Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Matthias May <matthias.may@westermo.com>
To:     <netdev@vger.kernel.org>
CC:     <davem@davemloft.net>, <yoshfuji@linux-ipv6.org>,
        <dsahern@kernel.org>, <edumazet@google.com>, <kuba@kernel.org>,
        <pabeni@redhat.com>, <linux-kernel@vger.kernel.org>,
        Matthias May <matthias.may@westermo.com>
Subject: [PATCH net-next v2] ip_tunnel: allow to inherit from VLAN encapsulated IP frames
Date:   Wed, 6 Jul 2022 18:00:22 +0200
Message-ID: <20220706160021.10710-1-matthias.may@westermo.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
Precedence: bulk

The current code allows to inherit the TOS, TTL, DF from the payload
when skb->protocol is ETH_P_IP or ETH_P_IPV6.
However when the payload is VLAN encapsulated (e.g because the tunnel
is of type GRETAP), then this inheriting does not work, because the
visible skb->protocol is of type ETH_P_8021Q.

Add a check on ETH_P_8021Q and subsequently check the payload protocol.

Signed-off-by: Matthias May <matthias.may@westermo.com>
---
v1 -> v2:
 - Add support for ETH_P_8021AD as suggested by Jakub Kicinski.
---
 net/ipv4/ip_tunnel.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 94017a8c3994..bdcc0f1e83c8 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -648,6 +648,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	u8 tos, ttl;
 	__be32 dst;
 	__be16 df;
+	__be16 *payload_protocol;
+
+	if (skb->protocol == htons(ETH_P_8021Q) ||
+	    skb->protocol == htons(ETH_P_8021AD))
+		payload_protocol = (__be16 *)(skb->head + skb->network_header - 2);
+	else
+		payload_protocol = &skb->protocol;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
@@ -670,13 +677,12 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			dst = tun_info->key.u.ipv4.dst;
 			md = true;
 			connected = true;
-		}
-		else if (skb->protocol == htons(ETH_P_IP)) {
+		} else if (*payload_protocol == htons(ETH_P_IP)) {
 			rt = skb_rtable(skb);
 			dst = rt_nexthop(rt, inner_iph->daddr);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6)) {
+		else if (*payload_protocol == htons(ETH_P_IPV6)) {
 			const struct in6_addr *addr6;
 			struct neighbour *neigh;
 			bool do_tx_error_icmp;
@@ -716,10 +722,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	tos = tnl_params->tos;
 	if (tos & 0x1) {
 		tos &= ~0x1;
-		if (skb->protocol == htons(ETH_P_IP)) {
+		if (*payload_protocol == htons(ETH_P_IP)) {
 			tos = inner_iph->tos;
 			connected = false;
-		} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (*payload_protocol == htons(ETH_P_IPV6)) {
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 			connected = false;
 		}
@@ -765,7 +771,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+	if (*payload_protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
 		df |= (inner_iph->frag_off & htons(IP_DF));
 
 	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
@@ -786,10 +792,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
 	ttl = tnl_params->ttl;
 	if (ttl == 0) {
-		if (skb->protocol == htons(ETH_P_IP))
+		if (*payload_protocol == htons(ETH_P_IP))
 			ttl = inner_iph->ttl;
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6))
+		else if (*payload_protocol == htons(ETH_P_IPV6))
 			ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
 #endif
 		else
-- 
2.35.1