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

12 files changed, 164 insertions, 48 deletions

diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 84122472656c3a..dec4f3817133c8 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -62,6 +62,15 @@ static int brnf_filter_pppoe_tagged __read_mostly = 0;
 #define brnf_filter_pppoe_tagged 0
 #endif
 
+#define IS_IP(skb) \
+	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
+
+#define IS_IPV6(skb) \
+	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))
+
+#define IS_ARP(skb) \
+	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))
+
 static inline __be16 vlan_proto(const struct sk_buff *skb)
 {
 	if (vlan_tx_tag_present(skb))
@@ -639,8 +648,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
 		return NF_DROP;
 	br = p->br;
 
-	if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
-	    IS_PPPOE_IPV6(skb)) {
+	if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) {
 		if (!brnf_call_ip6tables && !br->nf_call_ip6tables)
 			return NF_ACCEPT;
 
@@ -651,8 +659,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
 	if (!brnf_call_iptables && !br->nf_call_iptables)
 		return NF_ACCEPT;
 
-	if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) &&
-	    !IS_PPPOE_IP(skb))
+	if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb))
 		return NF_ACCEPT;
 
 	nf_bridge_pull_encap_header_rcsum(skb);
@@ -701,7 +708,7 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct net_device *in;
 
-	if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) {
+	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
 		in = nf_bridge->physindev;
 		if (nf_bridge->mask & BRNF_PKT_TYPE) {
 			skb->pkt_type = PACKET_OTHERHOST;
@@ -718,6 +725,7 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	return 0;
 }
 
+
 /* This is the 'purely bridged' case.  For IP, we pass the packet to
  * netfilter with indev and outdev set to the bridge device,
  * but we are still able to filter on the 'real' indev/outdev
@@ -744,11 +752,9 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
 	if (!parent)
 		return NF_DROP;
 
-	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
-	    IS_PPPOE_IP(skb))
+	if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
 		pf = PF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
-		 IS_PPPOE_IPV6(skb))
+	else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
 		pf = PF_INET6;
 	else
 		return NF_ACCEPT;
@@ -795,7 +801,7 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
 	if (!brnf_call_arptables && !br->nf_call_arptables)
 		return NF_ACCEPT;
 
-	if (skb->protocol != htons(ETH_P_ARP)) {
+	if (!IS_ARP(skb)) {
 		if (!IS_VLAN_ARP(skb))
 			return NF_ACCEPT;
 		nf_bridge_pull_encap_header(skb);
@@ -853,11 +859,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
 	if (!realoutdev)
 		return NF_DROP;
 
-	if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
-	    IS_PPPOE_IP(skb))
+	if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
 		pf = PF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
-		 IS_PPPOE_IPV6(skb))
+	else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
 		pf = PF_INET6;
 	else
 		return NF_ACCEPT;
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 6751ed4e0c074a..8c836d96ba769e 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -31,7 +31,7 @@ static const char *const br_port_state_names[] = {
 
 void br_log_state(const struct net_bridge_port *p)
 {
-	br_info(p->br, "port %u(%s) entering %s state\n",
+	br_info(p->br, "port %u(%s) entered %s state\n",
 		(unsigned) p->port_no, p->dev->name,
 		br_port_state_names[p->state]);
 }
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 19308e305d851a..f494496373d60c 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -98,14 +98,13 @@ void br_stp_disable_port(struct net_bridge_port *p)
 	struct net_bridge *br = p->br;
 	int wasroot;
 
-	br_log_state(p);
-
 	wasroot = br_is_root_bridge(br);
 	br_become_designated_port(p);
 	p->state = BR_STATE_DISABLED;
 	p->topology_change_ack = 0;
 	p->config_pending = 0;
 
+	br_log_state(p);
 	br_ifinfo_notify(RTM_NEWLINK, p);
 
 	del_timer(&p->message_age_timer);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 8aa4ad0e06af9a..5fe2ff3b01efe4 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1335,7 +1335,12 @@ static inline int ebt_make_matchname(const struct ebt_entry_match *m,
     const char *base, char __user *ubase)
 {
 	char __user *hlp = ubase + ((char *)m - base);
-	if (copy_to_user(hlp, m->u.match->name, EBT_FUNCTION_MAXNAMELEN))
+	char name[EBT_FUNCTION_MAXNAMELEN] = {};
+
+	/* ebtables expects 32 bytes long names but xt_match names are 29 bytes
+	   long. Copy 29 bytes and fill remaining bytes with zeroes. */
+	strncpy(name, m->u.match->name, sizeof(name));
+	if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;
 }
@@ -1344,7 +1349,10 @@ static inline int ebt_make_watchername(const struct ebt_entry_watcher *w,
     const char *base, char __user *ubase)
 {
 	char __user *hlp = ubase + ((char *)w - base);
-	if (copy_to_user(hlp , w->u.watcher->name, EBT_FUNCTION_MAXNAMELEN))
+	char name[EBT_FUNCTION_MAXNAMELEN] = {};
+
+	strncpy(name, w->u.watcher->name, sizeof(name));
+	if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;
 }
@@ -1355,6 +1363,7 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase)
 	int ret;
 	char __user *hlp;
 	const struct ebt_entry_target *t;
+	char name[EBT_FUNCTION_MAXNAMELEN] = {};
 
 	if (e->bitmask == 0)
 		return 0;
@@ -1368,7 +1377,8 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase)
 	ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase);
 	if (ret != 0)
 		return ret;
-	if (copy_to_user(hlp, t->u.target->name, EBT_FUNCTION_MAXNAMELEN))
+	strncpy(name, t->u.target->name, sizeof(name));
+	if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;
 }
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index bf4a9c4808e1fa..d4d61b694fab9b 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/net.h>
+#include <linux/workqueue.h>
 #include <net/ip.h>
 #include <net/inetpeer.h>
 #include <net/secure_seq.h>
@@ -66,6 +67,11 @@
 
 static struct kmem_cache *peer_cachep __read_mostly;
 
+static LIST_HEAD(gc_list);
+static const int gc_delay = 60 * HZ;
+static struct delayed_work gc_work;
+static DEFINE_SPINLOCK(gc_lock);
+
 #define node_height(x) x->avl_height
 
 #define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
@@ -102,6 +108,50 @@ int inet_peer_threshold __read_mostly = 65536 + 128;	/* start to throw entries m
 int inet_peer_minttl __read_mostly = 120 * HZ;	/* TTL under high load: 120 sec */
 int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min */
 
+static void inetpeer_gc_worker(struct work_struct *work)
+{
+	struct inet_peer *p, *n;
+	LIST_HEAD(list);
+
+	spin_lock_bh(&gc_lock);
+	list_replace_init(&gc_list, &list);
+	spin_unlock_bh(&gc_lock);
+
+	if (list_empty(&list))
+		return;
+
+	list_for_each_entry_safe(p, n, &list, gc_list) {
+
+		if(need_resched())
+			cond_resched();
+
+		if (p->avl_left != peer_avl_empty) {
+			list_add_tail(&p->avl_left->gc_list, &list);
+			p->avl_left = peer_avl_empty;
+		}
+
+		if (p->avl_right != peer_avl_empty) {
+			list_add_tail(&p->avl_right->gc_list, &list);
+			p->avl_right = peer_avl_empty;
+		}
+
+		n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
+
+		if (!atomic_read(&p->refcnt)) {
+			list_del(&p->gc_list);
+			kmem_cache_free(peer_cachep, p);
+		}
+	}
+
+	if (list_empty(&list))
+		return;
+
+	spin_lock_bh(&gc_lock);
+	list_splice(&list, &gc_list);
+	spin_unlock_bh(&gc_lock);
+
+	schedule_delayed_work(&gc_work, gc_delay);
+}
 
 /* Called from ip_output.c:ip_init  */
 void __init inet_initpeers(void)
@@ -126,6 +176,7 @@ void __init inet_initpeers(void)
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
 			NULL);
 
+	INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker);
 }
 
 static int addr_compare(const struct inetpeer_addr *a,
@@ -447,9 +498,8 @@ relookup:
 		p->rate_last = 0;
 		p->pmtu_expires = 0;
 		p->pmtu_orig = 0;
-		p->redirect_genid = 0;
 		memset(&p->redirect_learned, 0, sizeof(p->redirect_learned));
-
+		INIT_LIST_HEAD(&p->gc_list);
 
 		/* Link the node. */
 		link_to_pool(p, base);
@@ -509,3 +559,30 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
 	return rc;
 }
 EXPORT_SYMBOL(inet_peer_xrlim_allow);
+
+void inetpeer_invalidate_tree(int family)
+{
+	struct inet_peer *old, *new, *prev;
+	struct inet_peer_base *base = family_to_base(family);
+
+	write_seqlock_bh(&base->lock);
+
+	old = base->root;
+	if (old == peer_avl_empty_rcu)
+		goto out;
+
+	new = peer_avl_empty_rcu;
+
+	prev = cmpxchg(&base->root, old, new);
+	if (prev == old) {
+		base->total = 0;
+		spin_lock(&gc_lock);
+		list_add_tail(&prev->gc_list, &gc_list);
+		spin_unlock(&gc_lock);
+		schedule_delayed_work(&gc_work, gc_delay);
+	}
+
+out:
+	write_sequnlock_bh(&base->lock);
+}
+EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0489cedc1671db..815989b90dea2d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -132,7 +132,6 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly	= 20;
-static int redirect_genid;
 
 static struct delayed_work expires_work;
 static unsigned long expires_ljiffies;
@@ -937,7 +936,7 @@ static void rt_cache_invalidate(struct net *net)
 
 	get_random_bytes(&shuffle, sizeof(shuffle));
 	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
-	redirect_genid++;
+	inetpeer_invalidate_tree(AF_INET);
 }
 
 /*
@@ -1490,10 +1489,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 
 				peer = rt->peer;
 				if (peer) {
-					if (peer->redirect_learned.a4 != new_gw ||
-					    peer->redirect_genid != redirect_genid) {
+					if (peer->redirect_learned.a4 != new_gw) {
 						peer->redirect_learned.a4 = new_gw;
-						peer->redirect_genid = redirect_genid;
 						atomic_inc(&__rt_peer_genid);
 					}
 					check_peer_redir(&rt->dst, peer);
@@ -1798,8 +1795,6 @@ static void ipv4_validate_peer(struct rtable *rt)
 		if (peer) {
 			check_peer_pmtu(&rt->dst, peer);
 
-			if (peer->redirect_genid != redirect_genid)
-				peer->redirect_learned.a4 = 0;
 			if (peer->redirect_learned.a4 &&
 			    peer->redirect_learned.a4 != rt->rt_gateway)
 				check_peer_redir(&rt->dst, peer);
@@ -1963,8 +1958,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 		dst_init_metrics(&rt->dst, peer->metrics, false);
 
 		check_peer_pmtu(&rt->dst, peer);
-		if (peer->redirect_genid != redirect_genid)
-			peer->redirect_learned.a4 = 0;
+
 		if (peer->redirect_learned.a4 &&
 		    peer->redirect_learned.a4 != rt->rt_gateway) {
 			rt->rt_gateway = peer->redirect_learned.a4;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d9b83d198c3d3a..b5e315f13641d6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1585,6 +1585,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	/* tcp_sacktag_one() won't SACK-tag ranges below snd_una */
+	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
+		goto fallback;
+
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
 	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c02280a4d12698..6b8ebc5da0e134 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -434,6 +434,10 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
 	/* Join all-node multicast group */
 	ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes);
 
