linux-kernel - Re: [REGRESSION] Recent swiotlb DMA_FROM

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 for Android: free password hash cracker in your pocket

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

Message-ID: <CAHk-=whpKDePfUoKmvJhSNbWcHFY5e7Uq5qEypD=R14+66DNvQ@mail.gmail.com>
Date:   Fri, 25 Mar 2022 12:21:33 -0700
From:   Linus Torvalds <torvalds@...ux-foundation.org>
To:     Robin Murphy <robin.murphy@....com>
Cc:     Maxime Bizon <mbizon@...ebox.fr>,
        Toke Høiland-Jørgensen <toke@...e.dk>,
        Christoph Hellwig <hch@....de>,
        Oleksandr Natalenko <oleksandr@...alenko.name>,
        Halil Pasic <pasic@...ux.ibm.com>,
        Marek Szyprowski <m.szyprowski@...sung.com>,
        Kalle Valo <kvalo@...nel.org>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        Olha Cherevyk <olha.cherevyk@...il.com>,
        iommu <iommu@...ts.linux-foundation.org>,
        linux-wireless <linux-wireless@...r.kernel.org>,
        Netdev <netdev@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable <stable@...r.kernel.org>
Subject: Re: [REGRESSION] Recent swiotlb DMA_FROM_DEVICE fixes break
 ath9k-based AP

On Fri, Mar 25, 2022 at 12:14 PM Robin Murphy <robin.murphy@....com> wrote:
>
> Note "between the DMA transfers", and not "during the DMA transfers".
> The fundamental assumption of the streaming API is that only one thing
> is ever accessing the mapping at any given time, which is what the whole
> notion of ownership is about.

Well, but that ignores reality.

Any documentation that ignores the "CPU will want to see the
intermediate state" is by definition garbage, because that is clearly
a simple fact.

We don't write documentation for fantasy.

            Linus