Whenever either disconnecting the USB device or simply rmmod'ing the module (even when not in use), I get a kernel panic. I haven't managed to capture a backtrace, but at least the first two lines were saved after an rmmod: 18:53:17 kernel: thingm 0003:27B8:01ED.0004: hidraw3: USB HID v1.01 Device [ThingM blink(1) mk2] on usb-0000:00:12.2-3.1.4/input0 <snip, rmmod hid-thingm:> 08:38:42 kernel: BUG: unable to handle kernel paging request at fffffffb8a80aaf8 08:38:42 kernel: IP: [<ffffffff8106e30c>] osq_lock+0x3c/0x110 Let me know if you'd like me to try to capture more info, but this problem seems very reproducible (at least with a mk2 device; I never had the problem on older kernels with a mk1). I do direct write()s to the hidraw device, but don't otherwise use the driver while it's loaded. Also at https://bugzilla.kernel.org/show_bug.cgi?id=83751 -- To unsubscribe from this list: send the line "unsubscribe linux-input" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
