ipv6: do not overwrite inetpeer metrics prematurely
If an IPv6 host route with metrics exists, an attempt to add a
new route for the same target with different metrics fails but
rewrites the metrics anyway:
12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000
12sp0:~ # ip -6 route show
fe80::/64 dev eth0 proto kernel metric 256
fec0::1 dev eth0 metric 1024 rto_min lock 1s
12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500
RTNETLINK answers: File exists
12sp0:~ # ip -6 route show
fe80::/64 dev eth0 proto kernel metric 256
fec0::1 dev eth0 metric 1024 rto_min lock 1.5s
This is caused by all IPv6 host routes using the metrics in
their inetpeer (or the shared default). This also holds for the
new route created in ip6_route_add() which shares the metrics
with the already existing route and thus ip6_route_add()
rewrites the metrics even if the new route ends up not being
used at all.
Another problem is that old metrics in inetpeer can reappear
unexpectedly for a new route, e.g.
12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000
12sp0:~ # ip route del fec0::1
12sp0:~ # ip route add fec0::1 dev eth0
12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10
12sp0:~ # ip -6 route show
fe80::/64 dev eth0 proto kernel metric 256
fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s
Resolve the first problem by moving the setting of metrics down
into fib6_add_rt2node() to the point we are sure we are
inserting the new route into the tree. Second problem is
addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE
which is set for a new host route in ip6_route_add() and makes
ipv6_cow_metrics() always overwrite the metrics in inetpeer
(even if they are not "new"); it is reset after that.
v5: use a flag in _metrics member rather than one in flags
v4: fix a typo making a condition always true (thanks to Hannes
Frederic Sowa)
v3: rewritten based on David Miller's idea to move setting the
metrics (and allocation in non-host case) down to the point we
already know the route is to be inserted. Also rebased to
net-next as it is quite late in the cycle.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fba54a4..b93ae6a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -149,7 +149,8 @@
unsigned long prev, new;
p = peer->metrics;
- if (inet_metrics_new(peer))
+ if (inet_metrics_new(peer) ||
+ (old & DST_METRICS_FORCE_OVERWRITE))
memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
new = (unsigned long) p;
@@ -857,14 +858,15 @@
be destroyed.
*/
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
+ struct nlattr *mx, int mx_len)
{
int err;
struct fib6_table *table;
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
- err = fib6_add(&table->tb6_root, rt, info);
+ err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
write_unlock_bh(&table->tb6_lock);
return err;
@@ -875,7 +877,7 @@
struct nl_info info = {
.nl_net = dev_net(rt->dst.dev),
};
- return __ip6_ins_rt(rt, &info);
+ return __ip6_ins_rt(rt, &info, NULL, 0);
}
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1543,17 +1545,11 @@
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
- if (rt->rt6i_dst.plen == 128)
- rt->dst.flags |= DST_HOST;
-
- if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
- u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
- if (!metrics) {
- err = -ENOMEM;
- goto out;
- }
- dst_init_metrics(&rt->dst, metrics, 0);
+ if (rt->rt6i_dst.plen == 128) {
+ rt->dst.flags |= DST_HOST;
+ dst_metrics_set_force_overwrite(&rt->dst);
}
+
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
rt->rt6i_src.plen = cfg->fc_src_len;
@@ -1672,31 +1668,13 @@
rt->rt6i_flags = cfg->fc_flags;
install_route:
- if (cfg->fc_mx) {
- struct nlattr *nla;
- int remaining;
-
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
-
- if (type) {
- if (type > RTAX_MAX) {
- err = -EINVAL;
- goto out;
- }
-
- dst_metric_set(&rt->dst, type, nla_get_u32(nla));
- }
- }
- }
-
rt->dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
cfg->fc_nlinfo.nl_net = dev_net(dev);
- return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
+ return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
out:
if (dev)