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

Pull networking fixes from David Miller:

 1) Don't save TIPC header values before the header has been validated,
    from Jon Paul Maloy.

 2) Fix memory leak in RDS, from Zhu Yanjun.

 3) We miss to initialize the UID in the flow key in some paths, from
    Julian Anastasov.

 4) Fix latent TOS masking bug in the routing cache removal from years
    ago, also from Julian.

 5) We forget to set the sockaddr port in sctp_copy_local_addr_list(),
    fix from Xin Long.

 6) Missing module ref count drop in packet scheduler actions, from
    Roman Mashak.

 7) Fix RCU annotations in rht_bucket_nested, from Herbert Xu.

 8) Fix use after free which happens because L2TP's ipv4 support returns
    non-zero values from it's backlog_rcv function which ipv4 interprets
    as protocol values. Fix from Paul Hüber.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (35 commits)
  qed: Don't use attention PTT for configuring BW
  qed: Fix race with multiple VFs
  l2tp: avoid use-after-free caused by l2tp_ip_backlog_recv
  xfrm: provide correct dst in xfrm_neigh_lookup
  rhashtable: Fix RCU dereference annotation in rht_bucket_nested
  rhashtable: Fix use before NULL check in bucket_table_free
  net sched actions: do not overwrite status of action creation.
  rxrpc: Kernel calls get stuck in recvmsg
  net sched actions: decrement module reference count after table flush.
  lib: Allow compile-testing of parman
  ipv6: check sk sk_type and protocol early in ip_mroute_set/getsockopt
  sctp: set sin_port for addr param when checking duplicate address
  net/mlx4_en: fix overflow in mlx4_en_init_timestamp()
  netfilter: nft_set_bitmap: incorrect bitmap size
  net: s2io: fix typo argumnet argument
  net: vxge: fix typo argumnet argument
  netfilter: nf_ct_expect: Change __nf_ct_expect_check() return value.
  ipv4: mask tos for input route
  ipv4: add missing initialization for flowi4_uid
  lib: fix spelling mistake: "actualy" -> "actually"
  ...

17 files changed, 77 insertions, 41 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 7db2ad2e82d3..b39a791f6756 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -319,7 +319,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	int ret, no_addr;
 	struct fib_result res;
 	struct flowi4 fl4;
-	struct net *net;
+	struct net *net = dev_net(dev);
 	bool dev_match;
 
 	fl4.flowi4_oif = 0;
@@ -332,6 +332,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_tun_key.tun_id = 0;
 	fl4.flowi4_flags = 0;
+	fl4.flowi4_uid = sock_net_uid(net, NULL);
 
 	no_addr = idev->ifa_list == NULL;
 
@@ -339,13 +340,12 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 
 	trace_fib_validate_source(dev, &fl4);
 
-	net = dev_net(dev);
 	if (fib_lookup(net, &fl4, &res, 0))
 		goto last_resort;
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
 		goto e_inval;
-	if (!rpf && !fib_num_tclassid_users(dev_net(dev)) &&
+	if (!rpf && !fib_num_tclassid_users(net) &&
 	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
 		goto last_resort;
 	fib_combine_itag(itag, &res);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cb494a5050f7..8471dd116771 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1876,6 +1876,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.flowi4_flags = 0;
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
+	fl4.flowi4_uid = sock_net_uid(net, NULL);
 	err = fib_lookup(net, &fl4, &res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
@@ -2008,6 +2009,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	int res;
 
+	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
 
 	/* Multicast recognition logic is moved from route cache to here.
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c795fee372c4..644ba59fbd9d 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -693,6 +693,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
 	u->link = p->link;
 	u->i_key = p->i_key;
 	u->o_key = p->o_key;
+	if (u->i_key)
+		u->i_flags |= GRE_KEY;
+	if (u->o_key)
+		u->o_flags |= GRE_KEY;
 	u->proto = p->proto;
 
 	memcpy(u->name, p->name, sizeof(u->name));
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index babaf3ec2742..6ba6c900ebcf 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1666,6 +1666,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	struct net *net = sock_net(sk);
 	struct mr6_table *mrt;
 
+	if (sk->sk_type != SOCK_RAW ||
+	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
+		return -EOPNOTSUPP;
+
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
 	if (!mrt)
 		return -ENOENT;
@@ -1677,9 +1681,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 	switch (optname) {
 	case MRT6_INIT:
-		if (sk->sk_type != SOCK_RAW ||
-		    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
-			return -EOPNOTSUPP;
 		if (optlen < sizeof(int))
 			return -EINVAL;
 
@@ -1815,6 +1816,10 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 	struct net *net = sock_net(sk);
 	struct mr6_table *mrt;
 
+	if (sk->sk_type != SOCK_RAW ||
+	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
+		return -EOPNOTSUPP;
+
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
 	if (!mrt)
 		return -ENOENT;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index c59712057dc8..d25038cfd64e 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -388,7 +388,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 drop:
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
-	return -1;
+	return 0;
 }
 
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index e19a69787d99..4b2e1fb28bb4 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -410,7 +410,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	struct net *net = nf_ct_exp_net(expect);
 	struct hlist_node *next;
 	unsigned int h;
-	int ret = 1;
+	int ret = 0;
 
 	if (!master_help) {
 		ret = -ESHUTDOWN;
@@ -460,14 +460,14 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
 	ret = __nf_ct_expect_check(expect);
-	if (ret <= 0)
+	if (ret < 0)
 		goto out;
 
 	nf_ct_expect_insert(expect);
 
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
-	return ret;
+	return 0;
 out:
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 	return ret;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index c6b8022c0e47..bf548a7a71ec 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -528,6 +528,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
 		if (!nft_ct_tmpl_alloc_pcpu())
 			return -ENOMEM;
 		nft_ct_pcpu_template_refcnt++;
+		len = sizeof(u16);
 		break;
 #endif
 	default:
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 97f9649bcc7e..152d226552c1 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -258,7 +258,7 @@ static int nft_bitmap_init(const struct nft_set *set,
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
 
-	priv->bitmap_size = nft_bitmap_total_size(set->klen);
+	priv->bitmap_size = nft_bitmap_size(set->klen);
 
 	return 0;
 }
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 8d70884d7bb6..91fe46f1e4cc 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -111,8 +111,7 @@ static void rds_ib_dev_free(struct work_struct *work)
 		kfree(i_ipaddr);
 	}
 
-	if (rds_ibdev->vector_load)
-		kfree(rds_ibdev->vector_load);
+	kfree(rds_ibdev->vector_load);
 
 	kfree(rds_ibdev);
 }
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 57bb52361e0f..5438f6725092 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -641,12 +641,12 @@ static int rds_tcp_init(void)
 	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
 	if (ret) {
 		pr_warn("could not register rds_tcp_dev_notifier\n");
-		goto out;
+		goto out_slab;
 	}
 
 	ret = register_pernet_subsys(&rds_tcp_net_ops);
 	if (ret)
-		goto out_slab;
+		goto out_notifier;
 
 	ret = rds_tcp_recv_init();
 	if (ret)
@@ -664,9 +664,10 @@ out_recv:
 	rds_tcp_recv_exit();
 out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
-out_slab:
+out_notifier:
 	if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
 		pr_warn("could not unregister rds_tcp_dev_notifier\n");
+out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 18c737a61d80..0a4e28477ad9 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -1065,7 +1065,7 @@ static long rxrpc_read(const struct key *key,
 
 		switch (token->security_index) {
 		case RXRPC_SECURITY_RXKAD:
-			toksize += 8 * 4;	/* viceid, kvno, key*2, begin,
+			toksize += 9 * 4;	/* viceid, kvno, key*2 + len, begin,
 						 * end, primary, tktlen */
 			toksize += RND(token->kad->ticket_len);
 			break;
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index c29362d50a92..f3a688e10843 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -320,8 +320,10 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 
 	/* Barriers against rxrpc_input_data(). */
 	hard_ack = call->rx_hard_ack;
-	top = smp_load_acquire(&call->rx_top);
-	for (seq = hard_ack + 1; before_eq(seq, top); seq++) {
+	seq = hard_ack + 1;
+	while (top = smp_load_acquire(&call->rx_top),
+	       before_eq(seq, top)
+	       ) {
 		ix = seq & RXRPC_RXTX_BUFF_MASK;
 		skb = call->rxtx_buffer[ix];
 		if (!skb) {
@@ -394,6 +396,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 			ret = 1;
 			goto out;
 		}
+
+		seq++;
 	}
 
 out:
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f219ff325ed4..b70aa57319ea 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -613,8 +613,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 			goto err_mod;
 		}
 
-		err = nla_memdup_cookie(a, tb);
-		if (err < 0) {
+		if (nla_memdup_cookie(a, tb) < 0) {
+			err = -ENOMEM;
 			tcf_hash_release(a, bind);
 			goto err_mod;
 		}
@@ -859,10 +859,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
-	if (err < 0)
+	if (err <= 0)
 		goto out_module_put;
-	if (err == 0)
-		goto noflush_out;
 
 	nla_nest_end(skb, nest);
 
@@ -879,7 +877,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 out_module_put:
 	module_put(ops->owner);
 err_out:
-noflush_out:
 	kfree_skb(skb);
 	return err;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 8227bbbd077a..1b6d4574d2b0 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -199,6 +199,7 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 			      sctp_scope_t scope, gfp_t gfp, int copy_flags)
 {
 	struct sctp_sockaddr_entry *addr;
+	union sctp_addr laddr;
 	int error = 0;
 
 	rcu_read_lock();
@@ -220,7 +221,10 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
 			continue;
 
-		if (sctp_bind_addr_state(bp, &addr->a) != -1)
+		laddr = addr->a;
+		/* also works for setting ipv6 address port */
+		laddr.v4.sin_port = htons(bp->port);
+		if (sctp_bind_addr_state(bp, &laddr) != -1)
 			continue;
 
 		error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b5321486fbed..465a9c8464f9 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4862,6 +4862,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	if (!asoc)
 		return -EINVAL;
 
+	/* If there is a thread waiting on more sndbuf space for
+	 * sending on this asoc, it cannot be peeled.
+	 */
+	if (waitqueue_active(&asoc->wait))
+		return -EBUSY;
+
 	/* An association cannot be branched off from an already peeled-off
 	 * socket, nor is this supported for tcp style sockets.
 	 */
@@ -7599,8 +7605,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		if (sk != asoc->base.sk)
-			goto do_error;
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index e9295fa3a554..4512e83652b1 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1505,19 +1505,21 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 {
 	struct sk_buff_head xmitq;
 	struct tipc_node *n;
-	struct tipc_msg *hdr = buf_msg(skb);
-	int usr = msg_user(hdr);
+	struct tipc_msg *hdr;
 	int bearer_id = b->identity;
 	struct tipc_link_entry *le;
-	u16 bc_ack = msg_bcast_ack(hdr);
 	u32 self = tipc_own_addr(net);
-	int rc = 0;
+	int usr, rc = 0;
+	u16 bc_ack;
 
 	__skb_queue_head_init(&xmitq);
 
-	/* Ensure message is well-formed */
+	/* Ensure message is well-formed before touching the header */
 	if (unlikely(!tipc_msg_validate(skb)))
 		goto discard;
+	hdr = buf_msg(skb);
+	usr = msg_user(hdr);
+	bc_ack = msg_bcast_ack(hdr);
 
 	/* Handle arrival of discovery or broadcast packet */
 	if (unlikely(msg_non_seq(hdr))) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5f3e87866438..0806dccdf507 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2836,14 +2836,8 @@ static unsigned int xfrm_mtu(const struct dst_entry *dst)
 	return mtu ? : dst_mtu(dst->path);
 }
 
-static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
-					   struct sk_buff *skb,
-					   const void *daddr)
-{
-	return dst->path->ops->neigh_lookup(dst, skb, daddr);
-}
-
-static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
+static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
+					const void *daddr)
 {
 	const struct dst_entry *path = dst->path;
 
@@ -2857,6 +2851,25 @@ static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 		else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
 			daddr = &xfrm->id.daddr;
 	}
+	return daddr;
+}
+
+static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
+					   struct sk_buff *skb,
+					   const void *daddr)
+{
+	const struct dst_entry *path = dst->path;
+
+	if (!skb)
+		daddr = xfrm_get_dst_nexthop(dst, daddr);
+	return path->ops->neigh_lookup(path, skb, daddr);
+}
+
+static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
+{
+	const struct dst_entry *path = dst->path;
+
+	daddr = xfrm_get_dst_nexthop(dst, daddr);
 	path->ops->confirm_neigh(path, daddr);
 }