ipv6: start using dst_dev_rcu()

Refactor icmpv6_xrlim_allow() and ip6_dst_hoplimit()
so that we acquire rcu_read_lock() a bit longer
to be able to use dst_dev_rcu() instead of dst_dev().

__ip6_rt_update_pmtu() and rt6_do_redirect can directly
use dst_dev_rcu() in sections already holding rcu_read_lock().

Small changes to use dst_dev_net_rcu() in
ip6_default_advmss(), ipv6_sock_ac_join(),
ip6_mc_find_dev() and ndisc_send_skb().

Fixes: 4a6ce2b ("net: introduce a new function dst_dev_put()")
Signed-off-by: Eric Dumazet <[email protected]>
Reviewed-by: David Ahern <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: edumazet

net/ipv6/anycast.c

@@ -104,7 +104,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		rcu_read_lock();
 		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
-			dev = dst_dev(&rt->dst);
+			dev = dst_dev_rcu(&rt->dst);
 			netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
 			ip6_rt_put(rt);
 		} else if (ishost) {

net/ipv6/icmp.c

@@ -209,7 +209,8 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	 * this lookup should be more aggressive (not longer than timeout).
 	 */
 	dst = ip6_route_output(net, sk, fl6);
-	dev = dst_dev(dst);
+	rcu_read_lock();
+	dev = dst_dev_rcu(dst);
 	if (dst->error) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst),
 			      IPSTATS_MIB_OUTNOROUTES);
@@ -224,11 +225,10 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		rcu_read_lock();
 		peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr);
 		res = inet_peer_xrlim_allow(peer, tmo);
-		rcu_read_unlock();
 	}
+	rcu_read_unlock();
 	if (!res)
 		__ICMP6_INC_STATS(net, ip6_dst_idev(dst),
 				  ICMP6_MIB_RATELIMITHOST);

net/ipv6/mcast.c

@@ -180,7 +180,7 @@ static struct net_device *ip6_mc_find_dev(struct net *net,
 		rcu_read_lock();
 		rt = rt6_lookup(net, group, NULL, 0, NULL, 0);
 		if (rt) {
-			dev = dst_dev(&rt->dst);
+			dev = dst_dev_rcu(&rt->dst);
 			dev_hold(dev);
 			ip6_rt_put(rt);
 		}

net/ipv6/ndisc.c

@@ -505,7 +505,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
 
 	ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len);
 
-	dev = dst_dev(dst);
+	dev = dst_dev_rcu(dst);
 	idev = __in6_dev_get(dev);
 	IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
 

net/ipv6/output_core.c

@@ -104,18 +104,20 @@ EXPORT_SYMBOL(ip6_find_1stfragopt);
 int ip6_dst_hoplimit(struct dst_entry *dst)
 {
 	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
+
+	rcu_read_lock();
 	if (hoplimit == 0) {
-		struct net_device *dev = dst_dev(dst);
+		struct net_device *dev = dst_dev_rcu(dst);
 		struct inet6_dev *idev;
 
-		rcu_read_lock();
 		idev = __in6_dev_get(dev);
 		if (idev)
 			hoplimit = READ_ONCE(idev->cnf.hop_limit);
 		else
 			hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit);
-		rcu_read_unlock();
 	}
+	rcu_read_unlock();
+
 	return hoplimit;
 }
 EXPORT_SYMBOL(ip6_dst_hoplimit);

net/ipv6/route.c

@@ -2943,7 +2943,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 		if (res.f6i->nh) {
 			struct fib6_nh_match_arg arg = {
-				.dev = dst_dev(dst),
+				.dev = dst_dev_rcu(dst),
 				.gw = &rt6->rt6i_gateway,
 			};
 
@@ -3238,15 +3238,14 @@ EXPORT_SYMBOL_GPL(ip6_sk_redirect);
 
 static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 {
-	struct net_device *dev = dst_dev(dst);
 	unsigned int mtu = dst_mtu(dst);
 	struct net *net;
 
 	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
 
 	rcu_read_lock();
 
-	net = dev_net_rcu(dev);
+	net = dst_dev_net_rcu(dst);
 	if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
 		mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
 
@@ -4301,7 +4300,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	if (res.f6i->nh) {
 		struct fib6_nh_match_arg arg = {
-			.dev = dst_dev(dst),
+			.dev = dst_dev_rcu(dst),
 			.gw = &rt->rt6i_gateway,
 		};