net: Fix possible race in peernet2id_alloc()

peernet2id_alloc() is racy without rtnl_lock() as refcount_read(&peer->count)
under net->nsid_lock does not guarantee, peer is alive:

rcu_read_lock()
peernet2id_alloc()                            ..
  spin_lock_bh(&net->nsid_lock)               ..
  refcount_read(&peer->count) (!= 0)          ..
  ..                                          put_net()
  ..                                            cleanup_net()
  ..                                              for_each_net(tmp)
  ..                                                spin_lock_bh(&tmp->nsid_lock)
  ..                                                __peernet2id(tmp, net) == -1
  ..                                                    ..
  ..                                                    ..
    __peernet2id_alloc(alloc == true)                   ..
  ..                                                    ..
rcu_read_unlock()                                       ..
..                                                synchronize_rcu()
..                                                kmem_cache_free(net)

After the above situation, net::netns_id contains id pointing to freed memory,
and any other dereferencing by the id will operate with this freed memory.

Currently, peernet2id_alloc() is used under rtnl_lock() everywhere except
ovs_vport_cmd_fill_info(), and this race can't occur. But peernet2id_alloc()
is generic interface, and better we fix it before someone really starts
use it in wrong context.

v2: Don't place refcount_read(&net->count) under net->nsid_lock
    as suggested by Eric W. Biederman <ebiederm@xmission.com>
v3: Rebase on top of net-next

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 11 insertions, 2 deletions

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2213d45fcafd..3c77d84ad60d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -221,17 +221,26 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id);
  */
 int peernet2id_alloc(struct net *net, struct net *peer)
 {
-        bool alloc;
+        bool alloc = false, alive = false;
         int id;
 
         if (refcount_read(&net->count) == 0)
                 return NETNSA_NSID_NOT_ASSIGNED;
         spin_lock_bh(&net->nsid_lock);
-        alloc = refcount_read(&peer->count) == 0 ? false : true;
+        /*
+         * When peer is obtained from RCU lists, we may race with
+         * its cleanup. Check whether it's alive, and this guarantees
+         * we never hash a peer back to net->netns_ids, after it has
+         * just been idr_remove()'d from there in cleanup_net().
+         */
+        if (maybe_get_net(peer))
+                alive = alloc = true;
         id = __peernet2id_alloc(net, peer, &alloc);
         spin_unlock_bh(&net->nsid_lock);
         if (alloc && id >= 0)
                 rtnl_net_notifyid(net, RTM_NEWNSID, id);
+        if (alive)
+                put_net(peer);
         return id;
 }
 EXPORT_SYMBOL_GPL(peernet2id_alloc);