xfrm: dst_entries_init() per-net dst_ops

Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops
templates; their dst_entries counters will never be used.  Move the
xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to
xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init
and dst_entries_destroy for each net namespace.

The ipv4 and ipv6 xfrms each create dst_ops template, and perform
dst_entries_init on the templates.  The template values are copied to each
net namespace's xfrm.xfrm*_dst_ops.  The problem there is the dst_ops
pcpuc_entries field is a percpu counter and cannot be used correctly by
simply copying it to another object.

The result of this is a very subtle bug; changes to the dst entries
counter from one net namespace may sometimes get applied to a different
net namespace dst entries counter.  This is because of how the percpu
counter works; it has a main count field as well as a pointer to the
percpu variables.  Each net namespace maintains its own main count
variable, but all point to one set of percpu variables.  When any net
namespace happens to change one of the percpu variables to outside its
small batch range, its count is moved to the net namespace's main count
variable.  So with multiple net namespaces operating concurrently, the
dst_ops entries counter can stray from the actual value that it should
be; if counts are consistently moved from one net namespace to another
(which my testing showed is likely), then one net namespace winds up
with a negative dst_ops count while another winds up with a continually
increasing count, eventually reaching its gc_thresh limit, which causes
all new traffic on the net namespace to fail with -ENOBUFS.

Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

1 files changed, 0 insertions, 38 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 94af3d0..bacd30b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2807,7 +2807,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
-	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2838,26 +2837,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 	}
 	spin_unlock(&xfrm_policy_afinfo_lock);
 
-	rtnl_lock();
-	for_each_net(net) {
-		struct dst_ops *xfrm_dst_ops;
-
-		switch (afinfo->family) {
-		case AF_INET:
-			xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
-			break;
-#if IS_ENABLED(CONFIG_IPV6)
-		case AF_INET6:
-			xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
-			break;
-#endif
-		default:
-			BUG();
-		}
-		*xfrm_dst_ops = *afinfo->dst_ops;
-	}
-	rtnl_unlock();
-
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_register_afinfo);
@@ -2893,22 +2872,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
-	struct xfrm_policy_afinfo *afinfo;
-
-	rcu_read_lock();
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]);
-	if (afinfo)
-		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if IS_ENABLED(CONFIG_IPV6)
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]);
-	if (afinfo)
-		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
-#endif
-	rcu_read_unlock();
-}
-
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -3057,7 +3020,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_policy_init(net);
 	if (rv < 0)
 		goto out_policy;
-	xfrm_dst_ops_init(net);
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;