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>
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 36db4cf..6a0cbbe 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -775,10 +775,10 @@
struct flowi4 *fl4,
struct ip_tunnel_info *info)
{
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
struct dst_cache *dst_cache;
struct rtable *rt = NULL;
- bool use_cache = true;
__u8 tos;
memset(fl4, 0, sizeof(*fl4));
@@ -804,7 +804,6 @@
dst_cache = &geneve->dst_cache;
}
- use_cache = use_cache && !skb->mark;
if (use_cache) {
rt = dst_cache_get_ip4(dst_cache, &fl4->saddr);
if (rt)
@@ -832,11 +831,11 @@
struct flowi6 *fl6,
struct ip_tunnel_info *info)
{
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
struct geneve_sock *gs6 = geneve->sock6;
struct dst_entry *dst = NULL;
struct dst_cache *dst_cache;
- bool use_cache = true;
__u8 prio;
memset(fl6, 0, sizeof(*fl6));
@@ -862,7 +861,6 @@
dst_cache = &geneve->dst_cache;
}
- use_cache = use_cache && !skb->mark;
if (use_cache) {
dst = dst_cache_get_ip6(dst_cache, &fl6->saddr);
if (dst)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index fc998a3..7294a45 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1756,17 +1756,15 @@
struct sk_buff *skb, int oif, u8 tos,
__be32 daddr, __be32 *saddr,
struct dst_cache *dst_cache,
- struct ip_tunnel_info *info)
+ const struct ip_tunnel_info *info)
{
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct rtable *rt = NULL;
- bool use_cache = false;
struct flowi4 fl4;
- /* when the ip_tunnel_info is availble, the tos used for lookup is
- * packet independent, so we can use the cache
- */
- if (!skb->mark && (!tos || info)) {
- use_cache = true;
+ if (tos && !info)
+ use_cache = false;
+ if (use_cache) {
rt = dst_cache_get_ip4(dst_cache, saddr);
if (rt)
return rt;
@@ -1794,13 +1792,15 @@
struct sk_buff *skb, int oif,
const struct in6_addr *daddr,
struct in6_addr *saddr,
- struct dst_cache *dst_cache)
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info)
{
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct dst_entry *ndst;
struct flowi6 fl6;
int err;
- if (!skb->mark) {
+ if (use_cache) {
ndst = dst_cache_get_ip6(dst_cache, saddr);
if (ndst)
return ndst;
@@ -1820,7 +1820,7 @@
return ERR_PTR(err);
*saddr = fl6.saddr;
- if (!skb->mark)
+ if (use_cache)
dst_cache_set_ip6(dst_cache, ndst, saddr);
return ndst;
}
@@ -2018,7 +2018,7 @@
ndst = vxlan6_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0,
&dst->sin6.sin6_addr, &saddr,
- dst_cache);
+ dst_cache, info);
if (IS_ERR(ndst)) {
netdev_dbg(dev, "no route to %pI6\n",
&dst->sin6.sin6_addr);
@@ -2387,7 +2387,7 @@
return -EINVAL;
ndst = vxlan6_get_route(vxlan, skb, 0,
&info->key.u.ipv6.dst,
- &info->key.u.ipv6.src, NULL);
+ &info->key.u.ipv6.src, NULL, info);
if (IS_ERR(ndst))
return PTR_ERR(ndst);
dst_release(ndst);