From mboxrd@z Thu Jan  1 00:00:00 1970
From: Xiao Guangrong <xiaoguangrong.eric@gmail.com>
Subject: Re: [PATCH v3 07/15] KVM: MMU: introduce nulls desc
Date: Tue, 10 Dec 2013 14:58:12 +0800
Message-ID: <52A6BB84.30706@gmail.com>
References: <20131122191429.GA13308@amt.cnet> <65EE805B-B5DB-4BD0-A057-E5FF78D96D67@linux.vnet.ibm.com> <5292EE2F.5090305@linux.vnet.ibm.com> <20131125181254.GB21858@amt.cnet> <529413C1.60302@linux.vnet.ibm.com> <20131126193148.GA18071@amt.cnet> <5297049E.3020800@linux.vnet.ibm.com> <529D83F8.7050605@linux.vnet.ibm.com> <20131205135021.GA12996@amt.cnet> <F8A4D0B5-9900-48F3-9CA3-23A5A8CC0B4B@linux.vnet.ibm.com> <20131206002244.GA29960@amt.cnet>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: Gleb Natapov <gleb@redhat.com>, avi.kivity@gmail.com,
	"pbonzini@redhat.com Bonzini" <pbonzini@redhat.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Eric Dumazet <dada1@cosmosbay.com>,
	Peter Zijlstra <peterz@infradead.org>
To: Marcelo Tosatti <mtosatti@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail-oa0-f43.google.com ([209.85.219.43]:53175 "EHLO
	mail-oa0-f43.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750789Ab3LJG6X (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 10 Dec 2013 01:58:23 -0500
In-Reply-To: <20131206002244.GA29960@amt.cnet>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 12/06/2013 08:22 AM, Marcelo Tosatti wrote:
> On Thu, Dec 05, 2013 at 11:30:27PM +0800, Xiao Guangrong wrote:
>> In some cases, the lockless walker will do endless-walking on desc a=
nd
>> without rewalk, consider this case:
>>
>> there are two descs: desc1 and desc2 who is pointed by desc1->next=EF=
=BC=9A
>> desc1->next =3D desc2.
>>
>> CPU 0                                                               =
             CPU 1
>>
>> lockless walk on desc1
>>                                                                  del=
eting desc1 from the rmap
>> lockless walk on desc2 (desc1->next)
>>                                                                 dele=
te desc2 from the rmap
>>                                                                 add =
desc1
>>                                                                 add =
desc2, then desc2->next =3D desc1
>>
>> lockless walk on desc1
>>                                                                delet=
e desc2
>>                                                                delet=
e desc1
>>                                                                add d=
esc2
>>                                                                add d=
esc1; the desc1->next =3D desc2
>> lockless walk on desc2
>>
>> =E2=80=A6=E2=80=A6
>>
>> Then, the walker is endlessly walking on desc1 and desc2 without any=
 rewalk.
>=20
> The counter can be local to the walker. If its more than maximum rmap
> size, break.
>=20
> (but still, please consider carefully whether lockless list walking i=
s
> really necessary or can be avoided).

Yep, Marcelo, you're right.

After thinking more, i do not have any idea to simplify this. Your appr=
oach
(lockless on the first level) seems a better solution. Will do it based=
 on that
ways.

Thanks!