Commit 2a6a870e authored by Paolo Abeni's avatar Paolo Abeni Committed by David S. Miller

mptcp: stops worker on unaccepted sockets at listener close

This is a partial revert of the blamed commit, with a relevant
change: mptcp_subflow_queue_clean() now just change the msk
socket status and stop the worker, so that the UaF issue addressed
by the blamed commit is not re-introduced.

The above prevents the mptcp worker from running concurrently with
inet_csk_listen_stop(), as such race would trigger a warning, as
reported by Christoph:

RSP: 002b:00007f784fe09cd8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
WARNING: CPU: 0 PID: 25807 at net/ipv4/inet_connection_sock.c:1387 inet_csk_listen_stop+0x664/0x870 net/ipv4/inet_connection_sock.c:1387
RAX: ffffffffffffffda RBX: 00000000006bc050 RCX: 00007f7850afd6a9
RDX: 0000000000000000 RSI: 0000000020000340 RDI: 0000000000000004
Modules linked in:
RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006bc05c
R13: fffffffffffffea8 R14: 00000000006bc050 R15: 000000000001fe40

 </TASK>
CPU: 0 PID: 25807 Comm: syz-executor.7 Not tainted 6.2.0-g778e54711659 #7
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014
RIP: 0010:inet_csk_listen_stop+0x664/0x870 net/ipv4/inet_connection_sock.c:1387
RAX: 0000000000000000 RBX: ffff888100dfbd40 RCX: 0000000000000000
RDX: ffff8881363aab80 RSI: ffffffff81c494f4 RDI: 0000000000000005
RBP: ffff888126dad080 R08: 0000000000000005 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff888100dfe040
R13: 0000000000000001 R14: 0000000000000000 R15: ffff888100dfbdd8
FS:  00007f7850a2c800(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b32d26000 CR3: 000000012fdd8006 CR4: 0000000000770ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 __tcp_close+0x5b2/0x620 net/ipv4/tcp.c:2875
 __mptcp_close_ssk+0x145/0x3d0 net/mptcp/protocol.c:2427
 mptcp_destroy_common+0x8a/0x1c0 net/mptcp/protocol.c:3277
 mptcp_destroy+0x41/0x60 net/mptcp/protocol.c:3304
 __mptcp_destroy_sock+0x56/0x140 net/mptcp/protocol.c:2965
 __mptcp_close+0x38f/0x4a0 net/mptcp/protocol.c:3057
 mptcp_close+0x24/0xe0 net/mptcp/protocol.c:3072
 inet_release+0x53/0xa0 net/ipv4/af_inet.c:429
 __sock_release+0x4e/0xf0 net/socket.c:651
 sock_close+0x15/0x20 net/socket.c:1393
 __fput+0xff/0x420 fs/file_table.c:321
 task_work_run+0x8b/0xe0 kernel/task_work.c:179
 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x113/0x120 kernel/entry/common.c:203
 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline]
 syscall_exit_to_user_mode+0x1d/0x40 kernel/entry/common.c:296
 do_syscall_64+0x46/0x90 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x72/0xdc
RIP: 0033:0x7f7850af70dc
RAX: 0000000000000000 RBX: 0000000000000004 RCX: 00007f7850af70dc
RDX: 00007f7850a2c800 RSI: 0000000000000002 RDI: 0000000000000003
RBP: 00000000006bd980 R08: 0000000000000000 R09: 00000000000018a0
R10: 00000000316338a4 R11: 0000000000000293 R12: 0000000000211e31
R13: 00000000006bc05c R14: 00007f785062c000 R15: 0000000000211af0

Fixes: 0a3f4f1f ("mptcp: fix UaF in listener shutdown")
Cc: stable@vger.kernel.org
Reported-by: default avatarChristoph Paasch <cpaasch@apple.com>
Link: https://github.com/multipath-tcp/mptcp_net-next/issues/371Signed-off-by: default avatarPaolo Abeni <pabeni@redhat.com>
Reviewed-by: default avatarMatthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: default avatarMatthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 4e006c7a
...@@ -2365,8 +2365,12 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, ...@@ -2365,8 +2365,12 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
mptcp_subflow_drop_ctx(ssk); mptcp_subflow_drop_ctx(ssk);
} else { } else {
/* otherwise tcp will dispose of the ssk and subflow ctx */ /* otherwise tcp will dispose of the ssk and subflow ctx */
if (ssk->sk_state == TCP_LISTEN) if (ssk->sk_state == TCP_LISTEN) {
tcp_set_state(ssk, TCP_CLOSE);
mptcp_subflow_queue_clean(sk, ssk);
inet_csk_listen_stop(ssk);
mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
}
__tcp_close(ssk, 0); __tcp_close(ssk, 0);
......
...@@ -629,6 +629,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, ...@@ -629,6 +629,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow); struct mptcp_subflow_context *subflow);
void __mptcp_subflow_send_ack(struct sock *ssk); void __mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk);
void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent); void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
bool __mptcp_close(struct sock *sk, long timeout); bool __mptcp_close(struct sock *sk, long timeout);
......
...@@ -1819,6 +1819,78 @@ static void subflow_state_change(struct sock *sk) ...@@ -1819,6 +1819,78 @@ static void subflow_state_change(struct sock *sk)
} }
} }
void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
{
struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
struct mptcp_sock *msk, *next, *head = NULL;
struct request_sock *req;
/* build a list of all unaccepted mptcp sockets */
spin_lock_bh(&queue->rskq_lock);
for (req = queue->rskq_accept_head; req; req = req->dl_next) {
struct mptcp_subflow_context *subflow;
struct sock *ssk = req->sk;
if (!sk_is_mptcp(ssk))
continue;
subflow = mptcp_subflow_ctx(ssk);
if (!subflow || !subflow->conn)
continue;
/* skip if already in list */
msk = mptcp_sk(subflow->conn);
if (msk->dl_next || msk == head)
continue;
sock_hold(subflow->conn);
msk->dl_next = head;
head = msk;
}
spin_unlock_bh(&queue->rskq_lock);
if (!head)
return;
/* can't acquire the msk socket lock under the subflow one,
* or will cause ABBA deadlock
*/
release_sock(listener_ssk);
for (msk = head; msk; msk = next) {
struct sock *sk = (struct sock *)msk;
lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
next = msk->dl_next;
msk->dl_next = NULL;
/* prevent the stack from later re-schedule the worker for
* this socket
*/
inet_sk_state_store(sk, TCP_CLOSE);
release_sock(sk);
/* lockdep will report a false positive ABBA deadlock
* between cancel_work_sync and the listener socket.
* The involved locks belong to different sockets WRT
* the existing AB chain.
* Using a per socket key is problematic as key
* deregistration requires process context and must be
* performed at socket disposal time, in atomic
* context.
* Just tell lockdep to consider the listener socket
* released here.
*/
mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
mptcp_cancel_work(sk);
mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_);
sock_put(sk);
}
/* we are still under the listener msk socket lock */
lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
}
static int subflow_ulp_init(struct sock *sk) static int subflow_ulp_init(struct sock *sk)
{ {
struct inet_connection_sock *icsk = inet_csk(sk); struct inet_connection_sock *icsk = inet_csk(sk);
......
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