ip_tunnel_xmit unnecessarily references the dst_entry from the
dst_cache when interacting with the cache.

Reduce this overhead by avoiding the redundant refcount increments.

This is only possible in flows where the cache is used. Otherwise, we
fall-back to a referenced dst.

This change is safe since ipv4 supports noref xmit under RCU which is
already the case for ip_tunnel_xmit.

Signed-off-by: Marek Mietus <mmietus97@yahoo.com>
---
 net/ipv4/ip_tunnel.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ab10759dd2e4..fa34e6cfbe35 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -681,6 +681,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct rtable *rt = NULL;		/* Route to the other host */
 	__be16 payload_protocol;
 	bool use_cache = false;
+	bool noref = true;
 	struct flowi4 fl4;
 	bool md = false;
 	bool connected;
@@ -775,11 +776,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (connected && md) {
 		use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);
 		if (use_cache)
-			rt = dst_cache_get_ip4(&tun_info->dst_cache,
-					       &fl4.saddr);
+			rt = dst_cache_get_ip4_rcu(&tun_info->dst_cache,
+						   &fl4.saddr);
 	} else {
-		rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache,
-						&fl4.saddr) : NULL;
+		rt = connected ? dst_cache_get_ip4_rcu(&tunnel->dst_cache,
+						       &fl4.saddr) : NULL;
 	}
 
 	if (!rt) {
@@ -790,15 +791,18 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 		if (use_cache)
-			dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst,
-					  fl4.saddr);
+			dst_cache_steal_ip4(&tun_info->dst_cache, &rt->dst,
+					    fl4.saddr);
 		else if (!md && connected)
-			dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst,
-					  fl4.saddr);
+			dst_cache_steal_ip4(&tunnel->dst_cache, &rt->dst,
+					    fl4.saddr);
+		else
+			noref = false;
 	}
 
 	if (rt->dst.dev == dev) {
-		ip_rt_put(rt);
+		if (!noref)
+			ip_rt_put(rt);
 		DEV_STATS_INC(dev, collisions);
 		goto tx_error;
 	}
@@ -808,7 +812,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		df |= (inner_iph->frag_off & htons(IP_DF));
 
 	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
-		ip_rt_put(rt);
+		if (!noref)
+			ip_rt_put(rt);
 		goto tx_error;
 	}
 
@@ -839,7 +844,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 
 	if (skb_cow_head(skb, max_headroom)) {
-		ip_rt_put(rt);
+		if (!noref)
+			ip_rt_put(rt);
 		DEV_STATS_INC(dev, tx_dropped);
 		kfree_skb(skb);
 		return;
@@ -849,7 +855,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)), 0);
-	ip_rt_put(rt);
+	if (!noref)
+		ip_rt_put(rt);
 	return;
 
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.51.0