From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga04.intel.com ([192.55.52.120]:27525 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752120AbbLQS0A (ORCPT ); Thu, 17 Dec 2015 13:26:00 -0500 Date: Thu, 17 Dec 2015 18:25:57 +0000 From: Keith Busch To: Bjorn Helgaas Cc: LKML , x86@kernel.org, linux-pci@vger.kernel.org, Jiang Liu , Thomas Gleixner , Dan Williams , Bjorn Helgaas , Bryan Veal , Ingo Molnar , "H. Peter Anvin" , Martin Mares , Jon Derrick Subject: Re: [PATCHv6 5/7] x86/pci: Initial commit for new VMD device driver Message-ID: <20151217182557.GA32327@localhost.localdomain> References: <1449523949-21898-1-git-send-email-keith.busch@intel.com> <1449523949-21898-6-git-send-email-keith.busch@intel.com> <20151217181448.GF23549@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20151217181448.GF23549@localhost> Sender: linux-pci-owner@vger.kernel.org List-ID: On Thu, Dec 17, 2015 at 12:14:48PM -0600, Bjorn Helgaas wrote: > On Mon, Dec 07, 2015 at 02:32:27PM -0700, Keith Busch wrote: > > +/* > > + * VMD h/w converts posted config writes to non-posted. The read-back in this > > + * function forces the completion so it returns only after the config space was > > + * written, as expected. > > This comment sounds backwards: > > posted writes don't wait for completion > non-posted writes do wait for completion > > If the hardware converts to non-posted writes, you shouldn't need a > read-back. It seems like you would need the read-back if the hardware > converted non-posted to posted. Oops, the comment has it backwards. Non-posted config writes become posted memory write requests with this h/w. > Seems like it might be nice to have something in dmesg that would connect > this PCI device to the new PCI domain. It's a new, unusual topology and a > hint might help everybody understand what's going on. Sounds good, will add. In addition that, I'd like to mention this patch links a new domain's root bus kobject under the VMD end-point's so the sysfs hierarchy captures this as well.