6n->fb_tnl_dev); + ip6_dev_free(ip6n->fb_tnl_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 66078dad7fe8..6f32ffce7022 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -667,6 +667,7 @@ static int pim6_rcv(struct sk_buff *skb) skb_tunnel_rx(skb, reg_dev); netif_rx(skb); + dev_put(reg_dev); return 0; drop: diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7f66bc8f0b0..d1770e061c08 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -342,6 +342,25 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_TRANSPARENT: + if (!capable(CAP_NET_ADMIN)) { + retv = -EPERM; + break; + } + if (optlen < sizeof(int)) + goto e_inval; + /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ + inet_sk(sk)->transparent = valbool; + retv = 0; + break; + + case IPV6_RECVORIGDSTADDR: + if (optlen < sizeof(int)) + goto e_inval; + np->rxopt.bits.rxorigdstaddr = valbool; + retv = 0; + break; + case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: @@ -1104,6 +1123,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; } + case IPV6_TRANSPARENT: + val = inet_sk(sk)->transparent; + break; + + case IPV6_RECVORIGDSTADDR: + val = np->rxopt.bits.rxorigdstaddr; + break; + case IPV6_UNICAST_HOPS: case IPV6_MULTICAST_HOPS: { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 58841c4ae947..998d6d27e7cf 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -91,7 +91,9 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> -static u32 ndisc_hash(const void *pkey, const struct net_device *dev); +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __u32 rnd); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -228,12 +230,12 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while(cur < end && cur->nd_opt_type != type); - return (cur <= end && cur->nd_opt_type == type ? cur : NULL); + return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(struct nd_opt_hdr *opt) { - return (opt->nd_opt_type == ND_OPT_RDNSS); + return opt->nd_opt_type == ND_OPT_RDNSS; } static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, @@ -244,7 +246,7 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while(cur < end && !ndisc_is_useropt(cur)); - return (cur <= end && ndisc_is_useropt(cur) ? cur : NULL); + return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; } static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, @@ -319,7 +321,7 @@ static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, int prepad = ndisc_addr_option_pad(dev->type); if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) return NULL; - return (lladdr + prepad); + return lladdr + prepad; } int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir) @@ -350,7 +352,9 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d EXPORT_SYMBOL(ndisc_mc_map); -static u32 ndisc_hash(const void *pkey, const struct net_device *dev) +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __u32 hash_rnd) { const u32 *p32 = pkey; u32 addr_hash, i; @@ -359,7 +363,7 @@ static u32 ndisc_hash(const void *pkey, const struct net_device *dev) for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++) addr_hash ^= *p32++; - return jhash_2words(addr_hash, dev->ifindex, nd_tbl.hash_rnd); + return jhash_2words(addr_hash, dev->ifindex, hash_rnd); } static int ndisc_constructor(struct neighbour *neigh) @@ -1105,6 +1109,18 @@ errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } +static inline int accept_ra(struct inet6_dev *in6_dev) +{ + /* + * If forwarding is enabled, RA are not accepted unless the special + * hybrid mode (accept_ra=2) is enabled. + */ + if (in6_dev->cnf.forwarding && in6_dev->cnf.accept_ra < 2) + return 0; + + return in6_dev->cnf.accept_ra; +} + static void ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); @@ -1158,8 +1174,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - /* skip route and link configuration on routers */ - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + if (!accept_ra(in6_dev)) goto skip_linkparms; #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1309,8 +1324,7 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } - /* skip route and link configuration on routers */ - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + if (!accept_ra(in6_dev)) goto out; #ifdef CONFIG_IPV6_ROUTE_INFO diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 29d643bcafa4..448464844a25 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -5,10 +5,15 @@ menu "IPv6: Netfilter Configuration" depends on INET && IPV6 && NETFILTER +config NF_DEFRAG_IPV6 + tristate + default n + config NF_CONNTRACK_IPV6 tristate "IPv6 connection tracking support" depends on INET && IPV6 && NF_CONNTRACK default m if NETFILTER_ADVANCED=n + select NF_DEFRAG_IPV6 ---help--- Connection tracking keeps a record of what packets have passed through your machine, in order to figure out how they are related @@ -132,10 +137,10 @@ config IP6_NF_MATCH_RT # The targets config IP6_NF_TARGET_HL tristate '"HL" hoplimit target support' - depends on NETFILTER_ADVANCED + depends on NETFILTER_ADVANCED && IP6_NF_MANGLE select NETFILTER_XT_TARGET_HL ---help--- - This is a backwards-compat option for the user's convenience + This is a backwards-compatible option for the user's convenience (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index aafbba30c899..0a432c9b0795 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -11,10 +11,14 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o # objects for l3 independent conntrack -nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o nf_conntrack_reasm.o +nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o # l3 independent conntrack -obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o +obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o + +# defrag +nf_defrag_ipv6-objs := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o +obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 8e754be92c24..51df035897e7 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -82,13 +82,13 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); int ip6t_ext_hdr(u8 nexthdr) { - return ( (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS) ); + return (nexthdr == IPPROTO_HOPOPTS) || + (nexthdr == IPPROTO_ROUTING) || + (nexthdr == IPPROTO_FRAGMENT) || + (nexthdr == IPPROTO_ESP) || + (nexthdr == IPPROTO_AH) || + (nexthdr == IPPROTO_NONE) || + (nexthdr == IPPROTO_DSTOPTS); } /* Returns whether matches rule or not. */ @@ -215,7 +215,7 @@ static inline bool unconditional(const struct ip6t_ip6 *ipv6) return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } -static inline const struct ip6t_entry_target * +static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); @@ -260,9 +260,9 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - const struct ip6t_standard_target *t = (void *)ip6t_get_target_c(s); + const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); - if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) { + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; @@ -271,7 +271,7 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, if (s->target_offset == sizeof(struct ip6t_entry) && strcmp(t->target.u.kernel.target->name, - IP6T_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && t->verdict < 0 && unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ @@ -369,7 +369,7 @@ ip6t_do_table(struct sk_buff *skb, e = get_entry(table_base, private->hook_entry[hook]); do { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; const struct xt_entry_match *ematch; IP_NF_ASSERT(e); @@ -403,10 +403,10 @@ ip6t_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct ip6t_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != IP6T_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -434,7 +434,7 @@ ip6t_do_table(struct sk_buff *skb, acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); - if (verdict == IP6T_CONTINUE) + if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ @@ -474,7 +474,7 @@ mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct ip6t_standard_target *t + const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -488,13 +488,13 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct ip6t_entry) && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -537,7 +537,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ip6t_entry)) { @@ -565,7 +565,7 @@ mark_source_chains(const struct xt_table_info *newinfo, return 1; } -static void cleanup_match(struct ip6t_entry_match *m, struct net *net) +static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; @@ -581,14 +581,14 @@ static void cleanup_match(struct ip6t_entry_match *m, struct net *net) static int check_entry(const struct ip6t_entry *e, const char *name) { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; if (!ip6_checkentry(&e->ipv6)) { duprintf("ip_tables: ip check failed %p %s.\n", e, name); return -EINVAL; } - if (e->target_offset + sizeof(struct ip6t_entry_target) > + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -599,7 +599,7 @@ check_entry(const struct ip6t_entry *e, const char *name) return 0; } -static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) +static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; int ret; @@ -618,7 +618,7 @@ static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) } static int -find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; @@ -643,7 +643,7 @@ err: static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { - struct ip6t_entry_target *t = ip6t_get_target(e); + struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, @@ -670,7 +670,7 @@ static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; @@ -721,7 +721,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, static bool check_underflow(const struct ip6t_entry *e) { - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->ipv6)) @@ -729,7 +729,7 @@ static bool check_underflow(const struct ip6t_entry *e) t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct ip6t_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -752,7 +752,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, } if (e->next_offset - < sizeof(struct ip6t_entry) + sizeof(struct ip6t_entry_target)) { + < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -784,7 +784,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -985,8 +985,8 @@ copy_entries_to_user(unsigned int total_size, /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; - const struct ip6t_entry_match *m; - const struct ip6t_entry_target *t; + const struct xt_entry_match *m; + const struct xt_entry_target *t; e = (struct ip6t_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -1003,7 +1003,7 @@ copy_entries_to_user(unsigned int total_size, m = (void *)e + i; if (copy_to_user(userptr + off + i - + offsetof(struct ip6t_entry_match, + + offsetof(struct xt_entry_match, u.user.name), m->u.kernel.match->name, strlen(m->u.kernel.match->name)+1) @@ -1015,7 +1015,7 @@ copy_entries_to_user(unsigned int total_size, t = ip6t_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct ip6t_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -1053,7 +1053,7 @@ static int compat_calc_entry(const struct ip6t_entry *e, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; - const struct ip6t_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -1105,7 +1105,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -1118,7 +1118,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[IP6T_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(AF_INET6); @@ -1415,14 +1415,14 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, #ifdef CONFIG_COMPAT struct compat_ip6t_replace { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; - compat_uptr_t counters; /* struct ip6t_counters * */ + compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[0]; }; @@ -1431,7 +1431,7 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; @@ -1466,7 +1466,7 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, } static int -compat_find_calc_match(struct ip6t_entry_match *m, +compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ip6t_ip6 *ipv6, unsigned int hookmask, @@ -1488,7 +1488,7 @@ compat_find_calc_match(struct ip6t_entry_match *m, static void compat_release_entry(struct compat_ip6t_entry *e) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -1509,7 +1509,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, const char *name) { struct xt_entry_match *ematch; - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; @@ -1591,7 +1591,7 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct ip6t_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct ip6t_entry *de; unsigned int origsize; @@ -1899,7 +1899,7 @@ compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, } struct compat_ip6t_get_entries { - char name[IP6T_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[0]; }; @@ -2054,7 +2054,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { - struct ip6t_get_revision rev; + struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { @@ -2191,7 +2191,7 @@ static int icmp6_checkentry(const struct xt_mtchk_param *par) /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { - .name = IP6T_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_COMPAT @@ -2201,9 +2201,9 @@ static struct xt_target ip6t_builtin_tg[] __read_mostly = { #endif }, { - .name = IP6T_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = ip6t_error, - .targetsize = IP6T_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 0a07ae7b933f..09c88891a753 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -23,6 +23,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_log.h> +#include <net/netfilter/xt_log.h> MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); MODULE_DESCRIPTION("Xtables: IPv6 packet logging to syslog"); @@ -32,11 +33,9 @@ struct in_device; #include <net/route.h> #include <linux/netfilter_ipv6/ip6t_LOG.h> -/* Use lock to serialize, so printks don't overlap */ -static DEFINE_SPINLOCK(log_lock); - /* One level of recursion won't kill us */ -static void dump_packet(const struct nf_loginfo *info, +static void dump_packet(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int ip6hoff, int recurse) { @@ -55,15 +54,15 @@ static void dump_packet(const struct nf_loginfo *info, ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); if (ih == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - printk("SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", ntohs(ih->payload_len) + sizeof(struct ipv6hdr), (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, ih->hop_limit, @@ -78,35 +77,35 @@ static void dump_packet(const struct nf_loginfo *info, hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); if (hp == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 48 "OPT (...) " */ if (logflags & IP6T_LOG_IPOPT) - printk("OPT ( "); + sb_add(m, "OPT ( "); switch (currenthdr) { case IPPROTO_FRAGMENT: { struct frag_hdr _fhdr; const struct frag_hdr *fh; - printk("FRAG:"); + sb_add(m, "FRAG:"); fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), &_fhdr); if (fh == NULL) { - printk("TRUNCATED "); + sb_add(m, "TRUNCATED "); return; } /* Max length: 6 "65535 " */ - printk("%u ", ntohs(fh->frag_off) & 0xFFF8); + sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); /* Max length: 11 "INCOMPLETE " */ if (fh->frag_off & htons(0x0001)) - printk("INCOMPLETE "); + sb_add(m, "INCOMPLETE "); - printk("ID:%08x ", ntohl(fh->identification)); + sb_add(m, "ID:%08x ", ntohl(fh->identification)); if (ntohs(fh->frag_off) & 0xFFF8) fragment = 1; @@ -120,7 +119,7 @@ static void dump_packet(const struct nf_loginfo *info, case IPPROTO_HOPOPTS: if (fragment) { if (logflags & IP6T_LOG_IPOPT) - printk(")"); + sb_add(m, ")"); return; } hdrlen = ipv6_optlen(hp); @@ -132,10 +131,10 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_auth_hdr *ah; /* Max length: 3 "AH " */ - printk("AH "); + sb_add(m, "AH "); if (fragment) { - printk(")"); + sb_add(m, ")"); return; } @@ -146,13 +145,13 @@ static void dump_packet(const struct nf_loginfo *info, * Max length: 26 "INCOMPLETE [65535 * bytes] )" */ - printk("INCOMPLETE [%u bytes] )", + sb_add(m, "INCOMPLETE [%u bytes] )", skb->len - ptr); return; } /* Length: 15 "SPI=0xF1234567 */ - printk("SPI=0x%x ", ntohl(ah->spi)); + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); } @@ -164,10 +163,10 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_esp_hdr *eh; /* Max length: 4 "ESP " */ - printk("ESP "); + sb_add(m, "ESP "); if (fragment) { - printk(")"); + sb_add(m, ")"); return; } @@ -177,23 +176,23 @@ static void dump_packet(const struct nf_loginfo *info, eh = skb_header_pointer(skb, ptr, sizeof(_esph), &_esph); if (eh == NULL) { - printk("INCOMPLETE [%u bytes] )", + sb_add(m, "INCOMPLETE [%u bytes] )", skb->len - ptr); return; } /* Length: 16 "SPI=0xF1234567 )" */ - printk("SPI=0x%x )", ntohl(eh->spi) ); + sb_add(m, "SPI=0x%x )", ntohl(eh->spi) ); } return; default: /* Max length: 20 "Unknown Ext Hdr 255" */ - printk("Unknown Ext Hdr %u", currenthdr); + sb_add(m, "Unknown Ext Hdr %u", currenthdr); return; } if (logflags & IP6T_LOG_IPOPT) - printk(") "); + sb_add(m, ") "); currenthdr = hp->nexthdr; ptr += hdrlen; @@ -205,7 +204,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct tcphdr *th; /* Max length: 10 "PROTO=TCP " */ - printk("PROTO=TCP "); + sb_add(m, "PROTO=TCP "); if (fragment) break; @@ -213,40 +212,40 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph); if (th == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u ", + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ if (logflags & IP6T_LOG_TCPSEQ) - printk("SEQ=%u ACK=%u ", + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); /* Max length: 13 "WINDOW=65535 " */ - printk("WINDOW=%u ", ntohs(th->window)); + sb_add(m, "WINDOW=%u ", ntohs(th->window)); /* Max length: 9 "RES=0x3C " */ - printk("RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); + sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ if (th->cwr) - printk("CWR "); + sb_add(m, "CWR "); if (th->ece) - printk("ECE "); + sb_add(m, "ECE "); if (th->urg) - printk("URG "); + sb_add(m, "URG "); if (th->ack) - printk("ACK "); + sb_add(m, "ACK "); if (th->psh) - printk("PSH "); + sb_add(m, "PSH "); if (th->rst) - printk("RST "); + sb_add(m, "RST "); if (th->syn) - printk("SYN "); + sb_add(m, "SYN "); if (th->fin) - printk("FIN "); + sb_add(m, "FIN "); /* Max length: 11 "URGP=65535 " */ - printk("URGP=%u ", ntohs(th->urg_ptr)); + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); if ((logflags & IP6T_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { @@ -260,15 +259,15 @@ static void dump_packet(const struct nf_loginfo *info, ptr + sizeof(struct tcphdr), optsize, _opt); if (op == NULL) { - printk("OPT (TRUNCATED)"); + sb_add(m, "OPT (TRUNCATED)"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i =0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } break; } @@ -279,9 +278,9 @@ static void dump_packet(const struct nf_loginfo *info, if (currenthdr == IPPROTO_UDP) /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP " ); + sb_add(m, "PROTO=UDP " ); else /* Max length: 14 "PROTO=UDPLITE " */ - printk("PROTO=UDPLITE "); + sb_add(m, "PROTO=UDPLITE "); if (fragment) break; @@ -289,12 +288,12 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph); if (uh == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u LEN=%u ", + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); break; @@ -304,7 +303,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct icmp6hdr *ic; /* Max length: 13 "PROTO=ICMPv6 " */ - printk("PROTO=ICMPv6 "); + sb_add(m, "PROTO=ICMPv6 "); if (fragment) break; @@ -312,18 +311,18 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 25 "INCOMPLETE [65535 bytes] " */ ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); if (ic == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); return; } /* Max length: 18 "TYPE=255 CODE=255 " */ - printk("TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); + sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); switch (ic->icmp6_type) { case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: /* Max length: 19 "ID=65535 SEQ=65535 " */ - printk("ID=%u SEQ=%u ", + sb_add(m, "ID=%u SEQ=%u ", ntohs(ic->icmp6_identifier), ntohs(ic->icmp6_sequence)); break; @@ -334,35 +333,35 @@ static void dump_packet(const struct nf_loginfo *info, case ICMPV6_PARAMPROB: /* Max length: 17 "POINTER=ffffffff " */ - printk("POINTER=%08x ", ntohl(ic->icmp6_pointer)); + sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); /* Fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: /* Max length: 3+maxlen */ if (recurse) { - printk("["); - dump_packet(info, skb, ptr + sizeof(_icmp6h), - 0); - printk("] "); + sb_add(m, "["); + dump_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + sb_add(m, "] "); } /* Max length: 10 "MTU=65535 " */ if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - printk("MTU=%u ", ntohl(ic->icmp6_mtu)); + sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); } break; } /* Max length: 10 "PROTO=255 " */ default: - printk("PROTO=%u ", currenthdr); + sb_add(m, "PROTO=%u ", currenthdr); } /* Max length: 15 "UID=4294967295 " */ if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) - printk("UID=%u GID=%u ", + sb_add(m, "UID=%u GID=%u ", skb->sk->sk_socket->file->f_cred->fsuid, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); @@ -370,10 +369,11 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!recurse && skb->mark) - printk("MARK=0x%x ", skb->mark); + sb_add(m, "MARK=0x%x ", skb->mark); } -static void dump_mac_header(const struct nf_loginfo *info, +static void dump_mac_header(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -387,7 +387,7 @@ static void dump_mac_header(const struct nf_loginfo *info, switch (dev->type) { case ARPHRD_ETHER: - printk("MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, ntohs(eth_hdr(skb)->h_proto)); return; @@ -396,7 +396,7 @@ static void dump_mac_header(const struct nf_loginfo *info, } fallback: - printk("MAC="); + sb_add(m, "MAC="); if (dev->hard_header_len && skb->mac_header != skb->network_header) { const unsigned char *p = skb_mac_header(skb); @@ -408,19 +408,19 @@ fallback: p = NULL; if (p != NULL) { - printk("%02x", *p++); + sb_add(m, "%02x", *p++); for (i = 1; i < len; i++) - printk(":%02x", p[i]); + sb_add(m, ":%02x", p[i]); } - printk(" "); + sb_add(m, " "); if (dev->type == ARPHRD_SIT) { const struct iphdr *iph = (struct iphdr *)skb_mac_header(skb); - printk("TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); + sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); } } else - printk(" "); + sb_add(m, " "); } static struct nf_loginfo default_loginfo = { @@ -442,22 +442,23 @@ ip6t_log_packet(u_int8_t pf, const struct nf_loginfo *loginfo, const char *prefix) { + struct sbuff *m = sb_open(); + if (!loginfo) loginfo = &default_loginfo; - spin_lock_bh(&log_lock); - printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + prefix, + in ? in->name : "", + out ? out->name : ""); /* MAC logging for input path only. */ if (in && !out) - dump_mac_header(loginfo, skb); + dump_mac_header(m, loginfo, skb); + + dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); - dump_packet(loginfo, skb, skb_network_offset(skb), 1); - printk("\n"); - spin_unlock_bh(&log_lock); + sb_close(m); } static unsigned int diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index ff43461704be..c8af58b22562 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -16,7 +16,6 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmp.h> -#include <linux/sysctl.h> #include <net/ipv6.h> #include <net/inet_frag.h> @@ -29,6 +28,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_log.h> static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, @@ -189,53 +189,6 @@ out: return nf_conntrack_confirm(skb); } -static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, - struct sk_buff *skb) -{ - u16 zone = NF_CT_DEFAULT_ZONE; - - if (skb->nfct) - zone = nf_ct_zone((struct nf_conn *)skb->nfct); - -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; -#endif - if (hooknum == NF_INET_PRE_ROUTING) - return IP6_DEFRAG_CONNTRACK_IN + zone; - else - return IP6_DEFRAG_CONNTRACK_OUT + zone; - -} - -static unsigned int ipv6_defrag(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm; - - /* Previously seen (loopback)? */ - if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) - return NF_ACCEPT; - - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); - /* queued */ - if (reasm == NULL) - return NF_STOLEN; - - /* error occured or not fragmented */ - if (reasm == skb) - return NF_ACCEPT; - - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); - - return NF_STOLEN; -} - static unsigned int __ipv6_conntrack_in(struct net *net, unsigned int hooknum, struct sk_buff *skb, @@ -288,13 +241,6 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, - }, - { .hook = ipv6_conntrack_in, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -309,13 +255,6 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_CONNTRACK, }, { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, - }, - { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -387,10 +326,6 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .nlattr_to_tuple = ipv6_nlattr_to_tuple, .nla_policy = ipv6_nla_policy, #endif -#ifdef CONFIG_SYSCTL - .ctl_table_path = nf_net_netfilter_sysctl_path, - .ctl_table = nf_ct_ipv6_sysctl_table, -#endif .me = THIS_MODULE, }; @@ -403,16 +338,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) int ret = 0; need_conntrack(); + nf_defrag_ipv6_enable(); - ret = nf_ct_frag6_init(); - if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't initialize frag6.\n"); - return ret; - } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); if (ret < 0) { pr_err("nf_conntrack_ipv6: can't register tcp.\n"); - goto cleanup_frag6; + return ret; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); @@ -450,8 +381,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); cleanup_tcp: nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); - cleanup_frag6: - nf_ct_frag6_cleanup(); return ret; } @@ -463,7 +392,6 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); - nf_ct_frag6_cleanup(); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 578f3c1a16db..3a3f129a44cb 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -73,7 +73,7 @@ static struct inet_frags nf_frags; static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL -struct ctl_table nf_ct_ipv6_sysctl_table[] = { +struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .data = &nf_init_frags.timeout, @@ -97,6 +97,8 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { }, { } }; + +static struct ctl_table_header *nf_ct_frag6_sysctl_header; #endif static unsigned int nf_hashfn(struct inet_frag_queue *q) @@ -363,7 +365,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_has_frags(head)) { + if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; @@ -623,11 +625,24 @@ int nf_ct_frag6_init(void) inet_frags_init_net(&nf_init_frags); inet_frags_init(&nf_frags); +#ifdef CONFIG_SYSCTL + nf_ct_frag6_sysctl_header = register_sysctl_paths(nf_net_netfilter_sysctl_path, + nf_ct_frag6_sysctl_table); + if (!nf_ct_frag6_sysctl_header) { + inet_frags_fini(&nf_frags); + return -ENOMEM; + } +#endif + return 0; } void nf_ct_frag6_cleanup(void) { +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(nf_ct_frag6_sysctl_header); + nf_ct_frag6_sysctl_header = NULL; +#endif inet_frags_fini(&nf_frags); nf_init_frags.low_thresh = 0; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c new file mode 100644 index 000000000000..99abfb53bab9 --- /dev/null +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -0,0 +1,131 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/netfilter.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <linux/sysctl.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ + u16 zone = NF_CT_DEFAULT_ZONE; + + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); + +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN + zone; + else + return IP6_DEFRAG_CONNTRACK_OUT + zone; + +} + +static unsigned int ipv6_defrag(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct sk_buff *reasm; + + /* Previously seen (loopback)? */ + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) + return NF_ACCEPT; + + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); + /* queued */ + if (reasm == NULL) + return NF_STOLEN; + + /* error occured or not fragmented */ + if (reasm == skb) + return NF_ACCEPT; + + nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, + (struct net_device *)out, okfn); + + return NF_STOLEN; +} + +static struct nf_hook_ops ipv6_defrag_ops[] = { + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, +}; + +static int __init nf_defrag_init(void) +{ + int ret = 0; + + ret = nf_ct_frag6_init(); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); + return ret; + } + ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't register hooks\n"); + goto cleanup_frag6; + } + return ret; + +cleanup_frag6: + nf_ct_frag6_cleanup(); + return ret; + +} + +static void __exit nf_defrag_fini(void) +{ + nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + nf_ct_frag6_cleanup(); +} + +void nf_defrag_ipv6_enable(void) +{ +} +EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); + +module_init(nf_defrag_init); +module_exit(nf_defrag_fini); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 1fa3468f0f32..9a7978fdc02a 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -25,28 +25,15 @@ #include <linux/spinlock.h> #include <net/protocol.h> -const struct inet6_protocol *inet6_protos[MAX_INET_PROTOS]; -static DEFINE_SPINLOCK(inet6_proto_lock); - +const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int ret, hash = protocol & (MAX_INET_PROTOS - 1); - - spin_lock_bh(&inet6_proto_lock); - - if (inet6_protos[hash]) { - ret = -1; - } else { - inet6_protos[hash] = prot; - ret = 0; - } - - spin_unlock_bh(&inet6_proto_lock); + int hash = protocol & (MAX_INET_PROTOS - 1); - return ret; + return !cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + NULL, prot) ? 0 : -1; } - EXPORT_SYMBOL(inet6_add_protocol); /* @@ -57,20 +44,11 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol { int ret, hash = protocol & (MAX_INET_PROTOS - 1); - spin_lock_bh(&inet6_proto_lock); - - if (inet6_protos[hash] != prot) { - ret = -1; - } else { - inet6_protos[hash] = NULL; - ret = 0; - } - - spin_unlock_bh(&inet6_proto_lock); + ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + prot, NULL) == prot) ? 