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, 56 insertions, 40 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 854e4018d205..d1ddbc6ddac5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -222,7 +222,7 @@ static const u32 ip6_template_metrics[RTAX_MAX] = {
 	[RTAX_HOPLIMIT - 1] = 255,
 };
 
-static struct rt6_info ip6_null_entry_template = {
+static const struct rt6_info ip6_null_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
 		.__use		= 1,
@@ -242,7 +242,7 @@ static struct rt6_info ip6_null_entry_template = {
 static int ip6_pkt_prohibit(struct sk_buff *skb);
 static int ip6_pkt_prohibit_out(struct sk_buff *skb);
 
-static struct rt6_info ip6_prohibit_entry_template = {
+static const struct rt6_info ip6_prohibit_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
 		.__use		= 1,
@@ -257,7 +257,7 @@ static struct rt6_info ip6_prohibit_entry_template = {
 	.rt6i_ref	= ATOMIC_INIT(1),
 };
 
-static struct rt6_info ip6_blk_hole_entry_template = {
+static const struct rt6_info ip6_blk_hole_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
 		.__use		= 1,
@@ -370,15 +370,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static bool rt6_check_expired(const struct rt6_info *rt)
 {
-	struct rt6_info *ort = NULL;
-
 	if (rt->rt6i_flags & RTF_EXPIRES) {
 		if (time_after(jiffies, rt->dst.expires))
 			return true;
 	} else if (rt->dst.from) {
-		ort = (struct rt6_info *) rt->dst.from;
-		return (ort->rt6i_flags & RTF_EXPIRES) &&
-			time_after(jiffies, ort->dst.expires);
+		return rt6_check_expired((struct rt6_info *) rt->dst.from);
 	}
 	return false;
 }
@@ -452,10 +448,9 @@ static void rt6_probe(struct rt6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	rcu_read_lock();
 	neigh = rt ? rt->n : NULL;
 	if (!neigh || (neigh->nud_state & NUD_VALID))
-		goto out;
+		return;
 	read_lock_bh(&neigh->lock);
 	if (!(neigh->nud_state & NUD_VALID) &&
 	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
@@ -471,8 +466,6 @@ static void rt6_probe(struct rt6_info *rt)
 	} else {
 		read_unlock_bh(&neigh->lock);
 	}
-out:
-	rcu_read_unlock();
 }
 #else
 static inline void rt6_probe(struct rt6_info *rt)
@@ -499,7 +492,6 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
 	struct neighbour *neigh;
 	int m;
 
-	rcu_read_lock();
 	neigh = rt->n;
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
@@ -517,7 +509,6 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
 		read_unlock_bh(&neigh->lock);
 	} else
 		m = 0;
-	rcu_read_unlock();
 	return m;
 }
 
@@ -966,7 +957,7 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
 {
 	int flags = 0;
 
-	fl6->flowi6_iif = net->loopback_dev->ifindex;
+	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
 		flags |= RT6_LOOKUP_F_IFACE;
@@ -1469,8 +1460,21 @@ int ip6_route_add(struct fib6_config *cfg)
 		}
 		rt->dst.output = ip6_pkt_discard_out;
 		rt->dst.input = ip6_pkt_discard;
-		rt->dst.error = -ENETUNREACH;
 		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
+		switch (cfg->fc_type) {
+		case RTN_BLACKHOLE:
+			rt->dst.error = -EINVAL;
+			break;
+		case RTN_PROHIBIT:
+			rt->dst.error = -EACCES;
+			break;
+		case RTN_THROW:
+			rt->dst.error = -EAGAIN;
+			break;
+		default:
+			rt->dst.error = -ENETUNREACH;
+			break;
+		}
 		goto install_route;
 	}
 
@@ -1835,7 +1839,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 	if (!table)
 		return NULL;
 
-	write_lock_bh(&table->tb6_lock);
+	read_lock_bh(&table->tb6_lock);
 	fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
 	if (!fn)
 		goto out;
@@ -1851,7 +1855,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 		break;
 	}
 out:
-	write_unlock_bh(&table->tb6_lock);
+	read_unlock_bh(&table->tb6_lock);
 	return rt;
 }
 
@@ -1867,7 +1871,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_dst_len	= prefixlen,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
 				  RTF_UP | RTF_PREF(pref),
-		.fc_nlinfo.pid = 0,
+		.fc_nlinfo.portid = 0,
 		.fc_nlinfo.nlh = NULL,
 		.fc_nlinfo.nl_net = net,
 	};
@@ -1894,7 +1898,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	if (!table)
 		return NULL;
 