+	/* Join all-router multicast group if forwarding is set */
+	if (ndev->cnf.forwarding && dev && (dev->flags & IFF_MULTICAST))
+		ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters);
+
 	return ndev;
 }
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 81e2aa4ca1fe38..7b48035826eeed 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -636,8 +636,12 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 
 	if (del_timer(&ct->timeout)) {
 		death_by_timeout((unsigned long)ct);
-		dropped = 1;
-		NF_CT_STAT_INC_ATOMIC(net, early_drop);
+		/* Check if we indeed killed this entry. Reliable event
+		   delivery may have inserted it into the dying list. */
+		if (test_bit(IPS_DYING_BIT, &ct->status)) {
+			dropped = 1;
+			NF_CT_STAT_INC_ATOMIC(net, early_drop);
+		}
 	}
 	nf_ct_put(ct);
 	return dropped;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c1ea64c6c70d13..2124977ac31d0a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1084,16 +1084,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 	if (!parse_nat_setup) {
 #ifdef CONFIG_MODULES
 		rcu_read_unlock();
-		spin_unlock_bh(&nf_conntrack_lock);
 		nfnl_unlock();
 		if (request_module("nf-nat-ipv4") < 0) {
 			nfnl_lock();
-			spin_lock_bh(&nf_conntrack_lock);
 			rcu_read_lock();
 			return -EOPNOTSUPP;
 		}
 		nfnl_lock();
-		spin_lock_bh(&nf_conntrack_lock);
 		rcu_read_lock();
 		if (nfnetlink_parse_nat_setup_hook)
 			return -EAGAIN;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2725d1bdf2916b..48badffaafc1a2 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2011 Nicira Networks.
+ * Copyright (c) 2007-2012 Nicira Networks.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -145,9 +145,16 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
 			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
 						 *addr, new_addr, 1);
 	} else if (nh->protocol == IPPROTO_UDP) {
-		if (likely(transport_len >= sizeof(struct udphdr)))
-			inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
-						 *addr, new_addr, 1);
+		if (likely(transport_len >= sizeof(struct udphdr))) {
+			struct udphdr *uh = udp_hdr(skb);
+
+			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+				inet_proto_csum_replace4(&uh->check, skb,
+							 *addr, new_addr, 1);
+				if (!uh->check)
+					uh->check = CSUM_MANGLED_0;
+			}
+		}
 	}
 
 	csum_replace4(&nh->check, *addr, new_addr);
@@ -197,8 +204,22 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port,
 	skb->rxhash = 0;
 }
 
-static int set_udp_port(struct sk_buff *skb,
-			const struct ovs_key_udp *udp_port_key)
+static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+		set_tp_port(skb, port, new_port, &uh->check);
+
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	} else {
+		*port = new_port;
+		skb->rxhash = 0;
+	}
+}
+
+static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
 {
 	struct udphdr *uh;
 	int err;
@@ -210,16 +231,15 @@ static int set_udp_port(struct sk_buff *skb,
 
 	uh = udp_hdr(skb);
 	if (udp_port_key->udp_src != uh->source)
-		set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+		set_udp_port(skb, &uh->source, udp_port_key->udp_src);
 
 	if (udp_port_key->udp_dst != uh->dest)
-		set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+		set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
 
 	return 0;
 }
 
-static int set_tcp_port(struct sk_buff *skb,
-			const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
 {
 	struct tcphdr *th;
 	int err;
@@ -328,11 +348,11 @@ static int execute_set_action(struct sk_buff *skb,
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		err = set_tcp_port(skb, nla_data(nested_attr));
+		err = set_tcp(skb, nla_data(nested_attr));
 		break;
 
 	case OVS_KEY_ATTR_UDP:
-		err = set_udp_port(skb, nla_data(nested_attr));
+		err = set_udp(skb, nla_data(nested_attr));
 		break;
 	}
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ce64c18b8c79a9..2c030505b335fd 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1521,6 +1521,9 @@ static struct vport *lookup_vport(struct ovs_header *ovs_header,
 		vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME]));
 		if (!vport)
 			return ERR_PTR(-ENODEV);
+		if (ovs_header->dp_ifindex &&
+		    ovs_header->dp_ifindex != get_dpifindex(vport->dp))
+			return ERR_PTR(-ENODEV);
 		return vport;
 	} else if (a[OVS_VPORT_ATTR_PORT_NO]) {
 		u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);