10 files changed, 117 insertions, 17 deletions

diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a0d8392491c3..a69b4e4a02b5 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -269,7 +269,11 @@ static void ah_input_done(struct crypto_async_request *base, int err)
         skb->network_header += ah_hlen;
         memcpy(skb_network_header(skb), work_iph, ihl);
         __skb_pull(skb, ah_hlen + ihl);
-        skb_set_transport_header(skb, -ihl);
+
+        if (x->props.mode == XFRM_MODE_TUNNEL)
+                skb_reset_transport_header(skb);
+        else
+                skb_set_transport_header(skb, -ihl);
 out:
         kfree(AH_SKB_CB(skb)->tmp);
         xfrm_input_resume(skb, err);
@@ -381,7 +385,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
         skb->network_header += ah_hlen;
         memcpy(skb_network_header(skb), work_iph, ihl);
         __skb_pull(skb, ah_hlen + ihl);
-        skb_set_transport_header(skb, -ihl);
+        if (x->props.mode == XFRM_MODE_TUNNEL)
+                skb_reset_transport_header(skb);
+        else
+                skb_set_transport_header(skb, -ihl);
 
         err = nexthdr;
 
@@ -413,9 +420,12 @@ static void ah4_err(struct sk_buff *skb, u32 info)
         if (!x)
                 return;
 
-        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+                atomic_inc(&flow_cache_genid);
+                rt_genid_bump(net);
+
                 ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
-        else
+        } else
                 ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
         xfrm_state_put(x);
 }
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 424fafbc8cb0..b28e863fe0a7 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -85,3 +85,28 @@ out:
         return err;
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
+
+void ip4_datagram_release_cb(struct sock *sk)
+{
+        const struct inet_sock *inet = inet_sk(sk);
+        const struct ip_options_rcu *inet_opt;
+        __be32 daddr = inet->inet_daddr;
+        struct flowi4 fl4;
+        struct rtable *rt;
+
+        if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
+                return;
+
+        rcu_read_lock();
+        inet_opt = rcu_dereference(inet->inet_opt);
+        if (inet_opt && inet_opt->opt.srr)
+                daddr = inet_opt->opt.faddr;
+        rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
+                                   inet->inet_saddr, inet->inet_dport,
+                                   inet->inet_sport, sk->sk_protocol,
+                                   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+        if (!IS_ERR(rt))
+                __sk_dst_set(sk, &rt->dst);
+        rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b61e9deb7c7e..3b4f0cd2e63e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -346,7 +346,10 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 
         pskb_trim(skb, skb->len - alen - padlen - 2);
         __skb_pull(skb, hlen);
-        skb_set_transport_header(skb, -ihl);
+        if (x->props.mode == XFRM_MODE_TUNNEL)
+                skb_reset_transport_header(skb);
+        else
+                skb_set_transport_header(skb, -ihl);
 
         err = nexthdr[1];
 
@@ -499,9 +502,12 @@ static void esp4_err(struct sk_buff *skb, u32 info)
         if (!x)
                 return;
 
-        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+                atomic_inc(&flow_cache_genid);
+                rt_genid_bump(net);
+
                 ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
-        else
+        } else
                 ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
         xfrm_state_put(x);
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 303012adf9e6..e81b1caf2ea2 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -963,8 +963,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
                         ptr--;
                 }
                 if (tunnel->parms.o_flags&GRE_CSUM) {
+                        int offset = skb_transport_offset(skb);
+
                         *ptr = 0;
-                        *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr));
+                        *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
+                                                                 skb->len - offset,
+                                                                 0));
                 }
         }
 
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index d3ab47e19a89..9a46daed2f3c 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -47,9 +47,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
         if (!x)
                 return;
 
-        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+        if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+                atomic_inc(&flow_cache_genid);
+                rt_genid_bump(net);
+
                 ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
-        else
+        } else
                 ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
         xfrm_state_put(x);
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8f3d05424a3e..6f9c07268cf6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -738,6 +738,7 @@ struct proto ping_prot = {
         .recvmsg =      ping_recvmsg,
         .bind =         ping_bind,
         .backlog_rcv =  ping_queue_rcv_skb,
+        .release_cb =   ip4_datagram_release_cb,
         .hash =         ping_v4_hash,
         .unhash =       ping_v4_unhash,
         .get_port =     ping_v4_get_port,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 73d1e4df4bf6..6f08991409c3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -894,6 +894,7 @@ struct proto raw_prot = {
         .recvmsg           = raw_recvmsg,
         .bind              = raw_bind,
         .backlog_rcv       = raw_rcv_skb,
+        .release_cb        = ip4_datagram_release_cb,
         .hash              = raw_hash_sk,
         .unhash            = raw_unhash_sk,
         .obj_size          = sizeof(struct raw_sock),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 844a9ef60dbd..a0fcc47fee73 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -912,6 +912,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
         struct dst_entry *dst = &rt->dst;
         struct fib_result res;
 
+        if (dst_metric_locked(dst, RTAX_MTU))
+                return;
+
         if (dst->dev->mtu < mtu)
                 return;
 
@@ -962,7 +965,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 }
 EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
 
-void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
         const struct iphdr *iph = (const struct iphdr *) skb->data;
         struct flowi4 fl4;
@@ -975,6 +978,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
                 ip_rt_put(rt);
         }
 }
+
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+{
+        const struct iphdr *iph = (const struct iphdr *) skb->data;
+        struct flowi4 fl4;
+        struct rtable *rt;
+        struct dst_entry *dst;
+        bool new = false;
+
+        bh_lock_sock(sk);
+        rt = (struct rtable *) __sk_dst_get(sk);
+
+        if (sock_owned_by_user(sk) || !rt) {
+                __ipv4_sk_update_pmtu(skb, sk, mtu);
+                goto out;
+        }
+
+        __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+        if (!__sk_dst_check(sk, 0)) {
+                rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+                if (IS_ERR(rt))
+                        goto out;
+
+                new = true;
+        }
+
+        __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
+
+        dst = dst_check(&rt->dst, 0);
+        if (!dst) {
+                if (new)
+                        dst_release(&rt->dst);
+
+                rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+                if (IS_ERR(rt))
+                        goto out;
+
+                new = true;
+        }
+
+        if (new)
+                __sk_dst_set(sk, &rt->dst);
+
+out:
+        bh_unlock_sock(sk);
+}
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
 void ipv4_redirect(struct sk_buff *skb, struct net *net,
@@ -1120,7 +1170,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
         if (!mtu || time_after_eq(jiffies, rt->dst.expires))
                 mtu = dst_metric_raw(dst, RTAX_MTU);
 
-        if (mtu && rt_is_output_route(rt))
+        if (mtu)
                 return mtu;
 
         mtu = dst->dev->mtu;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 54139fa514e6..70b09ef2463b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -369,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
          * We do take care of PMTU discovery (RFC1191) special case :
          * we can receive locally generated ICMP messages while socket is held.
          */
-        if (sock_owned_by_user(sk) &&
-            type != ICMP_DEST_UNREACH &&
-            code != ICMP_FRAG_NEEDED)
-                NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
-
+        if (sock_owned_by_user(sk)) {
+                if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED))
+                        NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
+        }
         if (sk->sk_state == TCP_CLOSE)
                 goto out;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 79c8dbe59b54..1f4d405eafba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1952,6 +1952,7 @@ struct proto udp_prot = {
         .recvmsg           = udp_recvmsg,
         .sendpage          = udp_sendpage,
         .backlog_rcv       = __udp_queue_rcv_skb,
+        .release_cb        = ip4_datagram_release_cb,
         .hash              = udp_lib_hash,
         .unhash            = udp_lib_unhash,
         .rehash            = udp_v4_rehash,