On 8/9/21 9:14 PM, Desmond Cheong Zhi Xi wrote:
> struct sock.sk_timer should be used as a sock cleanup timer. However,
> SCO uses it to implement sock timeouts.
>
> This causes issues because struct sock.sk_timer's callback is run in
> an IRQ context, and the timer callback function sco_sock_timeout takes
> a spin lock on the socket. However, other functions such as
> sco_conn_del and sco_conn_ready take the spin lock with interrupts
> enabled.
>
> This inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} lock usage could
> lead to deadlocks as reported by Syzbot [1]:
> CPU0
> ----
> lock(slock-AF_BLUETOOTH-BTPROTO_SCO);
> <Interrupt>
> lock(slock-AF_BLUETOOTH-BTPROTO_SCO);
>
> To fix this, we use delayed work to implement SCO sock timouts
> instead. This allows us to avoid taking the spin lock on the socket in
> an IRQ context, and corrects the misuse of struct sock.sk_timer.
>
> As a note, cancel_delayed_work is used instead of
> cancel_delayed_work_sync in sco_sock_set_timer and
> sco_sock_clear_timer to avoid a deadlock. In the future, the call to
> bh_lock_sock inside sco_sock_timeout should be changed to lock_sock to
> synchronize with other functions using lock_sock. However, since
> sco_sock_set_timer and sco_sock_clear_timer are sometimes called under
> the locked socket (in sco_connect and __sco_sock_close),
> cancel_delayed_work_sync might cause them to sleep until an
> sco_sock_timeout that has started finishes running. But
> sco_sock_timeout would also sleep until it can grab the lock_sock.
>
> Using cancel_delayed_work is fine because sco_sock_timeout does not
> change from run to run, hence there is no functional difference
> between:
> 1. waiting for a timeout to finish running before scheduling another
> timeout
> 2. scheduling another timeout while a timeout is running.
>
> Link: https://syzkaller.appspot.com/bug?id=9089d89de0502e120f234ca0fc8a703f7368b31e [1]
> Reported-by: syzbot+2f6d7c28bb4bf7e82060@xxxxxxxxxxxxxxxxxxxxxxxxx
> Tested-by: syzbot+2f6d7c28bb4bf7e82060@xxxxxxxxxxxxxxxxxxxxxxxxx
> Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@xxxxxxxxx>
> ---
> net/bluetooth/sco.c | 35 +++++++++++++++++++++++++++++------
> 1 file changed, 29 insertions(+), 6 deletions(-)
>
> diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
> index ffa2a77a3e4c..62e638f971a9 100644
> --- a/net/bluetooth/sco.c
> +++ b/net/bluetooth/sco.c
> @@ -48,6 +48,8 @@ struct sco_conn {
> spinlock_t lock;
> struct sock *sk;
>
> + struct delayed_work timeout_work;
> +
> unsigned int mtu;
> };
>
> @@ -74,9 +76,20 @@ struct sco_pinfo {
> #define SCO_CONN_TIMEOUT (HZ * 40)
> #define SCO_DISCONN_TIMEOUT (HZ * 2)
>
> -static void sco_sock_timeout(struct timer_list *t)
> +static void sco_sock_timeout(struct work_struct *work)
> {
> - struct sock *sk = from_timer(sk, t, sk_timer);
> + struct sco_conn *conn = container_of(work, struct sco_conn,
> + timeout_work.work);
> + struct sock *sk;
> +
> + sco_conn_lock(conn);
> + sk = conn->sk;
> + if (sk)
> + sock_hold(sk);
syzbot complains here that sk refcount can be zero at this time.
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 0 PID: 10451 at lib/refcount.c:25 refcount_warn_saturate+0x169/0x1e0 lib/refcount.c:25
Modules linked in:
CPU: 0 PID: 10451 Comm: kworker/0:8 Not tainted 5.14.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events sco_sock_timeout
RIP: 0010:refcount_warn_saturate+0x169/0x1e0 lib/refcount.c:25
Code: 09 31 ff 89 de e8 d7 c9 9e fd 84 db 0f 85 36 ff ff ff e8 8a c3 9e fd 48 c7 c7 20 8f e3 89 c6 05 e8 7f 81 09 01 e8 f0 98 16 05 <0f> 0b e9 17 ff ff ff e8 6b c3 9e fd 0f b6 1d cd 7f 81 09 31 ff 89
RSP: 0018:ffffc9001766fce8 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff88802cea3880 RSI: ffffffff815d87a5 RDI: fffff52002ecdf8f
RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000
R10: ffffffff815d25de R11: 0000000000000000 R12: ffff88806d23ce08
R13: ffff8880712c8080 R14: ffff88802edf4500 R15: ffff8880b9c51240
FS: 0000000000000000(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f3748c20000 CR3: 0000000017644000 CR4: 00000000001506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
__refcount_add include/linux/refcount.h:199 [inline]
__refcount_inc include/linux/refcount.h:250 [inline]
refcount_inc include/linux/refcount.h:267 [inline]
sock_hold include/net/sock.h:702 [inline]
sco_sock_timeout+0x216/0x290 net/bluetooth/sco.c:88
process_one_work+0x98d/0x1630 kernel/workqueue.c:2276
worker_thread+0x658/0x11f0 kernel/workqueue.c:2422
kthread+0x3e5/0x4d0 kernel/kthread.c:319
> + sco_conn_unlock(conn);
> +
> + if (!sk)
> + return;
>
> BT_DBG("sock %p state %d", sk, sk->sk_state);
>
> @@ -91,14 +104,21 @@ static void sco_sock_timeout(struct timer_list *t)
>
> static void sco_sock_set_timer(struct sock *sk, long timeout)
> {
> + if (!sco_pi(sk)->conn)
> + return;
> +
> BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout);
> - sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
> + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
> + schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout);
> }
>
> static void sco_sock_clear_timer(struct sock *sk)
> {
> + if (!sco_pi(sk)->conn)
> + return;
> +
> BT_DBG("sock %p state %d", sk, sk->sk_state);
> - sk_stop_timer(sk, &sk->sk_timer);
> + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
> }
>
> /* ---- SCO connections ---- */
> @@ -179,6 +199,9 @@ static void sco_conn_del(struct hci_conn *hcon, int err)
> bh_unlock_sock(sk);
> sco_sock_kill(sk);
> sock_put(sk);
> +
> + /* Ensure no more work items will run before freeing conn. */
Maybe you should have done this cancel_delayed_work_sync() before the prior sock_put(sk) ?
> + cancel_delayed_work_sync(&conn->timeout_work);
> }
>
> hcon->sco_data = NULL;
> @@ -193,6 +216,8 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk,
> sco_pi(sk)->conn = conn;
> conn->sk = sk;
>
> + INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout);
> +
> if (parent)
> bt_accept_enqueue(parent, sk, true);
> }
> @@ -500,8 +525,6 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock,
>
> sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT;
>
> - timer_setup(&sk->sk_timer, sco_sock_timeout, 0);
> -
> bt_sock_link(&sco_sk_list, sk);
> return sk;
> }
>
