Merge branch 'from-linus'

13 files changed, 54 insertions, 49 deletions

diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 6bb0c7eb1ef0..e060aad8624d 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -90,6 +90,7 @@ static struct rtable __fake_rtable = {
 			.dev			= &__fake_net_device,
 			.path			= &__fake_rtable.u.dst,
 			.metrics		= {[RTAX_MTU - 1] = 1500},
+			.flags			= DST_NOXFRM,
 		}
 	},
 	.rt_flags	= 0,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6766f118f070..2144952d1c6c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -411,6 +411,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	C(pkt_type);
 	C(ip_summed);
 	C(priority);
+#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+	C(ipvs_property);
+#endif
 	C(protocol);
 	n->destructor = NULL;
 #ifdef CONFIG_NETFILTER
@@ -422,13 +425,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	C(nfct_reasm);
 	nf_conntrack_get_reasm(skb->nfct_reasm);
 #endif
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
-	C(ipvs_property);
-#endif
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	C(nfct_reasm);
-	nf_conntrack_get_reasm(skb->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	C(nf_bridge);
 	nf_bridge_get(skb->nf_bridge);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9890fd97e538..c971f14712ec 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -95,6 +95,12 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
 		saddr = dev->dev_addr;
 	memcpy(eth->h_source,saddr,dev->addr_len);
 
+	if(daddr)
+	{
+		memcpy(eth->h_dest,daddr,dev->addr_len);
+		return ETH_HLEN;
+	}
+	
 	/*
 	 *	Anyway, the loopback-device should never use this function... 
 	 */
@@ -105,12 +111,6 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
 		return ETH_HLEN;
 	}
 	
-	if(daddr)
-	{
-		memcpy(eth->h_dest,daddr,dev->addr_len);
-		return ETH_HLEN;
-	}
-	
 	return -ETH_HLEN;
 }
 
diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c
index c1a61462507f..1741d555ad0d 100644
--- a/net/ipv4/netfilter/ip_nat_core.c
+++ b/net/ipv4/netfilter/ip_nat_core.c
@@ -434,6 +434,7 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb,
 	} *inside;
 	struct ip_conntrack_tuple inner, target;
 	int hdrlen = (*pskb)->nh.iph->ihl * 4;
+	unsigned long statusbit;
 
 	if (!skb_make_writable(pskb, hdrlen + sizeof(*inside)))
 		return 0;
@@ -495,17 +496,16 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb,
 
 	/* Change outer to look the reply to an incoming packet
 	 * (proto 0 means don't invert per-proto part). */
+	if (manip == IP_NAT_MANIP_SRC)
+		statusbit = IPS_SRC_NAT;
+	else
+		statusbit = IPS_DST_NAT;
 
-	/* Obviously, we need to NAT destination IP, but source IP
-	   should be NAT'ed only if it is from a NAT'd host.
+	/* Invert if this is reply dir. */
+	if (dir == IP_CT_DIR_REPLY)
+		statusbit ^= IPS_NAT_MASK;
 
-	   Explanation: some people use NAT for anonymizing.  Also,
-	   CERT recommends dropping all packets from private IP
-	   addresses (although ICMP errors from internal links with
-	   such addresses are not too uncommon, as Alan Cox points
-	   out) */
-	if (manip != IP_NAT_MANIP_SRC
-	    || ((*pskb)->nh.iph->saddr == ct->tuplehash[dir].tuple.src.ip)) {
+	if (ct->status & statusbit) {
 		invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
 		if (!manip_pkt(0, pskb, 0, &target, manip))
 			return 0;
diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c
index 7c3f7d380240..ab1f88fa21ec 100644
--- a/net/ipv4/netfilter/ip_nat_standalone.c
+++ b/net/ipv4/netfilter/ip_nat_standalone.c
@@ -200,20 +200,14 @@ ip_nat_in(unsigned int hooknum,
           const struct net_device *out,
           int (*okfn)(struct sk_buff *))
 {
-	struct ip_conntrack *ct;
-	enum ip_conntrack_info ctinfo;
 	unsigned int ret;
+	u_int32_t daddr = (*pskb)->nh.iph->daddr;
 
 	ret = ip_nat_fn(hooknum, pskb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN
-	    && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.dst.ip !=
-		    ct->tuplehash[!dir].tuple.src.ip) {
-			dst_release((*pskb)->dst);
-			(*pskb)->dst = NULL;
-		}
+	    && daddr != (*pskb)->nh.iph->daddr) {
+		dst_release((*pskb)->dst);
+		(*pskb)->dst = NULL;
 	}
 	return ret;
 }
@@ -276,7 +270,7 @@ ip_nat_local_fn(unsigned int hooknum,
 		    ct->tuplehash[!dir].tuple.src.ip
 #ifdef CONFIG_XFRM
 		    || ct->tuplehash[dir].tuple.dst.u.all !=
-		       ct->tuplehash[dir].tuple.src.u.all
+		       ct->tuplehash[!dir].tuple.src.u.all
 #endif
 		    )
 			return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d82c242ea704..fca5fe0cf94a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -835,7 +835,7 @@ static int rt_garbage_collect(void)
 					int r;
 
