Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 16 Mar 2020 10:06:52 +0100
From:   Michal Hocko <mhocko@kernel.org>
To:     Vlastimil Babka <vbabka@suse.cz>
Cc:     Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
        Sachin Sant <sachinp@linux.vnet.ibm.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        LKML <linux-kernel@vger.kernel.org>, linux-mm@kvack.org,
        Mel Gorman <mgorman@suse.de>,
        "Kirill A. Shutemov" <kirill@shutemov.name>,
        Andrew Morton <akpm@linux-foundation.org>,
        linuxppc-dev@lists.ozlabs.org, Christopher Lameter <cl@linux.com>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>,
        Kirill Tkhai <ktkhai@virtuozzo.com>
Subject: Re: [PATCH 1/3] powerpc/numa: Set numa_node for all possible cpus
Message-ID: <20200316090652.GC11482@dhcp22.suse.cz>
References: <20200311110237.5731-1-srikar@linux.vnet.ibm.com>
 <20200311110237.5731-2-srikar@linux.vnet.ibm.com>
 <20200311115735.GM23944@dhcp22.suse.cz>
 <20200312052707.GA3277@linux.vnet.ibm.com>
 <C5560C71-483A-41FB-BDE9-526F1E0CFA36@linux.vnet.ibm.com>
 <5e5c736a-a88c-7c76-fc3d-7bc765e8dcba@suse.cz>
 <20200312131438.GB3277@linux.vnet.ibm.com>
 <61437352-8b54-38fa-4471-044a65c9d05a@suse.cz>
 <20200312161310.GC3277@linux.vnet.ibm.com>
 <e115048c-be38-c298-b8d1-d4b513e7d2fb@suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <e115048c-be38-c298-b8d1-d4b513e7d2fb@suse.cz>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu 12-03-20 17:41:58, Vlastimil Babka wrote:
[...]
> with nid present in:
> N_POSSIBLE - pgdat might not exist, node_to_mem_node() must return some online

I would rather have a dummy pgdat for those. Have a look at 
$ git grep "NODE_DATA.*->" | wc -l
63

Who knows how many else we have there. I haven't looked more closely.
Besides that what is a real reason to not have pgdat ther and force all
users of a $random node from those that the platform considers possible
for special casing? Is that a memory overhead? Is that really a thing?

Somebody has suggested to tweak some of the low level routines to do the
special casing but I really have to say I do not like that. We shouldn't
use the first online node or anything like that. We should simply always
follow the topology presented by FW and of that we need to have a pgdat.
-- 
Michal Hocko
SUSE Labs