From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dave Hansen Subject: Re: [PATCH 00/10] RFC: userfault Date: Thu, 03 Jul 2014 08:41:33 -0700 Message-ID: <53B579AD.1010201@sr71.net> References: <1404319816-30229-1-git-send-email-aarcange@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "\"Dr. David Alan Gilbert\"" , Johannes Weiner , Andrew Morton , Android Kernel Team , Robert Love , Mel Gorman , Hugh Dickins , Rik van Riel , Dmitry Adamushko , Neil Brown , Mike Hommey , Taras Glek , Jan Kara , KOSAKI Motohiro , Michel Lespinasse , Minchan Kim , Keith Packard , "Huangpeng (Peter)" , Isaku Yamahata , Paolo Bonzini , Anthony Liguori , Stefan Hajnoczi , Wenchao Xia , Andr To: Andrea Arcangeli , qemu-devel@nongnu.org, kvm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Return-path: In-Reply-To: <1404319816-30229-1-git-send-email-aarcange@redhat.com> Sender: owner-linux-mm@kvack.org List-Id: kvm.vger.kernel.org On 07/02/2014 09:50 AM, Andrea Arcangeli wrote: > The MADV_USERFAULT feature should be generic enough that it can > provide the userfaults to the Android volatile range feature too, on > access of reclaimed volatile pages. Maybe. I certainly can't keep track of all the versions of the variations of the volatile ranges patches. But, I don't think it's a given that this can be reused. First of all, volatile ranges is trying to replace ashmem and is going to require _some_ form of sharing. This mechanism, being tightly coupled to anonymous memory at the moment, is not a close fit for that. It's also important to call out that this is a VMA-based mechanism. I certainly can't predict what we'll merge for volatile ranges, but not all of them are VMA-based. We'd also need a mechanism on top of this to differentiate plain not-present pages from not-present-because-purged pages. That said, I _think_ this might fit well in to what the Mozilla guys wanted out of volatile ranges. I'm not confident about it, though. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pa0-f51.google.com (mail-pa0-f51.google.com [209.85.220.51]) by kanga.kvack.org (Postfix) with ESMTP id 340756B0031 for ; Thu, 3 Jul 2014 11:41:39 -0400 (EDT) Received: by mail-pa0-f51.google.com with SMTP id hz1so414208pad.38 for ; Thu, 03 Jul 2014 08:41:38 -0700 (PDT) Received: from blackbird.sr71.net (www.sr71.net. [198.145.64.142]) by mx.google.com with ESMTP id fi4si33193179pbb.193.2014.07.03.08.41.35 for ; Thu, 03 Jul 2014 08:41:37 -0700 (PDT) Message-ID: <53B579AD.1010201@sr71.net> Date: Thu, 03 Jul 2014 08:41:33 -0700 From: Dave Hansen MIME-Version: 1.0 Subject: Re: [PATCH 00/10] RFC: userfault References: <1404319816-30229-1-git-send-email-aarcange@redhat.com> In-Reply-To: <1404319816-30229-1-git-send-email-aarcange@redhat.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: Andrea Arcangeli , qemu-devel@nongnu.org, kvm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: "\"Dr. David Alan Gilbert\"" , Johannes Weiner , Andrew Morton , Android Kernel Team , Robert Love , Mel Gorman , Hugh Dickins , Rik van Riel , Dmitry Adamushko , Neil Brown , Mike Hommey , Taras Glek , Jan Kara , KOSAKI Motohiro , Michel Lespinasse , Minchan Kim , Keith Packard , "Huangpeng (Peter)" , Isaku Yamahata , Paolo Bonzini , Anthony Liguori , Stefan Hajnoczi , Wenchao Xia , Andrew Jones , Juan Quintela , Mel Gorman On 07/02/2014 09:50 AM, Andrea Arcangeli wrote: > The MADV_USERFAULT feature should be generic enough that it can > provide the userfaults to the Android volatile range feature too, on > access of reclaimed volatile pages. Maybe. I certainly can't keep track of all the versions of the variations of the volatile ranges patches. But, I don't think it's a given that this can be reused. First of all, volatile ranges is trying to replace ashmem and is going to require _some_ form of sharing. This mechanism, being tightly coupled to anonymous memory at the moment, is not a close fit for that. It's also important to call out that this is a VMA-based mechanism. I certainly can't predict what we'll merge for volatile ranges, but not all of them are VMA-based. We'd also need a mechanism on top of this to differentiate plain not-present pages from not-present-because-purged pages. That said, I _think_ this might fit well in to what the Mozilla guys wanted out of volatile ranges. I'm not confident about it, though. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758755AbaGCPlh (ORCPT ); Thu, 3 Jul 2014 11:41:37 -0400 Received: from www.sr71.net ([198.145.64.142]:52408 "EHLO blackbird.sr71.