 					rthp = rt_remove_balanced_route(
-						&rt_hash_table[i].chain,
+						&rt_hash_table[k].chain,
 						rth,
 						&r);
 					goal -= r;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 45f7ae58f2c0..f285bbf296e2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -35,6 +35,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
 		if (xdst->u.rt.fl.oif == fl->oif &&	/*XXX*/
 		    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
 	    	    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
+	    	    xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
 		    xfrm_bundle_ok(xdst, fl, AF_INET)) {
 			dst_clone(dst);
 			break;
@@ -61,7 +62,8 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
 		.nl_u = {
 			.ip4_u = {
 				.saddr = local,
-				.daddr = remote
+				.daddr = remote,
+				.tos = fl->fl4_tos
 			}
 		}
 	};
@@ -230,6 +232,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl)
 	fl->proto = iph->protocol;
 	fl->fl4_dst = iph->daddr;
 	fl->fl4_src = iph->saddr;
+	fl->fl4_tos = iph->tos;
 }
 
 static inline int xfrm4_garbage_collect(void)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index efa3e72cfcfa..f999edd846a9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -494,6 +494,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	struct net_device *dev;
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info*)skb->dst;
+	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
@@ -505,7 +506,12 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
 	nexthdr = *prevhdr;
 
-	mtu = dst_mtu(&rt->u.dst) - hlen - sizeof(struct frag_hdr);
+	mtu = dst_mtu(&rt->u.dst);
+	if (np && np->frag_size < mtu) {
+		if (np->frag_size)
+			mtu = np->frag_size;
+	}
+	mtu -= hlen + sizeof(struct frag_hdr);
 
 	if (skb_shinfo(skb)->frag_list) {
 		int first_len = skb_pagelen(skb);
@@ -882,7 +888,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		inet->cork.fl = *fl;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
+		mtu = dst_mtu(rt->u.dst.path);
+		if (np && np->frag_size < mtu) {
+			if (np->frag_size)
+				mtu = np->frag_size;
+		}
+		inet->cork.fragsize = mtu;
 		if (dst_allfrag(rt->u.dst.path))
 			inet->cork.flags |= IPCORK_ALLFRAG;
 		inet->cork.length = 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 92ead3cf956b..48597538db3f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -458,7 +458,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
 
-		if ((len = sizeof (*ipv6h) + ipv6h->payload_len) > mtu) {
+		if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
 			rel_type = ICMPV6_PKT_TOOBIG;
 			rel_code = 0;
 			rel_info = mtu;
@@ -884,6 +884,7 @@ ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
 	t->parms.encap_limit = p->encap_limit;
 	t->parms.flowinfo = p->flowinfo;
 	t->parms.link = p->link;
+	ip6_tnl_dst_reset(t);
 	ip6ip6_tnl_link_config(t);
 	return 0;
 }
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ae86d237a456..b2d4d1dd2116 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1423,7 +1423,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
-		xfrm_state_put(x);
+		__xfrm_state_put(x);
 		goto out;
 	}
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 98ec53bd3ac7..8206025d8e46 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -782,7 +782,7 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
 	int nx = 0;
 	int err;
 	u32 genid;
-	u16 family = dst_orig->ops->family;
+	u16 family;
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	u32 sk_sid = security_sk_sid(sk, fl, dir);
 restart:
@@ -796,13 +796,14 @@ restart:
 		if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT])
 			return 0;
 
-		policy = flow_cache_lookup(fl, sk_sid, family, dir,
-					   xfrm_policy_lookup);
+		policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family,
+					   dir, xfrm_policy_lookup);
 	}
 
 	if (!policy)
 		return 0;
 
+	family = dst_orig->ops->family;
 	policy->curlft.use_time = (unsigned long)xtime.tv_sec;
 
 	switch (policy->action) {
@@ -885,8 +886,6 @@ restart:
 			 * We can't enlist stable bundles either.
 			 */
 			write_unlock_bh(&policy->lock);
-
-			xfrm_pol_put(policy);
 			if (dst)
 				dst_free(dst);
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e12d0be5f976..c656cbaf35e8 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -220,14 +220,14 @@ static int __xfrm_state_delete(struct xfrm_state *x)
 		x->km.state = XFRM_STATE_DEAD;
 		spin_lock(&xfrm_state_lock);
 		list_del(&x->bydst);
-		atomic_dec(&x->refcnt);
+		__xfrm_state_put(x);
 		if (x->id.spi) {
 			list_del(&x->byspi);
-			atomic_dec(&x->refcnt);
+			__xfrm_state_put(x);
 		}
 		spin_unlock(&xfrm_state_lock);
 		if (del_timer(&x->timer))
-			atomic_dec(&x->refcnt);
+			__xfrm_state_put(x);
 
 		/* The number two in this test is the reference
 		 * mentioned in the comment below plus the reference
@@ -243,7 +243,7 @@ static int __xfrm_state_delete(struct xfrm_state *x)
 		 * The xfrm_state_alloc call gives a reference, and that
 		 * is what we are dropping here.
 		 */
-		atomic_dec(&x->refcnt);
+		__xfrm_state_put(x);
 		err = 0;
 	}
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ac87a09ba83e..7de17559249a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -345,7 +345,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
-		xfrm_state_put(x);
+		__xfrm_state_put(x);
 		goto out;
 	}