lkml.org 
[lkml]   [2020]   [Nov]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v5 05/15] mm/frame-vector: Use FOLL_LONGTERM
On Fri, Nov 6, 2020 at 11:01 AM Daniel Vetter <daniel@ffwll.ch> wrote:
>
> On Fri, Nov 6, 2020 at 5:08 AM John Hubbard <jhubbard@nvidia.com> wrote:
> >
> > On 11/5/20 4:49 AM, Jason Gunthorpe wrote:
> > > On Thu, Nov 05, 2020 at 10:25:24AM +0100, Daniel Vetter wrote:
> > >>> /*
> > >>> * If we can't determine whether or not a pte is special, then fail immediately
> > >>> * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
> > >>> * to be special.
> > >>> *
> > >>> * For a futex to be placed on a THP tail page, get_futex_key requires a
> > >>> * get_user_pages_fast_only implementation that can pin pages. Thus it's still
> > >>> * useful to have gup_huge_pmd even if we can't operate on ptes.
> > >>> */
> > >>
> > >> We support hugepage faults in gpu drivers since recently, and I'm not
> > >> seeing a pud_mkhugespecial anywhere. So not sure this works, but probably
> > >> just me missing something again.
> > >
> > > It means ioremap can't create an IO page PUD, it has to be broken up.
> > >
> > > Does ioremap even create anything larger than PTEs?
>
> gpu drivers also tend to use vmf_insert_pfn* directly, so we can do
> on-demand paging and move buffers around. From what I glanced for
> lowest level we to the pte_mkspecial correctly (I think I convinced
> myself that vm_insert_pfn does that), but for pud/pmd levels it seems
> just yolo.

So I dug around a bit more and ttm sets PFN_DEV | PFN_MAP to get past
the various pft_t_devmap checks (see e.g. vmf_insert_pfn_pmd_prot()).
x86-64 has ARCH_HAS_PTE_DEVMAP, and gup.c seems to handle these
specially, but frankly I got totally lost in what this does.

The comment above the pfn_t_devmap check makes me wonder whether doing
this is correct or not.

Also adding Thomas Hellstrom, who implemented the huge map support in ttm.
-Daniel

> remap_pfn_range seems to indeed split down to pte level always.
>
> > From my reading, yes. See ioremap_try_huge_pmd().
>
> The ioremap here shouldn't matter, since this is for kernel-internal
> mappings. So that's all fine I think.
> -Daniel
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch



--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch

\
 
 \ /
  Last update: 2020-11-06 11:29    [W:0.170 / U:0.104 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site