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

Conflicts:
	drivers/net/wireless/orinoco/main.c

9 files changed, 67 insertions, 13 deletions

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 95d7f32643a..72720c71035 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -75,6 +75,7 @@ static __initdata const char banner[] = KERN_INFO
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
+MODULE_ALIAS("can-proto-2");
 
 /* easy access to can_frame payload */
 static inline u64 GET_U64(const struct can_frame *cp)
@@ -1469,6 +1470,9 @@ static int bcm_release(struct socket *sock)
 		bo->ifindex = 0;
 	}
 
+	sock_orphan(sk);
+	sock->sk = NULL;
+
 	release_sock(sk);
 	sock_put(sk);
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 6aa154e806a..f4cc44548bd 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -62,6 +62,7 @@ static __initdata const char banner[] =
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
+MODULE_ALIAS("can-proto-1");
 
 #define MASK_ALL 0
 
@@ -306,6 +307,9 @@ static int raw_release(struct socket *sock)
 	ro->bound   = 0;
 	ro->count   = 0;
 
+	sock_orphan(sk);
+	sock->sk = NULL;
+
 	release_sock(sk);
 	sock_put(sk);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 6354863b1c6..d9eec153d53 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -919,13 +919,19 @@ static inline void sock_lock_init(struct sock *sk)
 			af_family_keys + sk->sk_family);
 }
 
+/*
+ * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
+ * even temporarly, because of RCU lookups. sk_node should also be left as is.
+ */
 static void sock_copy(struct sock *nsk, const struct sock *osk)
 {
 #ifdef CONFIG_SECURITY_NETWORK
 	void *sptr = nsk->sk_security;
 #endif
-
-	memcpy(nsk, osk, osk->sk_prot->obj_size);
+	BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
+		     sizeof(osk->sk_node) + sizeof(osk->sk_refcnt));
+	memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
+	       osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
 #ifdef CONFIG_SECURITY_NETWORK
 	nsk->sk_security = sptr;
 	security_sk_clone(osk, nsk);
@@ -939,8 +945,23 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
 	struct kmem_cache *slab;
 
 	slab = prot->slab;
-	if (slab != NULL)
-		sk = kmem_cache_alloc(slab, priority);
+	if (slab != NULL) {
+		sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
+		if (!sk)
+			return sk;
+		if (priority & __GFP_ZERO) {
+			/*
+			 * caches using SLAB_DESTROY_BY_RCU should let
+			 * sk_node.next un-modified. Special care is taken
+			 * when initializing object to zero.
+			 */
+			if (offsetof(struct sock, sk_node.next) != 0)
+				memset(sk, 0, offsetof(struct sock, sk_node.next));
+			memset(&sk->sk_node.pprev, 0,
+			       prot->obj_size - offsetof(struct sock,
+							 sk_node.pprev));
+		}
+	}
 	else
 		sk = kmalloc(prot->obj_size, priority);
 
@@ -1125,6 +1146,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 
 		newsk->sk_err	   = 0;
 		newsk->sk_priority = 0;
+		/*
+		 * Before updating sk_refcnt, we must commit prior changes to memory
+		 * (Documentation/RCU/rculist_nulls.txt for details)
+		 */
+		smp_wmb();
 		atomic_set(&newsk->sk_refcnt, 2);
 
 		/*
@@ -1840,6 +1866,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_stamp = ktime_set(-1L, 0);
 
+	/*
+	 * Before updating sk_refcnt, we must commit prior changes to memory
+	 * (Documentation/RCU/rculist_nulls.txt for details)
+	 */
+	smp_wmb();
 	atomic_set(&sk->sk_refcnt, 1);
 	atomic_set(&sk->sk_wmem_alloc, 1);
 	atomic_set(&sk->sk_drops, 0);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index cd85ebc119a..b902ef55be7 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -735,10 +735,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tos = tiph->tos;
-	if (tos&1) {
+	if (tos == 1) {
+		tos = 0;
 		if (skb->protocol == htons(ETH_P_IP))
 			tos = old_iph->tos;
-		tos &= ~1;
 	}
 
 	{
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24702628266..7d082105472 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1243,7 +1243,6 @@ int ip_push_pending_frames(struct sock *sk)
 		skb->len += tmp_skb->len;
 		skb->data_len += tmp_skb->len;
 		skb->truesize += tmp_skb->truesize;
-		__sock_put(tmp_skb->sk);
 		tmp_skb->destructor = NULL;
 		tmp_skb->sk = NULL;
 	}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index dd1a980b8ac..93beee94465 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1474,7 +1474,6 @@ int ip6_push_pending_frames(struct sock *sk)
 		skb->len += tmp_skb->len;
 		skb->data_len += tmp_skb->len;
 		skb->truesize += tmp_skb->truesize;
-		__sock_put(tmp_skb->sk);
 		tmp_skb->destructor = NULL;
 		tmp_skb->sk = NULL;
 	}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d0b850590fa..d335a306a4d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1018,6 +1018,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
 	dev->flags		= IFF_NOARP;
+	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7508f11c5b3..b5869b9574b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -561,23 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 		}
 	}
 
-	ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp);
+	/*
+	 * Do not use kmem_cache_zalloc(), as this cache uses
+	 * SLAB_DESTROY_BY_RCU.
+	 */
+	ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
 	if (ct == NULL) {
 		pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
 		atomic_dec(&net->ct.count);
 		return ERR_PTR(-ENOMEM);
 	}
-
+	/*
+	 * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
+	 * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
+	 */
+	memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
+	       sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
 	spin_lock_init(&ct->lock);
-	atomic_set(&ct->ct_general.use, 1);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
+	ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
 	/* Don't set timer yet: wait for confirmation */
 	setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
 #ifdef CONFIG_NET_NS
 	ct->ct_net = net;
 #endif
 
+	/*
+	 * changes to lookup keys must be done before setting refcnt to 1
+	 */
+	smp_wmb();
+	atomic_set(&ct->ct_general.use, 1);
 	return ct;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 863e40977a4..0f482e2440b 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -330,7 +330,8 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
 			fcount++;
 
 			if (info->flags & XT_OSF_LOG)
-				nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+				nf_log_packet(p->family, p->hooknum, skb,
+					p->in, p->out, NULL,
 					"%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n",
 					f->genre, f->version, f->subtype,
 					&ip->saddr, ntohs(tcp->source),
@@ -345,7 +346,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
 	rcu_read_unlock();
 
 	if (!fcount && (info->flags & XT_OSF_LOG))
-		nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+		nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL,
 			"Remote OS is not known: %pi4:%u -> %pi4:%u\n",
 				&ip->saddr, ntohs(tcp->source),
 				&ip->daddr, ntohs(tcp->dest));