From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759568Ab1LOVSw (ORCPT ); Thu, 15 Dec 2011 16:18:52 -0500 Received: from mga03.intel.com ([143.182.124.21]:65366 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759523Ab1LOVSK (ORCPT ); Thu, 15 Dec 2011 16:18:10 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.71,315,1320652800"; d="scan'208";a="86206938" Message-Id: <5d6588ab3dadabd8334cffee06b3e87abe3b81b7.1323979146.git.tony.luck@intel.com> In-Reply-To: References: From: Tony Luck Date: Wed, 14 Dec 2011 15:55:20 -0800 Subject: [PATCH 4/6] x86, mce: Add mechanism to safely save information in MCE handler To: linux-kernel@vger.kernel.org Cc: Ingo Molnar , Borislav Petkov , Chen Gong , "Huang, Ying" , Hidetoshi Seto Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Machine checks on Intel cpus interrupt execution on all cpus, regardless of interrupt masking. We have a need to save some data about the cause of the machine check (physical address) in the machine check handler that can be retrieved later to attempt recovery in a more flexible execution state. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce.c | 43 ++++++++++++++++++++++++++++++++++++++ 1 files changed, 43 insertions(+), 0 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 645070f..7d7303a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -887,6 +887,49 @@ static void mce_clear_state(unsigned long *toclear) } /* + * Need to save faulting physical address associated with a process + * in the machine check handler some place where we can grab it back + * later in mce_notify_process() + */ +#define MAX_MCE_INFO 16 + +struct mce_info { + atomic_t inuse; + struct task_struct *t; + __u64 paddr; +} mce_info[MAX_MCE_INFO]; + +static void mce_save_info(__u64 addr) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MAX_MCE_INFO]; mi++) { + if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) { + mi->t = current; + mi->paddr = addr; + return; + } + } + + mce_panic("Too many concurrent recoverable errors", NULL, NULL); +} + +static struct mce_info *mce_find_info(void) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MAX_MCE_INFO]; mi++) + if (atomic_read(&mi->inuse) && mi->t == current) + return mi; + return NULL; +} + +static void mce_clear_info(struct mce_info *mi) +{ + atomic_set(&mi->inuse, 0); +} + +/* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. * -- 1.7.3.1