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

Pull networking changes from David Miller:
 "Noteworthy changes this time around:

   1) Multicast rejoin support for team driver, from Jiri Pirko.

   2) Centralize and simplify TCP RTT measurement handling in order to
      reduce the impact of bad RTO seeding from SYN/ACKs.  Also, when
      both timestamps and local RTT measurements are available prefer
      the later because there are broken middleware devices which
      scramble the timestamp.

      From Yuchung Cheng.

   3) Add TCP_NOTSENT_LOWAT socket option to limit the amount of kernel
      memory consumed to queue up unsend user data.  From Eric Dumazet.

   4) Add a "physical port ID" abstraction for network devices, from
      Jiri Pirko.

   5) Add a "suppress" operation to influence fib_rules lookups, from
      Stefan Tomanek.

   6) Add a networking development FAQ, from Paul Gortmaker.

   7) Extend the information provided by tcp_probe and add ipv6 support,
      from Daniel Borkmann.

   8) Use RCU locking more extensively in openvswitch data paths, from
      Pravin B Shelar.

   9) Add SCTP support to openvswitch, from Joe Stringer.

  10) Add EF10 chip support to SFC driver, from Ben Hutchings.

  11) Add new SYNPROXY netfilter target, from Patrick McHardy.

  12) Compute a rate approximation for sending in TCP sockets, and use
      this to more intelligently coalesce TSO frames.  Furthermore, add
      a new packet scheduler which takes advantage of this estimate when
      available.  From Eric Dumazet.

  13) Allow AF_PACKET fanouts with random selection, from Daniel
      Borkmann.

  14) Add ipv6 support to vxlan driver, from Cong Wang"

Resolved conflicts as per discussion.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1218 commits)
  openvswitch: Fix alignment of struct sw_flow_key.
  netfilter: Fix build errors with xt_socket.c
  tcp: Add missing braces to do_tcp_setsockopt
  caif: Add missing braces to multiline if in cfctrl_linkup_request
  bnx2x: Add missing braces in bnx2x:bnx2x_link_initialize
  vxlan: Fix kernel panic on device delete.
  net: mvneta: implement ->ndo_do_ioctl() to support PHY ioctls
  net: mvneta: properly disable HW PHY polling and ensure adjust_link() works
  icplus: Use netif_running to determine device state
  ethernet/arc/arc_emac: Fix huge delays in large file copies
  tuntap: orphan frags before trying to set tx timestamp
  tuntap: purge socket error queue on detach
  qlcnic: use standard NAPI weights
  ipv6:introduce function to find route for redirect
  bnx2x: VF RSS support - VF side
  bnx2x: VF RSS support - PF side
  vxlan: Notify drivers for listening UDP port changes
  net: usbnet: update addr_assign_type if appropriate
  driver/net: enic: update enic maintainers and driver
  driver/net: enic: Exposing symbols for Cisco's low latency driver
  ...

1 files changed, 71 insertions, 9 deletions

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index cd71190d2962..d6c0e64ec97f 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -88,6 +88,7 @@
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/times.h>
+#include <linux/pkt_sched.h>
 
 #include <net/net_namespace.h>
 #include <net/arp.h>
@@ -113,7 +114,8 @@
 
 #define IGMP_V1_Router_Present_Timeout		(400*HZ)
 #define IGMP_V2_Router_Present_Timeout		(400*HZ)
-#define IGMP_Unsolicited_Report_Interval	(10*HZ)
+#define IGMP_V2_Unsolicited_Report_Interval	(10*HZ)
+#define IGMP_V3_Unsolicited_Report_Interval	(1*HZ)
 #define IGMP_Query_Response_Interval		(10*HZ)
 #define IGMP_Unsolicited_Report_Count		2
 
@@ -138,6 +140,29 @@
 	 ((in_dev)->mr_v2_seen && \
 	  time_before(jiffies, (in_dev)->mr_v2_seen)))
 
