[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1438875754-28025-2-git-send-email-gospo@cumulusnetworks.com>
Date: Thu, 6 Aug 2015 11:42:34 -0400
From: Andy Gospodarek <gospo@...ulusnetworks.com>
To: netdev@...r.kernel.org
Cc: Andy Gospodarek <gospo@...ulusnetworks.com>,
Dinesh Dutt <ddutt@...ulusnetworks.com>
Subject: [PATCH net-next 2/2] net: ipv6 sysctl option to ignore routes when nexthop link is down
Like the ipv4 patch with a similar title, this adds a sysctl to allow
the user to change routing behavior based on whether or not the
interface associated with the nexthop was an up or down link. The
default setting preserves the current behavior, but anyone that enables
it will notice that nexthops on down interfaces will no longer be
selected:
net.ipv6.conf.all.ignore_routes_with_linkdown = 0
net.ipv6.conf.default.ignore_routes_with_linkdown = 0
net.ipv6.conf.lo.ignore_routes_with_linkdown = 0
...
When the above sysctls are set, not only will link status be reported to
userspace, but an indication that a nexthop is dead and will not be used
is also reported.
1000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium
1000::/8 via 8000::2 dev p8p1 metric 1024 pref medium
7000::/8 dev p7p1 proto kernel metric 256 dead linkdown pref medium
8000::/8 dev p8p1 proto kernel metric 256 pref medium
9000::/8 via 8000::2 dev p8p1 metric 2048 pref medium
9000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium
fe80::/64 dev p7p1 proto kernel metric 256 dead linkdown pref medium
fe80::/64 dev p8p1 proto kernel metric 256 pref medium
This also adds devconf support and notification when sysctl values
change.
Signed-off-by: Andy Gospodarek <gospo@...ulusnetworks.com>
Signed-off-by: Dinesh Dutt <ddutt@...ulusnetworks.com>
---
include/linux/ipv6.h | 1 +
include/uapi/linux/ipv6.h | 1 +
net/ipv6/addrconf.c | 105 +++++++++++++++++++++++++++++++++++++++++++++-
net/ipv6/route.c | 8 ++++
4 files changed, 114 insertions(+), 1 deletion(-)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index cb9dcad..f1f32af 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -31,6 +31,7 @@ struct ipv6_devconf {
__s32 accept_ra_defrtr;
__s32 accept_ra_min_hop_limit;
__s32 accept_ra_pinfo;
+ __s32 ignore_routes_with_linkdown;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 80f3b74..38b4fef 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -173,6 +173,7 @@ enum {
DEVCONF_STABLE_SECRET,
DEVCONF_USE_OIF_ADDRS_ONLY,
DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
+ DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
DEVCONF_MAX
};
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3fc8ee2..ab97461 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -214,6 +214,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.initialized = false,
},
.use_oif_addrs_only = 0,
+ .ignore_routes_with_linkdown = 0,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.initialized = false,
},
.use_oif_addrs_only = 0,
+ .ignore_routes_with_linkdown = 0,
};
/* Check if a valid qdisc is available */
@@ -472,6 +474,9 @@ static int inet6_netconf_msgsize_devconf(int type)
if (type == -1 || type == NETCONFA_PROXY_NEIGH)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
+ size += nla_total_size(4);
+
return size;
}
@@ -508,6 +513,11 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
+ nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ devconf->ignore_routes_with_linkdown) < 0)
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -544,6 +554,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
[NETCONFA_IFINDEX] = { .len = sizeof(int) },
[NETCONFA_FORWARDING] = { .len = sizeof(int) },
[NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) },
+ [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) },
};
static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
@@ -766,6 +777,63 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
rt6_purge_dflt_routers(net);
return 1;
}
+
+static void addrconf_linkdown_change(struct net *net, __s32 newf)
+{
+ struct net_device *dev;
+ struct inet6_dev *idev;
+
+ for_each_netdev(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (idev) {
+ int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf);
+
+ idev->cnf.ignore_routes_with_linkdown = newf;
+ if (changed)
+ inet6_netconf_notify_devconf(dev_net(dev),
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ dev->ifindex,
+ &idev->cnf);
+ }
+ }
+}
+
+static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
+{
+ struct net *net;
+ int old;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ net = (struct net *)table->extra2;
+ old = *p;
+ *p = newf;
+
+ if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) {
+ if ((!newf) ^ (!old))
+ inet6_netconf_notify_devconf(net,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt);
+ rtnl_unlock();
+ return 0;
+ }
+
+ if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) {
+ net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf;
+ addrconf_linkdown_change(net, newf);
+ if ((!newf) ^ (!old))
+ inet6_netconf_notify_devconf(net,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
+ }
+ rtnl_unlock();
+
+ return 1;
+}
+
#endif
/* Nobody refers to this ifaddr, destroy it */
@@ -4618,6 +4686,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
+ array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown;
/* we omit DEVCONF_STABLE_SECRET for now */
array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only;
}
@@ -5340,6 +5409,34 @@ out:
return err;
}
+static
+int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
+ int write,
+ void __user *buffer,
+ size_t *lenp,
+ loff_t *ppos)
+{
+ int *valp = ctl->data;
+ int val = *valp;
+ loff_t pos = *ppos;
+ struct ctl_table lctl;
+ int ret;
+
+ /* ctl->data points to idev->cnf.ignore_routes_when_linkdown
+ * we should not modify it until we get the rtnl lock.
+ */
+ lctl = *ctl;
+ lctl.data = &val;
+
+ ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+
+ if (write)
+ ret = addrconf_fixup_linkdown(ctl, valp, val);
+ if (ret)
+ *ppos = pos;
+ return ret;
+}
+
static struct addrconf_sysctl_table
{
struct ctl_table_header *sysctl_header;
@@ -5631,7 +5728,13 @@ static struct addrconf_sysctl_table
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
-
+ },
+ {
+ .procname = "ignore_routes_with_linkdown",
+ .data = &ipv6_devconf.ignore_routes_with_linkdown,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown,
},
{
/* sentinel */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a5c8c6a..d4b0723 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -665,6 +665,11 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
{
int m;
bool match_do_rr = false;
+ struct inet6_dev *idev = rt->rt6i_idev;
+
+ if (idev && (rt->rt6i_nhflags & RTNH_F_LINKDOWN) &&
+ idev->cnf.ignore_routes_with_linkdown)
+ goto out;
if (rt6_check_expired(rt))
goto out;
@@ -2930,6 +2935,9 @@ static int rt6_fill_node(struct net *net,
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = rt->rt6i_nhflags;
+ if ((rt->rt6i_nhflags & RTNH_F_LINKDOWN) &&
+ rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+ rtm->rtm_flags |= RTNH_F_DEAD;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
if (rt->rt6i_flags & RTF_DYNAMIC)
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists