Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752247AbYGYN4i (ORCPT ); Fri, 25 Jul 2008 09:56:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751100AbYGYN4a (ORCPT ); Fri, 25 Jul 2008 09:56:30 -0400 Received: from tama50.ecl.ntt.co.jp ([129.60.39.147]:62889 "EHLO tama50.ecl.ntt.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750854AbYGYN4a (ORCPT ); Fri, 25 Jul 2008 09:56:30 -0400 To: joerg.roedel@amd.com Cc: fujita.tomonori@lab.ntt.co.jp, mingo@redhat.com, tglx@linutronix.de, linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, bhavna.sarathy@amd.com, robert.richter@amd.com Subject: Re: [PATCH] add iommu_num_pages helper function From: FUJITA Tomonori In-Reply-To: <20080725134159.GA7493@amd.com> References: <20080725132121.GZ7493@amd.com> <20080725223533A.fujita.tomonori@lab.ntt.co.jp> <20080725134159.GA7493@amd.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-Id: <20080725225724J.fujita.tomonori@lab.ntt.co.jp> Date: Fri, 25 Jul 2008 22:57:24 +0900 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3340 Lines: 75 On Fri, 25 Jul 2008 15:41:59 +0200 Joerg Roedel wrote: > On Fri, Jul 25, 2008 at 10:34:57PM +0900, FUJITA Tomonori wrote: > > On Fri, 25 Jul 2008 15:21:21 +0200 > > Joerg Roedel wrote: > > > > > On Fri, Jul 25, 2008 at 10:15:06PM +0900, FUJITA Tomonori wrote: > > > > On Fri, 25 Jul 2008 14:57:58 +0200 > > > > Joerg Roedel wrote: > > > > > > > > > Calculating the number of pages from given address and length numbers is a task > > > > > required in multiple IOMMU implementations. So implement this as a generic > > > > > function into the IOMMU helper code. > > > > > > > > > > Cc: FUJITA Tomonori > > > > > Signed-off-by: Joerg Roedel > > > > > --- > > > > > include/linux/iommu-helper.h | 1 + > > > > > lib/iommu-helper.c | 8 ++++++++ > > > > > 2 files changed, 9 insertions(+), 0 deletions(-) > > > > > > > > Thanks. I planed to work on this after rc1. You beat me. :) > > > > > > > > > > > > > diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h > > > > > index c975caf..f8598f5 100644 > > > > > --- a/include/linux/iommu-helper.h > > > > > +++ b/include/linux/iommu-helper.h > > > > > @@ -8,3 +8,4 @@ extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, > > > > > unsigned long align_mask); > > > > > extern void iommu_area_free(unsigned long *map, unsigned long start, > > > > > unsigned int nr); > > > > > +extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len); > > > > > diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c > > > > > index a3b8d4c..889ddce 100644 > > > > > --- a/lib/iommu-helper.c > > > > > +++ b/lib/iommu-helper.c > > > > > @@ -80,3 +80,11 @@ void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr) > > > > > } > > > > > } > > > > > EXPORT_SYMBOL(iommu_area_free); > > > > > + > > > > > +unsigned long iommu_num_pages(unsigned long addr, unsigned long len) > > > > > +{ > > > > > + unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE); > > > > > + > > > > > + return size >> PAGE_SHIFT; > > > > > +} > > > > > +EXPORT_SYMBOL(iommu_num_pages); > > > > > > > > This doesn't work since PAGE_SIZE != IOMMU_PAGE_SIZE on the majority > > > > of architectures. > > > > > > A quick grep in include/ tells me that only powerpc is declaring > > > IOMMU_PAGE_SIZE by now. > > > > Ah, I just meant the I/O size of IOMMUs. > > > > This macro doesn't work for IA64, POWER, and SPARC. > > Is there any other architecture independent way to find out the page > size the IOMMU is using? If yes I can rework that patchset. There isn't now, I think. > If not, I suggest that we (you?) introduce one in a follow-on patch > series and fix the iommu_num_pages function then. That's fine by me. Or I could try to find a solution and submit new patchset with your AMD and GART patches. BTW, I prefer to push this patchset via -mm rather than x86 since after all we need to clean up all the IOMMUs. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/