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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 147 insertions, 18 deletions

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index edac9ef..c42b60b 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -35,6 +35,9 @@
 #include <linux/in.h>
 #include <linux/module.h>
 #include <net/tcp.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/tcp.h>
 
 #include "rds.h"
 #include "tcp.h"
@@ -189,9 +192,9 @@ out:
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
-static int rds_tcp_laddr_check(__be32 addr)
+static int rds_tcp_laddr_check(struct net *net, __be32 addr)
 {
-	if (inet_addr_type(&init_net, addr) == RTN_LOCAL)
+	if (inet_addr_type(net, addr) == RTN_LOCAL)
 		return 0;
 	return -EADDRNOTAVAIL;
 }
@@ -250,16 +253,7 @@ static void rds_tcp_destroy_conns(void)
 	}
 }
 
-static void rds_tcp_exit(void)
-{
-	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
-	rds_tcp_listen_stop();
-	rds_tcp_destroy_conns();
-	rds_trans_unregister(&rds_tcp_transport);
-	rds_tcp_recv_exit();
-	kmem_cache_destroy(rds_tcp_conn_slab);
-}
-module_exit(rds_tcp_exit);
+static void rds_tcp_exit(void);
 
 struct rds_transport rds_tcp_transport = {
 	.laddr_check		= rds_tcp_laddr_check,
@@ -281,6 +275,136 @@ struct rds_transport rds_tcp_transport = {
 	.t_prefer_loopback	= 1,
 };
 
+static int rds_tcp_netid;
+
+/* per-network namespace private data for this module */
+struct rds_tcp_net {
+	struct socket *rds_tcp_listen_sock;
+	struct work_struct rds_tcp_accept_w;
+};
+
+static void rds_tcp_accept_worker(struct work_struct *work)
+{
+	struct rds_tcp_net *rtn = container_of(work,
+					       struct rds_tcp_net,
+					       rds_tcp_accept_w);
+
+	while (rds_tcp_accept_one(rtn->rds_tcp_listen_sock) == 0)
+		cond_resched();
+}
+
+void rds_tcp_accept_work(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	queue_work(rds_wq, &rtn->rds_tcp_accept_w);
+}
+
+static __net_init int rds_tcp_init_net(struct net *net)
+{
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net);
+	if (!rtn->rds_tcp_listen_sock) {
+		pr_warn("could not set up listen sock\n");
+		return -EAFNOSUPPORT;
+	}
+	INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker);
+	return 0;
+}
+
+static void __net_exit rds_tcp_exit_net(struct net *net)
+{
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	/* If rds_tcp_exit_net() is called as a result of netns deletion,
+	 * the rds_tcp_kill_sock() device notifier would already have cleaned
+	 * up the listen socket, thus there is no work to do in this function.
+	 *
+	 * If rds_tcp_exit_net() is called as a result of module unload,
+	 * i.e., due to rds_tcp_exit() -> unregister_pernet_subsys(), then
+	 * we do need to clean up the listen socket here.
+	 */
+	if (rtn->rds_tcp_listen_sock) {
+		rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+		rtn->rds_tcp_listen_sock = NULL;
+		flush_work(&rtn->rds_tcp_accept_w);
+	}
+}
+
+static struct pernet_operations rds_tcp_net_ops = {
+	.init = rds_tcp_init_net,
+	.exit = rds_tcp_exit_net,
+	.id = &rds_tcp_netid,
+	.size = sizeof(struct rds_tcp_net),
+};
+
+static void rds_tcp_kill_sock(struct net *net)
+{
+	struct rds_tcp_connection *tc, *_tc;
+	struct sock *sk;
+	LIST_HEAD(tmp_list);
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+	rtn->rds_tcp_listen_sock = NULL;
+	flush_work(&rtn->rds_tcp_accept_w);
+	spin_lock_irq(&rds_tcp_conn_lock);
+	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
+		struct net *c_net = read_pnet(&tc->conn->c_net);
+
+		if (net != c_net || !tc->t_sock)
+			continue;
+		list_move_tail(&tc->t_tcp_node, &tmp_list);
+	}
+	spin_unlock_irq(&rds_tcp_conn_lock);
+	list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) {
+		sk = tc->t_sock->sk;
+		sk->sk_prot->disconnect(sk, 0);
+		tcp_done(sk);
+		if (tc->conn->c_passive)
+			rds_conn_destroy(tc->conn->c_passive);
+		rds_conn_destroy(tc->conn);
+	}
+}
+
+static int rds_tcp_dev_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	/* rds-tcp registers as a pernet subys, so the ->exit will only
+	 * get invoked after network acitivity has quiesced. We need to
+	 * clean up all sockets  to quiesce network activity, and use
+	 * the unregistration of the per-net loopback device as a trigger
+	 * to start that cleanup.
+	 */
+	if (event == NETDEV_UNREGISTER_FINAL &&
+	    dev->ifindex == LOOPBACK_IFINDEX)
+		rds_tcp_kill_sock(dev_net(dev));
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rds_tcp_dev_notifier = {
+	.notifier_call        = rds_tcp_dev_event,
+	.priority = -10, /* must be called after other network notifiers */
+};
+
+static void rds_tcp_exit(void)
+{
+	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	unregister_pernet_subsys(&rds_tcp_net_ops);
+	if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
+		pr_warn("could not unregister rds_tcp_dev_notifier\n");
+	rds_tcp_destroy_conns();
+	rds_trans_unregister(&rds_tcp_transport);
+	rds_tcp_recv_exit();
+	kmem_cache_destroy(rds_tcp_conn_slab);
+}
+module_exit(rds_tcp_exit);
+
 static int rds_tcp_init(void)
 {
 	int ret;
@@ -293,6 +417,16 @@ static int rds_tcp_init(void)
 		goto out;
 	}
 
+	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+	if (ret) {
+		pr_warn("could not register rds_tcp_dev_notifier\n");
+		goto out;
+	}
+
+	ret = register_pernet_subsys(&rds_tcp_net_ops);
+	if (ret)
+		goto out_slab;
+
 	ret = rds_tcp_recv_init();
 	if (ret)
 		goto out_slab;
@@ -301,19 +435,14 @@ static int rds_tcp_init(void)
 	if (ret)
 		goto out_recv;
 
-	ret = rds_tcp_listen_init();
-	if (ret)
-		goto out_register;
-
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
 
 	goto out;
 
-out_register:
-	rds_trans_unregister(&rds_tcp_transport);
 out_recv:
 	rds_tcp_recv_exit();
 out_slab:
+	unregister_pernet_subsys(&rds_tcp_net_ops);
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;