From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753573AbaKXNDo (ORCPT ); Mon, 24 Nov 2014 08:03:44 -0500 Received: from e06smtp17.uk.ibm.com ([195.75.94.113]:58590 "EHLO e06smtp17.uk.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753099AbaKXNDk (ORCPT ); Mon, 24 Nov 2014 08:03:40 -0500 From: Christian Borntraeger To: linux-kernel@vger.kernel.org Cc: "linux-arch@vger.kernel.org, linux-mips@linux-mips.org, linux-x86_64@vger.kernel.org, linux-s390"@vger.kernel.org, Paolo Bonzini , paulmck@linux.vnet.ibm.com, mingo@kernel.org, torvalds@linux-foundation.org, Catalin Marinas , Will Deacon , Christian Borntraeger Subject: [PATCH/RFC 2/7] mm: replace page table access via ACCESS_ONCE with barriers Date: Mon, 24 Nov 2014 14:03:25 +0100 Message-Id: <1416834210-61738-3-git-send-email-borntraeger@de.ibm.com> X-Mailer: git-send-email 1.9.3 In-Reply-To: <1416834210-61738-1-git-send-email-borntraeger@de.ibm.com> References: <1416834210-61738-1-git-send-email-borntraeger@de.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14112413-0029-0000-0000-000001CF0D68 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org ACCESS_ONCE does not work reliably on non-scalar types. For example gcc 4.6 and 4.7 might remove the volatile tag for such accesses during the SRA (scalar replacement of aggregates) step (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145) Let's change the code to access the page table elements with a barrier afterwards. Signed-off-by: Christian Borntraeger --- mm/gup.c | 4 +++- mm/memory.c | 3 ++- mm/rmap.c | 3 ++- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index cd62c8c..e44af3c 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -917,7 +917,9 @@ static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end, pudp = pud_offset(pgdp, addr); do { - pud_t pud = ACCESS_ONCE(*pudp); + pud_t pud = *pudp; + + barrier(); next = pud_addr_end(addr, end); if (pud_none(pud)) diff --git a/mm/memory.c b/mm/memory.c index 3e50383..d982e35 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3202,7 +3202,8 @@ static int handle_pte_fault(struct mm_struct *mm, pte_t entry; spinlock_t *ptl; - entry = ACCESS_ONCE(*pte); + entry = *pte; + barrier(); if (!pte_present(entry)) { if (pte_none(entry)) { if (vma->vm_ops) { diff --git a/mm/rmap.c b/mm/rmap.c index 19886fb..1e54274 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -581,7 +581,8 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ - pmde = ACCESS_ONCE(*pmd); + pmde = *pmd; + barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: -- 1.9.3