linux/net/netlink/af_netlink.h
Johannes Berg ee1c244219 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>
2015-01-16 17:04:25 -05:00

80 lines
1.8 KiB
C

#ifndef _AF_NETLINK_H
#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)
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
struct netlink_ring {
void **pg_vec;
unsigned int head;
unsigned int frames_per_block;
unsigned int frame_size;
unsigned int frame_max;
unsigned int pg_vec_order;
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
atomic_t pending;
};
struct netlink_sock {
/* struct sock has to be the first member of netlink_sock */
struct sock sk;
u32 portid;
u32 dst_portid;
u32 dst_group;
u32 flags;
u32 subscriptions;
u32 ngroups;
unsigned long *groups;
unsigned long state;
size_t max_recvmsg_len;
wait_queue_head_t wait;
bool cb_running;
struct netlink_callback cb;
struct mutex *cb_mutex;
struct mutex cb_def_mutex;
void (*netlink_rcv)(struct sk_buff *skb);
int (*netlink_bind)(struct net *net, int group);
void (*netlink_unbind)(struct net *net, int group);
struct module *module;
#ifdef CONFIG_NETLINK_MMAP
struct mutex pg_vec_lock;
struct netlink_ring rx_ring;
struct netlink_ring tx_ring;
atomic_t mapped;
#endif /* CONFIG_NETLINK_MMAP */
struct rhash_head node;
};
static inline struct netlink_sock *nlk_sk(struct sock *sk)
{
return container_of(sk, struct netlink_sock, sk);
}
struct netlink_table {
struct rhashtable hash;
struct hlist_head mc_list;
struct listeners __rcu *listeners;
unsigned int flags;
unsigned int groups;
struct mutex *cb_mutex;
struct module *module;
int (*bind)(struct net *net, int group);
void (*unbind)(struct net *net, int group);
bool (*compare)(struct net *net, struct sock *sock);
int registered;
};
extern struct netlink_table *nl_table;
extern rwlock_t nl_table_lock;
extern struct mutex nl_sk_hash_lock;
#endif