-	write_lock_bh(&table->tb6_lock);
+	read_lock_bh(&table->tb6_lock);
 	for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
 		if (dev == rt->dst.dev &&
 		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
@@ -1903,7 +1907,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	}
 	if (rt)
 		dst_hold(&rt->dst);
-	write_unlock_bh(&table->tb6_lock);
+	read_unlock_bh(&table->tb6_lock);
 	return rt;
 }
 
@@ -1917,7 +1921,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 		.fc_ifindex	= dev->ifindex,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
 				  RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
-		.fc_nlinfo.pid = 0,
+		.fc_nlinfo.portid = 0,
 		.fc_nlinfo.nlh = NULL,
 		.fc_nlinfo.nl_net = dev_net(dev),
 	};
@@ -2266,14 +2270,18 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	cfg->fc_src_len = rtm->rtm_src_len;
 	cfg->fc_flags = RTF_UP;
 	cfg->fc_protocol = rtm->rtm_protocol;
+	cfg->fc_type = rtm->rtm_type;
 
-	if (rtm->rtm_type == RTN_UNREACHABLE)
+	if (rtm->rtm_type == RTN_UNREACHABLE ||
+	    rtm->rtm_type == RTN_BLACKHOLE ||
+	    rtm->rtm_type == RTN_PROHIBIT ||
+	    rtm->rtm_type == RTN_THROW)
 		cfg->fc_flags |= RTF_REJECT;
 
 	if (rtm->rtm_type == RTN_LOCAL)
 		cfg->fc_flags |= RTF_LOCAL;
 
-	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
+	cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
 	cfg->fc_nlinfo.nlh = nlh;
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
 
@@ -2364,7 +2372,7 @@ static inline size_t rt6_nlmsg_size(void)
 static int rt6_fill_node(struct net *net,
 			 struct sk_buff *skb, struct rt6_info *rt,
 			 struct in6_addr *dst, struct in6_addr *src,
-			 int iif, int type, u32 pid, u32 seq,
+			 int iif, int type, u32 portid, u32 seq,
 			 int prefix, int nowait, unsigned int flags)
 {
 	struct rtmsg *rtm;
@@ -2380,7 +2388,7 @@ static int rt6_fill_node(struct net *net,
 		}
 	}
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -2396,8 +2404,22 @@ static int rt6_fill_node(struct net *net,
 	rtm->rtm_table = table;
 	if (nla_put_u32(skb, RTA_TABLE, table))
 		goto nla_put_failure;
-	if (rt->rt6i_flags & RTF_REJECT)
-		rtm->rtm_type = RTN_UNREACHABLE;
+	if (rt->rt6i_flags & RTF_REJECT) {
+		switch (rt->dst.error) {
+		case -EINVAL:
+			rtm->rtm_type = RTN_BLACKHOLE;
+			break;
+		case -EACCES:
+			rtm->rtm_type = RTN_PROHIBIT;
+			break;
+		case -EAGAIN:
+			rtm->rtm_type = RTN_THROW;
+			break;
+		default:
+			rtm->rtm_type = RTN_UNREACHABLE;
+			break;
+		}
+	}
 	else if (rt->rt6i_flags & RTF_LOCAL)
 		rtm->rtm_type = RTN_LOCAL;
 	else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
@@ -2470,15 +2492,11 @@ static int rt6_fill_node(struct net *net,
 	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
 		goto nla_put_failure;
 
-	rcu_read_lock();
 	n = rt->n;
 	if (n) {
-		if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) {
-			rcu_read_unlock();
+		if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0)
 			goto nla_put_failure;
-		}
 	}
-	rcu_read_unlock();
 
 	if (rt->dst.dev &&
 	    nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
@@ -2511,7 +2529,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
 
 	return rt6_fill_node(arg->net,
 		     arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
-		     NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq,
+		     NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
 		     prefix, 0, NLM_F_MULTI);
 }
 
@@ -2591,14 +2609,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	skb_dst_set(skb, &rt->dst);
 
 	err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
-			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
+			    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
 			    nlh->nlmsg_seq, 0, 0, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
 	}
 
-	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
+	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
 	return err;
 }
@@ -2618,14 +2636,14 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
 		goto errout;
 
 	err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
-				event, info->pid, seq, 0, 0, 0);
+				event, info->portid, seq, 0, 0, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
+	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
 		    info->nlh, gfp_any());
 	return;
 errout:
@@ -2680,14 +2698,12 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 #else
 	seq_puts(m, "00000000000000000000000000000000 00 ");
 #endif
-	rcu_read_lock();
 	n = rt->n;
 	if (n) {
 		seq_printf(m, "%pi6", n->primary_key);
 	} else {
 		seq_puts(m, "00000000000000000000000000000000");
 	}
-	rcu_read_unlock();
 	seq_printf(m, " %08x %08x %08x %08x %8s\n",
 		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
 		   rt->dst.__use, rt->rt6i_flags,