netns: protect netns ID lookups with RCU

__peernet2id() can be protected by RCU as it only calls idr_for_each(),
which is RCU-safe, and never modifies the nsid table.

rtnl_net_dumpid() can also do lockless lookups. It does two nested
idr_for_each() calls on nsid tables (one direct call and one indirect
call because of rtnl_net_dumpid_one() calling __peernet2id()). The
netnsid tables are never updated. Therefore it is safe to not take the
nsid_lock and run within an RCU-critical section instead.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 05e07d2..e7a5ff4 100644 (file)
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -211,7 +211,7 @@ static int net_eq_idr(int id, void *net, void *peer)
        return 0;
 }
 
-/* Should be called with nsid_lock held. */
+/* Must be called from RCU-critical section or with nsid_lock held */
 static int __peernet2id(const struct net *net, struct net *peer)
 {
        int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
@@ -272,9 +272,10 @@ int peernet2id(struct net *net, struct net *peer)
 {
        int id;
 
-       spin_lock_bh(&net->nsid_lock);
+       rcu_read_lock();
        id = __peernet2id(net, peer);
-       spin_unlock_bh(&net->nsid_lock);
+       rcu_read_unlock();
+
        return id;
 }
 EXPORT_SYMBOL(peernet2id);
@@ -941,6 +942,7 @@ struct rtnl_net_dump_cb {
        int s_idx;
 };
 
+/* Runs in RCU-critical section. */
 static int rtnl_net_dumpid_one(int id, void *peer, void *data)
 {
        struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data;
@@ -1025,19 +1027,9 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
                        goto end;
        }
 
-       spin_lock_bh(&net_cb.tgt_net->nsid_lock);
-       if (net_cb.fillargs.add_ref &&
-           !net_eq(net_cb.ref_net, net_cb.tgt_net) &&
-           !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) {
-               spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
-               err = -EAGAIN;
-               goto end;
-       }
+       rcu_read_lock();
        idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
-       if (net_cb.fillargs.add_ref &&
-           !net_eq(net_cb.ref_net, net_cb.tgt_net))
-               spin_unlock_bh(&net_cb.ref_net->nsid_lock);
-       spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
+       rcu_read_unlock();
 
        cb->args[0] = net_cb.idx;
 end: