mpls: support for dead routes

Adds support for RTNH_F_DEAD and RTNH_F_LINKDOWN flags on mpls
routes due to link events. Also adds code to ignore dead
routes during route selection.

Unlike ip routes, mpls routes are not deleted when the route goes
dead. This is current mpls behaviour and this patch does not change
that. With this patch however, routes will be marked dead.
dead routes are not notified to userspace (this is consistent with ipv4
routes).

dead routes:
-----------
$ip -f mpls route show
100
    nexthop as to 200 via inet 10.1.1.2  dev swp1
    nexthop as to 700 via inet 10.1.1.6  dev swp2

$ip link set dev swp1 down

$ip link show dev swp1
4: swp1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN mode
DEFAULT group default qlen 1000
    link/ether 00:02:00:00:00:01 brd ff:ff:ff:ff:ff:ff

$ip -f mpls route show
100
    nexthop as to 200 via inet 10.1.1.2  dev swp1 dead linkdown
    nexthop as to 700 via inet 10.1.1.6  dev swp2

linkdown routes:
----------------
$ip -f mpls route show
100
    nexthop as to 200 via inet 10.1.1.2  dev swp1
    nexthop as to 700 via inet 10.1.1.6  dev swp2

$ip link show dev swp1
4: swp1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast
state UP mode DEFAULT group default qlen 1000
    link/ether 00:02:00:00:00:01 brd ff:ff:ff:ff:ff:ff

/* carrier goes down */
$ip link show dev swp1
4: swp1: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc pfifo_fast
state DOWN mode DEFAULT group default qlen 1000
    link/ether 00:02:00:00:00:01 brd ff:ff:ff:ff:ff:ff

$ip -f mpls route show
100
    nexthop as to 200 via inet 10.1.1.2  dev swp1 linkdown
    nexthop as to 700 via inet 10.1.1.6  dev swp2
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mpls/af_mpls.c

@@ -96,22 +96,15 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 }
 EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
-static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
+static u32 mpls_multipath_hash(struct mpls_route *rt,
 			       struct sk_buff *skb, bool bos)
 {
 	struct mpls_entry_decoded dec;
 	struct mpls_shim_hdr *hdr;
 	bool eli_seen = false;
 	int label_index;
-	int nh_index = 0;
 	u32 hash = 0;
 
-	/* No need to look further into packet if there's only
-	 * one path
-	 */
-	if (rt->rt_nhn == 1)
-		goto out;
-
 	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
 	     label_index++) {
 		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
@@ -165,7 +158,38 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 		}
 	}
 
-	nh_index = hash % rt->rt_nhn;
+	return hash;
+}
+
+static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
+					     struct sk_buff *skb, bool bos)
+{
+	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
+	u32 hash = 0;
+	int nh_index = 0;
+	int n = 0;
+
+	/* No need to look further into packet if there's only
+	 * one path
+	 */
+	if (rt->rt_nhn == 1)
+		goto out;
+
+	if (alive <= 0)
+		return NULL;
+
+	hash = mpls_multipath_hash(rt, skb, bos);
+	nh_index = hash % alive;
+	if (alive == rt->rt_nhn)
+		goto out;
+	for_nexthops(rt) {
+		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			continue;
+		if (n == nh_index)
+			return nh;
+		n++;
+	} endfor_nexthops(rt);
+
 out:
 	return &rt->rt_nh[nh_index];
 }
@@ -365,6 +389,7 @@ static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
 		     GFP_KERNEL);
 	if (rt) {
 		rt->rt_nhn = num_nh;
+		rt->rt_nhn_alive = num_nh;
 		rt->rt_max_alen = max_alen_aligned;
 	}
 
@@ -536,6 +561,16 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
 
 	RCU_INIT_POINTER(nh->nh_dev, dev);
 
+	if (!(dev->flags & IFF_UP)) {
+		nh->nh_flags |= RTNH_F_DEAD;
+	} else {
+		unsigned int flags;
+
+		flags = dev_get_flags(dev);
+		if (!(flags & (IFF_RUNNING | IFF_LOWER_UP)))
+			nh->nh_flags |= RTNH_F_LINKDOWN;
+	}
+
 	return 0;
 
 errout:
@@ -570,6 +605,9 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
 	if (err)
 		goto errout;
 
+	if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		rt->rt_nhn_alive--;
+
 	return 0;
 
 errout:
@@ -577,8 +615,8 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
 }
 
 static int mpls_nh_build(struct net *net, struct mpls_route *rt,
-			 struct mpls_nh *nh, int oif,
-			 struct nlattr *via, struct nlattr *newdst)
+			 struct mpls_nh *nh, int oif, struct nlattr *via,
+			 struct nlattr *newdst)
 {
 	int err = -ENOMEM;
 
@@ -681,11 +719,13 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
 			goto errout;
 
 		err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
-				    rtnh->rtnh_ifindex, nla_via,
-				    nla_newdst);
+				    rtnh->rtnh_ifindex, nla_via, nla_newdst);
 		if (err)
 			goto errout;
 
+		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			rt->rt_nhn_alive--;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 		nhs++;
 	} endfor_nexthops(rt);
@@ -875,34 +915,74 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
 	return ERR_PTR(err);
 }
 
