Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking updates from David Miller:

 1) UAPI changes for networking from David Howells

 2) A netlink dump is an operation we can sleep within, and therefore we
    need to make sure the dump provider module doesn't disappear on us
    meanwhile.  Fix from Gao Feng.

 3) Now that tunnels support GRO, we have to be more careful in
    skb_gro_reset_offset() otherwise we OOPS, from Eric Dumazet.

 4) We can end up processing packets for VLANs we aren't actually
    configured to be on, fix from Florian Zumbiehl.

 5) Fix routing cache removal regression in redirects and IPVS.  The
    core issue on the IPVS side is that it wants to rewrite who the
    nexthop is and we have to explicitly accomodate that case.  From
    Julian Anastasov.

 6) Error code return fixes all over the networking drivers from Peter
    Senna Tschudin.

 7) Fix routing cache removal regressions in IPSEC, from Steffen
    Klassert.

 8) Fix deadlock in RDS during pings, from Jeff Liu.

 9) Neighbour packet queue can trigger skb_under_panic() because we do
    not reset the network header of the SKB in the right spot.  From
    Ramesh Nagappa.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
  RDS: fix rds-ping spinlock recursion
  netdev/phy: Prototype of_mdio_find_bus()
  farsync: fix support for over 30 cards
  be2net: Remove code that stops further access to BE NIC based on UE bits
  pch_gbe: Fix build error by selecting all the possible dependencies.
  e1000e: add device IDs for i218
  ixgbe/ixgbevf: Limit maximum jumbo frame size to 9.5K to avoid Tx hangs
  ixgbevf: Set the netdev number of Tx queues
  UAPI: (Scripted) Disintegrate include/linux/tc_ematch
  UAPI: (Scripted) Disintegrate include/linux/tc_act
  UAPI: (Scripted) Disintegrate include/linux/netfilter_ipv6
  UAPI: (Scripted) Disintegrate include/linux/netfilter_ipv4
  UAPI: (Scripted) Disintegrate include/linux/netfilter_bridge
  UAPI: (Scripted) Disintegrate include/linux/netfilter_arp
  UAPI: (Scripted) Disintegrate include/linux/netfilter/ipset
  UAPI: (Scripted) Disintegrate include/linux/netfilter
  UAPI: (Scripted) Disintegrate include/linux/isdn
  UAPI: (Scripted) Disintegrate include/linux/caif
  net: fix typo in freescale/ucc_geth.c
  vxlan: fix more sparse warnings
  ...

15 files changed, 178 insertions, 165 deletions

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index add69d0fd99d..fbbf1fa00940 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -5,7 +5,7 @@
 #include <linux/export.h>
 #include "vlan.h"
 
-bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
+bool vlan_do_receive(struct sk_buff **skbp)
 {
 	struct sk_buff *skb = *skbp;
 	u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
@@ -13,14 +13,8 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
 	struct vlan_pcpu_stats *rx_stats;
 
 	vlan_dev = vlan_find_dev(skb->dev, vlan_id);
-	if (!vlan_dev) {
-		/* Only the last call to vlan_do_receive() should change
-		 * pkt_type to PACKET_OTHERHOST
-		 */
-		if (vlan_id && last_handler)
-			skb->pkt_type = PACKET_OTHERHOST;
+	if (!vlan_dev)
 		return false;
-	}
 
 	skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
diff --git a/net/core/dev.c b/net/core/dev.c
index 1e0a1847c3bb..09cb3f6dc40c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3300,18 +3300,18 @@ ncls:
 				&& !skb_pfmemalloc_protocol(skb))
 		goto drop;
 
-	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (vlan_tx_tag_present(skb)) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
 		}
-		if (vlan_do_receive(&skb, !rx_handler))
+		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
 			goto unlock;
 	}
 
+	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (rx_handler) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -3331,6 +3331,9 @@ ncls:
 		}
 	}
 
+	if (vlan_tx_nonzero_tag_present(skb))
+		skb->pkt_type = PACKET_OTHERHOST;
+
 	/* deliver only exact match when indicated */
 	null_or_dev = deliver_exact ? skb->dev : NULL;
 
@@ -3471,17 +3474,31 @@ out:
 	return netif_receive_skb(skb);
 }
 
-inline void napi_gro_flush(struct napi_struct *napi)
+/* napi->gro_list contains packets ordered by age.
+ * youngest packets at the head of it.
+ * Complete skbs in reverse order to reduce latencies.
+ */
+void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	struct sk_buff *skb, *next;
+	struct sk_buff *skb, *prev = NULL;
 
-	for (skb = napi->gro_list; skb; skb = next) {
-		next = skb->next;
+	/* scan list and build reverse chain */
+	for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
+		skb->prev = prev;
+		prev = skb;
+	}
+
+	for (skb = prev; skb; skb = prev) {
 		skb->next = NULL;
+
+		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
+			return;
+
+		prev = skb->prev;
 		napi_gro_complete(skb);
+		napi->gro_count--;
 	}
 
-	napi->gro_count = 0;
 	napi->gro_list = NULL;
 }
 EXPORT_SYMBOL(napi_gro_flush);
@@ -3542,6 +3559,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 	napi->gro_count++;
 	NAPI_GRO_CB(skb)->count = 1;
+	NAPI_GRO_CB(skb)->age = jiffies;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -3631,20 +3649,22 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(napi_skb_finish);
 
-void skb_gro_reset_offset(struct sk_buff *skb)
+static void skb_gro_reset_offset(struct sk_buff *skb)
 {
+	const struct skb_shared_info *pinfo = skb_shinfo(skb);
+	const skb_frag_t *frag0 = &pinfo->frags[0];
+
 	NAPI_GRO_CB(skb)->data_offset = 0;
 	NAPI_GRO_CB(skb)->frag0 = NULL;
 	NAPI_GRO_CB(skb)->frag0_len = 0;
 
 	if (skb->mac_header == skb->tail &&
-	    !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
-		NAPI_GRO_CB(skb)->frag0 =
-			skb_frag_address(&skb_shinfo(skb)->frags[0]);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
+	    pinfo->nr_frags &&
+	    !PageHighMem(skb_frag_page(frag0))) {
+		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
 	}
 }
-EXPORT_SYMBOL(skb_gro_reset_offset);
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -3876,7 +3896,7 @@ void napi_complete(struct napi_struct *n)
 	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
 		return;
 
-	napi_gro_flush(n);
+	napi_gro_flush(n, false);
 	local_irq_save(flags);
 	__napi_complete(n);
 	local_irq_restore(flags);
@@ -3981,8 +4001,17 @@ static void net_rx_action(struct softirq_action *h)
 				local_irq_enable();
 				napi_complete(n);
 				local_irq_disable();
-			} else
+			} else {
+				if (n->gro_list) {
+					/* flush too old packets
+					 * If HZ < 1000, flush all packets.
+					 */
+					local_irq_enable();
+					napi_gro_flush(n, HZ >= 1000);
+					local_irq_disable();
+				}
 				list_move_tail(&n->poll_list, &sd->poll_list);
+			}
 		}
 
 		netpoll_poll_unlock(have);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index baca771caae2..22571488730a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1301,8 +1301,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 	if (!dst)
 		goto discard;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	if (!neigh_event_send(neigh, skb)) {
 		int err;
 		struct net_device *dev = neigh->dev;
@@ -1312,6 +1310,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 			neigh_hh_init(neigh, dst);
 
 		do {
+			__skb_pull(skb, skb_network_offset(skb));
 			seq = read_seqbegin(&neigh->ha_lock);
 			err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 					      neigh->ha, NULL, skb->len);
@@ -1342,9 +1341,8 @@ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
 	unsigned int seq;
 	int err;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	do {
+		__skb_pull(skb, skb_network_offset(skb));
 		seq = read_seqbegin(&neigh->ha_lock);
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 				      neigh->ha, NULL, skb->len);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cdc28598f4ef..6e04b1fa11f2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -655,53 +655,6 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
-/**
- * 	skb_recycle - clean up an skb for reuse
- * 	@skb: buffer
- *
- * 	Recycles the skb to be reused as a receive buffer. This
- * 	function does any necessary reference count dropping, and
- * 	cleans up the skbuff as if it just came from __alloc_skb().
- */
-void skb_recycle(struct sk_buff *skb)
-{
-	struct skb_shared_info *shinfo;
-
-	skb_release_head_state(skb);
-
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->data = skb->head + NET_SKB_PAD;
-	skb_reset_tail_pointer(skb);
-}
-EXPORT_SYMBOL(skb_recycle);
-
-/**
- *	skb_recycle_check - check if skb can be reused for receive
- *	@skb: buffer
- *	@skb_size: minimum receive buffer size
- *
- *	Checks that the skb passed in is not shared or cloned, and
- *	that it is linear and its head portion at least as large as
- *	skb_size so that it can be recycled as a receive buffer.
- *	If these conditions are met, this function does any necessary
- *	reference count dropping and cleans up the skbuff as if it
- *	just came from __alloc_skb().
- */
-bool skb_recycle_check(struct sk_buff *skb, int skb_size)
-{
-	if (!skb_is_recycleable(skb, skb_size))
-		return false;
-
-	skb_recycle(skb);
-
-	return true;
-}
-EXPORT_SYMBOL(skb_recycle_check);
-
 static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 {
 	new->tstamp		= old->tstamp;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 68c93d1bb03a..825c608826de 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -322,7 +322,8 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 {
 	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
 
-	if (!r && !fib_num_tclassid_users(dev_net(dev))) {
+	if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
+	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
 		*itag = 0;
 		return 0;
 	}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 267753060ffc..71b125cd5db1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -840,6 +840,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	change_nexthops(fi) {
 		nexthop_nh->nh_parent = fi;
 		nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+		if (!nexthop_nh->nh_pcpu_rth_output)
+			goto failure;
 	} endfor_nexthops(fi)
 
 	if (cfg->fc_mx) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f0c5b9c1a957..d34ce2972c8f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -406,7 +406,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	return &rt->dst;
 
@@ -442,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index ab09b126423c..694de3b7aebf 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -85,7 +85,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
+	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
 	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24a29a39e9a8..6537a408a4fb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -193,7 +193,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr;
+	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
 	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff622069fcef..1a0da8dc8180 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -802,7 +802,8 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	net = dev_net(rt->dst.dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
 	if (!peer) {
-		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
+			  rt_nexthop(rt, ip_hdr(skb)->daddr));
 		return;
 	}
 
@@ -827,7 +828,9 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->rate_tokens)))) {
-		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+		__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
+
+		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
@@ -835,7 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		    peer->rate_tokens == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
 					     &ip_hdr(skb)->saddr, inet_iif(skb),
-					     &ip_hdr(skb)->daddr, &rt->rt_gateway);
+					     &ip_hdr(skb)->daddr, &gw);
 #endif
 	}
 out_put_peer:
@@ -904,22 +907,32 @@ out:	kfree_skb(skb);
 	return 0;
 }
 
-static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
+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->dev->mtu < mtu)
+		return;
+
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
+	if (!rt->rt_pmtu) {
+		dst->obsolete = DST_OBSOLETE_KILL;
+	} else {
+		rt->rt_pmtu = mtu;
+		dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
+	}
+
 	rcu_read_lock();
-	if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
+	if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
 		struct fib_nh *nh = &FIB_RES_NH(res);
 
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
 				      jiffies + ip_rt_mtu_expires);
 	}
 	rcu_read_unlock();
-	return mtu;
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
@@ -929,14 +942,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
-	mtu = __ip_rt_update_pmtu(rt, &fl4, mtu);
-
-	if (!rt->rt_pmtu) {
-		dst->obsolete = DST_OBSOLETE_KILL;
-	} else {
-		rt->rt_pmtu = mtu;
-		rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
-	}
+	__ip_rt_update_pmtu(rt, &fl4, mtu);
 }
 
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
@@ -1120,7 +1126,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = dst->dev->mtu;
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-		if (rt->rt_gateway && mtu > 576)
+		if (rt->rt_uses_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1171,7 +1177,9 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 		if (fnhe->fnhe_gw) {
 			rt->rt_flags |= RTCF_REDIRECTED;
 			rt->rt_gateway = fnhe->fnhe_gw;
-		}
+			rt->rt_uses_gateway = 1;
+		} else if (!rt->rt_gateway)
+			rt->rt_gateway = daddr;
 
 		orig = rcu_dereference(fnhe->fnhe_rth);
 		rcu_assign_pointer(fnhe->fnhe_rth, rt);
@@ -1180,13 +1188,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 
 		fnhe->fnhe_stamp = jiffies;
 		ret = true;
-	} else {
-		/* Routes we intend to cache in nexthop exception have
-		 * the DST_NOCACHE bit clear.  However, if we are
-		 * unsuccessful at storing this route into the cache
-		 * we really need to set it.
-		 */
-		rt->dst.flags |= DST_NOCACHE;
 	}
 	spin_unlock_bh(&fnhe_lock);
 
@@ -1201,8 +1202,6 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (rt_is_input_route(rt)) {
 		p = (struct rtable **)&nh->nh_rth_input;
 	} else {
-		if (!nh->nh_pcpu_rth_output)
-			goto nocache;
 		p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
 	}
 	orig = *p;
@@ -1211,16 +1210,8 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (prev == orig) {
 		if (orig)
 			rt_free(orig);
-	} else {
-		/* Routes we intend to cache in the FIB nexthop have
-		 * the DST_NOCACHE bit clear.  However, if we are
-		 * unsuccessful at storing this route into the cache
-		 * we really need to set it.
-		 */
-nocache:
-		rt->dst.flags |= DST_NOCACHE;
+	} else
 		ret = false;
-	}
 
 	return ret;
 }
@@ -1281,8 +1272,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 	if (fi) {
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
 			rt->rt_gateway = nh->nh_gw;
+			rt->rt_uses_gateway = 1;
+		}
 		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
@@ -1291,8 +1284,18 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			cached = rt_bind_exception(rt, fnhe, daddr);
 		else if (!(rt->dst.flags & DST_NOCACHE))
 			cached = rt_cache_route(nh, rt);
-	}
-	if (unlikely(!cached))
+		if (unlikely(!cached)) {
+			/* Routes we intend to cache in nexthop exception or
+			 * FIB nexthop have the DST_NOCACHE bit clear.
+			 * However, if we are unsuccessful at storing this
+			 * route into the cache we really need to set it.
+			 */
+			rt->dst.flags |= DST_NOCACHE;
+			if (!rt->rt_gateway)
+				rt->rt_gateway = daddr;
+			rt_add_uncached_list(rt);
+		}
+	} else
 		rt_add_uncached_list(rt);
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1360,6 +1363,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->rt_iif	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 	if (our) {
 		rth->dst.input= ip_local_deliver;
@@ -1429,7 +1433,6 @@ static int __mkroute_input(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-
 	err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
 				  in_dev->dev, in_dev, &itag);
 	if (err < 0) {
@@ -1439,10 +1442,13 @@ static int __mkroute_input(struct sk_buff *skb,
 		goto cleanup;
 	}
 
-	if (out_dev == in_dev && err &&
+	do_cache = res->fi && !itag;
+	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
 		flags |= RTCF_DOREDIRECT;
+		do_cache = false;
+	}
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1459,15 +1465,11 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	do_cache = false;
-	if (res->fi) {
-		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-			if (rt_cache_valid(rth)) {
-				skb_dst_set_noref(skb, &rth->dst);
-				goto out;
-			}
-			do_cache = true;
+	if (do_cache) {
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+		if (rt_cache_valid(rth)) {
+			skb_dst_set_noref(skb, &rth->dst);
+			goto out;
 		}
 	}
 
