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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 77 insertions, 39 deletions

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 86152de8248d..22c059ad2999 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -42,6 +42,7 @@
 
 static void node_lost_contact(struct tipc_node *n_ptr);
 static void node_established_contact(struct tipc_node *n_ptr);
+static void tipc_node_delete(struct tipc_node *node);
 
 struct tipc_sock_conn {
 	u32 port;
@@ -67,6 +68,23 @@ static unsigned int tipc_hashfn(u32 addr)
 	return addr & (NODE_HTABLE_SIZE - 1);
 }
 
+static void tipc_node_kref_release(struct kref *kref)
+{
+	struct tipc_node *node = container_of(kref, struct tipc_node, kref);
+
+	tipc_node_delete(node);
+}
+
+void tipc_node_put(struct tipc_node *node)
+{
+	kref_put(&node->kref, tipc_node_kref_release);
+}
+
+static void tipc_node_get(struct tipc_node *node)
+{
+	kref_get(&node->kref);
+}
+
 /*
  * tipc_node_find - locate specified node object, if it exists
  */
@@ -82,6 +100,7 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr)
 	hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)],
 				 hash) {
 		if (node->addr == addr) {
+			tipc_node_get(node);
 			rcu_read_unlock();
 			return node;
 		}
@@ -106,12 +125,13 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr)
 	}
 	n_ptr->addr = addr;
 	n_ptr->net = net;
+	kref_init(&n_ptr->kref);
 	spin_lock_init(&n_ptr->lock);
 	INIT_HLIST_NODE(&n_ptr->hash);
 	INIT_LIST_HEAD(&n_ptr->list);
 	INIT_LIST_HEAD(&n_ptr->publ_list);
 	INIT_LIST_HEAD(&n_ptr->conn_sks);
-	__skb_queue_head_init(&n_ptr->bclink.deferred_queue);
+	__skb_queue_head_init(&n_ptr->bclink.deferdq);
 	hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]);
 	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
 		if (n_ptr->addr < temp_node->addr)
@@ -120,16 +140,17 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr)
 	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
 	n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN;
 	n_ptr->signature = INVALID_NODE_SIG;
+	tipc_node_get(n_ptr);
 exit:
 	spin_unlock_bh(&tn->node_list_lock);
 	return n_ptr;
 }
 
-static void tipc_node_delete(struct tipc_net *tn, struct tipc_node *n_ptr)
+static void tipc_node_delete(struct tipc_node *node)
 {
-	list_del_rcu(&n_ptr->list);
-	hlist_del_rcu(&n_ptr->hash);
-	kfree_rcu(n_ptr, rcu);
+	list_del_rcu(&node->list);
+	hlist_del_rcu(&node->hash);
+	kfree_rcu(node, rcu);
 }
 
 void tipc_node_stop(struct net *net)
@@ -139,7 +160,7 @@ void tipc_node_stop(struct net *net)
 
 	spin_lock_bh(&tn->node_list_lock);
 	list_for_each_entry_safe(node, t_node, &tn->node_list, list)
-		tipc_node_delete(tn, node);
+		tipc_node_put(node);
 	spin_unlock_bh(&tn->node_list_lock);
 }
 
@@ -147,6 +168,7 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
 {
 	struct tipc_node *node;
 	struct tipc_sock_conn *conn;
+	int err = 0;
 
 	if (in_own_node(net, dnode))
 		return 0;
@@ -157,8 +179,10 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
 		return -EHOSTUNREACH;
 	}
 	conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
-	if (!conn)
-		return -EHOSTUNREACH;
+	if (!conn) {
+		err = -EHOSTUNREACH;
+		goto exit;
+	}
 	conn->peer_node = dnode;
 	conn->port = port;
 	conn->peer_port = peer_port;
@@ -166,7 +190,9 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
 	tipc_node_lock(node);
 	list_add_tail(&conn->list, &node->conn_sks);
 	tipc_node_unlock(node);
-	return 0;
+exit:
+	tipc_node_put(node);
+	return err;
 }
 
 void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
@@ -189,6 +215,7 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
 		kfree(conn);
 	}
 	tipc_node_unlock(node);
+	tipc_node_put(node);
 }
 
 /**
@@ -227,8 +254,8 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 	active[0] = active[1] = l_ptr;
 exit:
 	/* Leave room for changeover header when returning 'mtu' to users: */
-	n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
-	n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
+	n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE;
+	n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE;
 }
 
