net: mpls: Fix notifications when deleting a device

There are various problems related to netlink notifications for mpls route
changes in response to interfaces being deleted:
* delete interface of only nexthop
	DELROUTE notification is missing RTA_OIF attribute
* delete interface of non-last nexthop
	NEWROUTE notification is missing entirely
* delete interface of last nexthop
	DELROUTE notification is missing nexthop

All of these problems stem from the fact that existing routes are modified
in-place before sending a notification. Restructure mpls_ifdown() to avoid
changing the route in the DELROUTE cases and to create a copy in the
NEWROUTE case.

Fixes: f8efb73c97 ("mpls: multipath route support")
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mpls/af_mpls.c

@@ -1491,22 +1491,52 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head)
 	kfree(mdev);
 }
 
-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		bool nh_del = false;
+		u8 alive = 0;
 
 		if (!rt)
 			continue;
 
-		alive = 0;
+		if (event == NETDEV_UNREGISTER) {
-		deleted = 0;
+			u8 deleted = 0;
+
+			for_nexthops(rt) {
+				struct net_device *nh_dev =
+					rtnl_dereference(nh->nh_dev);
+
+				if (!nh_dev || nh_dev == dev)
+					deleted++;
+				if (nh_dev == dev)
+					nh_del = true;
+			} endfor_nexthops(rt);
+
+			/* if there are no more nexthops, delete the route */
+			if (deleted == rt->rt_nhn) {
+				mpls_route_update(net, index, NULL, NULL);
+				continue;
+			}
+
+			if (nh_del) {
+				size_t size = sizeof(*rt) + rt->rt_nhn *
+					rt->rt_nh_size;
+				struct mpls_route *orig = rt;
+
+				rt = kmalloc(size, GFP_KERNEL);
+				if (!rt)
+					return -ENOMEM;
+				memcpy(rt, orig, size);
+			}
+		}
+
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
 
@@ -1530,16 +1560,15 @@ static void mpls_ifdown(struct net_device *dev, int event)
 next:
 			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
-			if (!rtnl_dereference(nh->nh_dev))
-				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
 
-		/* if there are no more nexthops, delete the route */
+		if (nh_del)
-		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
+			mpls_route_update(net, index, rt, NULL);
-			mpls_route_update(net, index, NULL, NULL);
 	}
+
+	return 0;
 }
 
 static void mpls_ifup(struct net_device *dev, unsigned int flags)
@@ -1597,8 +1626,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		return NOTIFY_OK;
 
 	switch (event) {
+		int err;
+
 	case NETDEV_DOWN:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
 		flags = dev_get_flags(dev);
@@ -1609,13 +1642,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
-		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
-		else
+		} else {
-			mpls_ifdown(dev, event);
+			err = mpls_ifdown(dev, event);
+			if (err)
+				return notifier_from_errno(err);
+		}
 		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
 			mpls_dev_sysctl_unregister(dev, mdev);
@@ -1626,8 +1664,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			int err;
-
 			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)