From 2c8e1411e93391c5a78f55b09697a997474a4707 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:45 +0200 Subject: 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 Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/l2cap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 7b4cc5b98535..fb94cf13c777 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 */ -- cgit v1.2.3