lkml.org 
[lkml]   [2019]   [Aug]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [Freedreno] [PATCH v3 0/2] iommu/arm-smmu: Split pagetable support
From
Date
On 16/08/2019 19:12, Rob Clark wrote:
> On Fri, Aug 16, 2019 at 9:58 AM Robin Murphy <robin.murphy@arm.com> wrote:
>>
>> Hi Jordan,
>>
>> On 15/08/2019 16:33, Jordan Crouse wrote:
>>> On Wed, Aug 07, 2019 at 04:21:38PM -0600, Jordan Crouse wrote:
>>>> (Sigh, resend. I freaked out my SMTP server)
>>>>
>>>> This is part of an ongoing evolution for enabling split pagetable support for
>>>> arm-smmu. Previous versions can be found [1].
>>>>
>>>> In the discussion for v2 Robin pointed out that this is a very Adreno specific
>>>> use case and that is exactly true. Not only do we want to configure and use a
>>>> pagetable in the TTBR1 space, we also want to configure the TTBR0 region but
>>>> not allocate a pagetable for it or touch it until the GPU hardware does so. As
>>>> much as I want it to be a generic concept it really isn't.
>>>>
>>>> This revision leans into that idea. Most of the same io-pgtable code is there
>>>> but now it is wrapped as an Adreno GPU specific format that is selected by the
>>>> compatible string in the arm-smmu device.
>>>>
>>>> Additionally, per Robin's suggestion we are skipping creating a TTBR0 pagetable
>>>> to save on wasted memory.
>>>>
>>>> This isn't as clean as I would like it to be but I think that this is a better
>>>> direction than trying to pretend that the generic format would work.
>>>>
>>>> I'm tempting fate by posting this and then taking some time off, but I wanted
>>>> to try to kick off a conversation or at least get some flames so I can try to
>>>> refine this again next week. Please take a look and give some advice on the
>>>> direction.
>>>
>>> Will, Robin -
>>>
>>> Modulo the impl changes from Robin, do you think that using a dedicated
>>> pagetable format is the right approach for supporting split pagetables for the
>>> Adreno GPU?
>>
>> How many different Adreno drivers would benefit from sharing it?
>
> Hypothetically everything back to a3xx, so I *could* see usefulness of
> this in qcom_iommu (or maybe even msm-iommu). OTOH maybe with
> "modularizing" arm-smmu we could re-combine qcom_iommu and arm-smmu.

Indeed, that's certainly something I'm planning to investigate as a
future refactoring step.

> And as a practical matter, I'm not sure if anyone will get around to
> backporting per-context pagetables as far back as a3xx.
>
> BR,
> -R
>
>> The more I come back to this, the more I'm convinced that io-pgtable
>> should focus on the heavy lifting of pagetable management - the code
>> that nobody wants to have to write at all, let alone more than once -
>> and any subtleties which aren't essential to that should be pushed back
>> into whichever callers actually care. Consider that already, literally
>> no caller actually uses an unmodified stage 1 TCR value as provided in
>> the io_pgtable_cfg.
>>
>> I feel it would be most productive to elaborate further in the form of
>> patches, so let me get right on that and try to bash something out
>> before I go home tonight...

...and now there's a rough WIP branch here:

http://linux-arm.org/git?p=linux-rm.git;a=shortlog;h=refs/heads/iommu/pgtable

I'll finish testing and polishing those patches at some point next week,
probably, but hopefully they're sufficiently illustrative for the moment.

Robin.

\
 
 \ /
  Last update: 2019-08-16 21:56    [W:0.055 / U:0.336 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site