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, 14 insertions, 11 deletions

diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 7254e3f899a7..dbdc696f5fc5 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -24,7 +24,6 @@
 #include <net/mip6.h>
 #endif
 
-static struct dst_ops xfrm6_dst_ops;
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
 
 static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
@@ -224,8 +223,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 
 static inline int xfrm6_garbage_collect(struct dst_ops *ops)
 {
-        xfrm6_policy_afinfo.garbage_collect(&init_net);
-        return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2);
+        struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
+
+        xfrm6_policy_afinfo.garbage_collect(net);
+        return (atomic_read(&ops->entries) > ops->gc_thresh * 2);
 }
 
 static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -310,7 +311,7 @@ static void xfrm6_policy_fini(void)
 static struct ctl_table xfrm6_policy_table[] = {
         {
                 .procname       = "xfrm6_gc_thresh",
-                .data           = &xfrm6_dst_ops.gc_thresh,
+                .data           = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = proc_dointvec,
@@ -326,13 +327,6 @@ int __init xfrm6_init(void)
         int ret;
         unsigned int gc_thresh;
 
-        ret = xfrm6_policy_init();
-        if (ret)
-                goto out;
-
-        ret = xfrm6_state_init();
-        if (ret)
-                goto out_policy;
         /*
          * We need a good default value for the xfrm6 gc threshold.
          * In ipv4 we set it to the route hash table size * 8, which
@@ -346,6 +340,15 @@ int __init xfrm6_init(void)
          */
         gc_thresh = FIB6_TABLE_HASHSZ * 8;
         xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh;
+
+        ret = xfrm6_policy_init();
+        if (ret)
+                goto out;
+
+        ret = xfrm6_state_init();
+        if (ret)
+                goto out_policy;
+
 #ifdef CONFIG_SYSCTL
         sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path,
                                                 xfrm6_policy_table);