From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751580AbdJVNEy (ORCPT <rfc822;w@1wt.eu>);
        Sun, 22 Oct 2017 09:04:54 -0400
Received: from merlin.infradead.org ([205.233.59.134]:46058 "EHLO
        merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1750991AbdJVNEw (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Sun, 22 Oct 2017 09:04:52 -0400
Date: Sun, 22 Oct 2017 15:04:29 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: hpa@zytor.com, torvalds@linux-foundation.org, tglx@linutronix.de,
        mingo@kernel.org, Yazen.Ghannam@amd.com, mirh@protonmail.ch,
        sherry.hurwitz@amd.com, bp@suse.de, stable@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc: linux-tip-commits@vger.kernel.org
Subject: Re: [tip:x86/urgent] x86/cpu/AMD: Apply the Erratum 688 fix when the
 BIOS doesn't
Message-ID: <20171022130429.GA3165@worktop.lehotels.local>
References: <20171022104731.28249-1-bp@alien8.de>
 <tip-bfc1168de949cd3e9ca18c3480b5085deff1ea7c@git.kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <tip-bfc1168de949cd3e9ca18c3480b5085deff1ea7c@git.kernel.org>
User-Agent: Mutt/1.5.22.1 (2013-10-16)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Sun, Oct 22, 2017 at 05:16:29AM -0700, tip-bot for Borislav Petkov wrote:
> +static void __fix_erratum_688(void *info)
> +{
> +#define MSR_AMD64_IC_CFG 0xC0011021
> +
> +	msr_set_bit(MSR_AMD64_IC_CFG, 3);
> +	msr_set_bit(MSR_AMD64_IC_CFG, 14);

I realize this is an erratum work around, but would it be too much to
ask for a small comment explaining the magic values?

> +}
> +
> +/* Apply erratum 688 fix so machines without a BIOS fix work. */
> +static __init void fix_erratum_688(void)
> +{
> +	struct pci_dev *F4;
> +	u32 val;
> +
> +	if (boot_cpu_data.x86 != 0x14)
> +		return;
> +
> +	if (!amd_northbridges.num)
> +		return;
> +
> +	F4 = node_to_amd_nb(0)->link;
> +	if (!F4)
> +		return;
> +
> +	if (pci_read_config_dword(F4, 0x164, &val))
> +		return;
> +
> +	if (val & BIT(2))
> +		return;
> +
> +	on_each_cpu(__fix_erratum_688, NULL, 0);
> +
> +	pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n");

Except for all CPUs that were not online at this point in time... So
suppose I boot with a limited number of CPUs and then later bring up the
rest, bad things happen.