Re: [PATCH v2 3/4] drm/i915/ttm: Calculate the object placement at get_pages time

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Fri, 11 Jun 2021 at 15:55, Thomas Hellström
<thomas.hellstrom@xxxxxxxxxxxxxxx> wrote:
>
> Instead of relying on a static placement, calculate at get_pages() time.
> This should work for LMEM regions and system for now. For stolen we need
> to take preallocated range into account. That well be added later.

That will be

>
> Signed-off-by: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
> ---
> v2:
> - Fixed a style issue (Reported by Matthew Auld)
> ---
>  drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 92 ++++++++++++++++++-------
>  drivers/gpu/drm/i915/intel_region_ttm.c |  8 ++-
>  drivers/gpu/drm/i915/intel_region_ttm.h |  2 +
>  3 files changed, 75 insertions(+), 27 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> index 45ef1d101937..fd3d11728229 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> @@ -24,6 +24,11 @@
>  #define I915_TTM_PRIO_NO_PAGES  1
>  #define I915_TTM_PRIO_HAS_PAGES 2
>
> +/*
> + * Size of struct ttm_place vector in on-stack struct ttm_placement allocs
> + */
> +#define I915_TTM_MAX_PLACEMENTS 10

I915_TTM_MAX_PLACEMENTS INTEL_REGION_UNKNOWN ?

> +
>  /**
>   * struct i915_ttm_tt - TTM page vector with additional private information
>   * @ttm: The base TTM page vector.
> @@ -42,32 +47,18 @@ struct i915_ttm_tt {
>         struct sg_table *cached_st;
>  };
>
> -static const struct ttm_place lmem0_sys_placement_flags[] = {
> -       {
> -               .fpfn = 0,
> -               .lpfn = 0,
> -               .mem_type = I915_PL_LMEM0,
> -               .flags = 0,
> -       }, {
> -               .fpfn = 0,
> -               .lpfn = 0,
> -               .mem_type = I915_PL_SYSTEM,
> -               .flags = 0,
> -       }
> -};
> -
> -static struct ttm_placement i915_lmem0_placement = {
> -       .num_placement = 1,
> -       .placement = &lmem0_sys_placement_flags[0],
> -       .num_busy_placement = 1,
> -       .busy_placement = &lmem0_sys_placement_flags[0],
> +static const struct ttm_place sys_placement_flags = {
> +       .fpfn = 0,
> +       .lpfn = 0,
> +       .mem_type = I915_PL_SYSTEM,
> +       .flags = 0,
>  };
>
>  static struct ttm_placement i915_sys_placement = {
>         .num_placement = 1,
> -       .placement = &lmem0_sys_placement_flags[1],
> +       .placement = &sys_placement_flags,
>         .num_busy_placement = 1,
> -       .busy_placement = &lmem0_sys_placement_flags[1],
> +       .busy_placement = &sys_placement_flags,
>  };
>
>  static bool gpu_binds_iomem(struct ttm_resource *mem)
> @@ -83,6 +74,55 @@ static bool cpu_maps_iomem(struct ttm_resource *mem)
>
>  static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj);
>
> +static enum ttm_caching
> +i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
> +{
> +       /*
> +        * Objects only allowed in system get cached cpu-mappings.
> +        * Other objects get WC mapping for now. Even if in system.
> +        */
> +       if (obj->mm.region->type == INTEL_MEMORY_SYSTEM &&
> +           obj->mm.n_placements <= 1)
> +               return ttm_cached;
> +
> +       return ttm_write_combined;
> +}
> +
> +static void
> +i915_ttm_place_from_region(const struct intel_memory_region *mr,
> +                          struct ttm_place *place)
> +{
> +       memset(place, 0, sizeof(*place));
> +       place->mem_type = intel_region_to_ttm_type(mr);
> +}
> +
> +static void
> +i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
> +                           struct ttm_place *requested,
> +                           struct ttm_place *busy,
> +                           struct ttm_placement *placement)
> +{
> +       unsigned int num_allowed = obj->mm.n_placements;
> +       unsigned int i;
> +
> +       placement->num_placement = 1;
> +       i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
> +                                  obj->mm.region, requested);
> +
> +       /* Cache this on object? */
> +       placement->num_busy_placement = num_allowed;
> +       for (i = 0; i < placement->num_busy_placement; ++i)
> +               i915_ttm_place_from_region(obj->mm.placements[i], busy + i);
> +
> +       if (num_allowed == 0) {
> +               *busy = *requested;
> +               placement->num_busy_placement = 1;
> +       }
> +
> +       placement->placement = requested;
> +       placement->busy_placement = busy;
> +}
> +
>  static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
>                                          uint32_t page_flags)
>  {
> @@ -100,7 +140,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
>             man->use_tt)
>                 page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
>
> -       ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, ttm_write_combined);
> +       ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
> +                         i915_ttm_select_tt_caching(obj));
>         if (ret) {
>                 kfree(i915_tt);
>                 return NULL;
> @@ -465,10 +506,13 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
>                 .no_wait_gpu = false,
>         };
>         struct sg_table *st;
> +       struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
> +       struct ttm_placement placement;
>         int ret;

GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS)?

Reviewed-by: Matthew Auld <matthew.auld@xxxxxxxxx>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [AMD Graphics]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux