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 S1752857AbdHKMHf (ORCPT <rfc822;w@1wt.eu>);
        Fri, 11 Aug 2017 08:07:35 -0400
Received: from bombadil.infradead.org ([65.50.211.133]:48064 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1752610AbdHKMHe (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 11 Aug 2017 08:07:34 -0400
Date: Fri, 11 Aug 2017 14:07:14 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>,
        Juergen Gross <jgross@suse.com>,
        Stephen Hemminger <sthemmin@microsoft.com>, boris.ostrovsky@oracle.com,
        "linux-tip-commits@vger.kernel.org" 
        <linux-tip-commits@vger.kernel.org>,
        Jork Loeser <Jork.Loeser@microsoft.com>,
        Haiyang Zhang <haiyangz@microsoft.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "rostedt@goodmis.org" <rostedt@goodmis.org>,
        Simon Xiao <sixiao@microsoft.com>,
        "andy.shevchenko@gmail.com" <andy.shevchenko@gmail.com>,
        "luto@kernel.org" <luto@kernel.org>, "hpa@zytor.com" <hpa@zytor.com>,
        xen-devel@lists.xenproject.org,
        "tglx@linutronix.de" <tglx@linutronix.de>,
        KY Srinivasan <kys@microsoft.com>,
        "torvalds@linux-foundation.org" <torvalds@linux-foundation.org>,
        "mingo@kernel.org" <mingo@kernel.org>
Subject: Re: [Xen-devel] [tip:x86/platform] x86/hyper-v: Use hypercall for
 remote TLB flush
Message-ID: <20170811120714.rwr24ewr4mjzwznn@hirez.programming.kicks-ass.net>
References: <20170802160921.21791-8-vkuznets@redhat.com>
 <tip-2ffd9e33ce4af4e8cfa3e17bf493defe8474e2eb@git.kernel.org>
 <20170810185646.GI6524@worktop.programming.kicks-ass.net>
 <DM5PR21MB0476915D204F850F7F7C1475A0880@DM5PR21MB0476.namprd21.prod.outlook.com>
 <CY4PR21MB06313B9D59F8846CDDE443F0F1880@CY4PR21MB0631.namprd21.prod.outlook.com>
 <20170810192742.GJ6524@worktop.programming.kicks-ass.net>
 <87lgmqqwzl.fsf@vitty.brq.redhat.com>
 <20170811105625.hmdfnp3yh72zut33@hirez.programming.kicks-ass.net>
 <43ddd29a-1670-ef0b-c327-10a2dca67cb4@citrix.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <43ddd29a-1670-ef0b-c327-10a2dca67cb4@citrix.com>
User-Agent: NeoMutt/20170609 (1.8.3)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Aug 11, 2017 at 12:05:45PM +0100, Andrew Cooper wrote:
> >> Oh, I see your concern. Hyper-V, however, is not the first x86
> >> hypervisor trying to avoid IPIs on remote TLB flush, Xen does this
> >> too. Briefly looking at xen_flush_tlb_others() I don't see anything
> >> special, do we know how serialization is achieved there?
> > No idea on how Xen works, I always just hope it goes away :-) But lets
> > ask some Xen folks.
> 
> How is the software pagewalker relying on IF being clear safe at all (on
> native, let alone under virtualisation)?  Hardware has no architectural
> requirement to keep entries in the TLB.

No, but it _can_, therefore when we unhook pages we _must_ invalidate.

It goes like:

	CPU0			CPU1

	unhook page
				cli
				traverse page tables
	TLB invalidate --->	<IF clear, therefore CPU0 waits>
				sti
				<IPI>
				 TLB invalidate
			<------	 complete
				</IPI>
	free page

So the CPU1 page-table walker gets an existence guarantee of the
page-tables by clearing IF.

> In the virtualisation case, at any point the vcpu can be scheduled on a
> different pcpu even during a critical region like that, so the TLB
> really can empty itself under your feet.

Not the point.