netdev - [PATCH net-next 15/18] ipv6: Flush multipath routes when all siblings are dead

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sun,  7 Jan 2018 12:45:15 +0200
From:   Ido Schimmel <idosch@...lanox.com>
To:     netdev@...r.kernel.org
Cc:     davem@...emloft.net, dsahern@...il.com, roopa@...ulusnetworks.com,
        nicolas.dichtel@...nd.com, weiwan@...gle.com, kafai@...com,
        yoshfuji@...ux-ipv6.org, mlxsw@...lanox.com,
        Ido Schimmel <idosch@...lanox.com>
Subject: [PATCH net-next 15/18] ipv6: Flush multipath routes when all siblings are dead

By default, IPv6 deletes nexthops from a multipath route when the
nexthop device is put administratively down. This differs from IPv4
where the nexthops are kept, but marked with the RTNH_F_DEAD flag. A
multipath route is flushed when all of its nexthops become dead.

Align IPv6 with IPv4 and have it conform to the same guidelines.

In case the multipath route needs to be flushed, its siblings are
flushed one by one. Otherwise, the nexthops are marked with the
appropriate flags and the tree walker is instructed to skip all the
siblings.

As explained in previous patches, care is taken to update the sernum of
the affected tree nodes, so as to prevent the use of wrong dst entries.

Signed-off-by: Ido Schimmel <idosch@...lanox.com>
---
 net/ipv6/route.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 75 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a3bfce71c861..1054b059747f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3486,8 +3486,10 @@ static int fib6_ifup(struct rt6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	const struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev)
+	if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) {
 		rt->rt6i_nh_flags &= ~arg->nh_flags;
+		fib6_update_sernum_upto_root(dev_net(rt->dst.dev), rt);
+	}
 
 	return 0;
 }
@@ -3505,6 +3507,58 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags)
 	fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
 }
 
+static bool rt6_multipath_uses_dev(const struct rt6_info *rt,
+				   const struct net_device *dev)
+{
+	struct rt6_info *iter;
+
+	if (rt->dst.dev == dev)
+		return true;
+	list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+		if (iter->dst.dev == dev)
+			return true;
+
+	return false;
+}
+
+static void rt6_multipath_flush(struct rt6_info *rt)
+{
+	struct rt6_info *iter;
+
+	rt->should_flush = 1;
+	list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+		iter->should_flush = 1;
+}
+
+static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt,
+					     const struct net_device *down_dev)
+{
+	struct rt6_info *iter;
+	unsigned int dead = 0;
+
+	if (rt->dst.dev == down_dev || rt->rt6i_nh_flags & RTNH_F_DEAD)
+		dead++;
+	list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+		if (iter->dst.dev == down_dev ||
+		    iter->rt6i_nh_flags & RTNH_F_DEAD)
+			dead++;
+
+	return dead;
+}
+
+static void rt6_multipath_nh_flags_set(struct rt6_info *rt,
+				       const struct net_device *dev,
+				       unsigned int nh_flags)
+{
+	struct rt6_info *iter;
+
+	if (rt->dst.dev == dev)
+		rt->rt6i_nh_flags |= nh_flags;
+	list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+		if (iter->dst.dev == dev)
+			iter->rt6i_nh_flags |= nh_flags;
+}
+
 /* called with write lock held for table with rt */
 static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
 {
@@ -3512,20 +3566,33 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
 	const struct net_device *dev = arg->dev;
 	const struct net *net = dev_net(dev);
 
-	if (rt->dst.dev != dev || rt == net->ipv6.ip6_null_entry)
+	if (rt == net->ipv6.ip6_null_entry)
 		return 0;
 
 	switch (arg->event) {
 	case NETDEV_UNREGISTER:
-		return -1;
+		return rt->dst.dev == dev ? -1 : 0;
 	case NETDEV_DOWN:
-		if (rt->rt6i_nsiblings == 0 ||
-		    !rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+		if (rt->should_flush)
 			return -1;
-		rt->rt6i_nh_flags |= RTNH_F_DEAD;
-		/* fall through */
+		if (!rt->rt6i_nsiblings)
+			return rt->dst.dev == dev ? -1 : 0;
+		if (rt6_multipath_uses_dev(rt, dev)) {
+			unsigned int count;
+
+			count = rt6_multipath_dead_count(rt, dev);
+			if (rt->rt6i_nsiblings + 1 == count) {
+				rt6_multipath_flush(rt);
+				return -1;
+			}
+			rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD |
+						   RTNH_F_LINKDOWN);
+			fib6_update_sernum(rt);
+		}
+		return -2;
 	case NETDEV_CHANGE:
-		if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST))
+		if (rt->dst.dev != dev ||
+		    rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST))
 			break;
 		rt->rt6i_nh_flags |= RTNH_F_LINKDOWN;
 		break;
-- 
2.14.3