Hi, The generic HID layer changes introduced an endianness bug for USB HID devices.
The USB vendor and product IDs are not byteswapped appropriately, and thus come out in the wrong endianness when fetched through the evdev using ioctl() on big endian platforms. This byteswapping used to be done in hidinput_connect() (by usb_to_input_id()) when filling up the hid device structure, and now needs to be done upstream. USB is the only user so far, and the hid_device structure is set up in usb_hid_configure(). Signed-off-by: Julien BLACHE <[EMAIL PROTECTED]>
--- hid-core.c~ 2007-02-05 11:16:33.905278861 +0100 +++ hid-core.c 2007-02-10 21:53:52.366333019 +0100 @@ -1220,8 +1220,8 @@ le16_to_cpu(dev->descriptor.idProduct)); hid->bus = BUS_USB; - hid->vendor = dev->descriptor.idVendor; - hid->product = dev->descriptor.idProduct; + hid->vendor = le16_to_cpu(dev->descriptor.idVendor); + hid->product = le16_to_cpu(dev->descriptor.idProduct); usb_make_path(dev, hid->phys, sizeof(hid->phys)); strlcat(hid->phys, "/input", sizeof(hid->phys));
Please apply, and this is a candidate for -stable as it breaks a documented API/ABI in userspace. JB. -- Julien BLACHE <http://www.jblache.org> <[EMAIL PROTECTED]> GPG KeyID 0xF5D65169