@@ -1486,6 +1488,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_iif 	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 
 	rth->dst.input = ip_forward;
@@ -1656,6 +1659,7 @@ local_input:
 	rth->rt_iif	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
@@ -1758,6 +1762,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
+	bool do_cache;
 
 	in_dev = __in_dev_get_rcu(dev_out);
 	if (!in_dev)
@@ -1794,24 +1799,36 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	}
 
 	fnhe = NULL;
+	do_cache = fi != NULL;
 	if (fi) {
 		struct rtable __rcu **prth;
+		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+		fnhe = find_exception(nh, fl4->daddr);
 		if (fnhe)
 			prth = &fnhe->fnhe_rth;
-		else
-			prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+		else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
+			}
+			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
 		}
 	}
+
+add:
 	rth = rt_dst_alloc(dev_out,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
 			   IN_DEV_CONF_GET(in_dev, NOXFRM),
-			   fi);
+			   do_cache);
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
@@ -1824,6 +1841,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_iif	= orig_oif ? : 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway = 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 
 	RT_CACHE_STAT_INC(out_slow_tot);
@@ -2102,6 +2120,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
 		rt->rt_gateway = ort->rt_gateway;
+		rt->rt_uses_gateway = ort->rt_uses_gateway;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
 
@@ -2180,12 +2199,22 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 		if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_gateway &&
+	if (rt->rt_uses_gateway &&
 	    nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
 		goto nla_put_failure;
 
+	expires = rt->dst.expires;
+	if (expires) {
+		unsigned long now = jiffies;
+
+		if (time_before(now, expires))
+			expires -= now;
+		else
+			expires = 0;
+	}
+
 	memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
-	if (rt->rt_pmtu)
+	if (rt->rt_pmtu && expires)
 		metrics[RTAX_MTU - 1] = rt->rt_pmtu;
 	if (rtnetlink_put_metrics(skb, metrics) < 0)
 		goto nla_put_failure;
@@ -2195,13 +2224,6 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 		goto nla_put_failure;
 
 	error = rt->dst.error;
-	expires = rt->dst.expires;
-	if (expires) {
-		if (time_before(jiffies, expires))
-			expires -= jiffies;
-		else
-			expires = 0;
-	}
 
 	if (rt_is_input_route(rt)) {
 		if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 681ea2f413e2..05c5ab8d983c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,6 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
 	xdst->u.rt.rt_gateway = rt->rt_gateway;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e22e6d88bac6..a974247a9ae4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -822,13 +822,6 @@ out:
 	return segs;
 }
 
-struct ipv6_gro_cb {
-	struct napi_gro_cb napi;
-	int proto;
-};
-
-#define IPV6_GRO_CB(skb) ((struct ipv6_gro_cb *)(skb)->cb)
-
 static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -874,28 +867,31 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		iph = ipv6_hdr(skb);
 	}
 
-	IPV6_GRO_CB(skb)->proto = proto;
+	NAPI_GRO_CB(skb)->proto = proto;
 
 	flush--;
 	nlen = skb_network_header_len(skb);
 
 	for (p = *head; p; p = p->next) {
-		struct ipv6hdr *iph2;
+		const struct ipv6hdr *iph2;
+		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
 
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
 		iph2 = ipv6_hdr(p);
+		first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
 
-		/* All fields must match except length. */
+		/* All fields must match except length and Traffic Class. */
 		if (nlen != skb_network_header_len(p) ||
-		    memcmp(iph, iph2, offsetof(struct ipv6hdr, payload_len)) ||
+		    (first_word & htonl(0xF00FFFFF)) ||
 		    memcmp(&iph->nexthdr, &iph2->nexthdr,
 			   nlen - offsetof(struct ipv6hdr, nexthdr))) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
-
+		/* flush if Traffic Class fields are different */
+		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
 	}
 
@@ -927,7 +923,7 @@ static int ipv6_gro_complete(struct sk_buff *skb)
 				 sizeof(*iph));
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_protos[IPV6_GRO_CB(skb)->proto]);
+	ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]);
 	if (WARN_ON(!ops || !ops->gro_complete))
 		goto out_unlock;
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 56f6d5d81a77..cc4c8095681a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -50,6 +50,7 @@ enum {
 				      * local
 				      */
 	IP_VS_RT_MODE_CONNECT	= 8, /* Always bind route to saddr */
+	IP_VS_RT_MODE_KNOWN_NH	= 16,/* Route via remote addr */
 };
 
 /*
@@ -113,6 +114,8 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 	fl4.daddr = daddr;
 	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
 	fl4.flowi4_tos = rtos;
+	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
+			   FLOWI_FLAG_KNOWN_NH : 0;
 
 retry:
 	rt = ip_route_output_key(net, &fl4);
@@ -1061,7 +1064,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
 				      RT_TOS(iph->tos),
 				      IP_VS_RT_MODE_LOCAL |
-					IP_VS_RT_MODE_NON_LOCAL, NULL)))
+				      IP_VS_RT_MODE_NON_LOCAL |
+				      IP_VS_RT_MODE_KNOWN_NH, NULL)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0f2e3ad69c47..01e944a017a4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -169,6 +169,8 @@ static void netlink_sock_destruct(struct sock *sk)
 	if (nlk->cb) {
 		if (nlk->cb->done)
 			nlk->cb->done(nlk->cb);
+
+		module_put(nlk->cb->module);
 		netlink_destroy_callback(nlk->cb);
 	}
 
@@ -1758,6 +1760,7 @@ static int netlink_dump(struct sock *sk)
 	nlk->cb = NULL;
 	mutex_unlock(nlk->cb_mutex);
 
+	module_put(cb->module);
 	netlink_consume_callback(cb);
 	return 0;
 
@@ -1767,9 +1770,9 @@ errout_skb:
 	return err;
 }
 
-int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
-		       const struct nlmsghdr *nlh,
-		       struct netlink_dump_control *control)
+int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
+			 const struct nlmsghdr *nlh,
+			 struct netlink_dump_control *control)
 {
 	struct netlink_callback *cb;
 	struct sock *sk;
@@ -1784,6 +1787,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->done = control->done;
 	cb->nlh = nlh;
 	cb->data = control->data;
+	cb->module = control->module;
 	cb->min_dump_alloc = control->min_dump_alloc;
 	atomic_inc(&skb->users);
 	cb->skb = skb;
@@ -1794,19 +1798,28 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 		return -ECONNREFUSED;
 	}
 	nlk = nlk_sk(sk);
-	/* A dump is in progress... */
+
 	mutex_lock(nlk->cb_mutex);
+	/* A dump is in progress... */
 	if (nlk->cb) {
 		mutex_unlock(nlk->cb_mutex);
 		netlink_destroy_callback(cb);
-		sock_put(sk);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out;
 	}
+	/* add reference of module which cb->dump belongs to */
+	if (!try_module_get(cb->module)) {
+		mutex_unlock(nlk->cb_mutex);
+		netlink_destroy_callback(cb);
+		ret = -EPROTONOSUPPORT;
+		goto out;
+	}
+
 	nlk->cb = cb;
 	mutex_unlock(nlk->cb_mutex);
 
 	ret = netlink_dump(sk);
-
+out:
 	sock_put(sk);
 
 	if (ret)
@@ -1817,7 +1830,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	 */
 	return -EINTR;
 }
-EXPORT_SYMBOL(netlink_dump_start);
+EXPORT_SYMBOL(__netlink_dump_start);
 
 void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 {
diff --git a/net/rds/send.c b/net/rds/send.c
index 96531d4033a2..88eace57dd6b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1122,7 +1122,7 @@ rds_send_pong(struct rds_connection *conn, __be16 dport)
 	rds_stats_inc(s_send_pong);
 
 	if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
-		rds_send_xmit(conn);
+		queue_delayed_work(rds_wq, &conn->c_send_w, 0);
 
 	rds_message_put(rm);
 	return 0;