diff options
Diffstat (limited to 'net/ipv6')
43 files changed, 2183 insertions, 1040 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index b6d3f79151e2..2068ac4fbdad 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -7,9 +7,11 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ - raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o +ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o + ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o @@ -39,5 +41,6 @@ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-y += addrconf_core.o exthdrs_core.o +obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6_offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0424e4e27414..6fca01f136ad 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -81,6 +81,7 @@ #include <net/pkt_sched.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> +#include <linux/netconf.h> #ifdef CONFIG_IPV6_PRIVACY #include <linux/random.h> @@ -401,7 +402,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { pr_info("%s: Disabled Multicast RS\n", dev->name); ndev->cnf.rtr_solicits = 0; @@ -460,6 +461,150 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev) return idev; } +static int inet6_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + + /* type -1 is used for ALL */ + if (type == -1 || type == NETCONFA_FORWARDING) + size += nla_total_size(4); +#ifdef CONFIG_IPV6_MROUTE + if (type == -1 || type == NETCONFA_MC_FORWARDING) + size += nla_total_size(4); +#endif + + return size; +} + +static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, + struct ipv6_devconf *devconf, u32 portid, + u32 seq, int event, unsigned int flags, + int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (nlh == NULL) + return -EMSGSIZE; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_INET6; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) + goto nla_put_failure; + + /* type -1 is used for ALL */ + if ((type == -1 || type == NETCONFA_FORWARDING) && + nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) + goto nla_put_failure; +#ifdef CONFIG_IPV6_MROUTE + if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + nla_put_s32(skb, NETCONFA_MC_FORWARDING, + devconf->mc_forwarding) < 0) + goto nla_put_failure; +#endif + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv6_devconf *devconf) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, + RTM_NEWNETCONF, 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err); +} + +static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, + [NETCONFA_FORWARDING] = { .len = sizeof(int) }, +}; + +static int inet6_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX+1]; + struct netconfmsg *ncm; + struct sk_buff *skb; + struct ipv6_devconf *devconf; + struct inet6_dev *in6_dev; + struct net_device *dev; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_ipv6_policy); + if (err < 0) + goto errout; + + err = EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + switch (ifindex) { + case NETCONFA_IFINDEX_ALL: + devconf = net->ipv6.devconf_all; + break; + case NETCONFA_IFINDEX_DEFAULT: + devconf = net->ipv6.devconf_dflt; + break; + default: + dev = __dev_get_by_index(net, ifindex); + if (dev == NULL) + goto errout; + in6_dev = __in6_dev_get(dev); + if (in6_dev == NULL) + goto errout; + devconf = &in6_dev->cnf; + break; + } + + err = -ENOBUFS; + skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + -1); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + #ifdef CONFIG_SYSCTL static void dev_forward_change(struct inet6_dev *idev) { @@ -471,7 +616,7 @@ static void dev_forward_change(struct inet6_dev *idev) dev = idev->dev; if (idev->cnf.forwarding) dev_disable_lro(dev); - if (dev && (dev->flags & IFF_MULTICAST)) { + if (dev->flags & IFF_MULTICAST) { if (idev->cnf.forwarding) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); else @@ -486,6 +631,8 @@ static void dev_forward_change(struct inet6_dev *idev) else addrconf_leave_anycast(ifa); } + inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING, + dev->ifindex, &idev->cnf); } @@ -518,6 +665,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) *p = newf; if (p == &net->ipv6.devconf_dflt->forwarding) { + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); rtnl_unlock(); return 0; } @@ -525,6 +676,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_all->forwarding) { net->ipv6.devconf_dflt->forwarding = newf; addrconf_forward_change(net, newf); + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); rtnl_unlock(); @@ -553,7 +708,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_warn("Freeing alive inet6 address %p\n", ifp); return; } - dst_release(&ifp->rt->dst); + ip6_rt_put(ifp->rt); kfree_rcu(ifp, rcu); } @@ -805,7 +960,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) rt6_set_expires(rt, expires); } } - dst_release(&rt->dst); + ip6_rt_put(rt); } /* clean up prefsrc entries */ @@ -1692,7 +1847,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) cfg.fc_flags |= RTF_NONEXTHOP; #endif @@ -1752,7 +1907,7 @@ static void addrconf_add_mroute(struct net_device *dev) ip6_route_add(&cfg); } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void sit_route_add(struct net_device *dev) { struct fib6_config cfg = { @@ -1881,8 +2036,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, dev, expires, flags); } - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); } /* Try to figure out our local address for this prefix */ @@ -2104,7 +2258,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) if (dev == NULL) goto err_exit; -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT) { const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; @@ -2268,7 +2422,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -2287,7 +2441,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -2315,7 +2469,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, } } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void sit_add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; @@ -2434,7 +2588,7 @@ static void addrconf_dev_config(struct net_device *dev) addrconf_add_linklocal(idev, &addr); } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; @@ -2471,7 +2625,7 @@ static void addrconf_sit_config(struct net_device *dev) } #endif -#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) +#if IS_ENABLED(CONFIG_NET_IPGRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; @@ -2601,12 +2755,12 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } switch (dev->type) { -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: addrconf_sit_config(dev); break; #endif -#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) +#if IS_ENABLED(CONFIG_NET_IPGRE) case ARPHRD_IPGRE: addrconf_gre_config(dev); break; @@ -2843,7 +2997,7 @@ static void addrconf_rs_timer(unsigned long data) if (idev->dead || !(idev->if_flags & IF_READY)) goto out; - if (idev->cnf.forwarding) + if (!ipv6_accept_ra(idev)) goto out; /* Announcement received after solicitation was sent */ @@ -3005,8 +3159,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) router advertisements, start sending router solicitations. */ - if (((ifp->idev->cnf.accept_ra == 1 && !ifp->idev->cnf.forwarding) || - ifp->idev->cnf.accept_ra == 2) && + if (ipv6_accept_ra(ifp->idev) && ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { @@ -3194,7 +3347,7 @@ void if6_proc_exit(void) } #endif /* CONFIG_PROC_FS */ -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { @@ -3892,6 +4045,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; + array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; } static inline size_t inet6_ifla6_size(void) @@ -4560,6 +4714,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "ndisc_notify", + .data = &ipv6_devconf.ndisc_notify, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { /* sentinel */ } }, @@ -4784,6 +4945,8 @@ int __init addrconf_init(void) inet6_dump_ifmcaddr, NULL); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, + NULL, NULL); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a974247a9ae4..b043c60429bd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -160,7 +160,8 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; @@ -282,7 +283,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; lock_sock(sk); @@ -699,249 +700,9 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ipv6_opt_accepted); -static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) -{ - const struct inet6_protocol *ops = NULL; - - for (;;) { - struct ipv6_opt_hdr *opth; - int len; - - if (proto != NEXTHDR_HOP) { - ops = rcu_dereference(inet6_protos[proto]); - - if (unlikely(!ops)) - break; - - if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) - break; - } - - if (unlikely(!pskb_may_pull(skb, 8))) - break; - - opth = (void *)skb->data; - len = ipv6_optlen(opth); - - if (unlikely(!pskb_may_pull(skb, len))) - break; - - proto = opth->nexthdr; - __skb_pull(skb, len); - } - - return proto; -} - -static int ipv6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int err = -EINVAL; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - err = -EPROTONOSUPPORT; - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - - if (likely(ops && ops->gso_send_check)) { - skb_reset_transport_header(skb); - err = ops->gso_send_check(skb); - } - rcu_read_unlock(); - -out: - return err; -} - -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int proto; - struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; - u8 *prevhdr; - int offset = 0; - - if (!(features & NETIF_F_V6_CSUM)) - features &= ~NETIF_F_SG; - - if (unlikely(skb_shinfo(skb)->gso_type & - ~(SKB_GSO_UDP | - SKB_GSO_DODGY | - SKB_GSO_TCP_ECN | - SKB_GSO_TCPV6 | - 0))) - goto out; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - segs = ERR_PTR(-EPROTONOSUPPORT); - - proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[proto]); - if (likely(ops && ops->gso_segment)) { - skb_reset_transport_header(skb); - segs = ops->gso_segment(skb, features); - } - rcu_read_unlock(); - - if (IS_ERR(segs)) - goto out; - - for (skb = segs; skb; skb = skb->next) { - ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(skb->len - skb->mac_len - - sizeof(*ipv6h)); - if (proto == IPPROTO_UDP) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)(skb_network_header(skb) + - unfrag_ip6hlen); - fptr->frag_off = htons(offset); - if (skb->next != NULL) - fptr->frag_off |= htons(IP6_MF); - offset += (ntohs(ipv6h->payload_len) - - sizeof(struct frag_hdr)); - } - } - -out: - return segs; -} - -static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; - struct ipv6hdr *iph; - unsigned int nlen; - unsigned int hlen; - unsigned int off; - int flush = 1; - int proto; - __wsum csum; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*iph); - iph = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - iph = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!iph)) - goto out; - } - - skb_gro_pull(skb, sizeof(*iph)); - skb_set_transport_header(skb, skb_gro_offset(skb)); - - flush += ntohs(iph->payload_len) != skb_gro_len(skb); - - rcu_read_lock(); - proto = iph->nexthdr; - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) { - __pskb_pull(skb, skb_gro_offset(skb)); - proto = ipv6_gso_pull_exthdrs(skb, proto); - skb_gro_pull(skb, -skb_transport_offset(skb)); - skb_reset_transport_header(skb); - __skb_push(skb, skb_gro_offset(skb)); - - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) - goto out_unlock; - - iph = ipv6_hdr(skb); - } - - NAPI_GRO_CB(skb)->proto = proto; - - flush--; - nlen = skb_network_header_len(skb); - - for (p = *head; p; p = p->next) { - const struct ipv6hdr *iph2; - __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ - - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - iph2 = ipv6_hdr(p); - first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - - /* All fields must match except length and Traffic Class. */ - if (nlen != skb_network_header_len(p) || - (first_word & htonl(0xF00FFFFF)) || - memcmp(&iph->nexthdr, &iph2->nexthdr, - nlen - offsetof(struct ipv6hdr, nexthdr))) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); - NAPI_GRO_CB(p)->flush |= flush; - } - - NAPI_GRO_CB(skb)->flush |= flush; - - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); - - pp = ops->gro_receive(head, skb); - - skb->csum = csum; - -out_unlock: - rcu_read_unlock(); - -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int ipv6_gro_complete(struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct ipv6hdr *iph = ipv6_hdr(skb); - int err = -ENOSYS; - - iph->payload_len = htons(skb->len - skb_network_offset(skb) - - sizeof(*iph)); - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]); - if (WARN_ON(!ops || !ops->gro_complete)) - goto out_unlock; - - err = ops->gro_complete(skb); - -out_unlock: - rcu_read_unlock(); - - return err; -} - static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, - .gso_send_check = ipv6_gso_send_check, - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, }; static int __init ipv6_packet_init(void) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7e6139508ee7..ecc35b93314b 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -44,7 +44,7 @@ #define IPV6HDR_BASELEN 8 struct tmp_ext { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) struct in6_addr saddr; #endif struct in6_addr daddr; @@ -152,7 +152,7 @@ bad: return false; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) /** * ipv6_rearrange_destopt - rearrange IPv6 destination options header * @iph: IPv6 header @@ -320,7 +320,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err) memcpy(top_iph, iph_base, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(&top_iph->saddr, iph_ext, extlen); #else memcpy(&top_iph->daddr, iph_ext, extlen); @@ -385,7 +385,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(iph_base, top_iph, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(iph_ext, &top_iph->saddr, extlen); #else memcpy(iph_ext, &top_iph->daddr, extlen); @@ -434,7 +434,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph, iph_base, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(&top_iph->saddr, iph_ext, extlen); #else memcpy(&top_iph->daddr, iph_ext, extlen); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index cdf02be5f191..757a810d8f15 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -64,7 +64,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; @@ -84,7 +84,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } else if (ishost) { err = -EADDRNOTAVAIL; goto error; @@ -189,6 +189,9 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; + if (!np->ipv6_ac_list) + return; + write_lock_bh(&ipv6_sk_ac_lock); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index be2b67d631e5..8edf2601065a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -701,7 +701,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -721,7 +721,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -746,7 +746,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -769,7 +769,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); switch (rthdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index fa3d9c328092..473f628f9f20 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -43,56 +43,12 @@ #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/xfrm.h> #endif #include <asm/uaccess.h> -int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) -{ - const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; - struct ipv6_opt_hdr *hdr; - int len; - - if (offset + 2 > packet_len) - goto bad; - hdr = (struct ipv6_opt_hdr *)(nh + offset); - len = ((hdr->hdrlen + 1) << 3); - - if (offset + len > packet_len) - goto bad; - - offset += 2; - len -= 2; - - while (len > 0) { - int opttype = nh[offset]; - int optlen; - - if (opttype == type) - return offset; - - switch (opttype) { - case IPV6_TLV_PAD1: - optlen = 1; - break; - default: - optlen = nh[offset + 1] + 2; - if (optlen > len) - goto bad; - break; - } - offset += optlen; - len -= optlen; - } - /* not_found */ - bad: - return -1; -} -EXPORT_SYMBOL_GPL(ipv6_find_tlv); - /* * Parsing tlv encoded headers. * @@ -224,7 +180,7 @@ bad: Destination options header. *****************************/ -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; @@ -288,7 +244,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) #endif static const struct tlvtype_proc tlvprocdestopt_lst[] = { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) { .type = IPV6_TLV_HAO, .func = ipv6_dest_hao, @@ -300,7 +256,7 @@ static const struct tlvtype_proc tlvprocdestopt_lst[] = { static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); @@ -315,14 +271,14 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) } opt->lastopt = opt->dst1 = skb_network_header_len(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; #else opt->nhoff = opt->dst1; @@ -378,7 +334,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: /* Silently discard type 2 header unless it was * processed by own @@ -404,7 +360,7 @@ looped_back: } switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (accept_source_route < 0) goto unknown_rh; @@ -461,7 +417,7 @@ looped_back: addr += i - 1; switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, @@ -528,12 +484,12 @@ unknown_rh: static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { @@ -559,10 +515,10 @@ int __init ipv6_exthdrs_init(void) out: return ret; -out_rthdr: - inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); +out_rthdr: + inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index f73d59a14131..c5e83fae4df4 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -111,3 +111,171 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, return start; } EXPORT_SYMBOL(ipv6_skip_exthdr); + +int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) +{ + const unsigned char *nh = skb_network_header(skb); + int packet_len = skb->tail - skb->network_header; + struct ipv6_opt_hdr *hdr; + int len; + + if (offset + 2 > packet_len) + goto bad; + hdr = (struct ipv6_opt_hdr *)(nh + offset); + len = ((hdr->hdrlen + 1) << 3); + + if (offset + len > packet_len) + goto bad; + + offset += 2; + len -= 2; + + while (len > 0) { + int opttype = nh[offset]; + int optlen; + + if (opttype == type) + return offset; + + switch (opttype) { + case IPV6_TLV_PAD1: + optlen = 1; + break; + default: + optlen = nh[offset + 1] + 2; + if (optlen > len) + goto bad; + break; + } + offset += optlen; + len -= optlen; + } + /* not_found */ + bad: + return -1; +} +EXPORT_SYMBOL_GPL(ipv6_find_tlv); + +/* + * find the offset to specified header or the protocol number of last header + * if target < 0. "last header" is transport protocol header, ESP, or + * "No next header". + * + * Note that *offset is used as input/output parameter. an if it is not zero, + * then it must be a valid offset to an inner IPv6 header. This can be used + * to explore inner IPv6 header, eg. ICMPv6 error messages. + * + * If target header is found, its offset is set in *offset and return protocol + * number. Otherwise, return -1. + * + * If the first fragment doesn't contain the final protocol header or + * NEXTHDR_NONE it is considered invalid. + * + * Note that non-1st fragment is special case that "the protocol number + * of last header" is "next header" field in Fragment header. In this case, + * *offset is meaningless and fragment offset is stored in *fragoff if fragoff + * isn't NULL. + * + * if flags is not NULL and it's a fragment, then the frag flag + * IP6_FH_F_FRAG will be set. If it's an AH header, the + * IP6_FH_F_AUTH flag is set and target < 0, then this function will + * stop at the AH header. If IP6_FH_F_SKIP_RH flag was passed, then this + * function will skip all those routing headers, where segements_left was 0. + */ +int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, + int target, unsigned short *fragoff, int *flags) +{ + unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + unsigned int len; + bool found; + + if (fragoff) + *fragoff = 0; + + if (*offset) { + struct ipv6hdr _ip6, *ip6; + + ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); + if (!ip6 || (ip6->version != 6)) { + printk(KERN_ERR "IPv6 header not found\n"); + return -EBADMSG; + } + start = *offset + sizeof(struct ipv6hdr); + nexthdr = ip6->nexthdr; + } + len = skb->len - start; + + do { + struct ipv6_opt_hdr _hdr, *hp; + unsigned int hdrlen; + found = (nexthdr == target); + + if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { + if (target < 0) + break; + return -ENOENT; + } + + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); + if (hp == NULL) + return -EBADMSG; + + if (nexthdr == NEXTHDR_ROUTING) { + struct ipv6_rt_hdr _rh, *rh; + + rh = skb_header_pointer(skb, start, sizeof(_rh), + &_rh); + if (rh == NULL) + return -EBADMSG; + + if (flags && (*flags & IP6_FH_F_SKIP_RH) && + rh->segments_left == 0) + found = false; + } + + if (nexthdr == NEXTHDR_FRAGMENT) { + unsigned short _frag_off; + __be16 *fp; + + if (flags) /* Indicate that this is a fragment */ + *flags |= IP6_FH_F_FRAG; + fp = skb_header_pointer(skb, + start+offsetof(struct frag_hdr, + frag_off), + sizeof(_frag_off), + &_frag_off); + if (fp == NULL) + return -EBADMSG; + + _frag_off = ntohs(*fp) & ~0x7; + if (_frag_off) { + if (target < 0 && + ((!ipv6_ext_hdr(hp->nexthdr)) || + hp->nexthdr == NEXTHDR_NONE)) { + if (fragoff) + *fragoff = _frag_off; + return hp->nexthdr; + } + return -ENOENT; + } + hdrlen = 8; + } else if (nexthdr == NEXTHDR_AUTH) { + if (flags && (*flags & IP6_FH_F_AUTH) && (target < 0)) + break; + hdrlen = (hp->hdrlen + 2) << 2; + } else + hdrlen = ipv6_optlen(hp); + + if (!found) { + nexthdr = hp->nexthdr; + len -= hdrlen; + start += hdrlen; + } + } while (!found); + + *offset = start; + return nexthdr; +} +EXPORT_SYMBOL(ipv6_find_hdr); + diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c new file mode 100644 index 000000000000..cf77f3abfd06 --- /dev/null +++ b/net/ipv6/exthdrs_offload.c @@ -0,0 +1,41 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * IPV6 Extension Header GSO/GRO support + */ +#include <net/protocol.h> +#include "ip6_offload.h" + +static const struct net_offload rthdr_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +static const struct net_offload dstopt_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +int __init ipv6_exthdrs_offload_init(void) +{ + int ret; + + ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); + if (!ret) + goto out; + + ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); + if (!ret) + goto out_rt; + +out: + return ret; + +out_rt: + inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + goto out; +} diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index d9fb9110f607..2e1a432867c0 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -100,7 +100,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } again: - dst_release(&rt->dst); + ip6_rt_put(rt); rt = NULL; goto out; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 24d69dbca4d6..b4a9fd51dae7 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -280,7 +280,7 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st return 0; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) static void mip6_addr_swap(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 73f1a00a96af..dea17fd28e50 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -87,11 +87,13 @@ struct sock *__inet6_lookup_established(struct net *net, rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { - /* For IPV6 do the cheaper port and family tests first. */ - if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto begintw; - if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, + ports, dif))) { sock_put(sk); goto begin; } @@ -104,12 +106,16 @@ begin: begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ sk_nulls_for_each_rcu(sk, node, &head->twchain) { - if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET6_TW_MATCH(sk, net, saddr, daddr, + ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { sk = NULL; goto out; } - if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, + ports, dif))) { sock_put(sk); goto begintw; } @@ -236,9 +242,12 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, /* Check TIME-WAIT sockets first. */ sk_nulls_for_each(sk2, node, &head->twchain) { - tw = inet_twsk(sk2); + if (sk2->sk_hash != hash) + continue; - if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) { + if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr, + ports, dif))) { + tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) goto unique; else @@ -249,7 +258,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, /* And established part... */ sk_nulls_for_each(sk2, node, &head->chain) { - if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) + if (sk2->sk_hash != hash) + continue; + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) goto not_unique; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 24995a93ef8c..710cafd2e1a9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -672,6 +672,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, iter->rt6i_idev == rt->rt6i_idev && ipv6_addr_equal(&iter->rt6i_gateway, &rt->rt6i_gateway)) { + if (rt->rt6i_nsiblings) + rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->rt6i_flags & RTF_EXPIRES)) @@ -680,6 +682,21 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt->rt6i_flags & RTF_GATEWAY && + !(rt->rt6i_flags & RTF_EXPIRES) && + !(iter->rt6i_flags & RTF_EXPIRES)) + rt->rt6i_nsiblings++; } if (iter->rt6i_metric > rt->rt6i_metric) @@ -692,6 +709,35 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (ins == &fn->leaf) fn->rr_ptr = NULL; + /* Link this route to others same route. */ + if (rt->rt6i_nsiblings) { + unsigned int rt6i_nsiblings; + struct rt6_info *sibling, *temp_sibling; + + /* Find the first route that have the same metric */ + sibling = fn->leaf; + while (sibling) { + if (sibling->rt6i_metric == rt->rt6i_metric) { + list_add_tail(&rt->rt6i_siblings, + &sibling->rt6i_siblings); + break; + } + sibling = sibling->dst.rt6_next; + } + /* For each sibling in the list, increment the counter of + * siblings. BUG() if counters does not match, list of siblings + * is broken! + */ + rt6i_nsiblings = 0; + list_for_each_entry_safe(sibling, temp_sibling, + &rt->rt6i_siblings, rt6i_siblings) { + sibling->rt6i_nsiblings++; + BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); + rt6i_nsiblings++; + } + BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); + } + /* * insert node */ @@ -1193,6 +1239,17 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (fn->rr_ptr == rt) fn->rr_ptr = NULL; + /* Remove this entry from other siblings */ + if (rt->rt6i_nsiblings) { + struct rt6_info *sibling, *next_sibling; + + list_for_each_entry_safe(sibling, next_sibling, + &rt->rt6i_siblings, rt6i_siblings) + sibling->rt6i_nsiblings--; + rt->rt6i_nsiblings = 0; + list_del_init(&rt->rt6i_siblings); + } + /* Adjust walkers */ read_lock(&fib6_walker_lock); FOR_WALKERS(w) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 90bbefb57943..29124b7a04c8 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -519,7 +519,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } read_unlock_bh(&ip6_sk_fl_lock); - if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) { + if (freq.flr_share == IPV6_FL_S_NONE && + ns_capable(net->user_ns, CAP_NET_ADMIN)) { fl = fl_lookup(net, freq.flr_label); if (fl) { err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d5cb3c4e66f8..867466c96aac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -109,21 +109,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr) #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#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 { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -181,7 +166,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; - for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || @@ -206,7 +191,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) @@ -230,7 +215,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { if ((!ipv6_addr_equal(local, &t->parms.laddr) && (!ipv6_addr_equal(local, &t->parms.raddr) || !ipv6_addr_is_multicast(local))) || @@ -256,7 +241,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -1069,7 +1054,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) dev->mtu = IPV6_MIN_MTU; } } - dst_release(&rt->dst); + ip6_rt_put(rt); } t->hlen = addend; @@ -1161,7 +1146,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1209,7 +1194,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ign->fb_tunnel_dev) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c new file mode 100644 index 000000000000..f26f0da7f095 --- /dev/null +++ b/net/ipv6/ip6_offload.c @@ -0,0 +1,282 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/socket.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/printk.h> + +#include <net/protocol.h> +#include <net/ipv6.h> + +#include "ip6_offload.h" + +static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) +{ + const struct net_offload *ops = NULL; + + for (;;) { + struct ipv6_opt_hdr *opth; + int len; + + if (proto != NEXTHDR_HOP) { + ops = rcu_dereference(inet6_offloads[proto]); + + if (unlikely(!ops)) + break; + + if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + + if (unlikely(!pskb_may_pull(skb, 8))) + break; + + opth = (void *)skb->data; + len = ipv6_optlen(opth); + + if (unlikely(!pskb_may_pull(skb, len))) + break; + + proto = opth->nexthdr; + __skb_pull(skb, len); + } + + return proto; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + 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; + + rcu_read_lock(); + 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); + } + rcu_read_unlock(); + +out: + return err; +} + +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + + if (!(features & NETIF_F_V6_CSUM)) + features &= ~NETIF_F_SG; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_TCPV6 | + 0))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + segs = ERR_PTR(-EPROTONOSUPPORT); + + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) { + skb_reset_transport_header(skb); + segs = ops->callbacks.gso_segment(skb, features); + } + rcu_read_unlock(); + + if (IS_ERR(segs)) + goto out; + + for (skb = segs; skb; skb = skb->next) { + ipv6h = ipv6_hdr(skb); + ipv6h->payload_len = htons(skb->len - skb->mac_len - + sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } + } + +out: + return segs; +} + +static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct net_offload *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct ipv6hdr *iph; + unsigned int nlen; + unsigned int hlen; + unsigned int off; + int flush = 1; + int proto; + __wsum csum; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } + + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + + flush += ntohs(iph->payload_len) != skb_gro_len(skb); + + rcu_read_lock(); + proto = iph->nexthdr; + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) { + __pskb_pull(skb, skb_gro_offset(skb)); + proto = ipv6_gso_pull_exthdrs(skb, proto); + skb_gro_pull(skb, -skb_transport_offset(skb)); + skb_reset_transport_header(skb); + __skb_push(skb, skb_gro_offset(skb)); + + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) + goto out_unlock; + + iph = ipv6_hdr(skb); + } + + NAPI_GRO_CB(skb)->proto = proto; + + flush--; + nlen = skb_network_header_len(skb); + + for (p = *head; p; p = p->next) { + const struct ipv6hdr *iph2; + __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = ipv6_hdr(p); + first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; + + /* All fields must match except length and Traffic Class. */ + if (nlen != skb_network_header_len(p) || + (first_word & htonl(0xF00FFFFF)) || + memcmp(&iph->nexthdr, &iph2->nexthdr, + nlen - offsetof(struct ipv6hdr, nexthdr))) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + /* flush if Traffic Class fields are different */ + NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + + csum = skb->csum; + skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + + pp = ops->callbacks.gro_receive(head, skb); + + skb->csum = csum; + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int ipv6_gro_complete(struct sk_buff *skb) +{ + const struct net_offload *ops; + struct ipv6hdr *iph = ipv6_hdr(skb); + int err = -ENOSYS; + + iph->payload_len = htons(skb->len - skb_network_offset(skb) - + sizeof(*iph)); + + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + goto out_unlock; + + err = ops->callbacks.gro_complete(skb); + +out_unlock: + rcu_read_unlock(); + + return err; +} + +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, + }, +}; + +static int __init ipv6_offload_init(void) +{ + + if (tcpv6_offload_init() < 0) + pr_crit("%s: Cannot add TCP protocol offload\n", __func__); + if (udp_offload_init() < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (ipv6_exthdrs_offload_init() < 0) + pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); + + dev_add_offload(&ipv6_packet_offload); + return 0; +} + +fs_initcall(ipv6_offload_init); diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h new file mode 100644 index 000000000000..2e155c651b35 --- /dev/null +++ b/net/ipv6/ip6_offload.h @@ -0,0 +1,18 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef __ip6_offload_h +#define __ip6_offload_h + +int ipv6_exthdrs_offload_init(void); +int udp_offload_init(void); +int tcpv6_offload_init(void); + +#endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index aece3e792f84..5552d13ae92f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -538,78 +538,12 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) to->nf_trace = from->nf_trace; #endif skb_copy_secmark(to, from); } -int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; - int found_rhdr = 0; - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - found_rhdr = 1; - break; - case NEXTHDR_DEST: -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) - break; -#endif - if (found_rhdr) - return offset; - break; - default : - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + - offset); - } - - return offset; -} - -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - int old, new; - - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); -} - int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -756,7 +690,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); - dst_release(&rt->dst); + ip6_rt_put(rt); return 0; } @@ -768,7 +702,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); - dst_release(&rt->dst); + ip6_rt_put(rt); return err; slow_path_clean: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cb7e2ded6f08..a14f28b280f5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,6 +74,10 @@ MODULE_ALIAS_NETDEV("ip6tnl0"); #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); @@ -83,6 +87,7 @@ static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); +static struct rtnl_link_ops ip6_link_ops __read_mostly; static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { @@ -94,14 +99,6 @@ struct ip6_tnl_net { 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; -} __attribute__((aligned(4*sizeof(unsigned long)))); - static struct net_device_stats *ip6_get_stats(struct net_device *dev) { struct pcpu_tstats sum = { 0 }; @@ -258,6 +255,33 @@ static void ip6_dev_free(struct net_device *dev) free_netdev(dev); } +static int ip6_tnl_create2(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; + + t = netdev_priv(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ip6_link_ops; + + dev_hold(dev); + ip6_tnl_link(ip6n, t); + return 0; + +out: + return err; +} + /** * ip6_tnl_create - create a new tunnel * @p: tunnel parameters @@ -276,7 +300,6 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct ip6_tnl *t; char name[IFNAMSIZ]; int err; - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -291,17 +314,10 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; - err = ip6_tnl_dev_init(dev); + err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; - if ((err = register_netdevice(dev)) < 0) - goto failed_free; - - strcpy(t->parms.name, dev->name); - - dev_hold(dev); - ip6_tnl_link(ip6n, t); return t; failed_free: @@ -663,8 +679,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_send(skb2, rel_type, rel_code, rel_info); - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); kfree_skb(skb2); } @@ -672,28 +687,26 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } -static void ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); - if (INET_ECN_is_ce(dsfield)) - IP_ECN_set_ce(ip_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } -static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); - if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h))) - IP6_ECN_set_ce(ipv6_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, @@ -757,12 +770,13 @@ EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, __u8 ipproto, - void (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb)) + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int err; rcu_read_lock(); @@ -792,14 +806,26 @@ 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); + + err = dscp_ecn_decapsulate(t, ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++t->dev->stats.rx_frame_errors; + ++t->dev->stats.rx_errors; + rcu_read_unlock(); + goto discard; + } + } + 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(); @@ -1208,7 +1234,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - dst_release(&rt->dst); + ip6_rt_put(rt); } } @@ -1237,6 +1263,20 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) return 0; } +static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = dev_net(t->dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + ip6_tnl_unlink(ip6n, t); + synchronize_net(); + err = ip6_tnl_change(t, p); + ip6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { @@ -1325,7 +1365,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) @@ -1345,11 +1385,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else t = netdev_priv(dev); - ip6_tnl_unlink(ip6n, t); - synchronize_net(); - err = ip6_tnl_change(t, &p1); - ip6_tnl_link(ip6n, t); - netdev_state_change(dev); + err = ip6_tnl_update(t, &p1); } if (t) { err = 0; @@ -1362,7 +1398,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { @@ -1505,6 +1541,164 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + +static void ip6_tnl_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); + + if (data[IFLA_IPTUN_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); + + if (data[IFLA_IPTUN_FLOWINFO]) + parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); + + if (data[IFLA_IPTUN_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); +} + +static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + ip6_tnl_netlink_parms(data, &nt->parms); + + if (ip6_tnl_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ip6_tnl_create2(dev); +} + +static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t; + struct __ip6_tnl_parm p; + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + ip6_tnl_netlink_parms(data, &p); + + t = ip6_tnl_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return ip6_tnl_update(t, &p); +} + +static size_t ip6_tnl_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_IPTUN_FLOWINFO */ + nla_total_size(4) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(4) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + 0; +} + +static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), + &parm->raddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->laddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || + nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || + nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || + nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ip6_link_ops __read_mostly = { + .kind = "ip6tnl", + .maxtype = IFLA_IPTUN_MAX, + .policy = ip6_tnl_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6_tnl_dev_setup, + .validate = ip6_tnl_validate, + .newlink = ip6_tnl_newlink, + .changelink = ip6_tnl_changelink, + .get_size = ip6_tnl_get_size, + .fill_info = ip6_tnl_fill_info, +}; + static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, @@ -1613,9 +1807,14 @@ static int __init ip6_tunnel_init(void) pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } + err = rtnl_link_register(&ip6_link_ops); + if (err < 0) + goto rtnl_link_failed; return 0; +rtnl_link_failed: + xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: @@ -1630,6 +1829,7 @@ out_pernet: static void __exit ip6_tunnel_cleanup(void) { + rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f7c7c6319720..26dcdec9e3a5 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -52,6 +52,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/export.h> #include <net/ip6_checksum.h> +#include <linux/netconf.h> struct mr6_table { struct list_head list; @@ -66,8 +67,8 @@ struct mr6_table { struct mif_device vif6_table[MAXMIFS]; int maxvif; atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; + bool mroute_do_assert; + bool mroute_do_pim; #ifdef CONFIG_IPV6_PIMSM_V2 int mroute_reg_vif_num; #endif @@ -115,6 +116,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr6_table *mrt); @@ -805,8 +808,12 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev_set_allmulti(dev, -1); in6_dev = __in6_dev_get(dev); - if (in6_dev) + if (in6_dev) { in6_dev->cnf.mc_forwarding--; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } if (v->flags & MIFF_REGISTER) unregister_netdevice_queue(dev, head); @@ -865,6 +872,7 @@ static void ipmr_do_expire_process(struct mr6_table *mrt) } list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, c); } @@ -958,8 +966,12 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, } in6_dev = __in6_dev_get(dev); - if (in6_dev) + if (in6_dev) { in6_dev->cnf.mc_forwarding++; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } /* * Fill in the VIF structures @@ -1211,6 +1223,7 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->list, &mrt->mfc6_unres_queue); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } @@ -1248,6 +1261,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) list_del(&c->list); write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_cache_free(c); return 0; } @@ -1412,6 +1426,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1456,6 +1471,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } + mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1489,6 +1505,7 @@ static void mroute_clean_tables(struct mr6_table *mrt) list_del(&c->list); write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_cache_free(c); } } @@ -1497,6 +1514,7 @@ static void mroute_clean_tables(struct mr6_table *mrt) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); @@ -1513,6 +1531,9 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) if (likely(mrt->mroute6_sk == NULL)) { mrt->mroute6_sk = sk; net->ipv6.devconf_all->mc_forwarding++; + inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); } else err = -EADDRINUSE; @@ -1535,6 +1556,10 @@ int ip6mr_sk_done(struct sock *sk) write_lock_bh(&mrt_lock); mrt->mroute6_sk = NULL; net->ipv6.devconf_all->mc_forwarding--; + inet6_netconf_notify_devconf(net, + NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); write_unlock_bh(&mrt_lock); mroute_clean_tables(mrt); @@ -1583,7 +1608,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -ENOENT; if (optname != MRT6_INIT) { - if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } @@ -1646,9 +1671,12 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ASSERT: { int v; + + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - mrt->mroute_do_assert = !!v; + mrt->mroute_do_assert = v; return 0; } @@ -1656,6 +1684,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_PIM: { int v; + + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; v = !!v; @@ -2097,8 +2128,8 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, { int ct; struct rtnexthop *nhp; - u8 *b = skb_tail_pointer(skb); - struct rtattr *mp_head; + struct nlattr *mp_attr; + struct rta_mfc_stats mfcs; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mf6c_parent >= MAXMIFS) @@ -2107,28 +2138,35 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (MIF_EXISTS(mrt, c->mf6c_parent) && nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) return -EMSGSIZE; - - mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); + mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + if (mp_attr == NULL) + return -EMSGSIZE; for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); + if (nhp == NULL) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head; + + nla_nest_end(skb, mp_attr); + + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0) + return -EMSGSIZE; + rtm->rtm_type = RTN_MULTICAST; return 1; - -rtattr_failure: - nlmsg_trim(skb, b); - return -EMSGSIZE; } int ip6mr_get_route(struct net *net, @@ -2202,31 +2240,38 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd) { struct nlmsghdr *nlh; struct rtmsg *rtm; + int err; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); - rtm->rtm_family = RTNL_FAMILY_IPMR; + rtm->rtm_family = RTNL_FAMILY_IP6MR; rtm->rtm_dst_len = 128; rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; + rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = RTPROT_UNSPEC; + if (c->mfc_flags & MFC_STATIC) + rtm->rtm_protocol = RTPROT_STATIC; + else + rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) || nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp)) goto nla_put_failure; - if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0) + err = __ip6mr_fill_mroute(mrt, skb, c, rtm); + /* do not break the dump if cache is unresolved */ + if (err < 0 && err != -ENOENT) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2236,6 +2281,52 @@ nla_put_failure: return -EMSGSIZE; } +static int mr6_msgsize(bool unresolved, int maxvif) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ + ; + + if (!unresolved) + len = len + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(0) /* RTA_MULTIPATH */ + + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) + /* RTA_MFC_STATS */ + + nla_total_size(sizeof(struct rta_mfc_stats)) + ; + + return len; +} + +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), + GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + if (err < 0) + goto errout; + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); + return; + +errout: + kfree_skb(skb); + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); +} + static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2262,13 +2353,29 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc) < 0) + mfc, RTM_NEWROUTE) < 0) goto done; next_entry: e++; } e = s_e = 0; } + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE) < 0) { + spin_unlock_bh(&mfc_unres_lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(&mfc_unres_lock); + e = s_e = 0; s_h = 0; next_table: t++; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index e02faed6d17e..ee94d31c9d4d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -343,7 +343,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) { + if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { retv = -EPERM; break; } @@ -381,7 +382,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, /* hop-by-hop / destination options are privileged option */ retv = -EPERM; - if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; opt = ipv6_renew_options(sk, np->opt, optname, @@ -397,7 +398,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_RTHDR && opt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; switch (rthdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) @@ -754,7 +755,7 @@ done: case IPV6_IPSEC_POLICY: case IPV6_XFRM_POLICY: retv = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; retv = xfrm_user_policy(sk, optname, optval, optlen); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 92f8e48e4ba4..28dfa5f3801f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -163,7 +163,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } } else dev = dev_get_by_index_rcu(net, ifindex); @@ -260,7 +260,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } } else dev = dev_get_by_index_rcu(net, ifindex); @@ -284,6 +284,9 @@ void ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(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) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2edce30ef733..f2a007b7bde3 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -151,8 +151,8 @@ static inline int ndisc_opt_addr_space(struct net_device *dev) static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, unsigned short addr_type) { - int space = NDISC_OPT_SPACE(data_len); int pad = ndisc_addr_option_pad(addr_type); + int space = NDISC_OPT_SPACE(data_len + pad); opt[0] = type; opt[1] = space>>3; @@ -370,12 +370,12 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -struct sk_buff *ndisc_build_skb(struct net_device *dev, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, - const struct in6_addr *target, - int llinfo) +static struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; @@ -431,14 +431,11 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, return skb; } -EXPORT_SYMBOL(ndisc_build_skb); - -void ndisc_send_skb(struct sk_buff *skb, - struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h) +static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) { struct flowi6 fl6; struct dst_entry *dst; @@ -473,8 +470,6 @@ void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } -EXPORT_SYMBOL(ndisc_send_skb); - /* * Send a Neighbour Discover packet */ @@ -535,7 +530,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr = IN6ADDR_LINKLOCAL_ALLNODES_INIT; idev = in6_dev_get(dev); if (!idev) @@ -543,7 +537,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, + ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -905,7 +899,7 @@ static void ndisc_recv_na(struct sk_buff *skb) if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { - /* XXX: idev->cnf.prixy_ndp */ + /* XXX: idev->cnf.proxy_ndp */ goto out; } @@ -1033,18 +1027,6 @@ 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); @@ -1092,7 +1074,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - if (!accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) goto skip_linkparms; #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1144,7 +1126,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - dst_release(&rt->dst); + ip6_rt_put(rt); return; } } @@ -1169,7 +1151,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - dst_release(&rt->dst); + ip6_rt_put(rt); return; } neigh->flags |= NTF_ROUTER; @@ -1248,7 +1230,7 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } - if (!accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) goto out; #ifdef CONFIG_IPV6_ROUTE_INFO @@ -1325,8 +1307,7 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); if (neigh) neigh_release(neigh); } @@ -1574,11 +1555,18 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(~0UL, net); + idev = in6_dev_get(dev); + if (!idev) + break; + if (idev->cnf.ndisc_notify) + ndisc_send_unsol_na(dev); + in6_dev_put(idev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d7cb04506c3d..125a90d6a795 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -207,8 +207,7 @@ ip6t_get_target_c(const struct ip6t_entry *e) return ip6t_get_target((struct ip6t_entry *)e); } -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", @@ -381,8 +380,7 @@ ip6t_do_table(struct sk_buff *skb, t = ip6t_get_target_c(e); IP_NF_ASSERT(t->u.kernel.target); -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(skb, hook, in, out, @@ -1856,7 +1854,7 @@ compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1971,7 +1969,7 @@ compat_do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1993,7 +1991,7 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2018,7 +2016,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2273,112 +2271,9 @@ static void __exit ip6_tables_fini(void) unregister_pernet_subsys(&ip6_tables_net_ops); } -/* - * find the offset to specified header or the protocol number of last header - * if target < 0. "last header" is transport protocol header, ESP, or - * "No next header". - * - * Note that *offset is used as input/output parameter. an if it is not zero, - * then it must be a valid offset to an inner IPv6 header. This can be used - * to explore inner IPv6 header, eg. ICMPv6 error messages. - * - * If target header is found, its offset is set in *offset and return protocol - * number. Otherwise, return -1. - * - * If the first fragment doesn't contain the final protocol header or - * NEXTHDR_NONE it is considered invalid. - * - * Note that non-1st fragment is special case that "the protocol number - * of last header" is "next header" field in Fragment header. In this case, - * *offset is meaningless and fragment offset is stored in *fragoff if fragoff - * isn't NULL. - * - * if flags is not NULL and it's a fragment, then the frag flag IP6T_FH_F_FRAG - * will be set. If it's an AH header, the IP6T_FH_F_AUTH flag is set and - * target < 0, then this function will stop at the AH header. - */ -int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, - int target, unsigned short *fragoff, int *flags) -{ - unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len; - - if (fragoff) - *fragoff = 0; - - if (*offset) { - struct ipv6hdr _ip6, *ip6; - - ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); - if (!ip6 || (ip6->version != 6)) { - printk(KERN_ERR "IPv6 header not found\n"); - return -EBADMSG; - } - start = *offset + sizeof(struct ipv6hdr); - nexthdr = ip6->nexthdr; - } - len = skb->len - start; - - while (nexthdr != target) { - struct ipv6_opt_hdr _hdr, *hp; - unsigned int hdrlen; - - if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) - break; - return -ENOENT; - } - - hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); - if (hp == NULL) - return -EBADMSG; - if (nexthdr == NEXTHDR_FRAGMENT) { - unsigned short _frag_off; - __be16 *fp; - - if (flags) /* Indicate that this is a fragment */ - *flags |= IP6T_FH_F_FRAG; - fp = skb_header_pointer(skb, - start+offsetof(struct frag_hdr, - frag_off), - sizeof(_frag_off), - &_frag_off); - if (fp == NULL) - return -EBADMSG; - - _frag_off = ntohs(*fp) & ~0x7; - if (_frag_off) { - if (target < 0 && - ((!ipv6_ext_hdr(hp->nexthdr)) || - hp->nexthdr == NEXTHDR_NONE)) { - if (fragoff) - *fragoff = _frag_off; - return hp->nexthdr; - } - return -ENOENT; - } - hdrlen = 8; - } else if (nexthdr == NEXTHDR_AUTH) { - if (flags && (*flags & IP6T_FH_F_AUTH) && (target < 0)) - break; - hdrlen = (hp->hdrlen + 2) << 2; - } else - hdrlen = ipv6_optlen(hp); - - nexthdr = hp->nexthdr; - len -= hdrlen; - start += hdrlen; - } - - *offset = start; - return nexthdr; -} - EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ipv6_find_hdr); module_init(ip6_tables_init); module_exit(ip6_tables_fini); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 5d1d8b04d694..5060d54199ab 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -67,7 +67,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) ret = true; out: - dst_release(&rt->dst); + ip6_rt_put(rt); return ret; } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index d57dab17a182..6c8ae24b85eb 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -137,6 +137,10 @@ nf_nat_ipv6_fn(unsigned int hooknum, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) { + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; + } } return nf_nat_packet(ct, ctinfo, hooknum, skb); @@ -277,9 +281,7 @@ static int __net_init ip6table_nat_net_init(struct net *net) return -ENOMEM; net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_nat)) - return PTR_ERR(net->ipv6.ip6table_nat); - return 0; + return PTR_RET(net->ipv6.ip6table_nat); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 8860d23e61cf..00ee17c3e893 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -21,6 +21,7 @@ #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -295,7 +296,56 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { }, }; -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + struct nf_conn *ct; + + tuple.src.u3.in6 = inet6->rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = inet6->daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + + if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int) *len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + + if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) + sin6.sin6_scope_id = sk->sk_bound_dev_if; + else + sin6.sin6_scope_id = 0; + + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -346,7 +396,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .invert_tuple = ipv6_invert_tuple, .print_tuple = ipv6_print_tuple, .get_l4proto = ipv6_get_l4proto, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = ipv6_tuple_to_nlattr, .nlattr_tuple_size = ipv6_nlattr_tuple_size, .nlattr_to_tuple = ipv6_nlattr_to_tuple, @@ -359,6 +409,14 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + static int ipv6_net_init(struct net *net) { int ret = 0; @@ -425,6 +483,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) need_conntrack(); nf_defrag_ipv6_enable(); + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) { + pr_err("Unable to register netfilter socket option\n"); + return ret; + } + ret = register_pernet_subsys(&ipv6_net_ops); if (ret < 0) goto cleanup_pernet; @@ -440,6 +504,7 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) cleanup_ipv6: unregister_pernet_subsys(&ipv6_net_ops); cleanup_pernet: + nf_unregister_sockopt(&so_getorigdst6); return ret; } @@ -448,6 +513,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) synchronize_net(); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); unregister_pernet_subsys(&ipv6_net_ops); + nf_unregister_sockopt(&so_getorigdst6); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 2d54b2061d68..24df3dde0076 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -232,7 +232,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum); } -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -375,7 +375,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .get_timeouts = icmpv6_get_timeouts, .new = icmpv6_new, .error = icmpv6_error, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, .nlattr_to_tuple = icmpv6_nlattr_to_tuple, diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index cdd6d045e42e..aacd121fe8c5 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -19,7 +19,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -35,7 +35,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, { u16 zone = NF_CT_DEFAULT_ZONE; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); #endif @@ -60,7 +60,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, { struct sk_buff *reasm; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 5d6da784305b..61aaf70f376e 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -84,7 +84,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = { .manip_pkt = icmpv6_manip_pkt, .in_range = icmpv6_in_range, .unique_tuple = icmpv6_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c new file mode 100644 index 000000000000..c2e73e647e44 --- /dev/null +++ b/net/ipv6/output_core.c @@ -0,0 +1,76 @@ +/* + * IPv6 library code, needed by static components when full IPv6 support is + * not configured or static. These functions are needed by GSO/GRO implementation. + */ +#include <linux/export.h> +#include <net/ipv6.h> +#include <net/ip6_fib.h> + +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static atomic_t ipv6_fragmentation_id; + int old, new; + +#if IS_ENABLED(CONFIG_IPV6) + if (rt && !(rt->dst.flags & DST_NOPEER)) { + struct inet_peer *peer; + struct net *net; + + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + if (peer) { + fhdr->identification = htonl(inet_getid(peer, 0)); + inet_putpeer(peer); + return; + } + } +#endif + do { + old = atomic_read(&ipv6_fragmentation_id); + new = old + 1; + if (!new) + new = 1; + } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); + fhdr->identification = htonl(new); +} +EXPORT_SYMBOL(ipv6_select_ident); + +int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb->tail - skb->network_header; + int found_rhdr = 0; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: +#if IS_ENABLED(CONFIG_IPV6_MIP6) + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + break; +#endif + if (found_rhdr) + return offset; + break; + default : + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + } + + return offset; +} +EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 053082dfc93e..22d1bd4670da 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -25,7 +25,9 @@ #include <linux/spinlock.h> #include <net/protocol.h> +#if IS_ENABLED(CONFIG_IPV6) const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet6_protos); int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { @@ -50,3 +52,26 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol return ret; } EXPORT_SYMBOL(inet6_del_protocol); +#endif + +const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly; + +int inet6_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet6_add_offload); + +int inet6_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet6_del_offload); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d8e95c77db99..6cd29b1e8b92 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -50,7 +50,7 @@ #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> @@ -123,7 +123,7 @@ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) return 1; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; @@ -184,7 +184,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) filtered = icmpv6_filter(sk, skb); break; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index da8a4e301b1b..e5253ec9e0fc 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -616,6 +616,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[0].data = &net->ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; table[2].data = &net->ipv6.frags.timeout; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } hdr = register_net_sysctl(net, "net/ipv6", table); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b1e6cf0b95fd..e229a3bc345d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -57,6 +57,7 @@ #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> +#include <net/nexthop.h> #include <asm/uaccess.h> @@ -289,6 +290,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); rt->rt6i_genid = rt_genid(net); + INIT_LIST_HEAD(&rt->rt6i_siblings); + rt->rt6i_nsiblings = 0; } return rt; } @@ -318,13 +321,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } -static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); - -static u32 rt6_peer_genid(void) -{ - return atomic_read(&__rt6_peer_genid); -} - void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer_base *base; @@ -338,8 +334,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create) if (peer) { if (!rt6_set_peer(rt, peer)) inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); } } @@ -385,6 +379,69 @@ static bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +/* Multipath route selection: + * Hash based function using packet header and flowlabel. + * Adapted from fib_info_hashfn() + */ +static int rt6_info_hash_nhsfn(unsigned int candidate_count, + const struct flowi6 *fl6) +{ + unsigned int val = fl6->flowi6_proto; + + val ^= (__force u32)fl6->daddr.s6_addr32[0]; + val ^= (__force u32)fl6->daddr.s6_addr32[1]; + val ^= (__force u32)fl6->daddr.s6_addr32[2]; + val ^= (__force u32)fl6->daddr.s6_addr32[3]; + + val ^= (__force u32)fl6->saddr.s6_addr32[0]; + val ^= (__force u32)fl6->saddr.s6_addr32[1]; + val ^= (__force u32)fl6->saddr.s6_addr32[2]; + val ^= (__force u32)fl6->saddr.s6_addr32[3]; + + /* Work only if this not encapsulated */ + switch (fl6->flowi6_proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_SCTP: + val ^= (__force u16)fl6->fl6_sport; + val ^= (__force u16)fl6->fl6_dport; + break; + + case IPPROTO_ICMPV6: + val ^= (__force u16)fl6->fl6_icmp_type; + val ^= (__force u16)fl6->fl6_icmp_code; + break; + } + /* RFC6438 recommands to use flowlabel */ + val ^= (__force u32)fl6->flowlabel; + + /* Perhaps, we need to tune, this function? */ + val = val ^ (val >> 7) ^ (val >> 12); + return val % candidate_count; +} + +static struct rt6_info *rt6_multipath_select(struct rt6_info *match, + struct flowi6 *fl6) +{ + struct rt6_info *sibling, *next_sibling; + int route_choosen; + + route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6); + /* Don't change the route, if route_choosen == 0 + * (siblings does not include ourself) + */ + if (route_choosen) + list_for_each_entry_safe(sibling, next_sibling, + &match->rt6i_siblings, rt6i_siblings) { + route_choosen--; + if (route_choosen == 0) { + match = sibling; + break; + } + } + return match; +} + /* * Route lookup. Any table->tb6_lock is implied. */ @@ -487,35 +544,32 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline int rt6_check_neigh(struct rt6_info *rt) +static inline bool rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - int m; + bool ret = false; neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - m = 1; + ret = true; else if (neigh) { read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) - m = 2; + ret = true; #ifdef CONFIG_IPV6_ROUTER_PREF - else if (neigh->nud_state & NUD_FAILED) - m = 0; + else if (!(neigh->nud_state & NUD_FAILED)) + ret = true; #endif - else - m = 1; read_unlock_bh(&neigh->lock); - } else - m = 0; - return m; + } + return ret; } static int rt6_score_route(struct rt6_info *rt, int oif, int strict) { - int m, n; + int m; m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) @@ -523,8 +577,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - n = rt6_check_neigh(rt); - if (!n && (strict & RT6_LOOKUP_F_REACHABLE)) + if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE)) return -1; return m; } @@ -666,7 +719,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, else rt6_set_expires(rt, jiffies + HZ * lifetime); - dst_release(&rt->dst); + ip6_rt_put(rt); } return 0; } @@ -702,6 +755,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, restart: rt = fn->leaf; rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6); BACKTRACK(net, &fl6->saddr); out: dst_use(&rt->dst, jiffies); @@ -863,7 +918,8 @@ restart_2: restart: rt = rt6_select(fn, oif, strict | reachable); - + if (rt->rt6i_nsiblings && oif == 0) + rt = rt6_multipath_select(rt, fl6); BACKTRACK(net, &fl6->saddr); if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) @@ -879,7 +935,7 @@ restart: else goto out2; - dst_release(&rt->dst); + ip6_rt_put(rt); rt = nrt ? : net->ipv6.ip6_null_entry; dst_hold(&rt->dst); @@ -896,7 +952,7 @@ restart: * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ - dst_release(&rt->dst); + ip6_rt_put(rt); goto relookup; out: @@ -1030,14 +1086,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { - if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt6_has_peer(rt)) - rt6_bind_peer(rt, 0); - rt->rt6i_peer_genid = rt6_peer_genid(); - } + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) return dst; - } + return NULL; } @@ -1316,12 +1367,6 @@ out: return entries > rt_max_size; } -/* Clean host part of a prefix. Not necessary in radix tree, - but results in cleaner routing tables. - - Remove it only when all the things will work! - */ - int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); @@ -1507,7 +1552,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; if (dev) { if (dev != grt->dst.dev) { - dst_release(&grt->dst); + ip6_rt_put(grt); goto out; } } else { @@ -1518,7 +1563,7 @@ int ip6_route_add(struct fib6_config *cfg) } if (!(grt->rt6i_flags & RTF_GATEWAY)) err = 0; - dst_release(&grt->dst); + ip6_rt_put(grt); if (err) goto out; @@ -1604,7 +1649,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) write_unlock_bh(&table->tb6_lock); out: - dst_release(&rt->dst); + ip6_rt_put(rt); return err; } @@ -1987,7 +2032,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch(cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = copy_from_user(&rtmsg, arg, sizeof(struct in6_rtmsg)); @@ -2249,6 +2294,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2326,11 +2372,71 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + if (tb[RTA_MULTIPATH]) { + cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); + cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + } + err = 0; errout: return err; } +static int ip6_route_multipath(struct fib6_config *cfg, int add) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 0, last_err = 0; + +beginning: + rtnh = (struct rtnexthop *)cfg->fc_mp; + remaining = cfg->fc_mp_len; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + if (err) { + last_err = err; + /* If we are trying to remove a route, do not stop the + * loop when ip6_route_del() fails (because next hop is + * already gone), we should try to remove all next hops. + */ + if (add) { + /* If add fails, we should try to delete all + * next hops that have been already added. + */ + add = 0; + goto beginning; + } + } + /* Because each route is added like a single route we remove + * this flag after the first nexthop (if there is a collision, + * we have already fail to add the first nexthop: + * fib6_add_rt2node() has reject it). + */ + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + rtnh = rtnh_next(rtnh, &remaining); + } + + return last_err; +} + static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct fib6_config cfg; @@ -2340,7 +2446,10 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_del(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 0); + else + return ip6_route_del(&cfg); } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) @@ -2352,7 +2461,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_add(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 1); + else + return ip6_route_add(&cfg); } static inline size_t rt6_nlmsg_size(void) @@ -2596,7 +2708,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { - dst_release(&rt->dst); + ip6_rt_put(rt); err = -ENOBUFS; goto errout; } @@ -2873,6 +2985,10 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } return table; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3ed54ffd8d50..cfba99b2c2a4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -65,9 +65,14 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + 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 struct rtnl_link_ops sit_link_ops __read_mostly; static int sit_net_id __read_mostly; struct sit_net { @@ -80,22 +85,6 @@ struct sit_net { struct net_device *fb_tunnel_dev; }; -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#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 { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { @@ -121,6 +110,7 @@ static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev, } tot->rx_errors = dev->stats.rx_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; tot->tx_fifo_errors = dev->stats.tx_fifo_errors; tot->tx_carrier_errors = dev->stats.tx_carrier_errors; tot->tx_dropped = dev->stats.tx_dropped; @@ -141,20 +131,20 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) @@ -231,6 +221,37 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #endif } +static int ipip6_tunnel_create(struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + int err; + + err = ipip6_tunnel_init(dev); + if (err < 0) + goto out; + ipip6_tunnel_clone_6rd(dev, sitn); + + if ((__force u16)t->parms.i_flags & SIT_ISATAP) + dev->priv_flags |= IFF_ISATAP; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &sit_link_ops; + + dev_hold(dev); + + ipip6_tunnel_link(sitn, t); + return 0; + +out: + return err; +} + static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { @@ -271,21 +292,9 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - if (ipip6_tunnel_init(dev) < 0) + if (ipip6_tunnel_create(dev) < 0) goto failed_free; - ipip6_tunnel_clone_6rd(dev, sitn); - if (parms->i_flags & SIT_ISATAP) - dev->priv_flags |= IFF_ISATAP; - - if (register_netdevice(dev) < 0) - goto failed_free; - - strcpy(nt->parms.name, dev->name); - - dev_hold(dev); - - ipip6_tunnel_link(sitn, nt); return nt; failed_free: @@ -581,16 +590,11 @@ out: return err; } -static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) -{ - if (INET_ECN_is_ce(iph->tos)) - IP6_ECN_set_ce(ipv6_hdr(skb)); -} - static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph; struct ip_tunnel *tunnel; + int err; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; @@ -612,18 +616,27 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - kfree_skb(skb); - return 0; + goto out; + } + + __skb_tunnel_rx(skb, tunnel->dev); + + err = IP_ECN_decapsulate(iph, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &iph->saddr, iph->tos); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto out; + } } 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); return 0; @@ -683,7 +696,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; @@ -864,9 +876,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if ((iph->ttl = tiph->ttl) == 0) iph->ttl = iph6->hop_limit; - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; tx_error_icmp: @@ -914,6 +924,59 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) dev->iflink = tunnel->parms.link; } +static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = dev_net(t->dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + ipip6_tunnel_unlink(sitn, t); + synchronize_net(); + t->parms.iph.saddr = p->iph.saddr; + t->parms.iph.daddr = p->iph.daddr; + memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + memcpy(t->dev->broadcast, &p->iph.daddr, 4); + ipip6_tunnel_link(sitn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip6_tunnel_bind_dev(t->dev); + } + netdev_state_change(t->dev); +} + +#ifdef CONFIG_IPV6_SIT_6RD +static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, + struct ip_tunnel_6rd *ip6rd) +{ + struct in6_addr prefix; + __be32 relay_prefix; + + if (ip6rd->relay_prefixlen > 32 || + ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) + return -EINVAL; + + ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) + return -EINVAL; + if (ip6rd->relay_prefixlen) + relay_prefix = ip6rd->relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd->relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd->relay_prefix) + return -EINVAL; + + t->ip6rd.prefix = prefix; + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd->prefixlen; + t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + netdev_state_change(t->dev); + return 0; +} +#endif + static int ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -966,7 +1029,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -995,28 +1058,13 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } 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); - memcpy(dev->broadcast, &p.iph.daddr, 4); - ipip6_tunnel_link(sitn, t); - netdev_state_change(dev); } + + ipip6_tunnel_update(t, &p); } if (t) { err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.iph.ttl = p.iph.ttl; - t->parms.iph.tos = p.iph.tos; - if (t->parms.link != p.link) { - t->parms.link = p.link; - ipip6_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -1025,7 +1073,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == sitn->fb_tunnel_dev) { @@ -1058,7 +1106,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELPRL: case SIOCCHGPRL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EINVAL; if (dev == sitn->fb_tunnel_dev) @@ -1087,7 +1135,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCCHG6RD: case SIOCDEL6RD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1098,31 +1146,9 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) t = netdev_priv(dev); if (cmd != SIOCDEL6RD) { - struct in6_addr prefix; - __be32 relay_prefix; - - err = -EINVAL; - if (ip6rd.relay_prefixlen > 32 || - ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) - goto done; - - ipv6_addr_prefix(&prefix, &ip6rd.prefix, - ip6rd.prefixlen); - if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) - goto done; - if (ip6rd.relay_prefixlen) - relay_prefix = ip6rd.relay_prefix & - htonl(0xffffffffUL << - (32 - ip6rd.relay_prefixlen)); - else - relay_prefix = 0; - if (relay_prefix != ip6rd.relay_prefix) + err = ipip6_tunnel_update_6rd(t, &ip6rd); + if (err < 0) goto done; - - t->ip6rd.prefix = prefix; - t->ip6rd.relay_prefix = relay_prefix; - t->ip6rd.prefixlen = ip6rd.prefixlen; - t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; } else ipip6_tunnel_clone_6rd(dev, sitn); @@ -1216,6 +1242,239 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) return 0; } +static void ipip6_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPV6; + parms->iph.ihl = 5; + parms->iph.ttl = 64; + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_FLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); +} + +#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[], + struct ip_tunnel_6rd *ip6rd) +{ + bool ret = false; + memset(ip6rd, 0, sizeof(*ip6rd)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_6RD_PREFIX]) { + ret = true; + nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX], + sizeof(struct in6_addr)); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { + ret = true; + ip6rd->relay_prefix = + nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); + } + + if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { + ret = true; + ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { + ret = true; + ip6rd->relay_prefixlen = + nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); + } + + return ret; +} +#endif + +static int ipip6_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip_tunnel *nt; +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + int err; + + nt = netdev_priv(dev); + ipip6_netlink_parms(data, &nt->parms); + + if (ipip6_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + err = ipip6_tunnel_create(dev); + if (err < 0) + return err; + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + err = ipip6_tunnel_update_6rd(nt, &ip6rd); +#endif + + return err; +} + +static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t; + struct ip_tunnel_parm p; + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + + if (dev == sitn->fb_tunnel_dev) + return -EINVAL; + + ipip6_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip6_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip6_tunnel_update(t, &p); + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + return ipip6_tunnel_update_6rd(t, &ip6rd); +#endif + + return 0; +} + +static size_t ipip6_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(2) + +#ifdef CONFIG_IPV6_SIT_6RD + /* IFLA_IPTUN_6RD_PREFIX */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ + nla_total_size(4) + + /* IFLA_IPTUN_6RD_PREFIXLEN */ + nla_total_size(2) + + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ + nla_total_size(2) + +#endif + 0; +} + +static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) + goto nla_put_failure; + +#ifdef CONFIG_IPV6_SIT_6RD + if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr), + &tunnel->ip6rd.prefix) || + nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, + tunnel->ip6rd.relay_prefix) || + nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, + tunnel->ip6rd.prefixlen) || + nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, + tunnel->ip6rd.relay_prefixlen)) + goto nla_put_failure; +#endif + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, +#ifdef CONFIG_IPV6_SIT_6RD + [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, + [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, + [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, +#endif +}; + +static struct rtnl_link_ops sit_link_ops __read_mostly = { + .kind = "sit", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip6_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip6_tunnel_setup, + .newlink = ipip6_newlink, + .changelink = ipip6_changelink, + .get_size = ipip6_get_size, + .fill_info = ipip6_fill_info, +}; + static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, @@ -1302,6 +1561,7 @@ static struct pernet_operations sit_net_ops = { static void __exit sit_cleanup(void) { + rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); unregister_pernet_device(&sit_net_ops); @@ -1319,10 +1579,21 @@ static int __init sit_init(void) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { - unregister_pernet_device(&sit_net_ops); pr_info("%s: can't add protocol\n", __func__); + goto xfrm_tunnel_failed; } + err = rtnl_link_register(&sit_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: return err; + +rtnl_link_failed: + xfrm4_tunnel_deregister(&sit_handler, AF_INET6); +xfrm_tunnel_failed: + unregister_pernet_device(&sit_net_ops); + goto out; } module_init(sit_init); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 182ab9a85d6c..40161977f7cf 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -214,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq6->iif = inet6_iif(skb); req->expires = 0UL; - req->retrans = 0; + req->num_retrans = 0; ireq->ecn_ok = ecn_ok; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 26175bffbaa0..6565cf55eb1e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -77,9 +77,6 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, - const struct in6_addr *daddr); static const struct inet_connection_sock_af_ops ipv6_mapped; static const struct inet_connection_sock_af_ops ipv6_specific; @@ -119,14 +116,6 @@ static void tcp_v6_hash(struct sock *sk) } } -static __inline__ __sum16 tcp_v6_check(int len, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - __wsum base) -{ - return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -306,7 +295,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (err) goto late_failure; - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, inet->inet_sport, @@ -495,9 +484,12 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { struct flowi6 fl6; + int res; - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); + res = tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); + if (!res) + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return res; } static void tcp_v6_reqsk_destructor(struct request_sock *req) @@ -719,94 +711,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, const struct in6_addr *daddr) -{ - struct tcphdr *th = tcp_hdr(skb); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v6_check(skb->len, saddr, daddr, - csum_partial(th, th->doff << 2, - skb->csum)); - } -} - -static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - - __tcp_v6_send_check(skb, &np->saddr, &np->daddr); -} - -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) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - __wsum wsum; - __sum16 sum; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } -flush: - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - - return tcp_gro_receive(head, skb); -} - -static int tcp6_gro_complete(struct sk_buff *skb) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); - - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - - return tcp_gro_complete(skb); -} - static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) { @@ -1364,7 +1268,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->retrans; + newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; @@ -1741,11 +1645,11 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { struct dst_entry *dst = sk->sk_rx_dst; - struct inet_sock *icsk = inet_sk(sk); + if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); if (dst && - icsk->rx_dst_ifindex == skb->skb_iif) + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -1866,7 +1770,7 @@ static void get_openreq6(struct seq_file *seq, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), - req->retrans, + req->num_timeout, from_kuid_munged(seq_user_ns(seq), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ @@ -2063,10 +1967,6 @@ static const struct inet6_protocol tcpv6_protocol = { .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -2121,10 +2021,10 @@ int __init tcpv6_init(void) out: return ret; -out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); +out_tcpv6_protocol: + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); goto out; } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c new file mode 100644 index 000000000000..2ec6bf6a0aa0 --- /dev/null +++ b/net/ipv6/tcpv6_offload.c @@ -0,0 +1,95 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * TCPv6 GSO/GRO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/tcp.h> +#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) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + __wsum wsum; + __sum16 sum; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + + case CHECKSUM_NONE: + wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), + IPPROTO_TCP, 0)); + sum = csum_fold(skb_checksum(skb, + skb_gro_offset(skb), + skb_gro_len(skb), + wsum)); + if (sum) + goto flush; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + return tcp_gro_receive(head, skb); +} + +static int tcp6_gro_complete(struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), + &iph->saddr, &iph->daddr, 0); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + + return tcp_gro_complete(skb); +} + +static const struct net_offload tcpv6_offload = { + .callbacks = { + .gso_send_check = tcp_v6_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, +}; + +int __init tcpv6_offload_init(void) +{ + return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); +} diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fc9997260a6b..dfaa29b8b293 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1343,103 +1343,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -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; - - 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) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - unsigned int mss; - unsigned int unfrag_ip6hlen, unfrag_len; - struct frag_hdr *fptr; - u8 *mac_start, *prevhdr; - u8 nexthdr; - u8 frag_hdr_sz = sizeof(struct frag_hdr); - int offset; - __wsum csum; - - mss = skb_shinfo(skb)->gso_size; - if (unlikely(skb->len <= mss)) - goto out; - - if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { - /* Packet is from an untrusted source, reset gso_segs. */ - int type = skb_shinfo(skb)->gso_type; - - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || - !(type & (SKB_GSO_UDP)))) - goto out; - - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); - - segs = NULL; - 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); - skb->ip_summed = CHECKSUM_NONE; - - /* Check if there is enough headroom to insert fragment header. */ - if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && - pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) - goto out; - - /* Find the unfragmentable header and shift it left by frag_hdr_sz - * bytes to insert fragment header. - */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - nexthdr = *prevhdr; - *prevhdr = NEXTHDR_FRAGMENT; - unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + - unfrag_ip6hlen; - mac_start = skb_mac_header(skb); - memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); - - skb->mac_header -= frag_hdr_sz; - skb->network_header -= frag_hdr_sz; - - fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); - fptr->nexthdr = nexthdr; - fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); - - /* Fragment the skb. ipv6 header and the remaining fields of the - * fragment header are updated in ipv6_gso_segment() - */ - segs = skb_segment(skb, features); - -out: - return segs; -} - static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, - .gso_send_check = udp6_ufo_send_check, - .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c new file mode 100644 index 000000000000..0c8934a317c2 --- /dev/null +++ b/net/ipv6/udp_offload.c @@ -0,0 +1,120 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * UDPv6 GSO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/ipv6.h> +#include <net/udp.h> +#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; + + 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) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + 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); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} +static const struct net_offload udpv6_offload = { + .callbacks = { + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, + }, +}; + +int __init udp_offload_init(void) +{ + return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); +} diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f8c4c08ffb60..c9844135c9ca 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -20,7 +20,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif @@ -182,7 +182,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) fl6->flowi6_proto = nexthdr; return; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; @@ -327,21 +327,7 @@ static struct ctl_table_header *sysctl_hdr; int __init xfrm6_init(void) { int ret; - unsigned int gc_thresh; - - /* - * We need a good default value for the xfrm6 gc threshold. - * In ipv4 we set it to the route hash table size * 8, which - * is half the size of the maximaum route cache for ipv4. It - * would be good to do the same thing for v6, except the table is - * constructed differently here. Here each table for a net namespace - * can have FIB_TABLE_HASHSZ entries, so lets go with the same - * computation that we used for ipv4 here. Also, lets keep the initial - * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults - * to that as a minimum as well - */ - 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(); @@ -370,7 +356,6 @@ void xfrm6_fini(void) if (sysctl_hdr) unregister_net_sysctl_table(sysctl_hdr); #endif - //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); dst_entries_destroy(&xfrm6_dst_ops); diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 3f2f7c4ab721..d8c70b8efc24 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -101,7 +101,7 @@ static int __xfrm6_state_sort_cmp(void *p) return 1; else return 3; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; @@ -134,7 +134,7 @@ static int __xfrm6_tmpl_sort_cmp(void *p) switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; |