From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.2 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_MUTT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 26E8BC43613 for ; Thu, 20 Jun 2019 08:31:40 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id E96612085A for ; Thu, 20 Jun 2019 08:31:39 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org E96612085A Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:44864 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hdsTr-0004DI-5s for qemu-devel@archiver.kernel.org; Thu, 20 Jun 2019 04:31:39 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:58809) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hdsIN-0003mf-C7 for qemu-devel@nongnu.org; Thu, 20 Jun 2019 04:19:48 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hdsIL-0004fh-DT for qemu-devel@nongnu.org; Thu, 20 Jun 2019 04:19:47 -0400 Received: from mga04.intel.com ([192.55.52.120]:57182) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1hdsIK-0004c9-Am for qemu-devel@nongnu.org; Thu, 20 Jun 2019 04:19:45 -0400 X-Amp-Result: UNKNOWN X-Amp-Original-Verdict: FILE UNKNOWN X-Amp-File-Uploaded: False Received: from orsmga007.jf.intel.com ([10.7.209.58]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 20 Jun 2019 01:19:39 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.63,396,1557212400"; d="scan'208";a="150860441" Received: from joy-optiplex-7040.sh.intel.com (HELO joy-OptiPlex-7040) ([10.239.13.9]) by orsmga007.jf.intel.com with ESMTP; 20 Jun 2019 01:19:38 -0700 Date: Thu, 20 Jun 2019 04:13:46 -0400 From: Yan Zhao To: Peter Xu Message-ID: <20190620081345.GC9303@joy-OptiPlex-7040> References: <1560934185-14152-1-git-send-email-yan.y.zhao@intel.com> <39c4c32b-e34a-8d8f-abbc-ab346ec5bed7@redhat.com> <20190620040230.GB9073@xz-x1> <20190620041400.GB9303@joy-OptiPlex-7040> <20190620081437.GA11135@xz-x1> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20190620081437.GA11135@xz-x1> User-Agent: Mutt/1.9.4 (2018-02-28) X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.120 Subject: Re: [Qemu-devel] [PATCH] memory: do not do out of bound notification X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Yan Zhao Cc: Auger Eric , "qemu-devel@nongnu.org" , "pbonzini@redhat.com" Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" On Thu, Jun 20, 2019 at 04:14:37PM +0800, Peter Xu wrote: > On Thu, Jun 20, 2019 at 12:14:00AM -0400, Yan Zhao wrote: > > On Thu, Jun 20, 2019 at 12:02:30PM +0800, Peter Xu wrote: > > > On Wed, Jun 19, 2019 at 03:17:41PM +0200, Auger Eric wrote: > > > > Hi Yan, > > > > > > > > [+ Peter] > > > > > > > > On 6/19/19 10:49 AM, Yan Zhao wrote: > > > > > even if an entry overlaps with notifier's range, should not map/unmap > > > > > out of bound part in the entry. > > > > > > > > I don't think the patch was based on the master as the trace at the very > > > > end if not part of the upstream code. > > > > > > > > > > This would cause problem in below case: > > > > > 1. initially there are two notifiers with ranges > > > > > 0-0xfedfffff, 0xfef00000-0xffffffffffffffff, > > > > > IOVAs from 0x3c000000 - 0x3c1fffff is in shadow page table. > > > > > > > > > > 2. in vfio, memory_region_register_iommu_notifier() is followed by > > > > > memory_region_iommu_replay(), which will first call address space unmap, > > > > > and walk and add back all entries in vtd shadow page table. e.g. > > > > > (1) for notifier 0-0xfedfffff, > > > > > IOVAs from 0 - 0xffffffff get unmapped, > > > > > and IOVAs from 0x3c000000 - 0x3c1fffff get mapped > > > > > > > > While the patch looks sensible, the issue is the notifier scope used in > > > > vtd_address_space_unmap is not a valid mask (ctpop64(size) != 1). Then > > > > the size is recomputed (either using n = 64 - clz64(size) for the 1st > > > > notifier or n = s->aw_bits for the 2d) and also the entry (especially > > > > for the 2d notifier where it becomes 0) to get a proper alignment. > > > > > > > > vtd_page_walk sends notifications per block or page (with valid > > > > addr_mask) so stays within the notifier. > > > > > > > > Modifying the entry->iova/addr_mask again in memory_region_notify_one > > > > leads to unaligned start address / addr_mask. I don't think we want that. > > > > > > > > Can't we modity the vtd_address_space_unmap() implementation to split > > > > the invalidation in smaller chunks instead? > > > > > > Seems workable, to be explicit - we can even cut it into chunks with > > > different size to be efficient. Like, this range: > > > > > > 0x0e00_0000 - 0x1_0000_0000 (size 0xf200_0000) > > > > > > can be one of this: > > > > > > 0x0e000000 - 0x1000_0000 (size 0x0200_0000) > > > > > > plus one of this: > > > > > > 0x1000_0000 - 0x1_0000_0000 (size 0xf000_0000) > > > > > > Yan, could you help explain the issue better on how to reproduce and > > > what's the error when the problem occurs? For example, is that > > > happened when a device hot-plugged into an existing VFIO container > > > (with some mapped IOVAs)? Did you get host DMA errors later on? > > > > > > Thanks, > > > > > > -- > > > Peter Xu > > > > Hi Peter > > it happens when there's an RMRR region in my guest iommu driver. > > Do you mean a RMRR region in the ACPI table? AFAIK current QEMU VT-d > does not have RMRR at all, so that's a customized QEMU? it can be a customized QEMU with RMRR region in ACPI table. or simply hardcode in guest kernel. > > > if not adding this range check, IOVAs in this region would be unmapped and DMA > > faults are met in host. > > I see, thanks. > > -- > Peter Xu