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

Pull networking fixes from David Miller:

 1) nfnetlink timestamp taken from wrong skb, fix from Florian Westphal.

 2) Revert some msleep conversions in rtlwifi as these spots are in
    atomic context, from Larry Finger.

 3) Validate that NFTA_SET_TABLE attribute is actually specified when we
    call nf_tables_getset().  From Phil Turnbull.

 4) Don't do mdio_reset in stmmac driver with spinlock held as that can
    sleep, from Vincent Palatin.

 5) sk_filter() does things other than run a BPF filter, so we should
    not elide it's call just because sk->sk_filter is NULL.  Fix from
    Eric Dumazet.

 6) Fix missing backlog updates in several packet schedulers, from Cong
    Wang.

 7) bnx2x driver should allow VLAN add/remove while the interface is
    down, from Michal Schmidt.

 8) Several RDS/TCP race fixes from Sowmini Varadhan.

 9) fq_codel scheduler doesn't return correct queue length in dumps,
    from Eric Dumazet.

10) Fix TCP stats for tail loss probe and early retransmit in ipv6, from
    Yuchung Cheng.

11) Properly initialize udp_tunnel_socket_cfg in l2tp_tunnel_create(),
    from Guillaume Nault.

12) qfq scheduler leaks SKBs if a kzalloc fails, fix from Florian
    Westphal.

13) sock_fprog passed into PACKET_FANOUT_DATA needs compat handling,
    from Willem de Bruijn.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (85 commits)
  vmxnet3: segCnt can be 1 for LRO packets
  packet: compat support for sock_fprog
  stmmac: fix parameter to dwmac4_set_umac_addr()
  net/mlx5e: Fix blue flame quota logic
  net/mlx5e: Use ndo_stop explicitly at shutdown flow
  net/mlx5: E-Switch, always set mc_promisc for allmulti vports
  net/mlx5: E-Switch, Modify node guid on vf set MAC
  net/mlx5: E-Switch, Fix vport enable flow
  net/mlx5: E-Switch, Use the correct error check on returned pointers
  net/mlx5: E-Switch, Use the correct free() function
  net/mlx5: Fix E-Switch flow steering capabilities check
  net/mlx5: Fix flow steering NIC capabilities check
  net/mlx5: Fix root flow table update
  net/mlx5: Fix MLX5_CMD_OP_MAX to be defined correctly
  net/mlx5: Fix masking of reserved bits in XRCD number
  net/mlx5: Fix the size of modify QP mailbox
  mlxsw: spectrum: Don't sleep during ndo_get_phys_port_name()
  mlxsw: spectrum: Make split flow match firmware requirements
  wext: Fix 32 bit iwpriv compatibility issue with 64 bit Kernel
  cfg80211: remove get/set antenna and tx power warnings
  ...

1 files changed, 75 insertions, 3 deletions

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 86187dad1440..74ee126a6fe6 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -126,9 +126,81 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 }
 
 /*
- * This is the only path that sets tc->t_sock.  Send and receive trust that
- * it is set.  The RDS_CONN_UP bit protects those paths from being
- * called while it isn't set.
+ * rds_tcp_reset_callbacks() switches the to the new sock and
+ * returns the existing tc->t_sock.
+ *
+ * The only functions that set tc->t_sock are rds_tcp_set_callbacks
+ * and rds_tcp_reset_callbacks.  Send and receive trust that
+ * it is set.  The absence of RDS_CONN_UP bit protects those paths
+ * from being called while it isn't set.
+ */
+void rds_tcp_reset_callbacks(struct socket *sock,
+			     struct rds_connection *conn)
+{
+	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct socket *osock = tc->t_sock;
+
+	if (!osock)
+		goto newsock;
+
+	/* Need to resolve a duelling SYN between peers.
+	 * We have an outstanding SYN to this peer, which may
+	 * potentially have transitioned to the RDS_CONN_UP state,
+	 * so we must quiesce any send threads before resetting
+	 * c_transport_data. We quiesce these threads by setting
+	 * c_state to something other than RDS_CONN_UP, and then
+	 * waiting for any existing threads in rds_send_xmit to
+	 * complete release_in_xmit(). (Subsequent threads entering
+	 * rds_send_xmit() will bail on !rds_conn_up().
+	 *
+	 * However an incoming syn-ack at this point would end up
+	 * marking the conn as RDS_CONN_UP, and would again permit
+	 * rds_send_xmi() threads through, so ideally we would
+	 * synchronize on RDS_CONN_UP after lock_sock(), but cannot
+	 * do that: waiting on !RDS_IN_XMIT after lock_sock() may
+	 * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT
+	 * would not get set. As a result, we set c_state to
+	 * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change
+	 * cannot mark rds_conn_path_up() in the window before lock_sock()
+	 */
+	atomic_set(&conn->c_state, RDS_CONN_RESETTING);
+	wait_event(conn->c_waitq, !test_bit(RDS_IN_XMIT, &conn->c_flags));
+	lock_sock(osock->sk);
+	/* reset receive side state for rds_tcp_data_recv() for osock  */
+	if (tc->t_tinc) {
+		rds_inc_put(&tc->t_tinc->ti_inc);
+		tc->t_tinc = NULL;
+	}
+	tc->t_tinc_hdr_rem = sizeof(struct rds_header);
+	tc->t_tinc_data_rem = 0;
+	tc->t_sock = NULL;
+
+	write_lock_bh(&osock->sk->sk_callback_lock);
+
+	osock->sk->sk_user_data = NULL;
+	osock->sk->sk_data_ready = tc->t_orig_data_ready;
+	osock->sk->sk_write_space = tc->t_orig_write_space;
+	osock->sk->sk_state_change = tc->t_orig_state_change;
+	write_unlock_bh(&osock->sk->sk_callback_lock);
+	release_sock(osock->sk);
+	sock_release(osock);
+newsock:
+	rds_send_reset(conn);
+	lock_sock(sock->sk);
+	write_lock_bh(&sock->sk->sk_callback_lock);
+	tc->t_sock = sock;
+	sock->sk->sk_user_data = conn;
+	sock->sk->sk_data_ready = rds_tcp_data_ready;
+	sock->sk->sk_write_space = rds_tcp_write_space;
+	sock->sk->sk_state_change = rds_tcp_state_change;
+
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+	release_sock(sock->sk);
+}
+
+/* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments
+ * above rds_tcp_reset_callbacks for notes about synchronization
+ * with data path
  */
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
 {