1 files changed, 58 insertions, 16 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7c38e0e058ae..e3226284e480 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -517,10 +517,11 @@ static void rt6_probe_deferred(struct work_struct *w)
 
 static void rt6_probe(struct fib6_info *rt)
 {
-	struct __rt6_probe_work *work;
+	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
 	struct neighbour *neigh;
 	struct net_device *dev;
+	struct inet6_dev *idev;
 
 	/*
 	 * Okay, this does not seem to be appropriate
@@ -536,15 +537,12 @@ static void rt6_probe(struct fib6_info *rt)
 	nh_gw = &rt->fib6_nh.nh_gw;
 	dev = rt->fib6_nh.nh_dev;
 	rcu_read_lock_bh();
+	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
-		struct inet6_dev *idev;
-
 		if (neigh->nud_state & NUD_VALID)
 			goto out;
 
-		idev = __in6_dev_get(dev);
-		work = NULL;
 		write_lock(&neigh->lock);
 		if (!(neigh->nud_state & NUD_VALID) &&
 		    time_after(jiffies,
@@ -554,11 +552,13 @@ static void rt6_probe(struct fib6_info *rt)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else {
+	} else if (time_after(jiffies, rt->last_probe +
+				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
 	if (work) {
+		rt->last_probe = jiffies;
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
@@ -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)
@@ -4763,28 +4767,52 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static bool fib6_info_uses_dev(const struct fib6_info *f6i,
+			       const struct net_device *dev)
+{
+	if (f6i->fib6_nh.nh_dev == dev)
+		return true;
+
+	if (f6i->fib6_nsiblings) {
+		struct fib6_info *sibling, *next_sibling;
+
+		list_for_each_entry_safe(sibling, next_sibling,
+					 &f6i->fib6_siblings, fib6_siblings) {
+			if (sibling->fib6_nh.nh_dev == dev)
+				return true;
+		}
+	}
+
+	return false;
+}
+
 int rt6_dump_route(struct fib6_info *rt, void *p_arg)
 {
 	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
+	struct fib_dump_filter *filter = &arg->filter;
+	unsigned int flags = NLM_F_MULTI;
 	struct net *net = arg->net;
 
 	if (rt == net->ipv6.fib6_null_entry)
 		return 0;
 
-	if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
-		struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
-
-		/* user wants prefix routes only */
-		if (rtm->rtm_flags & RTM_F_PREFIX &&
-		    !(rt->fib6_flags & RTF_PREFIX_RT)) {
-			/* success since this is not a prefix route */
+	if ((filter->flags & RTM_F_PREFIX) &&
+	    !(rt->fib6_flags & RTF_PREFIX_RT)) {
+		/* success since this is not a prefix route */
+		return 1;
+	}
+	if (filter->filter_set) {
+		if ((filter->rt_type && rt->fib6_type != filter->rt_type) ||
+		    (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) ||
+		    (filter->protocol && rt->fib6_protocol != filter->protocol)) {
 			return 1;
 		}
+		flags |= NLM_F_DUMP_FILTERED;
 	}
 
 	return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0,
 			     RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid,
-			     arg->cb->nlh->nlmsg_seq, NLM_F_MULTI);
+			     arg->cb->nlh->nlmsg_seq, flags);
 }
 
 static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
@@ -5031,7 +5059,10 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
 	return 0;
 }
 
-struct ctl_table ipv6_route_table_template[] = {
+static int zero;
+static int one = 1;
+
+static struct ctl_table ipv6_route_table_template[] = {
 	{
 		.procname	=	"flush",
 		.data		=	&init_net.ipv6.sysctl.flush_delay,
@@ -5102,6 +5133,15 @@ 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 +5165,7 @@ 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 +5230,7 @@ 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;