Commit dc3ee32e authored by Eric W. Biederman's avatar Eric W. Biederman Committed by Pablo Neira Ayuso

netfilter: nf_queue: Make the queue_handler pernet

Florian Weber reported:
> Under full load (unshare() in loop -> OOM conditions) we can
> get kernel panic:
>
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> IP: [<ffffffff81476c85>] nfqnl_nf_hook_drop+0x35/0x70
> [..]
> task: ffff88012dfa3840 ti: ffff88012dffc000 task.ti: ffff88012dffc000
> RIP: 0010:[<ffffffff81476c85>]  [<ffffffff81476c85>] nfqnl_nf_hook_drop+0x35/0x70
> RSP: 0000:ffff88012dfffd80  EFLAGS: 00010206
> RAX: 0000000000000008 RBX: ffffffff81add0c0 RCX: ffff88013fd80000
> [..]
> Call Trace:
>  [<ffffffff81474d98>] nf_queue_nf_hook_drop+0x18/0x20
>  [<ffffffff814738eb>] nf_unregister_net_hook+0xdb/0x150
>  [<ffffffff8147398f>] netfilter_net_exit+0x2f/0x60
>  [<ffffffff8141b088>] ops_exit_list.isra.4+0x38/0x60
>  [<ffffffff8141b652>] setup_net+0xc2/0x120
>  [<ffffffff8141bd09>] copy_net_ns+0x79/0x120
>  [<ffffffff8106965b>] create_new_namespaces+0x11b/0x1e0
>  [<ffffffff810698a7>] unshare_nsproxy_namespaces+0x57/0xa0
>  [<ffffffff8104baa2>] SyS_unshare+0x1b2/0x340
>  [<ffffffff81608276>] entry_SYSCALL_64_fastpath+0x1e/0xa8
> Code: 65 00 48 89 e5 41 56 41 55 41 54 53 83 e8 01 48 8b 97 70 12 00 00 48 98 49 89 f4 4c 8b 74 c2 18 4d 8d 6e 08 49 81 c6 88 00 00 00 <49> 8b 5d 00 48 85 db 74 1a 48 89 df 4c 89 e2 48 c7 c6 90 68 47
>

The simple fix for this requires a new pernet variable for struct
nf_queue that indicates when it is safe to use the dynamically
allocated nf_queue state.

As we need a variable anyway make nf_register_queue_handler and
nf_unregister_queue_handler pernet.  This allows the existing logic of
when it is safe to use the state from the nfnetlink_queue module to be
reused with no changes except for making it per net.

The syncrhonize_rcu from nf_unregister_queue_handler is moved to a new
function nfnl_queue_net_exit_batch so that the worst case of having a
syncrhonize_rcu in the pernet exit path is not experienced in batch
mode.
Reported-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatar"Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatarPablo Neira Ayuso <pablo@netfilter.org>
parent 720b287d
......@@ -28,8 +28,8 @@ struct nf_queue_handler {
struct nf_hook_ops *ops);
};
void nf_register_queue_handler(const struct nf_queue_handler *qh);
void nf_unregister_queue_handler(void);
void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
void nf_unregister_queue_handler(struct net *net);
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
......
......@@ -5,11 +5,13 @@
struct proc_dir_entry;
struct nf_logger;
struct nf_queue_handler;
struct netns_nf {
#if defined CONFIG_PROC_FS
struct proc_dir_entry *proc_netfilter;
#endif
const struct nf_queue_handler __rcu *queue_handler;
const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO];
#ifdef CONFIG_SYSCTL
struct ctl_table_header *nf_log_dir_header;
......
......@@ -26,23 +26,21 @@
* Once the queue is registered it must reinject all packets it
* receives, no matter what.
*/
static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
/* return EBUSY when somebody else is registered, return EEXIST if the
* same handler is registered, return 0 in case of success. */
void nf_register_queue_handler(const struct nf_queue_handler *qh)
void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh)
{
/* should never happen, we only have one queueing backend in kernel */
WARN_ON(rcu_access_pointer(queue_handler));
rcu_assign_pointer(queue_handler, qh);
WARN_ON(rcu_access_pointer(net->nf.queue_handler));
rcu_assign_pointer(net->nf.queue_handler, qh);
}
EXPORT_SYMBOL(nf_register_queue_handler);
/* The caller must flush their queue before this */
void nf_unregister_queue_handler(void)
void nf_unregister_queue_handler(struct net *net)
{
RCU_INIT_POINTER(queue_handler, NULL);
synchronize_rcu();
RCU_INIT_POINTER(net->nf.queue_handler, NULL);
}
EXPORT_SYMBOL(nf_unregister_queue_handler);
......@@ -103,7 +101,7 @@ void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops)
const struct nf_queue_handler *qh;
rcu_read_lock();
qh = rcu_dereference(queue_handler);
qh = rcu_dereference(net->nf.queue_handler);
if (qh)
qh->nf_hook_drop(net, ops);
rcu_read_unlock();
......@@ -122,9 +120,10 @@ int nf_queue(struct sk_buff *skb,
struct nf_queue_entry *entry = NULL;
const struct nf_afinfo *afinfo;
const struct nf_queue_handler *qh;
struct net *net = state->net;
/* QUEUE == DROP if no one is waiting, to be safe. */
qh = rcu_dereference(queue_handler);
qh = rcu_dereference(net->nf.queue_handler);
if (!qh) {
status = -ESRCH;
goto err;
......
......@@ -1377,21 +1377,29 @@ static int __net_init nfnl_queue_net_init(struct net *net)
net->nf.proc_netfilter, &nfqnl_file_ops))
return -ENOMEM;
#endif
nf_register_queue_handler(net, &nfqh);
return 0;
}
static void __net_exit nfnl_queue_net_exit(struct net *net)
{
nf_unregister_queue_handler(net);
#ifdef CONFIG_PROC_FS
remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter);
#endif
}
static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list)
{
synchronize_rcu();
}
static struct pernet_operations nfnl_queue_net_ops = {
.init = nfnl_queue_net_init,
.exit = nfnl_queue_net_exit,
.id = &nfnl_queue_net_id,
.size = sizeof(struct nfnl_queue_net),
.init = nfnl_queue_net_init,
.exit = nfnl_queue_net_exit,
.exit_batch = nfnl_queue_net_exit_batch,
.id = &nfnl_queue_net_id,
.size = sizeof(struct nfnl_queue_net),
};
static int __init nfnetlink_queue_init(void)
......@@ -1412,7 +1420,6 @@ static int __init nfnetlink_queue_init(void)
}
register_netdevice_notifier(&nfqnl_dev_notifier);
nf_register_queue_handler(&nfqh);
return status;
cleanup_netlink_notifier:
......@@ -1424,7 +1431,6 @@ static int __init nfnetlink_queue_init(void)
static void __exit nfnetlink_queue_fini(void)
{
nf_unregister_queue_handler();
unregister_netdevice_notifier(&nfqnl_dev_notifier);
nfnetlink_subsys_unregister(&nfqnl_subsys);
netlink_unregister_notifier(&nfqnl_rtnl_notifier);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment