Merge tag 'drm-amdkfd-next-2018-07-28' of git://people.freedesktop.org/~gabbayo/linux into drm-next

This is amdkfd pull for 4.19. The major changes are:

- Add Raven support. Raven refers to Ryzen APUs with integrated GFXv9 GPU.
- Integrate GPU reset support

In addition, there are a couple of small fixes and improvements, such as:

- Better handling and reporting to user of VM faults
- Fix race upon context restore
- Allow the user to use specific Compute Units
- Basic power management

Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180728122306.GA5235@ogabbay-vm

1 files changed, 6 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ec53d8f96d06..13acef526c5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3307,6 +3307,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
         atomic_inc(&adev->gpu_reset_counter);
         adev->in_gpu_reset = 1;
 
+        /* Block kfd */
+        amdgpu_amdkfd_pre_reset(adev);
+
         /* block TTM */
         resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
@@ -3322,7 +3325,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
                 if (job && job->base.sched == &ring->sched)
                         continue;
 
-                drm_sched_hw_job_reset(&ring->sched, &job->base);
+                drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
 
                 /* after all hw jobs are reset, hw fence is meaningless, so force_completion */
                 amdgpu_fence_driver_force_completion(ring);
@@ -3363,6 +3366,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
                 dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
         }
 
+        /*unlock kfd */
+        amdgpu_amdkfd_post_reset(adev);
         amdgpu_vf_error_trans_all(adev);
         adev->in_gpu_reset = 0;
         mutex_unlock(&adev->lock_reset);