linux-kernel - Re: [PATCH 3/6] iommu/vt-d: Don't force 32bit devices to uses DMA domain

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: <20200307142144.GB26190@lst.de>
Date:   Sat, 7 Mar 2020 15:21:44 +0100
From:   Christoph Hellwig <hch@....de>
To:     Lu Baolu <baolu.lu@...ux.intel.com>
Cc:     Joerg Roedel <joro@...tes.org>, ashok.raj@...el.com,
        jacob.jun.pan@...ux.intel.com, kevin.tian@...el.com,
        iommu@...ts.linux-foundation.org, linux-kernel@...r.kernel.org,
        Daniel Drake <drake@...lessm.com>,
        Derrick Jonathan <jonathan.derrick@...el.com>,
        Jerry Snitselaar <jsnitsel@...hat.com>,
        Robin Murphy <robin.murphy@....com>,
        Christoph Hellwig <hch@....de>
Subject: Re: [PATCH 3/6] iommu/vt-d: Don't force 32bit devices to uses DMA
 domain

On Sat, Mar 07, 2020 at 02:20:11PM +0800, Lu Baolu wrote:
> Currently, if a 32bit device initially uses an identity domain,
> Intel IOMMU driver will convert it forcibly to a DMA one if its
> address capability is not enough for the whole system memory.
> The motivation was to overcome the overhead caused by possible
> bounced buffer.
> 
> Unfortunately, this improvement has led to many problems. For
> example, some 32bit devices are required to use an identity
> domain, forcing them to use DMA domain will cause the device
> not to work anymore. On the other hand, the VMD sub-devices
> share a domain but each sub-device might have different address
> capability. Forcing a VMD sub-device to use DMA domain blindly
> will impact the operation of other sub-devices without any
> notification. Further more, PCI aliased devices (PCI bridge
> and all devices beneath it, VMD devices and various devices
> quirked with pci_add_dma_alias()) must use the same domain.
> Forcing one device to switch to DMA domain during runtime
> will cause in-fligh DMAs for other devices to abort or target
> to other memory which might cause undefind system behavior.

I still don't like the idea to enforce either a strict dynamic
IOMMU mapping or an identify mapping mode.

Can we add a new AUTO domain which will allow using the identity
mapping when available?  That somewhat matches the existing x86
default, and also what powerpc does.  I have a series to lift
that bypass mode into the core dma-mapping code that I need
to repost, which I think would be suitable for intel-iommu as well.