linux-kernel - Re: [PATCH] swiotlb: ensure io_tlb_default

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] [day] [month] [year] [list]

Message-ID: <20220711134000.GA18865@lst.de>
Date:   Mon, 11 Jul 2022 15:40:00 +0200
From:   Christoph Hellwig <hch@....de>
To:     Ben Dooks <ben.dooks@...ive.com>
Cc:     Robin Murphy <robin.murphy@....com>,
        Christoph Hellwig <hch@....de>, linux-kernel@...r.kernel.org,
        iommu@...ts.linux.dev, iommu@...ts.linux-foundation.org,
        Sudip Mukherjee <sudip.mukherjee@...ive.com>,
        Jude Onyenegecha <jude.onyenegecha@...ive.com>,
        Marek Szyprowski <m.szyprowski@...sung.com>
Subject: Re: [PATCH] swiotlb: ensure io_tlb_default_mem spinlock always
 initialised

On Mon, Jul 11, 2022 at 01:54:11PM +0100, Ben Dooks wrote:
> I need to go back and check through what we did to get some that worked
> for us, and then come back and try and make some idea of how that is
> best done with upstream kernel.
>
> It might be possible for the PCIe controller to do some sort of very
> simple IOMMU for the case where we might have somehow an PCI device
> added to the system, but that is a very rare use-case I expect and
> if someone does it they can do the effort of updating the PCIe code
> and everything else that goes with it.

Unfortunately there also are plenty of PCIe devices with addressing
limitation even if the PCIe spec explicitly forbits that.  40, 44 or
48 bit limitations seems to be more common than 32-bits, though.