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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 28 insertions, 6 deletions

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 7b2c2fce408a..42a95919df09 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -66,7 +66,9 @@ struct ovs_conntrack_info {
 	u8 commit : 1;
 	u8 nat : 3;                 /* enum ovs_ct_nat */
 	u8 force : 1;
+	u8 have_eventmask : 1;
 	u16 family;
+	u32 eventmask;              /* Mask of 1 << IPCT_*. */
 	struct md_mark mark;
 	struct md_labels labels;
 #ifdef CONFIG_NF_NAT_NEEDED
@@ -373,7 +375,7 @@ static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key,
 	}
 
 	/* Labels are included in the IPCTNL_MSG_CT_NEW event only if the
-	 * IPCT_LABEL bit it set in the event cache.
+	 * IPCT_LABEL bit is set in the event cache.
 	 */
 	nf_conntrack_event_cache(IPCT_LABEL, ct);
 
@@ -795,11 +797,6 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	enum nf_nat_manip_type maniptype;
 	int err;
 
-	if (nf_ct_is_untracked(ct)) {
-		/* A NAT action may only be performed on tracked packets. */
-		return NF_ACCEPT;
-	}
-
 	/* Add NAT extension if not confirmed yet. */
 	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
 		return NF_ACCEPT;   /* Can't NAT. */
@@ -1007,6 +1004,20 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 	if (!ct)
 		return 0;
 
+	/* Set the conntrack event mask if given.  NEW and DELETE events have
+	 * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener
+	 * typically would receive many kinds of updates.  Setting the event
+	 * mask allows those events to be filtered.  The set event mask will
+	 * remain in effect for the lifetime of the connection unless changed
+	 * by a further CT action with both the commit flag and the eventmask
+	 * option. */
+	if (info->have_eventmask) {
+		struct nf_conntrack_ecache *cache = nf_ct_ecache_find(ct);
+
+		if (cache)
+			cache->ctmask = info->eventmask;
+	}
+
 	/* Apply changes before confirming the connection so that the initial
 	 * conntrack NEW netlink event carries the values given in the CT
 	 * action.
@@ -1238,6 +1249,8 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
 	/* NAT length is checked when parsing the nested attributes. */
 	[OVS_CT_ATTR_NAT]	= { .minlen = 0, .maxlen = INT_MAX },
 #endif
+	[OVS_CT_ATTR_EVENTMASK]	= { .minlen = sizeof(u32),
+				    .maxlen = sizeof(u32) },
 };
 
 static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
@@ -1316,6 +1329,11 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 			break;
 		}
 #endif
+		case OVS_CT_ATTR_EVENTMASK:
+			info->have_eventmask = true;
+			info->eventmask = nla_get_u32(a);
+			break;
+
 		default:
 			OVS_NLERR(log, "Unknown conntrack attr (%d)",
 				  type);
@@ -1515,6 +1533,10 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 				   ct_info->helper->name))
 			return -EMSGSIZE;
 	}
+	if (ct_info->have_eventmask &&
+	    nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask))
+		return -EMSGSIZE;
+
 #ifdef CONFIG_NF_NAT_NEEDED
 	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
 		return -EMSGSIZE;