From mboxrd@z Thu Jan 1 00:00:00 1970 From: keith.busch@intel.com (Keith Busch) Date: Fri, 5 Aug 2016 16:50:53 -0400 Subject: NVME regression in all kernels after 4.4.x for NVME in M2 slot for laptop? In-Reply-To: <20160805190323.GA12853@merlins.org> References: <20160805190323.GA12853@merlins.org> Message-ID: <20160805205052.GA12688@localhost.localdomain> On Fri, Aug 05, 2016@12:03:23PM -0700, Marc MERLIN wrote: > Would this patch make sense as being the reason why I can't S3 sleep > anymore and would you have a test patch against 4.5, 4.6, or 4.7 I can > try to see if it fixes the problem? Hi Marc, It might be blk-mq's hot cpu notifier is invoked during suspend and waiting for nvme's queues to freeze, which may not happen if a request is waiting on a stopped queue. The patch you biseceted doesn't necessarilly fix that, but the window for when a request could get queued like that was much shorter. Assuming that is the problem, S3 suspends PCI hardware before IO tasks. I'll see if I can reproduce on one of my machines and look into a fix. Thanks, Keith From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S942972AbcHEUlP (ORCPT ); Fri, 5 Aug 2016 16:41:15 -0400 Received: from mga04.intel.com ([192.55.52.120]:14977 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S938954AbcHEUlH (ORCPT ); Fri, 5 Aug 2016 16:41:07 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.28,474,1464678000"; d="scan'208";a="1035952451" Date: Fri, 5 Aug 2016 16:50:53 -0400 From: Keith Busch To: Marc MERLIN Cc: axboe@fb.com, linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org Subject: Re: NVME regression in all kernels after 4.4.x for NVME in M2 slot for laptop? Message-ID: <20160805205052.GA12688@localhost.localdomain> References: <20160805190323.GA12853@merlins.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160805190323.GA12853@merlins.org> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Aug 05, 2016 at 12:03:23PM -0700, Marc MERLIN wrote: > Would this patch make sense as being the reason why I can't S3 sleep > anymore and would you have a test patch against 4.5, 4.6, or 4.7 I can > try to see if it fixes the problem? Hi Marc, It might be blk-mq's hot cpu notifier is invoked during suspend and waiting for nvme's queues to freeze, which may not happen if a request is waiting on a stopped queue. The patch you biseceted doesn't necessarilly fix that, but the window for when a request could get queued like that was much shorter. Assuming that is the problem, S3 suspends PCI hardware before IO tasks. I'll see if I can reproduce on one of my machines and look into a fix. Thanks, Keith