15 files changed, 156 insertions, 33 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e5586783e..438a73aa777c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
 config IPV6_VTI
 tristate "Virtual (secure) IPv6: tunneling"
         select IPV6_TUNNEL
+        select NET_IP_TUNNEL
         depends on INET6_XFRM_MODE_TUNNEL
         ---help---
         Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad235690684c..344e972426df 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1103,8 +1103,11 @@ retry:
          * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
          * an implementation must not create a temporary address with a zero
          * Preferred Lifetime.
+         * Use age calculation as in addrconf_verify to avoid unnecessary
+         * temporary addresses being generated.
          */
-        if (tmp_prefered_lft <= regen_advance) {
+        age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+        if (tmp_prefered_lft <= regen_advance + age) {
                 in6_ifa_put(ifp);
                 in6_dev_put(idev);
                 ret = -1;
@@ -2783,6 +2786,8 @@ static void addrconf_gre_config(struct net_device *dev)
         ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
         if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
                 addrconf_add_linklocal(idev, &addr);
+        else
+                addrconf_prefix_route(&addr, 64, dev, 0, 0);
 }
 #endif
 
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748debc4a..8af3eb57f438 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
                 found = (nexthdr == target);
 
                 if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-                        if (target < 0)
+                        if (target < 0 || found)
                                 break;
                         return -ENOENT;
                 }
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3abfd06..447a7fbd1bb6 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void)
         int ret;
 
         ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
-        if (!ret)
+        if (ret)
                 goto out;
 
         ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
-        if (!ret)
+        if (ret)
                 goto out_rt;
 
 out:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f81f59686f21..f2610e157660 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -414,7 +414,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
         addr_type = ipv6_addr_type(&hdr->daddr);
 
         if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
-            ipv6_anycast_destination(skb))
+            ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
                 saddr = &hdr->daddr;
 
         /*
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1e8683b135bb..59f95affceb0 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
         unsigned int unfrag_ip6hlen;
         u8 *prevhdr;
         int offset = 0;
-        bool tunnel;
+        bool encap, udpfrag;
         int nhoff;
 
         if (unlikely(skb_shinfo(skb)->gso_type &
@@ -110,8 +110,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
         if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
                 goto out;
 
-        tunnel = SKB_GSO_CB(skb)->encap_level > 0;
-        if (tunnel)
+        encap = SKB_GSO_CB(skb)->encap_level > 0;
+        if (encap)
                 features = skb->dev->hw_enc_features & netif_skb_features(skb);
         SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
 
@@ -121,6 +121,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
         proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 
+        if (skb->encapsulation &&
+            skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+                udpfrag = proto == IPPROTO_UDP && encap;
+        else
+                udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
         ops = rcu_dereference(inet6_offloads[proto]);
         if (likely(ops && ops->callbacks.gso_segment)) {
                 skb_reset_transport_header(skb);
@@ -133,13 +139,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
         for (skb = segs; skb; skb = skb->next) {
                 ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
                 ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
-                if (tunnel) {
-                        skb_reset_inner_headers(skb);
-                        skb->encapsulation = 1;
-                }
                 skb->network_header = (u8 *)ipv6h - skb->head;
 
-                if (!tunnel && proto == IPPROTO_UDP) {
+                if (udpfrag) {
                         unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
                         fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
                         fptr->frag_off = htons(offset);
@@ -148,6 +150,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
                         offset += (ntohs(ipv6h->payload_len) -
                                    sizeof(struct frag_hdr));
                 }
+                if (encap)
+                        skb_reset_inner_headers(skb);
         }
 
 out:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef02b26ccf81..64d6073731d3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
         return mtu;
 }
 
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+        if (skb->len <= mtu || skb->local_df)
+                return false;
+
+        if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+                return true;
+
+        if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+                return false;
+
+        return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
         struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb)
         if (mtu < IPV6_MIN_MTU)
                 mtu = IPV6_MIN_MTU;
 
-        if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-            (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+        if (ip6_pkt_too_big(skb, mtu)) {
                 /* Again, force OUTPUT device used as source address */
                 skb->dev = dst->dev;
                 icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -517,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
         to->tc_index = from->tc_index;
 #endif
         nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-        to->nf_trace = from->nf_trace;
-#endif
         skb_copy_secmark(to, from);
 }
 
