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 S1751409AbdJXB11 (ORCPT <rfc822;w@1wt.eu>);
        Mon, 23 Oct 2017 21:27:27 -0400
Received: from mga04.intel.com ([192.55.52.120]:56465 "EHLO mga04.intel.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1751327AbdJXB1Y (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 23 Oct 2017 21:27:24 -0400
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.43,424,1503385200"; 
   d="scan'208";a="1209224220"
Subject: Re: [PATCH] buffer: Avoid setting buffer bits that are already set
To: Andi Kleen <ak@linux.intel.com>
Cc: Jens Axboe <axboe@kernel.dk>, Jan Kara <jack@suse.cz>,
        Darrick J Wong <darrick.wong@oracle.com>,
        Eric Biggers <ebiggers@google.com>,
        Andreas Gruenbacher <agruenba@redhat.com>,
        Jeff Layton <jlayton@redhat.com>, Dave <dave.hansen@linux.intel.com>,
        Andi Kleen <andi.kleen@intel.com>, Tim Chen <tim.c.chen@intel.com>,
        Ying Huang <ying.huang@intel.com>, Aaron Lu <aaron.lu@intel.com>,
        Linux Kernel <linux-kernel@vger.kernel.org>
References: <1508772444-27879-1-git-send-email-kemi.wang@intel.com>
 <e2953a84-31d1-fdd2-faf8-62967a9f29c6@kernel.dk>
 <f475ae05-733d-b0a2-cadc-a5913f521153@intel.com>
 <87h8upxrvy.fsf@linux.intel.com>
From: kemi <kemi.wang@intel.com>
Message-ID: <131ef377-7edb-738c-4ed1-debac7857434@intel.com>
Date: Tue, 24 Oct 2017 09:25:44 +0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.4.0
MIME-Version: 1.0
In-Reply-To: <87h8upxrvy.fsf@linux.intel.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org



On 2017年10月24日 09:21, Andi Kleen wrote:
> kemi <kemi.wang@intel.com> writes:
>>
>> I'll see if I can find some
>>> time to implement the above in a nice way.
>>
>> Agree. Maybe something like test_and_set_bit() would be more suitable.
> 
> test_and_set_bit is a very different operation for the CPU because
> it is atomic for both. But we want the initial read to not
> be atomic.
> 

I meant to express the meaning of test before setting bit.
Apologize to make you confused.

> If you add special functions use a different variant that is only
> atomic for the set.
> 
> -Andi
>