Testing a little more, I found that on fresh boots the latest bluez.git doesn't always work to switch dell BT adapters to HCI mode depending on the state of the killswitch on boot. Whenever running hid2hci, the kernel driver should attempt to be released. As long as this is done before trying to claim, each of the scenarios is successful. The previous dmesg errors were coming up because the order of the usb_claim_interface and usb_detach_kernel_driver_np were reversed. The commit message should be shortened this time too, sorry about that before. --- From 3e40fbd035b35613c8d1ad3f0aa11a639f487600 Mon Sep 17 00:00:00 2001 From: Mario Limonciello <Mario_Limonciello@xxxxxxxx> Date: Mon, 18 May 2009 13:07:40 -0500 Subject: [PATCH] Reinstitute usb_detach_kernel_driver_np, but in the proper place. The kernel might still be grab the usb device, so release it before claim. --- tools/hid2hci.c | 4 ++++ 1 files changed, 4 insertions(+), 0 deletions(-) -- Mario Limonciello *Dell | Linux Engineering* mario_limonciello@xxxxxxxx
From 3e40fbd035b35613c8d1ad3f0aa11a639f487600 Mon Sep 17 00:00:00 2001 From: Mario Limonciello <Mario_Limonciello@xxxxxxxx> Date: Mon, 18 May 2009 13:07:40 -0500 Subject: [PATCH] Reinstitute usb_detach_kernel_driver_np, but in the proper place. The kernel might still be grab the usb device, so release it before claim. --- tools/hid2hci.c | 4 ++++ 1 files changed, 4 insertions(+), 0 deletions(-) diff --git a/tools/hid2hci.c b/tools/hid2hci.c index d5c8d32..c5b6558 100644 --- a/tools/hid2hci.c +++ b/tools/hid2hci.c @@ -223,6 +223,10 @@ static int switch_dell(struct device_info *devinfo) handle = usb_open(devinfo->dev); + /* Don't need to check return, as might not be in use */ + if (handle) + usb_detach_kernel_driver_np(handle, 0); + if (handle && usb_claim_interface(handle,0) == 0) err = usb_control_msg(handle, USB_ENDPOINT_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE, -- 1.6.0.4
Attachment:
signature.asc
Description: OpenPGP digital signature
