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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

1 files changed, 36 insertions, 13 deletions

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 4c0766e201e3..b01d8dd9ee7c 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -106,6 +106,34 @@ struct listen_sock {
 	struct request_sock	*syn_table[0];
 };
 
+/*
+ * For a TCP Fast Open listener -
+ *	lock - protects the access to all the reqsk, which is co-owned by
+ *		the listener and the child socket.
+ *	qlen - pending TFO requests (still in TCP_SYN_RECV).
+ *	max_qlen - max TFO reqs allowed before TFO is disabled.
+ *
+ *	XXX (TFO) - ideally these fields can be made as part of "listen_sock"
+ *	structure above. But there is some implementation difficulty due to
+ *	listen_sock being part of request_sock_queue hence will be freed when
+ *	a listener is stopped. But TFO related fields may continue to be
+ *	accessed even after a listener is closed, until its sk_refcnt drops
+ *	to 0 implying no more outstanding TFO reqs. One solution is to keep
+ *	listen_opt around until	sk_refcnt drops to 0. But there is some other
+ *	complexity that needs to be resolved. E.g., a listener can be disabled
+ *	temporarily through shutdown()->tcp_disconnect(), and re-enabled later.
+ */
+struct fastopen_queue {
+	struct request_sock	*rskq_rst_head; /* Keep track of past TFO */
+	struct request_sock	*rskq_rst_tail; /* requests that caused RST.
+						 * This is part of the defense
+						 * against spoofing attack.
+						 */
+	spinlock_t	lock;
+	int		qlen;		/* # of pending (TCP_SYN_RECV) reqs */
+	int		max_qlen;	/* != 0 iff TFO is currently enabled */
+};
+
 /** struct request_sock_queue - queue of request_socks
  *
  * @rskq_accept_head - FIFO head of established children
@@ -129,6 +157,12 @@ struct request_sock_queue {
 	u8			rskq_defer_accept;
 	/* 3 bytes hole, try to pack */
 	struct listen_sock	*listen_opt;
+	struct fastopen_queue	*fastopenq; /* This is non-NULL iff TFO has been
+					     * enabled on this listener. Check
+					     * max_qlen != 0 in fastopen_queue
+					     * to determine if TFO is enabled
+					     * right at this moment.
+					     */
 };
 
 extern int reqsk_queue_alloc(struct request_sock_queue *queue,
@@ -136,6 +170,8 @@ extern int reqsk_queue_alloc(struct request_sock_queue *queue,
 
 extern void __reqsk_queue_destroy(struct request_sock_queue *queue);
 extern void reqsk_queue_destroy(struct request_sock_queue *queue);
+extern void reqsk_fastopen_remove(struct sock *sk,
+				  struct request_sock *req, bool reset);
 
 static inline struct request_sock *
 	reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
@@ -190,19 +226,6 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue
 	return req;
 }
 
-static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue,
-						 struct sock *parent)
-{
-	struct request_sock *req = reqsk_queue_remove(queue);
-	struct sock *child = req->sk;
-
-	WARN_ON(child == NULL);
-
-	sk_acceptq_removed(parent);
-	__reqsk_free(req);
-	return child;
-}
-
 static inline int reqsk_queue_removed(struct request_sock_queue *queue,
 				      struct request_sock *req)
 {