net/ipv6: Add knob to skip DELROUTE message on device down
Another difference between IPv4 and IPv6 is the generation of RTM_DELROUTE
notifications when a device is taken down (admin down) or deleted. IPv4
does not generate a message for routes evicted by the down or delete;
IPv6 does. A NOS at scale really needs to avoid these messages and have
IPv4 and IPv6 behave similarly, relying on userspace to handle link
notifications and evict the routes.
At this point existing user behavior needs to be preserved. Since
notifications are a global action (not per app) the only way to preserve
existing behavior and allow the messages to be skipped is to add a new
sysctl (net/ipv6/route/skip_notify_on_dev_down) which can be set to
disable the notificatioons.
IPv6 route code already supports the option to skip the message (it is
used for multipath routes for example). Besides the new sysctl we need
to pass the skip_notify setting through the generic fib6_clean and
fib6_walk functions to fib6_clean_node and to set skip_notify on calls
to __ip_del_rt for the addrconf_ifdown path.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bf4cd64..f4e08b0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4026,8 +4026,12 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event)
.event = event,
},
};
+ struct net *net = dev_net(dev);
- fib6_clean_all(dev_net(dev), fib6_ifdown, &arg);
+ if (net->ipv6.sysctl.skip_notify_on_dev_down)
+ fib6_clean_all_skip_notify(net, fib6_ifdown, &arg);
+ else
+ fib6_clean_all(net, fib6_ifdown, &arg);
}
void rt6_disable_ip(struct net_device *dev, unsigned long event)
@@ -5031,6 +5035,9 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
return 0;
}
+static int zero;
+static int one = 1;
+
static struct ctl_table ipv6_route_table_template[] = {
{
.procname = "flush",
@@ -5102,6 +5109,15 @@ static struct ctl_table ipv6_route_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
+ {
+ .procname = "skip_notify_on_dev_down",
+ .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{ }
};
@@ -5125,6 +5141,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
@@ -5189,6 +5206,7 @@ static int __net_init ip6_route_net_init(struct net *net)
net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
+ net->ipv6.sysctl.skip_notify_on_dev_down = 0;
net->ipv6.ip6_rt_gc_expire = 30*HZ;