Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757383AbZIOUP7 (ORCPT ); Tue, 15 Sep 2009 16:15:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753739AbZIOUPx (ORCPT ); Tue, 15 Sep 2009 16:15:53 -0400 Received: from mk-filter-3-a-1.mail.uk.tiscali.com ([212.74.100.54]:40536 "EHLO mk-filter-3-a-1.mail.uk.tiscali.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753687AbZIOUPx (ORCPT ); Tue, 15 Sep 2009 16:15:53 -0400 X-Trace: 259116194/mk-filter-3.mail.uk.tiscali.com/B2C/$b2c-THROTTLED-DYNAMIC/b2c-CUSTOMER-DYNAMIC-IP/79.69.84.74/None/hugh.dickins@tiscali.co.uk X-SBRS: None X-RemoteIP: 79.69.84.74 X-IP-MAIL-FROM: hugh.dickins@tiscali.co.uk X-SMTP-AUTH: X-MUA: X-IP-BHB: Once X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AlgFACWTr0pPRVRK/2dsb2JhbACBU98BhBcF X-IronPort-AV: E=Sophos;i="4.44,391,1249254000"; d="scan'208";a="259116194" Date: Tue, 15 Sep 2009 21:15:07 +0100 (BST) From: Hugh Dickins X-X-Sender: hugh@sister.anvils To: KAMEZAWA Hiroyuki cc: Hugh Dickins , Andrew Morton , KOSAKI Motohiro , Linus Torvalds , Nick Piggin , Rik van Riel , linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH 7/8] mm: reinstate ZERO_PAGE In-Reply-To: <20090909104423.4bd23a2c.kamezawa.hiroyu@jp.fujitsu.com> Message-ID: References: <20090908113734.869cdad7.kamezawa.hiroyu@jp.fujitsu.com> <20090909104423.4bd23a2c.kamezawa.hiroyu@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1097 Lines: 26 On Wed, 9 Sep 2009, KAMEZAWA Hiroyuki wrote: > On Tue, 8 Sep 2009 12:56:57 +0100 (BST) > Hugh Dickins wrote: > > > > Though I like that we don't _need_ to change mlock.c for reinstated > > ZERO_PAGE, this morning I'm having trouble persuading myself that > > mlocking a readonly anonymous area is too silly to optimize for. > > > > Maybe the very people who persuaded you to bring back the anonymous > > use of ZERO_PAGE, are also doing a huge mlock of the area first? > No, as far as I know, they'll not do huge mlock. Thanks for that (not entirely conclusive!) info. I've decided for the moment to make a couple of further optimizations in mlock.c (along with the comment you asked for), and leave adding another __get_user_pages flag until a case for it is demonstrated. Small patch series following shortly. Hugh -- 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/