[Intel-gfx] [PATCH] drm/i915: Remove redundant i915_request_await_object in blit clears

[Chris Wilson]

Quoting Tvrtko Ursulin (2020-06-15 15:09:28)
> From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> 
> One i915_request_await_object is enough and we keep the one under the
> object lock so it is final.
> 
> At the same time move async clflushing setup under the same locked
> section and consolidate common code into a helper function.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> Cc: Matthew Auld <matthew.auld at intel.com>
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Michael J. Ruhl <michael.j.ruhl at intel.com>
> ---
>  .../gpu/drm/i915/gem/i915_gem_object_blt.c    | 35 +++++++------------
>  1 file changed, 13 insertions(+), 22 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
> index f457d7130491..7d8b396e265a 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
> @@ -126,6 +126,17 @@ void intel_emit_vma_release(struct intel_context *ce, struct i915_vma *vma)
>         intel_engine_pm_put(ce->engine);
>  }
>  
> +static int
> +move_obj_to_gpu(struct drm_i915_gem_object *obj,
> +               struct i915_request *rq,
> +               bool write)
> +{
> +       if (obj->cache_dirty & ~obj->cache_coherent)
> +               i915_gem_clflush_object(obj, 0);
> +
> +       return i915_request_await_object(rq, obj, write);
> +}
> +
>  int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
>                              struct intel_context *ce,
>                              u32 value)
> @@ -143,12 +154,6 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
>         if (unlikely(err))
>                 return err;
>  
> -       if (obj->cache_dirty & ~obj->cache_coherent) {
> -               i915_gem_object_lock(obj);
> -               i915_gem_clflush_object(obj, 0);
> -               i915_gem_object_unlock(obj);
> -       }
> -
>         batch = intel_emit_vma_fill_blt(ce, vma, value);
>         if (IS_ERR(batch)) {
>                 err = PTR_ERR(batch);
> @@ -165,10 +170,6 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
>         if (unlikely(err))
>                 goto out_request;
>  
> -       err = i915_request_await_object(rq, obj, true);
> -       if (unlikely(err))
> -               goto out_request;
> -
>         if (ce->engine->emit_init_breadcrumb) {
>                 err = ce->engine->emit_init_breadcrumb(rq);
>                 if (unlikely(err))
> @@ -176,7 +177,7 @@ int i915_gem_object_fill_blt(struct drm_i915_gem_object *obj,
>         }
>  
>         i915_vma_lock(vma);
> -       err = i915_request_await_object(rq, vma->obj, true);
> +       err = move_obj_to_gpu(vma->obj, rq, true);
>         if (err == 0)
>                 err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
>         i915_vma_unlock(vma);

Ah, but here it's also the wrong side of init_breadcrumb.
-Chris