rtnetlink: Introduce struct rtnl_nets and helpers.

rtnl_newlink() needs to hold 3 per-netns RTNL: 2 for a new device
and 1 for its peer.

We will add rtnl_nets_lock() later, which performs the nested locking
based on struct rtnl_nets, which has an array of struct net pointers.

rtnl_nets_add() adds a net pointer to the array and sorts it so that
rtnl_nets_lock() can simply acquire per-netns RTNL from array[0] to [2].

Before calling rtnl_nets_add(), get_net() must be called for the net,
and rtnl_nets_destroy() will call put_net() for each.

Let's apply the helpers to rtnl_newlink().

When CONFIG_DEBUG_NET_SMALL_RTNL is disabled, we do not call
rtnl_net_lock() thus do not care about the array order, so
rtnl_net_cmp_locks() returns -1 so that the loop in rtnl_nets_add()
can be optimised to NOP.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20241108004823.29419-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e8357a3..960d9d2 100644 (file)
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -258,8 +258,67 @@ bool lockdep_rtnl_net_is_held(struct net *net)
        return lockdep_rtnl_is_held() && lockdep_is_held(&net->rtnl_mutex);
 }
 EXPORT_SYMBOL(lockdep_rtnl_net_is_held);
+#else
+static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b)
+{
+       /* No need to swap */
+       return -1;
+}
 #endif
 
+struct rtnl_nets {
+       /* ->newlink() needs to freeze 3 netns at most;
+        * 2 for the new device, 1 for its peer.
+        */
+       struct net *net[3];
+       unsigned char len;
+};
+
+static void rtnl_nets_init(struct rtnl_nets *rtnl_nets)
+{
+       memset(rtnl_nets, 0, sizeof(*rtnl_nets));
+}
+
+static void rtnl_nets_destroy(struct rtnl_nets *rtnl_nets)
+{
+       int i;
+
+       for (i = 0; i < rtnl_nets->len; i++) {
+               put_net(rtnl_nets->net[i]);
+               rtnl_nets->net[i] = NULL;
+       }
+
+       rtnl_nets->len = 0;
+}
+
+/**
+ * rtnl_nets_add - Add netns to be locked before ->newlink().
+ *
+ * @rtnl_nets: rtnl_nets pointer passed to ->get_peer_net().
+ * @net: netns pointer with an extra refcnt held.
+ *
+ * The extra refcnt is released in rtnl_nets_destroy().
+ */
+static void rtnl_nets_add(struct rtnl_nets *rtnl_nets, struct net *net)
+{
+       int i;
+
+       DEBUG_NET_WARN_ON_ONCE(rtnl_nets->len == ARRAY_SIZE(rtnl_nets->net));
+
+       for (i = 0; i < rtnl_nets->len; i++) {
+               switch (rtnl_net_cmp_locks(rtnl_nets->net[i], net)) {
+               case 0:
+                       put_net(net);
+                       return;
+               case 1:
+                       swap(rtnl_nets->net[i], net);
+               }
+       }
+
+       rtnl_nets->net[i] = net;
+       rtnl_nets->len++;
+}
+
 static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
 
 static inline int rtm_msgindex(int msgtype)
@@ -3767,6 +3826,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
        struct net *tgt_net, *link_net = NULL;
        struct rtnl_link_ops *ops = NULL;
        struct rtnl_newlink_tbs *tbs;
+       struct rtnl_nets rtnl_nets;
        int ops_srcu_index;
        int ret;
 
@@ -3810,6 +3870,8 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 #endif
        }
 
+       rtnl_nets_init(&rtnl_nets);
+
        if (ops) {
                if (ops->maxtype > RTNL_MAX_TYPE) {
                        ret = -EINVAL;
@@ -3839,6 +3901,8 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
                goto put_ops;
        }
 
+       rtnl_nets_add(&rtnl_nets, tgt_net);
+
        if (tb[IFLA_LINK_NETNSID]) {
                int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
 
@@ -3849,6 +3913,8 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
                        goto put_net;
                }
 
+               rtnl_nets_add(&rtnl_nets, link_net);
+
                if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        goto put_net;
@@ -3858,9 +3924,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
        ret = __rtnl_newlink(skb, nlh, ops, tgt_net, link_net, tbs, data, extack);
 
 put_net:
-       if (link_net)
-               put_net(link_net);
-       put_net(tgt_net);
+       rtnl_nets_destroy(&rtnl_nets);
 put_ops:
        if (ops)
                rtnl_link_ops_put(ops, ops_srcu_index);