From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965400AbXCLJIX (ORCPT ); Mon, 12 Mar 2007 05:08:23 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S965404AbXCLJIX (ORCPT ); Mon, 12 Mar 2007 05:08:23 -0400 Received: from phpmyadmin.profiwh.com ([85.93.165.67]:42588 "EHLO cacti.profiwh.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S965397AbXCLJIW (ORCPT ); Mon, 12 Mar 2007 05:08:22 -0400 Message-ID: <45F5188D.4030106@gmail.com> Date: Mon, 12 Mar 2007 10:08:29 +0100 From: Jiri Slaby User-Agent: Thunderbird 2.0b2 (X11/20070116) MIME-Version: 1.0 To: Jiri Kosina Cc: Dmitry Torokhov , Andrew Morton , linux-kernel@vger.kernel.org, Richard Purdie , Alan Stern , Greg Kroah-Hartman Subject: Re: Keyboard stops working after *lock [Was: 2.6.21-rc2-mm1] References: <20070302030026.5eef0c92.akpm@linux-foundation.org> <45E996A0.6070700@gmail.com> <45E99A45.9030506@gmail.com> <20070303094125.838ce04d.akpm@linux-foundation.org> <45F13791.8040408@gmail.com> <45F4770F.4090902@gmail.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Jiri Kosina napsal(a): > On Sun, 11 Mar 2007, Jiri Slaby wrote: > >>> - /* make sure the unused bits in the last byte are zeros */ >>> - if (count > 0 && size > 0) >>> - data[(offset+count*size-1)/8] = 0; >>> - >> No, this doesn't help -- -rc3-mm2 minus this behaves exactly the same. [...] > Otherwise, would you care to bisect? Bisecting figured out the culprit: Commit: 17230acdc71137622ca7dfd789b3944c75d39404 Author: Alan Stern Mon, 19 Feb 2007 15:52:45 -0500 UHCI: Eliminate asynchronous skeleton Queue Headers This patch (as856) attempts to improve the performance of uhci-hcd by removing the asynchronous skeleton Queue Headers. They don't contain any useful information but the controller has to read through them at least once every millisecond, incurring a non-zero DMA overhead. Now all the asynchronous queues are combined, along with the period-1 interrupt queue, into a single list with a single skeleton QH. The start of the low-speed control, full-speed control, and bulk sublists is determined by linear search. Since there should rarely be more than a couple of QHs in the list, the searches should incur a much smaller total load than keeping the skeleton QHs. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman -mm minus (only) this one is OK. regards, -- http://www.fi.muni.cz/~xslaby/ Jiri Slaby faculty of informatics, masaryk university, brno, cz e-mail: jirislaby gmail com, gpg pubkey fingerprint: B674 9967 0407 CE62 ACC8 22A0 32CC 55C3 39D4 7A7E Hnus is an alias for /dev/null