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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 9 insertions, 59 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 1f4f954c4b47..de88c4ab5146 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -352,40 +352,6 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct)
 	local_bh_enable();
 }
 
-static void death_by_event(unsigned long ul_conntrack)
-{
-	struct nf_conn *ct = (void *)ul_conntrack;
-	struct net *net = nf_ct_net(ct);
-	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
-
-	BUG_ON(ecache == NULL);
-
-	if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) {
-		/* bad luck, let's retry again */
-		ecache->timeout.expires = jiffies +
-			(prandom_u32() % net->ct.sysctl_events_retry_timeout);
-		add_timer(&ecache->timeout);
-		return;
-	}
-	/* we've got the event delivered, now it's dying */
-	set_bit(IPS_DYING_BIT, &ct->status);
-	nf_ct_put(ct);
-}
-
-static void nf_ct_dying_timeout(struct nf_conn *ct)
-{
-	struct net *net = nf_ct_net(ct);
-	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
-
-	BUG_ON(ecache == NULL);
-
-	/* set a new timer to retry event delivery */
-	setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
-	ecache->timeout.expires = jiffies +
-		(prandom_u32() % net->ct.sysctl_events_retry_timeout);
-	add_timer(&ecache->timeout);
-}
-
 bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 {
 	struct nf_conn_tstamp *tstamp;
@@ -394,15 +360,20 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 	if (tstamp && tstamp->stop == 0)
 		tstamp->stop = ktime_to_ns(ktime_get_real());
 
-	if (!nf_ct_is_dying(ct) &&
-	    unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct,
-	    portid, report) < 0)) {
+	if (nf_ct_is_dying(ct))
+		goto delete;
+
+	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
+				    portid, report) < 0) {
 		/* destroy event was not delivered */
 		nf_ct_delete_from_lists(ct);
-		nf_ct_dying_timeout(ct);
+		nf_conntrack_ecache_delayed_work(nf_ct_net(ct));
 		return false;
 	}
+
+	nf_conntrack_ecache_work(nf_ct_net(ct));
 	set_bit(IPS_DYING_BIT, &ct->status);
+ delete:
 	nf_ct_delete_from_lists(ct);
 	nf_ct_put(ct);
 	return true;
@@ -1464,26 +1435,6 @@ void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
 
-static void nf_ct_release_dying_list(struct net *net)
-{
-	struct nf_conntrack_tuple_hash *h;
-	struct nf_conn *ct;
-	struct hlist_nulls_node *n;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
-
-		spin_lock_bh(&pcpu->lock);
-		hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) {
-			ct = nf_ct_tuplehash_to_ctrack(h);
-			/* never fails to remove them, no listeners at this point */
-			nf_ct_kill(ct);
-		}
-		spin_unlock_bh(&pcpu->lock);
-	}
-}
-
 static int untrack_refs(void)
 {
 	int cnt = 0, cpu;
@@ -1548,7 +1499,6 @@ i_see_dead_people:
 	busy = 0;
 	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0);
-		nf_ct_release_dying_list(net);
 		if (atomic_read(&net->ct.count) != 0)
 			busy = 1;
 	}