Merge branch 'x-netns'

Nicolas Dichtel says:

====================
This series is a follow up of the previous series whcih adds this
functionality for sit tunnels.

The goal is to add x-netns support for the module ipip and ip6_tunnel,
ie. the encapsulation addresses and the network device are not owned
by the same namespace.

Note that the two first patches are cleanups.

Example to configure an ipip tunnel:

modprobe ipip
ip netns add netns1
ip link add ipip1 type ipip remote 10.16.0.121 local 10.16.0.249
ip l s ipip1 netns netns1
ip netns exec netns1 ip l s lo up
ip netns exec netns1 ip l s ipip1 up
ip netns exec netns1 ip a a dev ipip1 192.168.2.123 remote 192.168.2.121

or an ip6_tunnel:

modprobe ip6_tunnel
ip netns add netns1
ip link add ip6tnl1 type ip6tnl remote 2001:660:3008:c1c3::121 local 2001:660:3008:c1c3::123
ip l s ip6tnl1 netns netns1
ip netns exec netns1 ip l s lo up
ip netns exec netns1 ip l s ip6tnl1 up
ip netns exec netns1 ip a a dev ip6tnl1 192.168.1.123 remote 192.168.1.121
ip netns exec netns1 ip -6 a a dev ip6tnl1 2001:1235::123 remote 2001:1235::121

v2: remove the patch 1/3 of the v1 series (already included)
    use net_eq()
    add patch 1/4 and 2/4
====================-

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 79 insertions, 40 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 58eb802584b9..1ed2b66a10a6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1691,13 +1691,13 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_scrub_packet(skb);
 	skb->protocol = eth_type_trans(skb, dev);
 
 	/* eth_type_trans() can set pkt_type.
-	 * clear pkt_type _after_ calling eth_type_trans()
+	 * call skb_scrub_packet() after it to clear pkt_type _after_ calling
+	 * eth_type_trans().
 	 */
-	skb->pkt_type = PACKET_HOST;
+	skb_scrub_packet(skb);
 
 	return netif_rx(skb);
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 1f6eab66f7ce..bc3a76521deb 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -534,7 +534,7 @@ static int __net_init ipgre_init_net(struct net *net)
 static void __net_exit ipgre_exit_net(struct net *net)
 {
 	struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
-	ip_tunnel_delete_net(itn);
+	ip_tunnel_delete_net(itn, &ipgre_link_ops);
 }
 
 static struct pernet_operations ipgre_net_ops = {
@@ -767,7 +767,7 @@ static int __net_init ipgre_tap_init_net(struct net *net)
 static void __net_exit ipgre_tap_exit_net(struct net *net)
 {
 	struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
-	ip_tunnel_delete_net(itn);
+	ip_tunnel_delete_net(itn, &ipgre_tap_ops);
 }
 
 static struct pernet_operations ipgre_tap_net_ops = {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 9fdf8a6d95f3..a4d9126c7b51 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -350,7 +350,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		struct flowi4 fl4;
 		struct rtable *rt;
 
-		rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+		rt = ip_route_output_tunnel(tunnel->net, &fl4,
 					    tunnel->parms.iph.protocol,
 					    iph->daddr, iph->saddr,
 					    tunnel->parms.o_key,
@@ -365,7 +365,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	}
 
 	if (!tdev && tunnel->parms.link)
-		tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
 
 	if (tdev) {
 		hlen = tdev->hard_header_len + tdev->needed_headroom;
@@ -454,15 +454,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 	tstats->rx_bytes += skb->len;
 	u64_stats_update_end(&tstats->syncp);
 
-	if (tunnel->net != dev_net(tunnel->dev))
-		skb_scrub_packet(skb);
-
 	if (tunnel->dev->type == ARPHRD_ETHER) {
 		skb->protocol = eth_type_trans(skb, tunnel->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 	} else {
 		skb->dev = tunnel->dev;
 	}
+
+	if (!net_eq(tunnel->net, dev_net(tunnel->dev)))
+		skb_scrub_packet(skb);
+
 	gro_cells_receive(&tunnel->gro_cells, skb);
 	return 0;
 
@@ -613,7 +614,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tunnel->net != dev_net(dev))
+	if (!net_eq(tunnel->net, dev_net(dev)))
 		skb_scrub_packet(skb);
 
 	if (tunnel->err_count > 0) {
@@ -653,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	err = iptunnel_xmit(dev_net(dev), rt, skb,
+	err = iptunnel_xmit(tunnel->net, rt, skb,
 			    fl4.saddr, fl4.daddr, protocol,
 			    ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df);
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
@@ -820,11 +821,10 @@ static void ip_tunnel_dev_free(struct net_device *dev)
 
 void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
 {
-	struct net *net = dev_net(dev);
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct ip_tunnel_net *itn;
 
-	itn = net_generic(net, tunnel->ip_tnl_net_id);
+	itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);
 
 	if (itn->fb_tunnel_dev != dev) {
 		ip_tunnel_del(netdev_priv(dev));
@@ -854,6 +854,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 
 	rtnl_lock();
 	itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
+	/* FB netdevice is special: we have one, and only one per netns.
+	 * Allowing to move it to another netns is clearly unsafe.
+	 */
+	itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 	rtnl_unlock();
 
 	if (IS_ERR(itn->fb_tunnel_dev))
@@ -863,28 +867,39 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
-static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
+static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
+			      struct rtnl_link_ops *ops)
 {
+	struct net *net = dev_net(itn->fb_tunnel_dev);
+	struct net_device *dev, *aux;
 	int h;
 
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == ops)
+			unregister_netdevice_queue(dev, head);
+
 	for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
 		struct ip_tunnel *t;
 		struct hlist_node *n;
 		struct hlist_head *thead = &itn->tunnels[h];
 
 		hlist_for_each_entry_safe(t, n, thead, hash_node)
-			unregister_netdevice_queue(t->dev, head);
+			/* If dev is in the same netns, it has already
+			 * been added to the list by the previous loop.
+			 */
+			if (!net_eq(dev_net(t->dev), net))
+				unregister_netdevice_queue(t->dev, head);
 	}
 	if (itn->fb_tunnel_dev)
 		unregister_netdevice_queue(itn->fb_tunnel_dev, head);
 }
 
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn)
+void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
 {
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	ip_tunnel_destroy(itn, &list);
+	ip_tunnel_destroy(itn, &list, ops);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
@@ -928,23 +943,21 @@ EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 			 struct ip_tunnel_parm *p)
 {
-	struct ip_tunnel *t, *nt;
-	struct net *net = dev_net(dev);
+	struct ip_tunnel *t;
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct net *net = tunnel->net;
 	struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
 
 	if (dev == itn->fb_tunnel_dev)
 		return -EINVAL;
 
-	nt = netdev_priv(dev);
-
 	t = ip_tunnel_find(itn, p, dev->type);
 
 	if (t) {
 		if (t->dev != dev)
 			return -EEXIST;
 	} else {
-		t = nt;
+		t = tunnel;
 
 		if (dev->type != ARPHRD_ETHER) {
 			unsigned int nflags = 0;
@@ -983,6 +996,7 @@ int ip_tunnel_init(struct net_device *dev)
 	}
 
 	tunnel->dev = dev;
+	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 	iph->version		= 4;
 	iph->ihl		= 5;
@@ -993,8 +1007,8 @@ EXPORT_SYMBOL_GPL(ip_tunnel_init);
 
 void ip_tunnel_uninit(struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct net *net = tunnel->net;
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 79b263da4168..e805e7b3030e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -318,7 +318,7 @@ static int __net_init vti_init_net(struct net *net)
 static void __net_exit vti_exit_net(struct net *net)
 {
 	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
-	ip_tunnel_delete_net(itn);
+	ip_tunnel_delete_net(itn, &vti_link_ops);
 }
 
 static struct pernet_operations vti_net_ops = {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 51fc2a1dcdd3..87bd2952c733 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -286,7 +286,6 @@ static void ipip_tunnel_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
 	dev->features		|= NETIF_F_LLTX;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 
@@ -437,7 +436,7 @@ static int __net_init ipip_init_net(struct net *net)
 static void __net_exit ipip_exit_net(struct net *net)
 {
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
-	ip_tunnel_delete_net(itn);
+	ip_tunnel_delete_net(itn, &ipip_link_ops);
 }
 
 static struct pernet_operations ipip_net_ops = {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ecd60733e5e2..f2d0a42f8057 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -335,6 +335,7 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 	dev->rtnl_link_ops = &ip6gre_link_ops;
 
 	nt->dev = dev;
+	nt->net = dev_net(dev);
 	ip6gre_tnl_link_config(nt, 1);
 
 	if (register_netdevice(dev) < 0)
@@ -1255,6 +1256,7 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 	tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
+	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
@@ -1275,6 +1277,7 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev)
 	struct ip6_tnl *tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
+	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	tunnel->hlen		= sizeof(struct ipv6hdr) + 4;
@@ -1450,6 +1453,7 @@ static int ip6gre_tap_init(struct net_device *dev)
 	tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
+	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	ip6gre_tnl_link_config(tunnel, 1);
@@ -1501,6 +1505,7 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 		eth_hw_addr_random(dev);
 
 	nt->dev = dev;
+	nt->net = dev_net(dev);
 	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
 	/* Can use a lockless transmit, unless we generate output sequences */
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e55866cead7..cc3bb201b8b0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -315,6 +315,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 
 	t = netdev_priv(dev);
 	t->parms = *p;
+	t->net = dev_net(dev);
 	err = ip6_tnl_create2(dev);
 	if (err < 0)
 		goto failed_free;
@@ -374,7 +375,7 @@ static void
 ip6_tnl_dev_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
@@ -741,7 +742,7 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 
 	if ((p->flags & IP6_TNL_F_CAP_RCV) ||
 	    ((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
@@ -827,6 +828,9 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
 
+		if (!net_eq(t->net, dev_net(t->dev)))
+			skb_scrub_packet(skb);
+
 		netif_rx(skb);
 
 		rcu_read_unlock();
@@ -895,7 +899,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		struct net_device *ldev = NULL;
@@ -945,8 +949,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 			 int encap_limit,
 			 __u32 *pmtu)
 {
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct ipv6_tel_txoption opt;
@@ -996,6 +1000,9 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		goto tx_err_dst_release;
 	}
 
+	if (!net_eq(t->net, dev_net(dev)))
+		skb_scrub_packet(skb);
+
 	/*
 	 * Okay, now see if we can stuff it in the buffer as-is.
 	 */
@@ -1202,7 +1209,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
 
-		struct rt6_info *rt = rt6_lookup(dev_net(dev),
+		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
@@ -1251,7 +1258,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 
 static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 {
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	int err;
 
@@ -1463,7 +1470,6 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 		dev->mtu-=8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 }
 
@@ -1479,6 +1485,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 
 	t->dev = dev;
+	t->net = dev_net(dev);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
@@ -1596,9 +1603,9 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 			      struct nlattr *data[])
 {
-	struct ip6_tnl *t;
+	struct ip6_tnl *t = netdev_priv(dev);
 	struct __ip6_tnl_parm p;
-	struct net *net = dev_net(dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
@@ -1699,14 +1706,24 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 
 static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
 {
+	struct net *net = dev_net(ip6n->fb_tnl_dev);
+	struct net_device *dev, *aux;
 	int h;
 	struct ip6_tnl *t;
 	LIST_HEAD(list);
 
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &ip6_link_ops)
+			unregister_netdevice_queue(dev, &list);
+
 	for (h = 0; h < HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
 		while (t != NULL) {
-			unregister_netdevice_queue(t->dev, &list);
+			/* If dev is in the same netns, it has already
+			 * been added to the list by the previous loop.
+			 */
+			if (!net_eq(dev_net(t->dev), net))
+				unregister_netdevice_queue(t->dev, &list);
 			t = rtnl_dereference(t->next);
 		}
 	}
@@ -1732,6 +1749,10 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	if (!ip6n->fb_tnl_dev)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
+	/* FB netdevice is special: we have one, and only one per netns.
+	 * Allowing to move it to another netns is clearly unsafe.
+	 */
+	ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
 
 	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a3437a4cd07e..f18f842ac893 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -621,7 +621,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
 
-		if (tunnel->net != dev_net(tunnel->dev))
+		if (!net_eq(tunnel->net, dev_net(tunnel->dev)))
 			skb_scrub_packet(skb);
 		netif_rx(skb);
 
@@ -860,7 +860,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			tunnel->err_count = 0;
 	}
 
-	if (tunnel->net != dev_net(dev))
+	if (!net_eq(tunnel->net, dev_net(dev)))
 		skb_scrub_packet(skb);
 
 	/*
@@ -1589,7 +1589,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
-				if (dev_net(t->dev) != net)
+				if (!net_eq(dev_net(t->dev), net))
 					unregister_netdevice_queue(t->dev,
 								   head);
 				t = rtnl_dereference(t->next);