[PATCHv2 0/2] Fix kernel crash in rfcomm/l2cap

[PATCHv2 0/2] Fix kernel crash in rfcomm/l2cap

[Emeltchenko Andrei]

From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>

Version 2 of patches fixing kernel crash in RFCOMM / L2CAP.

Do not delete l2cap channel and socket sk when sk is owned by user.
To delete l2cap channel standard timer is used.

lock_sock and release_sock do not hold a normal spinlock directly but 
instead hold the owner field. This means bh_lock_sock can still execute
even if the socket is "locked". More info can be found here:
http://www.linuxfoundation.org/collaborate/workgroups/networking/socketlocks

Andrei Emeltchenko (2):
  Bluetooth: Check sk is not owned before freeing l2cap_conn
  Bluetooth: timer check sk is not owned before freeing

 net/bluetooth/l2cap.c |   57 ++++++++++++++++++++++++++++++++++++++----------
 1 files changed, 45 insertions(+), 12 deletions(-)

[PATCHv2 1/2] Bluetooth: Check sk is not owned before freeing l2cap_conn

[Emeltchenko Andrei]

From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>

Check that socket sk is not locked in user process before removing
l2cap connection handler.

krfcommd kernel thread may be preempted with l2cap tasklet which remove
l2cap_conn structure. If krfcommd is in process of sending of RFCOMM reply
(like "RFCOMM UA" reply to "RFCOMM DISC") then kernel crash happens.

...
[  694.175933] Unable to handle kernel NULL pointer dereference at virtual address 00000000
[  694.184936] pgd = c0004000
[  694.187683] [00000000] *pgd=00000000
[  694.191711] Internal error: Oops: 5 [#1] PREEMPT
[  694.196350] last sysfs file: /sys/devices/platform/hci_h4p/firmware/hci_h4p/loading
[  694.260375] CPU: 0    Not tainted  (2.6.32.10 #1)
[  694.265106] PC is at l2cap_sock_sendmsg+0x43c/0x73c [l2cap]
[  694.270721] LR is at 0xd7017303
...
[  694.525085] Backtrace:
[  694.527587] [<bf266be0>] (l2cap_sock_sendmsg+0x0/0x73c [l2cap]) from [<c02f2cc8>] (sock_sendmsg+0xb8/0xd8)
[  694.537292] [<c02f2c10>] (sock_sendmsg+0x0/0xd8) from [<c02f3044>] (kernel_sendmsg+0x48/0x80)

Modified version after comments of Gustavo F. Padovan <gustavo@padovan.org>

Fixes: NB#164721 - Device reboots while executing OBEX FTP tests

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
---
 net/bluetooth/l2cap.c |   25 +++++++++++++++++++++++++
 1 files changed, 25 insertions(+), 0 deletions(-)

diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 1874ece..0221d05 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -2708,6 +2708,13 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd
 		break;
 
 	default:
+		/* don't delete l2cap channel if sk is owned by user */
+		if (sock_owned_by_user(sk)) {
+			sk->sk_state = BT_DISCONN;
+			l2cap_sock_clear_timer(sk);
+			l2cap_sock_set_timer(sk, HZ);
+			break;
+		}
 		l2cap_chan_del(sk, ECONNREFUSED);
 		break;
 	}
@@ -2914,6 +2921,15 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd
 		del_timer(&l2cap_pi(sk)->monitor_timer);
 	}
 
+	/* don't delete l2cap channel if sk is owned by user */
+	if (sock_owned_by_user(sk)) {
+		sk->sk_state = BT_DISCONN;
+		l2cap_sock_clear_timer(sk);
+		l2cap_sock_set_timer(sk, HZ);
+		bh_unlock_sock(sk);
+		return 0;
+	}
+
 	l2cap_chan_del(sk, ECONNRESET);
 	bh_unlock_sock(sk);
 
@@ -2944,6 +2960,15 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd
 		del_timer(&l2cap_pi(sk)->monitor_timer);
 	}
 
+	/* don't delete l2cap channel if sk is owned by user */
+	if (sock_owned_by_user(sk)) {
+		sk->sk_state = BT_DISCONN;
+		l2cap_sock_clear_timer(sk);
+		l2cap_sock_set_timer(sk, HZ);
+		bh_unlock_sock(sk);
+		return 0;
+	}
+
 	l2cap_chan_del(sk, 0);
 	bh_unlock_sock(sk);
 
-- 
1.7.0.4

[PATCHv2 2/2] Bluetooth: timer check sk is not owned before freeing

[Emeltchenko Andrei]

From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>

In timer context we might delete l2cap channel used by krfcommd.
The check makes sure that sk is not owned.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
---
 net/bluetooth/l2cap.c |   32 ++++++++++++++++++++------------
 1 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 0221d05..2f8ac5d 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -73,6 +73,18 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				u8 code, u8 ident, u16 dlen, void *data);
 
 /* ---- L2CAP timers ---- */
+static void l2cap_sock_set_timer(struct sock *sk, long timeout)
+{
+	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
+}
+
+static void l2cap_sock_clear_timer(struct sock *sk)
+{
+	BT_DBG("sock %p state %d", sk, sk->sk_state);
+	sk_stop_timer(sk, &sk->sk_timer);
+}
+
 static void l2cap_sock_timeout(unsigned long arg)
 {
 	struct sock *sk = (struct sock *) arg;
@@ -82,6 +94,14 @@ static void l2cap_sock_timeout(unsigned long arg)
 
 	bh_lock_sock(sk);
 
+	if (sock_owned_by_user(sk)) {
+		/* sk is owned by user. Try again later */
+		l2cap_sock_set_timer(sk, HZ * 2);
+		bh_unlock_sock(sk);
+		sock_put(sk);
+		return;
+	}
+
 	if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
 		reason = ECONNREFUSED;
 	else if (sk->sk_state == BT_CONNECT &&
@@ -98,18 +118,6 @@ static void l2cap_sock_timeout(unsigned long arg)
 	sock_put(sk);
 }
 
-static void l2cap_sock_set_timer(struct sock *sk, long timeout)
-{
-	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
-}
-
-static void l2cap_sock_clear_timer(struct sock *sk)
-{
-	BT_DBG("sock %p state %d", sk, sk->sk_state);
-	sk_stop_timer(sk, &sk->sk_timer);
-}
-
 /* ---- L2CAP channels ---- */
 static struct sock *__l2cap_get_chan_by_dcid(struct l2cap_chan_list *l, u16 cid)
 {
-- 
1.7.0.4

Re: [PATCHv2 2/2] Bluetooth: timer check sk is not owned before freeing

[Gustavo F. Padovan]

Hi Andrei,

* Emeltchenko Andrei <Andrei.Emeltchenko.news@gmail.com> [2010-08-12 16:25:37 +0300]:

> From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
> 
> In timer context we might delete l2cap channel used by krfcommd.
> The check makes sure that sk is not owned.
> 
> Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
> ---
>  net/bluetooth/l2cap.c |   32 ++++++++++++++++++++------------
>  1 files changed, 20 insertions(+), 12 deletions(-)
> 
> diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
> index 0221d05..2f8ac5d 100644
> --- a/net/bluetooth/l2cap.c
> +++ b/net/bluetooth/l2cap.c
> @@ -73,6 +73,18 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
>  				u8 code, u8 ident, u16 dlen, void *data);
>  
>  /* ---- L2CAP timers ---- */
> +static void l2cap_sock_set_timer(struct sock *sk, long timeout)
> +{
> +	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
> +	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
> +}
> +
> +static void l2cap_sock_clear_timer(struct sock *sk)
> +{
> +	BT_DBG("sock %p state %d", sk, sk->sk_state);
> +	sk_stop_timer(sk, &sk->sk_timer);
> +}
> +
>  static void l2cap_sock_timeout(unsigned long arg)
>  {
>  	struct sock *sk = (struct sock *) arg;
> @@ -82,6 +94,14 @@ static void l2cap_sock_timeout(unsigned long arg)
>  
>  	bh_lock_sock(sk);
>  
> +	if (sock_owned_by_user(sk)) {
> +		/* sk is owned by user. Try again later */
> +		l2cap_sock_set_timer(sk, HZ * 2);
> +		bh_unlock_sock(sk);
> +		sock_put(sk);
> +		return;
> +	}

I'm not sure if I like this defer through timers. OTOH could be too much
overhead to do this defer through a work queue.
Also I think that 2 seconds is too much for this timer. 200 miliseconds
should be enough, what do you think?

-- 
Gustavo F. Padovan
http://padovan.org

[PATCHv2 1/2] Bluetooth: Check sk is not owned before freeing l2cap_conn

[Emeltchenko Andrei]

From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>

Check that socket sk is not locked in user process before removing
l2cap connection handler.

krfcommd kernel thread may be preempted with l2cap tasklet which remove
l2cap_conn structure. If krfcommd is in process of sending of RFCOMM reply
(like "RFCOMM UA" reply to "RFCOMM DISC") then kernel crash happens.

