net: ipv4 sysctl option to ignore routes when nexthop link is down

This feature is only enabled with the new per-interface or ipv4 global
sysctls called 'ignore_routes_with_linkdown'.

net.ipv4.conf.all.ignore_routes_with_linkdown = 0
net.ipv4.conf.default.ignore_routes_with_linkdown = 0
net.ipv4.conf.lo.ignore_routes_with_linkdown = 0
...

When the above sysctls are set, will report to userspace that a route is
dead and will no longer resolve to this nexthop when performing a fib
lookup.  This will signal to userspace that the route will not be
selected.  The signalling of a RTNH_F_DEAD is only passed to userspace
if the sysctl is enabled and link is down.  This was done as without it
the netlink listeners would have no idea whether or not a nexthop would
be selected.   The kernel only sets RTNH_F_DEAD internally if the
interface has IFF_UP cleared.

With the new sysctl set, the following behavior can be observed
(interface p8p1 is link-down):

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1 dead linkdown
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1 dead linkdown
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2
90.0.0.1 via 70.0.0.2 dev p7p1  src 70.0.0.1
    cache
local 80.0.0.1 dev lo  src 80.0.0.1
    cache <local>
80.0.0.2 via 10.0.5.2 dev p9p1  src 10.0.5.15
    cache

While the route does remain in the table (so it can be modified if
needed rather than being wiped away as it would be if IFF_UP was
cleared), the proper next-hop is chosen automatically when the link is
down.  Now interface p8p1 is linked-up:

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2
192.168.56.0/24 dev p2p1  proto kernel  scope link  src 192.168.56.2
90.0.0.1 via 80.0.0.2 dev p8p1  src 80.0.0.1
    cache
local 80.0.0.1 dev lo  src 80.0.0.1
    cache <local>
80.0.0.2 dev p8p1  src 80.0.0.1
    cache

and the output changes to what one would expect.

If the sysctl is not set, the following output would be expected when
p8p1 is down:

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1 linkdown
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1 linkdown
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2

Since the dead flag does not appear, there should be no expectation that
the kernel would skip using this route due to link being down.

v2: Split kernel changes into 2 patches, this actually makes a
behavioral change if the sysctl is set.  Also took suggestion from Alex
to simplify code by only checking sysctl during fib lookup and
suggestion from Scott to add a per-interface sysctl.

v3: Code clean-ups to make it more readable and efficient as well as a
reverse path check fix.

v4: Drop binary sysctl

v5: Whitespace fixups from Dave

v6: Style changes from Dave and checkpatch suggestions

v7: One more checkpatch fixup

Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Acked-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 48 insertions, 16 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 419d23c53ec7..7498716e8f54 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2169,6 +2169,8 @@ static struct devinet_sysctl_table {
 					"igmpv2_unsolicited_report_interval"),
 		DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL,
 					"igmpv3_unsolicited_report_interval"),
+		DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN,
+					"ignore_routes_with_linkdown"),
 
 		DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
 		DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 534eb1485045..6bbc54940eb4 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -280,7 +280,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 		fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 		fl4.flowi4_scope = scope;
 		fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
-		if (!fib_lookup(net, &fl4, &res))
+		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
 	} else {
 		scope = RT_SCOPE_LINK;
@@ -319,7 +319,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
 
 	net = dev_net(dev);
-	if (fib_lookup(net, &fl4, &res))
+	if (fib_lookup(net, &fl4, &res, 0))
 		goto last_resort;
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
@@ -354,7 +354,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_oif = dev->ifindex;
 
 	ret = 0;
-	if (fib_lookup(net, &fl4, &res) == 0) {
+	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
 			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
 	}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 56151982f74e..18123d50f576 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,11 +47,12 @@ struct fib4_rule {
 #endif
 };
 
