diff options
author | Johannes Berg <johannes.berg@intel.com> | 2015-01-16 11:37:14 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-01-16 17:04:25 -0500 |
commit | ee1c244219fd652964710a6cc3e4f922e86aa492 (patch) | |
tree | 4420f067c6b1bbec48aa33a6ab96c627e2c2dbde /net/netlink | |
parent | 5ad6300524c0332ac67e912c20d6e5cf262ba58f (diff) | |
download | linux-stable-ee1c244219fd652964710a6cc3e4f922e86aa492.tar.gz linux-stable-ee1c244219fd652964710a6cc3e4f922e86aa492.tar.bz2 linux-stable-ee1c244219fd652964710a6cc3e4f922e86aa492.zip |
genetlink: synchronize socket closing and family removal
In addition to the problem Jeff Layton reported, I looked at the code
and reproduced the same warning by subscribing and removing the genl
family with a socket still open. This is a fairly tricky race which
originates in the fact that generic netlink allows the family to go
away while sockets are still open - unlike regular netlink which has
a module refcount for every open socket so in general this cannot be
triggered.
Trying to resolve this issue by the obvious locking isn't possible as
it will result in deadlocks between unregistration and group unbind
notification (which incidentally lockdep doesn't find due to the home
grown locking in the netlink table.)
To really resolve this, introduce a "closing socket" reference counter
(for generic netlink only, as it's the only affected family) in the
core netlink code and use that in generic netlink to wait for all the
sockets that are being closed at the same time as a generic netlink
family is removed.
This fixes the race that when a socket is closed, it will should call
the unbind, but if the family is removed at the same time the unbind
will not find it, leading to the warning. The real problem though is
that in this case the unbind could actually find a new family that is
registered to have a multicast group with the same ID, and call its
mcast_unbind() leading to confusing.
Also remove the warning since it would still trigger, but is now no
longer a problem.
This also moves the code in af_netlink.c to before unreferencing the
module to avoid having the same problem in the normal non-genl case.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/netlink')
-rw-r--r-- | net/netlink/af_netlink.c | 24 | ||||
-rw-r--r-- | net/netlink/af_netlink.h | 1 | ||||
-rw-r--r-- | net/netlink/genetlink.c | 16 |
3 files changed, 27 insertions, 14 deletions
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 84ea76ca3f1f..02fdde28dada 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -61,6 +61,7 @@ #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> +#include <linux/genetlink.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -1095,6 +1096,8 @@ static void netlink_remove(struct sock *sk) __sk_del_bind_node(sk); netlink_update_listeners(sk); } + if (sk->sk_protocol == NETLINK_GENERIC) + atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } @@ -1211,6 +1214,20 @@ static int netlink_release(struct socket *sock) * will be purged. */ + /* must not acquire netlink_table_lock in any way again before unbind + * and notifying genetlink is done as otherwise it might deadlock + */ + if (nlk->netlink_unbind) { + int i; + + for (i = 0; i < nlk->ngroups; i++) + if (test_bit(i, nlk->groups)) + nlk->netlink_unbind(sock_net(sk), i + 1); + } + if (sk->sk_protocol == NETLINK_GENERIC && + atomic_dec_return(&genl_sk_destructing_cnt) == 0) + wake_up(&genl_sk_destructing_waitq); + sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); @@ -1246,13 +1263,6 @@ static int netlink_release(struct socket *sock) netlink_table_ungrab(); } - if (nlk->netlink_unbind) { - int i; - - for (i = 0; i < nlk->ngroups; i++) - if (test_bit(i, nlk->groups)) - nlk->netlink_unbind(sock_net(sk), i + 1); - } kfree(nlk->groups); nlk->groups = NULL; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index f123a88496f8..f1c31b39aa3e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -2,6 +2,7 @@ #define _AF_NETLINK_H #include <linux/rhashtable.h> +#include <linux/atomic.h> #include <net/sock.h> #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c18d3f5624b2..ee57459fc258 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -23,6 +23,9 @@ static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); +atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); +DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); + void genl_lock(void) { mutex_lock(&genl_mutex); @@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family) genl_lock_all(); - genl_unregister_mc_groups(family); - list_for_each_entry(rc, genl_family_chain(family->id), family_list) { if (family->id != rc->id || strcmp(rc->name, family->name)) continue; + genl_unregister_mc_groups(family); + list_del(&rc->family_list); family->n_ops = 0; - genl_unlock_all(); + up_write(&cb_lock); + wait_event(genl_sk_destructing_waitq, + atomic_read(&genl_sk_destructing_cnt) == 0); + genl_unlock(); kfree(family->attrbuf); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); @@ -1014,7 +1020,6 @@ static int genl_bind(struct net *net, int group) static void genl_unbind(struct net *net, int group) { int i; - bool found = false; down_read(&cb_lock); for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { @@ -1027,14 +1032,11 @@ static void genl_unbind(struct net *net, int group) if (f->mcast_unbind) f->mcast_unbind(net, fam_grp); - found = true; break; } } } up_read(&cb_lock); - - WARN_ON(!found); } static int __net_init genl_pernet_init(struct net *net) |