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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <87r16r834b.fsf@toke.dk>
Date:   Thu, 24 Mar 2022 22:14:28 +0100
From:   Toke Høiland-Jørgensen <toke@...e.dk>
To:     Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     Robin Murphy <robin.murphy@....com>,
        Christoph Hellwig <hch@....de>,
        Maxime Bizon <mbizon@...ebox.fr>,
        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

Linus Torvalds <torvalds@...ux-foundation.org> writes:

> On Thu, Mar 24, 2022 at 10:07 AM Toke Høiland-Jørgensen <toke@...e.dk> wrote:
>>
>> Right, but is that sync_for_device call really needed?
>
> Well, imagine that you have a non-cache-coherent DMA (not bounce
> buffers - just bad hardware)...
>
> So the driver first does that dma_sync_single_for_cpu() for the CPU
> see the current state (for the non-cache-coherent case it would just
> invalidate caches).
>
> The driver then examines the command buffer state, sees that it's
> still in progress, and does that return -EINPROGRESS.
>
> It's actually very natural in that situation to flush the caches from
> the CPU side again. And so dma_sync_single_for_device() is a fairly
> reasonable thing to do in that situation.
>
> But it doesn't seem *required*, no. The CPU caches only have a copy of
> the data in them, no writeback needed (and writeback wouldn't work
> since DMA from the device may be in progress).
>
> So I don't think the dma_sync_single_for_device() is *wrong* per se,
> because the CPU didn't actually do any modifications.
>
> But yes, I think it's unnecessary - because any later CPU accesses
> would need that dma_sync_single_for_cpu() anyway, which should
> invalidate any stale caches.

OK, the above was basically how I understood it. Thank you for
confirming!

> And it clearly doesn't work in a bounce-buffer situation, but honestly
> I don't think a "CPU modified buffers concurrently with DMA" can
> *ever* work in that situation, so I think it's wrong for a bounce
> buffer model to ever do anything in the dma_sync_single_for_device()
> situation.

Right.

> Does removing that dma_sync_single_for_device() actually fix the
> problem for the ath driver?

I am hoping Oleksandr can help answer that since my own ath9k hardware
is currently on strike :(

-Toke