@@ -1091,21 +1101,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
                                 unsigned int fragheaderlen,
                                 struct sk_buff *skb,
                                 struct rt6_info *rt,
-                                bool pmtuprobe)
+                                unsigned int orig_mtu)
 {
         if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
                 if (skb == NULL) {
                         /* first fragment, reserve header_len */
-                        *mtu = *mtu - rt->dst.header_len;
+                        *mtu = orig_mtu - rt->dst.header_len;
 
                 } else {
                         /*
                          * this fragment is not first, the headers
                          * space is regarded as data space.
                          */
-                        *mtu = min(*mtu, pmtuprobe ?
-                                   rt->dst.dev->mtu :
-                                   dst_mtu(rt->dst.path));
+                        *mtu = orig_mtu;
                 }
                 *maxfraglen = ((*mtu - fragheaderlen) & ~7)
                               + fragheaderlen - sizeof(struct frag_hdr);
@@ -1122,7 +1130,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
         struct ipv6_pinfo *np = inet6_sk(sk);
         struct inet_cork *cork;
         struct sk_buff *skb, *skb_prev = NULL;
-        unsigned int maxfraglen, fragheaderlen, mtu;
+        unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
         int exthdrlen;
         int dst_exthdrlen;
         int hh_len;
@@ -1204,6 +1212,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                 dst_exthdrlen = 0;
                 mtu = cork->fragsize;
         }
+        orig_mtu = mtu;
 
         hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
@@ -1301,8 +1310,7 @@ alloc_new_skb:
                         if (skb == NULL || skb_prev == NULL)
                                 ip6_append_data_mtu(&mtu, &maxfraglen,
                                                     fragheaderlen, skb, rt,
-                                                    np->pmtudisc >=
-                                                    IPV6_PMTUDISC_PROBE);
+                                                    orig_mtu);
 
                         skb_prev = skb;
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0eb4038a4d63..8737400af0a0 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2349,13 +2349,14 @@ int ip6mr_get_route(struct net *net,
 }
 
 static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
-                             u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+                             u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+                             int flags)
 {
         struct nlmsghdr *nlh;
         struct rtmsg *rtm;
         int err;
 
-        nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+        nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
         if (nlh == NULL)
                 return -EMSGSIZE;
 
@@ -2423,7 +2424,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
         if (skb == NULL)
                 goto errout;
 
-        err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+        err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
         if (err < 0)
                 goto errout;
 
@@ -2462,7 +2463,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
                                 if (ip6mr_fill_mroute(mrt, skb,
                                                       NETLINK_CB(cb->skb).portid,
                                                       cb->nlh->nlmsg_seq,
-                                                      mfc, RTM_NEWROUTE) < 0)
+                                                      mfc, RTM_NEWROUTE,
+                                                      NLM_F_MULTI) < 0)
                                         goto done;
 next_entry:
                                 e++;
@@ -2476,7 +2478,8 @@ next_entry:
                         if (ip6mr_fill_mroute(mrt, skb,
                                               NETLINK_CB(cb->skb).portid,
                                               cb->nlh->nlmsg_seq,
-                                              mfc, RTM_NEWROUTE) < 0) {
+                                              mfc, RTM_NEWROUTE,
+                                              NLM_F_MULTI) < 0) {
                                 spin_unlock_bh(&mfc_unres_lock);
                                 goto done;
                         }
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 35750df744dc..4bff1f297e39 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -50,6 +50,11 @@ config NFT_CHAIN_NAT_IPV6
           packet transformations such as the source, destination address and
           source and destination ports.
 
