diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/Makefile | 4 | ||||
-rw-r--r-- | net/ipv6/addrconf.c | 42 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 6 | ||||
-rw-r--r-- | net/ipv6/anycast.c | 133 | ||||
-rw-r--r-- | net/ipv6/datagram.c | 15 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 20 | ||||
-rw-r--r-- | net/ipv6/ip6_offload.c | 32 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 10 | ||||
-rw-r--r-- | net/ipv6/ip6_udp_tunnel.c | 107 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 218 | ||||
-rw-r--r-- | net/ipv6/netfilter/Kconfig | 41 | ||||
-rw-r--r-- | net/ipv6/netfilter/Makefile | 4 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_MASQUERADE.c | 76 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6table_nat.c | 233 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 199 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 120 | ||||
-rw-r--r-- | net/ipv6/netfilter/nft_chain_nat_ipv6.c | 165 | ||||
-rw-r--r-- | net/ipv6/netfilter/nft_masq_ipv6.c | 89 | ||||
-rw-r--r-- | net/ipv6/protocol.c | 1 | ||||
-rw-r--r-- | net/ipv6/sit.c | 107 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 4 | ||||
-rw-r--r-- | net/ipv6/sysctl_net_ipv6.c | 10 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 32 | ||||
-rw-r--r-- | net/ipv6/tcpv6_offload.c | 43 | ||||
-rw-r--r-- | net/ipv6/udp.c | 4 | ||||
-rw-r--r-- | net/ipv6/udp_offload.c | 72 |
26 files changed, 1070 insertions, 717 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 2fe6836..2e8c061 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -45,3 +45,7 @@ obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o + +ifneq ($(CONFIG_IPV6),) +obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o +endif diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 267ce3c..e189480 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1690,14 +1690,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) addrconf_mod_dad_work(ifp, 0); } -/* Join to solicited addr multicast group. */ - +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1705,12 +1703,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1718,26 +1715,24 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; - ipv6_dev_ac_inc(ifp->idev->dev, &addr); + __ipv6_dev_ac_inc(ifp->idev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -2849,6 +2844,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (dev->flags & IFF_SLAVE) break; + if (idev && idev->cnf.disable_ipv6) + break; + if (event == NETDEV_UP) { if (!addrconf_qdisc_ok(dev)) { /* device is not ready yet. */ @@ -3099,11 +3097,13 @@ restart: write_unlock_bh(&idev->lock); - /* Step 5: Discard multicast list */ - if (how) + /* Step 5: Discard anycast and multicast list */ + if (how) { + ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); - else + } else { ipv6_mc_down(idev); + } idev->tstamp = jiffies; @@ -4773,15 +4773,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { struct rt6_info *rt; - struct net_device *dev = ifp->idev->dev; - - rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, - dev->ifindex, 1); - if (rt) { - dst_hold(&rt->dst); - if (ip6_del_rt(rt)) - dst_free(&rt->dst); - } + + rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); + if (rt && ip6_del_rt(rt)) + dst_free(&rt->dst); } dst_hold(&ifp->rt->dst); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b9393e6..34f726f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -302,7 +302,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; chk_addr_ret = inet_addr_type(net, v4addr); - if (!sysctl_ip_nonlocal_bind && + if (!net->ipv4.sysctl_ip_nonlocal_bind && !(inet->freebind || inet->transparent) && v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && @@ -672,10 +672,10 @@ int inet6_sk_rebuild_header(struct sock *sk) } EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header); -bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) +bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, + const struct inet6_skb_parm *opt) { const struct ipv6_pinfo *np = inet6_sk(sk); - const struct inet6_skb_parm *opt = IP6CB(skb); if (np->rxopt.all) { if ((opt->hop && (np->rxopt.bits.hopopts || diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 2101832..f5e319a 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -46,10 +46,6 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); -/* Big ac list lock for all the sockets */ -static DEFINE_SPINLOCK(ipv6_sk_ac_lock); - - /* * socket join an anycast group */ @@ -77,7 +73,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; - rcu_read_lock(); + rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -90,11 +86,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) goto error; } else { /* router, no matching interface: just pick one */ - dev = dev_get_by_flags_rcu(net, IFF_UP, - IFF_UP | IFF_LOOPBACK); + dev = __dev_get_by_flags(net, IFF_UP, + IFF_UP | IFF_LOOPBACK); } } else - dev = dev_get_by_index_rcu(net, ifindex); + dev = __dev_get_by_index(net, ifindex); if (dev == NULL) { err = -ENODEV; @@ -126,17 +122,15 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) goto error; } - err = ipv6_dev_ac_inc(dev, addr); + err = __ipv6_dev_ac_inc(idev, addr); if (!err) { - spin_lock_bh(&ipv6_sk_ac_lock); pac->acl_next = np->ipv6_ac_list; np->ipv6_ac_list = pac; - spin_unlock_bh(&ipv6_sk_ac_lock); pac = NULL; } error: - rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -152,7 +146,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_ac_socklist *pac, *prev_pac; struct net *net = sock_net(sk); - spin_lock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -161,7 +155,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) prev_pac = pac; } if (!pac) { - spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_unlock(); return -ENOENT; } if (prev_pac) @@ -169,13 +163,10 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) else np->ipv6_ac_list = pac->acl_next; - spin_unlock_bh(&ipv6_sk_ac_lock); - - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, pac->acl_ifindex); + dev = __dev_get_by_index(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -192,18 +183,16 @@ void ipv6_sock_ac_close(struct sock *sk) if (!np->ipv6_ac_list) return; - spin_lock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; - spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; - rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; if (pac->acl_ifindex != prev_index) { - dev = dev_get_by_index_rcu(net, pac->acl_ifindex); + dev = __dev_get_by_index(net, pac->acl_ifindex); prev_index = pac->acl_ifindex; } if (dev) @@ -211,7 +200,12 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } - rcu_read_unlock(); + rtnl_unlock(); +} + +static void aca_get(struct ifacaddr6 *aca) +{ + atomic_inc(&aca->aca_refcnt); } static void aca_put(struct ifacaddr6 *ac) @@ -223,20 +217,39 @@ static void aca_put(struct ifacaddr6 *ac) } } +static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, + const struct in6_addr *addr) +{ + struct inet6_dev *idev = rt->rt6i_idev; + struct ifacaddr6 *aca; + + aca = kzalloc(sizeof(*aca), GFP_ATOMIC); + if (aca == NULL) + return NULL; + + aca->aca_addr = *addr; + in6_dev_hold(idev); + aca->aca_idev = idev; + aca->aca_rt = rt; + aca->aca_users = 1; + /* aca_tstamp should be updated upon changes */ + aca->aca_cstamp = aca->aca_tstamp = jiffies; + atomic_set(&aca->aca_refcnt, 1); + spin_lock_init(&aca->aca_lock); + + return aca; +} + /* * device anycast group inc (add if not found) */ -int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) +int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca; - struct inet6_dev *idev; struct rt6_info *rt; int err; - idev = in6_dev_get(dev); - - if (idev == NULL) - return -EINVAL; + ASSERT_RTNL(); write_lock_bh(&idev->lock); if (idev->dead) { @@ -252,46 +265,35 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) } } - /* - * not found: create a new one. - */ - - aca = kzalloc(sizeof(struct ifacaddr6), GFP_ATOMIC); - - if (aca == NULL) { - err = -ENOMEM; - goto out; - } - rt = addrconf_dst_alloc(idev, addr, true); if (IS_ERR(rt)) { - kfree(aca); err = PTR_ERR(rt); goto out; } - - aca->aca_addr = *addr; - aca->aca_idev = idev; - aca->aca_rt = rt; - aca->aca_users = 1; - /* aca_tstamp should be updated upon changes */ - aca->aca_cstamp = aca->aca_tstamp = jiffies; - atomic_set(&aca->aca_refcnt, 2); - spin_lock_init(&aca->aca_lock); + aca = aca_alloc(rt, addr); + if (aca == NULL) { + ip6_rt_put(rt); + err = -ENOMEM; + goto out; + } aca->aca_next = idev->ac_list; idev->ac_list = aca; + + /* Hold this for addrconf_join_solict() below before we unlock, + * it is already exposed via idev->ac_list. + */ + aca_get(aca); write_unlock_bh(&idev->lock); ip6_ins_rt(rt); - addrconf_join_solict(dev, &aca->aca_addr); + addrconf_join_solict(idev->dev, &aca->aca_addr); aca_put(aca); return 0; out: write_unlock_bh(&idev->lock); - in6_dev_put(idev); return err; } @@ -302,6 +304,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { @@ -331,7 +335,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) return 0; } -/* called with rcu_read_lock() */ +/* called with rtnl_lock() */ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev = __in6_dev_get(dev); @@ -341,6 +345,27 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) return __ipv6_dev_ac_dec(idev, addr); } +void ipv6_ac_destroy_dev(struct inet6_dev *idev) +{ + struct ifacaddr6 *aca; + + write_lock_bh(&idev->lock); + while ((aca = idev->ac_list) != NULL) { + idev->ac_list = aca->aca_next; + write_unlock_bh(&idev->lock); + + addrconf_leave_solict(idev, &aca->aca_addr); + + dst_hold(&aca->aca_rt->dst); + ip6_del_rt(aca->aca_rt); + + aca_put(aca); + + write_lock_bh(&idev->lock); + } + write_unlock_bh(&idev->lock); +} + /* * check if the interface has this anycast address * called with rcu_read_lock() diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 1844e87..2cdc383 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -332,7 +332,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; - struct sk_buff *skb, *skb2; + struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; @@ -342,7 +342,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) int copied; err = -EAGAIN; - skb = skb_dequeue(&sk->sk_error_queue); + skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; @@ -415,17 +415,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) msg->msg_flags |= MSG_ERRQUEUE; err = copied; - /* Reset and regenerate socket error */ - spin_lock_bh(&sk->sk_error_queue.lock); - sk->sk_err = 0; - if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { - sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_bh(&sk->sk_error_queue.lock); - sk->sk_error_report(sk); - } else { - spin_unlock_bh(&sk->sk_error_queue.lock); - } - out_free_skb: kfree_skb(skb); out: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 394bb82..141e1f3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -170,11 +170,11 @@ static bool is_ineligible(const struct sk_buff *skb) /* * Check the ICMP output rate limit */ -static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, - struct flowi6 *fl6) +static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, + struct flowi6 *fl6) { - struct dst_entry *dst; struct net *net = sock_net(sk); + struct dst_entry *dst; bool res = false; /* Informational messages are not limited. */ @@ -199,16 +199,20 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; - struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - res = inet_peer_xrlim_allow(peer, tmo); - if (peer) - inet_putpeer(peer); + if (icmp_global_allow()) { + struct inet_peer *peer; + + peer = inet_getpeer_v6(net->ipv6.peers, + &rt->rt6i_dst.addr, 1); + res = inet_peer_xrlim_allow(peer, tmo); + if (peer) + inet_putpeer(peer); + } } dst_release(dst); return res; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 5bcda33..9034f76 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -53,31 +53,6 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) return proto; } -static int ipv6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - const struct net_offload *ops; - int err = -EINVAL; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - err = -EPROTONOSUPPORT; - - ops = rcu_dereference(inet6_offloads[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - - if (likely(ops && ops->callbacks.gso_send_check)) { - skb_reset_transport_header(skb); - err = ops->callbacks.gso_send_check(skb); - } - -out: - return err; -} - static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, netdev_features_t features) { @@ -261,6 +236,9 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, /* flush if Traffic Class fields are different */ NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); NAPI_GRO_CB(p)->flush |= flush; + + /* Clear flush_id, there's really no concept of ID in IPv6. */ + NAPI_GRO_CB(p)->flush_id = 0; } NAPI_GRO_CB(skb)->flush |= flush; @@ -303,7 +281,6 @@ out_unlock: static struct packet_offload ipv6_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .callbacks = { - .gso_send_check = ipv6_gso_send_check, .gso_segment = ipv6_gso_segment, .gro_receive = ipv6_gro_receive, .gro_complete = ipv6_gro_complete, @@ -312,8 +289,9 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { static const struct net_offload sit_offload = { .callbacks = { - .gso_send_check = ipv6_gso_send_check, .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, }, }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b7a3e7b..8e950c2 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -701,11 +701,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) return 0; } - while (frag) { - skb = frag->next; - kfree_skb(frag); - frag = skb; - } + kfree_skb_list(frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); @@ -1008,7 +1004,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1040,7 +1036,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c new file mode 100644 index 0000000..b04ed72 --- /dev/null +++ b/net/ipv6/ip6_udp_tunnel.c @@ -0,0 +1,107 @@ +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/socket.h> +#include <linux/udp.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/in6.h> +#include <net/udp.h> +#include <net/udp_tunnel.