[PATCH] Bluetooth: fix inconsistent lock state in sco

From: Desmond Cheong Zhi Xi
Date: Mon Jun 28 2021 - 03:50:21 EST


Syzbot reported an inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} lock
usage in sco_conn_del and sco_sock_timeout that could lead to
deadlocks:
https://syzkaller.appspot.com/bug?id=9089d89de0502e120f234ca0fc8a703f7368b31e

This inconsistent lock state can also happen between sco_conn_ready
and sco_sock_timeout.

The issue is that these three functions take a spin lock on the
socket, but sco_sock_timeout is called from an IRQ context. Since
bh_lock_sock calls spin_lock but does not disable softirqs, this could
lead to deadlocks:

CPU0
----
lock(slock-AF_BLUETOOTH-BTPROTO_SCO);
<Interrupt>
lock(slock-AF_BLUETOOTH-BTPROTO_SCO);

*** DEADLOCK ***

We fix this by replacing bh_lock_sock with spin_lock_bh in
sco_conn_del and sco_conn_ready.

Additionally, to avoid regressions, we pull the clean-up code out from
sco_chan_del and use it directly in sco_conn_del. This is necessary
because sco_chan_del makes a call to sco_conn_lock which takes an
SOFTIRQ-unsafe lock. This means that calling sco_chan_del while
holding the socket lock would result in a SOFTIRQ-safe ->
SOFTIRQ-unsafe lock hierarchy between slock-AF_BLUETOOTH-BTPROTO_SCO
and &conn->lock#2. This could lead to a deadlock as well:

CPU0 CPU1
---- ----
lock(&conn->lock#2);
local_irq_disable();
lock(slock-AF_BLUETOOTH-BTPROTO_SCO);
lock(&conn->lock#2);
<Interrupt>
lock(slock-AF_BLUETOOTH-BTPROTO_SCO);

*** DEADLOCK ***

Pulling out the code from sco_chan_del allows us to avoid this lock
dependency by holding the two locks for only their required critical
sections.

Reported-and-tested-by: syzbot+2f6d7c28bb4bf7e82060@xxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@xxxxxxxxx>
---
net/bluetooth/sco.c | 28 ++++++++++++++++++++--------
1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 3bd41563f118..d05629d7cc55 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -173,10 +173,22 @@ static void sco_conn_del(struct hci_conn *hcon, int err)

if (sk) {
sock_hold(sk);
- bh_lock_sock(sk);
+
+ spin_lock_bh(&sk->sk_lock.slock);
sco_sock_clear_timer(sk);
- sco_chan_del(sk, err);
- bh_unlock_sock(sk);
+ sco_pi(sk)->conn = NULL;
+ if (conn->hcon)
+ hci_conn_drop(conn->hcon);
+ sk->sk_state = BT_CLOSED;
+ sk->sk_err = err;
+ sk->sk_state_change(sk);
+ sock_set_flag(sk, SOCK_ZAPPED);
+ spin_unlock_bh(&sk->sk_lock.slock);
+
+ sco_conn_lock(conn);
+ conn->sk = NULL;
+ sco_conn_unlock(conn);
+
sco_sock_kill(sk);
sock_put(sk);
}
@@ -1084,10 +1096,10 @@ static void sco_conn_ready(struct sco_conn *conn)

if (sk) {
sco_sock_clear_timer(sk);
- bh_lock_sock(sk);
+ spin_lock_bh(&sk->sk_lock.slock);
sk->sk_state = BT_CONNECTED;
sk->sk_state_change(sk);
- bh_unlock_sock(sk);
+ spin_unlock_bh(&sk->sk_lock.slock);
} else {
sco_conn_lock(conn);

@@ -1102,12 +1114,12 @@ static void sco_conn_ready(struct sco_conn *conn)
return;
}

- bh_lock_sock(parent);
+ spin_lock_bh(&parent->sk_lock.slock);

sk = sco_sock_alloc(sock_net(parent), NULL,
BTPROTO_SCO, GFP_ATOMIC, 0);
if (!sk) {
- bh_unlock_sock(parent);
+ spin_unlock_bh(&parent->sk_lock.slock);
sco_conn_unlock(conn);
return;
}
@@ -1128,7 +1140,7 @@ static void sco_conn_ready(struct sco_conn *conn)
/* Wake up parent */
parent->sk_data_ready(parent);

- bh_unlock_sock(parent);
+ spin_unlock_bh(&parent->sk_lock.slock);

sco_conn_unlock(conn);
}
--
2.25.1