From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753983Ab2LSR72 (ORCPT ); Wed, 19 Dec 2012 12:59:28 -0500 Received: from zene.cmpxchg.org ([85.214.230.12]:36696 "EHLO zene.cmpxchg.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755671Ab2LSR7K (ORCPT ); Wed, 19 Dec 2012 12:59:10 -0500 Date: Wed, 19 Dec 2012 12:58:11 -0500 From: Johannes Weiner To: Simon Jeons Cc: Andrew Morton , Rik van Riel , Michal Hocko , Mel Gorman , Hugh Dickins , Satoru Moriya , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [patch 7/7] mm: reduce rmap overhead for ex-KSM page copies created on swap faults Message-ID: <20121219175811.GD7147@cmpxchg.org> References: <1355767957-4913-1-git-send-email-hannes@cmpxchg.org> <1355767957-4913-8-git-send-email-hannes@cmpxchg.org> <1355900479.1381.1.camel@kernel-VirtualBox> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1355900479.1381.1.camel@kernel-VirtualBox> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Dec 19, 2012 at 02:01:19AM -0500, Simon Jeons wrote: > On Mon, 2012-12-17 at 13:12 -0500, Johannes Weiner wrote: > > When ex-KSM pages are faulted from swap cache, the fault handler is > > not capable of re-establishing anon_vma-spanning KSM pages. In this > > case, a copy of the page is created instead, just like during a COW > > break. > > > > These freshly made copies are known to be exclusive to the faulting > > VMA and there is no reason to go look for this page in parent and > > sibling processes during rmap operations. > > > > Use page_add_new_anon_rmap() for these copies. This also puts them on > > the proper LRU lists and marks them SwapBacked, so we can get rid of > > doing this ad-hoc in the KSM copy code. > > Is it just a code cleanup instead of reduce rmap overhead? Both.