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 S932199AbcFNRSf (ORCPT <rfc822;w@1wt.eu>);
	Tue, 14 Jun 2016 13:18:35 -0400
Received: from mga04.intel.com ([192.55.52.120]:23203 "EHLO mga04.intel.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751727AbcFNRSd (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 14 Jun 2016 13:18:33 -0400
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.26,471,1459839600"; 
   d="scan'208";a="997511819"
Subject: Re: [PATCH] Linux VM workaround for Knights Landing A/D leak
To: Nadav Amit <nadav.amit@gmail.com>,
        Lukasz Anaczkowski <lukasz.anaczkowski@intel.com>
References: <1465919919-2093-1-git-send-email-lukasz.anaczkowski@intel.com>
 <7FB15233-B347-4A87-9506-A9E10D331292@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>, linux-mm@kvack.org,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        ak@linux.intel.com, kirill.shutemov@linux.intel.com, mhocko@suse.com,
        Andrew Morton <akpm@linux-foundation.org>,
        "H. Peter Anvin" <hpa@zytor.com>, harish.srinivasappa@intel.com,
        lukasz.odzioba@intel.com
From: Dave Hansen <dave.hansen@linux.intel.com>
Message-ID: <57603C61.5000408@linux.intel.com>
Date: Tue, 14 Jun 2016 10:18:25 -0700
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.8.0
MIME-Version: 1.0
In-Reply-To: <7FB15233-B347-4A87-9506-A9E10D331292@gmail.com>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 06/14/2016 09:47 AM, Nadav Amit wrote:
> Lukasz Anaczkowski <lukasz.anaczkowski@intel.com> wrote:
> 
>> > From: Andi Kleen <ak@linux.intel.com>
>> > +void fix_pte_leak(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
>> > +{
> Here there should be a call to smp_mb__after_atomic() to synchronize with
> switch_mm. I submitted a similar patch, which is still pending (hint).
> 
>> > +	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) {
>> > +		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
>> > +		flush_tlb_others(mm_cpumask(mm), mm, addr,
>> > +				 addr + PAGE_SIZE);
>> > +		mb();
>> > +		set_pte(ptep, __pte(0));
>> > +	}
>> > +}

Shouldn't that barrier be incorporated in the TLB flush code itself and
not every single caller (like this code is)?

It is insane to require individual TLB flushers to be concerned with the
barriers.