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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 21 insertions, 13 deletions

diff --git a/net/tipc/link.c b/net/tipc/link.c
index ac0144f532aa..6bce0b1117bd 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -239,7 +239,8 @@ static int link_is_up(struct tipc_link *l)
 static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			       struct sk_buff_head *xmitq);
 static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
-				      u16 rcvgap, int tolerance, int priority,
+				      bool probe_reply, u16 rcvgap,
+				      int tolerance, int priority,
 				      struct sk_buff_head *xmitq);
 static void link_print(struct tipc_link *l, const char *str);
 static int tipc_link_build_nack_msg(struct tipc_link *l,
@@ -773,7 +774,7 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 	}
 
 	if (state || probe || setup)
-		tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, xmitq);
+		tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq);
 
 	return rc;
 }
@@ -1039,6 +1040,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
 static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 			    struct sk_buff_head *inputq)
 {
+	struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq;
 	struct tipc_msg *hdr = buf_msg(skb);
 
 	switch (msg_user(hdr)) {
@@ -1046,13 +1048,16 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 	case TIPC_MEDIUM_IMPORTANCE:
 	case TIPC_HIGH_IMPORTANCE:
 	case TIPC_CRITICAL_IMPORTANCE:
-		if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) {
-			skb_queue_tail(l->bc_rcvlink->inputq, skb);
+		if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) {
+			skb_queue_tail(mc_inputq, skb);
 			return true;
 		}
 	case CONN_MANAGER:
 		skb_queue_tail(inputq, skb);
 		return true;
+	case GROUP_PROTOCOL:
+		skb_queue_tail(mc_inputq, skb);
+		return true;
 	case NAME_DISTRIBUTOR:
 		l->bc_rcvlink->state = LINK_ESTABLISHED;
 		skb_queue_tail(l->namedq, skb);
@@ -1170,7 +1175,7 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
 	/* Unicast ACK */
 	l->rcv_unacked = 0;
 	l->stats.sent_acks++;
-	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq);
+	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
 	return 0;
 }
 
@@ -1184,7 +1189,7 @@ void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
 	if (l->state == LINK_ESTABLISHING)
 		mtyp = ACTIVATE_MSG;
 
-	tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, xmitq);
+	tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, 0, xmitq);
 
 	/* Inform peer that this endpoint is going down if applicable */
 	skb = skb_peek_tail(xmitq);
@@ -1211,7 +1216,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
 	}
 
 	if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV))
-		tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq);
+		tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
 	return 0;
 }
 
@@ -1285,7 +1290,8 @@ drop:
 }
 
 static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
-				      u16 rcvgap, int tolerance, int priority,
+				      bool probe_reply, u16 rcvgap,
+				      int tolerance, int priority,
 				      struct sk_buff_head *xmitq)
 {
 	struct tipc_link *bcl = l->bc_rcvlink;
@@ -1333,6 +1339,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		msg_set_seq_gap(hdr, rcvgap);
 		msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
 		msg_set_probe(hdr, probe);
+		msg_set_is_keepalive(hdr, probe || probe_reply);
 		tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
 		msg_set_size(hdr, INT_H_SIZE + dlen);
 		skb_trim(skb, INT_H_SIZE + dlen);
@@ -1438,6 +1445,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	u16 rcv_nxt = l->rcv_nxt;
 	u16 dlen = msg_data_sz(hdr);
 	int mtyp = msg_type(hdr);
+	bool reply = msg_probe(hdr);
 	void *data;
 	char *if_name;
 	int rc = 0;
@@ -1524,9 +1532,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		/* Send NACK if peer has sent pkts we haven't received yet */
 		if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
 			rcvgap = peers_snd_nxt - l->rcv_nxt;
-		if (rcvgap || (msg_probe(hdr)))
-			tipc_link_build_proto_msg(l, STATE_MSG, 0, rcvgap,
-						  0, 0, xmitq);
+		if (rcvgap || reply)
+			tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
+						  rcvgap, 0, 0, xmitq);
 		tipc_link_release_pkts(l, ack);
 
 		/* If NACK, retransmit will now start at right position */
@@ -2118,14 +2126,14 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
 			     struct sk_buff_head *xmitq)
 {
 	l->tolerance = tol;
-	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, tol, 0, xmitq);
+	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq);
 }
 
 void tipc_link_set_prio(struct tipc_link *l, u32 prio,
 			struct sk_buff_head *xmitq)
 {
 	l->priority = prio;
-	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, prio, xmitq);
+	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, prio, xmitq);
 }
 
 void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit)