From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sfi-mx-1.v28.ch3.sourceforge.com ([172.29.28.121] helo=mx.sourceforge.net) by 335xhf1.ch3.sourceforge.com with esmtp (Exim 4.69) (envelope-from ) id 1Lx1xR-0008Ae-I1 for user-mode-linux-devel@lists.sourceforge.net; Thu, 23 Apr 2009 16:39:29 +0000 Received: from mail.gmx.net ([213.165.64.20]) by 29vjzd1.ch3.sourceforge.com with smtp (Exim 4.69) id 1Lx1xI-0001iq-7J for user-mode-linux-devel@lists.sourceforge.net; Thu, 23 Apr 2009 16:39:29 +0000 Message-ID: <49F099A2.5070408@gmx.de> Date: Thu, 23 Apr 2009 18:38:58 +0200 From: Ingo van Lil MIME-Version: 1.0 References: <20090418154021.GA14617@ivl.dyndns.org> <20090423160659.GD9820@c2.user-mode-linux.org> In-Reply-To: <20090423160659.GD9820@c2.user-mode-linux.org> Subject: Re: [uml-devel] [Patch] Save FPU registers between task switches List-Id: The user-mode Linux development list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: user-mode-linux-devel-bounces@lists.sourceforge.net To: Jeff Dike Cc: user-mode-linux-devel@lists.sourceforge.net Jeff Dike wrote: >> some time ago Jeff prepared a patch [1] for UML to stop saving the >> process FP state between task switches. The assumption was that since >> with SKAS0 every guest process runs inside a host process context the >> host OS will take care of keeping the proper FP state. Unfortunately >> this is not true for multi-threaded applications, where all guest >> threads share a single host process context yet all may use the FPU on >> their own. Although I haven't verified it I suspect things to be even >> worse in SKAS3 mode where all guest processes run inside a single host >> process. > > This seems plausible. Does reverting the patch fix any process crashes? Hi Jeff, the tiny test program I posted a few weeks ago [1] reproducibly crashes after a few seconds without the patch. Additionally I've been running UML with the patch for about a week now and I haven't seen the occasional erratic results that lead me to investigate the issue since then. I've never been using the SKAS3 patch, so I cannot comment on that. I had hoped that Stanislav Meduna could try whether the patch fixes the problems he reported last September [2]. Regards, Ingo [1] http://marc.info/?l=user-mode-linux-devel&m=123912656515459&w=2 [2] http://marc.info/?l=user-mode-linux-devel&m=121819897821728&w=2 ------------------------------------------------------------------------------ Stay on top of everything new and different, both inside and around Java (TM) technology - register by April 22, and save $200 on the JavaOne (SM) conference, June 2-5, 2009, San Francisco. 300 plus technical and hands-on sessions. Register today. Use priority code J9JMT32. http://p.sf.net/sfu/p _______________________________________________ User-mode-linux-devel mailing list User-mode-linux-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel