From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752266AbbATS1l (ORCPT ); Tue, 20 Jan 2015 13:27:41 -0500 Received: from cantor2.suse.de ([195.135.220.15]:37688 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751145AbbATS1j (ORCPT ); Tue, 20 Jan 2015 13:27:39 -0500 Message-ID: <1421775689.1112.4.camel@linux-0dmf.site> Subject: Re: USB autosuspend causing trouble with bluetooth From: Oliver Neukum To: Kirill Elagin Cc: linux-kernel@vger.kernel.org, linux-usb@vger.kernel.org In-Reply-To: References: <1421751814.29486.13.camel@linux-0dmf.site> <1421762788.29486.28.camel@linux-0dmf.site> Content-Type: text/plain; charset="UTF-8" Date: Tue, 20 Jan 2015 18:41:29 +0100 Mime-Version: 1.0 X-Mailer: Evolution 3.10.4 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2015-01-20 at 18:58 +0400, Kirill Elagin wrote: > On Tue, Jan 20, 2015 at 5:06 PM, Oliver Neukum wrote: > > On Tue, 2015-01-20 at 16:18 +0400, Kirill Elagin wrote: > >> I use a Logitech wireless keyboard (with a Unifying receiver) and it > >> keeps working fine even with `auto`. > >> > >> That is, everything is OK if the receiver is plugged before > >> `power/control` is switched to `auto`. > > > > Wait. There is no power/control file for the receiver before > > you plug it in. We are having a very big misunderstanding here. > > Sorry for not being clear. I was referring to `power/control` of the > USB-device itself except for the cases when I was talking about > hot-plugging issues — in those cases I was referring to the > `power/control` of the root hub. Please check whether you are not accidentally touching the ports linux-0dmf:/sys/bus/usb/devices/usb1/1-0:1.0/usb1-port1 At paths like this you find control files for ports, not the root hub as a device. > In this particular case I was talking about the `power/control` of the root hub. OK, so autosuspend does work if you enable it for the device but not the hub? > `laptop-mode-tools` by default writes `auto` to `power/control` of > _all_ the USB devices, root hubs included (even when on AC). Is it > really expected that kernel might completely power off the physical > USB port? Sounds weird. It can. It is a recent feature if ACPI supports that on a machine. > Here is an even more strange thing. First I set all the USB power > management to the defaults (that is, `auto` for all the usb devices > including root hubs). Again, the keyboard keeps working and as soon as > I unplug the receiver kernel says the device was disconnected. Now if > I plug the receiver back nothing happens. _But_ if I plug a flash > drive in the save physical port it gets detected. So, I tried a number > of other usb devices and it totally looks like USB2.0 ones are > properly hot-plugged while USB1.1 devices are not. Does this sound to > you like a bug in my laptop's hardware? Could be, but could also be software. Please double check where exactly an "on" is needed. Regards Oliver