linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>
To: marcel@holtmann.org, johan.hedberg@gmail.com,
	luiz.dentz@gmail.com, davem@davemloft.net, kuba@kernel.org,
	sudipm.mukherjee@gmail.com
Cc: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>,
	linux-bluetooth@vger.kernel.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org, skhan@linuxfoundation.org,
	gregkh@linuxfoundation.org,
	linux-kernel-mentees@lists.linuxfoundation.org,
	syzbot+2f6d7c28bb4bf7e82060@syzkaller.appspotmail.com
Subject: [RESEND PATCH v5 1/6] Bluetooth: schedule SCO timeouts with delayed_work
Date: Wed,  4 Aug 2021 23:47:07 +0800	[thread overview]
Message-ID: <20210804154712.929986-2-desmondcheongzx@gmail.com> (raw)
In-Reply-To: <20210804154712.929986-1-desmondcheongzx@gmail.com>

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@syzkaller.appspotmail.com
Tested-by: syzbot+2f6d7c28bb4bf7e82060@syzkaller.appspotmail.com
Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>
---
 net/bluetooth/sco.c | 41 +++++++++++++++++++++++++++++++++++------
 1 file changed, 35 insertions(+), 6 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index ffa2a77a3e4c..89cb987ca9eb 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);
+	sco_conn_unlock(conn);
+
+	if (!sk)
+		return;
 
 	BT_DBG("sock %p state %d", sk, sk->sk_state);
 
@@ -91,14 +104,27 @@ static void sco_sock_timeout(struct timer_list *t)
 
 static void sco_sock_set_timer(struct sock *sk, long timeout)
 {
+	struct delayed_work *work;
+
+	if (!sco_pi(sk)->conn)
+		return;
+	work = &sco_pi(sk)->conn->timeout_work;
+
 	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(work);
+	schedule_delayed_work(work, timeout);
 }
 
 static void sco_sock_clear_timer(struct sock *sk)
 {
+	struct delayed_work *work;
+
+	if (!sco_pi(sk)->conn)
+		return;
+	work = &sco_pi(sk)->conn->timeout_work;
+
 	BT_DBG("sock %p state %d", sk, sk->sk_state);
-	sk_stop_timer(sk, &sk->sk_timer);
+	cancel_delayed_work(work);
 }
 
 /* ---- SCO connections ---- */
@@ -179,6 +205,9 @@ 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. */
+		cancel_delayed_work_sync(&conn->timeout_work);
 	}
 
 	hcon->sco_data = NULL;
@@ -193,6 +222,8 @@ 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 +531,6 @@ 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;
 }
-- 
2.25.1


  reply	other threads:[~2021-08-04 15:48 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-04 15:47 [RESEND PATCH v5 0/6] Bluetooth: fix locking and socket killing in SCO and RFCOMM Desmond Cheong Zhi Xi
2021-08-04 15:47 ` Desmond Cheong Zhi Xi [this message]
2021-08-05 19:06   ` [RESEND PATCH v5 1/6] Bluetooth: schedule SCO timeouts with delayed_work Luiz Augusto von Dentz
2021-08-09  4:04     ` Desmond Cheong Zhi Xi
2021-08-09 16:42       ` Luiz Augusto von Dentz
2021-08-04 15:47 ` [RESEND PATCH v5 2/6] Bluetooth: avoid circular locks in sco_sock_connect Desmond Cheong Zhi Xi
2021-08-04 15:47 ` [RESEND PATCH v5 3/6] Bluetooth: switch to lock_sock in SCO Desmond Cheong Zhi Xi
2021-08-04 15:47 ` [RESEND PATCH v5 4/6] Bluetooth: serialize calls to sco_sock_{set,clear}_timer Desmond Cheong Zhi Xi
2021-08-04 15:47 ` [RESEND PATCH v5 5/6] Bluetooth: switch to lock_sock in RFCOMM Desmond Cheong Zhi Xi
2021-08-04 15:47 ` [RESEND PATCH v5 6/6] Bluetooth: fix repeated calls to sco_sock_kill Desmond Cheong Zhi Xi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210804154712.929986-2-desmondcheongzx@gmail.com \
    --to=desmondcheongzx@gmail.com \
    --cc=davem@davemloft.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=johan.hedberg@gmail.com \
    --cc=kuba@kernel.org \
    --cc=linux-bluetooth@vger.kernel.org \
    --cc=linux-kernel-mentees@lists.linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luiz.dentz@gmail.com \
    --cc=marcel@holtmann.org \
    --cc=netdev@vger.kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=sudipm.mukherjee@gmail.com \
    --cc=syzbot+2f6d7c28bb4bf7e82060@syzkaller.appspotmail.com \
    --subject='Re: [RESEND PATCH v5 1/6] Bluetooth: schedule SCO timeouts with delayed_work' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).