From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753609AbcBJJ20 (ORCPT ); Wed, 10 Feb 2016 04:28:26 -0500 Received: from foss.arm.com ([217.140.101.70]:45589 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752007AbcBJJ2X (ORCPT ); Wed, 10 Feb 2016 04:28:23 -0500 Date: Wed, 10 Feb 2016 09:28:23 +0000 From: Will Deacon To: David Daney Cc: linux-arm-kernel@lists.infradead.org, Mark Rutland , Catalin Marinas , Marc Zyngier , linux-kernel@vger.kernel.org, Andrew Pinski , David Daney Subject: Re: [PATCH] arm64: Add workaround for Cavium erratum 27456 Message-ID: <20160210092822.GA1052@arm.com> References: <1455046156-10582-1-git-send-email-ddaney.cavm@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1455046156-10582-1-git-send-email-ddaney.cavm@gmail.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Feb 09, 2016 at 11:29:16AM -0800, David Daney wrote: > From: Andrew Pinski > > On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI > instructions may cause the icache to become invalid if it contains > data for a non-current ASID. > > This patch implements the workaround (which flushes the local icache > when switching the mm) by using code patching. So, to be clear, is this "just" a performance problem as opposed to a correctness issue? If so, do you have any numbers with and without this change? Will From mboxrd@z Thu Jan 1 00:00:00 1970 From: will.deacon@arm.com (Will Deacon) Date: Wed, 10 Feb 2016 09:28:23 +0000 Subject: [PATCH] arm64: Add workaround for Cavium erratum 27456 In-Reply-To: <1455046156-10582-1-git-send-email-ddaney.cavm@gmail.com> References: <1455046156-10582-1-git-send-email-ddaney.cavm@gmail.com> Message-ID: <20160210092822.GA1052@arm.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Tue, Feb 09, 2016 at 11:29:16AM -0800, David Daney wrote: > From: Andrew Pinski > > On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI > instructions may cause the icache to become invalid if it contains > data for a non-current ASID. > > This patch implements the workaround (which flushes the local icache > when switching the mm) by using code patching. So, to be clear, is this "just" a performance problem as opposed to a correctness issue? If so, do you have any numbers with and without this change? Will