From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756061AbcCaK5F (ORCPT ); Thu, 31 Mar 2016 06:57:05 -0400 Received: from mail-wm0-f67.google.com ([74.125.82.67]:35349 "EHLO mail-wm0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755652AbcCaK5D (ORCPT ); Thu, 31 Mar 2016 06:57:03 -0400 Date: Thu, 31 Mar 2016 12:57:00 +0200 From: Michal Hocko To: Xishi Qiu Cc: Linux MM , LKML Subject: Re: [RFC] oom, but there is enough memory Message-ID: <20160331105700.GD27831@dhcp22.suse.cz> References: <56FCEAD0.9080806@huawei.com> <20160331093011.GC27831@dhcp22.suse.cz> <56FCEFFE.6040604@huawei.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <56FCEFFE.6040604@huawei.com> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu 31-03-16 17:38:06, Xishi Qiu wrote: [...] > Hi Michal, > > It's arm64, so DMA is [0-4G], and Normal is [4G-] I wasn't aware of that. Thanks for the clarification. > Is that something wrong with the RAM hardware, then trigger the problem? This is hard to tell but I would try to check which of the page fault path has returned with VM_FAULT_OOM. This might be a wrong .fault callback. -- Michal Hocko SUSE Labs