diff options
Diffstat (limited to 'net/ipv6/ip6_tunnel.c')
| -rw-r--r-- | net/ipv6/ip6_tunnel.c | 837 |
1 files changed, 575 insertions, 262 deletions
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b1155554bb1..afa08245836 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -18,6 +18,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> @@ -27,7 +29,6 @@ #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> -#include <linux/if_tunnel.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> @@ -38,12 +39,15 @@ #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> +#include <linux/hash.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> +#include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> @@ -57,24 +61,32 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); +MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG -#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) +#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__) #else #define IP6_TNL_TRACE(x...) do {;} while(0) #endif -#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 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 HASH_SIZE 32 +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); -#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ - (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ - (HASH_SIZE - 1)) + return hash_32(hash, HASH_SIZE_SHIFT); +} static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); +static struct rtnl_link_ops ip6_link_ops __read_mostly; static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { @@ -86,26 +98,28 @@ struct ip6_tnl_net { struct ip6_tnl __rcu **tnls[2]; }; -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -}; - static struct net_device_stats *ip6_get_stats(struct net_device *dev) { - struct pcpu_tstats sum = { 0 }; + struct pcpu_sw_netstats tmp, sum = { 0 }; int i; for_each_possible_cpu(i) { - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); - - sum.rx_packets += tstats->rx_packets; - sum.rx_bytes += tstats->rx_bytes; - sum.tx_packets += tstats->tx_packets; - sum.tx_bytes += tstats->tx_bytes; + unsigned int start; + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + tmp.rx_packets = tstats->rx_packets; + tmp.rx_bytes = tstats->rx_bytes; + tmp.tx_packets = tstats->tx_packets; + tmp.tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + sum.rx_packets += tmp.rx_packets; + sum.rx_bytes += tmp.rx_bytes; + sum.tx_packets += tmp.tx_packets; + sum.tx_bytes += tmp.tx_bytes; } dev->stats.rx_packets = sum.rx_packets; dev->stats.rx_bytes = sum.rx_bytes; @@ -118,7 +132,7 @@ 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; @@ -131,20 +145,23 @@ 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 @@ -161,14 +178,13 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip6_tnl * -ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) +ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { - unsigned int h0 = HASH(remote); - unsigned int h1 = HASH(local); + unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) @@ -193,16 +209,16 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) **/ static struct ip6_tnl __rcu ** -ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) +ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; - unsigned h = 0; + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; - h = HASH(remote) ^ HASH(local); + h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } @@ -248,8 +264,35 @@ static void ip6_dev_free(struct net_device *dev) free_netdev(dev); } +static int ip6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + t = netdev_priv(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ip6_link_ops; + + dev_hold(dev); + ip6_tnl_link(ip6n, t); + return 0; + +out: + return err; +} + /** - * ip6_tnl_create() - create a new tunnel + * ip6_tnl_create - create a new tunnel * @p: tunnel parameters * @pt: pointer to new tunnel * @@ -260,13 +303,12 @@ 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; char name[IFNAMSIZ]; int err; - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -279,22 +321,13 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) dev_net_set(dev, net); - if (strchr(name, '%')) { - if (dev_alloc_name(dev, name) < 0) - goto failed_free; - } - t = netdev_priv(dev); t->parms = *p; - err = ip6_tnl_dev_init(dev); + t->net = dev_net(dev); + err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; - if ((err = register_netdevice(dev)) < 0) - goto failed_free; - - dev_hold(dev); - ip6_tnl_link(ip6n, t); return t; failed_free: @@ -318,10 +351,10 @@ 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) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -350,11 +383,11 @@ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) - rcu_assign_pointer(ip6n->tnls_wc[0], NULL); + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); ip6_tnl_dst_reset(t); @@ -370,10 +403,9 @@ 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) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; __u8 nexthdr = ipv6h->nexthdr; __u16 off = sizeof (*ipv6h); @@ -421,6 +453,7 @@ 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 @@ -434,7 +467,7 @@ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; u8 rel_type = ICMPV6_DEST_UNREACH; @@ -462,41 +495,32 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Path to destination invalid " - "or inactive!\n", t->parms.name); + net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small hop limit or " - "routing loop in tunnel!\n", - t->parms.name); + net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } break; 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]; if (tel->encap_limit == 0) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small encapsulation " - "limit or routing loop in " - "tunnel!\n", t->parms.name); + net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } - } else if (net_ratelimit()) { - printk(KERN_WARNING - "%s: Recipient unable to parse tunneled " - "packet!\n ", t->parms.name); + } else { + net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -534,9 +558,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u32 rel_info = ntohl(info); int err; struct sk_buff *skb2; - struct iphdr *eiph; - struct flowi fl; + const struct iphdr *eiph; struct rtable *rt; + struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); @@ -559,6 +583,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; + case NDISC_REDIRECT: + rel_type = ICMP_REDIRECT; + rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -577,11 +604,11 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph = ip_hdr(skb2); /* Try to guess incoming interface */ - memset(&fl, 0, sizeof(fl)); - fl.fl4_dst = eiph->saddr; - fl.fl4_tos = RT_TOS(eiph->tos); - fl.proto = IPPROTO_IPIP; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl)) + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, + eiph->saddr, 0, + 0, 0, + IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; @@ -590,15 +617,18 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); rt = NULL; - fl.fl4_dst = eiph->daddr; - fl.fl4_src = eiph->saddr; - fl.fl4_tos = eiph->tos; - if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) || + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, + eiph->daddr, eiph->saddr, + 0, 0, + IPPROTO_IPIP, + RT_TOS(eiph->tos), 0); + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { - ip_rt_put(rt); + if (!IS_ERR(rt)) + ip_rt_put(rt); goto out; } - skb_dst_set(skb2, (struct dst_entry *)rt); + skb_dst_set(skb2, &rt->dst); } else { ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, @@ -612,8 +642,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); } + if (rel_type == ICMP_REDIRECT) + skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -652,13 +684,12 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); - if (rt && rt->rt6i_dev) - skb2->dev = rt->rt6i_dev; + if (rt && rt->dst.dev) + skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); kfree_skb(skb2); } @@ -666,51 +697,77 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } -static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); - if (INET_ECN_is_ce(dsfield)) - IP_ECN_set_ce(ip_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } -static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); - if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h))) - IP6_ECN_set_ce(ipv6_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } +__u32 ip6_tnl_get_cap(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) +{ + struct __ip6_tnl_parm *p = &t->parms; + int ltype = ipv6_addr_type(laddr); + int rtype = ipv6_addr_type(raddr); + __u32 flags = 0; + + if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { + flags = IP6_TNL_F_CAP_PER_PACKET; + } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && + (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { + if (ltype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_XMIT; + if (rtype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_RCV; + } + 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); + struct net *net = t->net; - if (p->flags & IP6_TNL_F_CAP_RCV) { + if ((p->flags & IP6_TNL_F_CAP_RCV) || + ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && + (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); - if ((ipv6_addr_is_multicast(&p->laddr) || - likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0))) + if ((ipv6_addr_is_multicast(laddr) || + likely(ipv6_chk_addr(net, laddr, ldev, 0))) && + likely(!ipv6_chk_addr(net, raddr, NULL, 0))) ret = 1; - } return ret; } +EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); /** * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally @@ -723,18 +780,19 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, __u8 ipproto, - void (*dscp_ecn_decapsulate)(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, - struct sk_buff *skb)) + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb)) { struct ip6_tnl *t; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int err; rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (t->parms.proto != ipproto && t->parms.proto != 0) { rcu_read_unlock(); @@ -746,25 +804,37 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, goto discard; } - if (!ip6_tnl_rcv_ctl(t)) { + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; } - secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); skb->protocol = htons(protocol); - skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); + __skb_tunnel_rx(skb, t->dev, t->net); + + err = dscp_ecn_decapsulate(t, ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++t->dev->stats.rx_frame_errors; + ++t->dev->stats.rx_errors; + rcu_read_unlock(); + goto discard; + } + } + tstats = this_cpu_ptr(t->dev->tstats); + u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; - - __skb_tunnel_rx(skb, t->dev); - - dscp_ecn_decapsulate(t, ipv6h, skb); + u64_stats_update_end(&tstats->syncp); netif_rx(skb); @@ -824,17 +894,17 @@ static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) * 0 else **/ -static inline int -ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr) +static inline bool +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); + struct net *net = t->net; if (p->flags & IP6_TNL_F_CAP_XMIT) { struct net_device *ldev = NULL; @@ -844,21 +914,20 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0))) - printk(KERN_WARNING - "%s xmit: Local address not yet configured!\n", - p->name); + pr_warn("%s xmit: Local address not yet configured!\n", + p->name); else if (!ipv6_addr_is_multicast(&p->raddr) && unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0))) - printk(KERN_WARNING - "%s xmit: Routing loop! " - "Remote address found on this node!\n", - p->name); + pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); else ret = 1; rcu_read_unlock(); } return ret; } +EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); + /** * ip6_tnl_xmit2 - encapsulate packet and send * @skb: the outgoing socket buffer @@ -881,40 +950,44 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) static int ip6_tnl_xmit2(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, - struct flowi *fl, + struct flowi6 *fl6, int encap_limit, __u32 *pmtu) { - struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ipv6_tel_txoption opt; - struct dst_entry *dst; + struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; unsigned int max_headroom = sizeof(struct ipv6hdr); u8 proto; int err = -1; - int pkt_len; - if ((dst = ip6_tnl_dst_check(t)) != NULL) - dst_hold(dst); - else { - dst = ip6_route_output(net, NULL, fl); + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(t); + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); - if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0) + 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++; - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Local routing loop detected!\n", - t->parms.name); + net_warn_ratelimited("%s: Local routing loop detected!\n", + t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof (*ipv6h); @@ -925,13 +998,15 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + 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; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + /* * Okay, now see if we can stuff it in the buffer as-is. */ @@ -946,49 +1021,45 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (skb->sk) skb_set_owner_w(new_skb, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = new_skb; } - skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(dst)); - + 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 = fl->proto; + proto = fl6->flowi6_proto; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); } + + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - *(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; - ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src); - ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst); - 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(t->dev->tstats); - - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - } else { - stats->tx_errors++; - stats->tx_aborted_errors++; - } - ip6_tnl_dst_store(t, dst); + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; + ip6tunnel_xmit(skb, dev); + if (ndst) + ip6_tnl_dst_store(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(dst); + dst_release(ndst); return err; } @@ -996,9 +1067,9 @@ static inline int ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); int encap_limit = -1; - struct flowi fl; + struct flowi6 fl6; __u8 dsfield; __u32 mtu; int err; @@ -1010,16 +1081,18 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; - memcpy(&fl, &t->fl, sizeof (fl)); - fl.proto = IPPROTO_IPIP; + 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)) - fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) + 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 = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu); + err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) @@ -1038,7 +1111,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) struct ipv6hdr *ipv6h = ipv6_hdr(skb); int encap_limit = -1; __u16 offset; - struct flowi fl; + struct flowi6 fl6; __u8 dsfield; __u32 mtu; int err; @@ -1047,7 +1120,7 @@ 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]; @@ -1060,16 +1133,18 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; - memcpy(&fl, &t->fl, sizeof (fl)); - fl.proto = IPPROTO_IPV6; + 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)) - fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); - - err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu); + 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 |= ip6_flowlabel(ipv6h); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + + err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { if (err == -EMSGSIZE) icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); @@ -1109,46 +1184,28 @@ tx_err: return NETDEV_TX_OK; } -static void ip6_tnl_set_cap(struct ip6_tnl *t) -{ - struct ip6_tnl_parm *p = &t->parms; - int ltype = ipv6_addr_type(&p->laddr); - int rtype = ipv6_addr_type(&p->raddr); - - p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV); - - if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && - (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { - if (ltype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_XMIT; - if (rtype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_RCV; - } -} - static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; - struct ip6_tnl_parm *p = &t->parms; - struct flowi *fl = &t->fl; + struct __ip6_tnl_parm *p = &t->parms; + struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ - ipv6_addr_copy(&fl->fl6_src, &p->laddr); - ipv6_addr_copy(&fl->fl6_dst, &p->raddr); - fl->oif = p->link; - fl->fl6_flowlabel = 0; + 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)) - fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; - ip6_tnl_set_cap(t); + 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->flags |= IFF_POINTOPOINT; @@ -1161,23 +1218,25 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); - struct rt6_info *rt = rt6_lookup(dev_net(dev), + struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, strict); if (rt == NULL) return; - if (rt->rt6i_dev) { - dev->hard_header_len = rt->rt6i_dev->hard_header_len + + if (rt->dst.dev) { + dev->hard_header_len = rt->dst.dev->hard_header_len + sizeof (struct ipv6hdr); - dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr); + dev->mtu = rt->dst.dev->mtu - sizeof (struct ipv6hdr); + 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); + ip6_rt_put(rt); } } @@ -1191,10 +1250,10 @@ 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) { - ipv6_addr_copy(&t->parms.laddr, &p->laddr); - ipv6_addr_copy(&t->parms.raddr, &p->raddr); + 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; @@ -1206,6 +1265,48 @@ ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) return 0; } +static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + ip6_tnl_unlink(ip6n, t); + synchronize_net(); + err = ip6_tnl_change(t, p); + ip6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + +static void +ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) +{ + 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 @@ -1239,8 +1340,9 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip6_tnl_parm p; - struct ip6_tnl *t = NULL; - struct net *net = dev_net(dev); + struct __ip6_tnl_parm p1; + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); switch (cmd) { @@ -1250,11 +1352,14 @@ 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); + if (t == NULL) + t = netdev_priv(dev); + } 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; } @@ -1262,7 +1367,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) @@ -1271,7 +1376,8 @@ 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) { @@ -1281,15 +1387,12 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else t = netdev_priv(dev); - ip6_tnl_unlink(ip6n, t); - synchronize_net(); - err = ip6_tnl_change(t, &p); - ip6_tnl_link(ip6n, t); - netdev_state_change(dev); + err = ip6_tnl_update(t, &p1); } 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 @@ -1297,7 +1400,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { @@ -1305,7 +1408,9 @@ 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) @@ -1334,9 +1439,17 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU) { - return -EINVAL; + struct ip6_tnl *tnl = netdev_priv(dev); + + if (tnl->parms.proto == IPPROTO_IPIP) { + if (new_mtu < 68) + return -EINVAL; + } else { + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; } + if (new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; dev->mtu = new_mtu; return 0; } @@ -1361,16 +1474,23 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { + struct ip6_tnl *t; + dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr); + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + /* This perm addr will be used as interface identifier by IPv6 */ + dev->addr_assign_type = NET_ADDR_RANDOM; + eth_random_addr(dev->perm_addr); } @@ -1385,8 +1505,8 @@ ip6_tnl_dev_init_gen(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; - strcpy(t->parms.name, dev->name); - dev->tstats = alloc_percpu(struct pcpu_tstats); + t->net = dev_net(dev); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; return 0; @@ -1427,10 +1547,181 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); + + ip6_tnl_link_config(t); + rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data || !data[IFLA_IPTUN_PROTO]) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + +static void ip6_tnl_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); + + if (data[IFLA_IPTUN_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); + + if (data[IFLA_IPTUN_FLOWINFO]) + parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); + + if (data[IFLA_IPTUN_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); +} + +static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + ip6_tnl_netlink_parms(data, &nt->parms); + + if (ip6_tnl_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ip6_tnl_create2(dev); +} + +static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct __ip6_tnl_parm p; + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + ip6_tnl_netlink_parms(data, &p); + + t = ip6_tnl_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return ip6_tnl_update(t, &p); +} + +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + +static size_t ip6_tnl_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_IPTUN_FLOWINFO */ + nla_total_size(4) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(4) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + 0; +} + +static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), + &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || + nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || + nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || + nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ip6_link_ops __read_mostly = { + .kind = "ip6tnl", + .maxtype = IFLA_IPTUN_MAX, + .policy = ip6_tnl_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6_tnl_dev_setup, + .validate = ip6_tnl_validate, + .newlink = ip6_tnl_newlink, + .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, + .get_size = ip6_tnl_get_size, + .fill_info = ip6_tnl_fill_info, +}; + static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, @@ -1443,28 +1734,37 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct net_device *dev, *aux; int h; struct ip6_tnl *t; LIST_HEAD(list); + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &ip6_link_ops) + unregister_netdevice_queue(dev, &list); + for (h = 0; h < HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t != NULL) { - unregister_netdevice_queue(t->dev, &list); + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, &list); t = rtnl_dereference(t->next); } } - t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; @@ -1477,6 +1777,11 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) @@ -1485,6 +1790,10 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; + + t = netdev_priv(ip6n->fb_tnl_dev); + + strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: @@ -1495,10 +1804,8 @@ err_alloc_dev: static void __net_exit ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - rtnl_lock(); - ip6_tnl_destroy_tunnels(ip6n); + ip6_tnl_destroy_tunnels(net); rtnl_unlock(); } @@ -1525,18 +1832,23 @@ static int __init ip6_tunnel_init(void) err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { - printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n"); + pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { - printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n"); + pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } + err = rtnl_link_register(&ip6_link_ops); + if (err < 0) + goto rtnl_link_failed; return 0; +rtnl_link_failed: + xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: @@ -1551,11 +1863,12 @@ out_pernet: static void __exit ip6_tunnel_cleanup(void) { + rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) - printk(KERN_INFO "ip6_tunnel close: can't deregister ip4ip6\n"); + pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) - printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n"); + pr_info("%s: can't deregister ip6ip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } |