From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932987AbaEMJlU (ORCPT ); Tue, 13 May 2014 05:41:20 -0400 Received: from szxga02-in.huawei.com ([119.145.14.65]:53753 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932570AbaEMJlI (ORCPT ); Tue, 13 May 2014 05:41:08 -0400 Date: Wed, 14 May 2014 11:29:48 +0200 From: Anthony Iliopoulos To: Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" CC: , , "Kirill A. Shutemov" , Dave Hansen , Shay Goikhman , Paul Mundt , "Carlos Villavieja" , Nacho Navarro , Avi Mendelson , Yoav Etsion Subject: [PATCH] x86, hugetlb: add missing TLB page invalidation for hugetlb_cow() Message-ID: <20140514092948.GA17391@server-36.huawei.corp> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline X-Originating-IP: [10.220.139.36] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The invalidation is required in order to maintain proper semantics under CoW conditions. In scenarios where a process clones several threads, a thread operating on a core whose DTLB entry for a particular hugepage has not been invalidated, will be reading from the hugepage that belongs to the forked child process, even after hugetlb_cow(). The thread will not see the updated page as long as the stale DTLB entry remains cached, the thread attempts to write into the page, the child process exits, or the thread gets migrated to a different processor. Signed-off-by: Anthony Iliopoulos Suggested-by: Shay Goikhman --- arch/x86/include/asm/hugetlb.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index a809121..68c0539 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + ptep_clear_flush(vma, addr, ptep); } static inline int huge_pte_none(pte_t pte) -- 1.8.1.2