ip_tunnel: replace dst_cache with generic implementation

The current ip_tunnel cache implementation is prone to a race
that will cause the wrong dst to be cached on cuncurrent dst cache
miss and ip tunnel update via netlink.

Replacing with the generic implementation fix the issue.

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>
This commit is contained in:
Paolo Abeni 2016-02-12 15:43:55 +01:00 committed by David S. Miller
parent 607f725f6f
commit e09acddf87
4 changed files with 25 additions and 80 deletions

View File

@ -13,6 +13,7 @@
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/lwtunnel.h>
#include <net/dst_cache.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
@ -85,11 +86,6 @@ struct ip_tunnel_prl_entry {
struct rcu_head rcu_head;
};
struct ip_tunnel_dst {
struct dst_entry __rcu *dst;
__be32 saddr;
};
struct metadata_dst;
struct ip_tunnel {
@ -108,7 +104,7 @@ struct ip_tunnel {
int tun_hlen; /* Precalculated header length */
int mlink;
struct ip_tunnel_dst __percpu *dst_cache;
struct dst_cache dst_cache;
struct ip_tunnel_parm parms;
@ -247,7 +243,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
void ip_tunnel_setup(struct net_device *dev, int net_id);
void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
int ip_tunnel_encap_setup(struct ip_tunnel *t,
struct ip_tunnel_encap *ipencap);

View File

@ -186,6 +186,7 @@ config NET_IPGRE_DEMUX
config NET_IP_TUNNEL
tristate
select DST_CACHE
default n
config NET_IPGRE

View File

@ -68,61 +68,6 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote)
IP_TNL_HASH_BITS);
}
static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
struct dst_entry *dst, __be32 saddr)
{
struct dst_entry *old_dst;
dst_clone(dst);
old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
dst_release(old_dst);
idst->saddr = saddr;
}
static noinline void tunnel_dst_set(struct ip_tunnel *t,
struct dst_entry *dst, __be32 saddr)
{
__tunnel_dst_set(raw_cpu_ptr(t->dst_cache), dst, saddr);
}
static void tunnel_dst_reset(struct ip_tunnel *t)
{
tunnel_dst_set(t, NULL, 0);
}
void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
{
int i;
for_each_possible_cpu(i)
__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0);
}
EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
static struct rtable *tunnel_rtable_get(struct ip_tunnel *t,
u32 cookie, __be32 *saddr)
{
struct ip_tunnel_dst *idst;
struct dst_entry *dst;
rcu_read_lock();
idst = raw_cpu_ptr(t->dst_cache);
dst = rcu_dereference(idst->dst);
if (dst && !atomic_inc_not_zero(&dst->__refcnt))
dst = NULL;
if (dst) {
if (!dst->obsolete || dst->ops->check(dst, cookie)) {
*saddr = idst->saddr;
} else {
tunnel_dst_reset(t);
dst_release(dst);
dst = NULL;
}
}
rcu_read_unlock();
return (struct rtable *)dst;
}
static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
{
@ -381,7 +326,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst,
fl4.saddr);
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
@ -729,7 +675,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
goto tx_error;
rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) :
NULL;
if (!rt) {
rt = ip_route_output_key(tunnel->net, &fl4);
@ -739,7 +686,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
if (connected)
tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst,
fl4.saddr);
}
if (rt->dst.dev == dev) {
@ -836,7 +784,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
if (set_mtu)
dev->mtu = mtu;
}
ip_tunnel_dst_reset_all(t);
dst_cache_reset(&t->dst_cache);
netdev_state_change(dev);
}
@ -961,7 +909,7 @@ static void ip_tunnel_dev_free(struct net_device *dev)
struct ip_tunnel *tunnel = netdev_priv(dev);
gro_cells_destroy(&tunnel->gro_cells);
free_percpu(tunnel->dst_cache);
dst_cache_destroy(&tunnel->dst_cache);
free_percpu(dev->tstats);
free_netdev(dev);
}
@ -1155,15 +1103,15 @@ int ip_tunnel_init(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;
tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
if (!tunnel->dst_cache) {
err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
if (err) {
free_percpu(dev->tstats);
return -ENOMEM;
return err;
}
err = gro_cells_init(&tunnel->gro_cells, dev);
if (err) {
free_percpu(tunnel->dst_cache);
dst_cache_destroy(&tunnel->dst_cache);
free_percpu(dev->tstats);
return err;
}
@ -1193,7 +1141,7 @@ void ip_tunnel_uninit(struct net_device *dev)
if (itn->fb_tunnel_dev != dev)
ip_tunnel_del(itn, netdev_priv(dev));
ip_tunnel_dst_reset_all(tunnel);
dst_cache_reset(&tunnel->dst_cache);
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);

View File

@ -475,7 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
ipip6_tunnel_unlink(sitn, tunnel);
ipip6_tunnel_del_prl(tunnel, NULL);
}
ip_tunnel_dst_reset_all(tunnel);
dst_cache_reset(&tunnel->dst_cache);
dev_put(dev);
}
@ -1093,7 +1093,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
t->parms.link = p->link;
ipip6_tunnel_bind_dev(t->dev);
}
ip_tunnel_dst_reset_all(t);
dst_cache_reset(&t->dst_cache);
netdev_state_change(t->dev);
}
@ -1124,7 +1124,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
t->ip6rd.relay_prefix = relay_prefix;
t->ip6rd.prefixlen = ip6rd->prefixlen;
t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
ip_tunnel_dst_reset_all(t);
dst_cache_reset(&t->dst_cache);
netdev_state_change(t->dev);
return 0;
}
@ -1278,7 +1278,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
break;
}
ip_tunnel_dst_reset_all(t);
dst_cache_reset(&t->dst_cache);
netdev_state_change(dev);
break;
@ -1339,7 +1339,7 @@ static void ipip6_dev_free(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
free_percpu(tunnel->dst_cache);
dst_cache_destroy(&tunnel->dst_cache);
free_percpu(dev->tstats);
free_netdev(dev);
}
@ -1372,6 +1372,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
static int ipip6_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int err;
tunnel->dev = dev;
tunnel->net = dev_net(dev);
@ -1382,10 +1383,10 @@ static int ipip6_tunnel_init(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;
tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
if (!tunnel->dst_cache) {
err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
if (err) {
free_percpu(dev->tstats);
return -ENOMEM;
return err;
}
return 0;