[PATCH v3 0/3] dma-mapping: Patches for speeding up allocation

[Doug Anderson]

Hi,

On Thu, Jan 7, 2016 at 5:52 AM, Marek Szyprowski
<m.szyprowski at samsung.com> wrote:
> Hello,
>
>
> On 2016-01-06 20:36, Douglas Anderson wrote:
>>
>> This series of 3 patches will speed up memory allocation in dma-mapping
>> quite a bit.
>>
>> The first patch ("ARM: dma-mapping: Optimize allocation") is hopefully
>> not terribly controversial: it merely doesn't try as hard to allocate
>> big chunks once it gets the first failure.  Since it's unlikely that
>> further big chunks will help (they're not likely to be virtually aligned
>> anyway), this should give a big speedup with no real regression to speak
>> of.  Yes, things could be made better, but this seems like a sane start.
>>
>> The second patch ("common: DMA-mapping: add DMA_ATTR_SEQUENTIAL
>> attribute") models MADV_SEQUENTIAL as I understand it.  Hopefully folks
>> are happy with following that lead.  It does nothing by itself.
>>
>> The third patch ("ARM: dma-mapping: Use DMA_ATTR_SEQUENTIAL hint to
>> optimize allocation") simply applies the 2nd patch.  Again it's pretty
>> simple.  ...and again it does nothing by itself.
>>
>> Notably missing from this series is the fourth patch that adds teeth to
>> the second and third.  You can find that out of tree at
>> <https://chromium-review.googlesource.com/#/c/320498/>.  Unfortunately
>> the rk3288_vpu, which is what I'm working on, is out of tree.
>>
>> All testing was done on the chromeos kernel-3.14.  Sanity (compile /
>> boot) testing was done on a v4.4-rc6-based kernel.
>>
>> Also note that v2 of this series had an extra patch
>> <https://patchwork.kernel.org/patch/7888861/> that would attempt to sort
>> the allocation results to opportunistically get some extra alignment.  I
>> dropped that, but it could be re-introduced if there was interest.  I
>> found that it did give a little extra alignment sometimes, but maybe not
>> enough to justify the extra complexity.  It also was a bit half-baked
>> since it really should have tried harder to ensure alignment.
>>
>> Changes in v3:
>> - add DMA_ATTR_SEQUENTIAL attribute new for v3
>> - Use DMA_ATTR_SEQUENTIAL hint patch new for v3.
>>
>> Changes in v2:
>> - No longer just 1 page at a time, but gives up higher order quickly.
>> - Only tries important higher order allocations that might help us.
>>
>> Douglas Anderson (3):
>>    ARM: dma-mapping: Optimize allocation
>>    common: DMA-mapping: add DMA_ATTR_SEQUENTIAL attribute
>>    ARM: dma-mapping: Use DMA_ATTR_SEQUENTIAL hint to optimize allocation
>>
>>   Documentation/DMA-attributes.txt | 11 +++++++++++
>>   arch/arm/mm/dma-mapping.c        | 41
>> ++++++++++++++++++++++++++--------------
>>   include/linux/dma-attrs.h        |  1 +
>>   3 files changed, 39 insertions(+), 14 deletions(-)
>
>
> Acked-by: Marek Szyprowski <m.szyprowski at samsung.com>

In the ChromeOS review Tomasz suggested "DMA_ATTR_NOHUGEPAGE", so I'll
plan to resend the series changing the name.  I'll also fix a typo he
found in a comment in the last patch in the series.  Neither of these
is substantive, so I'll plan to keep your Ack unless you say not to.
Thanks!

At some point I'll also need to figure out how to get things landed.
I'd tend to submit the ARM bits to Russell's patch tracker, and I
guess I'll also submit the "common: DMA-mapping" patch there too...

-Doug