8 files changed, 66 insertions, 21 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 8a3881e28aca..c29d75d8f1b1 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -801,11 +801,8 @@ static int arp_process(struct sk_buff *skb)
  *  cache.
  */
 
-        /*
-         *  Special case: IPv4 duplicate address detection packet (RFC2131)
-         *  and Gratuitous ARP/ARP Announce. (RFC3927, Section 2.4)
-         */
-        if (sip == 0 || tip == sip) {
+        /* Special case: IPv4 duplicate address detection packet (RFC2131) */
+        if (sip == 0) {
                 if (arp->ar_op == htons(ARPOP_REQUEST) &&
                     inet_addr_type(net, tip) == RTN_LOCAL &&
                     !arp_ignore(in_dev, sip, tip))
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 012cf5a68581..00a54b246dfe 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1021,6 +1021,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn)
                                       (struct node *)tn, wasfull);
 
                 tp = node_parent((struct node *) tn);
+                if (!tp)
+                        rcu_assign_pointer(t->trie, (struct node *)tn);
+
                 tnode_free_flush();
                 if (!tp)
                         break;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 490ce20faf38..db46b4b5b2b9 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -440,6 +440,9 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
         /* Remove any debris in the socket control block */
         memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 
+        /* Must drop socket now because of tproxy. */
+        skb_orphan(skb);
+
         return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL,
                        ip_rcv_finish);
 
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 155c008626c8..09172a65d9b6 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -191,7 +191,8 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb,
                                     ct, ctinfo);
                 /* Tell TCP window tracking about seq change */
                 nf_conntrack_tcp_update(skb, ip_hdrlen(skb),
-                                        ct, CTINFO2DIR(ctinfo));
+                                        ct, CTINFO2DIR(ctinfo),
+                                        (int)rep_len - (int)match_len);
 
                 nf_conntrack_event_cache(IPCT_NATSEQADJ, ct);
         }
@@ -377,6 +378,7 @@ nf_nat_seq_adjust(struct sk_buff *skb,
         struct tcphdr *tcph;
         int dir;
         __be32 newseq, newack;
+        s16 seqoff, ackoff;
         struct nf_conn_nat *nat = nfct_nat(ct);
         struct nf_nat_seq *this_way, *other_way;
 
@@ -390,15 +392,18 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 
         tcph = (void *)skb->data + ip_hdrlen(skb);
         if (after(ntohl(tcph->seq), this_way->correction_pos))
-                newseq = htonl(ntohl(tcph->seq) + this_way->offset_after);
+                seqoff = this_way->offset_after;
         else
-                newseq = htonl(ntohl(tcph->seq) + this_way->offset_before);
+                seqoff = this_way->offset_before;
 
         if (after(ntohl(tcph->ack_seq) - other_way->offset_before,
                   other_way->correction_pos))
-                newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after);
+                ackoff = other_way->offset_after;
         else
-                newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before);
+                ackoff = other_way->offset_before;
+
+        newseq = htonl(ntohl(tcph->seq) + seqoff);
+        newack = htonl(ntohl(tcph->ack_seq) - ackoff);
 
         inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0);
         inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0);
@@ -413,7 +418,7 @@ nf_nat_seq_adjust(struct sk_buff *skb,
         if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo))
                 return 0;
 
-        nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir);
+        nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff);
 
         return 1;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cd76b3cb7092..278f46f5011b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1085,8 +1085,35 @@ restart:
         now = jiffies;
 
         if (!rt_caching(dev_net(rt->u.dst.dev))) {
-                rt_drop(rt);
-                return 0;
+                /*
+                 * If we're not caching, just tell the caller we
+                 * were successful and don't touch the route.  The
+                 * caller hold the sole reference to the cache entry, and
+                 * it will be released when the caller is done with it.
+                 * If we drop it here, the callers have no way to resolve routes
+                 * when we're not caching.  Instead, just point *rp at rt, so
+                 * the caller gets a single use out of the route
+                 * Note that we do rt_free on this new route entry, so that
+                 * once its refcount hits zero, we are still able to reap it
+                 * (Thanks Alexey)
+                 * Note also the rt_free uses call_rcu.  We don't actually
+                 * need rcu protection here, this is just our path to get
+                 * on the route gc list.
+                 */
+
+                if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
+                        int err = arp_bind_neighbour(&rt->u.dst);
+                        if (err) {
+                                if (net_ratelimit())
+                                        printk(KERN_WARNING
+                                            "Neighbour table failure & not caching routes.\n");
+                                rt_drop(rt);
+                                return err;
+                        }
+                }
+
+                rt_free(rt);
+                goto skip_hashing;
         }
 
         rthp = &rt_hash_table[hash].chain;
@@ -1203,7 +1230,8 @@ restart:
 #if RT_CACHE_DEBUG >= 2
         if (rt->u.dst.rt_next) {
                 struct rtable *trt;
-                printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst);
+                printk(KERN_DEBUG "rt_cache @%02x: %pI4",
+                       hash, &rt->rt_dst);
                 for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
                         printk(" . %pI4", &trt->rt_dst);
                 printk("\n");
@@ -1217,6 +1245,8 @@ restart:
         rcu_assign_pointer(rt_hash_table[hash].chain, rt);
 
         spin_unlock_bh(rt_hash_lock_addr(hash));
+
+skip_hashing:
         if (rp)
                 *rp = rt;
         else
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 17b89c523f9d..7870a535dac6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -903,13 +903,17 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
                 iov++;
 
                 while (seglen > 0) {
-                        int copy;
+                        int copy = 0;
+                        int max = size_goal;
 
                         skb = tcp_write_queue_tail(sk);
+                        if (tcp_send_head(sk)) {
+                                if (skb->ip_summed == CHECKSUM_NONE)
+                                        max = mss_now;
+                                copy = max - skb->len;
+                        }
 
-                        if (!tcp_send_head(sk) ||
-                            (copy = size_goal - skb->len) <= 0) {
-
+                        if (copy <= 0) {
 new_segment:
                                 /* Allocate new segment. If the interface is SG,
                                  * allocate skb fitting to single page.
@@ -930,6 +934,7 @@ new_segment:
 
                                 skb_entail(sk, skb);
                                 copy = size_goal;
+                                max = size_goal;
                         }
 
                         /* Try to append data to the end of skb. */
@@ -1028,7 +1033,7 @@ new_segment:
                         if ((seglen -= copy) == 0 && iovlen == 0)
                                 goto out;
 
-                        if (skb->len < size_goal || (flags & MSG_OOB))
+                        if (skb->len < max || (flags & MSG_OOB))
                                 continue;
 
                         if (forced_push(tp)) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 43bbba7926ee..f8d67ccc64f3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -128,7 +128,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
                         goto kill_with_rst;
 
                 /* Dup ACK? */
-                if (!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
+                if (!th->ack ||
+                    !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
                     TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
                         inet_twsk_put(tw);
                         return TCP_TW_SUCCESS;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 416fc4c2e7eb..5bdf08d312d9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -725,7 +725,8 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
                                  unsigned int mss_now)
 {
-        if (skb->len <= mss_now || !sk_can_gso(sk)) {
+        if (skb->len <= mss_now || !sk_can_gso(sk) ||
+            skb->ip_summed == CHECKSUM_NONE) {
                 /* Avoid the costly divide in the normal
                  * non-TSO case.
                  */