[Intel-gfx] [PATCH 2/6] drm/i915/ttm: audit remaining bo->resource

[Matthew Auld]

On Mon, 30 Jan 2023 at 11:00, Andrzej Hajda <andrzej.hajda at intel.com> wrote:
>
> On 30.01.2023 11:12, Matthew Auld wrote:
> > In the near future TTM will have NULL bo->resource when the object is
> > initially created, plus after calling into pipeline-gutting. Try to
> > handle the remaining cases. In practice NULL bo->resource should be
> > taken to mean swapped-out or purged object.
> >
> > References: 516198d317d8 ("drm/i915: audit bo->resource usage v3")
> > Signed-off-by: Matthew Auld <matthew.auld at intel.com>
> > Cc: Christian König <ckoenig.leichtzumerken at gmail.com>
> > Cc: Nirmoy Das <nirmoy.das at intel.com>
> > ---
> >   drivers/gpu/drm/i915/gem/i915_gem_ttm.c      | 12 +++++++++---
> >   drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c |  7 ++++++-
> >   drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c   |  7 +++++--
> >   3 files changed, 20 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > index 4758f21c91e1..4ba1d7862ff9 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > @@ -472,7 +472,7 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags)
> >       struct ttm_placement place = {};
> >       int ret;
> >
> > -     if (!bo->ttm || bo->resource->mem_type != TTM_PL_SYSTEM)
> > +     if (!bo->ttm || (bo->resource && bo->resource->mem_type != TTM_PL_SYSTEM))
> >               return 0;
> >
> >       GEM_BUG_ON(!i915_tt->is_shmem);
> > @@ -511,7 +511,13 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
> >   {
> >       struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
> >
> > -     if (bo->resource && !i915_ttm_is_ghost_object(bo)) {
> > +     /*
> > +      * This gets called twice by ttm, so long as we have a ttm resource or
> > +      * ttm_tt then we can still safely call this. Due to pipeline-gutting,
> > +      * we maybe have NULL bo->resource, but in that case we should always
> > +      * have a ttm alive (like if the pages are swapped out).
> > +      */
> > +     if ((bo->resource || bo->ttm) && !i915_ttm_is_ghost_object(bo)) {
> >               __i915_gem_object_pages_fini(obj);
> >               i915_ttm_free_cached_io_rsgt(obj);
> >       }
> > @@ -1198,7 +1204,7 @@ static void i915_ttm_unmap_virtual(struct drm_i915_gem_object *obj)
> >
> >       assert_object_held_shared(obj);
> >
> > -     if (i915_ttm_cpu_maps_iomem(bo->resource)) {
> > +     if (bo->resource && i915_ttm_cpu_maps_iomem(bo->resource)) {
>
> I wonder if i915_ttm_cpu_maps_iomem couldn't handle null resource?

Yeah, seems reasonable to me.

>
>
> >               wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm);
> >
> >               /* userfault_count is protected by obj lock and rpm wakeref. */
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
> > index 76dd9e5e1a8b..72953ebadfd8 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
> > @@ -83,7 +83,8 @@ void i915_ttm_adjust_domains_after_move(struct drm_i915_gem_object *obj)
> >   {
> >       struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
> >
> > -     if (i915_ttm_cpu_maps_iomem(bo->resource) || bo->ttm->caching != ttm_cached) {
> > +     if ((bo->resource && i915_ttm_cpu_maps_iomem(bo->resource)) ||
> > +         bo->ttm->caching != ttm_cached) {
> >               obj->write_domain = I915_GEM_DOMAIN_WC;
> >               obj->read_domains = I915_GEM_DOMAIN_WC;
> >       } else {
> > @@ -711,6 +712,10 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
> >
> >       assert_object_held(dst);
> >       assert_object_held(src);
> > +
> > +     if (GEM_WARN_ON(!src_bo->resource || !dst_bo->resource))
> > +             return -EINVAL;
> > +
> >       i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
> >
> >       ret = dma_resv_reserve_fences(src_bo->base.resv, 1);
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
> > index 7e67742bc65e..be44e7eed892 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
> > @@ -53,7 +53,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
> >       unsigned int flags;
> >       int err = 0;
> >
> > -     if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup)
> > +     if (!bo->resource || bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup)
>
> !i915_ttm_cpu_maps_iomem ?
>
> >               return 0;
> >
> >       if (pm_apply->allow_gpu && i915_gem_object_evictable(obj))
> > @@ -187,7 +187,10 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply,
> >               return err;
> >
> >       /* Content may have been swapped. */
> > -     err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx);
> > +     if (!backup_bo->resource)
> > +             err = ttm_bo_validate(backup_bo, i915_ttm_sys_placement(), &ctx);
> > +     if (!err)
> > +             err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx);
>
> Reviewed-by: Andrzej Hajda <andrzej.hajda at intel.com>
>
> Regards
> Andrzej
>
>
> >       if (!err) {
> >               err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu,
> >                                           false);
>