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/ip6_tunnel.h> +#include <net/ip6_checksum.h> + +int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, + struct socket **sockp) +{ + struct sockaddr_in6 udp6_addr; + int err; + struct socket *sock = NULL; + + err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); + if (err < 0) + goto error; + + sk_change_net(sock->sk, net); + + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = cfg->local_udp_port; + err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, + sizeof(udp6_addr)); + if (err < 0) + goto error; + + if (cfg->peer_udp_port) { + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = cfg->peer_udp_port; + err = kernel_connect(sock, + (struct sockaddr *)&udp6_addr, + sizeof(udp6_addr), 0); + } + if (err < 0) + goto error; + + udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); + udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); + + *sockp = sock; + return 0; + +error: + if (sock) { + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sock->sk); + } + *sockp = NULL; + return err; +} +EXPORT_SYMBOL_GPL(udp_sock_create6); + +int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst, + struct sk_buff *skb, struct net_device *dev, + struct in6_addr *saddr, struct in6_addr *daddr, + __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port) +{ + struct udphdr *uh; + struct ipv6hdr *ip6h; + struct sock *sk = sock->sk; + + __skb_push(skb, sizeof(*uh)); + skb_reset_transport_header(skb); + uh = udp_hdr(skb); + + uh->dest = dst_port; + uh->source = src_port; + + uh->len = htons(skb->len); + uh->check = 0; + + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED + | IPSKB_REROUTED); + skb_dst_set(skb, dst); + + udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, + &sk->sk_v6_daddr, skb->len); + + __skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + ip6_flow_hdr(ip6h, prio, htonl(0)); + ip6h->payload_len = htons(skb->len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = ttl; + ip6h->daddr = *daddr; + ip6h->saddr = *saddr; + + ip6tunnel_xmit(skb, dev); + return 0; +} +EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7088179..9648de2 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -64,15 +64,6 @@ #include <net/ip6_checksum.h> -/* Set to 3 to get tracing... */ -#define MCAST_DEBUG 2 - -#if MCAST_DEBUG >= 3 -#define MDBG(x) printk x -#else -#define MDBG(x) -#endif - /* Ensure that we have struct in6_addr aligned on 32bit word. */ static void *__mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4), @@ -82,9 +73,6 @@ static void *__mld2_query_bugs[] __attribute__((__unused__)) = { static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; -/* Big mc list lock for all the sockets */ -static DEFINE_SPINLOCK(ipv6_sk_mc_lock); - static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void igmp6_timer_handler(unsigned long data); @@ -121,6 +109,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; +int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; /* * socket join on multicast group @@ -172,7 +161,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; - rcu_read_lock(); + rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, 0); @@ -181,10 +170,10 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) ip6_rt_put(rt); } } else - dev = dev_get_by_index_rcu(net, ifindex); + dev = __dev_get_by_index(net, ifindex); if (dev == NULL) { - rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -201,17 +190,15 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) err = ipv6_dev_mc_inc(dev, addr); if (err) { - rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } - spin_lock(&ipv6_sk_mc_lock); mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); - spin_unlock(&ipv6_sk_mc_lock); - rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,20 +216,17 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - spin_lock(&ipv6_sk_mc_lock); + rtnl_lock(); for (lnk = &np->ipv6_mc_list; - (mc_lst = rcu_dereference_protected(*lnk, - lockdep_is_held(&ipv6_sk_mc_lock))) != NULL; + (mc_lst = rtnl_dereference(*lnk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; - spin_unlock(&ipv6_sk_mc_lock); - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, mc_lst->ifindex); + dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev != NULL) { struct inet6_dev *idev = __in6_dev_get(dev); @@ -251,13 +235,14 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); - rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } - spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,16 +287,13 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; - spin_lock(&ipv6_sk_mc_lock); - while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, - lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { + rtnl_lock(); + while ((mc_lst = rtnl_dereference(np->ipv6_mc_list)) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; - spin_unlock(&ipv6_sk_mc_lock); - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, mc_lst->ifindex); + dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); @@ -320,14 +302,12 @@ void ipv6_sock_mc_close(struct sock *sk) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); - rcu_read_unlock(); atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); - spin_lock(&ipv6_sk_mc_lock); } - spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -576,9 +556,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, } 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, + /* changes to the ipv6_mc_list require the socket lock and + * rtnl lock. We have the socket lock and rcu read lock, * so reading the list is safe. */ @@ -602,9 +581,8 @@ 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. + /* changes to psl require the socket 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; @@ -663,14 +641,6 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, return rv; } -static void ma_put(struct ifmcaddr6 *mc) -{ - if (atomic_dec_and_test(&mc->mca_refcnt)) { - in6_dev_put(mc->idev); - kfree(mc); - } -} - static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; @@ -836,6 +806,48 @@ static void mld_clear_delrec(struct inet6_dev *idev) read_unlock_bh(&idev->lock); } +static void mca_get(struct ifmcaddr6 *mc) +{ + atomic_inc(&mc->mca_refcnt); +} + +static void ma_put(struct ifmcaddr6 *mc) +{ + if (atomic_dec_and_test(&mc->mca_refcnt)) { + in6_dev_put(mc->idev); + kfree(mc); + } +} + +static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, + const struct in6_addr *addr) +{ + struct ifmcaddr6 *mc; + + mc = kzalloc(sizeof(*mc), GFP_ATOMIC); + if (mc == NULL) + return NULL; + + setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); + + mc->mca_addr = *addr; + mc->idev = idev; /* reference taken by caller */ + mc->mca_users = 1; + /* mca_stamp should be updated upon changes */ + mc->mca_cstamp = mc->mca_tstamp = jiffies; + atomic_set(&mc->mca_refcnt, 1); + spin_lock_init(&mc->mca_lock); + + /* initial mode is (EX, empty) */ + mc->mca_sfmode = MCAST_EXCLUDE; + mc->mca_sfcount[MCAST_EXCLUDE] = 1; + + if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || + IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) + mc->mca_flags |= MAF_NOREPORT; + + return mc; +} /* * device multicast group inc (add if not found) @@ -845,6 +857,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -869,38 +883,20 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) } } - /* - * not found: create a new one. - */ - - mc = kzalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC); - - if (mc == NULL) { + mc = mca_alloc(idev, addr); + if (!mc) { write_unlock_bh(&idev->lock); in6_dev_put(idev); return -ENOMEM; } - setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); - - mc->mca_addr = *addr; - mc->idev = idev; /* (reference taken) */ - mc->mca_users = 1; - /* mca_stamp should be updated upon changes */ - mc->mca_cstamp = mc->mca_tstamp = jiffies; - atomic_set(&mc->mca_refcnt, 2); - spin_lock_init(&mc->mca_lock); - - /* initial mode is (EX, empty) */ - mc->mca_sfmode = MCAST_EXCLUDE; - mc->mca_sfcount[MCAST_EXCLUDE] = 1; - - if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || - IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) - mc->mca_flags |= MAF_NOREPORT; - mc->next = idev->mc_list; idev->mc_list = mc; + + /* Hold this for the code below before we unlock, + * it is already exposed via idev->mc_list. + */ + mca_get(mc); write_unlock_bh(&idev->lock); mld_del_delrec(idev, &mc->mca_addr); @@ -916,6 +912,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma = *map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { @@ -942,7 +940,7 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) struct inet6_dev *idev; int err; - rcu_read_lock(); + ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) @@ -950,7 +948,6 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) else err = __ipv6_dev_mc_dec(idev, addr); - rcu_read_unlock(); return err; } @@ -1191,15 +1188,16 @@ static void mld_update_qrv(struct inet6_dev *idev, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ + const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; - if (unlikely(idev->mc_qrv < 2)) { + if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", - idev->mc_qrv, MLD_QRV_DEFAULT); - idev->mc_qrv = MLD_QRV_DEFAULT; + idev->mc_qrv, min_qrv); + idev->mc_qrv = min_qrv; } } @@ -1239,7 +1237,7 @@ static void mld_update_qri(struct inet6_dev *idev, } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, - unsigned long *max_delay) + unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; @@ -1247,11 +1245,32 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, if (mld_in_v2_mode_only(idev)) return -EINVAL; - /* MLDv1 router present */ mldv1_md = ntohs(mld->mld_maxdelay); + + /* When in MLDv1 fallback and a MLDv2 router start-up being + * unaware of current MLDv1 operation, the MRC == MRD mapping + * only works when the exponential algorithm is not being + * used (as MLDv1 is unaware of such things). + * + * According to the RFC author, the MLDv2 implementations + * he's aware of all use a MRC < 32768 on start up queries. + * + * Thus, should we *ever* encounter something else larger + * than that, just assume the maximum possible within our + * reach. + */ + if (!v1_query) + mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); + *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); - mld_set_v1_mode(idev); + /* MLDv1 router present: we need to go into v1 mode *only* + * when an MLDv1 query is received as per section 9.12. of + * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 + * queries MUST be of exactly 24 octets. + */ + if (v1_query) + mld_set_v1_mode(idev); /* cancel MLDv2 report timer */ mld_gq_stop_timer(idev); @@ -1266,10 +1285,6 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { - /* hosts need to stay in MLDv1 mode, discard MLDv2 queries */ - if (mld_in_v1_mode(idev)) - return -EINVAL; - *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); @@ -1326,8 +1341,11 @@ int igmp6_event_query(struct sk_buff *skb) !(group_type&IPV6_ADDR_MULTICAST)) return -EINVAL; - if (len == MLD_V1_QUERY_LEN) { - err = mld_process_v1(idev, mld, &max_delay); + if (len < MLD_V1_QUERY_LEN) { + return -EINVAL; + } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { + err = mld_process_v1(idev, mld, &max_delay, + len == MLD_V1_QUERY_LEN); if (err < 0) return err; } else if (len >= MLD_V2_QUERY_LEN_MIN) { @@ -1359,8 +1377,9 @@ int igmp6_event_query(struct sk_buff *skb) mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } - } else + } else { return -EINVAL; + } read_lock_bh(&idev->lock); if (group_type == IPV6_ADDR_ANY) { @@ -2366,7 +2385,7 @@ 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, + /* callers have the socket lock and rtnl lock * so no other readers or writers of iml or its sflist */ if (!iml->sflist) { @@ -2478,6 +2497,14 @@ void ipv6_mc_down(struct inet6_dev *idev) mld_clear_delrec(idev); } +static void ipv6_mc_reset(struct inet6_dev *idev) +{ + idev->mc_qrv = sysctl_mld_qrv; + idev->mc_qi = MLD_QI_DEFAULT; + idev->mc_qri = MLD_QRI_DEFAULT; + idev->mc_v1_seen = 0; + idev->mc_maxdelay = unsolicited_report_interval(idev); +} /* Device going up */ @@ -2488,6 +2515,7 @@ void ipv6_mc_up(struct inet6_dev *idev) /* Install multicast list, except for all-nodes (already installed) */ read_lock_bh(&idev->lock); + ipv6_mc_reset(idev); for (i = idev->mc_list; i; i = i->next) igmp6_group_added(i); read_unlock_bh(&idev->lock); @@ -2508,13 +2536,7 @@ void ipv6_mc_init_dev(struct inet6_dev *idev) (unsigned long)idev); setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire, (unsigned long)idev); - - idev->mc_qrv = MLD_QRV_DEFAULT; - idev->mc_qi = MLD_QI_DEFAULT; - idev->mc_qri = MLD_QRI_DEFAULT; - - idev->mc_maxdelay = unsolicited_report_interval(idev); - idev->mc_v1_seen = 0; + ipv6_mc_reset(idev); write_unlock_bh(&idev->lock); } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ac93df1..a8f2530 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -57,9 +57,19 @@ config NFT_REJECT_IPV6 config NF_LOG_IPV6 tristate "IPv6 packet logging" - depends on NETFILTER_ADVANCED + default m if NETFILTER_ADVANCED=n select NF_LOG_COMMON +config NF_NAT_IPV6 + tristate "IPv6 NAT" + depends on NF_CONNTRACK_IPV6 + depends on NETFILTER_ADVANCED + select NF_NAT + help + The IPv6 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables or nft. + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 @@ -232,22 +242,37 @@ config IP6_NF_SECURITY If unsure, say N. -config NF_NAT_IPV6 - tristate "IPv6 NAT" +config IP6_NF_NAT + tristate "ip6tables NAT support" depends on NF_CONNTRACK_IPV6 depends on NETFILTER_ADVANCED select NF_NAT + select NF_NAT_IPV6 + select NETFILTER_XT_NAT help - The IPv6 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. It is controlled by - the `nat' table in ip6tables, see the man page for ip6tables(8). + This enables the `nat' table in ip6tables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. To compile it as a module, choose M here. If unsure, say N. -if NF_NAT_IPV6 +if IP6_NF_NAT + +config NF_NAT_MASQUERADE_IPV6 + tristate "IPv6 masquerade support" + help + This is the kernel functionality to provide NAT in the masquerade + flavour (automatic source address selection) for IPv6. + +config NFT_MASQ_IPV6 + tristate "IPv6 masquerade support for nf_tables" + depends on NF_TABLES_IPV6 + depends on NFT_MASQ + select NF_NAT_MASQUERADE_IPV6 config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" + select NF_NAT_MASQUERADE_IPV6 help Masquerading is a special case of NAT: all outgoing connections are changed to seem to come from a particular interface's address, and @@ -265,7 +290,7 @@ config IP6_NF_TARGET_NPT To compile it as a module, choose M here. If unsure, say N. -endif # NF_NAT_IPV6 +endif # IP6_NF_NAT endif # IP6_NF_IPTABLES diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index c0b2631..0f7e5b3 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o -obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o +obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o # objects for l3 independent conntrack nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o @@ -18,6 +18,7 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o +obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o # defrag nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o @@ -31,6 +32,7 @@ obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o +obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 3e4e92d..7f9f45d 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -19,33 +19,12 @@ #include <net/netfilter/nf_nat.h> #include <net/addrconf.h> #include <net/ipv6.h> +#include <net/netfilter/ipv6/nf_nat_masquerade.h> static unsigned int masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; - enum ip_conntrack_info ctinfo; - struct in6_addr src; - struct nf_conn *ct; - struct nf_nat_range newrange; - - ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); - - if (ipv6_dev_get_saddr(dev_net(par->out), par->out, - &ipv6_hdr(skb)->daddr, 0, &src) < 0) - return NF_DROP; - - nfct_nat(ct)->masq_index = par->out->ifindex; - - newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr.in6 = src; - newrange.max_addr.in6 = src; - newrange.min_proto = range->min_proto; - newrange.max_proto = range->max_proto; - - return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); + return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out); } static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) @@ -57,48 +36,6 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) return 0; } -static int device_cmp(struct nf_conn *ct, void *ifindex) -{ - const struct nf_conn_nat *nat = nfct_nat(ct); - - if (!nat) - return 0; - if (nf_ct_l3num(ct) != NFPROTO_IPV6) - return 0; - return nat->masq_index == (int)(long)ifindex; -} - -static int masq_device_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - const struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct net *net = dev_net(dev); - - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); - - return NOTIFY_DONE; -} - -static struct notifier_block masq_dev_notifier = { - .notifier_call = masq_device_event, -}; - -static int masq_inet_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; - - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); -} - -static struct notifier_block masq_inet_notifier = { - .notifier_call = masq_inet_event, -}; - static struct xt_target masquerade_tg6_reg __read_mostly = { .name = "MASQUERADE", .family = NFPROTO_IPV6, @@ -115,17 +52,14 @@ static int __init masquerade_tg6_init(void) int err; err = xt_register_target(&masquerade_tg6_reg); - if (err == 0) { - register_netdevice_notifier(&masq_dev_notifier); - register_inet6addr_notifier(&masq_inet_notifier); - } + if (err == 0) + nf_nat_masquerade_ipv6_register_notifier(); return err; } static void __exit masquerade_tg6_exit(void) { - unregister_inet6addr_notifier(&masq_inet_notifier); - unregister_netdevice_notifier(&masq_dev_notifier); + nf_nat_masquerade_ipv6_unregister_notifier(); xt_unregister_target(&masquerade_tg6_reg); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 387d8b8..b0634ac 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -30,222 +30,57 @@ static const struct xt_table nf_nat_ipv6_table = { .af = NFPROTO_IPV6, }; -static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) -{ - /* Force range to this IP; let proto decide mapping for - * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). - */ - struct nf_nat_range range; - - range.flags = 0; - pr_debug("Allocating NULL binding for %p (%pI6)\n", ct, - HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? - &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 : - &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6); - - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); -} - -static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, - const struct net_device *in, - const struct net_device *out, - struct nf_conn *ct) +static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - unsigned int ret; - ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat); - if (ret == NF_ACCEPT) { - if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) - ret = alloc_null_binding(ct, hooknum); - } - return ret; + return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat); } -static unsigned int -nf_nat_ipv6_fn(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); - __be16 frag_off; - int hdrlen; - u8 nexthdr; - - ct = nf_ct_get(skb, &ctinfo); - /* Can't track? It's not due to stress, or conntrack would - * have dropped it. Hence it's the user's responsibilty to - * packet filter it out, or implement conntrack/NAT for that - * protocol. 8) --RR - */ - if (!ct) - return NF_ACCEPT; - - /* Don't try to NAT if this packet is not conntracked */ - if (nf_ct_is_untracked(ct)) - return NF_ACCEPT; - - nat = nf_ct_nat_ext_add(ct); - if (nat == NULL) - return NF_ACCEPT; - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - nexthdr = ipv6_hdr(skb)->nexthdr; - hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - ops->hooknum, - hdrlen)) - return NF_DROP; - else - return NF_ACCEPT; - } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - unsigned int ret; - - ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct); - if (ret != NF_ACCEPT) - return ret; - } else { - pr_debug("Already setup manip %s for ct %p\n", - maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", - ct); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) - goto oif_changed; - } - break; - - default: - /* ESTABLISHED */ - NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) - goto oif_changed; - } - - return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); - -oif_changed: - nf_ct_kill_acct(ct, ctinfo, skb); - return NF_DROP; + return nf_nat_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain); } -static unsigned int -nf_nat_ipv6_in(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - unsigned int ret; - struct in6_addr daddr = ipv6_hdr(skb)->daddr; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) - skb_dst_drop(skb); - - return ret; + return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain); } -static unsigned int -nf_nat_ipv6_out(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { -#ifdef CONFIG_XFRM - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - int err; -#endif - unsigned int ret; - - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct ipv6hdr)) - return NF_ACCEPT; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); -#ifdef CONFIG_XFRM - if (ret != NF_DROP && ret != NF_STOLEN && - !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, - &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && - ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(skb, AF_INET6); - if (err < 0) - ret = NF_DROP_ERR(err); - } - } -#endif - return ret; + return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain); } -static unsigned int -nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int ret; - int err; - - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct ipv6hdr)) - return NF_ACCEPT; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, - &ct->tuplehash[!dir].tuple.src.u3)) { - err = ip6_route_me_harder(skb); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#ifdef CONFIG_XFRM - else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && - ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(skb, AF_INET6); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#endif - } - return ret; + return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { /* Before packet filtering, change destination */ { - .hook = nf_nat_ipv6_in, + .hook = ip6table_nat_in, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, @@ -253,7 +88,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { }, /* After packet filtering, change source */ { - .hook = nf_nat_ipv6_out, + .hook = ip6table_nat_out, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, @@ -261,7 +96,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { }, /* Before packet filtering, change destination */ { - .hook = nf_nat_ipv6_local_fn, + .hook = ip6table_nat_local_fn, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, @@ -269,7 +104,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { }, /* After packet filtering, change source */ { - .hook = nf_nat_ipv6_fn, + .hook = ip6table_nat_fn, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index fc8e49b..c5812e1 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -261,6 +261,205 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); +unsigned int +nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + __be16 frag_off; + int hdrlen; + u8 nexthdr; + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; + + /* Don't try to NAT if this packet is not conntracked */ + if (nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + ops->hooknum, + hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + unsigned int ret; + + ret = do_chain(ops, skb, in, out, ct); + if (ret != NF_ACCEPT) + return ret; + + if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum))) + break; + + ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + if (ret != NF_ACCEPT) + return ret; + } else { + pr_debug("Already setup manip %s for ct %p\n", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", + ct); + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + goto oif_changed; + } + break; + + default: + /* ESTABLISHED */ + NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || + ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + goto oif_changed; + } + + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn); + +unsigned int +nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)) +{ + unsigned int ret; + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_in); + +unsigned int +nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + int err; +#endif + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) { + err = nf_xfrm_me_harder(skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } + } +#endif + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_out); + +unsigned int +nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + int err; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + err = ip6_route_me_harder(skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) { + err = nf_xfrm_me_harder(skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#endif + } + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_local_fn); + static int __init nf_nat_l3proto_ipv6_init(void) { int err; diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c new file mode 100644 index 0000000..7745609 --- /dev/null +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -0,0 +1,120 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/atomic.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_nat.h> +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/netfilter/ipv6/nf_nat_masquerade.h> + +unsigned int +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, + const struct net_device *out) +{ + enum ip_conntrack_info ctinfo; + struct in6_addr src; + struct nf_conn *ct; + struct nf_nat_range newrange; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + if (ipv6_dev_get_saddr(dev_net(out), out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) + return NF_DROP; + + nfct_nat(ct)->masq_index = out->ifindex; + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = src; + newrange.max_addr.in6 = src; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); + +static int device_cmp(struct nf_conn *ct, void *ifindex) +{ + const struct nf_conn_nat *nat = nfct_nat(ct); + + if (!nat) + return 0; + if (nf_ct_l3num(ct) != NFPROTO_IPV6) + return 0; + return nat->masq_index == (int)(long)ifindex; +} + +static int masq_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + + if (event == NETDEV_DOWN) + nf_ct_iterate_cleanup(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); + + return NOTIFY_DONE; +} + +static struct notifier_block masq_dev_notifier = { + .notifier_call = masq_device_event, +}; + +static int masq_inet_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + struct netdev_notifier_info info; + + netdev_notifier_info_init(&info, ifa->idev->dev); + return masq_device_event(this, event, &info); +} + +static struct notifier_block masq_inet_notifier = { + .notifier_call = masq_inet_event, +}; + +static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0); + +void nf_nat_masquerade_ipv6_register_notifier(void) +{ + /* check if the notifier is already set */ + if (atomic_inc_return(&masquerade_notifier_refcount) > 1) + return; + + register_netdevice_notifier(&masq_dev_notifier); + register_inet6addr_notifier(&masq_inet_notifier); +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier); + +void nf_nat_masquerade_ipv6_unregister_notifier(void) +{ + /* check if the notifier still has clients */ + if (atomic_dec_return(&masquerade_notifier_refcount) > 0) + return; + + unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_netdevice_notifier(&masq_dev_notifier); +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index d189fcb..1c4b75d 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -24,144 +24,53 @@ #include <net/netfilter/nf_nat_l3proto.h> #include <net/ipv6.h> -/* - * IPv6 NAT chains - */ - -static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct) { - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); - __be16 frag_off; - int hdrlen; - u8 nexthdr; struct nft_pktinfo pkt; - unsigned int ret; - - if (ct == NULL || nf_ct_is_untracked(ct)) - return NF_ACCEPT; - - nat = nf_ct_nat_ext_add(ct); - if (nat == NULL) - return NF_ACCEPT; - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED + IP_CT_IS_REPLY: - nexthdr = ipv6_hdr(skb)->nexthdr; - hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - ops->hooknum, - hdrlen)) - return NF_DROP; - else - return NF_ACCEPT; - } - /* Fall through */ - case IP_CT_NEW: - if (nf_nat_initialized(ct, maniptype)) - break; - - nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); - ret = nft_do_chain(&pkt, ops); - if (ret != NF_ACCEPT) - return ret; - if (!nf_nat_initialized(ct, maniptype)) { - ret = nf_nat_alloc_null_binding(ct, ops->hooknum); - if (ret != NF_ACCEPT) - return ret; - } - default: - break; - } + nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); - return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); + return nft_do_chain(&pkt, ops); } -static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - struct in6_addr daddr = ipv6_hdr(skb)->daddr; - unsigned int ret; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) - skb_dst_drop(skb); - - return ret; + return nf_nat_ipv6_fn(ops, skb, in, out, nft_nat_do_chain); } -static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int nft_nat_ipv6_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - enum ip_conntrack_info ctinfo __maybe_unused; - const struct nf_conn *ct __maybe_unused; - unsigned int ret; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); -#ifdef CONFIG_XFRM - if (ret != NF_DROP && ret != NF_STOLEN && - !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, - &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all)) - if (nf_xfrm_me_harder(skb, AF_INET6) < 0) - ret = NF_DROP; - } -#endif - return ret; + return nf_nat_ipv6_in(ops, skb, in, out, nft_nat_do_chain); } -static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int nft_nat_ipv6_out(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - enum ip_conntrack_info ctinfo; - const struct nf_conn *ct; - unsigned int ret; - - ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + return nf_nat_ipv6_out(ops, skb, in, out, nft_nat_do_chain); +} - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, - &ct->tuplehash[!dir].tuple.src.u3)) { - if (ip6_route_me_harder(skb)) - ret = NF_DROP; - } -#ifdef CONFIG_XFRM - else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[!dir].tuple.src.u.all) - if (nf_xfrm_me_harder(skb, AF_INET6)) - ret = NF_DROP; -#endif - } - return ret; +static unsigned int nft_nat_ipv6_local_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return nf_nat_ipv6_local_fn(ops, skb, in, out, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv6 = { @@ -174,10 +83,10 @@ static const struct nf_chain_type nft_chain_nat_ipv6 = { (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .hooks = { - [NF_INET_PRE_ROUTING] = nf_nat_ipv6_prerouting, - [NF_INET_POST_ROUTING] = nf_nat_ipv6_postrouting, - [NF_INET_LOCAL_OUT] = nf_nat_ipv6_output, - [NF_INET_LOCAL_IN] = nf_nat_ipv6_fn, + [NF_INET_PRE_ROUTING] = nft_nat_ipv6_in, + [NF_INET_POST_ROUTING] = nft_nat_ipv6_out, + [NF_INET_LOCAL_OUT] = nft_nat_ipv6_local_fn, + [NF_INET_LOCAL_IN] = nft_nat_ipv6_fn, }, }; diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c new file mode 100644 index 0000000..4e51334 --- /dev/null +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com> + * + * 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/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nft_masq.h> +#include <net/netfilter/ipv6/nf_nat_masquerade.h> + +static void nft_masq_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_masq *priv = nft_expr_priv(expr); + struct nf_nat_range range; + unsigned int verdict; + + range.flags = priv->flags; + + verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); + + data[NFT_REG_VERDICT].verdict = verdict; +} + +static int nft_masq_ipv6_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + int err; + + err = nft_masq_init(ctx, expr, tb); + if (err < 0) + return err; + + nf_nat_masquerade_ipv6_register_notifier(); + return 0; +} + +static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + nf_nat_masquerade_ipv6_unregister_notifier(); +} + +static struct nft_expr_type nft_masq_ipv6_type; +static const struct nft_expr_ops nft_masq_ipv6_ops = { + .type = &nft_masq_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)), + .eval = nft_masq_ipv6_eval, + .init = nft_masq_ipv6_init, + .destroy = nft_masq_ipv6_destroy, + .dump = nft_masq_dump, +}; + +static struct nft_expr_type nft_masq_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "masq", + .ops = &nft_masq_ipv6_ops, + .policy = nft_masq_policy, + .maxattr = NFTA_MASQ_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_masq_ipv6_module_init(void) +{ + return nft_register_expr(&nft_masq_ipv6_type); +} + +static void __exit nft_masq_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_masq_ipv6_type); +} + +module_init(nft_masq_ipv6_module_init); +module_exit(nft_masq_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq"); diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index e048cf1..e3770ab 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -51,6 +51,7 @@ EXPORT_SYMBOL(inet6_del_protocol); #endif const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet6_offloads); int inet6_add_offload(const struct net_offload *prot, unsigned char protocol) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 86e3fa8..db75809 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -822,6 +822,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, int addr_type; u8 ttl; int err; + u8 protocol = IPPROTO_IPV6; + int t_hlen = tunnel->hlen + sizeof(struct iphdr); if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; @@ -911,8 +913,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + if (IS_ERR(skb)) { + ip_rt_put(rt); + goto out; + } + if (df) { - mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); + mtu = dst_mtu(&rt->dst) - t_hlen; if (mtu < 68) { dev->stats.collisions++; @@ -947,7 +955,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, /* * Okay, now see if we can stuff it in the buffer as-is. */ - max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr); + max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { @@ -969,14 +977,13 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); - if (IS_ERR(skb)) { + if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) { ip_rt_put(rt); - goto out; + goto tx_error; } err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, - IPPROTO_IPV6, tos, ttl, df, + protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; @@ -1059,8 +1066,10 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { + int t_hlen = tunnel->hlen + sizeof(struct iphdr); + dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); - dev->mtu = tdev->mtu - sizeof(struct iphdr); + dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } @@ -1307,7 +1316,10 @@ done: static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr)) + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen = tunnel->hlen + sizeof(struct iphdr); + + if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - t_hlen) return -EINVAL; dev->mtu = new_mtu; return 0; @@ -1338,12 +1350,15 @@ static void ipip6_dev_free(struct net_device *dev) static void ipip6_tunnel_setup(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen = tunnel->hlen + sizeof(struct iphdr); + dev->netdev_ops = &ipip6_netdev_ops; dev->destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); - dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr); + dev->hard_header_len = LL_MAX_HEADER + t_hlen; + dev->mtu = ETH_DATA_LEN - t_hlen; dev->flags = IFF_NOARP; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->iflink = 0; @@ -1466,6 +1481,40 @@ static void ipip6_netlink_parms(struct nlattr *data[], } +/* This function returns true when ENCAP attributes are present in the nl msg */ +static bool ipip6_netlink_encap_parms(struct nlattr *data[], + struct ip_tunnel_encap *ipencap) +{ + bool ret = false; + + memset(ipencap, 0, sizeof(*ipencap)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_ENCAP_TYPE]) { + ret = true; + ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); + } + + if (data[IFLA_IPTUN_ENCAP_FLAGS]) { + ret = true; + ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); + } + + if (data[IFLA_IPTUN_ENCAP_SPORT]) { + ret = true; + ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]); + } + + if (data[IFLA_IPTUN_ENCAP_DPORT]) { + ret = true; + ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]); + } + + return ret; +} + #ifdef CONFIG_IPV6_SIT_6RD /* This function returns true when 6RD attributes are present in the nl msg */ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], @@ -1509,12 +1558,20 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip_tunnel *nt; + struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif int err; nt = netdev_priv(dev); + + if (ipip6_netlink_encap_parms(data, &ipencap)) { + err = ip_tunnel_encap_setup(nt, &ipencap); + if (err < 0) + return err; + } + ipip6_netlink_parms(data, &nt->parms); if (ipip6_tunnel_locate(net, &nt->parms, 0)) @@ -1537,15 +1594,23 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; + struct ip_tunnel_encap ipencap; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif + int err; if (dev == sitn->fb_tunnel_dev) return -EINVAL; + if (ipip6_netlink_encap_parms(data, &ipencap)) { + err = ip_tunnel_encap_setup(t, &ipencap); + if (err < 0) + return err; + } + ipip6_netlink_parms(data, &p); if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || @@ -1599,6 +1664,14 @@ static size_t ipip6_get_size(const struct net_device *dev) /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ nla_total_size(2) + #endif + /* IFLA_IPTUN_ENCAP_TYPE */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_FLAGS */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_SPORT */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_DPORT */ + nla_total_size(2) + 0; } @@ -1630,6 +1703,16 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; #endif + if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, + tunnel->encap.type) || + nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT, + tunnel->encap.sport) || + nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT, + tunnel->encap.dport) || + nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, + tunnel->encap.dport)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -1651,6 +1734,10 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, #endif + [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, }; static void ipip6_dellink(struct net_device *dev, struct list_head *head) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 83cea1d..9a2838e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -24,7 +24,7 @@ #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) -static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS]; +static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly; /* RFC 2460, Section 8.3: * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] @@ -203,7 +203,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->ir_num = ntohs(th->dest); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - if (ipv6_opt_accepted(sk, skb) || + if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { atomic_inc(&skb->users); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 0c56c93..c5c10fa 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,6 +16,8 @@ #include <net/addrconf.h> #include <net/inet_frag.h> +static int one = 1; + static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", @@ -63,6 +65,14 @@ static struct ctl_table ipv6_rotable[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "mld_qrv", + .data = &sysctl_mld_qrv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, { } }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 29964c3..132bac1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,13 +93,16 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); - sk->sk_rx_dst = dst; - inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; - if (rt->rt6i_node) - inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; + if (dst) { + const struct rt6_info *rt = (const struct rt6_info *)dst; + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + if (rt->rt6i_node) + inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; + } } static void tcp_v6_hash(struct sock *sk) @@ -738,8 +741,9 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = inet6_iif(skb); - if (!TCP_SKB_CB(skb)->when && - (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || + if (!TCP_SKB_CB(skb)->tcp_tw_isn && + (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || + np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { atomic_inc(&skb->users); @@ -1364,7 +1368,7 @@ ipv6_pktoptions: np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); - if (ipv6_opt_accepted(sk, opt_skb)) { + if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); } else { @@ -1408,11 +1412,19 @@ static int tcp_v6_rcv(struct sk_buff *skb) th = tcp_hdr(skb); hdr = ipv6_hdr(skb); + /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() + * barrier() makes sure compiler wont play fool^Waliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), + sizeof(struct inet6_skb_parm)); + barrier(); + TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->when = 0; + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index dbb3d92..c1ab771 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -15,23 +15,6 @@ #include <net/ip6_checksum.h> #include "ip6_offload.h" -static int tcp_v6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct tcphdr *th; - - if (!pskb_may_pull(skb, sizeof(*th))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - skb->ip_summed = CHECKSUM_PARTIAL; - __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); - return 0; -} - static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -58,10 +41,32 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) return tcp_gro_complete(skb); } +struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return ERR_PTR(-EINVAL); + + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + /* Set up pseudo header, usually expect stack to have done + * this. + */ + + th->check = 0; + skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); + } + + return tcp_gso_segment(skb, features); +} static const struct net_offload tcpv6_offload = { .callbacks = { - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_gso_segment, + .gso_segment = tcp6_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 12fcce8f..f6ba535 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -891,6 +891,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; } + if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b13e377..212ebfc 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -17,28 +17,6 @@ #include <net/ip6_checksum.h> #include "ip6_offload.h" -static int udp6_ufo_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct udphdr *uh; - - if (!pskb_may_pull(skb, sizeof(*uh))) - return -EINVAL; - - if (likely(!skb->encapsulation)) { - ipv6h = ipv6_hdr(skb); - uh = udp_hdr(skb); - - uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_UDP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct udphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - } - - return 0; -} - static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { @@ -49,7 +27,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); - int offset; __wsum csum; int tnl_hlen; @@ -83,13 +60,27 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features); else { + const struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ - offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset += skb->csum_offset; - *(__sum16 *)(skb->data + offset) = csum_fold(csum); + + uh = udp_hdr(skb); + ipv6h = ipv6_hdr(skb); + + uh->check = 0; + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = udp_v6_check(skb->len, &ipv6h->saddr, + &ipv6h->daddr, csum); + + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + skb->ip_summed = CHECKSUM_NONE; /* Check if there is enough headroom to insert fragment header. */ @@ -134,19 +125,29 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head, { struct udphdr *uh = udp_gro_udphdr(skb); + if (unlikely(!uh)) + goto flush; + /* Don't bother verifying checksum if we're going to flush anyway. */ - if (unlikely(!uh) || - (!NAPI_GRO_CB(skb)->flush && - skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, - ip6_gro_compute_pseudo))) { - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - } + if (NAPI_GRO_CB(skb)->flush) + goto skip; + if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, + ip6_gro_compute_pseudo)) + goto flush; + else if (uh->check) + skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_gro_compute_pseudo); + +skip: return udp_gro_receive(head, skb, uh); + +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; } -int udp6_gro_complete(struct sk_buff *skb, int nhoff) +static int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); @@ -160,7 +161,6 @@ int udp6_gro_complete(struct sk_buff *skb, int nhoff) static const struct net_offload udpv6_offload = { .callbacks = { - .gso_send_check = udp6_ufo_send_check, .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, |