Re: [PATCH 0/3] More ARM DMA ops cleanup

[Robin Murphy]

On 2022-08-27 13:24, Yongqin Liu wrote:
> Hi, Robin, Christoph
>
> With the changes landed in the mainline kernel,
> one problem is exposed with our out of tree pvr module.
> Like the source here[1], arm_dma_ops.sync_single_for_cpu is called in
> the format like the following:
>      arm_dma_ops.sync_single_for_cpu(NULL, pStart, pEnd - pStart,
> DMA_FROM_DEVICE);
>
> Not sure if you could give some suggestions on what I should do next
> to make the pvr module work again.

Wow, that driver reinvents so many standard APIs for no apparent reason 
it's not even funny.

Anyway, from a brief look it seemingly already knows how to call the DMA 
API semi-correctly, so WTF that's doing behind an #ifdef, who knows? 
However it's still so completely wrong in general - fundamentally broken 
AArch64 set/way cache maintenance!? - that it looks largely beyond help. 
"Throw CONFIG_DMA_API_DEBUG at it and cry" is about the extent of 
support I'm prepared to provide for that mess.

Thanks,
Robin.

> Thanks in advance!
>
> [1]: https://android-git.linaro.org/kernel/omap-modules.git/tree/pvr/services4/srvkm/env/linux/osfunc.c?h=android-mainline#n4615
>
> Thanks,
> Yongqin Liu
>
> On Thu, 21 Apr 2022 at 22:35, Robin Murphy <robin.murphy@xxxxxxx> wrote:
> > On 2022-04-21 15:13, Christoph Hellwig wrote:
> > > On Thu, Apr 21, 2022 at 12:36:56PM +0100, Robin Murphy wrote:
> > > > Hi all,
> > > >
> > > > Thanks to Christoph's latest series, I'm reminded that, if we're going
> > > > to give the ARM DMA ops some cleanup this cycle, it's as good a time as
> > > > any to dust off these old patches and add them on top as well. I've
> > > > based these on the arm-dma-direct branch which I assume matches the
> > > > patches posted at [1].
> > >
> > > All these do look sensible to me.  But weren't you working on replacing
> > > the ARM iommu dma_ops with dma-іommu anyway?
> >
> > Yes, that's somewhat entangled with the IOMMU bus ops stuff, so I'll
> > probably get to the point of having to revisit it in a couple of months
> > or so. These patches are off the bottom of that stack from my first
> > attempt, where the aim was to make the current ops the same shape first
> > so that the switch is then easier to reason about (particularly in terms
> > of sounding out any issues with the hooking up of dev->dma_coherent,
> > although your series will now be taking most of the load off there).
> >
> > Cheers,
> > Robin.