From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.2 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_SANE_1 autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 69DD4C2BB1D for ; Fri, 17 Apr 2020 07:10:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 4CD4C206D5 for ; Fri, 17 Apr 2020 07:10:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728913AbgDQHKD (ORCPT ); Fri, 17 Apr 2020 03:10:03 -0400 Received: from verein.lst.de ([213.95.11.211]:56051 "EHLO verein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728155AbgDQHKD (ORCPT ); Fri, 17 Apr 2020 03:10:03 -0400 Received: by verein.lst.de (Postfix, from userid 2407) id 12BF968BFE; Fri, 17 Apr 2020 09:09:59 +0200 (CEST) Date: Fri, 17 Apr 2020 09:09:58 +0200 From: Christoph Hellwig To: David Rientjes Cc: Christoph Hellwig , Tom Lendacky , Brijesh Singh , Jon Grimm , Joerg Roedel , linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org Subject: Re: [patch 4/7] dma-direct: atomic allocations must come from atomic coherent pools Message-ID: <20200417070958.GB19153@lst.de> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The subject should say something like "atomic unencrypted allocations.." as many other atomic allocations are fine. Which brings up that with the codebase in this patch we can't really support architectures that require both an atomic pool for uncached remapping for just some devices and unencrypted for others. We don't have such an archicture right now, and I hope we don't grow one, but we probably need a little safeguard with a BUILD_BUG_ON if both options are set. I can send an incremental patch for that if that is ok with you.