rtnetlink: move rtnl_lock handling out of af_netlink

Now that we have an intermediate layer of code for handling
rtnl-level netlink dump quirks, we can move the rtnl_lock
taking there.

For dump handlers with RTNL_FLAG_DUMP_SPLIT_NLM_DONE we can
avoid taking rtnl_lock just to generate NLM_DONE, once again.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/core/rtnetlink.c

@@ -6486,6 +6486,7 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	const bool needs_lock = !(cb->flags & RTNL_FLAG_DUMP_UNLOCKED);
 	rtnl_dumpit_func dumpit = cb->data;
 	int err;
 
@@ -6495,7 +6496,11 @@ static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!dumpit)
 		return 0;
 
+	if (needs_lock)
+		rtnl_lock();
 	err = dumpit(skb, cb);
+	if (needs_lock)
+		rtnl_unlock();
 
 	/* Old dump handlers used to send NLM_DONE as in a separate recvmsg().
 	 * Some applications which parse netlink manually depend on this.
@@ -6515,7 +6520,8 @@ static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				struct netlink_dump_control *control)
 {
-	if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+	if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE ||
+	    !(control->flags & RTNL_FLAG_DUMP_UNLOCKED)) {
 		WARN_ON(control->data);
 		control->data = control->dump;
 		control->dump = rtnl_dumpit;
@@ -6703,7 +6709,6 @@ static int __net_init rtnetlink_net_init(struct net *net)
 	struct netlink_kernel_cfg cfg = {
 		.groups		= RTNLGRP_MAX,
 		.input		= rtnetlink_rcv,
-		.cb_mutex	= &rtnl_mutex,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= rtnetlink_bind,
 	};

net/netlink/af_netlink.c

@@ -2330,8 +2330,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 
 		cb->extack = &extack;
 
-		if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED)
-			extra_mutex = NULL;
 		if (extra_mutex)
 			mutex_lock(extra_mutex);
 		nlk->dump_done_errno = cb->dump(skb, cb);