From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758485Ab3KMHdG (ORCPT ); Wed, 13 Nov 2013 02:33:06 -0500 Received: from m53-178.qiye.163.com ([123.58.178.53]:36081 "EHLO m53-178.qiye.163.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757480Ab3KMHdC (ORCPT ); Wed, 13 Nov 2013 02:33:02 -0500 From: Li Wang To: ceph-devel@vger.kernel.org Cc: Sage Weil , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, Li Wang Subject: [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage() Date: Wed, 13 Nov 2013 15:22:14 +0800 Message-Id: <1384327335-18812-1-git-send-email-liwang@ubuntukylin.com> X-Mailer: git-send-email 1.7.9.5 X-HM-Spam-Status: e1koWUFPN1dZCBgUCR5ZQUpMVUNJQkJCQkJJSExLTUtOTldZCQ4XHghZQV koKz0kKzooKCQyNSQzPjo*PilBS1VLQDYjJCI#KCQyNSQzPjo*PilBS1VLQCsvKSQ1NCQyNSQzPj o*PilBSVVLQDg0LjUvKSIkODVBS1VLQCk#PDI0NSQ6KDI6QUtVS0ArKTQtMjU4PiQ8Ljo1PD80NT xBS1VLQD8iNTo2MjgkMiskNTQkMjUkMz46Pz4pQUtVS0ApPjo3JDIrJDI1JCk5NyQyNSQzPjo*Pi lBSklVS0A2LjcvMiQpOCsvJD8yPT0#KT41LyQyNSQzPjo*PilBSVVLQDIrJC80PzoiJDg1LyRLJE pLS0FLVUtAMiskTiQ2MjUuLz4kODUvJEskSktBS1VLQDIrJEhLJDYyNS4vPiQ4NS8kSyROS0FLVU tAMiskSiQzNC4pJDg1LyRLJEpLS0FLVUtAMiskSiQ2MjUuLz4kODUvJEskSktBS1VLQCguOSQ#QU pVTk5APTUkKC45JD41LDQpPygkMzcxJEpLS0lLSkFLVUlDWQY+ X-HM-Sender-Digest: e1kSHx4VD1lBWUc6MQg6Cjo4LDo4EDorKjhIOj4qOkMwCjFVSlVKSENP SElMSENMTE5CVTMWGhIXVRcSDBoVHDsOGQ4VDw4QAhcSFVUYFBZFWVdZDB4ZWUEdGhcIHldZCAFZ QUpMSEo3V1kSC1lBWUpDSFVNSFVJTktVTVkG Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org If the length of data to be read in readpage() is exactly PAGE_CACHE_SIZE, the original code does not flush d-cache for data consistency after finishing reading. This patches fixes this. Signed-off-by: Li Wang --- fs/ceph/addr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6df8bd4..7b0000a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page) if (err < 0) { SetPageError(page); goto out; - } else if (err < PAGE_CACHE_SIZE) { + } else { + if (err < PAGE_CACHE_SIZE) { /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_CACHE_SIZE); + zero_user_segment(page, err, PAGE_CACHE_SIZE); + } else { + flush_dcache_page(page); + } } SetPageUptodate(page); -- 1.7.9.5