Bluetooth: Fix missing hdev locking for LE scan cleanup

The hci_conn objects don't have a dedicated lock themselves but rely
on the caller to hold the hci_dev lock for most types of access. The
hci_conn_timeout() function has so far sent certain HCI commands based
on the hci_conn state which has been possible without holding the
hci_dev lock.

The recent changes to do LE scanning before connect attempts added
even more operations to hci_conn and hci_dev from hci_conn_timeout,
thereby exposing potential race conditions with the hci_dev and
hci_conn states.

As an example of such a race, here there's a timeout but an
l2cap_sock_connect() call manages to race with the cleanup routine:

[Oct21 08:14] l2cap_chan_timeout: chan ee4b12c0 state BT_CONNECT
[  +0.000004] l2cap_chan_close: chan ee4b12c0 state BT_CONNECT
[  +0.000002] l2cap_chan_del: chan ee4b12c0, conn f3141580, err 111, state BT_CONNECT
[  +0.000002] l2cap_sock_teardown_cb: chan ee4b12c0 state BT_CONNECT
[  +0.000005] l2cap_chan_put: chan ee4b12c0 orig refcnt 4
[  +0.000010] hci_conn_drop: hcon f53d56e0 orig refcnt 1
[  +0.000013] l2cap_chan_put: chan ee4b12c0 orig refcnt 3
[  +0.000063] hci_conn_timeout: hcon f53d56e0 state BT_CONNECT
[  +0.000049] hci_conn_params_del: addr ee:0d:30:09:53:1f (type 1)
[  +0.000002] hci_chan_list_flush: hcon f53d56e0
[  +0.000001] hci_chan_del: hci0 hcon f53d56e0 chan f4e7ccc0
[  +0.004528] l2cap_sock_create: sock e708fc00
[  +0.000023] l2cap_chan_create: chan ee4b1770
[  +0.000001] l2cap_chan_hold: chan ee4b1770 orig refcnt 1
[  +0.000002] l2cap_sock_init: sk ee4b3390
[  +0.000029] l2cap_sock_bind: sk ee4b3390
[  +0.000010] l2cap_sock_setsockopt: sk ee4b3390
[  +0.000037] l2cap_sock_connect: sk ee4b3390
[  +0.000002] l2cap_chan_connect: 00:02:72:d9:e5:8b -> ee:0d:30:09:53:1f (type 2) psm 0x00
[  +0.000002] hci_get_route: 00:02:72:d9:e5:8b -> ee:0d:30:09:53:1f
[  +0.000001] hci_dev_hold: hci0 orig refcnt 8
[  +0.000003] hci_conn_hold: hcon f53d56e0 orig refcnt 0

Above the l2cap_chan_connect() shouldn't have been able to reach the
hci_conn f53d56e0 anymore but since hci_conn_timeout didn't do proper
locking that's not the case. The end result is a reference to hci_conn
that's not in the conn_hash list, resulting in list corruption when
trying to remove it later:

[Oct21 08:15] l2cap_chan_timeout: chan ee4b1770 state BT_CONNECT
[  +0.000004] l2cap_chan_close: chan ee4b1770 state BT_CONNECT
[  +0.000003] l2cap_chan_del: chan ee4b1770, conn f3141580, err 111, state BT_CONNECT
[  +0.000001] l2cap_sock_teardown_cb: chan ee4b1770 state BT_CONNECT
[  +0.000005] l2cap_chan_put: chan ee4b1770 orig refcnt 4
[  +0.000002] hci_conn_drop: hcon f53d56e0 orig refcnt 1
[  +0.000015] l2cap_chan_put: chan ee4b1770 orig refcnt 3
[  +0.000038] hci_conn_timeout: hcon f53d56e0 state BT_CONNECT
[  +0.000003] hci_chan_list_flush: hcon f53d56e0
[  +0.000002] hci_conn_hash_del: hci0 hcon f53d56e0
[  +0.000001] ------------[ cut here ]------------
[  +0.000461] WARNING: CPU: 0 PID: 1782 at lib/list_debug.c:56 __list_del_entry+0x3f/0x71()
[  +0.000839] list_del corruption, f53d56e0->prev is LIST_POISON2 (00000200)

The necessary fix is unfortunately more complicated than just adding
hci_dev_lock/unlock calls to the hci_conn_timeout() call path.
Particularly, the hci_conn_del() API, which expects the hci_dev lock to
be held, performs a cancel_delayed_work_sync(&hcon->disc_work) which
would lead to a deadlock if the hci_conn_timeout() call path tries to
acquire the same lock.

This patch solves the problem by deferring the cleanup work to a
separate work callback. To protect against the hci_dev or hci_conn
going away meanwhile temporary references are taken with the help of
hci_dev_hold() and hci_conn_get().

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Cc: stable@vger.kernel.org # 4.3

2 files changed, 44 insertions, 9 deletions

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 44fb95685611..0015d087d8b1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -471,6 +471,7 @@ struct hci_conn {
         struct delayed_work auto_accept_work;
         struct delayed_work idle_work;
         struct delayed_work le_conn_timeout;
+        struct work_struct  le_scan_cleanup;
 
         struct device   dev;
         struct dentry   *debugfs;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 2dda439c8cb8..ec4836f243bc 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -137,18 +137,51 @@ static void hci_conn_cleanup(struct hci_conn *conn)
         hci_conn_put(conn);
 }
 
-/* This function requires the caller holds hdev->lock */
-static void hci_connect_le_scan_remove(struct hci_conn *conn)
+static void le_scan_cleanup(struct work_struct *work)
 {
-        hci_connect_le_scan_cleanup(conn);
+        struct hci_conn *conn = container_of(work, struct hci_conn,
+                                             le_scan_cleanup);
+        struct hci_dev *hdev = conn->hdev;
+        struct hci_conn *c = NULL;
 
-        /* We can't call hci_conn_del here since that would deadlock
-         * with trying to call cancel_delayed_work_sync(&conn->disc_work).
-         * Instead, call just hci_conn_cleanup() which contains the bare
-         * minimum cleanup operations needed for a connection in this
-         * state.
+        BT_DBG("%s hcon %p", hdev->name, conn);
+
+        hci_dev_lock(hdev);
+
+        /* Check that the hci_conn is still around */
+        rcu_read_lock();
+        list_for_each_entry_rcu(c, &hdev->conn_hash.list, list) {
+                if (c == conn)
+                        break;
+        }
+        rcu_read_unlock();
+
+        if (c == conn) {
+                hci_connect_le_scan_cleanup(conn);
+                hci_conn_cleanup(conn);
+        }
+
+        hci_dev_unlock(hdev);
+        hci_dev_put(hdev);
+        hci_conn_put(conn);
+}
+
+static void hci_connect_le_scan_remove(struct hci_conn *conn)
+{
+        BT_DBG("%s hcon %p", conn->hdev->name, conn);
+
+        /* We can't call hci_conn_del/hci_conn_cleanup here since that
+         * could deadlock with another hci_conn_del() call that's holding
+         * hci_dev_lock and doing cancel_delayed_work_sync(&conn->disc_work).
+         * Instead, grab temporary extra references to the hci_dev and
+         * hci_conn and perform the necessary cleanup in a separate work
+         * callback.
          */
-        hci_conn_cleanup(conn);
+
+        hci_dev_hold(conn->hdev);
+        hci_conn_get(conn);
+
+        schedule_work(&conn->le_scan_cleanup);
 }
 
 static void hci_acl_create_connection(struct hci_conn *conn)
@@ -580,6 +613,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
         INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept);
         INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle);
         INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout);
+        INIT_WORK(&conn->le_scan_cleanup, le_scan_cleanup);
 
         atomic_set(&conn->refcnt, 0);