[PATCH 3.10 223/319] ipv6: fix rtnl locking in setsockopt for anycast and multicast

[Willy Tarreau <w@1wt.eu>]

From: Sabrina Dubroca <sd@queasysnail.net>

commit a9ed4a2986e13011fcf4ed2d1a1647c53112f55b upstream.

Calling setsockopt with IPV6_JOIN_ANYCAST or IPV6_LEAVE_ANYCAST
triggers the assertion in addrconf_join_solict()/addrconf_leave_solict()

ipv6_sock_ac_join(), ipv6_sock_ac_drop(), ipv6_sock_ac_close() need to
take RTNL before calling ipv6_dev_ac_inc/dec. Same thing with
ipv6_sock_mc_join(), ipv6_sock_mc_drop(), ipv6_sock_mc_close() before
calling ipv6_dev_mc_inc/dec.

This patch moves ASSERT_RTNL() up a level in the call stack.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reported-by: Tommi Rantala <tt.rantala@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: <stable@vger.kernel.org> 
Cc: <stable@vger.kernel.org> 
Cc: <stable@vger.kernel.org> 
[Mike Manning <mmanning@brocade.com>: resolved minor conflicts in addrconf.c]
Signed-off-by: Mike Manning <mmanning@brocade.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
---
 net/ipv6/addrconf.c | 15 +++++----------
 net/ipv6/anycast.c  | 12 ++++++++++++
 net/ipv6/mcast.c    | 14 ++++++++++++++
 3 files changed, 31 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0f18d858..3bfd8a5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1697,14 +1697,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 	in6_ifa_put(ifp);
 }
 
-/* Join to solicited addr multicast group. */
-
+/* Join to solicited addr multicast group.
+ * caller must hold RTNL */
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
-	ASSERT_RTNL();
-
 	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1712,12 +1710,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 	ipv6_dev_mc_inc(dev, &maddr);
 }
 
+/* caller must hold RTNL */
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
-	ASSERT_RTNL();
-
 	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1725,12 +1722,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 	__ipv6_dev_mc_dec(idev, &maddr);
 }
 
+/* caller must hold RTNL */
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
 
-	ASSERT_RTNL();
-
 	if (ifp->prefix_len == 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1739,12 +1735,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 	ipv6_dev_ac_inc(ifp->idev->dev, &addr);
 }
 
+/* caller must hold RTNL */
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
 
-	ASSERT_RTNL();
-
 	if (ifp->prefix_len == 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 5a80f15..c59083c 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	pac->acl_next = NULL;
 	pac->acl_addr = *addr;
 
+	rtnl_lock();
 	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
@@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 error:
 	rcu_read_unlock();
+	rtnl_unlock();
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 	return err;
@@ -171,13 +173,17 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
+	rtnl_lock();
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
 	rcu_read_unlock();
+	rtnl_unlock();
 
 	sock_kfree_s(sk, pac, sizeof(*pac));
+	if (!dev)
+		return -ENODEV;
 	return 0;
 }
 
@@ -198,6 +204,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
 	prev_index = 0;
+	rtnl_lock();
 	rcu_read_lock();
 	while (pac) {
 		struct ipv6_ac_socklist *next = pac->acl_next;
@@ -212,6 +219,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 		pac = next;
 	}
 	rcu_read_unlock();
+	rtnl_unlock();
 }
 
 static void aca_put(struct ifacaddr6 *ac)
@@ -233,6 +241,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 	struct rt6_info *rt;
 	int err;
 
+	ASSERT_RTNL();
+
 	idev = in6_dev_get(dev);
 
 	if (idev == NULL)
@@ -302,6 +312,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca, *prev_aca;
 
+	ASSERT_RTNL();
+
 	write_lock_bh(&idev->lock);
 	prev_aca = NULL;
 	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7ba6180..cf16eb4 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -157,6 +157,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	mc_lst->next = NULL;
 	mc_lst->addr = *addr;
 
+	rtnl_lock();
 	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
@@ -170,6 +171,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	if (dev == NULL) {
 		rcu_read_unlock();
+		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return -ENODEV;
 	}
@@ -187,6 +189,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	if (err) {
 		rcu_read_unlock();
+		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return err;
 	}
@@ -197,6 +200,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	spin_unlock(&ipv6_sk_mc_lock);
 
 	rcu_read_unlock();
+	rtnl_unlock();
 
 	return 0;
 }
@@ -214,6 +218,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (!ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
+	rtnl_lock();
 	spin_lock(&ipv6_sk_mc_lock);
 	for (lnk = &np->ipv6_mc_list;
 	     (mc_lst = rcu_dereference_protected(*lnk,
@@ -237,12 +242,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			} else
 				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
 			rcu_read_unlock();
+			rtnl_unlock();
+
 			atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 			kfree_rcu(mc_lst, rcu);
 			return 0;
 		}
 	}
 	spin_unlock(&ipv6_sk_mc_lock);
+	rtnl_unlock();
 
 	return -EADDRNOTAVAIL;
 }
@@ -287,6 +295,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 	if (!rcu_access_pointer(np->ipv6_mc_list))
 		return;
 
+	rtnl_lock();
 	spin_lock(&ipv6_sk_mc_lock);
 	while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list,
 				lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) {
@@ -313,6 +322,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 		spin_lock(&ipv6_sk_mc_lock);
 	}
 	spin_unlock(&ipv6_sk_mc_lock);
+	rtnl_unlock();
 }
 
 int ip6_mc_source(int add, int omode, struct sock *sk,
@@ -830,6 +840,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	struct ifmcaddr6 *mc;
 	struct inet6_dev *idev;
 
+	ASSERT_RTNL();
+
 	/* we need to take a reference on idev */
 	idev = in6_dev_get(dev);
 
@@ -901,6 +913,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifmcaddr6 *ma, **map;
 
+	ASSERT_RTNL();
+
 	write_lock_bh(&idev->lock);
 	for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) {
 		if (ipv6_addr_equal(&ma->mca_addr, addr)) {
-- 
2.8.0.rc2.1.gbe9624a