Re: AGP and PAT (induced?) problem (on AMD family 6)

[Venki Pallipadi <venkatesh.pallipadi@intel.com>]

On Wed, Aug 20, 2008 at 07:27:22AM -0700, Rene Herman wrote:
> On 20-08-08 12:50, Rene Herman wrote:
> 
> > On 20-08-08 12:04, Ingo Molnar wrote:
> >
> >> * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote:
> >>
> >>>> I'd really like a reply from the AGP or PAT side right about now.
> >>> Hmm. Looks like there are more than 16000 entries in the PAT list!
> >>
> >> hm, btw., why is that?
> >
> > Because 64M of AGP memory divided by 4K pages is 16K. That is, the
> > underlying problem seems to be AGP drivers using order 0 allocations.
> > I'm looking.
> >
> > Do note also that this means that Venki's change would not constitite a
> > correct/final fix. Sure, caching the last entry speeds up traversing a
> > 16K entry list but the issue is that there shouldn't be a 16K entry
> > list. Through AGP, or maybe even by coalescing entries in the PAT list
> > if that's at all possible (I guess it's not really).
> >
> > Even if such a more fundamental fix isn't (easily) available, the PAT
> > code already comments that the list, which is sorted by ->start value,
> > is expected to be short, and should be turned into an rbtree if it isn't
> > which might be slightly less of a bandaid.
> >
> > Dave Airlie (as the MAINTAINERS entry) can't be arsed to answer email it
> > seems so I've added Dave Jones for a possible comment from the AGP side.
> > If I'm reading this right upto now, still many AGP driver (among which
> > my amd-k7-agp) are affected.
> 
> This was based on a wrong reading; I was looking at the GATT allocation.
> 
> I'm giving up looking until someone can tell me whether or not those 16K
> entries are expected though. I have just one AGP card in a PAT capable
> machine.
> 

OK. I have reproduced this list size issue locally and this order 1
allocation and set_memory_uc on that allocation is actually coming from
agp_allocate_memory() -> agp_generic_alloc_page() -> map_page_into_agp()
agp_allocate_memory breaks higher order page requests into order 1 allocs.

On my system I see multiple agp_allocate_memory requests for nrpages
8841, 1020, 16, 2160, 2160, 8192. Together they end up resulting in
more than 22K entries in PAT pages.

Thanks,
Venki