ipv6: remove RTNL protection from ip6addrlbl_dump()

No longer hold RTNL while calling ip6addrlbl_dump()
("ip addrlabel show")

ip6addrlbl_dump() was already mostly relying on RCU anyway.

Add READ_ONCE()/WRITE_ONCE() annotations around
net->ipv6.ip6addrlbl_table.seq

Note that ifal_seq value is currently ignored in iproute2,
and a bit weak.

We might user later cb->seq  / nl_dump_check_consistent()
protocol if needed.

Also change return value for a completed dump,
so that NLMSG_DONE can be appended to current skb,
saving one recvmsg() system call.

v2: read net->ipv6.ip6addrlbl_table.seq once, (David Ahern)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link:https://lore.kernel.org/netdev/67f5cb70-14a4-4455-8372-f039da2f15c2@kernel.org/
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 17ac45aa7194ce9c148ed95e14dd575d17feeb98..acd70b5992a7b9c1aadcfb9a279da7fe6aebfed9 100644 (file)
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -234,7 +234,8 @@ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp,
                hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head);
 out:
        if (!ret)
-               net->ipv6.ip6addrlbl_table.seq++;
+               WRITE_ONCE(net->ipv6.ip6addrlbl_table.seq,
+                          net->ipv6.ip6addrlbl_table.seq + 1);
        return ret;
 }
 
@@ -445,7 +446,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh,
 };
 
 static int ip6addrlbl_fill(struct sk_buff *skb,
-                          struct ip6addrlbl_entry *p,
+                          const struct ip6addrlbl_entry *p,
                           u32 lseq,
                           u32 portid, u32 seq, int event,
                           unsigned int flags)
@@ -498,7 +499,8 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
        struct net *net = sock_net(skb->sk);
        struct ip6addrlbl_entry *p;
        int idx = 0, s_idx = cb->args[0];
-       int err;
+       int err = 0;
+       u32 lseq;
 
        if (cb->strict_check) {
                err = ip6addrlbl_valid_dump_req(nlh, cb->extack);
@@ -507,10 +509,11 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
        }
 
        rcu_read_lock();
+       lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq);
        hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
                if (idx >= s_idx) {
                        err = ip6addrlbl_fill(skb, p,
-                                             net->ipv6.ip6addrlbl_table.seq,
+                                             lseq,
                                              NETLINK_CB(cb->skb).portid,
                                              nlh->nlmsg_seq,
                                              RTM_NEWADDRLABEL,
@@ -522,7 +525,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
        }
        rcu_read_unlock();
        cb->args[0] = idx;
-       return skb->len;
+       return err;
 }
 
 static inline int ip6addrlbl_msgsize(void)
@@ -614,7 +617,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
        rcu_read_lock();
        p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
-       lseq = net->ipv6.ip6addrlbl_table.seq;
+       lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq);
        if (p)
                err = ip6addrlbl_fill(skb, p, lseq,
                                      NETLINK_CB(in_skb).portid,
@@ -647,6 +650,7 @@ int __init ipv6_addr_label_rtnl_register(void)
                return ret;
        ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDRLABEL,
                                   ip6addrlbl_get,
-                                  ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
+                                  ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED |
+                                                   RTNL_FLAG_DUMP_UNLOCKED);
        return ret;
 }