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753988AbaGCPlg (ORCPT ); Thu, 3 Jul 2014 11:41:36 -0400 Message-ID: <53B579AD.1010201@sr71.net> Date: Thu, 03 Jul 2014 08:41:33 -0700 From: Dave Hansen User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Andrea Arcangeli , qemu-devel@nongnu.org, kvm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org CC: "\"Dr. David Alan Gilbert\"" , Johannes Weiner , Andrew Morton , Android Kernel Team , Robert Love , Mel Gorman , Hugh Dickins , Rik van Riel , Dmitry Adamushko , Neil Brown , Mike Hommey , Taras Glek , Jan Kara , KOSAKI Motohiro , Michel Lespinasse , Minchan Kim , Keith Packard , "Huangpeng (Peter)" , Isaku Yamahata , Paolo Bonzini , Anthony Liguori , Stefan Hajnoczi , Wenchao Xia , Andrew Jones , Juan Quintela , Mel Gorman Subject: Re: [PATCH 00/10] RFC: userfault References: <1404319816-30229-1-git-send-email-aarcange@redhat.com> In-Reply-To: <1404319816-30229-1-git-send-email-aarcange@redhat.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 07/02/2014 09:50 AM, Andrea Arcangeli wrote: > The MADV_USERFAULT feature should be generic enough that it can > provide the userfaults to the Android volatile range feature too, on > access of reclaimed volatile pages. Maybe. I certainly can't keep track of all the versions of the variations of the volatile ranges patches. But, I don't think it's a given that this can be reused. First of all, volatile ranges is trying to replace ashmem and is going to require _some_ form of sharing. This mechanism, being tightly coupled to anonymous memory at the moment, is not a close fit for that. It's also important to call out that this is a VMA-based mechanism. I certainly can't predict what we'll merge for volatile ranges, but not all of them are VMA-based. We'd also need a mechanism on top of this to differentiate plain not-present pages from not-present-because-purged pages. That said, I _think_ this might fit well in to what the Mozilla guys wanted out of volatile ranges. I'm not confident about it, though. From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40150) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X2j8t-0002ac-4p for qemu-devel@nongnu.org; Thu, 03 Jul 2014 11:41:55 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1X2j8k-0007pv-Ah for qemu-devel@nongnu.org; Thu, 03 Jul 2014 11:41:47 -0400 Received: from www.sr71.net ([198.145.64.142]:46556 helo=blackbird.sr71.net) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X2j8k-0007pS-66 for qemu-devel@nongnu.org; Thu, 03 Jul 2014 11:41:38 -0400 Message-ID: <53B579AD.1010201@sr71.net> Date: Thu, 03 Jul 2014 08:41:33 -0700 From: Dave Hansen MIME-Version: 1.0 References: <1404319816-30229-1-git-send-email-aarcange@redhat.com> In-Reply-To: <1404319816-30229-1-git-send-email-aarcange@redhat.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 00/10] RFC: userfault List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Andrea Arcangeli , qemu-devel@nongnu.org, kvm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: Robert Love , Jan Kara , Neil Brown , Stefan Hajnoczi , Andrew Jones , KOSAKI Motohiro , Michel Lespinasse , Taras Glek , Juan Quintela , Hugh Dickins , Isaku Yamahata , Mel Gorman , Android Kernel Team , Mel Gorman , "\"Dr. David Alan Gilbert\"" , "Huangpeng (Peter)" , Anthony Liguori , Mike Hommey , Keith Packard , Wenchao Xia , Minchan Kim , Dmitry Adamushko , Johannes Weiner , Paolo Bonzini , Andrew Morton On 07/02/2014 09:50 AM, Andrea Arcangeli wrote: > The MADV_USERFAULT feature should be generic enough that it can > provide the userfaults to the Android volatile range feature too, on > access of reclaimed volatile pages. Maybe. I certainly can't keep track of all the versions of the variations of the volatile ranges patches. But, I don't think it's a given that this can be reused. First of all, volatile ranges is trying to replace ashmem and is going to require _some_ form of sharing. This mechanism, being tightly coupled to anonymous memory at the moment, is not a close fit for that. It's also important to call out that this is a VMA-based mechanism. I certainly can't predict what we'll merge for volatile ranges, but not all of them are VMA-based. We'd also need a mechanism on top of this to differentiate plain not-present pages from not-present-because-purged pages. That said, I _think_ this might fit well in to what the Mozilla guys wanted out of volatile ranges. I'm not confident about it, though.