mpls: no longer hold RTNL in mpls_netconf_dump_devconf()

- Use for_each_netdev_dump() to no longer rely
  on net->dev_index_head hash table.

- No longer care of net->dev_base_seq

- Fix return value at the end of a dump,
  so that NLMSG_DONE can be appended to current skb,
  saving one recvmsg() system call.

- No longer grab RTNL, RCU protection is enough,
  afer adding one READ_ONCE(mdev->input_enabled)
  in mpls_netconf_fill_devconf()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240410111951.2673193-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 1303acb9cdd23f48f22c35e019115895d14df8b4..0315b8deed3ffeec7778acc4a098e5dc17aff209 100644 (file)
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1154,7 +1154,7 @@ static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev,
 
        if ((all || type == NETCONFA_INPUT) &&
            nla_put_s32(skb, NETCONFA_INPUT,
-                       mdev->input_enabled) < 0)
+                       READ_ONCE(mdev->input_enabled)) < 0)
                goto nla_put_failure;
 
        nlmsg_end(skb, nlh);
@@ -1303,11 +1303,12 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb,
 {
        const struct nlmsghdr *nlh = cb->nlh;
        struct net *net = sock_net(skb->sk);
-       struct hlist_head *head;
+       struct {
+               unsigned long ifindex;
+       } *ctx = (void *)cb->ctx;
        struct net_device *dev;
        struct mpls_dev *mdev;
-       int idx, s_idx;
-       int h, s_h;
+       int err = 0;
 
        if (cb->strict_check) {
                struct netlink_ext_ack *extack = cb->extack;
@@ -1324,40 +1325,23 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb,
                }
        }
 
-       s_h = cb->args[0];
-       s_idx = idx = cb->args[1];
-
-       for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-               idx = 0;
-               head = &net->dev_index_head[h];
-               rcu_read_lock();
-               cb->seq = net->dev_base_seq;
-               hlist_for_each_entry_rcu(dev, head, index_hlist) {
-                       if (idx < s_idx)
-                               goto cont;
-                       mdev = mpls_dev_get(dev);
-                       if (!mdev)
-                               goto cont;
-                       if (mpls_netconf_fill_devconf(skb, mdev,
-                                                     NETLINK_CB(cb->skb).portid,
-                                                     nlh->nlmsg_seq,
-                                                     RTM_NEWNETCONF,
-                                                     NLM_F_MULTI,
-                                                     NETCONFA_ALL) < 0) {
-                               rcu_read_unlock();
-                               goto done;
-                       }
-                       nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-cont:
-                       idx++;
-               }
-               rcu_read_unlock();
+       rcu_read_lock();
+       for_each_netdev_dump(net, dev, ctx->ifindex) {
+               mdev = mpls_dev_get(dev);
+               if (!mdev)
+                       continue;
+               err = mpls_netconf_fill_devconf(skb, mdev,
+                                               NETLINK_CB(cb->skb).portid,
+                                               nlh->nlmsg_seq,
+                                               RTM_NEWNETCONF,
+                                               NLM_F_MULTI,
+                                               NETCONFA_ALL);
+               if (err < 0)
+                       break;
        }
-done:
-       cb->args[0] = h;
-       cb->args[1] = idx;
+       rcu_read_unlock();
 
-       return skb->len;
+       return err;
 }
 
 #define MPLS_PERDEV_SYSCTL_OFFSET(field)       \
@@ -2773,7 +2757,8 @@ static int __init mpls_init(void)
                             mpls_getroute, mpls_dump_routes, 0);
        rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_GETNETCONF,
                             mpls_netconf_get_devconf,
-                            mpls_netconf_dump_devconf, 0);
+                            mpls_netconf_dump_devconf,
+                            RTNL_FLAG_DUMP_UNLOCKED);
        err = ipgre_tunnel_encap_add_mpls_ops();
        if (err)
                pr_err("Can't add mpls over gre tunnel ops\n");