 /**
@@ -292,11 +319,10 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 
 	/* Leave room for changeover header when returning 'mtu' to users: */
 	if (active[0]) {
-		n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
-		n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
+		n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE;
+		n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE;
 		return;
 	}
-
 	/* Loopback link went down? No fragmentation needed from now on. */
 	if (n_ptr->addr == tn->own_addr) {
 		n_ptr->act_mtus[0] = MAX_MSG_SIZE;
@@ -354,7 +380,7 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 
 	/* Flush broadcast link info associated with lost node */
 	if (n_ptr->bclink.recv_permitted) {
-		__skb_queue_purge(&n_ptr->bclink.deferred_queue);
+		__skb_queue_purge(&n_ptr->bclink.deferdq);
 
 		if (n_ptr->bclink.reasm_buf) {
 			kfree_skb(n_ptr->bclink.reasm_buf);
@@ -367,18 +393,17 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 		n_ptr->bclink.recv_permitted = false;
 	}
 
-	/* Abort link changeover */
+	/* Abort any ongoing link failover */
 	for (i = 0; i < MAX_BEARERS; i++) {
 		struct tipc_link *l_ptr = n_ptr->links[i];
 		if (!l_ptr)
 			continue;
-		l_ptr->reset_checkpoint = l_ptr->next_in_no;
-		l_ptr->exp_msg_count = 0;
+		l_ptr->flags &= ~LINK_FAILINGOVER;
+		l_ptr->failover_checkpt = 0;
+		l_ptr->failover_pkts = 0;
+		kfree_skb(l_ptr->failover_skb);
+		l_ptr->failover_skb = NULL;
 		tipc_link_reset_fragments(l_ptr);
-
-		/* Link marked for deletion after failover? => do it now */
-		if (l_ptr->flags & LINK_STOPPED)
-			tipc_link_delete(l_ptr);
 	}
 
 	n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;
@@ -417,19 +442,25 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
 			   char *linkname, size_t len)
 {
 	struct tipc_link *link;
+	int err = -EINVAL;
 	struct tipc_node *node = tipc_node_find(net, addr);
 
-	if ((bearer_id >= MAX_BEARERS) || !node)
-		return -EINVAL;
+	if (!node)
+		return err;
+
+	if (bearer_id >= MAX_BEARERS)
+		goto exit;
+
 	tipc_node_lock(node);
 	link = node->links[bearer_id];
 	if (link) {
 		strncpy(linkname, link->name, len);
-		tipc_node_unlock(node);
-		return 0;
+		err = 0;
 	}
+exit:
 	tipc_node_unlock(node);
-	return -EINVAL;
+	tipc_node_put(node);
+	return err;
 }
 
 void tipc_node_unlock(struct tipc_node *node)
@@ -459,7 +490,7 @@ void tipc_node_unlock(struct tipc_node *node)
 				TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
 				TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP |
 				TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT |
-				TIPC_NAMED_MSG_EVT);
+				TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET);
 
 	spin_unlock_bh(&node->lock);
 
@@ -488,6 +519,9 @@ void tipc_node_unlock(struct tipc_node *node)
 
 	if (flags & TIPC_BCAST_MSG_EVT)
 		tipc_bclink_input(net);
+
+	if (flags & TIPC_BCAST_RESET)
+		tipc_link_reset_all(node);
 }
 
 /* Caller should hold node lock for the passed node */
@@ -542,17 +576,21 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	msg.seq = cb->nlh->nlmsg_seq;
 
 	rcu_read_lock();
-
-	if (last_addr && !tipc_node_find(net, last_addr)) {
-		rcu_read_unlock();
-		/* We never set seq or call nl_dump_check_consistent() this
-		 * means that setting prev_seq here will cause the consistence
-		 * check to fail in the netlink callback handler. Resulting in
-		 * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if
-		 * the node state changed while we released the lock.
-		 */
-		cb->prev_seq = 1;
-		return -EPIPE;
+	if (last_addr) {
+		node = tipc_node_find(net, last_addr);
+		if (!node) {
+			rcu_read_unlock();
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the NLMSG_DONE message having
+			 * the NLM_F_DUMP_INTR flag set if the node state
+			 * changed while we released the lock.
+			 */
+			cb->prev_seq = 1;
+			return -EPIPE;
+		}
+		tipc_node_put(node);
 	}
 
 	list_for_each_entry_rcu(node, &tn->node_list, list) {