linux-kernel - Re: ehci-pci breakage with dma-mapping changes in 5.4-rc2

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: <20191008125008.GA4829@lst.de>
Date:   Tue, 8 Oct 2019 14:50:08 +0200
From:   Christoph Hellwig <hch@....de>
To:     Arvind Sankar <nivedita@...m.mit.edu>
Cc:     Christoph Hellwig <hch@....de>,
        Christoph Hellwig <hch@...radead.org>,
        linux-kernel@...r.kernel.org
Subject: Re: ehci-pci breakage with dma-mapping changes in 5.4-rc2

On Tue, Oct 08, 2019 at 07:51:03AM -0400, Arvind Sankar wrote:
> What I mean is, do there exist devices (which would necessarily support
> 64-bit DMA) that want to DMA using bigger than 4Gb buffers. Eg a GPU
> accelerator card with 16Gb of RAM on-board that wants to map 6Gb for DMA
> in one go, or 5 accelerator cards that are in one IOMMU domain and want
> to simultaneously map 1Gb each.

If you allocate more than 32-bits worth of address space the IOMMU
address space allocator will dip into 64-bit values if the device
dma mask supports that.