netns xfrm: deal with dst entries in netns

GC is non-existent in netns, so after you hit GC threshold, no new
dst entries will be created until someone triggers cleanup in init_net.

Make xfrm4_dst_ops and xfrm6_dst_ops per-netns.
This is not done in a generic way, because it woule waste
(AF_MAX - 2) * sizeof(struct dst_ops) bytes per-netns.

Reorder GC threshold initialization so it'd be done before registering
XFRM policies.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 56 insertions, 3 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d2c8cb57ee4c..0ecb16a9a883 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1309,15 +1309,28 @@ static inline int xfrm_get_tos(struct flowi *fl, int family)
 	return tos;
 }
 
-static inline struct xfrm_dst *xfrm_alloc_dst(int family)
+static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct dst_ops *dst_ops;
 	struct xfrm_dst *xdst;
 
 	if (!afinfo)
 		return ERR_PTR(-EINVAL);
 
-	xdst = dst_alloc(afinfo->dst_ops) ?: ERR_PTR(-ENOBUFS);
+	switch (family) {
+	case AF_INET:
+		dst_ops = &net->xfrm.xfrm4_dst_ops;
+		break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	case AF_INET6:
+		dst_ops = &net->xfrm.xfrm6_dst_ops;
+		break;
+#endif
+	default:
+		BUG();
+	}
+	xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS);
 
 	xfrm_policy_put_afinfo(afinfo);
 
@@ -1366,6 +1379,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 					    struct flowi *fl,
 					    struct dst_entry *dst)
 {
+	struct net *net = xp_net(policy);
 	unsigned long now = jiffies;
 	struct net_device *dev;
 	struct dst_entry *dst_prev = NULL;
@@ -1389,7 +1403,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 	dst_hold(dst);
 
 	for (; i < nx; i++) {
-		struct xfrm_dst *xdst = xfrm_alloc_dst(family);
+		struct xfrm_dst *xdst = xfrm_alloc_dst(net, family);
 		struct dst_entry *dst1 = &xdst->u.dst;
 
 		err = PTR_ERR(xdst);
@@ -2279,6 +2293,7 @@ EXPORT_SYMBOL(xfrm_bundle_ok);
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
+	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2302,6 +2317,27 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 		xfrm_policy_afinfo[afinfo->family] = afinfo;
 	}
 	write_unlock_bh(&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 defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+		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);
@@ -2332,6 +2368,22 @@ 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;
+
+	read_lock_bh(&xfrm_policy_afinfo_lock);
+	afinfo = xfrm_policy_afinfo[AF_INET];
+	if (afinfo)
+		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	afinfo = xfrm_policy_afinfo[AF_INET6];
+	if (afinfo)
+		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
+#endif
+	read_unlock_bh(&xfrm_policy_afinfo_lock);
+}
+
 static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family)
 {
 	struct xfrm_policy_afinfo *afinfo;
@@ -2494,6 +2546,7 @@ 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;