Connecting the same socket twice consecutively in sco_sock_connect()
could lead to a race condition where two sco_conn objects are created
but only one is associated with the socket. If the socket is closed
before the SCO connection is established, the timer associated with the
dangling sco_conn object won't be canceled. As the sock object is being
freed, the use-after-free problem happens when the timer callback
function sco_sock_timeout() accesses the socket. Here's the call trace:
dump_stack+0x107/0x163
? refcount_inc+0x1c/
print_address_description.constprop.0+0x1c/0x47e
? refcount_inc+0x1c/0x7b
kasan_report+0x13a/0x173
? refcount_inc+0x1c/0x7b
check_memory_region+0x132/0x139
refcount_inc+0x1c/0x7b
sco_sock_timeout+0xb2/0x1ba
process_one_work+0x739/0xbd1
? cancel_delayed_work+0x13f/0x13f
? __raw_spin_lock_init+0xf0/0xf0
? to_kthread+0x59/0x85
worker_thread+0x593/0x70e
kthread+0x346/0x35a
? drain_workqueue+0x31a/0x31a
? kthread_bind+0x4b/0x4b
ret_from_fork+0x1f/0x30
Signed-off-by: Ying Hsu <[email protected]>
Reviewed-by: Joseph Hwang <[email protected]>
---
Tested this commit using a C reproducer on qemu-x86_64 for 8 hours.
net/bluetooth/sco.c | 21 +++++++++++++--------
1 file changed, 13 insertions(+), 8 deletions(-)
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 8eabf41b2993..380c63194736 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -574,19 +574,24 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
- if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND)
- return -EBADFD;
+ lock_sock(sk);
+ if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+ err = -EBADFD;
+ goto done;
+ }
- if (sk->sk_type != SOCK_SEQPACKET)
- return -EINVAL;
+ if (sk->sk_type != SOCK_SEQPACKET) {
+ err = -EINVAL;
+ goto done;
+ }
hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR);
- if (!hdev)
- return -EHOSTUNREACH;
+ if (!hdev) {
+ err = -EHOSTUNREACH;
+ goto done;
+ }
hci_dev_lock(hdev);
- lock_sock(sk);
-
/* Set destination address and psm */
bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
--
2.35.1.1021.g381101b075-goog
Hi Ying,
On Thu, Mar 24, 2022 at 8:31 PM Ying Hsu <[email protected]> wrote:
>
> Connecting the same socket twice consecutively in sco_sock_connect()
> could lead to a race condition where two sco_conn objects are created
> but only one is associated with the socket. If the socket is closed
> before the SCO connection is established, the timer associated with the
> dangling sco_conn object won't be canceled. As the sock object is being
> freed, the use-after-free problem happens when the timer callback
> function sco_sock_timeout() accesses the socket. Here's the call trace:
>
> dump_stack+0x107/0x163
> ? refcount_inc+0x1c/
> print_address_description.constprop.0+0x1c/0x47e
> ? refcount_inc+0x1c/0x7b
> kasan_report+0x13a/0x173
> ? refcount_inc+0x1c/0x7b
> check_memory_region+0x132/0x139
> refcount_inc+0x1c/0x7b
> sco_sock_timeout+0xb2/0x1ba
> process_one_work+0x739/0xbd1
> ? cancel_delayed_work+0x13f/0x13f
> ? __raw_spin_lock_init+0xf0/0xf0
> ? to_kthread+0x59/0x85
> worker_thread+0x593/0x70e
> kthread+0x346/0x35a
> ? drain_workqueue+0x31a/0x31a
> ? kthread_bind+0x4b/0x4b
> ret_from_fork+0x1f/0x30
>
> Signed-off-by: Ying Hsu <[email protected]>
> Reviewed-by: Joseph Hwang <[email protected]>
> ---
> Tested this commit using a C reproducer on qemu-x86_64 for 8 hours.
We should probably add a link or something to the reproducer then, was
it syzbot? It does have some instructions on how to link its issues.
> net/bluetooth/sco.c | 21 +++++++++++++--------
> 1 file changed, 13 insertions(+), 8 deletions(-)
>
> diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
> index 8eabf41b2993..380c63194736 100644
> --- a/net/bluetooth/sco.c
> +++ b/net/bluetooth/sco.c
> @@ -574,19 +574,24 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
> addr->sa_family != AF_BLUETOOTH)
> return -EINVAL;
>
> - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND)
> - return -EBADFD;
> + lock_sock(sk);
> + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
> + err = -EBADFD;
> + goto done;
> + }
>
> - if (sk->sk_type != SOCK_SEQPACKET)
> - return -EINVAL;
> + if (sk->sk_type != SOCK_SEQPACKET) {
> + err = -EINVAL;
> + goto done;
> + }
>
> hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR);
> - if (!hdev)
> - return -EHOSTUNREACH;
> + if (!hdev) {
> + err = -EHOSTUNREACH;
> + goto done;
> + }
> hci_dev_lock(hdev);
>
> - lock_sock(sk);
> -
Also are we sure we are not introducing a locking hierarchy problem
here? Previously we had hci_dev_lock then sock_lock now it is the
opposite, or perhaps we never want to have them at the same time?
> /* Set destination address and psm */
> bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
>
> --
> 2.35.1.1021.g381101b075-goog
>
--
Luiz Augusto von Dentz