+config NFT_REJECT_IPV6
+        depends on NF_TABLES_IPV6
+        default NFT_REJECT
+        tristate
+
 config IP6_NF_IPTABLES
         tristate "IP6 tables support (required for filtering)"
         depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d1b4928f34f7..70d3dd66f2cd 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
+obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
new file mode 100644
index 000000000000..0bc19fa87821
--- /dev/null
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+                          struct nft_data data[NFT_REG_MAX + 1],
+                          const struct nft_pktinfo *pkt)
+{
+        struct nft_reject *priv = nft_expr_priv(expr);
+        struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
+        switch (priv->type) {
+        case NFT_REJECT_ICMP_UNREACH:
+                nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+                                 pkt->ops->hooknum);
+                break;
+        case NFT_REJECT_TCP_RST:
+                nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+                break;
+        }
+
+        data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval);
+
+static struct nft_expr_type nft_reject_ipv6_type;
+static const struct nft_expr_ops nft_reject_ipv6_ops = {
+        .type           = &nft_reject_ipv6_type,
+        .size           = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+        .eval           = nft_reject_ipv6_eval,
+        .init           = nft_reject_init,
+        .dump           = nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
+        .family         = NFPROTO_IPV6,
+        .name           = "reject",
+        .ops            = &nft_reject_ipv6_ops,
+        .policy         = nft_reject_policy,
+        .maxattr        = NFTA_REJECT_MAX,
+        .owner          = THIS_MODULE,
+};
+
+static int __init nft_reject_ipv6_module_init(void)
+{
+        return nft_register_expr(&nft_reject_ipv6_type);
+}
+
+static void __exit nft_reject_ipv6_module_exit(void)
+{
+        nft_unregister_expr(&nft_reject_ipv6_type);
+}
+
+module_init(nft_reject_ipv6_module_init);
+module_exit(nft_reject_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject");
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index fb9beb78f00b..587bbdcb22b4 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -135,6 +135,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         fl6.flowi6_proto = IPPROTO_ICMPV6;
         fl6.saddr = np->saddr;
         fl6.daddr = *daddr;
+        fl6.flowi6_mark = sk->sk_mark;
         fl6.fl6_icmp_type = user_icmph.icmp6_type;
         fl6.fl6_icmp_code = user_icmph.icmp6_code;
         security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11dac21e6586..fba54a407bb2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1513,7 +1513,7 @@ int ip6_route_add(struct fib6_config *cfg)
         if (!table)
                 goto out;
 
-        rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+        rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
         if (!rt) {
                 err = -ENOMEM;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1dcb1c..b4d74c86586c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
                 ipip6_tunnel_unlink(sitn, tunnel);
                 ipip6_tunnel_del_prl(tunnel, NULL);
         }
+        ip_tunnel_dst_reset_all(tunnel);
         dev_put(dev);
 }
 
@@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
                 t->parms.link = p->link;
                 ipip6_tunnel_bind_dev(t->dev);
         }
+        ip_tunnel_dst_reset_all(t);
         netdev_state_change(t->dev);
 }
 
@@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
         t->ip6rd.relay_prefix = relay_prefix;
         t->ip6rd.prefixlen = ip6rd->prefixlen;
         t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+        ip_tunnel_dst_reset_all(t);
         netdev_state_change(t->dev);
         return 0;
 }
@@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
                         err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
                         break;
                 }
+                ip_tunnel_dst_reset_all(t);
                 netdev_state_change(dev);
                 break;
 
@@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = {
 
 static void ipip6_dev_free(struct net_device *dev)
 {
+        struct ip_tunnel *tunnel = netdev_priv(dev);
+
+        free_percpu(tunnel->dst_cache);
         free_percpu(dev->tstats);
         free_netdev(dev);
 }
@@ -1375,6 +1382,12 @@ static int ipip6_tunnel_init(struct net_device *dev)
                 u64_stats_init(&ipip6_tunnel_stats->syncp);
         }
 
+        tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+        if (!tunnel->dst_cache) {
+                free_percpu(dev->tstats);
+                return -ENOMEM;
+        }
+
         return 0;
 }
 
@@ -1405,6 +1418,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
                 u64_stats_init(&ipip6_fb_stats->syncp);
         }
 
+        tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+        if (!tunnel->dst_cache) {
+                free_percpu(dev->tstats);
+                return -ENOMEM;
+        }
+
         dev_hold(dev);
         rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
         return 0;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9eaa8d..b261ee8b83fc 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -113,7 +113,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
                 fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
                 fptr->nexthdr = nexthdr;
                 fptr->reserved = 0;
-                ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+                fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
                 /* Fragment the skb. ipv6 header and the remaining fields of the
                  * fragment header are updated in ipv6_gso_segment()