From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754247AbaKRRCw (ORCPT ); Tue, 18 Nov 2014 12:02:52 -0500 Received: from cantor2.suse.de ([195.135.220.15]:33768 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752006AbaKRRCv (ORCPT ); Tue, 18 Nov 2014 12:02:51 -0500 Date: Tue, 18 Nov 2014 18:02:58 +0100 From: Petr Mladek To: Steven Rostedt Cc: linux-kernel@vger.kernel.org, Ingo Molnar , Andrew Morton , Jiri Kosina , "Paul E. McKenney" Subject: Re: [PATCH 26/26 v5] x86/nmi: Perform a safe NMI stack trace on all CPUs Message-ID: <20141118170258.GM23958@pathway.suse.cz> References: <20141115045847.712848224@goodmis.org> <20141115050605.055232587@goodmis.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20141115050605.055232587@goodmis.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri 2014-11-14 23:59:13, Steven Rostedt wrote: > From: "Steven Rostedt (Red Hat)" > > When trigger_all_cpu_backtrace() is called on x86, it will trigger an > NMI on each CPU and call show_regs(). But this can lead to a hard lock > up if the NMI comes in on another printk(). > > In order to avoid this, when the NMI triggers, it switches the printk > routine for that CPU to call a NMI safe printk function that records the > printk in a per_cpu seq_buf descriptor. After all NMIs have finished > recording its data, the seq_bufs are printed in a safe context. > > Link: http://lkml.kernel.org/p/20140619213952.360076309@goodmis.org > > Tested-by: Jiri Kosina > Acked-by: Jiri Kosina > Acked-by: Paul E. McKenney > Signed-off-by: Steven Rostedt Reviewed-by: Petr Mladek I really like that the NMI part is fast and we do not longer block many CPUs until the others are finished with priting. Best Regards, Petr