From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752222Ab1LTOOo (ORCPT ); Tue, 20 Dec 2011 09:14:44 -0500 Received: from cantor2.suse.de ([195.135.220.15]:55378 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751515Ab1LTOOk (ORCPT ); Tue, 20 Dec 2011 09:14:40 -0500 Date: Tue, 20 Dec 2011 15:14:37 +0100 From: Michal Hocko To: Hillf Danton Cc: KAMEZAWA Hiroyuki , Andrew Morton , linux-mm@kvack.org, LKML , Mel Gorman Subject: Re: [PATCH] mm: hugetlb: fix pgoff computation when unmapping page from vma Message-ID: <20111220141437.GJ10565@tiehlicka.suse.cz> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org [CCing Mel] On Tue 20-12-11 21:45:51, Hillf Danton wrote: > The computation for pgoff is incorrect, at least with > > (vma->vm_pgoff >> PAGE_SHIFT) > > involved. It is fixed with the available method if HPAGE_SIZE is concerned in > page cache lookup. Have you seen this as a real issue? I guess nobody noticed as it is quite rare error case. Anyways, yes, looks good. > Cc: Michal Hocko > Cc: KAMEZAWA Hiroyuki > Cc: Andrew Morton > Signed-off-by: Hillf Danton Reviewed-by: Michal Hocko > --- > > --- a/mm/hugetlb.c Tue Dec 20 21:26:30 2011 > +++ b/mm/hugetlb.c Tue Dec 20 21:40:44 2011 > @@ -2315,8 +2315,7 @@ static int unmap_ref_private(struct mm_s > * from page cache lookup which is in HPAGE_SIZE units. > */ > address = address & huge_page_mask(h); > - pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) > - + (vma->vm_pgoff >> PAGE_SHIFT); > + pgoff = linear_hugepage_index(vma, address); You have hstate so you can use vma_hugecache_offset directly > mapping = (struct address_space *)page_private(page); > > /* > Thanks -- Michal Hocko SUSE Labs SUSE LINUX s.r.o. Lihovarska 1060/12 190 00 Praha 9 Czech Republic