Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753704AbbBZNQK (ORCPT ); Thu, 26 Feb 2015 08:16:10 -0500 Received: from bastet.se.axis.com ([195.60.68.11]:35183 "EHLO bastet.se.axis.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753190AbbBZNQI (ORCPT ); Thu, 26 Feb 2015 08:16:08 -0500 From: Lars Persson To: linux-mips@linux-mips.org, ralf@linux-mips.org, paul.burton@imgtec.com Cc: linux-kernel@vger.kernel.org, Lars Persson Subject: [PATCH 0/2] New fix for icache coherency race Date: Thu, 26 Feb 2015 14:16:01 +0100 Message-Id: <1424956563-29535-1-git-send-email-larper@axis.com> X-Mailer: git-send-email 1.7.10.4 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1429 Lines: 34 This patch set proposes an improved fix for the race condition that originally was fixed in commit 2a4a8b1e5d9d ("MIPS: Remove race window in page fault handling"). I have used the flush_icache_page API that is marked as deprecated in Documentation/cachetlb.txt. There are strong reasons to keep this API because it is not possible to implement an efficient and race-free lazy flushing using the other APIs. You can refer to a discussion about the same issue in arch/arm where they chose to implement the solution in set_pte_at. In arch/mips we could not do this because we lack information about the executability of the mapping in set_pte_at() and thus we would have to flush all pages to be safe. http://lists.infradead.org/pipermail/linux-arm-kernel/2010-November/030915.html Lars Persson (2): Revert "MIPS: Remove race window in page fault handling" MIPS: Fix race condition in lazy cache flushing. arch/mips/include/asm/cacheflush.h | 35 ++++++++++++++++++++--------------- arch/mips/include/asm/pgtable.h | 10 ++++++---- arch/mips/mm/cache.c | 27 ++++++++------------------- 3 files changed, 34 insertions(+), 38 deletions(-) -- 1.7.10.4 -- 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/