...
[  694.175933] Unable to handle kernel NULL pointer dereference at virtual address 00000000
[  694.184936] pgd = c0004000
[  694.187683] [00000000] *pgd=00000000
[  694.191711] Internal error: Oops: 5 [#1] PREEMPT
[  694.196350] last sysfs file: /sys/devices/platform/hci_h4p/firmware/hci_h4p/loading
[  694.260375] CPU: 0    Not tainted  (2.6.32.10 #1)
[  694.265106] PC is at l2cap_sock_sendmsg+0x43c/0x73c [l2cap]
[  694.270721] LR is at 0xd7017303
...
[  694.525085] Backtrace:
[  694.527587] [<bf266be0>] (l2cap_sock_sendmsg+0x0/0x73c [l2cap]) from [<c02f2cc8>] (sock_sendmsg+0xb8/0xd8)
[  694.537292] [<c02f2c10>] (sock_sendmsg+0x0/0xd8) from [<c02f3044>] (kernel_sendmsg+0x48/0x80)
...

Modified version after comments of Gustavo F. Padovan <gustavo@padovan.org>

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
---
 net/bluetooth/l2cap.c |   25 +++++++++++++++++++++++++
 1 files changed, 25 insertions(+), 0 deletions(-)

diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index bb00015..11060d6 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -2927,6 +2927,13 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd
 		break;
 
 	default:
+		/* don't delete l2cap channel if sk is owned by user */
+		if (sock_owned_by_user(sk)) {
+			sk->sk_state = BT_DISCONN;
+			l2cap_sock_clear_timer(sk);
+			l2cap_sock_set_timer(sk, HZ);
+			break;
+		}
 		l2cap_chan_del(sk, ECONNREFUSED);
 		break;
 	}
@@ -3135,6 +3142,15 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd
 		del_timer(&l2cap_pi(sk)->ack_timer);
 	}
 
+	/* don't delete l2cap channel if sk is owned by user */
+	if (sock_owned_by_user(sk)) {
+		sk->sk_state = BT_DISCONN;
+		l2cap_sock_clear_timer(sk);
+		l2cap_sock_set_timer(sk, HZ);
+		bh_unlock_sock(sk);
+		return 0;
+	}
+
 	l2cap_chan_del(sk, ECONNRESET);
 	bh_unlock_sock(sk);
 
@@ -3167,6 +3183,15 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd
 		del_timer(&l2cap_pi(sk)->ack_timer);
 	}
 
+	/* don't delete l2cap channel if sk is owned by user */
+	if (sock_owned_by_user(sk)) {
+		sk->sk_state = BT_DISCONN;
+		l2cap_sock_clear_timer(sk);
+		l2cap_sock_set_timer(sk, HZ);
+		bh_unlock_sock(sk);
+		return 0;
+	}
+
 	l2cap_chan_del(sk, 0);
 	bh_unlock_sock(sk);
 
-- 
1.7.0.4

[PATCHv2 2/2] Bluetooth: timer check sk is not owned before freeing

[Emeltchenko Andrei]

From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>

In timer context we might delete l2cap channel used by krfcommd.
The check makes sure that sk is not owned.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
---
 net/bluetooth/l2cap.c |   32 ++++++++++++++++++++------------
 1 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 11060d6..1a6c5bb 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -84,6 +84,18 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				u8 code, u8 ident, u16 dlen, void *data);
 
 /* ---- L2CAP timers ---- */
+static void l2cap_sock_set_timer(struct sock *sk, long timeout)
+{
+	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
+}
+
+static void l2cap_sock_clear_timer(struct sock *sk)
+{
+	BT_DBG("sock %p state %d", sk, sk->sk_state);
+	sk_stop_timer(sk, &sk->sk_timer);
+}
+
 static void l2cap_sock_timeout(unsigned long arg)
 {
 	struct sock *sk = (struct sock *) arg;
@@ -93,6 +105,14 @@ static void l2cap_sock_timeout(unsigned long arg)
 
 	bh_lock_sock(sk);
 
+	if (sock_owned_by_user(sk)) {
+		/* sk is owned by user. Try again later */
+		l2cap_sock_set_timer(sk, HZ * 2);
+		bh_unlock_sock(sk);
+		sock_put(sk);
+		return;
+	}
+
 	if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
 		reason = ECONNREFUSED;
 	else if (sk->sk_state == BT_CONNECT &&
@@ -109,18 +129,6 @@ static void l2cap_sock_timeout(unsigned long arg)
 	sock_put(sk);
 }
 
-static void l2cap_sock_set_timer(struct sock *sk, long timeout)
-{
-	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
-}
-
-static void l2cap_sock_clear_timer(struct sock *sk)
-{
-	BT_DBG("sock %p state %d", sk, sk->sk_state);
-	sk_stop_timer(sk, &sk->sk_timer);
-}
-
 /* ---- L2CAP channels ---- */
 static struct sock *__l2cap_get_chan_by_dcid(struct l2cap_chan_list *l, u16 cid)
 {
-- 
1.7.0.4