netdev - [PATCH net-next v5 07/11] net: tunnel: convert ip_md_tunnel

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20260113162954.5948-8-mmietus97@yahoo.com>
Date: Tue, 13 Jan 2026 17:29:50 +0100
From: Marek Mietus <mmietus97@...oo.com>
To: netdev@...r.kernel.org,
	sd@...asysnail.net,
	kuba@...nel.org
Cc: Jason@...c4.com,
	Marek Mietus <mmietus97@...oo.com>
Subject: [PATCH net-next v5 07/11] net: tunnel: convert ip_md_tunnel_xmit to use a noref dst when possible

ip_md_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_md_tunnel_xmit.

Signed-off-by: Marek Mietus <mmietus97@...oo.com>
---
 net/ipv4/ip_tunnel.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 8a0c611ab1bf..ab10759dd2e4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -609,7 +609,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	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);
 	if (!rt) {
 		rt = ip_route_output_key(tunnel->net, &fl4);
 		if (IS_ERR(rt)) {
@@ -617,11 +617,12 @@ void ip_md_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);
 	}
 	if (rt->dst.dev == dev) {
-		ip_rt_put(rt);
+		if (!use_cache)
+			ip_rt_put(rt);
 		DEV_STATS_INC(dev, collisions);
 		goto tx_error;
 	}
@@ -630,7 +631,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		df = htons(IP_DF);
 	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen,
 			    key->u.ipv4.dst, true)) {
-		ip_rt_put(rt);
+		if (!use_cache)
+			ip_rt_put(rt);
 		goto tx_error;
 	}
 
@@ -647,7 +649,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
 	if (skb_cow_head(skb, headroom)) {
-		ip_rt_put(rt);
+		if (!use_cache)
+			ip_rt_put(rt);
 		goto tx_dropped;
 	}
 
@@ -655,7 +658,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)), 0);
-	ip_rt_put(rt);
+	if (!use_cache)
+		ip_rt_put(rt);
 	return;
 tx_error:
 	DEV_STATS_INC(dev, tx_errors);
-- 
2.51.0