[PATCH net-next 3/7] net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup

[David Ahern <dsa@cumulusnetworks.com>]

Convert inet_rtm_getroute to use ip_route_input_rcu and
ip_route_output_key_hash_rcu passing the fib_result arg to both.
The rcu lock is held through the creation of the response, so the
rtable/dst does not need to be attached to the skb and is passed
to rt_fill_info directly.

In converting from ip_route_output_key to ip_route_output_key_hash_rcu
the xfrm_lookup_route in ip_route_output_flow is dropped since
flowi4_proto is not set for a route get request. Also, the flow struct
adjustments from __ip_route_output_key_hash are added to make sure
the route request logic is not altered by the conversion.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 net/ipv4/route.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3142cd802e79..03ddc03c185a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2467,11 +2467,11 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 }
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
+/* called with rcu_read_lock held */
 static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq, int event)
+			u32 seq, int event, struct rtable *rt)
 {
-	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
@@ -2585,10 +2585,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	struct fib_result res = {};
 	struct rtable *rt = NULL;
 	struct flowi4 fl4;
 	__be32 dst = 0;
 	__be32 src = 0;
+	__u8 tos;
 	u32 iif;
 	int err;
 	int mark;
@@ -2630,15 +2632,20 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
 	fl4.saddr = src;
-	fl4.flowi4_tos = rtm->rtm_tos;
+	tos = rtm->rtm_tos & (IPTOS_RT_MASK | RTO_ONLINK);
+	fl4.flowi4_tos = tos & IPTOS_RT_MASK;
+	fl4.flowi4_scope = ((tos & RTO_ONLINK) ?
+				RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
 
+	rcu_read_lock();
+
 	if (iif) {
 		struct net_device *dev;
 
-		dev = __dev_get_by_index(net, iif);
+		dev = dev_get_by_index_rcu(net, iif);
 		if (!dev) {
 			err = -ENODEV;
 			goto errout_free;
@@ -2647,14 +2654,16 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		skb->protocol	= htons(ETH_P_IP);
 		skb->dev	= dev;
 		skb->mark	= mark;
-		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
+		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
+					 dev, &res);
 
 		rt = skb_rtable(skb);
 		if (err == 0 && rt->dst.error)
 			err = -rt->dst.error;
 	} else {
-		rt = ip_route_output_key(net, &fl4);
+		fl4.flowi4_iif = LOOPBACK_IFINDEX;
 
+		rt = ip_route_output_key_hash_rcu(net, &fl4, &res, -1);
 		err = 0;
 		if (IS_ERR(rt))
 			err = PTR_ERR(rt);
@@ -2663,7 +2672,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	if (err)
 		goto errout_free;
 
-	skb_dst_set(skb, &rt->dst);
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
@@ -2672,15 +2680,18 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
 			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			   RTM_NEWROUTE);
+			   RTM_NEWROUTE, rt);
 	if (err < 0)
 		goto errout_free;
 
+	rcu_read_unlock();
+
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
 	return err;
 
 errout_free:
+	rcu_read_unlock();
 	kfree_skb(skb);
 	goto errout;
 }
-- 
2.1.4