From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751480AbdAORlN (ORCPT ); Sun, 15 Jan 2017 12:41:13 -0500 Received: from mail-qt0-f193.google.com ([209.85.216.193]:32774 "EHLO mail-qt0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751241AbdAORlM (ORCPT ); Sun, 15 Jan 2017 12:41:12 -0500 Date: Sun, 15 Jan 2017 12:41:08 -0500 From: Konrad Rzeszutek Wilk To: Nikita Yushchenko Cc: Konrad Rzeszutek Wilk , linux-kernel@vger.kernel.org, Artemi Ivanov , Christoph Hellwig , linux-nvme@lists.infradead.org Subject: Re: [PATCH resend] swiotlb: ensure that page-sized mappings are page-aligned Message-ID: <20170115174106.GA6150@localhost.localdomain> References: <1484160991-29624-1-git-send-email-nikita.yoush@cogentembedded.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1484160991-29624-1-git-send-email-nikita.yoush@cogentembedded.com> User-Agent: Mutt/1.7.1 (2016-10-04) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Jan 11, 2017 at 09:56:31PM +0300, Nikita Yushchenko wrote: > Some drivers do depend on page mappings to be page aligned. > > Swiotlb already enforces such alignment for mappings greater than page, > extend that to page-sized mappings as well. > > Without this fix, nvme hits BUG() in nvme_setup_prps(), because that routine > assumes page-aligned mappings. > > Signed-off-by: Nikita Yushchenko I queued it up in stable/for-linus-4.10 in swiotlb queue tree. > --- > lib/swiotlb.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > diff --git a/lib/swiotlb.c b/lib/swiotlb.c > index 975b8fc..a8d74a7 100644 > --- a/lib/swiotlb.c > +++ b/lib/swiotlb.c > @@ -483,11 +483,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, > : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); > > /* > - * For mappings greater than a page, we limit the stride (and > - * hence alignment) to a page size. > + * For mappings greater than or equal to a page, we limit the stride > + * (and hence alignment) to a page size. > */ > nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; > - if (size > PAGE_SIZE) > + if (size >= PAGE_SIZE) > stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); > else > stride = 1; > -- > 2.1.4 >