From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965099AbVHJNUs (ORCPT ); Wed, 10 Aug 2005 09:20:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S965101AbVHJNUs (ORCPT ); Wed, 10 Aug 2005 09:20:48 -0400 Received: from silver.veritas.com ([143.127.12.111]:59728 "EHLO silver.veritas.com") by vger.kernel.org with ESMTP id S965099AbVHJNUr (ORCPT ); Wed, 10 Aug 2005 09:20:47 -0400 Date: Wed, 10 Aug 2005 14:22:40 +0100 (BST) From: Hugh Dickins X-X-Sender: hugh@goblin.wat.veritas.com To: Gleb Natapov cc: "Michael S. Tsirkin" , Roland Dreier , linux-kernel@vger.kernel.org, openib-general@openib.org Subject: Re: [openib-general] Re: [PATCH repost] PROT_DONTCOPY: ifiniband uverbs fork support In-Reply-To: <20050810083943.GM16361@minantech.com> Message-ID: References: <20050719165542.GB16028@mellanox.co.il> <20050725171928.GC12206@mellanox.co.il> <20050726133553.GA22276@mellanox.co.il> <20050810083943.GM16361@minantech.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-OriginalArrivalTime: 10 Aug 2005 13:20:46.0928 (UTC) FILETIME=[51A0A500:01C59DAE] Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 10 Aug 2005, Gleb Natapov wrote: > On Tue, Aug 09, 2005 at 07:13:33PM +0100, Hugh Dickins wrote: > > Even more I'd prefer one of these two solutions below, which sidestep > > that uncleanliness - but both of these would be in mmap only, no clean > > way to change afterwards (except by munmap or mmap MAP_FIXED): > > > > 1. Use the standard mmap(NULL, len, PROT_READ|PROT_WRITE, > > MAP_SHARED|MAP_ANONYMOUS, -1, 0) which gives you a memory object > > shared with children, so write-protection and COW won't come into it. > > > > or if there's good reason why that's no good, > > > > 2. Define a MAP_DONTCOPY to mmap: we have a fine tradition of MAP_flags > > to achieve this or that effect, adding one more would be cleaner than > > now corrupting mprotect or madvise. > > They are both relying on the way user allocates memory for RDMA. The idea > behind Michael's propose it to let library (MPI for instance) to tell to the > kernel that the pages are used for RDMA and it is not safe to copy them now. > The pages may be anywhere in the process address space bss, text, stack > whatever. That's a nice aim, but I don't think it can quite be done in the face of the fork issue - one way or another, we have to change the behaviour of a forked RDMA area slightly, which might interfere with common assumptions. Your stack example is a good one: if we end up setting VM_DONTCOPY on the user stack, then I don't think fork's child will get very far without hitting a SIGSEGV. Hugh