bpf, vxlan, geneve, gre: fix usage of dst_cache on xmit

The assumptions from commit 0c1d70af924b ("net: use dst_cache for vxlan
device"), 468dfffcd762 ("geneve: add dst caching support") and 3c1cb4d2604c
("net/ipv4: add dst cache support for gre lwtunnels") on dst_cache usage
when ip_tunnel_info is used is unfortunately not always valid as assumed.

While it seems correct for ip_tunnel_info front-ends such as OVS, eBPF
however can fill in ip_tunnel_info for consumers like vxlan, geneve or gre
with different remote dsts, tos, etc, therefore they cannot be assumed as
packet independent.

Right now vxlan, geneve, gre would cache the dst for eBPF and every packet
would reuse the same entry that was first created on the initial route
lookup. eBPF doesn't store/cache the ip_tunnel_info, so each skb may have
a different one.

Fix it by adding a flag that checks the ip_tunnel_info. Also the !tos test
in vxlan needs to be handeled differently in this context as it is currently
inferred from ip_tunnel_info as well if present. ip_tunnel_dst_cache_usable()
helper is added for the three tunnel cases, which checks if we can use dst
cache.

Fixes: 0c1d70af924b ("net: use dst_cache for vxlan device")
Fixes: 468dfffcd762 ("geneve: add dst caching support")
Fixes: 3c1cb4d2604c ("net/ipv4: add dst cache support for gre lwtunnels")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 7 insertions, 5 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 012a10c2da94..a66dc03c261f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1870,7 +1870,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
 	info = &md->u.tun_info;
 	info->mode = IP_TUNNEL_INFO_TX;
 
-	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM;
+	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
 	if (flags & BPF_F_DONT_FRAGMENT)
 		info->key.tun_flags |= TUNNEL_DONT_FRAGMENT;
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 202437d6087b..31936d387cfd 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -527,11 +527,12 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel_info *tun_info;
 	const struct ip_tunnel_key *key;
+	struct rtable *rt = NULL;
 	struct flowi4 fl;
-	struct rtable *rt;
 	int min_headroom;
 	int tunnel_hlen;
 	__be16 df, flags;
+	bool use_cache;
 	int err;
 
 	tun_info = skb_tunnel_info(skb);
@@ -540,13 +541,14 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto err_free_skb;
 
 	key = &tun_info->key;
-	rt = !skb->mark ? dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr) :
-			 NULL;
+	use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);
+	if (use_cache)
+		rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr);
 	if (!rt) {
 		rt = gre_get_rt(skb, dev, &fl, key);
 		if (IS_ERR(rt))
 				goto err_free_skb;
-		if (!skb->mark)
+		if (use_cache)
 			dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst,
 					  fl.saddr);
 	}