rtnetlink: Register rtnl_dellink() and rtnl_setlink() with RTNL_FLAG_DOIT_PERNET_WIP.

Currently, rtnl_setlink() and rtnl_dellink() cannot be fully converted
to per-netns RTNL due to a lack of handling peer/lower/upper devices in
different netns.

For example, when we change a device in rtnl_setlink() and need to
propagate that to its upper devices, we want to avoid acquiring all netns
locks, for which we do not know the upper limit.

The same situation happens when we remove a device.

rtnl_dellink() could be transformed to remove a single device in the
requested netns and delegate other devices to per-netns work, and
rtnl_setlink() might be ?

Until we come up with a better idea, let's use a new flag
RTNL_FLAG_DOIT_PERNET_WIP for rtnl_dellink() and rtnl_setlink().

This will unblock converting RTNL users where such devices are not related.

Signed-off-by: Kuniyuki Iwashima <[email protected]>
Reviewed-by: Nikolay Aleksandrov <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: q2ven

include/net/rtnetlink.h

@@ -13,6 +13,7 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 enum rtnl_link_flags {
 	RTNL_FLAG_DOIT_UNLOCKED		= BIT(0),
 #define RTNL_FLAG_DOIT_PERNET		RTNL_FLAG_DOIT_UNLOCKED
+#define RTNL_FLAG_DOIT_PERNET_WIP	RTNL_FLAG_DOIT_UNLOCKED
 	RTNL_FLAG_BULK_DEL_SUPPORTED	= BIT(1),
 	RTNL_FLAG_DUMP_UNLOCKED		= BIT(2),
 	RTNL_FLAG_DUMP_SPLIT_NLM_DONE	= BIT(3),	/* legacy behavior */

net/core/rtnetlink.c

@@ -3379,6 +3379,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFLA_MAX+1];
 	struct net_device *dev = NULL;
+	struct rtnl_nets rtnl_nets;
 	struct net *tgt_net;
 	int err;
 
@@ -3397,6 +3398,12 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
+	rtnl_nets_init(&rtnl_nets);
+	rtnl_nets_add(&rtnl_nets, get_net(net));
+	rtnl_nets_add(&rtnl_nets, tgt_net);
+
+	rtnl_nets_lock(&rtnl_nets);
+
 	if (ifm->ifi_index > 0)
 		dev = __dev_get_by_index(net, ifm->ifi_index);
 	else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
@@ -3409,7 +3416,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else if (!err)
 		err = -ENODEV;
 
-	put_net(tgt_net);
+	rtnl_nets_unlock(&rtnl_nets);
 errout:
 	return err;
 }
@@ -3494,6 +3501,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			return PTR_ERR(tgt_net);
 	}
 
+	rtnl_net_lock(tgt_net);
+
 	if (ifm->ifi_index > 0)
 		dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
 	else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
@@ -3508,6 +3517,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		err = -EINVAL;
 
+	rtnl_net_unlock(tgt_net);
+
 	if (netnsid >= 0)
 		put_net(tgt_net);
 
@@ -6994,10 +7005,12 @@ static struct pernet_operations rtnetlink_net_ops = {
 static const struct rtnl_msg_handler rtnetlink_rtnl_msg_handlers[] __initconst = {
 	{.msgtype = RTM_NEWLINK, .doit = rtnl_newlink,
 	 .flags = RTNL_FLAG_DOIT_PERNET},
-	{.msgtype = RTM_DELLINK, .doit = rtnl_dellink},
+	{.msgtype = RTM_DELLINK, .doit = rtnl_dellink,
+	 .flags = RTNL_FLAG_DOIT_PERNET_WIP},
 	{.msgtype = RTM_GETLINK, .doit = rtnl_getlink,
 	 .dumpit = rtnl_dump_ifinfo, .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
-	{.msgtype = RTM_SETLINK, .doit = rtnl_setlink},
+	{.msgtype = RTM_SETLINK, .doit = rtnl_setlink,
+	 .flags = RTNL_FLAG_DOIT_PERNET_WIP},
 	{.msgtype = RTM_GETADDR, .dumpit = rtnl_dump_all},
 	{.msgtype = RTM_GETROUTE, .dumpit = rtnl_dump_all},
 	{.msgtype = RTM_GETNETCONF, .dumpit = rtnl_dump_all},