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

Conflicts:
	drivers/net/ethernet/mellanox/mlx4/main.c
	net/packet/af_packet.c

Both conflicts were cases of simple overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

14 files changed, 100 insertions, 42 deletions

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b..8d423bc 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2e246a1..742a6c2 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -37,6 +37,8 @@
 
 static void br_multicast_start_querier(struct net_bridge *br,
 				       struct bridge_mcast_own_query *query);
+static void br_multicast_add_router(struct net_bridge *br,
+				    struct net_bridge_port *port);
 unsigned int br_mdb_rehash_seq;
 
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
@@ -936,6 +938,8 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 #if IS_ENABLED(CONFIG_IPV6)
 	br_multicast_enable(&port->ip6_own_query);
 #endif
+	if (port->multicast_router == 2 && hlist_unhashed(&port->rlist))
+		br_multicast_add_router(br, port);
 
 out:
 	spin_unlock(&br->multicast_lock);
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4114687..7832d07 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index d4d404b..7933e62 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -310,8 +310,12 @@ int can_send(struct sk_buff *skb, int loop)
 		return err;
 	}
 
-	if (newskb)
+	if (newskb) {
+		if (!(newskb->tstamp.tv64))
+			__net_timestamp(newskb);
+
 		netif_rx_ni(newskb);
+	}
 
 	/* update statistics */
 	can_stats.tx_frames++;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3a74df7..84195da 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -958,6 +958,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1014,6 +1016,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1077,6 +1086,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1228,6 +1239,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cc858ef..9532ee8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 04ae299..c3c359a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -432,6 +432,15 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv4 supports cmsg on all imcp errors and some timestamps
  *
  * Timestamp code paths do not initialize the fields expected by cmsg:
@@ -498,7 +507,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv4_datagram_support_addr(serr)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 697b86d..7f40567 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2573,10 +2573,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 46b087a..f9c0fb8 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 762a58c..62d908e 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
  *
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
@@ -389,7 +399,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv6_datagram_support_addr(serr)) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 8abc31e..b22df3a 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -66,12 +66,15 @@ update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta)
 	if (sdata->vif.type != NL80211_IFTYPE_AP)
 		return;
 
-	mutex_lock(&sdata->local->mtx);
+	/* crypto_tx_tailroom_needed_cnt is protected by this */
+	assert_key_lock(sdata->local);
+
+	rcu_read_lock();
 
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+	list_for_each_entry_rcu(vlan, &sdata->u.ap.vlans, u.vlan.list)
 		vlan->crypto_tx_tailroom_needed_cnt += delta;
 
-	mutex_unlock(&sdata->local->mtx);
+	rcu_read_unlock();
 }
 
 static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
@@ -95,6 +98,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 	 * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net
 	 */
 
+	assert_key_lock(sdata->local);
+
 	update_vlan_tailroom_need_count(sdata, 1);
 
 	if (!sdata->crypto_tx_tailroom_needed_cnt++) {
@@ -109,6 +114,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata,
 					 int delta)
 {
+	assert_key_lock(sdata->local);
+
 	WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta);
 
 	update_vlan_tailroom_need_count(sdata, -delta);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f5c8703..c9e8741 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1322,16 +1322,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
 {
 	u32 rxhash;
@@ -1357,13 +1347,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
@@ -1435,7 +1421,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 36dbc2d..129d357 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -192,7 +192,8 @@ static void rose_kill_by_device(struct net_device *dev)
 
 		if (rose->device == dev) {
 			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
-			rose->neighbour->use--;
+			if (rose->neighbour)
+				rose->neighbour->use--;
 			rose->device = NULL;
 		}
 	}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f09de7f..5f6c4e6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1528,8 +1528,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1539,7 +1541,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3580,6 +3582,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3588,6 +3591,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4121,18 +4125,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -7195,6 +7209,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -7209,7 +7236,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -7217,12 +7243,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.