-static void mpls_ifdown(struct net_device *dev)
+static void mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	struct mpls_dev *mdev;
 	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]);
+
 		if (!rt)
 			continue;
-		for_nexthops(rt) {
+
+		change_nexthops(rt) {
 			if (rtnl_dereference(nh->nh_dev) != dev)
 				continue;
-			nh->nh_dev = NULL;
+			switch (event) {
+			case NETDEV_DOWN:
+			case NETDEV_UNREGISTER:
+				nh->nh_flags |= RTNH_F_DEAD;
+				/* fall through */
+			case NETDEV_CHANGE:
+				nh->nh_flags |= RTNH_F_LINKDOWN;
+				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				break;
+			}
+			if (event == NETDEV_UNREGISTER)
+				RCU_INIT_POINTER(nh->nh_dev, NULL);
 		} endfor_nexthops(rt);
 	}
 
-	mdev = mpls_dev_get(dev);
-	if (!mdev)
+
 	return;
+}
 
-	mpls_dev_sysctl_unregister(mdev);
+static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+{
+	struct mpls_route __rcu **platform_label;
+	struct net *net = dev_net(dev);
+	unsigned index;
+	int alive;
 
-	RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+	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]);
 
-	kfree_rcu(mdev, rcu);
+		if (!rt)
+			continue;
+
+		alive = 0;
+		change_nexthops(rt) {
+			struct net_device *nh_dev =
+				rtnl_dereference(nh->nh_dev);
+
+			if (!(nh->nh_flags & nh_flags)) {
+				alive++;
+				continue;
+			}
+			if (nh_dev != dev)
+				continue;
+			alive++;
+			nh->nh_flags &= ~nh_flags;
+		} endfor_nexthops(rt);
+
+		ACCESS_ONCE(rt->rt_nhn_alive) = alive;
+	}
+
+	return;
 }
 
 static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
@@ -910,9 +990,9 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mpls_dev *mdev;
+	unsigned int flags;
 
-	switch(event) {
-	case NETDEV_REGISTER:
+	if (event == NETDEV_REGISTER) {
 		/* For now just support ethernet devices */
 		if ((dev->type == ARPHRD_ETHER) ||
 		    (dev->type == ARPHRD_LOOPBACK)) {
@@ -920,10 +1000,39 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 			if (IS_ERR(mdev))
 				return notifier_from_errno(PTR_ERR(mdev));
 		}
-		break;
+		return NOTIFY_OK;
+	}
 
+	mdev = mpls_dev_get(dev);
+	if (!mdev)
+		return NOTIFY_OK;
+
+	switch (event) {
+	case NETDEV_DOWN:
+		mpls_ifdown(dev, event);
+		break;
+	case NETDEV_UP:
+		flags = dev_get_flags(dev);
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+		else
+			mpls_ifup(dev, RTNH_F_DEAD);
+		break;
+	case NETDEV_CHANGE:
+		flags = dev_get_flags(dev);
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+		else
+			mpls_ifdown(dev, event);
+		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev);
+		mpls_ifdown(dev, event);
+		mdev = mpls_dev_get(dev);
+		if (mdev) {
+			mpls_dev_sysctl_unregister(mdev);
+			RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+			kfree_rcu(mdev, rcu);
+		}
 		break;
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
@@ -1237,9 +1346,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		dev = rtnl_dereference(nh->nh_dev);
 		if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 			goto nla_put_failure;
+		if (nh->nh_flags & RTNH_F_LINKDOWN)
+			rtm->rtm_flags |= RTNH_F_LINKDOWN;
+		if (nh->nh_flags & RTNH_F_DEAD)
+			rtm->rtm_flags |= RTNH_F_DEAD;
 	} else {
 		struct rtnexthop *rtnh;
 		struct nlattr *mp;
+		int dead = 0;
+		int linkdown = 0;
 
 		mp = nla_nest_start(skb, RTA_MULTIPATH);
 		if (!mp)
@@ -1253,6 +1368,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			dev = rtnl_dereference(nh->nh_dev);
 			if (dev)
 				rtnh->rtnh_ifindex = dev->ifindex;
+			if (nh->nh_flags & RTNH_F_LINKDOWN) {
+				rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
+				linkdown++;
+			}
+			if (nh->nh_flags & RTNH_F_DEAD) {
+				rtnh->rtnh_flags |= RTNH_F_DEAD;
+				dead++;
+			}
+
 			if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST,
 							    nh->nh_labels,
 							    nh->nh_label))
@@ -1266,6 +1390,11 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
 		} endfor_nexthops(rt);
 
+		if (linkdown == rt->rt_nhn)
+			rtm->rtm_flags |= RTNH_F_LINKDOWN;
+		if (dead == rt->rt_nhn)
+			rtm->rtm_flags |= RTNH_F_DEAD;
+
 		nla_nest_end(skb, mp);
 	}
 

net/mpls/internal.h

@@ -41,6 +41,7 @@ enum mpls_payload_type {
 
 struct mpls_nh { /* next hop label forwarding entry */
 	struct net_device __rcu *nh_dev;
+	unsigned int		nh_flags;
 	u32			nh_label[MAX_NEW_LABELS];
 	u8			nh_labels;
 	u8			nh_via_alen;
@@ -74,6 +75,7 @@ struct mpls_route { /* next hop label forwarding entry */
 	u8			rt_payload_type;
 	u8			rt_max_alen;
 	unsigned int		rt_nhn;
+	unsigned int		rt_nhn_alive;
 	struct mpls_nh		rt_nh[0];
 };