From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932679AbbFRQC5 (ORCPT ); Thu, 18 Jun 2015 12:02:57 -0400 Received: from mail-wg0-f41.google.com ([74.125.82.41]:35850 "EHLO mail-wg0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932605AbbFRQCt (ORCPT ); Thu, 18 Jun 2015 12:02:49 -0400 Message-ID: <5582EBA6.1080607@redhat.com> Date: Thu, 18 Jun 2015 18:02:46 +0200 From: Paolo Bonzini User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 MIME-Version: 1.0 To: "Michael S. Tsirkin" CC: Igor Mammedov , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, andrey@xdel.ru Subject: Re: [PATCH 3/5] vhost: support upto 509 memory regions References: <20150617173736-mutt-send-email-mst@redhat.com> <20150617180921.7972345d@igors-macbook-pro.local> <20150617182917-mutt-send-email-mst@redhat.com> <20150618111224.0aa6dff7@nial.brq.redhat.com> <20150618112004-mutt-send-email-mst@redhat.com> <20150618133912.63636a47@nial.brq.redhat.com> <20150618134040-mutt-send-email-mst@redhat.com> <5582B088.1090207@redhat.com> <20150618142455-mutt-send-email-mst@redhat.com> <5582CBA6.5070105@redhat.com> <20150618164559-mutt-send-email-mst@redhat.com> In-Reply-To: <20150618164559-mutt-send-email-mst@redhat.com> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 18/06/2015 16:47, Michael S. Tsirkin wrote: >> However, with Igor's patches a memory_region_del_subregion will cause a >> mmap(MAP_NORESERVE), which _does_ have the effect of making the hva go away. >> >> I guess one way to do it would be to alias the same page in two places, >> one for use by vhost and one for use by everything else. However, the >> kernel does not provide the means to do this kind of aliasing for >> anonymous mmaps. > > Basically pages go away on munmap, so won't simple > lock > munmap > mmap(MAP_NORESERVE) > unlock > do the trick? Not sure I follow. Here we have this: VCPU 1 VCPU 2 I/O worker ---------------------------------------------------------------------------------------- take big QEMU lock p = address_space_map(hva, len) pass I/O request to worker thread read(fd, p, len) release big QEMU lock memory_region_del_subregion mmap(MAP_NORESERVE) read returns EFAULT wake up VCPU 1 take big QEMU lock EFAULT? What's that? In another scenario you are less lucky: the memory accesses between address_space_map/unmap aren't done in the kernel and you get a plain old SIGSEGV. This is not something that you can fix with a lock. The very purpose of the map/unmap API is to do stuff asynchronously while the lock is released. Thanks, Paolo