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

Pull networking fixes from David Miller:
 "Mostly these are fixes for fallout due to merge window changes, as
  well as cures for problems that have been with us for a much longer
  period of time"

 1) Johannes Berg noticed two major deficiencies in our genetlink
    registration.  Some genetlink protocols we passing in constant
    counts for their ops array rather than something like
    ARRAY_SIZE(ops) or similar.  Also, some genetlink protocols were
    using fixed IDs for their multicast groups.

    We have to retain these fixed IDs to keep existing userland tools
    working, but reserve them so that other multicast groups used by
    other protocols can not possibly conflict.

    In dealing with these two problems, we actually now use less state
    management for genetlink operations and multicast groups.

 2) When configuring interface hardware timestamping, fix several
    drivers that simply do not validate that the hwtstamp_config value
    is one the driver actually supports.  From Ben Hutchings.

 3) Invalid memory references in mwifiex driver, from Amitkumar Karwar.

 4) In dev_forward_skb(), set the skb->protocol in the right order
    relative to skb_scrub_packet().  From Alexei Starovoitov.

 5) Bridge erroneously fails to use the proper wrapper functions to make
    calls to netdev_ops->ndo_vlan_rx_{add,kill}_vid.  Fix from Toshiaki
    Makita.

 6) When detaching a bridge port, make sure to flush all VLAN IDs to
    prevent them from leaking, also from Toshiaki Makita.

 7) Put in a compromise for TCP Small Queues so that deep queued devices
    that delay TX reclaim non-trivially don't have such a performance
    decrease.  One particularly problematic area is 802.11 AMPDU in
    wireless.  From Eric Dumazet.

 8) Fix crashes in tcp_fastopen_cache_get(), we can see NULL socket dsts
    here.  Fix from Eric Dumzaet, reported by Dave Jones.

 9) Fix use after free in ipv6 SIT driver, from Willem de Bruijn.

10) When computing mergeable buffer sizes, virtio-net fails to take the
    virtio-net header into account.  From Michael Dalton.

11) Fix seqlock deadlock in ip4_datagram_connect() wrt.  statistic
    bumping, this one has been with us for a while.  From Eric Dumazet.

12) Fix NULL deref in the new TIPC fragmentation handling, from Erik
    Hugne.

13) 6lowpan bit used for traffic classification was wrong, from Jukka
    Rissanen.

14) macvlan has the same issue as normal vlans did wrt.  propagating LRO
    disabling down to the real device, fix it the same way.  From Michal
    Kubecek.

15) CPSW driver needs to soft reset all slaves during suspend, from
    Daniel Mack.

16) Fix small frame pacing in FQ packet scheduler, from Eric Dumazet.

17) The xen-netfront RX buffer refill timer isn't properly scheduled on
    partial RX allocation success, from Ma JieYue.

18) When ipv6 ping protocol support was added, the AF_INET6 protocol
    initialization cleanup path on failure was borked a little.  Fix
    from Vlad Yasevich.

19) If a socket disconnects during a read/recvmsg/recvfrom/etc that
    blocks we can do the wrong thing with the msg_name we write back to
    userspace.  From Hannes Frederic Sowa.  There is another fix in the
    works from Hannes which will prevent future problems of this nature.

20) Fix route leak in VTI tunnel transmit, from Fan Du.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  genetlink: make multicast groups const, prevent abuse
  genetlink: pass family to functions using groups
  genetlink: add and use genl_set_err()
  genetlink: remove family pointer from genl_multicast_group
  genetlink: remove genl_unregister_mc_group()
  hsr: don't call genl_unregister_mc_group()
  quota/genetlink: use proper genetlink multicast APIs
  drop_monitor/genetlink: use proper genetlink multicast APIs
  genetlink: only pass array to genl_register_family_with_ops()
  tcp: don't update snd_nxt, when a socket is switched from repair mode
  atm: idt77252: fix dev refcnt leak
  xfrm: Release dst if this dst is improper for vti tunnel
  netlink: fix documentation typo in netlink_set_err()
  be2net: Delete secondary unicast MAC addresses during be_close
  be2net: Fix unconditional enabling of Rx interface options
  net, virtio_net: replace the magic value
  ping: prevent NULL pointer dereference on write to msg_name
  bnx2x: Prevent "timeout waiting for state X"
  bnx2x: prevent CFC attention
  bnx2x: Prevent panic during DMAE timeout
  ...

7 files changed, 41 insertions, 48 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5658d9d..12c97d8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1996,23 +1996,6 @@ static void addrconf_add_mroute(struct net_device *dev)
 	ip6_route_add(&cfg);
 }
 
-#if IS_ENABLED(CONFIG_IPV6_SIT)
-static void sit_route_add(struct net_device *dev)
-{
-	struct fib6_config cfg = {
-		.fc_table = RT6_TABLE_MAIN,
-		.fc_metric = IP6_RT_PRIO_ADDRCONF,
-		.fc_ifindex = dev->ifindex,
-		.fc_dst_len = 96,
-		.fc_flags = RTF_UP | RTF_NONEXTHOP,
-		.fc_nlinfo.nl_net = dev_net(dev),
-	};
-
-	/* prefix length - 96 bits "::d.d.d.d" */
-	ip6_route_add(&cfg);
-}
-#endif
-
 static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
 {
 	struct inet6_dev *idev;
@@ -2542,7 +2525,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
 	struct in6_addr addr;
 	struct net_device *dev;
 	struct net *net = dev_net(idev->dev);
-	int scope;
+	int scope, plen;
+	u32 pflags = 0;
 
 	ASSERT_RTNL();
 
