drm/amdgpu: fix VM faults caused by vm_grab_id() v4

The owner must be per ring as long as we don't
support sharing VMIDs per process. Also move the
assigned VMID and page directory address into the
IB structure.

v3: assign the VMID to all IBs, not just the first one.
v4: use correct pointer for owner

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 11 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index f29bbb96a881..90e52f7e17a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -105,16 +105,23 @@ static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 
         struct fence *fence = amdgpu_sync_get_fence(&job->sync);
 
-        if (fence == NULL && vm && !job->ibs->grabbed_vmid) {
+        if (fence == NULL && vm && !job->ibs->vm_id) {
                 struct amdgpu_ring *ring = job->ring;
+                unsigned i, vm_id;
+                uint64_t vm_pd_addr;
                 int r;
 
                 r = amdgpu_vm_grab_id(vm, ring, &job->sync,
-                                      &job->base.s_fence->base);
+                                      &job->base.s_fence->base,
+                                      &vm_id, &vm_pd_addr);
                 if (r)
                         DRM_ERROR("Error getting VM ID (%d)\n", r);
-                else
-                        job->ibs->grabbed_vmid = true;
+                else {
+                        for (i = 0; i < job->num_ibs; ++i) {
+                                job->ibs[i].vm_id = vm_id;
+                                job->ibs[i].vm_pd_addr = vm_pd_addr;
+                        }
+                }
 
                 fence = amdgpu_sync_get_fence(&job->sync);
         }