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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

1 files changed, 38 insertions, 45 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6bc85f7c31e3..480e68422efb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -127,8 +127,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
 #endif
 
 #ifdef CONFIG_IPV6_PRIVACY
-static int __ipv6_regen_rndid(struct inet6_dev *idev);
-static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
+static void __ipv6_regen_rndid(struct inet6_dev *idev);
+static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
 static void ipv6_regen_rndid(unsigned long data);
 #endif
 
@@ -788,10 +788,16 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 		struct in6_addr prefix;
 		struct rt6_info *rt;
 		struct net *net = dev_net(ifp->idev->dev);
+		struct flowi6 fl6 = {};
+
 		ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len);
-		rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1);
+		fl6.flowi6_oif = ifp->idev->dev->ifindex;
+		fl6.daddr = prefix;
+		rt = (struct rt6_info *)ip6_route_lookup(net, &fl6,
+							 RT6_LOOKUP_F_IFACE);
 
-		if (rt && addrconf_is_prefix_route(rt)) {
+		if (rt != net->ipv6.ip6_null_entry &&
+		    addrconf_is_prefix_route(rt)) {
 			if (onlink == 0) {
 				ip6_del_rt(rt);
 				rt = NULL;
@@ -852,16 +858,7 @@ retry:
 	}
 	in6_ifa_hold(ifp);
 	memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
-	if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) {
-		spin_unlock_bh(&ifp->lock);
-		write_unlock(&idev->lock);
-		pr_warn("%s: regeneration of randomized interface id failed\n",
-			__func__);
-		in6_ifa_put(ifp);
-		in6_dev_put(idev);
-		ret = -1;
-		goto out;
-	}
+	__ipv6_try_regen_rndid(idev, tmpaddr);
 	memcpy(&addr.s6_addr[8], idev->rndid, 8);
 	age = (now - ifp->tstamp) / HZ;
 	tmp_valid_lft = min_t(__u32,
@@ -1079,8 +1076,10 @@ static int ipv6_get_saddr_eval(struct net *net,
 		break;
 	case IPV6_SADDR_RULE_PREFIX:
 		/* Rule 8: Use longest matching prefix */
-		score->matchlen = ret = ipv6_addr_diff(&score->ifa->addr,
-						       dst->addr);
+		ret = ipv6_addr_diff(&score->ifa->addr, dst->addr);
+		if (ret > score->ifa->prefix_len)
+			ret = score->ifa->prefix_len;
+		score->matchlen = ret;
 		break;
 	default:
 		ret = 0;
@@ -1093,7 +1092,7 @@ out:
 	return ret;
 }
 
-int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev,
+int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 		       const struct in6_addr *daddr, unsigned int prefs,
 		       struct in6_addr *saddr)
 {
@@ -1600,7 +1599,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
 
 #ifdef CONFIG_IPV6_PRIVACY
 /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
-static int __ipv6_regen_rndid(struct inet6_dev *idev)
+static void __ipv6_regen_rndid(struct inet6_dev *idev)
 {
 regen:
 	get_random_bytes(idev->rndid, sizeof(idev->rndid));
@@ -1627,8 +1626,6 @@ regen:
 		if ((idev->rndid[2]|idev->rndid[3]|idev->rndid[4]|idev->rndid[5]|idev->rndid[6]|idev->rndid[7]) == 0x00)
 			goto regen;
 	}
-
-	return 0;
 }
 
 static void ipv6_regen_rndid(unsigned long data)
@@ -1642,8 +1639,7 @@ static void ipv6_regen_rndid(unsigned long data)
 	if (idev->dead)
 		goto out;
 
-	if (__ipv6_regen_rndid(idev) < 0)
-		goto out;
+	__ipv6_regen_rndid(idev);
 
 	expires = jiffies +
 		idev->cnf.temp_prefered_lft * HZ -
@@ -1664,13 +1660,10 @@ out:
 	in6_dev_put(idev);
 }
 
-static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
+static void  __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
 {
-	int ret = 0;
-
 	if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
-		ret = __ipv6_regen_rndid(idev);
-	return ret;
+		__ipv6_regen_rndid(idev);
 }
 #endif
 
@@ -1721,7 +1714,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	if (table == NULL)
 		return NULL;
 
-	write_lock_bh(&table->tb6_lock);
+	read_lock_bh(&table->tb6_lock);
 	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
 	if (!fn)
 		goto out;
@@ -1736,7 +1729,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 		break;
 	}
 out:
-	write_unlock_bh(&table->tb6_lock);
+	read_unlock_bh(&table->tb6_lock);
 	return rt;
 }
 
@@ -3549,12 +3542,12 @@ static inline int inet6_ifaddr_msgsize(void)
 }
 
 static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
-			     u32 pid, u32 seq, int event, unsigned int flags)
+			     u32 portid, u32 seq, int event, unsigned int flags)
 {
 	struct nlmsghdr  *nlh;
 	u32 preferred, valid;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -3592,7 +3585,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 }
 
 static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
-				u32 pid, u32 seq, int event, u16 flags)
+				u32 portid, u32 seq, int event, u16 flags)
 {
 	struct nlmsghdr  *nlh;
 	u8 scope = RT_SCOPE_UNIVERSE;
@@ -3601,7 +3594,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 	if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE)
 		scope = RT_SCOPE_SITE;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -3617,7 +3610,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 }
 
 static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
-				u32 pid, u32 seq, int event, unsigned int flags)
+				u32 portid, u32 seq, int event, unsigned int flags)
 {
 	struct nlmsghdr  *nlh;
 	u8 scope = RT_SCOPE_UNIVERSE;
@@ -3626,7 +3619,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
 	if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE)
 		scope = RT_SCOPE_SITE;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -3667,7 +3660,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 			if (++ip_idx < s_ip_idx)
 				continue;
 			err = inet6_fill_ifaddr(skb, ifa,
-						NETLINK_CB(cb->skb).pid,
+						NETLINK_CB(cb->skb).portid,
 						cb->nlh->nlmsg_seq,
 						RTM_NEWADDR,
 						NLM_F_MULTI);
@@ -3683,7 +3676,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 			if (ip_idx < s_ip_idx)
 				continue;
 			err = inet6_fill_ifmcaddr(skb, ifmca,
-						  NETLINK_CB(cb->skb).pid,
+						  NETLINK_CB(cb->skb).portid,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETMULTICAST,
 						  NLM_F_MULTI);
@@ -3698,7 +3691,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 			if (ip_idx < s_ip_idx)
 				continue;
 			err = inet6_fill_ifacaddr(skb, ifaca,
-						  NETLINK_CB(cb->skb).pid,
+						  NETLINK_CB(cb->skb).portid,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETANYCAST,
 						  NLM_F_MULTI);
@@ -3820,7 +3813,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		goto errout_ifa;
 	}
 
-	err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid,
+	err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid,
 				nlh->nlmsg_seq, RTM_NEWADDR, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */
@@ -3828,7 +3821,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		kfree_skb(skb);
 		goto errout_ifa;
 	}
-	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
+	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout_ifa:
 	in6_ifa_put(ifa);
 errout:
@@ -4030,14 +4023,14 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
 }
 
 static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
-			     u32 pid, u32 seq, int event, unsigned int flags)
+			     u32 portid, u32 seq, int event, unsigned int flags)
 {
 	struct net_device *dev = idev->dev;
 	struct ifinfomsg *hdr;
 	struct nlmsghdr *nlh;
 	void *protoinfo;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -4095,7 +4088,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			if (!idev)
 				goto cont;
 			if (inet6_fill_ifinfo(skb, idev,
-					      NETLINK_CB(cb->skb).pid,
+					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWLINK, NLM_F_MULTI) <= 0)
 				goto out;
@@ -4143,14 +4136,14 @@ static inline size_t inet6_prefix_nlmsg_size(void)
 }
 
 static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
-			     struct prefix_info *pinfo, u32 pid, u32 seq,
+			     struct prefix_info *pinfo, u32 portid, u32 seq,
 			     int event, unsigned int flags)
 {
 	struct prefixmsg *pmsg;
 	struct nlmsghdr *nlh;
 	struct prefix_cacheinfo	ci;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*pmsg), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;