Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

6 files changed, 46 insertions, 61 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0600f0fbe325..1b745d412cf6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -465,8 +465,10 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
         if (addr_len < sizeof(struct sockaddr_in))
                 goto out;
 
-        if (addr->sin_family != AF_INET)
+        if (addr->sin_family != AF_INET) {
+                err = -EAFNOSUPPORT;
                 goto out;
+        }
 
         chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 167da8ba416a..54119d5aae8f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -802,8 +802,6 @@ static int __ip_append_data(struct sock *sk,
         skb = skb_peek_tail(queue);
 
         exthdrlen = !skb ? rt->dst.header_len : 0;
-        length += exthdrlen;
-        transhdrlen += exthdrlen;
         mtu = cork->fragsize;
 
         hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -830,7 +828,7 @@ static int __ip_append_data(struct sock *sk,
         cork->length += length;
         if (((length > mtu) || (skb && skb_is_gso(skb))) &&
             (sk->sk_protocol == IPPROTO_UDP) &&
-            (rt->dst.dev->features & NETIF_F_UFO)) {
+            (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
                 err = ip_ufo_append_data(sk, queue, getfrag, from, length,
                                          hh_len, fragheaderlen, transhdrlen,
                                          mtu, flags);
@@ -883,17 +881,16 @@ alloc_new_skb:
                         else
                                 alloclen = fraglen;
 
+                        alloclen += exthdrlen;
+
                         /* The last fragment gets additional space at tail.
                          * Note, with MSG_MORE we overallocate on fragments,
                          * because we have no idea what fragment will be
                          * the last.
                          */
-                        if (datalen == length + fraggap) {
+                        if (datalen == length + fraggap)
                                 alloclen += rt->dst.trailer_len;
-                                /* make sure mtu is not reached */
-                                if (datalen > mtu - fragheaderlen - rt->dst.trailer_len)
-                                        datalen -= ALIGN(rt->dst.trailer_len, 8);
-                        }
+
                         if (transhdrlen) {
                                 skb = sock_alloc_send_skb(sk,
                                                 alloclen + hh_len + 15,
@@ -926,11 +923,11 @@ alloc_new_skb:
                         /*
                          *      Find where to start putting bytes.
                          */
-                        data = skb_put(skb, fraglen);
+                        data = skb_put(skb, fraglen + exthdrlen);
                         skb_set_network_header(skb, exthdrlen);
                         skb->transport_header = (skb->network_header +
                                                  fragheaderlen);
-                        data += fragheaderlen;
+                        data += fragheaderlen + exthdrlen;
 
                         if (fraggap) {
                                 skb->csum = skb_copy_and_csum_bits(
@@ -1064,7 +1061,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
          */
         *rtp = NULL;
         cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-                         rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+                         rt->dst.dev->mtu : dst_mtu(&rt->dst);
         cork->dst = &rt->dst;
         cork->length = 0;
         cork->tx_flags = ipc->tx_flags;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 4614babdc45f..2e97e3ec1eb7 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,51 +17,35 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
         const struct iphdr *iph = ip_hdr(skb);
         struct rtable *rt;
         struct flowi4 fl4 = {};
-        unsigned long orefdst;
+        __be32 saddr = iph->saddr;
+        __u8 flags = 0;
         unsigned int hh_len;
-        unsigned int type;
 
-        type = inet_addr_type(net, iph->saddr);
-        if (skb->sk && inet_sk(skb->sk)->transparent)
-                type = RTN_LOCAL;
-        if (addr_type == RTN_UNSPEC)
-                addr_type = type;
+        if (!skb->sk && addr_type != RTN_LOCAL) {
+                if (addr_type == RTN_UNSPEC)
+                        addr_type = inet_addr_type(net, saddr);
+                if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
+                        flags |= FLOWI_FLAG_ANYSRC;
+                else
+                        saddr = 0;
+        }
 
         /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
          * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
          */
-        if (addr_type == RTN_LOCAL) {
-                fl4.daddr = iph->daddr;
-                if (type == RTN_LOCAL)
-                        fl4.saddr = iph->saddr;
-                fl4.flowi4_tos = RT_TOS(iph->tos);
-                fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
-                fl4.flowi4_mark = skb->mark;
-                fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
-                rt = ip_route_output_key(net, &fl4);
-                if (IS_ERR(rt))
-                        return -1;
-
-                /* Drop old route. */
-                skb_dst_drop(skb);
-                skb_dst_set(skb, &rt->dst);
-        } else {
-                /* non-local src, find valid iif to satisfy
-                 * rp-filter when calling ip_route_input. */
-                fl4.daddr = iph->saddr;
-                rt = ip_route_output_key(net, &fl4);
-                if (IS_ERR(rt))
-                        return -1;
+        fl4.daddr = iph->daddr;
+        fl4.saddr = saddr;
+        fl4.flowi4_tos = RT_TOS(iph->tos);
+        fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+        fl4.flowi4_mark = skb->mark;
+        fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags;
+        rt = ip_route_output_key(net, &fl4);
+        if (IS_ERR(rt))
+                return -1;
 
-                orefdst = skb->_skb_refdst;
-                if (ip_route_input(skb, iph->daddr, iph->saddr,
-                                   RT_TOS(iph->tos), rt->dst.dev) != 0) {
-                        dst_release(&rt->dst);
-                        return -1;
-                }
-                dst_release(&rt->dst);
-                refdst_drop(orefdst);
-        }
+        /* Drop old route. */
+        skb_dst_drop(skb);
+        skb_dst_set(skb, &rt->dst);
 
         if (skb_dst(skb)->error)
                 return -1;
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 1ff79e557f96..51f13f8ec724 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -40,7 +40,6 @@ static void send_reset(struct sk_buff *oldskb, int hook)
         struct iphdr *niph;
         const struct tcphdr *oth;
         struct tcphdr _otcph, *tcph;
-        unsigned int addr_type;
 
         /* IP header checks: fragment. */
         if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
@@ -55,6 +54,9 @@ static void send_reset(struct sk_buff *oldskb, int hook)
         if (oth->rst)
                 return;
 
+        if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+                return;
+
         /* Check checksum */
         if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
                 return;
@@ -101,19 +103,11 @@ static void send_reset(struct sk_buff *oldskb, int hook)
         nskb->csum_start = (unsigned char *)tcph - nskb->head;
         nskb->csum_offset = offsetof(struct tcphdr, check);
 
-        addr_type = RTN_UNSPEC;
-        if (hook != NF_INET_FORWARD
-#ifdef CONFIG_BRIDGE_NETFILTER
-            || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED)
-#endif
-           )
-                addr_type = RTN_LOCAL;
-
         /* ip_route_me_harder expects skb->dst to be set */
         skb_dst_set_noref(nskb, skb_dst(oldskb));
 
         nskb->protocol = htons(ETH_P_IP);
-        if (ip_route_me_harder(nskb, addr_type))
+        if (ip_route_me_harder(nskb, RTN_UNSPEC))
                 goto free_nskb;
 
         niph->ttl       = ip4_dst_hoplimit(skb_dst(nskb));
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 37aa9bf8d382..95e0d3b8977f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1250,6 +1250,9 @@ csum_copy_err:
 
         if (noblock)
                 return -EAGAIN;
+
+        /* starting over for a new packet */
+        msg->msg_flags &= ~MSG_TRUNC;
         goto try_again;
 }
 
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 2d51840e53a1..327a617d594c 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -32,7 +32,12 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
         dst = skb_dst(skb);
         mtu = dst_mtu(dst);
         if (skb->len > mtu) {
-                icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+                if (skb->sk)
+                        ip_local_error(skb->sk, EMSGSIZE, ip_hdr(skb)->daddr,
+                                       inet_sk(skb->sk)->inet_dport, mtu);
+                else
+                        icmp_send(skb, ICMP_DEST_UNREACH,
+                                  ICMP_FRAG_NEEDED, htonl(mtu));
                 ret = -EMSGSIZE;
         }
 out: