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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 40 insertions, 36 deletions

diff --git a/net/tipc/server.c b/net/tipc/server.c
index 78a292a84afc..df0c563c90cd 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -132,10 +132,11 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid)
 
 	spin_lock_bh(&s->idr_lock);
 	con = idr_find(&s->conn_idr, conid);
-	if (con && test_bit(CF_CONNECTED, &con->flags))
-		conn_get(con);
-	else
-		con = NULL;
+	if (con) {
+		if (!test_bit(CF_CONNECTED, &con->flags) ||
+		    !kref_get_unless_zero(&con->kref))
+			con = NULL;
+	}
 	spin_unlock_bh(&s->idr_lock);
 	return con;
 }
@@ -183,35 +184,28 @@ static void tipc_register_callbacks(struct socket *sock, struct tipc_conn *con)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
-static void tipc_unregister_callbacks(struct tipc_conn *con)
-{
-	struct sock *sk = con->sock->sk;
-
-	write_lock_bh(&sk->sk_callback_lock);
-	sk->sk_user_data = NULL;
-	write_unlock_bh(&sk->sk_callback_lock);
-}
-
 static void tipc_close_conn(struct tipc_conn *con)
 {
 	struct tipc_server *s = con->server;
+	struct sock *sk = con->sock->sk;
+	bool disconnect = false;
 
-	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
-		if (con->sock)
-			tipc_unregister_callbacks(con);
-
+	write_lock_bh(&sk->sk_callback_lock);
+	disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags);
+	if (disconnect) {
+		sk->sk_user_data = NULL;
 		if (con->conid)
 			s->tipc_conn_release(con->conid, con->usr_data);
-
-		/* We shouldn't flush pending works as we may be in the
-		 * thread. In fact the races with pending rx/tx work structs
-		 * are harmless for us here as we have already deleted this
-		 * connection from server connection list.
-		 */
-		if (con->sock)
-			kernel_sock_shutdown(con->sock, SHUT_RDWR);
-		conn_put(con);
 	}
+	write_unlock_bh(&sk->sk_callback_lock);
+
+	/* Handle concurrent calls from sending and receiving threads */
+	if (!disconnect)
+		return;
+
+	/* Don't flush pending works, -just let them expire */
+	kernel_sock_shutdown(con->sock, SHUT_RDWR);
+	conn_put(con);
 }
 
 static struct tipc_conn *tipc_alloc_conn(struct tipc_server *s)
@@ -248,9 +242,10 @@ static struct tipc_conn *tipc_alloc_conn(struct tipc_server *s)
 
 static int tipc_receive_from_sock(struct tipc_conn *con)
 {
-	struct msghdr msg = {};
 	struct tipc_server *s = con->server;
+	struct sock *sk = con->sock->sk;
 	struct sockaddr_tipc addr;
+	struct msghdr msg = {};
 	struct kvec iov;
 	void *buf;
 	int ret;
@@ -271,12 +266,15 @@ static int tipc_receive_from_sock(struct tipc_conn *con)
 		goto out_close;
 	}
 
-	s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid, &addr,
-			     con->usr_data, buf, ret);
-
+	read_lock_bh(&sk->sk_callback_lock);
+	if (test_bit(CF_CONNECTED, &con->flags))
+		ret = s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid,
+					   &addr, con->usr_data, buf, ret);
+	read_unlock_bh(&sk->sk_callback_lock);
 	kmem_cache_free(s->rcvbuf_cache, buf);
-
-	return 0;
+	if (ret < 0)
+		tipc_conn_terminate(s, con->conid);
+	return ret;
 
 out_close:
 	if (ret != -EWOULDBLOCK)
@@ -489,8 +487,8 @@ void tipc_conn_terminate(struct tipc_server *s, int conid)
 	}
 }
 
-bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
-			     u32 lower, u32 upper, int *conid)
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower,
+			     u32 upper, u32 filter, int *conid)
 {
 	struct tipc_subscriber *scbr;
 	struct tipc_subscr sub;
@@ -501,7 +499,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
 	sub.seq.lower = lower;
 	sub.seq.upper = upper;
 	sub.timeout = TIPC_WAIT_FOREVER;
-	sub.filter = TIPC_SUB_PORTS;
+	sub.filter = filter;
 	*(u32 *)&sub.usr_handle = port;
 
 	con = tipc_alloc_conn(tipc_topsrv(net));
@@ -525,11 +523,17 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
 void tipc_topsrv_kern_unsubscr(struct net *net, int conid)
 {
 	struct tipc_conn *con;
+	struct tipc_server *srv;
 
 	con = tipc_conn_lookup(tipc_topsrv(net), conid);
 	if (!con)
 		return;
-	tipc_close_conn(con);
+
+	test_and_clear_bit(CF_CONNECTED, &con->flags);
+	srv = con->server;
+	if (con->conid)
+		srv->tipc_conn_release(con->conid, con->usr_data);
+	conn_put(con);
 	conn_put(con);
 }