1 files changed, 119 insertions, 130 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index abcb5ae77319..e3226284e480 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -364,14 +364,11 @@ EXPORT_SYMBOL(ip6_dst_alloc);
 
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
-	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct fib6_info *from;
 	struct inet6_dev *idev;
 
-	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
-		kfree(p);
-
+	ip_dst_metrics_put(dst);
 	rt6_uncached_list_del(rt);
 
 	idev = rt->rt6i_idev;
@@ -978,11 +975,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 {
 	rt->rt6i_flags &= ~RTF_EXPIRES;
 	rcu_assign_pointer(rt->from, from);
-	dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
-	if (from->fib6_metrics != &dst_default_metrics) {
-		rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-		refcount_inc(&from->fib6_metrics->refcnt);
-	}
+	ip_dst_init_metrics(&rt->dst, from->fib6_metrics);
 }
 
 /* Caller must already hold reference to @ort */
@@ -1000,7 +993,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 #ifdef CONFIG_IPV6_SUBTREES
 	rt->rt6i_src = ort->fib6_src;
 #endif
-	rt->rt6i_prefsrc = ort->fib6_prefsrc;
 }
 
 static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
@@ -1454,11 +1446,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
 	if (ort->fib6_src.plen)
 		src_key = &nrt->rt6i_src.addr;
 #endif
-
-	/* Update rt6i_prefsrc as it could be changed
-	 * in rt6_remove_prefsrc()
-	 */
-	nrt->rt6i_prefsrc = ort->fib6_prefsrc;
 	/* rt6_mtu_change() might lower mtu on ort.
 	 * Only insert this exception route if its mtu
 	 * is less than ort's mtu value.
@@ -1640,25 +1627,6 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 	rcu_read_unlock();
 }
 
-static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt)
-{
-	struct rt6_exception_bucket *bucket;
-	struct rt6_exception *rt6_ex;
-	int i;
-
-	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
-					lockdep_is_held(&rt6_exception_lock));
-
-	if (bucket) {
-		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
-			hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
-				rt6_ex->rt6i->rt6i_prefsrc.plen = 0;
-			}
-			bucket++;
-		}
-	}
-}
-
 static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
 					 struct rt6_info *rt, int mtu)
 {
@@ -2103,7 +2071,8 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 {
 	bool any_src;
 
-	if (rt6_need_strict(&fl6->daddr)) {
+	if (ipv6_addr_type(&fl6->daddr) &
+	    (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) {
 		struct dst_entry *dst;
 
 		dst = l3mdev_link_scope_lookup(net, fl6);
@@ -2373,15 +2342,14 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 {
 	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
 	struct dst_entry *dst;
-	struct flowi6 fl6;
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
-	fl6.daddr = iph->daddr;
-	fl6.saddr = iph->saddr;
-	fl6.flowlabel = ip6_flowinfo(iph);
-	fl6.flowi6_uid = uid;
+	struct flowi6 fl6 = {
+		.flowi6_oif = oif,
+		.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark),
+		.daddr = iph->daddr,
+		.saddr = iph->saddr,
+		.flowlabel = ip6_flowinfo(iph),
+		.flowi6_uid = uid,
+	};
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
@@ -2532,16 +2500,15 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
 {
 	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
 	struct dst_entry *dst;
-	struct flowi6 fl6;
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_iif = LOOPBACK_IFINDEX;
-	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark;
-	fl6.daddr = iph->daddr;
-	fl6.saddr = iph->saddr;
-	fl6.flowlabel = ip6_flowinfo(iph);
-	fl6.flowi6_uid = uid;
+	struct flowi6 fl6 = {
+		.flowi6_iif = LOOPBACK_IFINDEX,
+		.flowi6_oif = oif,
+		.flowi6_mark = mark,
+		.daddr = iph->daddr,
+		.saddr = iph->saddr,
+		.flowlabel = ip6_flowinfo(iph),
+		.flowi6_uid = uid,
+	};
 
 	dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr);
 	rt6_do_redirect(dst, NULL, skb);
@@ -2549,21 +2516,18 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
 }
 EXPORT_SYMBOL_GPL(ip6_redirect);
 
-void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
-			    u32 mark)
+void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb);
 	struct dst_entry *dst;
-	struct flowi6 fl6;
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_iif = LOOPBACK_IFINDEX;
-	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark;
-	fl6.daddr = msg->dest;
-	fl6.saddr = iph->daddr;
-	fl6.flowi6_uid = sock_net_uid(net, NULL);
+	struct flowi6 fl6 = {
+		.flowi6_iif = LOOPBACK_IFINDEX,
+		.flowi6_oif = oif,
+		.daddr = msg->dest,
+		.saddr = iph->daddr,
+		.flowi6_uid = sock_net_uid(net, NULL),
+	};
 
 	dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr);
 	rt6_do_redirect(dst, NULL, skb);
@@ -2734,24 +2698,6 @@ out:
 	return entries > rt_max_size;
 }
 
-static int ip6_convert_metrics(struct net *net, struct fib6_info *rt,
-			       struct fib6_config *cfg)
-{
-	struct dst_metrics *p;
-
-	if (!cfg->fc_mx)
-		return 0;
-
-	p = kzalloc(sizeof(*rt->fib6_metrics), GFP_KERNEL);
-	if (unlikely(!p))
-		return -ENOMEM;
-
-	refcount_set(&p->refcnt, 1);
-	rt->fib6_metrics = p;
-
-	return ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len, p->metrics);
-}
-
 static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 					    struct fib6_config *cfg,
 					    const struct in6_addr *gw_addr,
@@ -3027,13 +2973,17 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (!rt)
 		goto out;
 
+	rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len);
+	if (IS_ERR(rt->fib6_metrics)) {
+		err = PTR_ERR(rt->fib6_metrics);
+		/* Do not leave garbage there. */
+		rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
+		goto out;
+	}
+
 	if (cfg->fc_flags & RTF_ADDRCONF)
 		rt->dst_nocount = true;
 
-	err = ip6_convert_metrics(net, rt, cfg);
-	if (err < 0)
-		goto out;
-
 	if (cfg->fc_flags & RTF_EXPIRES)
 		fib6_set_expires(rt, jiffies +
 				clock_t_to_jiffies(cfg->fc_expires));
@@ -3142,8 +3092,6 @@ install_route:
 	rt->fib6_nh.nh_dev = dev;
 	rt->fib6_table = table;
 
-	cfg->fc_nlinfo.nl_net = dev_net(dev);
-
 	if (idev)
 		in6_dev_put(idev);
 
@@ -3635,23 +3583,23 @@ static void rtmsg_to_fib6_config(struct net *net,
 				 struct in6_rtmsg *rtmsg,
 				 struct fib6_config *cfg)
 {
-	memset(cfg, 0, sizeof(*cfg));
+	*cfg = (struct fib6_config){
+		.fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+			 : RT6_TABLE_MAIN,
+		.fc_ifindex = rtmsg->rtmsg_ifindex,
+		.fc_metric = rtmsg->rtmsg_metric,
+		.fc_expires = rtmsg->rtmsg_info,
+		.fc_dst_len = rtmsg->rtmsg_dst_len,
+		.fc_src_len = rtmsg->rtmsg_src_len,
+		.fc_flags = rtmsg->rtmsg_flags,
+		.fc_type = rtmsg->rtmsg_type,
 
-	cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
-			 : RT6_TABLE_MAIN;
-	cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
-	cfg->fc_metric = rtmsg->rtmsg_metric;
-	cfg->fc_expires = rtmsg->rtmsg_info;
-	cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
-	cfg->fc_src_len = rtmsg->rtmsg_src_len;
-	cfg->fc_flags = rtmsg->rtmsg_flags;
-	cfg->fc_type = rtmsg->rtmsg_type;
-
-	cfg->fc_nlinfo.nl_net = net;
+		.fc_nlinfo.nl_net = net,
 
-	cfg->fc_dst = rtmsg->rtmsg_dst;
-	cfg->fc_src = rtmsg->rtmsg_src;
-	cfg->fc_gateway = rtmsg->rtmsg_gateway;
+		.fc_dst = rtmsg->rtmsg_dst,
+		.fc_src = rtmsg->rtmsg_src,
+		.fc_gateway = rtmsg->rtmsg_gateway,
+	};
 }
 
 int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
@@ -3758,6 +3706,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	if (!f6i)
 		return ERR_PTR(-ENOMEM);
 
+	f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0);
 	f6i->dst_nocount = true;
 	f6i->dst_host = true;
 	f6i->fib6_protocol = RTPROT_KERNEL;
@@ -3800,8 +3749,6 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
 		spin_lock_bh(&rt6_exception_lock);
 		/* remove prefsrc entry */
 		rt->fib6_prefsrc.plen = 0;
-		/* need to update cache as well */
-		rt6_exceptions_remove_prefsrc(rt);
 		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
@@ -4079,8 +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)
@@ -4170,20 +4121,25 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
-			  NULL);
+			  extack);
 	if (err < 0)
 		goto errout;
 
 	err = -EINVAL;
 	rtm = nlmsg_data(nlh);
-	memset(cfg, 0, sizeof(*cfg));
 
-	cfg->fc_table = rtm->rtm_table;
-	cfg->fc_dst_len = rtm->rtm_dst_len;
-	cfg->fc_src_len = rtm->rtm_src_len;
-	cfg->fc_flags = RTF_UP;
-	cfg->fc_protocol = rtm->rtm_protocol;
-	cfg->fc_type = rtm->rtm_type;
+	*cfg = (struct fib6_config){
+		.fc_table = rtm->rtm_table,
+		.fc_dst_len = rtm->rtm_dst_len,
+		.fc_src_len = rtm->rtm_src_len,
+		.fc_flags = RTF_UP,
+		.fc_protocol = rtm->rtm_protocol,
+		.fc_type = rtm->rtm_type,
+
+		.fc_nlinfo.portid = NETLINK_CB(skb).portid,
+		.fc_nlinfo.nlh = nlh,
+		.fc_nlinfo.nl_net = sock_net(skb->sk),
+	};
 
 	if (rtm->rtm_type == RTN_UNREACHABLE ||
 	    rtm->rtm_type == RTN_BLACKHOLE ||
@@ -4199,10 +4155,6 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK);
 
-	cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
-	cfg->fc_nlinfo.nlh = nlh;
-	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
-
 	if (tb[RTA_GATEWAY]) {
 		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
@@ -4815,28 +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,
@@ -4850,7 +4826,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	struct rt6_info *rt;
 	struct sk_buff *skb;
 	struct rtmsg *rtm;
-	struct flowi6 fl6;
+	struct flowi6 fl6 = {};
 	bool fibmatch;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
@@ -4859,7 +4835,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	err = -EINVAL;
-	memset(&fl6, 0, sizeof(fl6));
 	rtm = nlmsg_data(nlh);
 	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
 	fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH);
@@ -5084,7 +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,
@@ -5155,6 +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,
+	},
 	{ }
 };
 
@@ -5178,6 +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)
@@ -5242,6 +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;