netlink: allow to listen "all" netns
More accurately, listen all netns that have a nsid assigned into the netns
where the netlink socket is opened.
For this purpose, a netlink socket option is added:
NETLINK_LISTEN_ALL_NSID. When this option is set on a netlink socket, this
socket will receive netlink notifications from all netns that have a nsid
assigned into the netns where the socket has been opened. The nsid is sent
to userland via an anscillary data.
With this patch, a daemon needs only one socket to listen many netns. This
is useful when the number of netns is high.
Because 0 is a valid value for a nsid, the field nsid_is_set indicates if
the field nsid is valid or not. skb->cb is initialized to 0 on skb
allocation, thus we are sure that we will never send a nsid 0 by error to
the userland.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bf7f56d..a5fff75 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -83,6 +83,7 @@
#define NETLINK_F_RECV_PKTINFO 0x2
#define NETLINK_F_BROADCAST_SEND_ERROR 0x4
#define NETLINK_F_RECV_NO_ENOBUFS 0x8
+#define NETLINK_F_LISTEN_ALL_NSID 0x10
static inline int netlink_is_kernel(struct sock *sk)
{
@@ -1932,8 +1933,17 @@
!test_bit(p->group - 1, nlk->groups))
return;
- if (!net_eq(sock_net(sk), p->net))
- return;
+ if (!net_eq(sock_net(sk), p->net)) {
+ if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID))
+ return;
+
+ if (!peernet_has_id(sock_net(sk), p->net))
+ return;
+
+ if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns,
+ CAP_NET_BROADCAST))
+ return;
+ }
if (p->failure) {
netlink_overrun(sk);
@@ -1959,13 +1969,22 @@
p->failure = 1;
if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
p->delivery_failure = 1;
- } else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
+ goto out;
+ }
+ if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
kfree_skb(p->skb2);
p->skb2 = NULL;
- } else if (sk_filter(sk, p->skb2)) {
+ goto out;
+ }
+ if (sk_filter(sk, p->skb2)) {
kfree_skb(p->skb2);
p->skb2 = NULL;
- } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
+ goto out;
+ }
+ NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net);
+ NETLINK_CB(p->skb2).nsid_is_set = true;
+ val = netlink_broadcast_deliver(sk, p->skb2);
+ if (val < 0) {
netlink_overrun(sk);
if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
p->delivery_failure = 1;
@@ -1974,6 +1993,7 @@
p->delivered = 1;
p->skb2 = NULL;
}
+out:
sock_put(sk);
}
@@ -2202,6 +2222,16 @@
break;
}
#endif /* CONFIG_NETLINK_MMAP */
+ case NETLINK_LISTEN_ALL_NSID:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
+ return -EPERM;
+
+ if (val)
+ nlk->flags |= NETLINK_F_LISTEN_ALL_NSID;
+ else
+ nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID;
+ err = 0;
+ break;
default:
err = -ENOPROTOOPT;
}
@@ -2268,6 +2298,16 @@
put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
}
+static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg,
+ struct sk_buff *skb)
+{
+ if (!NETLINK_CB(skb).nsid_is_set)
+ return;
+
+ put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int),
+ &NETLINK_CB(skb).nsid);
+}
+
static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
@@ -2421,6 +2461,8 @@
if (nlk->flags & NETLINK_F_RECV_PKTINFO)
netlink_cmsg_recv_pktinfo(msg, skb);
+ if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+ netlink_cmsg_listen_all_nsid(sk, msg, skb);
memset(&scm, 0, sizeof(scm));
scm.creds = *NETLINK_CREDS(skb);