linux-kernel - Re: [PATCH v3 15/16] iommu: introduce page response function

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

Message-ID: <af3c1d0f-e325-9507-0d59-7faadc79d66b@arm.com>
Date:   Fri, 8 Dec 2017 13:51:48 +0000
From:   Jean-Philippe Brucker <jean-philippe.brucker@....com>
To:     Alex Williamson <alex.williamson@...hat.com>
Cc:     Jacob Pan <jacob.jun.pan@...ux.intel.com>,
        "iommu@...ts.linux-foundation.org" <iommu@...ts.linux-foundation.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Joerg Roedel <joro@...tes.org>,
        David Woodhouse <dwmw2@...radead.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Rafael Wysocki <rafael.j.wysocki@...el.com>,
        Lan Tianyu <tianyu.lan@...el.com>,
        Jean Delvare <khali@...ux-fr.org>,
        Will Deacon <Will.Deacon@....com>,
        "Kumar, Sanjay K" <sanjay.k.kumar@...el.com>
Subject: Re: [PATCH v3 15/16] iommu: introduce page response function

On 07/12/17 21:56, Alex Williamson wrote:
[...]
>> Seems like VFIO should enforce this quota, since the IOMMU layer doesn't
>> know which device is assigned to which VM. If it's the IOMMU that enforces
>> quotas per device and a VM has 15 devices assigned, then the guest can
>> still DoS the IOMMU.
> 
> VFIO also doesn't know about VMs.  We know that devices attached to the
> same container are probably used by the same user, but once we add
> viommu, each device(group) uses its own container and we have no idea
> they're associated.  So, no to VM based accounting, and it seems like
> an IOMMU problem, X number of outstanding requests per device.  Thanks,

Ok. It's not clear anyway how the architecture and implementations expect
us to virtualize stall, I'll try to clarify it.

Thanks,
Jean