Date: Fri, 22 Sep 2017 16:01:13 -0500
From: Reza Arbab <arbab@linux.vnet.ibm.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>, Jan Kara <jack@suse.cz>,
        Ross Zwisler <ross.zwisler@linux.intel.com>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Lorenzo Stoakes <lstoakes@gmail.com>,
        Dave Jiang <dave.jiang@intel.com>,
        =?iso-8859-1?B?Suly9G1l?= Glisse <jglisse@redhat.com>,
        Matthew Wilcox <willy@linux.intel.com>,
        Hugh Dickins <hughd@google.com>, Huang Ying <ying.huang@intel.com>,
        Ingo Molnar <mingo@kernel.org>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
        James Morse <james.morse@arm.com>,
        Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
        Minchan Kim <minchan@kernel.org>, Johannes Weiner <hannes@cmpxchg.org>,
        Will Deacon <will.deacon@arm.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm/device-public-memory: Enable move_pages() to stat
 device memory
References: <1506111236-28975-1-git-send-email-arbab@linux.vnet.ibm.com>
 <20170922203157.4txavkwmvyh2ufmd@arbab-laptop.localdomain>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Disposition: inline
In-Reply-To: <20170922203157.4txavkwmvyh2ufmd@arbab-laptop.localdomain>
Organization: IBM Linux Technology Center
User-Agent: NeoMutt/20170914 (1.9.0)
Message-Id: <20170922210113.c2dn5mjis6zyted7@arbab-laptop.localdomain>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 923
Lines: 31

On Fri, Sep 22, 2017 at 08:31:57PM +0000, Reza Arbab wrote:
>On Fri, Sep 22, 2017 at 08:13:56PM +0000, Reza Arbab wrote:
>>The move_pages() syscall can be used to find the numa node where a page
>>currently resides. This is not working for device public memory pages,
>>which erroneously report -EFAULT (unmapped or zero page).
>
>Argh. Please disregard this patch.
>
>My test setup has a chunk of system memory carved out as pretend 
>device public memory, to experiment with. Of course the real thing has 
>no numa node!

On third thought, yes it does! 

static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
{
	:
	nid = dev_to_node(device);
	if (nid < 0)
		nid = numa_mem_id();
	:
	if (devmem->pagemap.type == MEMORY_DEVICE_PUBLIC)
		ret = arch_add_memory(nid, align_start, align_size, false);
	:
}

So now I think the patch may be right after all. Please un-disregard it.  
Regard it? Whatever.

-- 
Reza Arbab