linux-kernel - Re: [RFC PATCH v2 08/10] vfio/type1: Add domain at(de)taching group helpers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <75517c87-6ffd-2023-a541-3c69ae52ef4b@arm.com>
Date:   Tue, 25 Sep 2018 18:55:41 +0100
From:   Jean-Philippe Brucker <jean-philippe.brucker@....com>
To:     "Tian, Kevin" <kevin.tian@...el.com>,
        Lu Baolu <baolu.lu@...ux.intel.com>,
        Joerg Roedel <joro@...tes.org>,
        David Woodhouse <dwmw2@...radead.org>,
        Alex Williamson <alex.williamson@...hat.com>,
        Kirti Wankhede <kwankhede@...dia.com>
Cc:     "Raj, Ashok" <ashok.raj@...el.com>,
        "Bie, Tiwei" <tiwei.bie@...el.com>,
        "Kumar, Sanjay K" <sanjay.k.kumar@...el.com>,
        "iommu@...ts.linux-foundation.org" <iommu@...ts.linux-foundation.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "Sun, Yi Y" <yi.y.sun@...el.com>,
        "Pan, Jacob jun" <jacob.jun.pan@...el.com>,
        "kvm@...r.kernel.org" <kvm@...r.kernel.org>
Subject: Re: [RFC PATCH v2 08/10] vfio/type1: Add domain at(de)taching group
 helpers

On 19/09/2018 00:26, Tian, Kevin wrote:
>> If the core actually calls it, we can implement detach_dev :) The
>> problem is that the core never calls detach_dev when default_domain is
>> present (affects any IOMMU driver that relies on default_domain,
>> including AMD), and even in case 4) the default_domain is present for
>> the parent device
> 
> Then can we change that core logic so detach_dev is invoked in all
> cases? yes there will be some changes in vendor drivers, but I expect
> this change trivial (especially considering the gain in IOMMU API
> simplicity side as described below).

Thinking more about this, there might be a way that doesn't require too
much rewriting of IOMMU drivers. When VFIO calls iommu_detach_group to
detach a vfio-pci device from its domain, it could do detach_dev(dev,
old_domain) followed by attach_dev(dev, default_domain) instead of only
attach_dev(dev, default_domain), so:

__iommu_attach_group(grp, unmanaged_domain)
  ops->attach_dev(dev, unmanaged_domain)
    -> IOMMU driver detaches from default_domain only if the dev isn't
       in auxiliary mode

__iommu_detach_group(grp, unmanaged_domain)
  if (ops->detach_dev)
      ops->detach_dev(dev, unmanaged_domain)
  ops->attach_dev(dev, default_domain)
    -> IOMMU driver ignores this if still attached to default_domain

It's not trivial: since half the IOMMU drivers seem to be using default
domain now, their detach_dev callback might have been dead code for a
while (I can't find a path where it still gets called), so re-enabling
it requires some attention. However, since most of them won't care about
aux domains, maybe we could just remove their detach_dev pointer.

The resulting logic of attach/detach_dev in IOMMU drivers that do use
aux domains still seems unnecessarily convoluted. It could as well be
done with separate attach_aux/detach_aux functions. If you want to keep
it that way though, I think the above could work for us and I'll try to
write an RFC.

Thanks,
Jean