From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PATCH 0/5] ahci: nvme remap support Date: Sat, 22 Oct 2016 08:50:38 +0200 Message-ID: <20161022065038.GA8547@lst.de> References: <147709592108.3733.7194541797066785254.stgit@dwillia2-desk3.amr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from verein.lst.de ([213.95.11.211]:55704 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752102AbcJVGul (ORCPT ); Sat, 22 Oct 2016 02:50:41 -0400 Content-Disposition: inline In-Reply-To: <147709592108.3733.7194541797066785254.stgit@dwillia2-desk3.amr.corp.intel.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Dan Williams Cc: tj@kernel.org, keith.busch@intel.com, linux-ide@vger.kernel.org, hch@lst.de, linux-nvme@lists.infradead.org On Fri, Oct 21, 2016 at 05:25:21PM -0700, Dan Williams wrote: > Some Intel ahci implementations have the capability to expose another > pci-express device's memory resources through an ahci memory bar. Add > the enabling to detect these configurations and register the resources > for the nvme driver to consume. Otherwise, the nvme device is > effectively hidden from the kernel for this configuration. Honestly I think this is just too ugly to live. I think people getting tricked by Intel into buying this piece of junk will just have to live with AHCI mode. From mboxrd@z Thu Jan 1 00:00:00 1970 From: hch@lst.de (Christoph Hellwig) Date: Sat, 22 Oct 2016 08:50:38 +0200 Subject: [PATCH 0/5] ahci: nvme remap support In-Reply-To: <147709592108.3733.7194541797066785254.stgit@dwillia2-desk3.amr.corp.intel.com> References: <147709592108.3733.7194541797066785254.stgit@dwillia2-desk3.amr.corp.intel.com> Message-ID: <20161022065038.GA8547@lst.de> On Fri, Oct 21, 2016@05:25:21PM -0700, Dan Williams wrote: > Some Intel ahci implementations have the capability to expose another > pci-express device's memory resources through an ahci memory bar. Add > the enabling to detect these configurations and register the resources > for the nvme driver to consume. Otherwise, the nvme device is > effectively hidden from the kernel for this configuration. Honestly I think this is just too ugly to live. I think people getting tricked by Intel into buying this piece of junk will just have to live with AHCI mode.