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

Pull networking fixes from David Miller:

 1) Various ipvlan fixes from Eric Dumazet and Mahesh Bandewar.

    The most important is to not assume the packet is RX just because
    the destination address matches that of the device. Such an
    assumption causes problems when an interface is put into loopback
    mode.

 2) If we retry when creating a new tc entry (because we dropped the
    RTNL mutex in order to load a module, for example) we end up with
    -EAGAIN and then loop trying to replay the request. But we didn't
    reset some state when looping back to the top like this, and if
    another thread meanwhile inserted the same tc entry we were trying
    to, we re-link it creating an enless loop in the tc chain. Fix from
    Daniel Borkmann.

 3) There are two different WRITE bits in the MDIO address register for
    the stmmac chip, depending upon the chip variant. Due to a bug we
    could set them both, fix from Hock Leong Kweh.

 4) Fix mlx4 bug in XDP_TX handling, from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net: stmmac: fix incorrect bit set in gmac4 mdio addr register
  r8169: add support for RTL8168 series add-on card.
  net: xdp: remove unused bfp_warn_invalid_xdp_buffer()
  openvswitch: upcall: Fix vlan handling.
  ipv4: Namespaceify tcp_tw_reuse knob
  net: korina: Fix NAPI versus resources freeing
  net, sched: fix soft lockup in tc_classify
  net/mlx4_en: Fix user prio field in XDP forward
  tipc: don't send FIN message from connectionless socket
  ipvlan: fix multicast processing
  ipvlan: fix various issues in ipvlan_process_multicast()

7 files changed, 52 insertions, 55 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index e6c412b..1969b3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2972,12 +2972,6 @@ void bpf_warn_invalid_xdp_action(u32 act)
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
-void bpf_warn_invalid_xdp_buffer(void)
-{
-	WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
-}
-EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);
-
 static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 					int src_reg, int ctx_off,
 					struct bpf_insn *insn_buf,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b..22cbd61 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -433,13 +433,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &tcp_adv_win_scale_max,
 	},
 	{
-		.procname	= "tcp_tw_reuse",
-		.data		= &sysctl_tcp_tw_reuse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_frto",
 		.data		= &sysctl_tcp_frto,
 		.maxlen		= sizeof(int),
@@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_tw_reuse",
+		.data		= &init_net.ipv4.sysctl_tcp_tw_reuse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30d81f5..fe9da4f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_orphan_retries = 0;
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	return 0;
 fail:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2d4c4d3..9c62b63 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -606,7 +606,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	rcu_assign_pointer(flow->sf_acts, acts);
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
-	packet->protocol = flow->key.eth.type;
 
 	rcu_read_lock();
 	dp = get_dp_rcu(net, ovs_header->dp_ifindex);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 08aa926..2c0a00f 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -312,7 +312,8 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
  * Returns 0 if it encounters a non-vlan or incomplete packet.
  * Returns 1 after successfully parsing vlan tag.
  */
-static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+			  bool untag_vlan)
 {
 	struct vlan_head *vh = (struct vlan_head *)skb->data;
 
@@ -330,7 +331,20 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
 	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
 	key_vh->tpid = vh->tpid;
 
-	__skb_pull(skb, sizeof(struct vlan_head));
+	if (unlikely(untag_vlan)) {
+		int offset = skb->data - skb_mac_header(skb);
+		u16 tci;
+		int err;
+
+		__skb_push(skb, offset);
+		err = __skb_vlan_pop(skb, &tci);
+		__skb_pull(skb, offset);
+		if (err)
+			return err;
+		__vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+	} else {
+		__skb_pull(skb, sizeof(struct vlan_head));
+	}
 	return 1;
 }
 
@@ -351,13 +365,13 @@ static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 		key->eth.vlan.tpid = skb->vlan_proto;
 	} else {
 		/* Parse outer vlan tag in the non-accelerated case. */
-		res = parse_vlan_tag(skb, &key->eth.vlan);
+		res = parse_vlan_tag(skb, &key->eth.vlan, true);
 		if (res <= 0)
 			return res;
 	}
 
 	/* Parse inner vlan tag. */
-	res = parse_vlan_tag(skb, &key->eth.cvlan);
+	res = parse_vlan_tag(skb, &key->eth.cvlan, false);
 	if (res <= 0)
 		return res;
 
@@ -800,29 +814,15 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
 	if (err)
 		return err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		/* key_extract assumes that skb->protocol is set-up for
-		 * layer 3 packets which is the case for other callers,
-		 * in particular packets recieved from the network stack.
-		 * Here the correct value can be set from the metadata
-		 * extracted above.
-		 */
-		skb->protocol = key->eth.type;
-	} else {
-		struct ethhdr *eth;
-
-		skb_reset_mac_header(skb);
-		eth = eth_hdr(skb);
-
-		/* Normally, setting the skb 'protocol' field would be
-		 * handled by a call to eth_type_trans(), but it assumes
-		 * there's a sending device, which we may not have.
-		 */
-		if (eth_proto_is_802_3(eth->h_proto))
-			skb->protocol = eth->h_proto;
-		else
-			skb->protocol = htons(ETH_P_802_2);
-	}
+	/* key_extract assumes that skb->protocol is set-up for
+	 * layer 3 packets which is the case for other callers,
+	 * in particular packets received from the network stack.
+	 * Here the correct value can be set from the metadata
+	 * extracted above.
+	 * For L2 packet key eth type would be zero. skb protocol
+	 * would be set to correct value later during key-extact.
+	 */
 
+	skb->protocol = key->eth.type;
 	return key_extract(skb, key);
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3fbba79..1ecdf80 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 333c5da..800caaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -441,15 +441,19 @@ static void __tipc_shutdown(struct socket *sock, int error)
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (TIPC_SKB_CB(skb)->bytes_read) {
 			kfree_skb(skb);
-		} else {
-			if (!tipc_sk_type_connectionless(sk) &&
-			    sk->sk_state != TIPC_DISCONNECTING) {
-				tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-				tipc_node_remove_conn(net, dnode, tsk->portid);
-			}
-			tipc_sk_respond(sk, skb, error);
+			continue;
+		}
+		if (!tipc_sk_type_connectionless(sk) &&
+		    sk->sk_state != TIPC_DISCONNECTING) {
+			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+			tipc_node_remove_conn(net, dnode, tsk->portid);
 		}
+		tipc_sk_respond(sk, skb, error);
 	}
+
+	if (tipc_sk_type_connectionless(sk))
+		return;
+
 	if (sk->sk_state != TIPC_DISCONNECTING) {
 		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
 				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
@@ -457,10 +461,8 @@ static void __tipc_shutdown(struct socket *sock, int error)
 				      tsk->portid, error);
 		if (skb)
 			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
-		if (!tipc_sk_type_connectionless(sk)) {
-			tipc_node_remove_conn(net, dnode, tsk->portid);
-			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-		}
+		tipc_node_remove_conn(net, dnode, tsk->portid);
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 	}
 }