summaryrefslogtreecommitdiffstats
path: root/include/net
diff options
context:
space:
mode:
authorDavid Herrmann <dh.herrmann@gmail.com>2013-04-06 20:28:45 +0200
committerGustavo Padovan <gustavo.padovan@collabora.co.uk>2013-04-17 03:03:43 -0300
commit2c8e1411e93391c5a78f55b09697a997474a4707 (patch)
tree3881d50853b94b260ba15b09e9c3b07a951fa482 /include/net
parent9c903e373c11f62d62bce1209f662ca92589a075 (diff)
Bluetooth: l2cap: add l2cap_user sub-modules
Several sub-modules like HIDP, rfcomm, ... need to track l2cap connections. The l2cap_conn->hcon->dev object is used as parent for sysfs devices so the sub-modules need to be notified when the hci_conn object is removed from sysfs. As submodules normally use the l2cap layer, the l2cap_user objects are registered there instead of on the underlying hci_conn object. This avoids any direct dependency on the HCI layer and lets the l2cap core handle any specifics. This patch introduces l2cap_user objects which contain a "probe" and "remove" callback. You can register them on any l2cap_conn object and if it is active, the "probe" callback will get called. Otherwise, an error is returned. The l2cap_conn object will call your "remove" callback directly before it is removed from user-space. This allows you to remove your submodules _before_ the parent l2cap_conn and hci_conn object is removed. At any time you can asynchronously unregister your l2cap_user object if your submodule vanishes before the l2cap_conn object does. There is no way around l2cap_user. If we want wire-protocols in the kernel, we always want the hci_conn object as parent in the sysfs tree. We cannot use a channel here since we might need multiple channels for a single protocol. But the problem is, we _must_ get notified when an l2cap_conn object is removed. We cannot use reference-counting for object-removal! This is not how it works. If a hardware is removed, we should immediately remove the object from sysfs. Any other behavior would be inconsistent with the rest of the system. Also note that device_del() might sleep, but it doesn't wait for user-space or block very long. It only _unlinks_ the object from sysfs and the whole device-tree. Everything else is handled by ref-counts! This is exactly what the other sub-modules must do: unlink their devices when the "remove" l2cap_user callback is called. They should not do any cleanup or synchronous shutdowns. Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Marcel Holtmann <marcel@holtmann.org> Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Diffstat (limited to 'include/net')
-rw-r--r--include/net/bluetooth/l2cap.h10
1 files changed, 10 insertions, 0 deletions
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7b4cc5b9853..fb94cf13c77 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -584,6 +584,13 @@ struct l2cap_conn {
struct list_head chan_l;
struct mutex chan_lock;
struct kref ref;
+ struct list_head users;
+};
+
+struct l2cap_user {
+ struct list_head list;
+ int (*probe) (struct l2cap_conn *conn, struct l2cap_user *user);
+ void (*remove) (struct l2cap_conn *conn, struct l2cap_user *user);
};
#define L2CAP_INFO_CL_MTU_REQ_SENT 0x01
@@ -817,4 +824,7 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
void l2cap_conn_get(struct l2cap_conn *conn);
void l2cap_conn_put(struct l2cap_conn *conn);
+int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user);
+void l2cap_unregister_user(struct l2cap_conn *conn, struct l2cap_user *user);
+
#endif /* __L2CAP_H */