+static int unsolicited_report_interval(struct in_device *in_dev)
+{
+	int interval_ms, interval_jiffies;
+
+	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
+		interval_ms = IN_DEV_CONF_GET(
+			in_dev,
+			IGMPV2_UNSOLICITED_REPORT_INTERVAL);
+	else /* v3 */
+		interval_ms = IN_DEV_CONF_GET(
+			in_dev,
+			IGMPV3_UNSOLICITED_REPORT_INTERVAL);
+
+	interval_jiffies = msecs_to_jiffies(interval_ms);
+
+	/* _timer functions can't handle a delay of 0 jiffies so ensure
+	 *  we always return a positive value.
+	 */
+	if (interval_jiffies <= 0)
+		interval_jiffies = 1;
+	return interval_jiffies;
+}
+
 static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im);
 static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr);
 static void igmpv3_clear_delrec(struct in_device *in_dev);
@@ -315,6 +340,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 		if (size < 256)
 			return NULL;
 	}
+	skb->priority = TC_PRIO_CONTROL;
 	igmp_skb_size(skb) = size;
 
 	rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0,
@@ -670,6 +696,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 		ip_rt_put(rt);
 		return -1;
 	}
+	skb->priority = TC_PRIO_CONTROL;
 
 	skb_dst_set(skb, &rt->dst);
 
@@ -719,7 +746,8 @@ static void igmp_ifc_timer_expire(unsigned long data)
 	igmpv3_send_cr(in_dev);
 	if (in_dev->mr_ifc_count) {
 		in_dev->mr_ifc_count--;
-		igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval);
+		igmp_ifc_start_timer(in_dev,
+				     unsolicited_report_interval(in_dev));
 	}
 	__in_dev_put(in_dev);
 }
@@ -744,7 +772,7 @@ static void igmp_timer_expire(unsigned long data)
 
 	if (im->unsolicit_count) {
 		im->unsolicit_count--;
-		igmp_start_timer(im, IGMP_Unsolicited_Report_Interval);
+		igmp_start_timer(im, unsolicited_report_interval(in_dev));
 	}
 	im->reporter = 1;
 	spin_unlock(&im->lock);
@@ -1323,16 +1351,17 @@ out:
 EXPORT_SYMBOL(ip_mc_inc_group);
 
 /*
- *	Resend IGMP JOIN report; used for bonding.
- *	Called with rcu_read_lock()
+ *	Resend IGMP JOIN report; used by netdev notifier.
  */
-void ip_mc_rejoin_groups(struct in_device *in_dev)
+static void ip_mc_rejoin_groups(struct in_device *in_dev)
 {
 #ifdef CONFIG_IP_MULTICAST
 	struct ip_mc_list *im;
 	int type;
 
-	for_each_pmc_rcu(in_dev, im) {
+	ASSERT_RTNL();
+
+	for_each_pmc_rtnl(in_dev, im) {
 		if (im->multiaddr == IGMP_ALL_HOSTS)
 			continue;
 
@@ -1349,7 +1378,6 @@ void ip_mc_rejoin_groups(struct in_device *in_dev)
 	}
 #endif
 }
-EXPORT_SYMBOL(ip_mc_rejoin_groups);
 
 /*
  *	A socket has left a multicast group on device dev
@@ -2735,8 +2763,42 @@ static struct pernet_operations igmp_net_ops = {
 	.exit = igmp_net_exit,
 };
 
+static int igmp_netdev_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct in_device *in_dev;
+
+	switch (event) {
+	case NETDEV_RESEND_IGMP:
+		in_dev = __in_dev_get_rtnl(dev);
+		if (in_dev)
+			ip_mc_rejoin_groups(in_dev);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block igmp_notifier = {
+	.notifier_call = igmp_netdev_event,
+};
+
 int __init igmp_mc_proc_init(void)
 {
-	return register_pernet_subsys(&igmp_net_ops);
+	int err;
+
+	err = register_pernet_subsys(&igmp_net_ops);
+	if (err)
+		return err;
+	err = register_netdevice_notifier(&igmp_notifier);
+	if (err)
+		goto reg_notif_fail;
+	return 0;
+
+reg_notif_fail:
+	unregister_pernet_subsys(&igmp_net_ops);
+	return err;
 }
 #endif