From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932401AbaIWQMg (ORCPT ); Tue, 23 Sep 2014 12:12:36 -0400 Received: from mail-oi0-f52.google.com ([209.85.218.52]:41347 "EHLO mail-oi0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932117AbaIWQMe (ORCPT ); Tue, 23 Sep 2014 12:12:34 -0400 Message-ID: <54219BEE.7090309@mvista.com> Date: Tue, 23 Sep 2014 11:12:30 -0500 From: Corey Minyard User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.7.0 MIME-Version: 1.0 To: Ralf Baechle , minyard@acm.org CC: linux-mips@linux-mips.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] mips: Save all registers when saving the frame References: <1410903925-10744-1-git-send-email-minyard@acm.org> <20140918095813.GA9804@linux-mips.org> <541AD6E9.2010609@mvista.com> In-Reply-To: <541AD6E9.2010609@mvista.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Ping? I haven't heard anything on this. Thanks, -corey On 09/18/2014 07:58 AM, Corey Minyard wrote: > On 09/18/2014 04:58 AM, Ralf Baechle wrote: >> On Tue, Sep 16, 2014 at 04:45:25PM -0500, minyard@acm.org wrote: >> >>> From: Corey Minyard >>> >>> The MIPS frame save code was just saving a few registers, enough to >>> do a backtrace if every function set up a frame. However, this is >>> not working if you are using DWARF unwinding, because most of the >>> registers are wrong. This was causing kdump backtraces to be short >>> or bogus. >>> >>> So save all the registers. >> The stratey of partial and full stack frames was developed in '97 to bring >> down the syscall overhead. It certaily was very effective - it brought >> down the syscall latency to the level of Alphas running at much higher >> clock. >> >> That certainly worked well back then for kernel 2.0 / 2.2. But the syscall >> code has become much more complex. Since then support for 64 bit kernels, >> two 32 bit ABIs running on a 64 bit kernels and numerous features that >> changed the once simple syscall path have been implemented. My gut feeling >> is it might be worth to yank out the whole optimization to see how much >> code complexity we get rid of in exchange for how much extra syscall >> latency. > I"m not sure I understand. From what I can tell, this code is only > called by > things that print stack traces, kdb, and kexec/kdump. So it shouldn't be in > any normal syscall path. > > This patch will currently only help kdump, but it will be necessary if > anyone > adds MIPS support for DWARF unwinding for stack traces. And you'd have > to fix some things in context switching, too, I think. > > From what I can tell the partial save for syscalls is a good idea. You > don't have > to save half the registers and it doesn't affect tracebacks, kdump, or > anything else > like that. > > -corey