@@ -2552,12 +2536,16 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
 	if (idev->dev->flags&IFF_POINTOPOINT) {
 		addr.s6_addr32[0] = htonl(0xfe800000);
 		scope = IFA_LINK;
+		plen = 64;
 	} else {
 		scope = IPV6_ADDR_COMPATv4;
+		plen = 96;
+		pflags |= RTF_NONEXTHOP;
 	}
 
 	if (addr.s6_addr32[3]) {
-		add_addr(idev, &addr, 128, scope);
+		add_addr(idev, &addr, plen, scope);
+		addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags);
 		return;
 	}
 
@@ -2569,7 +2557,6 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
 			int flag = scope;
 
 			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
-				int plen;
 
 				addr.s6_addr32[3] = ifa->ifa_local;
 
@@ -2580,12 +2567,10 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
 						continue;
 					flag |= IFA_HOST;
 				}
-				if (idev->dev->flags&IFF_POINTOPOINT)
-					plen = 64;
-				else
-					plen = 96;
 
 				add_addr(idev, &addr, plen, flag);
+				addrconf_prefix_route(&addr, plen, idev->dev, 0,
+						      pflags);
 			}
 		}
 	}
@@ -2711,7 +2696,6 @@ static void addrconf_sit_config(struct net_device *dev)
 		struct in6_addr addr;
 
 		ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
-		addrconf_prefix_route(&addr, 64, dev, 0, 0);
 		if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
 			addrconf_add_linklocal(idev, &addr);
 		return;
@@ -2721,8 +2705,6 @@ static void addrconf_sit_config(struct net_device *dev)
 
 	if (dev->flags&IFF_POINTOPOINT)
 		addrconf_add_mroute(dev);
-	else
-		sit_route_add(dev);
 }
 #endif
 
@@ -2740,8 +2722,6 @@ static void addrconf_gre_config(struct net_device *dev)
 	}
 
 	ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
-	addrconf_prefix_route(&addr, 64, dev, 0, 0);
-
 	if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
 		addrconf_add_linklocal(idev, &addr);
 }
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ff75313..4fbdb70 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -972,10 +972,10 @@ out:
 
 #ifdef CONFIG_SYSCTL
 sysctl_fail:
-	ipv6_packet_cleanup();
+	pingv6_exit();
 #endif
 pingv6_fail:
-	pingv6_exit();
+	ipv6_packet_cleanup();
 ipv6_packet_fail:
 	tcpv6_exit();
 tcpv6_fail:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index df1fa58..d606232 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1642,6 +1642,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	return ip6_tnl_update(t, &p);
 }
 
+static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+
+	if (dev != ip6n->fb_tnl_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static size_t ip6_tnl_get_size(const struct net_device *dev)
 {
 	return
@@ -1706,6 +1715,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
 	.validate	= ip6_tnl_validate,
 	.newlink	= ip6_tnl_newlink,
 	.changelink	= ip6_tnl_changelink,
+	.dellink	= ip6_tnl_dellink,
 	.get_size	= ip6_tnl_get_size,
 	.fill_info	= ip6_tnl_fill_info,
 };
@@ -1722,9 +1732,9 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
-static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
+static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
 {
-	struct net *net = dev_net(ip6n->fb_tnl_dev);
+	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct net_device *dev, *aux;
 	int h;
 	struct ip6_tnl *t;
@@ -1792,10 +1802,8 @@ err_alloc_dev:
 
 static void __net_exit ip6_tnl_exit_net(struct net *net)
 {
-	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-
 	rtnl_lock();
-	ip6_tnl_destroy_tunnels(ip6n);
+	ip6_tnl_destroy_tunnels(net);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f8a55ff..3512177 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1726,8 +1726,8 @@ int __init ndisc_init(void)
 				    &ndisc_ifinfo_sysctl_change);
 	if (err)
 		goto out_unregister_pernet;
-#endif
 out:
+#endif
 	return err;
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 3c00842..e24ff1d 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -465,9 +465,6 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (addr_len)
-		*addr_len=sizeof(*sin6);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 
@@ -506,6 +503,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		sin6->sin6_flowinfo = 0;
 		sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
 							  IP6CB(skb)->iif);
+		*addr_len = sizeof(*sin6);
 	}
 
 	sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index bfc6fce..1b4a4a95 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1619,6 +1619,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 #endif
 };
 
+static void ipip6_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct sit_net *sitn = net_generic(net, sit_net_id);
+
+	if (dev != sitn->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.kind		= "sit",
 	.maxtype	= IFLA_IPTUN_MAX,
@@ -1630,6 +1639,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.changelink	= ipip6_changelink,
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
+	.dellink	= ipip6_dellink,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1644,9 +1654,10 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
 	.priority	=	2,
 };
 
-static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
+static void __net_exit sit_destroy_tunnels(struct net *net,
+					   struct list_head *head)
 {
-	struct net *net = dev_net(sitn->fb_tunnel_dev);
+	struct sit_net *sitn = net_generic(net, sit_net_id);
 	struct net_device *dev, *aux;
 	int prio;
 
@@ -1721,11 +1732,10 @@ err_alloc_dev:
 
 static void __net_exit sit_exit_net(struct net *net)
 {
-	struct sit_net *sitn = net_generic(net, sit_net_id);
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	sit_destroy_tunnels(sitn, &list);
+	sit_destroy_tunnels(net, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f3893e8..81eb8cf 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -392,9 +392,6 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	int is_udp4;
 	bool slow;
 
-	if (addr_len)
-		*addr_len = sizeof(struct sockaddr_in6);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 
@@ -480,7 +477,7 @@ try_again:
 				ipv6_iface_scope_id(&sin6->sin6_addr,
 						    IP6CB(skb)->iif);
 		}
-
+		*addr_len = sizeof(*sin6);
 	}
 	if (is_udp4) {
 		if (inet->cmsg_flags)