-int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
+int __fib_lookup(struct net *net, struct flowi4 *flp,
+		 struct fib_result *res, unsigned int flags)
 {
 	struct fib_lookup_arg arg = {
 		.result = res,
-		.flags = FIB_LOOKUP_NOREF,
+		.flags = flags,
 	};
 	int err;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b1b305b1e340..3bfccd83551c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -623,7 +623,8 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			/* It is not necessary, but requires a bit of thinking */
 			if (fl4.flowi4_scope < RT_SCOPE_LINK)
 				fl4.flowi4_scope = RT_SCOPE_LINK;
-			err = fib_lookup(net, &fl4, &res);
+			err = fib_lookup(net, &fl4, &res,
+					 FIB_LOOKUP_IGNORE_LINKSTATE);
 			if (err) {
 				rcu_read_unlock();
 				return err;
@@ -1035,12 +1036,20 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
+		struct in_device *in_dev;
+
 		if (fi->fib_nh->nh_gw &&
 		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
 			goto nla_put_failure;
 		if (fi->fib_nh->nh_oif &&
 		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
 			goto nla_put_failure;
+		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
+			in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev);
+			if (in_dev &&
+			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
+				rtm->rtm_flags |= RTNH_F_DEAD;
+		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid &&
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
@@ -1057,11 +1066,19 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 
 		for_nexthops(fi) {
+			struct in_device *in_dev;
+
 			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
 			if (!rtnh)
 				goto nla_put_failure;
 
 			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
+			if (nh->nh_flags & RTNH_F_LINKDOWN) {
+				in_dev = __in_dev_get_rcu(nh->nh_dev);
+				if (in_dev &&
+				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
+					rtnh->rtnh_flags |= RTNH_F_DEAD;
+			}
 			rtnh->rtnh_hops = nh->nh_weight - 1;
 			rtnh->rtnh_ifindex = nh->nh_oif;
 
@@ -1310,16 +1327,22 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 void fib_select_multipath(struct fib_result *res)
 {
 	struct fib_info *fi = res->fi;
+	struct in_device *in_dev;
 	int w;
 
 	spin_lock_bh(&fib_multipath_lock);
 	if (fi->fib_power <= 0) {
 		int power = 0;
 		change_nexthops(fi) {
-			if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) {
-				power += nexthop_nh->nh_weight;
-				nexthop_nh->nh_power = nexthop_nh->nh_weight;
-			}
+			in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev);
+			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
+				continue;
+			if (in_dev &&
+			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+			    nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
+				continue;
+			power += nexthop_nh->nh_weight;
+			nexthop_nh->nh_power = nexthop_nh->nh_weight;
 		} endfor_nexthops(fi);
 		fi->fib_power = power;
 		if (power <= 0) {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 6c666a9f1bd5..15d32612e3c6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1412,9 +1412,15 @@ found:
 			continue;
 		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
 			const struct fib_nh *nh = &fi->fib_nh[nhsel];
+			struct in_device *in_dev = __in_dev_get_rcu(nh->nh_dev);
 
 			if (nh->nh_flags & RTNH_F_DEAD)
 				continue;
+			if (in_dev &&
+			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+			    nh->nh_flags & RTNH_F_LINKDOWN &&
+			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
+				continue;
 			if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
 				continue;
 
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 4bfaedf9b34e..8618fd150c96 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -40,7 +40,7 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4,
 	struct net *net = dev_net(dev);
 	int ret __maybe_unused;
 
-	if (fib_lookup(net, fl4, &res))
+	if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
 		return false;
 
 	if (res.type != RTN_UNICAST) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6055984c307..d0362a2de3d3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -747,7 +747,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
 		} else {
-			if (fib_lookup(net, fl4, &res) == 0) {
+			if (fib_lookup(net, fl4, &res, 0) == 0) {
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
@@ -975,7 +975,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
+	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
 		struct fib_nh *nh = &FIB_RES_NH(res);
 
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
@@ -1186,7 +1186,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		fl4.flowi4_mark = skb->mark;
 
 		rcu_read_lock();
-		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
+		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
 			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
 		else
 			src = inet_select_addr(rt->dst.dev,
@@ -1716,7 +1716,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
-	err = fib_lookup(net, &fl4, &res);
+	err = fib_lookup(net, &fl4, &res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
 			err = -EHOSTUNREACH;
@@ -2123,7 +2123,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		goto make_route;
 	}
 
-	if (fib_lookup(net, fl4, &res)) {
+	if (fib_lookup(net, fl4, &res, 0)) {
 		res.fi = NULL;
 		res.table = NULL;
 		if (fl4->flowi4_oif) {