rxrpc: Fix deadlock around release of dst cached on udp tunnel

AF_RXRPC sockets use UDP ports in encap mode.  This causes socket and dst
from an incoming packet to get stolen and attached to the UDP socket from
whence it is leaked when that socket is closed.

When a network namespace is removed, the wait for dst records to be cleaned
up happens before the cleanup of the rxrpc and UDP socket, meaning that the
wait never finishes.

Fix this by moving the rxrpc (and, by dependence, the afs) private
per-network namespace registrations to the device group rather than subsys
group.  This allows cached rxrpc local endpoints to be cleared and their
UDP sockets closed before we try waiting for the dst records.

The symptom is that lines looking like the following:

	unregister_netdevice: waiting for lo to become free

get emitted at regular intervals after running something like the
referenced syzbot test.

Thanks to Vadim for tracking this down and work out the fix.

Reported-by: syzbot+df400f2f24a1677cd7e0@syzkaller.appspotmail.com
Reported-by: Vadim Fedorenko <vfedorenko@novek.ru>
Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook")
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vadim Fedorenko <vfedorenko@novek.ru>
Link: https://lore.kernel.org/r/161196443016.3868642.5577440140646403533.stgit@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/fs/afs/main.c b/fs/afs/main.c
index accdd8970e7c0cbaa67bf8eba097302c9b6274cd..b2975256dadbdf3abe4a1f1c784f83ec6d7ba8c2 100644 (file)
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -193,7 +193,7 @@ static int __init afs_init(void)
                goto error_cache;
 #endif
 
-       ret = register_pernet_subsys(&afs_net_ops);
+       ret = register_pernet_device(&afs_net_ops);
        if (ret < 0)
                goto error_net;
 
@@ -213,7 +213,7 @@ static int __init afs_init(void)
 error_proc:
        afs_fs_exit();
 error_fs:
-       unregister_pernet_subsys(&afs_net_ops);
+       unregister_pernet_device(&afs_net_ops);
 error_net:
 #ifdef CONFIG_AFS_FSCACHE
        fscache_unregister_netfs(&afs_cache_netfs);
@@ -244,7 +244,7 @@ static void __exit afs_exit(void)
 
        proc_remove(afs_proc_symlink);
        afs_fs_exit();
-       unregister_pernet_subsys(&afs_net_ops);
+       unregister_pernet_device(&afs_net_ops);
 #ifdef CONFIG_AFS_FSCACHE
        fscache_unregister_netfs(&afs_cache_netfs);
 #endif

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0a2f4817ec6cf2b8b2847aa26ccd7f16e4c6f10d..41671af6b33f91e9f77af4dc0c9d8f813247e4f3 100644 (file)
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -990,7 +990,7 @@ static int __init af_rxrpc_init(void)
                goto error_security;
        }
 
-       ret = register_pernet_subsys(&rxrpc_net_ops);
+       ret = register_pernet_device(&rxrpc_net_ops);
        if (ret)
                goto error_pernet;
 
@@ -1035,7 +1035,7 @@ error_key_type:
 error_sock:
        proto_unregister(&rxrpc_proto);
 error_proto:
-       unregister_pernet_subsys(&rxrpc_net_ops);
+       unregister_pernet_device(&rxrpc_net_ops);
 error_pernet:
        rxrpc_exit_security();
 error_security:
@@ -1057,7 +1057,7 @@ static void __exit af_rxrpc_exit(void)
        unregister_key_type(&key_type_rxrpc);
        sock_unregister(PF_RXRPC);
        proto_unregister(&rxrpc_proto);
-       unregister_pernet_subsys(&rxrpc_net_ops);
+       unregister_pernet_device(&rxrpc_net_ops);
        ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0);
        ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0);