net: ip6_gre: fix tunnel metadata device sharing.

Currently ip6gre and ip6erspan share single metadata mode device,
using 'collect_md_tun'.  Thus, when doing:
  ip link add dev ip6gre11 type ip6gretap external
  ip link add dev ip6erspan12 type ip6erspan external
  RTNETLINK answers: File exists
simply fails due to the 2nd tries to create the same collect_md_tun.

The patch fixes it by adding a separate collect md tunnel device
for the ip6erspan, 'collect_md_tun_erspan'.  As a result, a couple
of places need to refactor/split up in order to distinguish ip6gre
and ip6erspan.

First, move the collect_md check at ip6gre_tunnel_{unlink,link} and
create separate function {ip6gre,ip6ersapn}_tunnel_{link_md,unlink_md}.
Then before link/unlink, make sure the link_md/unlink_md is called.
Finally, a separate ndo_uninit is created for ip6erspan.  Tested it
using the samples/bpf/test_tunnel_bpf.sh.

Fixes: ef7baf5e083c ("ip6_gre: add ip6 erspan collect_md mode")
Signed-off-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv6/ip6_gre.c

@@ -71,6 +71,7 @@ struct ip6gre_net {
 	struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
 
 	struct ip6_tnl __rcu *collect_md_tun;
+	struct ip6_tnl __rcu *collect_md_tun_erspan;
 	struct net_device *fb_tunnel_dev;
 };
 
@@ -233,7 +234,12 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (cand)
 		return cand;
 
-	t = rcu_dereference(ign->collect_md_tun);
+	if (gre_proto == htons(ETH_P_ERSPAN) ||
+	    gre_proto == htons(ETH_P_ERSPAN2))
+		t = rcu_dereference(ign->collect_md_tun_erspan);
+	else
+		t = rcu_dereference(ign->collect_md_tun);
+
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
@@ -262,6 +268,31 @@ static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign,
 	return &ign->tunnels[prio][h];
 }
 
+static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun, t);
+}
+
+static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun_erspan, t);
+}
+
+static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun, NULL);
+}
+
+static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign,
+				       struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun_erspan, NULL);
+}
+
 static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign,
 		const struct ip6_tnl *t)
 {
@@ -272,9 +303,6 @@ static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t)
 {
 	struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
 
-	if (t->parms.collect_md)
-		rcu_assign_pointer(ign->collect_md_tun, t);
-
 	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
 	rcu_assign_pointer(*tp, t);
 }
@@ -284,9 +312,6 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
 	struct ip6_tnl __rcu **tp;
 	struct ip6_tnl *iter;
 
-	if (t->parms.collect_md)
-		rcu_assign_pointer(ign->collect_md_tun, NULL);
-
 	for (tp = ip6gre_bucket(ign, t);
 	     (iter = rtnl_dereference(*tp)) != NULL;
 	     tp = &iter->next) {
@@ -375,11 +400,23 @@ failed_free:
 	return NULL;
 }
 
+static void ip6erspan_tunnel_uninit(struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+
+	ip6erspan_tunnel_unlink_md(ign, t);
+	ip6gre_tunnel_unlink(ign, t);
+	dst_cache_reset(&t->dst_cache);
+	dev_put(dev);
+}
+
 static void ip6gre_tunnel_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
+	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
@@ -1806,7 +1843,7 @@ static int ip6erspan_tap_init(struct net_device *dev)
 
 static const struct net_device_ops ip6erspan_netdev_ops = {
 	.ndo_init =		ip6erspan_tap_init,
-	.ndo_uninit =		ip6gre_tunnel_uninit,
+	.ndo_uninit =		ip6erspan_tunnel_uninit,
 	.ndo_start_xmit =	ip6erspan_tunnel_xmit,
 	.ndo_set_mac_address =	eth_mac_addr,
 	.ndo_validate_addr =	eth_validate_addr,
@@ -1875,8 +1912,6 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
 				 struct netlink_ext_ack *extack)
 {
 	struct ip6_tnl *nt;
-	struct net *net = dev_net(dev);
-	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct ip_tunnel_encap ipencap;
 	int err;
 
@@ -1889,16 +1924,6 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	ip6gre_netlink_parms(data, &nt->parms);
-
-	if (nt->parms.collect_md) {
-		if (rtnl_dereference(ign->collect_md_tun))
-			return -EEXIST;
-	} else {
-		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
-			return -EEXIST;
-	}
-
 	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 
@@ -1922,12 +1947,26 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack)
 {
-	int err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
 	struct ip6_tnl *nt = netdev_priv(dev);
 	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign;
+	int err;
+
+	ip6gre_netlink_parms(data, &nt->parms);
+	ign = net_generic(net, ip6gre_net_id);
+
+	if (nt->parms.collect_md) {
+		if (rtnl_dereference(ign->collect_md_tun))
+			return -EEXIST;
+	} else {
+		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+			return -EEXIST;
+	}
 
+	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
 	if (!err) {
 		ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+		ip6gre_tunnel_link_md(ign, nt);
 		ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
 	}
 	return err;
@@ -1979,8 +2018,10 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
+	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6gre_tunnel_link_md(ign, t);
 	ip6gre_tunnel_link(ign, t);
 	return 0;
 }
@@ -2134,12 +2175,26 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
 			     struct nlattr *tb[], struct nlattr *data[],
 			     struct netlink_ext_ack *extack)
 {
-	int err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
 	struct ip6_tnl *nt = netdev_priv(dev);
 	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign;
+	int err;
+
+	ip6gre_netlink_parms(data, &nt->parms);
+	ign = net_generic(net, ip6gre_net_id);
+
+	if (nt->parms.collect_md) {
+		if (rtnl_dereference(ign->collect_md_tun_erspan))
+			return -EEXIST;
+	} else {
+		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+			return -EEXIST;
+	}
 
+	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
 	if (!err) {
 		ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
+		ip6erspan_tunnel_link_md(ign, nt);
 		ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
 	}
 	return err;
@@ -2171,8 +2226,10 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
+	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6erspan_tunnel_link_md(ign, t);
 	ip6gre_tunnel_link(ign, t);
 	return 0;
 }