drm/amdgpu: allocate gart memory when it's required (v3)

Instead of calling gart address space on every bo pin,
allocates it on demand

v2: fix error handling
v3: drop the change on amdgpu_amdkfd_gpuvm.c, not needed.

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index a80407cf099b..6748cd7fc129 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -194,6 +194,12 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
                 goto unreserve;
         }
 
+        r = amdgpu_ttm_alloc_gart(&new_abo->tbo);
+        if (unlikely(r != 0)) {
+                DRM_ERROR("%p bind failed\n", new_abo);
+                goto unpin;
+        }
+
         r = reservation_object_get_fences_rcu(new_abo->tbo.resv, &work->excl,
                                               &work->shared_count,
                                               &work->shared);