Re: [PATCH v4 5/7] dma-buf: system_heap: Allocate higher order pages if available

[John Stultz]

On Thu, Oct 29, 2020 at 12:02 AM Hillf Danton <hdanton@xxxxxxxx> wrote:
>
> On Thu, 29 Oct 2020 00:16:22 +0000 John Stultz wrote:
> >
> > +#define HIGH_ORDER_GFP  (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \
> > +                             | __GFP_NORETRY) & ~__GFP_RECLAIM) \
> > +                             | __GFP_COMP)
> > +#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO | __GFP_COMP)
> > +static gfp_t order_flags[] = {HIGH_ORDER_GFP, LOW_ORDER_GFP, LOW_ORDER_GFP};
> > +static const unsigned int orders[] = {8, 4, 0};
> > +#define NUM_ORDERS ARRAY_SIZE(orders)
>
> A two-line comment helps much understand the ORDERs above if it specifies the
> reasons behind the detour to HPAGE_PMD_ORDER and PAGE_ALLOC_COSTLY_ORDER.

Thanks so much for the review and feedback!

So yes, this was pulled from ION's system heap:
  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/staging/android/ion/ion_system_heap.c#n20

But adding __GFP_COMP as that's added by ION in the pagepool code I
didn't include:
  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/staging/android/ion/ion_page_pool.c#n146

I unfortunately don't have a lot of detail on the exact rationale
(other than what I can pull from the commit log), I suspect it has to
do experiential knowledge of the majority of graphics buffers being
small multiples of 1M or 64K.

But I do agree some rationale in a comment would be helpful, and will
try to add that.

As for your comment on HPAGE_PMD_ORDER (9 on arm64/arm) and
PAGE_ALLOC_COSTLY_ORDER(3), I'm not totally sure I understand your
question? Are you suggesting those values would be more natural orders
to choose from?

Thanks again!
-john