Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932249AbcK1Ih0 (ORCPT ); Mon, 28 Nov 2016 03:37:26 -0500 Received: from mga01.intel.com ([192.55.52.88]:19152 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932214AbcK1IhS (ORCPT ); Mon, 28 Nov 2016 03:37:18 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.31,563,1473145200"; d="scan'208";a="36317465" Date: Mon, 28 Nov 2016 16:37:15 +0800 From: Aaron Lu To: Linus Torvalds Cc: Linux Memory Management List , Dave Hansen , Andrew Morton , "Kirill A. Shutemov" , Huang Ying , linux-kernel@vger.kernel.org Subject: [PATCH 0/2] use mmu gather logic for tlb flush in mremap Message-ID: <20161128083715.GA21738@aaronlu.sh.intel.com> References: <026b73f6-ca1d-e7bb-766c-4aaeb7071ce6@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 922 Lines: 24 On Fri, Nov 18, 2016 at 10:48:20AM +0800, Aaron Lu wrote: > On 11/18/2016 01:53 AM, Linus Torvalds wrote: > > I'm not entirely happy with the force_flush vs need_flush games, and I > > really think this code should be updated to use the same "struct > > mmu_gather" that we use for the other TLB flushing cases (no need for > > the page freeing batching, but the tlb_flush_mmu_tlbonly() logic > > should be the same). > > I see. > > > > > But I guess that's a bigger change, so that wouldn't be approriate for > > rc5 or stable back-porting anyway. But it would be lovely if somebody > > could look at that. Hint hint. > > I'll work on it, thanks for the suggestion. So here it is. I'm not quite sure if I've done the right thing in patch 2/2, i.e. should I just use tlb_flush_mmu or export tlb_flush_mmu_tlbonly and then use it in mremap.c. Please take a look and let me know what you think, thanks! Regards, Aaron