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 S1755322AbcK1VMM (ORCPT <rfc822;w@1wt.eu>);
        Mon, 28 Nov 2016 16:12:12 -0500
Received: from mga03.intel.com ([134.134.136.65]:1984 "EHLO mga03.intel.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1753352AbcK1VMD (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 28 Nov 2016 16:12:03 -0500
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.31,565,1473145200"; 
   d="scan'208";a="36479617"
Subject: Re: [RFC 4/4] mm: Ignore cpuset enforcement when allocation flag has
 __GFP_THISNODE
To: Anshuman Khandual <khandual@linux.vnet.ibm.com>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
References: <1479824388-30446-1-git-send-email-khandual@linux.vnet.ibm.com>
 <1479824388-30446-5-git-send-email-khandual@linux.vnet.ibm.com>
Cc: mhocko@suse.com, vbabka@suse.cz, mgorman@suse.de, minchan@kernel.org,
        aneesh.kumar@linux.vnet.ibm.com, bsingharora@gmail.com,
        srikar@linux.vnet.ibm.com, haren@linux.vnet.ibm.com,
        jglisse@redhat.com
From: Dave Hansen <dave.hansen@intel.com>
Message-ID: <8216916c-c3f3-bad9-33cb-b0da2508f3d0@intel.com>
Date: Mon, 28 Nov 2016 13:12:02 -0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
 Thunderbird/45.4.0
MIME-Version: 1.0
In-Reply-To: <1479824388-30446-5-git-send-email-khandual@linux.vnet.ibm.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 11/22/2016 06:19 AM, Anshuman Khandual wrote:
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3715,7 +3715,7 @@ struct page *
>  		.migratetype = gfpflags_to_migratetype(gfp_mask),
>  	};
>  
> -	if (cpusets_enabled()) {
> +	if (cpusets_enabled() && !(alloc_mask & __GFP_THISNODE)) {
>  		alloc_mask |= __GFP_HARDWALL;
>  		alloc_flags |= ALLOC_CPUSET;
>  		if (!ac.nodemask)

This means now that any __GFP_THISNODE allocation can "escape" the
cpuset.  That seems like a pretty major change to how cpusets works.  Do
we know that *ALL* __GFP_THISNODE allocations are truly lacking in a
cpuset context that can be enforced?