net: use dst_cache for vxlan device
In case of UDP traffic with datagram length
below MTU this give about 3% performance increase
when tunneling over ipv4 and about 70% when
tunneling over ipv6.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Suggested-and-acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0a23c64..ad67303 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -480,6 +480,8 @@
rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
if (!rd)
return 0;
+
+ dst_cache_reset(&rd->dst_cache);
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
@@ -501,6 +503,12 @@
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
+
+ if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
+ kfree(rd);
+ return -ENOBUFS;
+ }
+
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
@@ -749,8 +757,10 @@
struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
struct vxlan_rdst *rd, *nd;
- list_for_each_entry_safe(rd, nd, &f->remotes, list)
+ list_for_each_entry_safe(rd, nd, &f->remotes, list) {
+ dst_cache_destroy(&rd->dst_cache);
kfree(rd);
+ }
kfree(f);
}
@@ -1754,11 +1764,24 @@
static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
struct sk_buff *skb, int oif, u8 tos,
- __be32 daddr, __be32 *saddr)
+ __be32 daddr, __be32 *saddr,
+ struct dst_cache *dst_cache,
+ struct ip_tunnel_info *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 (dst_cache && !skb->mark && (!tos || info)) {
+ use_cache = true;
+ rt = dst_cache_get_ip4(dst_cache, saddr);
+ if (rt)
+ return rt;
+ }
+
memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_oif = oif;
fl4.flowi4_tos = RT_TOS(tos);
@@ -1768,8 +1791,11 @@
fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
rt = ip_route_output_key(vxlan->net, &fl4);
- if (!IS_ERR(rt))
+ if (!IS_ERR(rt)) {
*saddr = fl4.saddr;
+ if (use_cache)
+ dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+ }
return rt;
}
@@ -1777,12 +1803,21 @@
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct sk_buff *skb, int oif,
const struct in6_addr *daddr,
- struct in6_addr *saddr)
+ struct in6_addr *saddr,
+ struct dst_cache *dst_cache)
{
+ bool use_cache = false;
struct dst_entry *ndst;
struct flowi6 fl6;
int err;
+ if (dst_cache && !skb->mark) {
+ use_cache = true;
+ ndst = dst_cache_get_ip6(dst_cache, saddr);
+ if (ndst)
+ return ndst;
+ }
+
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.daddr = *daddr;
@@ -1797,6 +1832,8 @@
return ERR_PTR(err);
*saddr = fl6.saddr;
+ if (use_cache)
+ dst_cache_set_ip6(dst_cache, ndst, saddr);
return ndst;
}
#endif
@@ -1938,7 +1975,8 @@
rt = vxlan_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
- dst->sin.sin_addr.s_addr, &saddr);
+ dst->sin.sin_addr.s_addr, &saddr,
+ rdst ? &rdst->dst_cache : NULL, info);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n",
&dst->sin.sin_addr.s_addr);
@@ -1990,7 +2028,8 @@
ndst = vxlan6_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0,
- &dst->sin6.sin6_addr, &saddr);
+ &dst->sin6.sin6_addr, &saddr,
+ rdst ? &rdst->dst_cache : NULL);
if (IS_ERR(ndst)) {
netdev_dbg(dev, "no route to %pI6\n",
&dst->sin6.sin6_addr);
@@ -2331,7 +2370,7 @@
return -EINVAL;
rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
info->key.u.ipv4.dst,
- &info->key.u.ipv4.src);
+ &info->key.u.ipv4.src, NULL, info);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
@@ -2343,7 +2382,7 @@
return -EINVAL;
ndst = vxlan6_get_route(vxlan, skb, 0,
&info->key.u.ipv6.dst,
- &info->key.u.ipv6.src);
+ &info->key.u.ipv6.src, NULL);
if (IS_ERR(ndst))
return PTR_ERR(ndst);
dst_release(ndst);