ipv4,ipv6: grab rtnl before locking the socket
There are some setsockopt operations in ipv4 and ipv6 that are grabbing
rtnl after having grabbed the socket lock. Yet this makes it impossible
to do operations that have to lock the socket when already within a rtnl
protected scope, like ndo dev_open and dev_stop.
We normally take coarse grained locks first but setsockopt inverted that.
So this patch invert the lock logic for these operations and makes
setsockopt grab rtnl if it will be needed prior to grabbing socket lock.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5cd9927..5171709 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -536,12 +536,25 @@
* Socket option code for IP. This is the end of the line after any
* TCP,UDP etc options on an IP socket.
*/
+static bool setsockopt_needs_rtnl(int optname)
+{
+ switch (optname) {
+ case IP_ADD_MEMBERSHIP:
+ case IP_ADD_SOURCE_MEMBERSHIP:
+ case IP_DROP_MEMBERSHIP:
+ case MCAST_JOIN_GROUP:
+ case MCAST_LEAVE_GROUP:
+ return true;
+ }
+ return false;
+}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
int val = 0, err;
+ bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
@@ -584,6 +597,8 @@
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
+ if (needs_rtnl)
+ rtnl_lock();
lock_sock(sk);
switch (optname) {
@@ -846,9 +861,9 @@
}
if (optname == IP_ADD_MEMBERSHIP)
- err = ip_mc_join_group(sk, &mreq);
+ err = __ip_mc_join_group(sk, &mreq);
else
- err = ip_mc_leave_group(sk, &mreq);
+ err = __ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
@@ -913,7 +928,7 @@
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
- err = ip_mc_join_group(sk, &mreq);
+ err = __ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
@@ -945,9 +960,9 @@
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
- err = ip_mc_join_group(sk, &mreq);
+ err = __ip_mc_join_group(sk, &mreq);
else
- err = ip_mc_leave_group(sk, &mreq);
+ err = __ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
@@ -990,7 +1005,7 @@
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
- err = ip_mc_join_group(sk, &mreq);
+ err = __ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
@@ -1118,10 +1133,14 @@
break;
}
release_sock(sk);
+ if (needs_rtnl)
+ rtnl_unlock();
return err;
e_inval:
release_sock(sk);
+ if (needs_rtnl)
+ rtnl_unlock();
return -EINVAL;
}