[Intel-gfx] [PATCH 5/7] drm/i915/gem/ttm: Respect the objection region in placement_from_obj

[Matthew Auld]

On Fri, 16 Jul 2021 at 15:10, Jason Ekstrand <jason at jlekstrand.net> wrote:
>
> On Fri, Jul 16, 2021 at 8:54 AM Matthew Auld
> <matthew.william.auld at gmail.com> wrote:
> >
> > On Thu, 15 Jul 2021 at 23:39, Jason Ekstrand <jason at jlekstrand.net> wrote:
> > >
> > > Whenever we had a user object (n_placements > 0), we were ignoring
> > > obj->mm.region and always putting obj->placements[0] as the requested
> > > region.  For LMEM+SMEM objects, this was causing them to get shoved into
> > > LMEM on every i915_ttm_get_pages() even when SMEM was requested by, say,
> > > i915_gem_object_migrate().
> >
> > i915_ttm_migrate calls i915_ttm_place_from_region() directly with the
> > requested region, so there shouldn't be an issue with migration right?
> > Do you have some more details?
>
> With i915_ttm_migrate directly, no.  But, in the last patch in the
> series, we're trying to migrate LMEM+SMEM buffers into SMEM on
> attach() and pin it there.  This blows up in a very unexpected (IMO)
> way.  The flow goes something like this:
>
>  - Client attempts a dma-buf import from another device
>  - In attach() we call i915_gem_object_migrate() which calls
> i915_ttm_migrate() which migrates as requested.
>  - Once the migration is complete, we call i915_gem_object_pin_pages()
> which calls i915_ttm_get_pages() which depends on
> i915_ttm_placement_from_obj() and so migrates it right back to LMEM.

The mm.pages must be NULL here, otherwise it would just increment the
pages_pin_count?

>
> Maybe the problem here is actually that our TTM code isn't respecting
> obj->mm.pages_pin_count?

I think if the resource is moved, we always nuke the mm.pages after
being notified of the move. Also TTM is also not allowed to move
pinned buffers.

I guess if we are evicted/swapped, so assuming we are not holding the
object lock, and it's not pinned, the future call to get_pages() will
see mm.pages = NULL, even though the ttm_resource is still there, and
because we prioritise the placements[0], instead of mm.region we end
up moving it for no good reason. But in your case you are holding the
lock, or it's pinned? Also is this just with the selftest, or
something real?

>
> In case you can't tell, I really have no clue what I'm doing here.
> I'm really stumbling around in the dark finding things that make my
> bug go away.  I'm happy for the feedback.
>
> --Jason
>
> >
> > >
> > > Signed-off-by: Jason Ekstrand <jason at jlekstrand.net>
> > > Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> > > Cc: Matthew Auld <matthew.auld at intel.com>
> > > Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
> > > ---
> > >  drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 3 +--
> > >  1 file changed, 1 insertion(+), 2 deletions(-)
> > >
> > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > index d30f274c329c7..5985e994d56cf 100644
> > > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > @@ -150,8 +150,7 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
> > >         unsigned int i;
> > >
> > >         placement->num_placement = 1;
> > > -       i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
> > > -                                  obj->mm.region, requested, flags);
> > > +       i915_ttm_place_from_region(obj->mm.region, requested, flags);
> > >
> > >         /* Cache this on object? */
> > >         placement->num_busy_placement = num_allowed;
> > > --
> > > 2.31.1
> > >