From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752534AbdF1TBU (ORCPT ); Wed, 28 Jun 2017 15:01:20 -0400 Received: from mx2.suse.de ([195.135.220.15]:59257 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751790AbdF1S4I (ORCPT ); Wed, 28 Jun 2017 14:56:08 -0400 Date: Wed, 28 Jun 2017 20:55:38 +0200 From: Borislav Petkov To: "Ghannam, Yazen" Cc: Jack Miller , "linux-kernel@vger.kernel.org" , "tglx@linutronix.de" , "x86@kernel.org" Subject: Re: [PATCH] x86/mce/AMD: Fix partial SMCA bank init when CPU 0 != thread 0 Message-ID: <20170628185538.ibwyv5pxpzf7liuu@pd.tnic> References: <20170628000630.1973-1-jack@codezen.org> <20170628092219.4df52dhwe7q3iao5@pd.tnic> <20170628181634.mmot6fdd3lmsrkog@pd.tnic> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: NeoMutt/20170113 (1.7.2) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Jun 28, 2017 at 06:51:08PM +0000, Ghannam, Yazen wrote: > The non-core MCA banks are only visible to a "master thread" on each Die. The > master thread is the first one on the Die. Since we have the same banks on each > Die we only need to read them once, and I assumed that CPU0 would always be > there. Right, I believe this is similar to the node-base core thing. Or something to that effect. So is there a reliable way to find out which is the node-base core, or the master thread? Because regardless what fw does, it should still configure such master thread if the BSP is a different thread. So if our code would be able to find that out, we should be good. [ Practically, a sane fw would simply go and make the new BSP also the master thread. But "sane" and "fw" in a sentence don't work. :-) ] Thanks. -- Regards/Gruss, Boris. SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nürnberg) --