11 files changed, 198 insertions, 81 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 fdbfeca36d63..6c7fa0853fc7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
 static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
 static DEFINE_SPINLOCK(addrconf_hash_lock);
 
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
 
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
 
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
                                                   u32 flags, u32 noflags);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev)
                 __in6_dev_put(idev);
 }
 
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
 {
-        if (del_timer(&ifp->dad_timer))
+        if (cancel_delayed_work(&ifp->dad_work))
                 __in6_ifa_put(ifp);
 }
 
@@ -261,12 +263,12 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
         mod_timer(&idev->rs_timer, jiffies + when);
 }
 
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
-                                   unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+                                   unsigned long delay)
 {
-        if (!timer_pending(&ifp->dad_timer))
+        if (!delayed_work_pending(&ifp->dad_work))
                 in6_ifa_hold(ifp);
-        mod_timer(&ifp->dad_timer, jiffies + when);
+        mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 
         in6_dev_put(ifp->idev);
 
-        if (del_timer(&ifp->dad_timer))
-                pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+        if (cancel_delayed_work(&ifp->dad_work))
+                pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+                          ifp);
 
         if (ifp->state != INET6_IFADDR_STATE_DEAD) {
                 pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
         spin_lock_init(&ifa->lock);
         spin_lock_init(&ifa->state_lock);
-        setup_timer(&ifa->dad_timer, addrconf_dad_timer,
-                    (unsigned long)ifa);
+        INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
         INIT_HLIST_NODE(&ifa->addr_lst);
         ifa->scope = scope;
         ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
         enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
         unsigned long expires;
 
+        ASSERT_RTNL();
+
         spin_lock_bh(&ifp->state_lock);
         state = ifp->state;
         ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
         write_unlock_bh(&ifp->idev->lock);
 
-        addrconf_del_dad_timer(ifp);
+        addrconf_del_dad_work(ifp);
 
         ipv6_ifa_notify(RTM_DELADDR, ifp);
 
@@ -1103,8 +1107,11 @@ 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;
@@ -1601,7 +1608,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 {
         if (ifp->flags&IFA_F_PERMANENT) {
                 spin_lock_bh(&ifp->lock);
-                addrconf_del_dad_timer(ifp);
+                addrconf_del_dad_work(ifp);
                 ifp->flags |= IFA_F_TENTATIVE;
                 if (dad_failed)
                         ifp->flags |= IFA_F_DADFAILED;
@@ -1622,20 +1629,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
                         spin_unlock_bh(&ifp->lock);
                 }
                 ipv6_del_addr(ifp);
-        } else
+        } else {
                 ipv6_del_addr(ifp);
+        }
 }
 
 static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 {
         int err = -ENOENT;
 
-        spin_lock(&ifp->state_lock);
+        spin_lock_bh(&ifp->state_lock);
         if (ifp->state == INET6_IFADDR_STATE_DAD) {
                 ifp->state = INET6_IFADDR_STATE_POSTDAD;
                 err = 0;
         }
-        spin_unlock(&ifp->state_lock);
+        spin_unlock_bh(&ifp->state_lock);
 
         return err;
 }
@@ -1668,7 +1676,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
                 }
         }
 
-        addrconf_dad_stop(ifp, 1);
+        spin_lock_bh(&ifp->state_lock);
+        /* transition from _POSTDAD to _ERRDAD */
+        ifp->state = INET6_IFADDR_STATE_ERRDAD;
+        spin_unlock_bh(&ifp->state_lock);
+
+        addrconf_mod_dad_work(ifp, 0);
 }
 
 /* Join to solicited addr multicast group. */
@@ -1677,6 +1690,8 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
         struct in6_addr maddr;
 
+        ASSERT_RTNL();
+
         if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
                 return;
 
@@ -1688,6 +1703,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
         struct in6_addr maddr;
 
+        ASSERT_RTNL();
+
         if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
                 return;
 
@@ -1698,6 +1715,9 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
         struct in6_addr addr;
+
+        ASSERT_RTNL();
+
         if (ifp->prefix_len >= 127) /* RFC 6164 */
                 return;
         ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1709,6 +1729,9 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
         struct in6_addr addr;
+
+        ASSERT_RTNL();
+
         if (ifp->prefix_len >= 127) /* RFC 6164 */
                 return;
         ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2268,11 +2291,13 @@ ok:
                                 return;
                         }
 
-                        ifp->flags |= IFA_F_MANAGETEMPADDR;
                         update_lft = 0;
                         create = 1;
+                        spin_lock_bh(&ifp->lock);
+                        ifp->flags |= IFA_F_MANAGETEMPADDR;
                         ifp->cstamp = jiffies;
                         ifp->tokenized = tokenized;
+                        spin_unlock_bh(&ifp->lock);
                         addrconf_dad_start(ifp);
                 }
 
@@ -2323,7 +2348,7 @@ ok:
                                          create, now);
 
                         in6_ifa_put(ifp);
-                        addrconf_verify(0);
+                        addrconf_verify();
                 }
         }
         inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2472,7 +2497,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
                         manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
                                          true, jiffies);
                 in6_ifa_put(ifp);
-                addrconf_verify(0);
+                addrconf_verify_rtnl();
                 return 0;
         }
 
@@ -3008,7 +3033,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
                 hlist_for_each_entry_rcu(ifa, h, addr_lst) {
                         if (ifa->idev == idev) {
                                 hlist_del_init_rcu(&ifa->addr_lst);
-                                addrconf_del_dad_timer(ifa);
+                                addrconf_del_dad_work(ifa);
                                 goto restart;
                         }
                 }
@@ -3046,7 +3071,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
         while (!list_empty(&idev->addr_list)) {
                 ifa = list_first_entry(&idev->addr_list,
                                        struct inet6_ifaddr, if_list);
-                addrconf_del_dad_timer(ifa);
+                addrconf_del_dad_work(ifa);
 
                 list_del(&ifa->if_list);
 
@@ -3145,10 +3170,10 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
                 rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
 
         ifp->dad_probes = idev->cnf.dad_transmits;
-        addrconf_mod_dad_timer(ifp, rand_num);
+        addrconf_mod_dad_work(ifp, rand_num);
 }
 
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
         struct inet6_dev *idev = ifp->idev;
         struct net_device *dev = idev->dev;
@@ -3200,25 +3225,68 @@ out:
         read_unlock_bh(&idev->lock);
 }
 
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
 {
-        struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+        bool begin_dad = false;
+
+        spin_lock_bh(&ifp->state_lock);
+        if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+                ifp->state = INET6_IFADDR_STATE_PREDAD;
+                begin_dad = true;
+        }
+        spin_unlock_bh(&ifp->state_lock);
+
+        if (begin_dad)
+                addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+        struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+                                                struct inet6_ifaddr,
+                                                dad_work);
         struct inet6_dev *idev = ifp->idev;
         struct in6_addr mcaddr;
 
+        enum {
+                DAD_PROCESS,
+                DAD_BEGIN,
+                DAD_ABORT,
+        } action = DAD_PROCESS;
+
+        rtnl_lock();
+
+        spin_lock_bh(&ifp->state_lock);
+        if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+                action = DAD_BEGIN;
+                ifp->state = INET6_IFADDR_STATE_DAD;
+        } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+                action = DAD_ABORT;
+                ifp->state = INET6_IFADDR_STATE_POSTDAD;
+        }
+        spin_unlock_bh(&ifp->state_lock);
+
+        if (action == DAD_BEGIN) {
+                addrconf_dad_begin(ifp);
+                goto out;
+        } else if (action == DAD_ABORT) {
+                addrconf_dad_stop(ifp, 1);
+                goto out;
+        }
+
         if (!ifp->dad_probes && addrconf_dad_end(ifp))
                 goto out;
 
-        write_lock(&idev->lock);
+        write_lock_bh(&idev->lock);
         if (idev->dead || !(idev->if_flags & IF_READY)) {
-                write_unlock(&idev->lock);
+                write_unlock_bh(&idev->lock);
                 goto out;
         }
 
         spin_lock(&ifp->lock);
         if (ifp->state == INET6_IFADDR_STATE_DEAD) {
                 spin_unlock(&ifp->lock);
-                write_unlock(&idev->lock);
+                write_unlock_bh(&idev->lock);
                 goto out;
         }
 
@@ -3229,7 +3297,7 @@ static void addrconf_dad_timer(unsigned long data)
 
                 ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
                 spin_unlock(&ifp->lock);
-                write_unlock(&idev->lock);
+                write_unlock_bh(&idev->lock);
 
                 addrconf_dad_completed(ifp);
 
@@ -3237,16 +3305,17 @@ static void addrconf_dad_timer(unsigned long data)
         }
 
         ifp->dad_probes--;
-        addrconf_mod_dad_timer(ifp,
-                               NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+        addrconf_mod_dad_work(ifp,
+                              NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
         spin_unlock(&ifp->lock);
-        write_unlock(&idev->lock);
+        write_unlock_bh(&idev->lock);
 
         /* send a neighbour solicitation for our addr */
         addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
         ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
 out:
         in6_ifa_put(ifp);
+        rtnl_unlock();
 }
 
 /* ifp->idev must be at least read locked */
@@ -3273,7 +3342,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
         struct in6_addr lladdr;
         bool send_rs, send_mld;
 
-        addrconf_del_dad_timer(ifp);
+        addrconf_del_dad_work(ifp);
 
         /*
          *      Configure the address for reception. Now it is valid.
@@ -3514,23 +3583,23 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
  *      Periodic address status verification
  */
 
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
 {
         unsigned long now, next, next_sec, next_sched;
         struct inet6_ifaddr *ifp;
         int i;
 
+        ASSERT_RTNL();
+
         rcu_read_lock_bh();
-        spin_lock(&addrconf_verify_lock);
         now = jiffies;
         next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
 
-        del_timer(&addr_chk_timer);
+        cancel_delayed_work(&addr_chk_work);
 
         for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 restart:
-                hlist_for_each_entry_rcu_bh(ifp,
-                                         &inet6_addr_lst[i], addr_lst) {
+                hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
                         unsigned long age;
 
                         /* When setting preferred_lft to a value not zero or
@@ -3625,13 +3694,22 @@ restart:
 
         ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
               now, next, next_sec, next_sched);
-
-        addr_chk_timer.expires = next_sched;
-        add_timer(&addr_chk_timer);
-        spin_unlock(&addrconf_verify_lock);
+        mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
         rcu_read_unlock_bh();
 }
 
+static void addrconf_verify_work(struct work_struct *w)
+{
+        rtnl_lock();
+        addrconf_verify_rtnl();
+        rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+        mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
 static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
                                      struct in6_addr **peer_pfx)
 {
@@ -3688,6 +3766,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
         bool was_managetempaddr;
         bool had_prefixroute;
 
+        ASSERT_RTNL();
+
         if (!valid_lft || (prefered_lft > valid_lft))
                 return -EINVAL;
 
@@ -3753,7 +3833,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
                                  !was_managetempaddr, jiffies);
         }
 
-        addrconf_verify(0);
+        addrconf_verify_rtnl();
 
         return 0;
 }
@@ -4383,6 +4463,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
         bool update_rs = false;
         struct in6_addr ll_addr;
 
+        ASSERT_RTNL();
+
         if (token == NULL)
                 return -EINVAL;
         if (ipv6_addr_any(token))
@@ -4431,7 +4513,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
         }
 
         write_unlock_bh(&idev->lock);
-        addrconf_verify(0);
+        addrconf_verify_rtnl();
         return 0;
 }
 
@@ -4633,6 +4715,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
         struct net *net = dev_net(ifp->idev->dev);
 
+        if (event)
+                ASSERT_RTNL();
+
         inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
 
         switch (event) {
@@ -5241,6 +5326,12 @@ int __init addrconf_init(void)
         if (err < 0)
                 goto out_addrlabel;
 
+        addrconf_wq = create_workqueue("ipv6_addrconf");
+        if (!addrconf_wq) {
+                err = -ENOMEM;
+                goto out_nowq;
+        }
+
         /* The addrconf netdev notifier requires that loopback_dev
          * has it's ipv6 private information allocated and setup
          * before it can bring up and give link-local addresses
@@ -5271,7 +5362,7 @@ int __init addrconf_init(void)
 
         register_netdevice_notifier(&ipv6_dev_notf);
 
-        addrconf_verify(0);
+        addrconf_verify();
 
         rtnl_af_register(&inet6_ops);
 
@@ -5299,6 +5390,8 @@ errout:
         rtnl_af_unregister(&inet6_ops);
         unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
+        destroy_workqueue(addrconf_wq);
+out_nowq:
         unregister_pernet_subsys(&addrconf_ops);
 out_addrlabel:
         ipv6_addr_label_cleanup();
@@ -5334,7 +5427,8 @@ void addrconf_cleanup(void)
         for (i = 0; i < IN6_ADDR_HSIZE; i++)
                 WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
         spin_unlock_bh(&addrconf_hash_lock);
-
-        del_timer(&addr_chk_timer);
+        cancel_delayed_work(&addr_chk_work);
         rtnl_unlock();
+
+        destroy_workqueue(addrconf_wq);
 }
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/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 070a2fae2375..64d6073731d3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -530,9 +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);
 }
 
@@ -1104,21 +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);
@@ -1135,7 +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;
@@ -1217,6 +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);
 
@@ -1314,8 +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/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()