diff options
Diffstat (limited to 'net/ipv6')
37 files changed, 3504 insertions, 546 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 5728695b5449..4f7fe7270e37 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -201,6 +201,22 @@ config IPV6_TUNNEL If unsure, say N. +config IPV6_GRE + tristate "IPv6: GRE tunnel" + select IPV6_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This particular tunneling driver implements + GRE (Generic Routing Encapsulation) and at this time allows + encapsulating of IPv4 or IPv6 over existing IPv6 infrastructure. + This driver is useful if the other endpoint is a Cisco router: Cisco + likes GRE much better than the other Linux tunneling driver ("IP + tunneling" above). In addition, GRE allows multicast redistribution + through the tunnel. + + Saying M here will produce a module called ip6_gre. If unsure, say N. + config IPV6_MULTIPLE_TABLES bool "IPv6: Multiple Routing Tables" depends on EXPERIMENTAL diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 686934acfac1..b6d3f79151e2 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o +obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-y += addrconf_core.o exthdrs_core.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 79181819a24f..d7c56f8a5b4e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -127,8 +127,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) #endif #ifdef CONFIG_IPV6_PRIVACY -static int __ipv6_regen_rndid(struct inet6_dev *idev); -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); +static void __ipv6_regen_rndid(struct inet6_dev *idev); +static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static void ipv6_regen_rndid(unsigned long data); #endif @@ -494,8 +494,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); @@ -504,7 +503,6 @@ static void addrconf_forward_change(struct net *net, __s32 newf) dev_forward_change(idev); } } - rcu_read_unlock(); } static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) @@ -790,10 +788,16 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) struct in6_addr prefix; struct rt6_info *rt; struct net *net = dev_net(ifp->idev->dev); + struct flowi6 fl6 = {}; + ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1); + fl6.flowi6_oif = ifp->idev->dev->ifindex; + fl6.daddr = prefix; + rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, + RT6_LOOKUP_F_IFACE); - if (rt && addrconf_is_prefix_route(rt)) { + if (rt != net->ipv6.ip6_null_entry && + addrconf_is_prefix_route(rt)) { if (onlink == 0) { ip6_del_rt(rt); rt = NULL; @@ -854,16 +858,7 @@ retry: } in6_ifa_hold(ifp); memcpy(addr.s6_addr, ifp->addr.s6_addr, 8); - if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) { - spin_unlock_bh(&ifp->lock); - write_unlock(&idev->lock); - pr_warn("%s: regeneration of randomized interface id failed\n", - __func__); - in6_ifa_put(ifp); - in6_dev_put(idev); - ret = -1; - goto out; - } + __ipv6_try_regen_rndid(idev, tmpaddr); memcpy(&addr.s6_addr[8], idev->rndid, 8); age = (now - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, @@ -1081,8 +1076,10 @@ static int ipv6_get_saddr_eval(struct net *net, break; case IPV6_SADDR_RULE_PREFIX: /* Rule 8: Use longest matching prefix */ - score->matchlen = ret = ipv6_addr_diff(&score->ifa->addr, - dst->addr); + ret = ipv6_addr_diff(&score->ifa->addr, dst->addr); + if (ret > score->ifa->prefix_len) + ret = score->ifa->prefix_len; + score->matchlen = ret; break; default: ret = 0; @@ -1095,7 +1092,7 @@ out: return ret; } -int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, +int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { @@ -1602,7 +1599,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) #ifdef CONFIG_IPV6_PRIVACY /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ -static int __ipv6_regen_rndid(struct inet6_dev *idev) +static void __ipv6_regen_rndid(struct inet6_dev *idev) { regen: get_random_bytes(idev->rndid, sizeof(idev->rndid)); @@ -1629,8 +1626,6 @@ regen: if ((idev->rndid[2]|idev->rndid[3]|idev->rndid[4]|idev->rndid[5]|idev->rndid[6]|idev->rndid[7]) == 0x00) goto regen; } - - return 0; } static void ipv6_regen_rndid(unsigned long data) @@ -1644,8 +1639,7 @@ static void ipv6_regen_rndid(unsigned long data) if (idev->dead) goto out; - if (__ipv6_regen_rndid(idev) < 0) - goto out; + __ipv6_regen_rndid(idev); expires = jiffies + idev->cnf.temp_prefered_lft * HZ - @@ -1666,13 +1660,10 @@ out: in6_dev_put(idev); } -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) +static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) { - int ret = 0; - if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) - ret = __ipv6_regen_rndid(idev); - return ret; + __ipv6_regen_rndid(idev); } #endif @@ -1723,7 +1714,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (table == NULL) return NULL; - write_lock_bh(&table->tb6_lock); + read_lock_bh(&table->tb6_lock); fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); if (!fn) goto out; @@ -1738,7 +1729,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, break; } out: - write_unlock_bh(&table->tb6_lock); + read_unlock_bh(&table->tb6_lock); return rt; } @@ -1778,14 +1769,6 @@ static void sit_route_add(struct net_device *dev) } #endif -static void addrconf_add_lroute(struct net_device *dev) -{ - struct in6_addr addr; - - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - addrconf_prefix_route(&addr, 64, dev, 0, 0); -} - static struct inet6_dev *addrconf_add_dev(struct net_device *dev) { struct inet6_dev *idev; @@ -1803,8 +1786,6 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) if (!(dev->flags & IFF_LOOPBACK)) addrconf_add_mroute(dev); - /* Add link local route */ - addrconf_add_lroute(dev); return idev; } @@ -2483,10 +2464,9 @@ static void addrconf_sit_config(struct net_device *dev) sit_add_v4_addrs(idev); - if (dev->flags&IFF_POINTOPOINT) { + if (dev->flags&IFF_POINTOPOINT) addrconf_add_mroute(dev); - addrconf_add_lroute(dev); - } else + else sit_route_add(dev); } #endif @@ -3551,12 +3531,12 @@ static inline int inet6_ifaddr_msgsize(void) } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3594,7 +3574,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 pid, u32 seq, int event, u16 flags) + u32 portid, u32 seq, int event, u16 flags) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -3603,7 +3583,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3619,7 +3599,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -3628,7 +3608,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3669,7 +3649,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (++ip_idx < s_ip_idx) continue; err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI); @@ -3685,7 +3665,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETMULTICAST, NLM_F_MULTI); @@ -3700,7 +3680,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETANYCAST, NLM_F_MULTI); @@ -3822,7 +3802,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_ifa; } - err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid, + err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDR, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ @@ -3830,7 +3810,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: @@ -4032,14 +4012,14 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; void *protoinfo; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; @@ -4097,7 +4077,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (!idev) goto cont; if (inet6_fill_ifinfo(skb, idev, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI) <= 0) goto out; @@ -4145,14 +4125,14 @@ static inline size_t inet6_prefix_nlmsg_size(void) } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, - struct prefix_info *pinfo, u32 pid, u32 seq, + struct prefix_info *pinfo, u32 portid, u32 seq, int event, unsigned int flags) { struct prefixmsg *pmsg; struct nlmsghdr *nlh; struct prefix_cacheinfo ci; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*pmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); if (nlh == NULL) return -EMSGSIZE; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index eb6a63632d3c..4be23da32b89 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -57,7 +57,7 @@ struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) } /* - * Default policy table (RFC3484 + extensions) + * Default policy table (RFC6724 + extensions) * * prefix addr_type label * ------------------------------------------------------------------------- @@ -69,8 +69,12 @@ struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) * fc00::/7 N/A 5 ULA (RFC 4193) * 2001::/32 N/A 6 Teredo (RFC 4380) * 2001:10::/28 N/A 7 ORCHID (RFC 4843) + * fec0::/10 N/A 11 Site-local + * (deprecated by RFC3879) + * 3ffe::/16 N/A 12 6bone * * Note: 0xffffffff is used if we do not have any policies. + * Note: Labels for ULA and 6to4 are different from labels listed in RFC6724. */ #define IPV6_ADDR_LABEL_DEFAULT 0xffffffffUL @@ -88,10 +92,18 @@ static const __net_initdata struct ip6addrlbl_init_table .prefix = &(struct in6_addr){{{ 0xfc }}}, .prefixlen = 7, .label = 5, + },{ /* fec0::/10 */ + .prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}}, + .prefixlen = 10, + .label = 11, },{ /* 2002::/16 */ .prefix = &(struct in6_addr){{{ 0x20, 0x02 }}}, .prefixlen = 16, .label = 2, + },{ /* 3ffe::/16 */ + .prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}}, + .prefixlen = 16, + .label = 12, },{ /* 2001::/32 */ .prefix = &(struct in6_addr){{{ 0x20, 0x01 }}}, .prefixlen = 32, @@ -470,10 +482,10 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, static int ip6addrlbl_fill(struct sk_buff *skb, struct ip6addrlbl_entry *p, u32 lseq, - u32 pid, u32 seq, int event, + u32 portid, u32 seq, int event, unsigned int flags) { - struct nlmsghdr *nlh = nlmsg_put(skb, pid, seq, event, + struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrlblmsg), flags); if (!nlh) return -EMSGSIZE; @@ -503,7 +515,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) net_eq(ip6addrlbl_net(p), net)) { if ((err = ip6addrlbl_fill(skb, p, ip6addrlbl_table.seq, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI)) <= 0) @@ -574,7 +586,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, } err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, 0); ip6addrlbl_put(p); @@ -585,7 +597,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, goto out; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6dc7fd353ef5..282f3723ee19 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -167,8 +167,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct esp_data *esp = x->data; /* skb is pure payload to encrypt */ - err = -ENOMEM; - aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -203,8 +201,10 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0251a6005be8..c4f934176cab 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -175,33 +175,12 @@ void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); - -#ifdef CONFIG_XFRM - { - struct rt6_info *rt = (struct rt6_info *)dst; - rt->rt6i_flow_cache_genid = atomic_read(&flow_cache_genid); - } -#endif } static inline struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst; - - dst = __sk_dst_check(sk, cookie); - -#ifdef CONFIG_XFRM - if (dst) { - struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - __sk_dst_reset(sk); - dst = NULL; - } - } -#endif - - return dst; + return __sk_dst_check(sk, cookie); } static struct dst_entry *inet6_csk_route_socket(struct sock *sk, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 13690d650c3e..24995a93ef8c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -514,7 +514,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, ln = node_alloc(); if (!ln) - return NULL; + return ERR_PTR(-ENOMEM); ln->fn_bit = plen; ln->parent = pn; @@ -561,7 +561,7 @@ insert_above: node_free(in); if (ln) node_free(ln); - return NULL; + return ERR_PTR(-ENOMEM); } /* @@ -611,7 +611,7 @@ insert_above: ln = node_alloc(); if (!ln) - return NULL; + return ERR_PTR(-ENOMEM); ln->fn_bit = plen; @@ -777,11 +777,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (IS_ERR(fn)) { err = PTR_ERR(fn); - fn = NULL; - } - - if (!fn) goto out; + } pn = fn; @@ -819,12 +816,13 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); - if (!sn) { + if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in st_failure) stale node in main tree. */ node_free(sfn); + err = PTR_ERR(sn); goto st_failure; } @@ -839,10 +837,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (IS_ERR(sn)) { err = PTR_ERR(sn); - sn = NULL; - } - if (!sn) goto st_failure; + } } if (!fn->leaf) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 9772fbd8a3f5..90bbefb57943 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -22,6 +22,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/pid_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -91,6 +92,8 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) static void fl_free(struct ip6_flowlabel *fl) { if (fl) { + if (fl->share == IPV6_FL_S_PROCESS) + put_pid(fl->owner.pid); release_net(fl->fl_net); kfree(fl->opt); } @@ -394,10 +397,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, case IPV6_FL_S_ANY: break; case IPV6_FL_S_PROCESS: - fl->owner = current->pid; + fl->owner.pid = get_task_pid(current, PIDTYPE_PID); break; case IPV6_FL_S_USER: - fl->owner = current_euid(); + fl->owner.uid = current_euid(); break; default: err = -EINVAL; @@ -561,7 +564,10 @@ recheck: err = -EPERM; if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || - fl1->owner != fl->owner) + ((fl1->share == IPV6_FL_S_PROCESS) && + (fl1->owner.pid == fl->owner.pid)) || + ((fl1->share == IPV6_FL_S_USER) && + uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -EINVAL; @@ -621,6 +627,7 @@ done: struct ip6fl_iter_state { struct seq_net_private p; + struct pid_namespace *pid_ns; int bucket; }; @@ -699,6 +706,7 @@ static void ip6fl_seq_stop(struct seq_file *seq, void *v) static int ip6fl_seq_show(struct seq_file *seq, void *v) { + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); if (v == SEQ_START_TOKEN) seq_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-32s %s\n", "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt"); @@ -708,7 +716,11 @@ static int ip6fl_seq_show(struct seq_file *seq, void *v) "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", (unsigned int)ntohl(fl->label), fl->share, - (int)fl->owner, + ((fl->share == IPV6_FL_S_PROCESS) ? + pid_nr_ns(fl->owner.pid, state->pid_ns) : + ((fl->share == IPV6_FL_S_USER) ? + from_kuid_munged(seq_user_ns(seq), fl->owner.uid) : + 0)), atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, @@ -727,8 +739,29 @@ static const struct seq_operations ip6fl_seq_ops = { static int ip6fl_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &ip6fl_seq_ops, - sizeof(struct ip6fl_iter_state)); + struct seq_file *seq; + struct ip6fl_iter_state *state; + int err; + + err = seq_open_net(inode, file, &ip6fl_seq_ops, + sizeof(struct ip6fl_iter_state)); + + if (!err) { + seq = file->private_data; + state = ip6fl_seq_private(seq); + rcu_read_lock(); + state->pid_ns = get_pid_ns(task_active_pid_ns(current)); + rcu_read_unlock(); + } + return err; +} + +static int ip6fl_seq_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + put_pid_ns(state->pid_ns); + return seq_release_net(inode, file); } static const struct file_operations ip6fl_seq_fops = { @@ -736,7 +769,7 @@ static const struct file_operations ip6fl_seq_fops = { .open = ip6fl_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_net, + .release = ip6fl_seq_release, }; static int __net_init ip6_flowlabel_proc_init(struct net *net) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c new file mode 100644 index 000000000000..0185679c5f53 --- /dev/null +++ b/net/ipv6/ip6_gre.c @@ -0,0 +1,1770 @@ +/* + * GRE over IPv6 protocol decoder. + * + * Authors: Dmitry Kozlov (xeb@mail.ru) + * + * 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. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_arp.h> +#include <linux/mroute.h> +#include <linux/init.h> +#include <linux/in6.h> +#include <linux/inetdevice.h> +#include <linux/igmp.h> +#include <linux/netfilter_ipv4.h> +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <linux/hash.h> +#include <linux/if_tunnel.h> +#include <linux/ip6_tunnel.h> + +#include <net/sock.h> +#include <net/ip.h> +#include <net/icmp.h> +#include <net/protocol.h> +#include <net/addrconf.h> +#include <net/arp.h> +#include <net/checksum.h> +#include <net/dsfield.h> +#include <net/inet_ecn.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/rtnetlink.h> + +#include <net/ipv6.h> +#include <net/ip6_fib.h> +#include <net/ip6_route.h> +#include <net/ip6_tunnel.h> + + +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"); + +#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) +#define IPV6_TCLASS_SHIFT 20 + +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) + +static int ip6gre_net_id __read_mostly; +struct ip6gre_net { + struct ip6_tnl __rcu *tunnels[4][HASH_SIZE]; + + struct net_device *fb_tunnel_dev; +}; + +static struct rtnl_link_ops ip6gre_link_ops __read_mostly; +static int ip6gre_tunnel_init(struct net_device *dev); +static void ip6gre_tunnel_setup(struct net_device *dev); +static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t); +static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu); + +/* Tunnel hash table */ + +/* + 4 hash tables: + + 3: (remote,local) + 2: (remote,*) + 1: (*,local) + 0: (*,*) + + We require exact key match i.e. if a key is present in packet + it will match only tunnel with the same key; if it is not present, + it will match only keyless tunnel. + + All keysless packets, if not matched configured keyless tunnels + will match fallback tunnel. + */ + +#define HASH_KEY(key) (((__force u32)key^((__force u32)key>>4))&(HASH_SIZE - 1)) +static u32 HASH_ADDR(const struct in6_addr *addr) +{ + u32 hash = ipv6_addr_hash(addr); + + return hash_32(hash, HASH_SIZE_SHIFT); +} + +#define tunnels_r_l tunnels[3] +#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) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_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; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; +} + +/* Given src, dst and key, find appropriate for input tunnel. */ + +static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, + const struct in6_addr *remote, const struct in6_addr *local, + __be32 key, __be16 gre_proto) +{ + struct net *net = dev_net(dev); + int link = dev->ifindex; + unsigned int h0 = HASH_ADDR(remote); + unsigned int h1 = HASH_KEY(key); + struct ip6_tnl *t, *cand = NULL; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int dev_type = (gre_proto == htons(ETH_P_TEB)) ? + ARPHRD_ETHER : ARPHRD_IP6GRE; + int score, cand_score = 4; + + for_each_ip_tunnel_rcu(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 || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { + if (!ipv6_addr_equal(remote, &t->parms.raddr) || + key != t->parms.i_key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { + if ((!ipv6_addr_equal(local, &t->parms.laddr) && + (!ipv6_addr_equal(local, &t->parms.raddr) || + !ipv6_addr_is_multicast(local))) || + key != t->parms.i_key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { + if (t->parms.i_key != key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + if (cand != NULL) + return cand; + + dev = ign->fb_tunnel_dev; + if (dev->flags & IFF_UP) + return netdev_priv(dev); + + return NULL; +} + +static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign, + const struct __ip6_tnl_parm *p) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = HASH_KEY(p->i_key); + int prio = 0; + + if (!ipv6_addr_any(local)) + prio |= 1; + if (!ipv6_addr_any(remote) && !ipv6_addr_is_multicast(remote)) { + prio |= 2; + h ^= HASH_ADDR(remote); + } + + return &ign->tunnels[prio][h]; +} + +static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign, + const struct ip6_tnl *t) +{ + return __ip6gre_bucket(ign, &t->parms); +} + +static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t); + + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = ip6gre_bucket(ign, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static struct ip6_tnl *ip6gre_tunnel_find(struct net *net, + const struct __ip6_tnl_parm *parms, + int type) +{ + const struct in6_addr *remote = &parms->raddr; + const struct in6_addr *local = &parms->laddr; + __be32 key = parms->i_key; + int link = parms->link; + struct ip6_tnl *t; + struct ip6_tnl __rcu **tp; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + for (tp = __ip6gre_bucket(ign, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr) && + key == t->parms.i_key && + link == t->parms.link && + type == t->dev->type) + break; + + return t; +} + +static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, + const struct __ip6_tnl_parm *parms, int create) +{ + struct ip6_tnl *t, *nt; + struct net_device *dev; + char name[IFNAMSIZ]; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE); + if (t || !create) + return t; + + if (parms->name[0]) + strlcpy(name, parms->name, IFNAMSIZ); + else + strcpy(name, "ip6gre%d"); + + dev = alloc_netdev(sizeof(*t), name, ip6gre_tunnel_setup); + if (!dev) + return NULL; + + dev_net_set(dev, net); + + nt = netdev_priv(dev); + nt->parms = *parms; + dev->rtnl_link_ops = &ip6gre_link_ops; + + nt->dev = dev; + ip6gre_tnl_link_config(nt, 1); + + if (register_netdevice(dev) < 0) + goto failed_free; + + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + + dev_hold(dev); + ip6gre_tunnel_link(ign, nt); + return nt; + +failed_free: + free_netdev(dev); + return NULL; +} + +static void ip6gre_tunnel_uninit(struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + ip6gre_tunnel_unlink(ign, netdev_priv(dev)); + dev_put(dev); +} + + +static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; + __be16 *p = (__be16 *)(skb->data + offset); + int grehlen = offset + 4; + struct ip6_tnl *t; + __be16 flags; + + flags = p[0]; + if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { + if (flags&(GRE_VERSION|GRE_ROUTING)) + return; + if (flags&GRE_KEY) { + grehlen += 4; + if (flags&GRE_CSUM) + grehlen += 4; + } + } + + /* If only 8 bytes returned, keyed message will be dropped here */ + if (!pskb_may_pull(skb, grehlen)) + return; + ipv6h = (const struct ipv6hdr *)skb->data; + p = (__be16 *)(skb->data + offset); + + t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, + flags & GRE_KEY ? + *(((__be32 *)p) + (grehlen / 4) - 1) : 0, + p[1]); + if (t == NULL) + return; + + switch (type) { + __u32 teli; + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 mtu; + case ICMPV6_DEST_UNREACH: + net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); + break; + case ICMPV6_TIME_EXCEED: + if (code == ICMPV6_EXC_HOPLIMIT) { + net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); + } + break; + case ICMPV6_PARAMPROB: + teli = 0; + if (code == ICMPV6_HDR_FIELD) + teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); + + if (teli && teli == info - 2) { + tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; + if (tel->encap_limit == 0) { + net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); + } + } else { + net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); + } + break; + case ICMPV6_PKT_TOOBIG: + mtu = info - offset; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + t->dev->mtu = mtu; + break; + } + + if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) + t->err_count++; + else + t->err_count = 1; + t->err_time = jiffies; +} + +static int ip6gre_rcv(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + u8 *h; + __be16 flags; + __sum16 csum = 0; + __be32 key = 0; + u32 seqno = 0; + struct ip6_tnl *tunnel; + int offset = 4; + __be16 gre_proto; + int err; + + if (!pskb_may_pull(skb, sizeof(struct in6_addr))) + goto drop; + + ipv6h = ipv6_hdr(skb); + h = skb->data; + flags = *(__be16 *)h; + + if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) { + /* - Version must be 0. + - We do not support routing headers. + */ + if (flags&(GRE_VERSION|GRE_ROUTING)) + goto drop; + + if (flags&GRE_CSUM) { + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + csum = csum_fold(skb->csum); + if (!csum) + break; + /* fall through */ + case CHECKSUM_NONE: + skb->csum = 0; + csum = __skb_checksum_complete(skb); + skb->ip_summed = CHECKSUM_COMPLETE; + } + offset += 4; + } + if (flags&GRE_KEY) { + key = *(__be32 *)(h + offset); + offset += 4; + } + if (flags&GRE_SEQ) { + seqno = ntohl(*(__be32 *)(h + offset)); + offset += 4; + } + } + + gre_proto = *(__be16 *)(h + 2); + + tunnel = ip6gre_tunnel_lookup(skb->dev, + &ipv6h->saddr, &ipv6h->daddr, key, + gre_proto); + if (tunnel) { + struct pcpu_tstats *tstats; + + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + if (!ip6_tnl_rcv_ctl(tunnel, &ipv6h->daddr, &ipv6h->saddr)) { + tunnel->dev->stats.rx_dropped++; + goto drop; + } + + secpath_reset(skb); + + skb->protocol = gre_proto; + /* WCCP version 1 and 2 protocol decoding. + * - Change protocol to IP + * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header + */ + if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { + skb->protocol = htons(ETH_P_IP); + if ((*(h + offset) & 0xF0) != 0x40) + offset += 4; + } + + skb->mac_header = skb->network_header; + __pskb_pull(skb, offset); + skb_postpull_rcsum(skb, skb_transport_header(skb), offset); + skb->pkt_type = PACKET_HOST; + + if (((flags&GRE_CSUM) && csum) || + (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) { + tunnel->dev->stats.rx_crc_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + if (tunnel->parms.i_flags&GRE_SEQ) { + if (!(flags&GRE_SEQ) || + (tunnel->i_seqno && + (s32)(seqno - tunnel->i_seqno) < 0)) { + tunnel->dev->stats.rx_fifo_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + tunnel->i_seqno = seqno + 1; + } + + /* Warning: All skb pointers will be invalidated! */ + if (tunnel->dev->type == ARPHRD_ETHER) { + if (!pskb_may_pull(skb, ETH_HLEN)) { + tunnel->dev->stats.rx_length_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + + ipv6h = ipv6_hdr(skb); + skb->protocol = eth_type_trans(skb, tunnel->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + } + + __skb_tunnel_rx(skb, tunnel->dev); + + skb_reset_network_header(skb); + + err = IP6_ECN_decapsulate(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) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto drop; + } + } + + tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + netif_rx(skb); + + return 0; + } + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + +drop: + kfree_skb(skb); + return 0; +} + +struct ipv6_tel_txoption { + struct ipv6_txoptions ops; + __u8 dst_opt[8]; +}; + +static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) +{ + memset(opt, 0, sizeof(struct ipv6_tel_txoption)); + + opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; + opt->dst_opt[3] = 1; + opt->dst_opt[4] = encap_limit; + opt->dst_opt[5] = IPV6_TLV_PADN; + opt->dst_opt[6] = 1; + + opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt; + opt->ops.opt_nflen = 8; +} + +static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, + struct net_device *dev, + __u8 dsfield, + struct flowi6 *fl6, + int encap_limit, + __u32 *pmtu) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *tunnel = netdev_priv(dev); + struct net_device *tdev; /* Device to other host */ + struct ipv6hdr *ipv6h; /* Our new IP header */ + unsigned int max_headroom; /* The extra header space needed */ + int gre_hlen; + struct ipv6_tel_txoption opt; + int mtu; + struct dst_entry *dst = NULL, *ndst = NULL; + struct net_device_stats *stats = &tunnel->dev->stats; + int err = -1; + u8 proto; + int pkt_len; + struct sk_buff *new_skb; + + if (dev->type == ARPHRD_ETHER) + IPCB(skb)->flags = 0; + + if (dev->header_ops && dev->type == ARPHRD_IP6GRE) { + gre_hlen = 0; + ipv6h = (struct ipv6hdr *)skb->data; + fl6->daddr = ipv6h->daddr; + } else { + gre_hlen = tunnel->hlen; + fl6->daddr = tunnel->parms.raddr; + } + + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(tunnel); + + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); + + if (ndst->error) + goto tx_err_link_failure; + ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); + ndst = NULL; + goto tx_err_link_failure; + } + dst = ndst; + } + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + tunnel->parms.name); + goto tx_err_dst_release; + } + + mtu = dst_mtu(dst) - sizeof(*ipv6h); + if (encap_limit >= 0) { + max_headroom += 8; + mtu -= 8; + } + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + if (skb->len > mtu) { + *pmtu = mtu; + err = -EMSGSIZE; + goto tx_err_dst_release; + } + + if (tunnel->err_count > 0) { + if (time_before(jiffies, + tunnel->err_time + IP6TUNNEL_ERR_TIMEO)) { + tunnel->err_count--; + + dst_link_failure(skb); + } else + tunnel->err_count = 0; + } + + max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + + if (skb_headroom(skb) < max_headroom || skb_shared(skb) || + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { + new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; + if (!new_skb) + goto tx_err_dst_release; + + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); + consume_skb(skb); + skb = new_skb; + } + + skb_dst_drop(skb); + + if (fl6->flowi6_mark) { + skb_dst_set(skb, dst); + ndst = NULL; + } else { + skb_dst_set_noref(skb, dst); + } + + skb->transport_header = skb->network_header; + + proto = NEXTHDR_GRE; + if (encap_limit >= 0) { + init_tel_txopt(&opt, encap_limit); + ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); + } + + skb_push(skb, gre_hlen); + skb_reset_network_header(skb); + + /* + * Push down and install the IP header. + */ + ipv6h = ipv6_hdr(skb); + *(__be32 *)ipv6h = fl6->flowlabel | htonl(0x60000000); + dsfield = INET_ECN_encapsulate(0, dsfield); + ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ipv6h->hop_limit = tunnel->parms.hop_limit; + ipv6h->nexthdr = proto; + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; + + ((__be16 *)(ipv6h + 1))[0] = tunnel->parms.o_flags; + ((__be16 *)(ipv6h + 1))[1] = (dev->type == ARPHRD_ETHER) ? + htons(ETH_P_TEB) : skb->protocol; + + if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)ipv6h) + tunnel->hlen - 4); + + if (tunnel->parms.o_flags&GRE_SEQ) { + ++tunnel->o_seqno; + *ptr = htonl(tunnel->o_seqno); + ptr--; + } + if (tunnel->parms.o_flags&GRE_KEY) { + *ptr = tunnel->parms.o_key; + ptr--; + } + if (tunnel->parms.o_flags&GRE_CSUM) { + *ptr = 0; + *(__sum16 *)ptr = ip_compute_csum((void *)(ipv6h+1), + skb->len - sizeof(struct ipv6hdr)); + } + } + + nf_reset(skb); + pkt_len = skb->len; + err = ip6_local_out(skb); + + if (net_xmit_eval(err) == 0) { + struct pcpu_tstats *tstats = this_cpu_ptr(tunnel->dev->tstats); + + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } + + if (ndst) + ip6_tnl_dst_store(tunnel, ndst); + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(ndst); + return err; +} + +static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + const struct iphdr *iph = ip_hdr(skb); + int encap_limit = -1; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; + + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; + + dsfield = ipv4_get_dsfield(iph); + + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) + fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) + & IPV6_TCLASS_MASK; + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + + err = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); + if (err != 0) { + /* XXX: send ICMP error even if DF is not set. */ + if (err == -EMSGSIZE) + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + return -1; + } + + return 0; +} + +static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int encap_limit = -1; + __u16 offset; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; + + if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr)) + return -1; + + offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + if (offset > 0) { + struct ipv6_tlv_tnl_enc_lim *tel; + tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; + if (tel->encap_limit == 0) { + icmpv6_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); + return -1; + } + encap_limit = tel->encap_limit - 1; + } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; + + dsfield = ipv6_get_dsfield(ipv6h); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) + fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) + fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + + err = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); + if (err != 0) { + if (err == -EMSGSIZE) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + return -1; + } + + return 0; +} + +/** + * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own + * @t: the outgoing tunnel device + * @hdr: IPv6 header from the incoming packet + * + * Description: + * Avoid trivial tunneling loop by checking that tunnel exit-point + * doesn't match source of incoming packet. + * + * Return: + * 1 if conflict, + * 0 else + **/ + +static inline bool ip6gre_tnl_addr_conflict(const struct ip6_tnl *t, + const struct ipv6hdr *hdr) +{ + return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); +} + +static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + int encap_limit = -1; + struct flowi6 fl6; + __u32 mtu; + int err; + + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = skb->protocol; + + err = ip6gre_xmit2(skb, dev, 0, &fl6, encap_limit, &mtu); + + return err; +} + +static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + int ret; + + if (!ip6_tnl_xmit_ctl(t)) + return -1; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ret = ip6gre_xmit_ipv4(skb, dev); + break; + case htons(ETH_P_IPV6): + ret = ip6gre_xmit_ipv6(skb, dev); + break; + default: + ret = ip6gre_xmit_other(skb, dev); + break; + } + + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) +{ + struct net_device *dev = t->dev; + struct __ip6_tnl_parm *p = &t->parms; + struct flowi6 *fl6 = &t->fl.u.ip6; + int addend = sizeof(struct ipv6hdr) + 4; + + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + } + + /* Set up flowi template */ + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; + fl6->flowi6_oif = p->link; + fl6->flowlabel = 0; + + if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) + fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; + if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) + fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; + + p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); + + if (p->flags&IP6_TNL_F_CAP_XMIT && + p->flags&IP6_TNL_F_CAP_RCV && dev->type != ARPHRD_ETHER) + dev->flags |= IFF_POINTOPOINT; + else + dev->flags &= ~IFF_POINTOPOINT; + + dev->iflink = p->link; + + /* Precalculate GRE options length */ + if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { + if (t->parms.o_flags&GRE_CSUM) + addend += 4; + if (t->parms.o_flags&GRE_KEY) + addend += 4; + if (t->parms.o_flags&GRE_SEQ) + addend += 4; + } + + if (p->flags & IP6_TNL_F_CAP_XMIT) { + int strict = (ipv6_addr_type(&p->raddr) & + (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); + + struct rt6_info *rt = rt6_lookup(dev_net(dev), + &p->raddr, &p->laddr, + p->link, strict); + + if (rt == NULL) + return; + + if (rt->dst.dev) { + dev->hard_header_len = rt->dst.dev->hard_header_len + addend; + + if (set_mtu) { + dev->mtu = rt->dst.dev->mtu - addend; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu -= 8; + + if (dev->mtu < IPV6_MIN_MTU) + dev->mtu = IPV6_MIN_MTU; + } + } + dst_release(&rt->dst); + } + + t->hlen = addend; +} + +static int ip6gre_tnl_change(struct ip6_tnl *t, + const struct __ip6_tnl_parm *p, int set_mtu) +{ + t->parms.laddr = p->laddr; + t->parms.raddr = p->raddr; + t->parms.flags = p->flags; + t->parms.hop_limit = p->hop_limit; + t->parms.encap_limit = p->encap_limit; + t->parms.flowinfo = p->flowinfo; + t->parms.link = p->link; + t->parms.proto = p->proto; + t->parms.i_key = p->i_key; + t->parms.o_key = p->o_key; + t->parms.i_flags = p->i_flags; + t->parms.o_flags = p->o_flags; + ip6_tnl_dst_reset(t); + ip6gre_tnl_link_config(t, set_mtu); + return 0; +} + +static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, + const struct ip6_tnl_parm2 *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->flags = u->flags; + p->hop_limit = u->hop_limit; + p->encap_limit = u->encap_limit; + p->flowinfo = u->flowinfo; + p->link = u->link; + p->i_key = u->i_key; + p->o_key = u->o_key; + p->i_flags = u->i_flags; + p->o_flags = u->o_flags; + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void ip6gre_tnl_parm_to_user(struct ip6_tnl_parm2 *u, + const struct __ip6_tnl_parm *p) +{ + u->proto = IPPROTO_GRE; + u->laddr = p->laddr; + u->raddr = p->raddr; + u->flags = p->flags; + u->hop_limit = p->hop_limit; + u->encap_limit = p->encap_limit; + u->flowinfo = p->flowinfo; + u->link = p->link; + u->i_key = p->i_key; + u->o_key = p->o_key; + u->i_flags = p->i_flags; + u->o_flags = p->o_flags; + memcpy(u->name, p->name, sizeof(u->name)); +} + +static int ip6gre_tunnel_ioctl(struct net_device *dev, + struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip6_tnl_parm2 p; + struct __ip6_tnl_parm p1; + struct ip6_tnl *t; + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + t = NULL; + if (dev == ign->fb_tunnel_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + err = -EFAULT; + break; + } + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, 0); + } + if (t == NULL) + t = netdev_priv(dev); + ip6gre_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + + err = -EINVAL; + if ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)) + goto done; + + if (!(p.i_flags&GRE_KEY)) + p.i_key = 0; + if (!(p.o_flags&GRE_KEY)) + p.o_key = 0; + + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL); + + if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else { + t = netdev_priv(dev); + + ip6gre_tunnel_unlink(ign, t); + synchronize_net(); + ip6gre_tnl_change(t, &p1, 1); + ip6gre_tunnel_link(ign, t); + netdev_state_change(dev); + } + } + + if (t) { + err = 0; + + ip6gre_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + + case SIOCDELTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + if (dev == ign->fb_tunnel_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + err = -ENOENT; + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, 0); + if (t == NULL) + goto done; + err = -EPERM; + if (t == netdev_priv(ign->fb_tunnel_dev)) + goto done; + dev = t->dev; + } + unregister_netdevice(dev); + err = 0; + break; + + default: + err = -EINVAL; + } + +done: + return err; +} + +static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + if (new_mtu < 68 || + new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + const void *daddr, const void *saddr, unsigned int len) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); + __be16 *p = (__be16 *)(ipv6h+1); + + *(__be32 *)ipv6h = t->fl.u.ip6.flowlabel | htonl(0x60000000); + ipv6h->hop_limit = t->parms.hop_limit; + ipv6h->nexthdr = NEXTHDR_GRE; + ipv6h->saddr = t->parms.laddr; + ipv6h->daddr = t->parms.raddr; + + p[0] = t->parms.o_flags; + p[1] = htons(type); + + /* + * Set the source hardware address. + */ + + if (saddr) + memcpy(&ipv6h->saddr, saddr, sizeof(struct in6_addr)); + if (daddr) + memcpy(&ipv6h->daddr, daddr, sizeof(struct in6_addr)); + if (!ipv6_addr_any(&ipv6h->daddr)) + return t->hlen; + + return -t->hlen; +} + +static const struct header_ops ip6gre_header_ops = { + .create = ip6gre_header, +}; + +static const struct net_device_ops ip6gre_netdev_ops = { + .ndo_init = ip6gre_tunnel_init, + .ndo_uninit = ip6gre_tunnel_uninit, + .ndo_start_xmit = ip6gre_tunnel_xmit, + .ndo_do_ioctl = ip6gre_tunnel_ioctl, + .ndo_change_mtu = ip6gre_tunnel_change_mtu, + .ndo_get_stats64 = ip6gre_get_stats64, +}; + +static void ip6gre_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static void ip6gre_tunnel_setup(struct net_device *dev) +{ + struct ip6_tnl *t; + + dev->netdev_ops = &ip6gre_netdev_ops; + dev->destructor = ip6gre_dev_free; + + dev->type = ARPHRD_IP6GRE; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr) + 4; + dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr) - 4; + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu -= 8; + dev->flags |= IFF_NOARP; + dev->iflink = 0; + dev->addr_len = sizeof(struct in6_addr); + dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +static int ip6gre_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + + tunnel = netdev_priv(dev); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); + + if (ipv6_addr_any(&tunnel->parms.raddr)) + dev->header_ops = &ip6gre_header_ops; + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; +} + +static void ip6gre_fb_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + tunnel->hlen = sizeof(struct ipv6hdr) + 4; + + dev_hold(dev); +} + + +static struct inet6_protocol ip6gre_protocol __read_mostly = { + .handler = ip6gre_rcv, + .err_handler = ip6gre_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static void ip6gre_destroy_tunnels(struct ip6gre_net *ign, + struct list_head *head) +{ + int prio; + + for (prio = 0; prio < 4; prio++) { + int h; + for (h = 0; h < HASH_SIZE; h++) { + struct ip6_tnl *t; + + t = rtnl_dereference(ign->tunnels[prio][h]); + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = rtnl_dereference(t->next); + } + } + } +} + +static int __net_init ip6gre_init_net(struct net *net) +{ + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int err; + + ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + ip6gre_tunnel_setup); + if (!ign->fb_tunnel_dev) { + err = -ENOMEM; + goto err_alloc_dev; + } + dev_net_set(ign->fb_tunnel_dev, net); + + ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); + ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; + + err = register_netdev(ign->fb_tunnel_dev); + if (err) + goto err_reg_dev; + + rcu_assign_pointer(ign->tunnels_wc[0], + netdev_priv(ign->fb_tunnel_dev)); + return 0; + +err_reg_dev: + ip6gre_dev_free(ign->fb_tunnel_dev); +err_alloc_dev: + return err; +} + +static void __net_exit ip6gre_exit_net(struct net *net) +{ + struct ip6gre_net *ign; + LIST_HEAD(list); + + ign = net_generic(net, ip6gre_net_id); + rtnl_lock(); + ip6gre_destroy_tunnels(ign, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations ip6gre_net_ops = { + .init = ip6gre_init_net, + .exit = ip6gre_exit_net, + .id = &ip6gre_net_id, + .size = sizeof(struct ip6gre_net), +}; + +static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + __be16 flags; + + if (!data) + return 0; + + flags = 0; + if (data[IFLA_GRE_IFLAGS]) + flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); + if (data[IFLA_GRE_OFLAGS]) + flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); + if (flags & (GRE_VERSION|GRE_ROUTING)) + return -EINVAL; + + return 0; +} + +static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + struct in6_addr daddr; + + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + + if (!data) + goto out; + + if (data[IFLA_GRE_REMOTE]) { + nla_memcpy(&daddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + if (ipv6_addr_any(&daddr)) + return -EINVAL; + } + +out: + return ip6gre_tunnel_validate(tb, data); +} + + +static void ip6gre_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_GRE_LINK]) + parms->link = nla_get_u32(data[IFLA_GRE_LINK]); + + if (data[IFLA_GRE_IFLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]); + + if (data[IFLA_GRE_OFLAGS]) + parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]); + + if (data[IFLA_GRE_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); + + if (data[IFLA_GRE_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); + + if (data[IFLA_GRE_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_GRE_LOCAL], sizeof(struct in6_addr)); + + if (data[IFLA_GRE_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + + if (data[IFLA_GRE_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]); + + if (data[IFLA_GRE_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]); + + if (data[IFLA_GRE_FLOWINFO]) + parms->flowinfo = nla_get_u32(data[IFLA_GRE_FLOWINFO]); + + if (data[IFLA_GRE_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]); +} + +static int ip6gre_tap_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + + tunnel = netdev_priv(dev); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + ip6gre_tnl_link_config(tunnel, 1); + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; +} + +static const struct net_device_ops ip6gre_tap_netdev_ops = { + .ndo_init = ip6gre_tap_init, + .ndo_uninit = ip6gre_tunnel_uninit, + .ndo_start_xmit = ip6gre_tunnel_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ip6gre_tunnel_change_mtu, + .ndo_get_stats64 = ip6gre_get_stats64, +}; + +static void ip6gre_tap_setup(struct net_device *dev) +{ + + ether_setup(dev); + + dev->netdev_ops = &ip6gre_tap_netdev_ops; + dev->destructor = ip6gre_dev_free; + + dev->iflink = 0; + dev->features |= NETIF_F_NETNS_LOCAL; +} + +static int ip6gre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct ip6_tnl *nt; + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int err; + + nt = netdev_priv(dev); + ip6gre_netlink_parms(data, &nt->parms); + + if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) + return -EEXIST; + + if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) + eth_hw_addr_random(dev); + + nt->dev = dev; + ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); + + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + + err = register_netdevice(dev); + if (err) + goto out; + + dev_hold(dev); + ip6gre_tunnel_link(ign, nt); + +out: + return err; +} + +static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t, *nt; + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct __ip6_tnl_parm p; + + if (dev == ign->fb_tunnel_dev) + return -EINVAL; + + nt = netdev_priv(dev); + ip6gre_netlink_parms(data, &p); + + t = ip6gre_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else { + t = nt; + + ip6gre_tunnel_unlink(ign, t); + ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link(ign, t); + netdev_state_change(dev); + } + + return 0; +} + +static size_t ip6gre_get_size(const struct net_device *dev) +{ + return + /* IFLA_GRE_LINK */ + nla_total_size(4) + + /* IFLA_GRE_IFLAGS */ + nla_total_size(2) + + /* IFLA_GRE_OFLAGS */ + nla_total_size(2) + + /* IFLA_GRE_IKEY */ + nla_total_size(4) + + /* IFLA_GRE_OKEY */ + nla_total_size(4) + + /* IFLA_GRE_LOCAL */ + nla_total_size(4) + + /* IFLA_GRE_REMOTE */ + nla_total_size(4) + + /* IFLA_GRE_TTL */ + nla_total_size(1) + + /* IFLA_GRE_TOS */ + nla_total_size(1) + + /* IFLA_GRE_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_GRE_FLOWINFO */ + nla_total_size(4) + + /* IFLA_GRE_FLAGS */ + nla_total_size(4) + + 0; +} + +static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct __ip6_tnl_parm *p = &t->parms; + + if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || + nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) || + nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || + nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || + nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || + /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ + nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || + nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || + nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { + [IFLA_GRE_LINK] = { .type = NLA_U32 }, + [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, + [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, + [IFLA_GRE_IKEY] = { .type = NLA_U32 }, + [IFLA_GRE_OKEY] = { .type = NLA_U32 }, + [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_TTL] = { .type = NLA_U8 }, + [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_GRE_FLAGS] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { + .kind = "ip6gre", + .maxtype = IFLA_GRE_MAX, + .policy = ip6gre_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6gre_tunnel_setup, + .validate = ip6gre_tunnel_validate, + .newlink = ip6gre_newlink, + .changelink = ip6gre_changelink, + .get_size = ip6gre_get_size, + .fill_info = ip6gre_fill_info, +}; + +static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = { + .kind = "ip6gretap", + .maxtype = IFLA_GRE_MAX, + .policy = ip6gre_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6gre_tap_setup, + .validate = ip6gre_tap_validate, + .newlink = ip6gre_newlink, + .changelink = ip6gre_changelink, + .get_size = ip6gre_get_size, + .fill_info = ip6gre_fill_info, +}; + +/* + * And now the modules code and kernel interface. + */ + +static int __init ip6gre_init(void) +{ + int err; + + pr_info("GRE over IPv6 tunneling driver\n"); + + err = register_pernet_device(&ip6gre_net_ops); + if (err < 0) + return err; + + err = inet6_add_protocol(&ip6gre_protocol, IPPROTO_GRE); + if (err < 0) { + pr_info("%s: can't add protocol\n", __func__); + goto add_proto_failed; + } + + err = rtnl_link_register(&ip6gre_link_ops); + if (err < 0) + goto rtnl_link_failed; + + err = rtnl_link_register(&ip6gre_tap_ops); + if (err < 0) + goto tap_ops_failed; + +out: + return err; + +tap_ops_failed: + rtnl_link_unregister(&ip6gre_link_ops); +rtnl_link_failed: + inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); +add_proto_failed: + unregister_pernet_device(&ip6gre_net_ops); + goto out; +} + +static void __exit ip6gre_fini(void) +{ + rtnl_link_unregister(&ip6gre_tap_ops); + rtnl_link_unregister(&ip6gre_link_ops); + inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); + unregister_pernet_device(&ip6gre_net_ops); +} + +module_init(ip6gre_init); +module_exit(ip6gre_fini); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); +MODULE_DESCRIPTION("GRE over IPv6 tunneling device"); +MODULE_ALIAS_RTNL_LINK("ip6gre"); +MODULE_ALIAS_NETDEV("ip6gre0"); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 5ab923e51af3..a52d864d562b 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,9 +47,16 @@ -inline int ip6_rcv_finish( struct sk_buff *skb) +int ip6_rcv_finish(struct sk_buff *skb) { - if (skb_dst(skb) == NULL) + if (sysctl_ip_early_demux && !skb_dst(skb)) { + const struct inet6_protocol *ipprot; + + ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); + if (ipprot && ipprot->early_demux) + ipprot->early_demux(skb); + } + if (!skb_dst(skb)) ip6_route_input(skb); return dst_input(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5b2d63ed793e..aece3e792f84 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -123,16 +123,11 @@ static int ip6_finish_output2(struct sk_buff *skb) skb->len); } - rcu_read_lock(); rt = (struct rt6_info *) dst; neigh = rt->n; - if (neigh) { - int res = dst_neigh_output(dst, neigh, skb); + if (neigh) + return dst_neigh_output(dst, neigh, skb); - rcu_read_unlock(); - return res; - } - rcu_read_unlock(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); @@ -493,7 +488,8 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb->len > mtu && !skb_is_gso(skb)) { + if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || + (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); @@ -636,7 +632,9 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (unlikely(!skb->local_df && skb->len > mtu)) { + if (unlikely(!skb->local_df && skb->len > mtu) || + (IP6CB(skb)->frag_max_size && + IP6CB(skb)->frag_max_size > mtu)) { if (skb->sk && dst_allfrag(skb_dst(skb))) sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); @@ -980,7 +978,6 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ - rcu_read_lock(); rt = (struct rt6_info *) *dst; n = rt->n; if (n && !(n->nud_state & NUD_VALID)) { @@ -988,7 +985,6 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct flowi6 fl_gw6; int redirect; - rcu_read_unlock(); ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); @@ -1008,8 +1004,6 @@ static int ip6_dst_lookup_tail(struct sock *sk, if ((err = (*dst)->error)) goto out_err_release; } - } else { - rcu_read_unlock(); } #endif @@ -1285,8 +1279,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; length += exthdrlen; transhdrlen += exthdrlen; @@ -1510,48 +1502,31 @@ alloc_new_skb: } } else { int i = skb_shinfo(skb)->nr_frags; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1]; - struct page *page = sk->sk_sndmsg_page; - int off = sk->sk_sndmsg_off; - unsigned int left; - - if (page && (left = PAGE_SIZE - off) > 0) { - if (copy >= left) - copy = left; - if (page != skb_frag_page(frag)) { - if (i == MAX_SKB_FRAGS) { - err = -EMSGSIZE; - goto error; - } - skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); - skb_frag_ref(skb, i); - frag = &skb_shinfo(skb)->frags[i]; - } - } else if(i < MAX_SKB_FRAGS) { - if (copy > PAGE_SIZE) - copy = PAGE_SIZE; - page = alloc_pages(sk->sk_allocation, 0); - if (page == NULL) { - err = -ENOMEM; - goto error; - } - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; + struct page_frag *pfrag = sk_page_frag(sk); - skb_fill_page_desc(skb, i, page, 0, 0); - frag = &skb_shinfo(skb)->frags[i]; - } else { - err = -EMSGSIZE; + err = -ENOMEM; + if (!sk_page_frag_refill(sk, pfrag)) goto error; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + err = -EMSGSIZE; + if (i == MAX_SKB_FRAGS) + goto error; + + __skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, 0); + skb_shinfo(skb)->nr_frags = ++i; + get_page(pfrag->page); } + copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, - skb_frag_address(frag) + skb_frag_size(frag), - offset, copy, skb->len, skb) < 0) { - err = -EFAULT; - goto error; - } - sk->sk_sndmsg_off += copy; - skb_frag_size_add(frag, copy); + page_address(pfrag->page) + pfrag->offset, + offset, copy, skb->len, skb) < 0) + goto error_efault; + + pfrag->offset += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -1560,7 +1535,11 @@ alloc_new_skb: offset += copy; length -= copy; } + return 0; + +error_efault: + err = -EFAULT; error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9a1d5fe6aef8..cb7e2ded6f08 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,7 +126,7 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) +struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { struct dst_entry *dst = t->dst_cache; @@ -139,20 +139,23 @@ static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) return dst; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_check); -static inline void ip6_tnl_dst_reset(struct ip6_tnl *t) +void ip6_tnl_dst_reset(struct ip6_tnl *t) { dst_release(t->dst_cache); t->dst_cache = NULL; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); -static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) +void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; dst_release(t->dst_cache); t->dst_cache = dst; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_store); /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses @@ -200,7 +203,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_ **/ static struct ip6_tnl __rcu ** -ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p) +ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; @@ -267,7 +270,7 @@ static void ip6_dev_free(struct net_device *dev) * created tunnel or NULL **/ -static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) +static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; @@ -322,7 +325,7 @@ failed: **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, - struct ip6_tnl_parm *p, int create) + struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; @@ -374,8 +377,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) * else index to encapsulation limit **/ -static __u16 -parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) +__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; __u8 nexthdr = ipv6h->nexthdr; @@ -425,6 +427,7 @@ parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) } return 0; } +EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /** * ip6_tnl_err - tunnel error handler @@ -480,7 +483,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, case ICMPV6_PARAMPROB: teli = 0; if ((*code) == ICMPV6_HDR_FIELD) - teli = parse_tlv_tnl_enc_lim(skb, skb->data); + teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; @@ -693,11 +696,11 @@ static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, IP6_ECN_set_ce(ipv6_hdr(skb)); } -static __u32 ip6_tnl_get_cap(struct ip6_tnl *t, +__u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { - struct ip6_tnl_parm *p = &t->parms; + struct __ip6_tnl_parm *p = &t->parms; int ltype = ipv6_addr_type(laddr); int rtype = ipv6_addr_type(raddr); __u32 flags = 0; @@ -715,13 +718,14 @@ static __u32 ip6_tnl_get_cap(struct ip6_tnl *t, } return flags; } +EXPORT_SYMBOL(ip6_tnl_get_cap); /* called with rcu_read_lock() */ -static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t, +int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { - struct ip6_tnl_parm *p = &t->parms; + struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = dev_net(t->dev); @@ -740,6 +744,7 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t, } return ret; } +EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); /** * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally @@ -859,9 +864,9 @@ ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } -static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) +int ip6_tnl_xmit_ctl(struct ip6_tnl *t) { - struct ip6_tnl_parm *p = &t->parms; + struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = dev_net(t->dev); @@ -885,6 +890,8 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) } return ret; } +EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); + /** * ip6_tnl_xmit2 - encapsulate packet and send * @skb: the outgoing socket buffer @@ -1085,7 +1092,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h)) return -1; - offset = parse_tlv_tnl_enc_lim(skb, skb_network_header(skb)); + offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; @@ -1152,7 +1159,7 @@ tx_err: static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; - struct ip6_tnl_parm *p = &t->parms; + struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); @@ -1215,7 +1222,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) **/ static int -ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) +ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; @@ -1230,6 +1237,34 @@ ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) return 0; } +static void +ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->flags = u->flags; + p->hop_limit = u->hop_limit; + p->encap_limit = u->encap_limit; + p->flowinfo = u->flowinfo; + p->link = u->link; + p->proto = u->proto; + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void +ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) +{ + u->laddr = p->laddr; + u->raddr = p->raddr; + u->flags = p->flags; + u->hop_limit = p->hop_limit; + u->encap_limit = p->encap_limit; + u->flowinfo = p->flowinfo; + u->link = p->link; + u->proto = p->proto; + memcpy(u->name, p->name, sizeof(u->name)); +} + /** * ip6_tnl_ioctl - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel @@ -1263,6 +1298,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip6_tnl_parm p; + struct __ip6_tnl_parm p1; struct ip6_tnl *t = NULL; struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -1274,11 +1310,14 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) err = -EFAULT; break; } - t = ip6_tnl_locate(net, &p, 0); + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, 0); + } else { + memset(&p, 0, sizeof(p)); } if (t == NULL) t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof (p)); + ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) { err = -EFAULT; } @@ -1295,7 +1334,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && p.proto != 0) break; - t = ip6_tnl_locate(net, &p, cmd == SIOCADDTUNNEL); + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { if (t->dev != dev) { @@ -1307,13 +1347,14 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ip6_tnl_unlink(ip6n, t); synchronize_net(); - err = ip6_tnl_change(t, &p); + err = ip6_tnl_change(t, &p1); ip6_tnl_link(ip6n, t); netdev_state_change(dev); } if (t) { err = 0; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof (p))) + ip6_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; } else @@ -1329,7 +1370,9 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) break; err = -ENOENT; - if ((t = ip6_tnl_locate(net, &p, 0)) == NULL) + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, 0); + if (t == NULL) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 4532973f0dd4..08ea3f0b6e55 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -838,7 +838,7 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT; - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else kfree_skb(skb); } @@ -1052,7 +1052,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else ip6_mr_forward(net, mrt, skb, c); } @@ -2202,12 +2202,12 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 pid, u32 seq, struct mfc6_cache *c) + u32 portid, u32 seq, struct mfc6_cache *c) { struct nlmsghdr *nlh; struct rtmsg *rtm; - nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; @@ -2260,7 +2260,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (e < s_e) goto next_entry; if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc) < 0) goto done; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 5b087c31d87b..0f9bdc5ee9f3 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -86,28 +86,30 @@ static int mip6_mh_len(int type) static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) { - struct ip6_mh *mh; + struct ip6_mh _hdr; + const struct ip6_mh *mh; - if (!pskb_may_pull(skb, (skb_transport_offset(skb)) + 8) || - !pskb_may_pull(skb, (skb_transport_offset(skb) + - ((skb_transport_header(skb)[1] + 1) << 3)))) + mh = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (!mh) return -1; - mh = (struct ip6_mh *)skb_transport_header(skb); + if (((mh->ip6mh_hdrlen + 1) << 3) > skb->len) + return -1; if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) { LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n", mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type)); - mip6_param_prob(skb, 0, ((&mh->ip6mh_hdrlen) - - skb_network_header(skb))); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) + + skb_network_header_len(skb)); return -1; } if (mh->ip6mh_proto != IPPROTO_NONE) { LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n", mh->ip6mh_proto); - mip6_param_prob(skb, 0, ((&mh->ip6mh_proto) - - skb_network_header(skb))); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) + + skb_network_header_len(skb)); return -1; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index db31561cc8df..429089cb073d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -15,6 +15,7 @@ int ip6_route_me_harder(struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); const struct ipv6hdr *iph = ipv6_hdr(skb); + unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, @@ -47,6 +48,13 @@ int ip6_route_me_harder(struct sk_buff *skb) } #endif + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -1; + return 0; } EXPORT_SYMBOL(ip6_route_me_harder); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 10135342799e..c72532a60d88 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -181,9 +181,44 @@ config IP6_NF_SECURITY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. - + If unsure, say N. +config NF_NAT_IPV6 + tristate "IPv6 NAT" + depends on NF_CONNTRACK_IPV6 + depends on NETFILTER_ADVANCED + select NF_NAT + help + The IPv6 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. It is controlled by + the `nat' table in ip6tables, see the man page for ip6tables(8). + + To compile it as a module, choose M here. If unsure, say N. + +if NF_NAT_IPV6 + +config IP6_NF_TARGET_MASQUERADE + tristate "MASQUERADE target support" + help + Masquerading is a special case of NAT: all outgoing connections are + changed to seem to come from a particular interface's address, and + if the interface goes down, those connections are lost. This is + only useful for dialup accounts with dynamic IP address (ie. your IP + address will be different on next dialup). + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_TARGET_NPT + tristate "NPT (Network Prefix translation) target support" + help + This option adds the `SNPT' and `DNPT' target, which perform + stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296. + + To compile it as a module, choose M here. If unsure, say N. + +endif # NF_NAT_IPV6 + endif # IP6_NF_IPTABLES endmenu diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 534d3f216f7b..2d11fcc2cf3c 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o +obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o # objects for l3 independent conntrack nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o @@ -15,6 +16,9 @@ nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o # l3 independent conntrack obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o +nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o +obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o + # defrag nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o @@ -30,4 +34,6 @@ obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets +obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o +obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c new file mode 100644 index 000000000000..60e9053bab05 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -0,0 +1,135 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_nat.h> +#include <net/addrconf.h> +#include <net/ipv6.h> + +static unsigned int +masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct in6_addr src; + struct nf_conn *ct; + struct nf_nat_range newrange; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + if (ipv6_dev_get_saddr(dev_net(par->out), par->out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) + return NF_DROP; + + nfct_nat(ct)->masq_index = par->out->ifindex; + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = src; + newrange.max_addr.in6 = src; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); +} + +static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) + return -EINVAL; + return 0; +} + +static int device_cmp(struct nf_conn *ct, void *ifindex) +{ + const struct nf_conn_nat *nat = nfct_nat(ct); + + if (!nat) + return 0; + if (nf_ct_l3num(ct) != NFPROTO_IPV6) + return 0; + return nat->masq_index == (int)(long)ifindex; +} + +static int masq_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + const struct net_device *dev = ptr; + struct net *net = dev_net(dev); + + if (event == NETDEV_DOWN) + nf_ct_iterate_cleanup(net, device_cmp, + (void *)(long)dev->ifindex); + + return NOTIFY_DONE; +} + +static struct notifier_block masq_dev_notifier = { + .notifier_call = masq_device_event, +}; + +static int masq_inet_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + + return masq_device_event(this, event, ifa->idev->dev); +} + +static struct notifier_block masq_inet_notifier = { + .notifier_call = masq_inet_event, +}; + +static struct xt_target masquerade_tg6_reg __read_mostly = { + .name = "MASQUERADE", + .family = NFPROTO_IPV6, + .checkentry = masquerade_tg6_checkentry, + .target = masquerade_tg6, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = 1 << NF_INET_POST_ROUTING, + .me = THIS_MODULE, +}; + +static int __init masquerade_tg6_init(void) +{ + int err; + + err = xt_register_target(&masquerade_tg6_reg); + if (err == 0) { + register_netdevice_notifier(&masq_dev_notifier); + register_inet6addr_notifier(&masq_inet_notifier); + } + + return err; +} +static void __exit masquerade_tg6_exit(void) +{ + unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_netdevice_notifier(&masq_dev_notifier); + xt_unregister_target(&masquerade_tg6_reg); +} + +module_init(masquerade_tg6_init); +module_exit(masquerade_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Xtables: automatic address SNAT"); diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c new file mode 100644 index 000000000000..e9486915eff6 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -0,0 +1,165 @@ +/* + * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6t_NPT.h> +#include <linux/netfilter/x_tables.h> + +static __sum16 csum16_complement(__sum16 a) +{ + return (__force __sum16)(0xffff - (__force u16)a); +} + +static __sum16 csum16_add(__sum16 a, __sum16 b) +{ + u16 sum; + + sum = (__force u16)a + (__force u16)b; + sum += (__force u16)a < (__force u16)b; + return (__force __sum16)sum; +} + +static __sum16 csum16_sub(__sum16 a, __sum16 b) +{ + return csum16_add(a, csum16_complement(b)); +} + +static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) +{ + struct ip6t_npt_tginfo *npt = par->targinfo; + __sum16 src_sum = 0, dst_sum = 0; + unsigned int i; + + if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) { + src_sum = csum16_add(src_sum, + (__force __sum16)npt->src_pfx.in6.s6_addr16[i]); + dst_sum = csum16_add(dst_sum, + (__force __sum16)npt->dst_pfx.in6.s6_addr16[i]); + } + + npt->adjustment = csum16_sub(src_sum, dst_sum); + return 0; +} + +static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, + struct in6_addr *addr) +{ + unsigned int pfx_len; + unsigned int i, idx; + __be32 mask; + __sum16 sum; + + pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len); + for (i = 0; i < pfx_len; i += 32) { + if (pfx_len - i >= 32) + mask = 0; + else + mask = htonl(~((1 << (pfx_len - i)) - 1)); + + idx = i / 32; + addr->s6_addr32[idx] &= mask; + addr->s6_addr32[idx] |= npt->dst_pfx.in6.s6_addr32[idx]; + } + + if (pfx_len <= 48) + idx = 3; + else { + for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) { + if ((__force __sum16)addr->s6_addr16[idx] != + CSUM_MANGLED_0) + break; + } + if (idx == ARRAY_SIZE(addr->s6_addr16)) + return false; + } + + sum = csum16_add((__force __sum16)addr->s6_addr16[idx], + npt->adjustment); + if (sum == CSUM_MANGLED_0) + sum = 0; + *(__force __sum16 *)&addr->s6_addr16[idx] = sum; + + return true; +} + +static unsigned int +ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, saddr)); + return NF_DROP; + } + return XT_CONTINUE; +} + +static unsigned int +ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, daddr)); + return NF_DROP; + } + return XT_CONTINUE; +} + +static struct xt_target ip6t_npt_target_reg[] __read_mostly = { + { + .name = "SNPT", + .target = ip6t_snpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, + }, + { + .name = "DNPT", + .target = ip6t_dnpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init ip6t_npt_init(void) +{ + return xt_register_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +static void __exit ip6t_npt_exit(void) +{ + xt_unregister_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +module_init(ip6t_npt_init); +module_exit(ip6t_npt_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS("ip6t_SNPT"); +MODULE_ALIAS("ip6t_DNPT"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 325e59a0224f..beb5777d2043 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -61,9 +61,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) net->ipv6.ip6table_filter = ip6t_register_table(net, &packet_filter, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_filter)) - return PTR_ERR(net->ipv6.ip6table_filter); - return 0; + return PTR_RET(net->ipv6.ip6table_filter); } static void __net_exit ip6table_filter_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 4d782405f125..7431121b87de 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -97,9 +97,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net) net->ipv6.ip6table_mangle = ip6t_register_table(net, &packet_mangler, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_mangle)) - return PTR_ERR(net->ipv6.ip6table_mangle); - return 0; + return PTR_RET(net->ipv6.ip6table_mangle); } static void __net_exit ip6table_mangle_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c new file mode 100644 index 000000000000..e418bd6350a4 --- /dev/null +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -0,0 +1,321 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT + * funded by Astaro. + */ + +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> + +static const struct xt_table nf_nat_ipv6_table = { + .name = "nat", + .valid_hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + .af = NFPROTO_IPV6, +}; + +static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + /* Force range to this IP; let proto decide mapping for + * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). + */ + struct nf_nat_range range; + + range.flags = 0; + pr_debug("Allocating NULL binding for %p (%pI6)\n", ct, + HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 : + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6); + + return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); +} + +static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct) +{ + struct net *net = nf_ct_net(ct); + unsigned int ret; + + ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat); + if (ret == NF_ACCEPT) { + if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) + ret = alloc_null_binding(ct, hooknum); + } + return ret; +} + +static unsigned int +nf_nat_ipv6_fn(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + __be16 frag_off; + int hdrlen; + u8 nexthdr; + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; + + /* Don't try to NAT if this packet is not conntracked */ + if (nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nfct_nat(ct); + if (!nat) { + /* NAT module was loaded late. */ + if (nf_ct_is_confirmed(ct)) + return NF_ACCEPT; + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + hooknum, hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + unsigned int ret; + + ret = nf_nat_rule_find(skb, hooknum, in, out, ct); + if (ret != NF_ACCEPT) + return ret; + } else + pr_debug("Already setup manip %s for ct %p\n", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", + ct); + break; + + default: + /* ESTABLISHED */ + NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || + ctinfo == IP_CT_ESTABLISHED_REPLY); + } + + return nf_nat_packet(ct, ctinfo, hooknum, skb); +} + +static unsigned int +nf_nat_ipv6_in(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + + ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int +nf_nat_ipv6_out(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; +#endif + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) + if (nf_xfrm_me_harder(skb, AF_INET6) < 0) + ret = NF_DROP; + } +#endif + return ret; +} + +static unsigned int +nf_nat_ipv6_local_fn(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + if (ip6_route_me_harder(skb)) + ret = NF_DROP; + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) + if (nf_xfrm_me_harder(skb, AF_INET6)) + ret = NF_DROP; +#endif + } + return ret; +} + +static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_out, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_local_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_NAT_SRC, + }, +}; + +static int __net_init ip6table_nat_net_init(struct net *net) +{ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); + if (repl == NULL) + 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; +} + +static void __net_exit ip6table_nat_net_exit(struct net *net) +{ + ip6t_unregister_table(net, net->ipv6.ip6table_nat); +} + +static struct pernet_operations ip6table_nat_net_ops = { + .init = ip6table_nat_net_init, + .exit = ip6table_nat_net_exit, +}; + +static int __init ip6table_nat_init(void) +{ + int err; + + err = register_pernet_subsys(&ip6table_nat_net_ops); + if (err < 0) + goto err1; + + err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); + if (err < 0) + goto err2; + return 0; + +err2: + unregister_pernet_subsys(&ip6table_nat_net_ops); +err1: + return err; +} + +static void __exit ip6table_nat_exit(void) +{ + nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); + unregister_pernet_subsys(&ip6table_nat_net_ops); +} + +module_init(ip6table_nat_init); +module_exit(ip6table_nat_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 5b9926a011bd..60d1bddff7a0 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -40,9 +40,7 @@ static int __net_init ip6table_raw_net_init(struct net *net) net->ipv6.ip6table_raw = ip6t_register_table(net, &packet_raw, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_raw)) - return PTR_ERR(net->ipv6.ip6table_raw); - return 0; + return PTR_RET(net->ipv6.ip6table_raw); } static void __net_exit ip6table_raw_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 91aa2b4d83c9..db155351339c 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -58,10 +58,7 @@ static int __net_init ip6table_security_net_init(struct net *net) net->ipv6.ip6table_security = ip6t_register_table(net, &security_table, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_security)) - return PTR_ERR(net->ipv6.ip6table_security); - - return 0; + return PTR_RET(net->ipv6.ip6table_security); } static void __net_exit ip6table_security_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 4794f96cf2e0..8860d23e61cf 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -28,6 +28,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_log.h> @@ -64,82 +65,31 @@ static int ipv6_print_tuple(struct seq_file *s, tuple->src.u3.ip6, tuple->dst.u3.ip6); } -/* - * Based on ipv6_skip_exthdr() in net/ipv6/exthdr.c - * - * This function parses (probably truncated) exthdr set "hdr" - * of length "len". "nexthdrp" initially points to some place, - * where type of the first header can be found. - * - * It skips all well-known exthdrs, and returns pointer to the start - * of unparsable area i.e. the first header with unknown type. - * if success, *nexthdr is updated by type/protocol of this header. - * - * NOTES: - it may return pointer pointing beyond end of packet, - * if the last recognized header is truncated in the middle. - * - if packet is truncated, so that all parsed headers are skipped, - * it returns -1. - * - if packet is fragmented, return pointer of the fragment header. - * - ESP is unparsable for now and considered like - * normal payload protocol. - * - Note also special handling of AUTH header. Thanks to IPsec wizards. - */ - -static int nf_ct_ipv6_skip_exthdr(const struct sk_buff *skb, int start, - u8 *nexthdrp, int len) -{ - u8 nexthdr = *nexthdrp; - - while (ipv6_ext_hdr(nexthdr)) { - struct ipv6_opt_hdr hdr; - int hdrlen; - - if (len < (int)sizeof(struct ipv6_opt_hdr)) - return -1; - if (nexthdr == NEXTHDR_NONE) - break; - if (nexthdr == NEXTHDR_FRAGMENT) - break; - if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) - BUG(); - if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hdr.hdrlen+2)<<2; - else - hdrlen = ipv6_optlen(&hdr); - - nexthdr = hdr.nexthdr; - len -= hdrlen; - start += hdrlen; - } - - *nexthdrp = nexthdr; - return start; -} - static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, unsigned int *dataoff, u_int8_t *protonum) { unsigned int extoff = nhoff + sizeof(struct ipv6hdr); - unsigned char pnum; + __be16 frag_off; int protoff; + u8 nexthdr; if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr), - &pnum, sizeof(pnum)) != 0) { + &nexthdr, sizeof(nexthdr)) != 0) { pr_debug("ip6_conntrack_core: can't get nexthdr\n"); return -NF_ACCEPT; } - protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff); + protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); /* * (protoff == skb->len) mean that the packet doesn't have no data * except of IPv6 & ext headers. but it's tracked anyway. - YK */ - if ((protoff < 0) || (protoff > skb->len)) { + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); return -NF_ACCEPT; } *dataoff = protoff; - *protonum = pnum; + *protonum = nexthdr; return NF_ACCEPT; } @@ -153,10 +103,10 @@ static unsigned int ipv6_helper(unsigned int hooknum, const struct nf_conn_help *help; const struct nf_conntrack_helper *helper; enum ip_conntrack_info ctinfo; - unsigned int ret, protoff; - unsigned int extoff = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; - unsigned char pnum = ipv6_hdr(skb)->nexthdr; - + unsigned int ret; + __be16 frag_off; + int protoff; + u8 nexthdr; /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); @@ -171,9 +121,10 @@ static unsigned int ipv6_helper(unsigned int hooknum, if (!helper) return NF_ACCEPT; - protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, - skb->len - extoff); - if (protoff > skb->len || pnum == NEXTHDR_FRAGMENT) { + nexthdr = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("proto header not found\n"); return NF_ACCEPT; } @@ -192,6 +143,36 @@ static unsigned int ipv6_confirm(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned char pnum = ipv6_hdr(skb)->nexthdr; + int protoff; + __be16 frag_off; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + goto out; + } + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + typeof(nf_nat_seq_adjust_hook) seq_adjust; + + seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); + if (!seq_adjust || + !seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } @@ -199,9 +180,14 @@ static unsigned int ipv6_confirm(unsigned int hooknum, static unsigned int __ipv6_conntrack_in(struct net *net, unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, int (*okfn)(struct sk_buff *)) { struct sk_buff *reasm = skb->nfct_reasm; + const struct nf_conn_help *help; + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; /* This packet is fragmented and has reassembled packet. */ if (reasm) { @@ -213,6 +199,25 @@ static unsigned int __ipv6_conntrack_in(struct net *net, if (ret != NF_ACCEPT) return ret; } + + /* Conntrack helpers need the entire reassembled packet in the + * POST_ROUTING hook. In case of unconfirmed connections NAT + * might reassign a helper, so the entire packet is also + * required. + */ + ct = nf_ct_get(reasm, &ctinfo); + if (ct != NULL && !nf_ct_is_untracked(ct)) { + help = nfct_help(ct); + if ((help && help->helper) || !nf_ct_is_confirmed(ct)) { + nf_conntrack_get_reasm(skb); + NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, + (struct net_device *)in, + (struct net_device *)out, + okfn, NF_IP6_PRI_CONNTRACK + 1); + return NF_DROP_ERR(-ECANCELED); + } + } + nf_conntrack_get(reasm->nfct); skb->nfct = reasm->nfct; skb->nfctinfo = reasm->nfctinfo; @@ -228,7 +233,7 @@ static unsigned int ipv6_conntrack_in(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, okfn); + return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); } static unsigned int ipv6_conntrack_local(unsigned int hooknum, @@ -242,7 +247,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn); + return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index c9c78c2e666b..18bd9bbbd1c6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -57,41 +57,27 @@ struct nf_ct_frag6_skb_cb #define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb*)((skb)->cb)) -struct nf_ct_frag6_queue -{ - struct inet_frag_queue q; - - __be32 id; /* fragment id */ - u32 user; - struct in6_addr saddr; - struct in6_addr daddr; - - unsigned int csum; - __u16 nhoffset; -}; - static struct inet_frags nf_frags; -static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", - .data = &nf_init_frags.timeout, + .data = &init_net.nf_frag.frags.timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_frag6_low_thresh", - .data = &nf_init_frags.low_thresh, + .data = &init_net.nf_frag.frags.low_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nf_conntrack_frag6_high_thresh", - .data = &nf_init_frags.high_thresh, + .data = &init_net.nf_frag.frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, @@ -99,68 +85,86 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { } }; -static struct ctl_table_header *nf_ct_frag6_sysctl_header; -#endif - -static unsigned int nf_hashfn(struct inet_frag_queue *q) +static int __net_init nf_ct_frag6_sysctl_register(struct net *net) { - const struct nf_ct_frag6_queue *nq; + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = nf_ct_frag6_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + table[0].data = &net->ipv6.frags.high_thresh; + table[1].data = &net->ipv6.frags.low_thresh; + table[2].data = &net->ipv6.frags.timeout; + } - nq = container_of(q, struct nf_ct_frag6_queue, q); - return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd); + hdr = register_net_sysctl(net, "net/netfilter", table); + if (hdr == NULL) + goto err_reg; + + net->nf_frag.sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; } -static void nf_skb_free(struct sk_buff *skb) +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { - if (NFCT_FRAG6_CB(skb)->orig) - kfree_skb(NFCT_FRAG6_CB(skb)->orig); -} + struct ctl_table *table; -/* Destruction primitives. */ + table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} -static __inline__ void fq_put(struct nf_ct_frag6_queue *fq) +#else +static int __net_init nf_ct_frag6_sysctl_register(struct net *net) { - inet_frag_put(&fq->q, &nf_frags); + return 0; } +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) +{ +} +#endif -/* Kill fq entry. It is not destroyed immediately, - * because caller (and someone more) holds reference count. - */ -static __inline__ void fq_kill(struct nf_ct_frag6_queue *fq) +static unsigned int nf_hashfn(struct inet_frag_queue *q) { - inet_frag_kill(&fq->q, &nf_frags); + const struct frag_queue *nq; + + nq = container_of(q, struct frag_queue, q); + return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd); } -static void nf_ct_frag6_evictor(void) +static void nf_skb_free(struct sk_buff *skb) { - local_bh_disable(); - inet_frag_evictor(&nf_init_frags, &nf_frags); - local_bh_enable(); + if (NFCT_FRAG6_CB(skb)->orig) + kfree_skb(NFCT_FRAG6_CB(skb)->orig); } static void nf_ct_frag6_expire(unsigned long data) { - struct nf_ct_frag6_queue *fq; - - fq = container_of((struct inet_frag_queue *)data, - struct nf_ct_frag6_queue, q); - - spin_lock(&fq->q.lock); + struct frag_queue *fq; + struct net *net; - if (fq->q.last_in & INET_FRAG_COMPLETE) - goto out; + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, nf_frag.frags); - fq_kill(fq); - -out: - spin_unlock(&fq->q.lock); - fq_put(fq); + ip6_expire_frag_queue(net, fq, &nf_frags); } /* Creation primitives. */ - -static __inline__ struct nf_ct_frag6_queue * -fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) +static inline struct frag_queue *fq_find(struct net *net, __be32 id, + u32 user, struct in6_addr *src, + struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -174,22 +178,23 @@ fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) read_lock_bh(&nf_frags.lock); hash = inet6_hash_frag(id, src, dst, nf_frags.rnd); - q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash); + q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); local_bh_enable(); if (q == NULL) goto oom; - return container_of(q, struct nf_ct_frag6_queue, q); + return container_of(q, struct frag_queue, q); oom: return NULL; } -static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, +static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { struct sk_buff *prev, *next; + unsigned int payload_len; int offset, end; if (fq->q.last_in & INET_FRAG_COMPLETE) { @@ -197,8 +202,10 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, goto err; } + payload_len = ntohs(ipv6_hdr(skb)->payload_len); + offset = ntohs(fhdr->frag_off) & ~0x7; - end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - + end = offset + (payload_len - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { @@ -307,7 +314,9 @@ found: skb->dev = NULL; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; - atomic_add(skb->truesize, &nf_init_frags.mem); + if (payload_len > fq->q.max_size) + fq->q.max_size = payload_len; + atomic_add(skb->truesize, &fq->q.net->mem); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -317,12 +326,12 @@ found: fq->q.last_in |= INET_FRAG_FIRST_IN; } write_lock(&nf_frags.lock); - list_move_tail(&fq->q.lru_list, &nf_init_frags.lru_list); + list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); write_unlock(&nf_frags.lock); return 0; discard_fq: - fq_kill(fq); + inet_frag_kill(&fq->q, &nf_frags); err: return -1; } @@ -337,12 +346,12 @@ err: * the last and the first frames arrived and all the bits are here. */ static struct sk_buff * -nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) +nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) { struct sk_buff *fp, *op, *head = fq->q.fragments; int payload_len; - fq_kill(fq); + inet_frag_kill(&fq->q, &nf_frags); WARN_ON(head == NULL); WARN_ON(NFCT_FRAG6_CB(head)->offset != 0); @@ -386,7 +395,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - atomic_add(clone->truesize, &nf_init_frags.mem); + atomic_add(clone->truesize, &fq->q.net->mem); } /* We have to remove fragment header from datagram and to relocate @@ -410,12 +419,14 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - atomic_sub(head->truesize, &nf_init_frags.mem); + atomic_sub(head->truesize, &fq->q.net->mem); + head->local_df = 1; head->next = NULL; head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); + IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ if (head->ip_summed == CHECKSUM_COMPLETE) @@ -520,8 +531,10 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; + struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) + : dev_net(skb->dev); struct frag_hdr *fhdr; - struct nf_ct_frag6_queue *fq; + struct frag_queue *fq; struct ipv6hdr *hdr; int fhoff, nhoff; u8 prevhdr; @@ -553,10 +566,11 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) hdr = ipv6_hdr(clone); fhdr = (struct frag_hdr *)skb_transport_header(clone); - if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh) - nf_ct_frag6_evictor(); + local_bh_disable(); + inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false); + local_bh_enable(); - fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr); + fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; @@ -567,7 +581,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { spin_unlock_bh(&fq->q.lock); pr_debug("Can't insert skb to queue\n"); - fq_put(fq); + inet_frag_put(&fq->q, &nf_frags); goto ret_orig; } @@ -579,7 +593,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) } spin_unlock_bh(&fq->q.lock); - fq_put(fq); + inet_frag_put(&fq->q, &nf_frags); return ret_skb; ret_orig: @@ -592,6 +606,7 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { struct sk_buff *s, *s2; + unsigned int ret = 0; for (s = NFCT_FRAG6_CB(skb)->orig; s;) { nf_conntrack_put_reasm(s->nfct_reasm); @@ -601,49 +616,62 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, s2 = s->next; s->next = NULL; - NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, in, out, okfn, - NF_IP6_PRI_CONNTRACK_DEFRAG + 1); + if (ret != -ECANCELED) + ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, + in, out, okfn, + NF_IP6_PRI_CONNTRACK_DEFRAG + 1); + else + kfree_skb(s); + s = s2; } nf_conntrack_put_reasm(skb); } +static int nf_ct_net_init(struct net *net) +{ + net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH; + net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT; + inet_frags_init_net(&net->nf_frag.frags); + + return nf_ct_frag6_sysctl_register(net); +} + +static void nf_ct_net_exit(struct net *net) +{ + nf_ct_frags6_sysctl_unregister(net); + inet_frags_exit_net(&net->nf_frag.frags, &nf_frags); +} + +static struct pernet_operations nf_ct_net_ops = { + .init = nf_ct_net_init, + .exit = nf_ct_net_exit, +}; + int nf_ct_frag6_init(void) { + int ret = 0; + nf_frags.hashfn = nf_hashfn; nf_frags.constructor = ip6_frag_init; nf_frags.destructor = NULL; nf_frags.skb_free = nf_skb_free; - nf_frags.qsize = sizeof(struct nf_ct_frag6_queue); + nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.secret_interval = 10 * 60 * HZ; - nf_init_frags.timeout = IPV6_FRAG_TIMEOUT; - nf_init_frags.high_thresh = IPV6_FRAG_HIGH_THRESH; - nf_init_frags.low_thresh = IPV6_FRAG_LOW_THRESH; - inet_frags_init_net(&nf_init_frags); inet_frags_init(&nf_frags); -#ifdef CONFIG_SYSCTL - nf_ct_frag6_sysctl_header = register_net_sysctl(&init_net, "net/netfilter", - nf_ct_frag6_sysctl_table); - if (!nf_ct_frag6_sysctl_header) { + ret = register_pernet_subsys(&nf_ct_net_ops); + if (ret) inet_frags_fini(&nf_frags); - return -ENOMEM; - } -#endif - return 0; + return ret; } void nf_ct_frag6_cleanup(void) { -#ifdef CONFIG_SYSCTL - unregister_net_sysctl_table(nf_ct_frag6_sysctl_header); - nf_ct_frag6_sysctl_header = NULL; -#endif + unregister_pernet_subsys(&nf_ct_net_ops); inet_frags_fini(&nf_frags); - - nf_init_frags.low_thresh = 0; - nf_ct_frag6_evictor(); } diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c new file mode 100644 index 000000000000..abfe75a2e316 --- /dev/null +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -0,0 +1,288 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of IPv6 NAT funded by Astaro. + */ +#include <linux/types.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <net/secure_seq.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv6; + +#ifdef CONFIG_XFRM +static void nf_nat_ipv6_decode_session(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl) +{ + const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; + struct flowi6 *fl6 = &fl->u.ip6; + + if (ct->status & statusbit) { + fl6->daddr = t->dst.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_dport = t->dst.u.all; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl6->saddr = t->src.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_sport = t->src.u.all; + } +} +#endif + +static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t, + const struct nf_nat_range *range) +{ + return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 && + ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0; +} + +static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t, + __be16 dport) +{ + return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport); +} + +static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ + struct ipv6hdr *ipv6h; + __be16 frag_off; + int hdroff; + u8 nexthdr; + + if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + return false; + + ipv6h = (void *)skb->data + iphdroff; + nexthdr = ipv6h->nexthdr; + hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), + &nexthdr, &frag_off); + if (hdroff < 0) + goto manip_addr; + + if ((frag_off & htons(~0x7)) == 0 && + !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, + target, maniptype)) + return false; +manip_addr: + if (maniptype == NF_NAT_MANIP_SRC) + ipv6h->saddr = target->src.u3.in6; + else + ipv6h->daddr = target->dst.u3.in6; + + return true; +} + +static void nf_nat_ipv6_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); + const struct in6_addr *oldip, *newip; + + if (maniptype == NF_NAT_MANIP_SRC) { + oldip = &ipv6h->saddr; + newip = &t->src.u3.in6; + } else { + oldip = &ipv6h->daddr; + newip = &t->dst.u3.in6; + } + inet_proto_csum_replace16(check, skb, oldip->s6_addr32, + newip->s6_addr32, 1); +} + +static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, + u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(rt->rt6i_flags & RTF_LOCAL) && + (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + + skb_network_offset(skb) + + (data - (void *)skb->data); + skb->csum_offset = (void *)check - data; + *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, proto, 0); + } else { + *check = 0; + *check = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, proto, + csum_partial(data, datalen, + 0)); + if (proto == IPPROTO_UDP && !*check) + *check = CSUM_MANGLED_0; + } + } else + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), 1); +} + +static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_NAT_V6_MINIP]) { + nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], + sizeof(struct in6_addr)); + range->flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (tb[CTA_NAT_V6_MAXIP]) + nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP], + sizeof(struct in6_addr)); + else + range->max_addr = range->min_addr; + + return 0; +} + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { + .l3proto = NFPROTO_IPV6, + .secure_port = nf_nat_ipv6_secure_port, + .in_range = nf_nat_ipv6_in_range, + .manip_pkt = nf_nat_ipv6_manip_pkt, + .csum_update = nf_nat_ipv6_csum_update, + .csum_recalc = nf_nat_ipv6_csum_recalc, + .nlattr_to_range = nf_nat_ipv6_nlattr_to_range, +#ifdef CONFIG_XFRM + .decode_session = nf_nat_ipv6_decode_session, +#endif +}; + +int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + unsigned int hdrlen) +{ + struct { + struct icmp6hdr icmp6; + struct ipv6hdr ip6; + } *inside; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + const struct nf_nat_l4proto *l4proto; + struct nf_conntrack_tuple target; + unsigned long statusbit; + + NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY); + + if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + return 0; + if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) + return 0; + + inside = (void *)skb->data + hdrlen; + if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + if (ct->status & IPS_NAT_MASK) + return 0; + } + + if (manip == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply direction */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr); + if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), + l4proto, &ct->tuplehash[!dir].tuple, !manip)) + return 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + inside = (void *)skb->data + hdrlen; + inside->icmp6.icmp6_cksum = 0; + inside->icmp6.icmp6_cksum = + csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + skb->len - hdrlen, IPPROTO_ICMPV6, + csum_partial(&inside->icmp6, + skb->len - hdrlen, 0)); + } + + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6); + if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip)) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); + +static int __init nf_nat_l3proto_ipv6_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); + if (err < 0) + goto err1; + err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6); + if (err < 0) + goto err2; + return err; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); +err1: + return err; +} + +static void __exit nf_nat_l3proto_ipv6_exit(void) +{ + nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6); + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); +} + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("nf-nat-" __stringify(AF_INET6)); + +module_init(nf_nat_l3proto_ipv6_init); +module_exit(nf_nat_l3proto_ipv6_exit); diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c new file mode 100644 index 000000000000..5d6da784305b --- /dev/null +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -0,0 +1,90 @@ +/* + * Copyright (c) 2011 Patrick Mchardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on Rusty Russell's IPv4 ICMP NAT code. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/types.h> +#include <linux/init.h> +#include <linux/icmpv6.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static bool +icmpv6_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) && + ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id); +} + +static void +icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + static u16 id; + unsigned int range_size; + unsigned int i; + + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) + range_size = 0xffff; + + for (i = 0; ; ++id) { + tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) + + (id % range_size)); + if (++i == range_size || !nf_nat_used_tuple(tuple, ct)) + return; + } +} + +static bool +icmpv6_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct icmp6hdr *hdr; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct icmp6hdr *)(skb->data + hdroff); + l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, + tuple, maniptype); + if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST || + hdr->icmp6_code == ICMPV6_ECHO_REPLY) { + inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, + hdr->icmp6_identifier, + tuple->src.u.icmp.id, 0); + hdr->icmp6_identifier = tuple->src.u.icmp.id; + } + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = { + .l4proto = IPPROTO_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) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index da2e92d05c15..745a32042950 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -307,10 +307,10 @@ static int __net_init ipv6_proc_init_net(struct net *net) goto proc_dev_snmp6_fail; return 0; +proc_dev_snmp6_fail: + proc_net_remove(net, "snmp6"); proc_snmp6_fail: proc_net_remove(net, "sockstat6"); -proc_dev_snmp6_fail: - proc_net_remove(net, "dev_snmp6"); return -ENOMEM; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ef0579d5bca6..d8e95c77db99 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -107,21 +107,20 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) +static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *icmph; - struct raw6_sock *rp = raw6_sk(sk); - - if (pskb_may_pull(skb, sizeof(struct icmp6hdr))) { - __u32 *data = &rp->filter.data[0]; - int bit_nr; + struct icmp6hdr *_hdr; + const struct icmp6hdr *hdr; - icmph = (struct icmp6hdr *) skb->data; - bit_nr = icmph->icmp6_type; + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (hdr) { + const __u32 *data = &raw6_sk(sk)->filter.data[0]; + unsigned int type = hdr->icmp6_type; - return (data[bit_nr >> 5] & (1 << (bit_nr & 31))) != 0; + return (data[type >> 5] & (1U << (type & 31))) != 0; } - return 0; + return 1; } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) @@ -1251,7 +1250,8 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - sock_i_uid(sp), 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4ff9af628e72..da8a4e301b1b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -65,36 +65,8 @@ struct ip6frag_skb_cb #define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb)) -/* - * Equivalent of ipv4 struct ipq - */ - -struct frag_queue -{ - struct inet_frag_queue q; - - __be32 id; /* fragment id */ - u32 user; - struct in6_addr saddr; - struct in6_addr daddr; - - int iif; - unsigned int csum; - __u16 nhoffset; -}; - static struct inet_frags ip6_frags; -int ip6_frag_nqueues(struct net *net) -{ - return net->ipv6.frags.nqueues; -} - -int ip6_frag_mem(struct net *net) -{ - return atomic_read(&net->ipv6.frags.mem); -} - static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev); @@ -159,46 +131,18 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_init); -/* Destruction primitives. */ - -static __inline__ void fq_put(struct frag_queue *fq) -{ - inet_frag_put(&fq->q, &ip6_frags); -} - -/* Kill fq entry. It is not destroyed immediately, - * because caller (and someone more) holds reference count. - */ -static __inline__ void fq_kill(struct frag_queue *fq) -{ - inet_frag_kill(&fq->q, &ip6_frags); -} - -static void ip6_evictor(struct net *net, struct inet6_dev *idev) +void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, + struct inet_frags *frags) { - int evicted; - - evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags); - if (evicted) - IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted); -} - -static void ip6_frag_expire(unsigned long data) -{ - struct frag_queue *fq; struct net_device *dev = NULL; - struct net *net; - - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); spin_lock(&fq->q.lock); if (fq->q.last_in & INET_FRAG_COMPLETE) goto out; - fq_kill(fq); + inet_frag_kill(&fq->q, frags); - net = container_of(fq->q.net, struct net, ipv6.frags); rcu_read_lock(); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) @@ -222,7 +166,19 @@ out_rcu_unlock: rcu_read_unlock(); out: spin_unlock(&fq->q.lock); - fq_put(fq); + inet_frag_put(&fq->q, frags); +} +EXPORT_SYMBOL(ip6_expire_frag_queue); + +static void ip6_frag_expire(unsigned long data) +{ + struct frag_queue *fq; + struct net *net; + + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, ipv6.frags); + + ip6_expire_frag_queue(net, fq, &ip6_frags); } static __inline__ struct frag_queue * @@ -391,7 +347,7 @@ found: return -1; discard_fq: - fq_kill(fq); + inet_frag_kill(&fq->q, &ip6_frags); err: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); @@ -417,7 +373,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, unsigned int nhoff; int sum_truesize; - fq_kill(fq); + inet_frag_kill(&fq->q, &ip6_frags); /* Make the one we just received the head. */ if (prev) { @@ -550,6 +506,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); + int evicted; IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); @@ -574,8 +531,10 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) - ip6_evictor(net, ip6_dst_idev(skb_dst(skb))); + evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false); + if (evicted) + IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS, evicted); fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr); if (fq != NULL) { @@ -586,7 +545,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); spin_unlock(&fq->q.lock); - fq_put(fq); + inet_frag_put(&fq->q, &ip6_frags); return ret; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index cf02cb97bbdd..7c7e963260e1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -222,11 +222,11 @@ static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 255, }; -static struct rt6_info ip6_null_entry_template = { +static const struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, @@ -242,11 +242,11 @@ static struct rt6_info ip6_null_entry_template = { static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct sk_buff *skb); -static struct rt6_info ip6_prohibit_entry_template = { +static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, @@ -257,11 +257,11 @@ static struct rt6_info ip6_prohibit_entry_template = { .rt6i_ref = ATOMIC_INIT(1), }; -static struct rt6_info ip6_blk_hole_entry_template = { +static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard, @@ -281,13 +281,14 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct fib6_table *table) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 0, DST_OBSOLETE_NONE, flags); + 0, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { struct dst_entry *dst = &rt->dst; 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); } return rt; } @@ -369,15 +370,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static bool rt6_check_expired(const struct rt6_info *rt) { - struct rt6_info *ort = NULL; - if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; } else if (rt->dst.from) { - ort = (struct rt6_info *) rt->dst.from; - return (ort->rt6i_flags & RTF_EXPIRES) && - time_after(jiffies, ort->dst.expires); + return rt6_check_expired((struct rt6_info *) rt->dst.from); } return false; } @@ -451,10 +448,9 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - rcu_read_lock(); neigh = rt ? rt->n : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) - goto out; + return; read_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { @@ -470,8 +466,6 @@ static void rt6_probe(struct rt6_info *rt) } else { read_unlock_bh(&neigh->lock); } -out: - rcu_read_unlock(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -498,7 +492,6 @@ static inline int rt6_check_neigh(struct rt6_info *rt) struct neighbour *neigh; int m; - rcu_read_lock(); neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) @@ -516,7 +509,6 @@ static inline int rt6_check_neigh(struct rt6_info *rt) read_unlock_bh(&neigh->lock); } else m = 0; - rcu_read_unlock(); return m; } @@ -965,7 +957,7 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, { int flags = 0; - fl6->flowi6_iif = net->loopback_dev->ifindex; + fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) flags |= RT6_LOOKUP_F_IFACE; @@ -1031,6 +1023,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; + /* All IPV6 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + */ + 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)) @@ -1397,8 +1396,6 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt->dst.obsolete = -1; - if (cfg->fc_flags & RTF_EXPIRES) rt6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); @@ -1463,8 +1460,21 @@ int ip6_route_add(struct fib6_config *cfg) } rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; - rt->dst.error = -ENETUNREACH; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; + switch (cfg->fc_type) { + case RTN_BLACKHOLE: + rt->dst.error = -EINVAL; + break; + case RTN_PROHIBIT: + rt->dst.error = -EACCES; + break; + case RTN_THROW: + rt->dst.error = -EAGAIN; + break; + default: + rt->dst.error = -ENETUNREACH; + break; + } goto install_route; } @@ -1583,17 +1593,18 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry) - return -ENOENT; + if (rt == net->ipv6.ip6_null_entry) { + err = -ENOENT; + goto out; + } table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_del(rt, info); - dst_release(&rt->dst); - write_unlock_bh(&table->tb6_lock); +out: + dst_release(&rt->dst); return err; } @@ -1829,7 +1840,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!table) return NULL; - write_lock_bh(&table->tb6_lock); + read_lock_bh(&table->tb6_lock); fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0); if (!fn) goto out; @@ -1845,7 +1856,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, break; } out: - write_unlock_bh(&table->tb6_lock); + read_unlock_bh(&table->tb6_lock); return rt; } @@ -1861,7 +1872,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), - .fc_nlinfo.pid = 0, + .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; @@ -1888,7 +1899,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev if (!table) return NULL; - write_lock_bh(&table->tb6_lock); + read_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) { if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && @@ -1897,7 +1908,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev } if (rt) dst_hold(&rt->dst); - write_unlock_bh(&table->tb6_lock); + read_unlock_bh(&table->tb6_lock); return rt; } @@ -1911,7 +1922,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), - .fc_nlinfo.pid = 0, + .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = dev_net(dev), }; @@ -2080,7 +2091,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_idev = idev; - rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; if (anycast) @@ -2261,14 +2271,18 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_src_len = rtm->rtm_src_len; cfg->fc_flags = RTF_UP; cfg->fc_protocol = rtm->rtm_protocol; + cfg->fc_type = rtm->rtm_type; - if (rtm->rtm_type == RTN_UNREACHABLE) + if (rtm->rtm_type == RTN_UNREACHABLE || + rtm->rtm_type == RTN_BLACKHOLE || + rtm->rtm_type == RTN_PROHIBIT || + rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; - cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2359,7 +2373,7 @@ static inline size_t rt6_nlmsg_size(void) static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, - int iif, int type, u32 pid, u32 seq, + int iif, int type, u32 portid, u32 seq, int prefix, int nowait, unsigned int flags) { struct rtmsg *rtm; @@ -2375,7 +2389,7 @@ static int rt6_fill_node(struct net *net, } } - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; @@ -2391,8 +2405,22 @@ static int rt6_fill_node(struct net *net, rtm->rtm_table = table; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; - if (rt->rt6i_flags & RTF_REJECT) - rtm->rtm_type = RTN_UNREACHABLE; + if (rt->rt6i_flags & RTF_REJECT) { + switch (rt->dst.error) { + case -EINVAL: + rtm->rtm_type = RTN_BLACKHOLE; + break; + case -EACCES: + rtm->rtm_type = RTN_PROHIBIT; + break; + case -EAGAIN: + rtm->rtm_type = RTN_THROW; + break; + default: + rtm->rtm_type = RTN_UNREACHABLE; + break; + } + } else if (rt->rt6i_flags & RTF_LOCAL) rtm->rtm_type = RTN_LOCAL; else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) @@ -2465,27 +2493,19 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - rcu_read_lock(); n = rt->n; if (n) { - if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) { - rcu_read_unlock(); + if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) goto nla_put_failure; - } } - rcu_read_unlock(); if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) goto nla_put_failure; - if (!(rt->rt6i_flags & RTF_EXPIRES)) - expires = 0; - else if (rt->dst.expires - jiffies < INT_MAX) - expires = rt->dst.expires - jiffies; - else - expires = INT_MAX; + + expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; @@ -2510,7 +2530,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) return rt6_fill_node(arg->net, arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, - NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, + NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, prefix, 0, NLM_F_MULTI); } @@ -2590,14 +2610,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_dst_set(skb, &rt->dst); err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).pid, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { kfree_skb(skb); goto errout; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } @@ -2617,14 +2637,14 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->pid, seq, 0, 0, 0); + event, info->portid, seq, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE, + rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: @@ -2679,14 +2699,12 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif - rcu_read_lock(); n = rt->n; if (n) { seq_printf(m, "%pi6", n->primary_key); } else { seq_puts(m, "00000000000000000000000000000000"); } - rcu_read_unlock(); seq_printf(m, " %08x %08x %08x %08x %8s\n", rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), rt->dst.__use, rt->rt6i_flags, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3bd1bfc01f85..3ed54ffd8d50 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -545,7 +545,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - rcu_read_lock(); t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, @@ -579,7 +578,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - rcu_read_unlock(); return err; } @@ -599,7 +597,6 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); - rcu_read_lock(); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -615,7 +612,6 @@ 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++; - rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -630,12 +626,10 @@ static int ipip6_rcv(struct sk_buff *skb) netif_rx(skb); - rcu_read_unlock(); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ - rcu_read_unlock(); return 1; out: kfree_skb(skb); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bb46061c813a..182ab9a85d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -190,6 +190,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); + treq->listener = NULL; if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f49476e2d884..49c890386ce9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -94,6 +94,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, } #endif +static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + const struct rt6_info *rt = (const struct rt6_info *)dst; + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + if (rt->rt6i_node) + inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; +} + static void tcp_v6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { @@ -391,8 +403,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp->mtu_info = ntohl(info); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); - else - set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); + else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, + &tp->tsq_flags)) + sock_hold(sk); goto out; } @@ -463,7 +476,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, rvp); + skb = tcp_make_synack(sk, dst, req, rvp, NULL); if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); @@ -750,6 +763,8 @@ 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: @@ -758,11 +773,23 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, skb->ip_summed = CHECKSUM_UNNECESSARY; break; } - - /* fall through */ - case CHECKSUM_NONE: +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); @@ -975,7 +1002,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, inet6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, @@ -1156,7 +1183,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) } have_isn: tcp_rsk(req)->snt_isn = isn; - tcp_rsk(req)->snt_synack = tcp_time_stamp; if (security_inet_conn_request(sk, skb, req)) goto drop_and_release; @@ -1167,6 +1193,8 @@ have_isn: want_cookie) goto drop_and_free; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_rsk(req)->listener = NULL; inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; @@ -1270,6 +1298,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(newsk, dst, NULL, NULL); + inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; @@ -1299,7 +1328,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone(treq->pktopts, + sk_gfp_atomic(sk, GFP_ATOMIC)); consume_skb(treq->pktopts); treq->pktopts = NULL; if (newnp->pktoptions) @@ -1332,9 +1362,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - if (tcp_rsk(req)->snt_synack) - tcp_valid_rtt_meas(newsk, - tcp_time_stamp - tcp_rsk(req)->snt_synack); + tcp_synack_rtt_meas(newsk, req); newtp->total_retrans = req->retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; @@ -1349,7 +1377,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, - AF_INET6, key->key, key->keylen, GFP_ATOMIC); + AF_INET6, key->key, key->keylen, + sk_gfp_atomic(sk, GFP_ATOMIC)); } #endif @@ -1442,10 +1471,20 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1674,6 +1713,43 @@ do_time_wait: goto discard_it; } +static void tcp_v6_early_demux(struct sk_buff *skb) +{ + const struct ipv6hdr *hdr; + const struct tcphdr *th; + struct sock *sk; + + if (skb->pkt_type != PACKET_HOST) + return; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; + + hdr = ipv6_hdr(skb); + th = tcp_hdr(skb); + + if (th->doff < sizeof(struct tcphdr) / 4) + return; + + sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + inet6_iif(skb)); + if (sk) { + skb->sk = sk; + 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) + skb_dst_set_noref(skb, dst); + } + } +} + static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, @@ -1684,6 +1760,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, + .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), @@ -1715,6 +1792,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct iphdr), @@ -1764,7 +1842,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - const struct sock *sk, struct request_sock *req, int i, int uid) + const struct sock *sk, struct request_sock *req, int i, kuid_t uid) { int ttd = req->expires - jiffies; const struct in6_addr *src = &inet6_rsk(req)->loc_addr; @@ -1788,7 +1866,7 @@ static void get_openreq6(struct seq_file *seq, 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->retrans, - uid, + from_kuid_munged(seq_user_ns(seq), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); @@ -1836,9 +1914,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) tp->write_seq-tp->snd_una, (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, - sock_i_uid(sp), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, @@ -1856,10 +1934,7 @@ static void get_timewait6_sock(struct seq_file *seq, const struct in6_addr *dest, *src; __u16 destp, srcp; const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + long delta = tw->tw_ttd - jiffies; dest = &tw6->tw_v6_daddr; src = &tw6->tw_v6_rcv_saddr; @@ -1875,7 +1950,7 @@ static void get_timewait6_sock(struct seq_file *seq, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw); } @@ -1978,12 +2053,13 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .proto_cgroup = tcp_proto_cgroup, #endif }; 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, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 99d0077b56b8..fc9997260a6b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -394,6 +394,17 @@ try_again: } if (unlikely(err)) { trace_kfree_skb(skb, udpv6_recvmsg); + if (!peeked) { + atomic_inc(&sk->sk_drops); + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, + is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, + is_udplite); + } goto out_free; } if (!peeked) { @@ -1458,7 +1469,8 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - sock_i_uid(sp), 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index ef39812107b1..f8c4c08ffb60 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -73,6 +73,13 @@ static int xfrm6_get_tos(const struct flowi *fl) return 0; } +static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst) +{ + struct rt6_info *rt = (struct rt6_info *)xdst; + + rt6_init_peer(rt, net->ipv6.peers); +} + static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { @@ -286,6 +293,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, + .init_dst = xfrm6_init_dst, .init_path = xfrm6_init_path, .fill_dst = xfrm6_fill_dst, .blackhole_route = ip6_blackhole_route, |