0 : -1; synchronize_net(); return ret; } - EXPORT_SYMBOL(inet6_del_protocol); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e677937a07fc..86c39526ba5e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -373,7 +373,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) { - if ((raw6_sk(sk)->checksum || sk->sk_filter) && + if ((raw6_sk(sk)->checksum || rcu_dereference_raw(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); @@ -764,7 +764,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); @@ -772,10 +772,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num) - return(-EINVAL); + return -EINVAL; if (proto > 255) - return(-EINVAL); + return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { @@ -985,7 +985,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) - return(-EINVAL); + return -EINVAL; if (val < 0) { rp->checksum = 0; } else { @@ -997,7 +997,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, break; default: - return(-ENOPROTOOPT); + return -ENOPROTOOPT; } } @@ -1190,7 +1190,7 @@ static int rawv6_init_sk(struct sock *sk) default: break; } - return(0); + return 0; } struct proto rawv6_prot = { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 64cfef1b0a4c..c7ba3149633f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -458,7 +458,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_has_frags(head)) { + if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a275c6e1e25c..25661f968f3f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -109,7 +109,6 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .local_out = __ip6_local_out, - .entries = ATOMIC_INIT(0), }; static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = { .destroy = ip6_dst_destroy, .check = ip6_dst_check, .update_pmtu = ip6_rt_blackhole_update_pmtu, - .entries = ATOMIC_INIT(0), }; static struct rt6_info ip6_null_entry_template = { @@ -217,14 +215,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static __inline__ int rt6_check_expired(const struct rt6_info *rt) { - return (rt->rt6i_flags & RTF_EXPIRES && - time_after(jiffies, rt->rt6i_expires)); + return (rt->rt6i_flags & RTF_EXPIRES) && + time_after(jiffies, rt->rt6i_expires); } static inline int rt6_need_strict(struct in6_addr *daddr) { - return (ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK)); + return ipv6_addr_type(daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* @@ -440,7 +438,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) __func__, match); net = dev_net(rt0->rt6i_dev); - return (match ? match : net->ipv6.ip6_null_entry); + return match ? match : net->ipv6.ip6_null_entry; } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -859,7 +857,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl dst_release(*dstp); *dstp = new; - return (new ? 0 : -ENOMEM); + return new ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(ip6_dst_blackhole); @@ -1058,19 +1056,22 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + int entries; + entries = dst_entries_get_fast(ops); if (time_after(rt_last_gc + rt_min_interval, now) && - atomic_read(&ops->entries) <= rt_max_size) + entries <= rt_max_size) goto out; net->ipv6.ip6_rt_gc_expire++; fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); net->ipv6.ip6_rt_last_gc = now; - if (atomic_read(&ops->entries) < ops->gc_thresh) + entries = dst_entries_get_slow(ops); + if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; out: net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; - return (atomic_read(&ops->entries) > rt_max_size); + return entries > rt_max_size; } /* Clean host part of a prefix. Not necessary in radix tree, @@ -1169,6 +1170,8 @@ int ip6_route_add(struct fib6_config *cfg) if (addr_type & IPV6_ADDR_MULTICAST) rt->dst.input = ip6_mc_input; + else if (cfg->fc_flags & RTF_LOCAL) + rt->dst.input = ip6_input; else rt->dst.input = ip6_forward; @@ -1190,7 +1193,8 @@ int ip6_route_add(struct fib6_config *cfg) they would result in kernel looping; promote them to reject routes */ if ((cfg->fc_flags & RTF_REJECT) || - (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { + (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK) + && !(cfg->fc_flags&RTF_LOCAL))) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { @@ -2102,6 +2106,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type == RTN_UNREACHABLE) cfg->fc_flags |= RTF_REJECT; + if (rtm->rtm_type == RTN_LOCAL) + cfg->fc_flags |= RTF_LOCAL; + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2222,6 +2229,8 @@ static int rt6_fill_node(struct net *net, NLA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; + else if (rt->rt6i_flags&RTF_LOCAL) + rtm->rtm_type = RTN_LOCAL; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) rtm->rtm_type = RTN_LOCAL; else @@ -2516,7 +2525,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) net->ipv6.rt6_stats->fib_rt_alloc, net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, - atomic_read(&net->ipv6.ip6_dst_ops.entries), + dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; @@ -2658,11 +2667,14 @@ static int __net_init ip6_route_net_init(struct net *net) memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); + if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) + goto out_ip6_dst_ops; + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) - goto out_ip6_dst_ops; + goto out_ip6_dst_entries; net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; @@ -2712,6 +2724,8 @@ out_ip6_prohibit_entry: out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif +out_ip6_dst_entries: + dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } @@ -2750,10 +2764,14 @@ int __init ip6_route_init(void) if (!ip6_dst_ops_template.kmem_cachep) goto out; - ret = register_pernet_subsys(&ip6_route_net_ops); + ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_dst_entries; + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; /* Registering of the loopback is done before this portion of code, @@ -2800,6 +2818,8 @@ out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); +out_dst_entries: + dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 4699cd3c3118..d6bfaec3bbbf 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -63,36 +63,63 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static void ipip6_tunnel_init(struct net_device *dev); +static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); +static void ipip6_dev_free(struct net_device *dev); static int sit_net_id __read_mostly; struct sit_net { - struct ip_tunnel *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel *tunnels_r[HASH_SIZE]; - struct ip_tunnel *tunnels_l[HASH_SIZE]; - struct ip_tunnel *tunnels_wc[1]; - struct ip_tunnel **tunnels[4]; + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipip6_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipip6_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); @@ -121,12 +148,12 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn, +static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - unsigned h = 0; + unsigned int h = 0; int prio = 0; if (remote) { @@ -140,7 +167,7 @@ static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn, return &sitn->tunnels[prio][h]; } -static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn, +static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); @@ -148,13 +175,14 @@ static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn, static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipip6_lock); - *tp = t->next; - spin_unlock_bh(&ipip6_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipip6_bucket(sitn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -162,12 +190,10 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipip6_bucket(sitn, t); + struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); - spin_lock_bh(&ipip6_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipip6_lock); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) @@ -187,17 +213,20 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #endif } -static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, +static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - struct ip_tunnel *t, **tp, *nt; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); - for (tp = __ipip6_bucket(sitn, parms); (t = *tp) != NULL; tp = &t->next) { + for (tp = __ipip6_bucket(sitn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { @@ -213,7 +242,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); else - sprintf(name, "sit%%d"); + strcpy(name, "sit%d"); dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup); if (dev == NULL) @@ -229,7 +258,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - ipip6_tunnel_init(dev); + if (ipip6_tunnel_init(dev) < 0) + goto failed_free; ipip6_tunnel_clone_6rd(dev, sitn); if (parms->i_flags & SIT_ISATAP) @@ -244,7 +274,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, return nt; failed_free: - free_netdev(dev); + ipip6_dev_free(dev); failed: return NULL; } @@ -340,7 +370,7 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) ASSERT_RTNL(); - for (p = t->prl; p; p = p->next) { + for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; @@ -451,15 +481,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - spin_lock_bh(&ipip6_lock); - sitn->tunnels_wc[0] = NULL; - spin_unlock_bh(&ipip6_lock); - dev_put(dev); + rcu_assign_pointer(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); ipip6_tunnel_del_prl(netdev_priv(dev), NULL); - dev_put(dev); } + dev_put(dev); } @@ -548,6 +575,8 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { + struct pcpu_tstats *tstats; + secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); @@ -563,10 +592,16 @@ static int ipip6_rcv(struct sk_buff *skb) return 0; } - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); ipip6_ecn_decapsulate(iph, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -590,7 +625,7 @@ __be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { - unsigned pbw0, pbi0; + unsigned int pbw0, pbi0; int pbi1; u32 d; @@ -625,14 +660,13 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -703,20 +737,20 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, .oif = tunnel->parms.link, .proto = IPPROTO_IPV6 }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -724,7 +758,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { - stats->collisions++; + dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } @@ -763,7 +797,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -799,14 +833,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph->ttl = iph6->hop_limit; nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -929,6 +963,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } t = netdev_priv(dev); ipip6_tunnel_unlink(sitn, t); + synchronize_net(); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; memcpy(dev->dev_addr, &p.iph.saddr, 4); @@ -1083,12 +1118,19 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_start_xmit = ipip6_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, + .ndo_get_stats = ipip6_get_stats, }; +static void ipip6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipip6_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip6_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -1098,9 +1140,10 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; } -static void ipip6_tunnel_init(struct net_device *dev) +static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); @@ -1111,9 +1154,14 @@ static void ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; } -static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) +static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1128,11 +1176,15 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; dev_hold(dev); sitn->tunnels_wc[0] = tunnel; + return 0; } -static struct xfrm_tunnel sit_handler = { +static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, .priority = 1, @@ -1173,7 +1225,10 @@ static int __net_init sit_init_net(struct net *net) } dev_net_set(sitn->fb_tunnel_dev, net); - ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + if (err) + goto err_dev_free; + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); if ((err = register_netdev(sitn->fb_tunnel_dev))) @@ -1183,7 +1238,8 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: dev_put(sitn->fb_tunnel_dev); - free_netdev(sitn->fb_tunnel_dev); +err_dev_free: + ipip6_dev_free(sitn->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fe6d40418c0b..7e41e2cbb85e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -139,7 +139,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; if (usin->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + return -EAFNOSUPPORT; memset(&fl, 0, sizeof(fl)); @@ -1409,7 +1409,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -1497,18 +1497,22 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto out; + } __inet6_hash(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); -out: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); +out_nonewsk: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); +out: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index fc3c86a47452..4f3cec12aa85 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -30,28 +30,31 @@ #include <net/protocol.h> #include <net/xfrm.h> -static struct xfrm6_tunnel *tunnel6_handlers; -static struct xfrm6_tunnel *tunnel46_handlers; +static struct xfrm6_tunnel __rcu *tunnel6_handlers __read_mostly; +static struct xfrm6_tunnel __rcu *tunnel46_handlers __read_mostly; static DEFINE_MUTEX(tunnel6_mutex); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family) { - struct xfrm6_tunnel **pprev; + struct xfrm6_tunnel __rcu **pprev; + struct xfrm6_tunnel *t; int ret = -EEXIST; int priority = handler->priority; mutex_lock(&tunnel6_mutex); for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; - *pprev; pprev = &(*pprev)->next) { - if ((*pprev)->priority > priority) + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel6_mutex))) != NULL; + pprev = &t->next) { + if (t->priority > priority) break; - if ((*pprev)->priority == priority) + if (t->priority == priority) goto err; } handler->next = *pprev; - *pprev = handler; + rcu_assign_pointer(*pprev, handler); ret = 0; @@ -65,14 +68,17 @@ EXPORT_SYMBOL(xfrm6_tunnel_register); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) { - struct xfrm6_tunnel **pprev; + struct xfrm6_tunnel __rcu **pprev; + struct xfrm6_tunnel *t; int ret = -ENOENT; mutex_lock(&tunnel6_mutex); for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; - *pprev; pprev = &(*pprev)->next) { - if (*pprev == handler) { + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel6_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { *pprev = handler->next; ret = 0; break; @@ -88,6 +94,11 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) EXPORT_SYMBOL(xfrm6_tunnel_deregister); +#define for_each_tunnel_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + static int tunnel6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; @@ -95,7 +106,7 @@ static int tunnel6_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; - for (handler = tunnel6_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->handler(skb)) return 0; @@ -113,7 +124,7 @@ static int tunnel46_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; - for (handler = tunnel46_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->handler(skb)) return 0; @@ -129,7 +140,7 @@ static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { struct xfrm6_tunnel *handler; - for (handler = tunnel6_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) break; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5acb3560ff15..91def93bec85 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -122,8 +122,8 @@ static void udp_v6_rehash(struct sock *sk) static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, - struct in6_addr *saddr, __be16 sport, - struct in6_addr *daddr, __be16 dport, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif) { int score = -1; @@ -239,8 +239,8 @@ exact_match: } static struct sock *__udp6_lib_lookup(struct net *net, - struct in6_addr *saddr, __be16 sport, - struct in6_addr *daddr, __be16 dport, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif, struct udp_table *udptable) { struct sock *sk, *result; @@ -320,6 +320,14 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, udptable); } +struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif) +{ + return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); +} +EXPORT_SYMBOL_GPL(udp6_lib_lookup); + + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -519,7 +527,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) } } - if (sk->sk_filter) { + if (rcu_dereference_raw(sk->sk_filter)) { if (udp_lib_checksum_complete(skb)) goto drop; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6baeabbbca82..7e74023ea6e4 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -199,7 +199,7 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops) struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); xfrm6_policy_afinfo.garbage_collect(net); - return (atomic_read(&ops->entries) > ops->gc_thresh * 2); + return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -255,7 +255,6 @@ static struct dst_ops xfrm6_dst_ops = { .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, .gc_thresh = 1024, - .entries = ATOMIC_INIT(0), }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { @@ -312,11 +311,13 @@ int __init xfrm6_init(void) */ gc_thresh = FIB6_TABLE_HASHSZ * 8; xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + dst_entries_init(&xfrm6_dst_ops); ret = xfrm6_policy_init(); - if (ret) + if (ret) { + dst_entries_destroy(&xfrm6_dst_ops); goto out; - + } ret = xfrm6_state_init(); if (ret) goto out_policy; @@ -341,4 +342,5 @@ void xfrm6_fini(void) //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); + dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 2ce3a8278f26..2969cad408de 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -199,7 +199,7 @@ static void x6spi_destroy_rcu(struct rcu_head *head) container_of(head, struct xfrm6_tunnel_spi, rcu_head)); } -void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) +static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; @@ -223,8 +223,6 @@ void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) spin_unlock_bh(&xfrm6_tunnel_spi_lock); } -EXPORT_SYMBOL(xfrm6_tunnel_free_spi); - static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { skb_push(skb, -skb_network_offset(skb)); @@ -317,13 +315,13 @@ static const struct xfrm_type xfrm6_tunnel_type = { .output = xfrm6_tunnel_output, }; -static struct xfrm6_tunnel xfrm6_tunnel_handler = { +static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, .priority = 2, }; -static struct xfrm6_tunnel xfrm46_tunnel_handler = { +static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, .priority = 2, |