[PATCH net-next v3 2/2] ipv4: snapshot dst.dev in ip_rt_send_redirect() and ip_rt_get_source()

[xuanqiang . luo]

From: Xuanqiang Luo <luoxuanqiang@xxxxxxxxxx>

rt_flush_dev() can replace rt->dst.dev with blackhole_netdev while RCU
readers are running.  ip_rt_send_redirect() and ip_rt_get_source() both
read rt->dst.dev more than once and use the results in one operation.

If rt->dst.dev changes between those reads, the operation can use values
from two devices.  For example, ip_rt_send_redirect() can use in_dev from
the old device and the L3 master ifindex from blackhole_netdev.

Read rt->dst.dev once in these two functions and use the snapshot for the
later device accesses.

Signed-off-by: Xuanqiang Luo <luoxuanqiang@xxxxxxxxxx>
---
 net/ipv4/route.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b668375df71e2..4fed07cae7da2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -874,21 +874,23 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 {
 	struct rtable *rt = skb_rtable(skb);
 	struct in_device *in_dev;
+	struct net_device *dev;
 	struct inet_peer *peer;
-	struct net *net;
 	int log_martians;
+	struct net *net;
 	int vif;
 
 	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(rt->dst.dev);
+	dev = dst_dev_rcu(&rt->dst);
+	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
 		rcu_read_unlock();
 		return;
 	}
 	log_martians = IN_DEV_LOG_MARTIANS(in_dev);
-	vif = l3mdev_master_ifindex_rcu(rt->dst.dev);
+	vif = l3mdev_master_ifindex_rcu(dev);
 
-	net = dev_net(rt->dst.dev);
+	net = dev_net_rcu(dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif);
 	if (!peer) {
 		rcu_read_unlock();
@@ -1287,29 +1289,32 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 {
 	__be32 src;
 
-	if (rt_is_output_route(rt))
+	rcu_read_lock();
+	if (rt_is_output_route(rt)) {
 		src = ip_hdr(skb)->saddr;
-	else {
-		struct fib_result res;
+	} else {
+		struct net_device *dev = dst_dev_rcu(&rt->dst);
+		struct net *net = dev_net_rcu(dev);
 		struct iphdr *iph = ip_hdr(skb);
+		struct fib_result res;
 		struct flowi4 fl4 = {
 			.daddr = iph->daddr,
 			.saddr = iph->saddr,
 			.flowi4_dscp = ip4h_dscp(iph),
-			.flowi4_oif = rt->dst.dev->ifindex,
+			.flowi4_oif = dev->ifindex,
 			.flowi4_iif = skb->dev->ifindex,
 			.flowi4_mark = skb->mark,
 		};
 
-		rcu_read_lock();
-		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
-			src = fib_result_prefsrc(dev_net(rt->dst.dev), &res);
+		if (fib_lookup(net, &fl4, &res, 0) == 0)
+			src = fib_result_prefsrc(net, &res);
 		else
-			src = inet_select_addr(rt->dst.dev,
+			src = inet_select_addr(dev,
 					       rt_nexthop(rt, iph->daddr),
 					       RT_SCOPE_UNIVERSE);
-		rcu_read_unlock();
 	}
+	rcu_read_unlock();
+
 	memcpy(addr, &src, 4);
 }
 
-- 
2.43.0