drm/amdgpu: Handle duplicate BOs during process restore
In certain situations, some apps can import a BO multiple times
(through IPC for example). To restore such processes successfully,
we need to tell drm to ignore duplicate BOs.
While at it, also add additional logging to prevent silent failures
when process restore fails.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 14dc9d2..df58a6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2869,14 +2869,16 @@
mutex_lock(&process_info->lock);
- drm_exec_init(&exec, 0, 0);
+ drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
drm_exec_until_all_locked(&exec) {
list_for_each_entry(peer_vm, &process_info->vm_list_head,
vm_list_node) {
ret = amdgpu_vm_lock_pd(peer_vm, &exec, 2);
drm_exec_retry_on_contention(&exec);
- if (unlikely(ret))
+ if (unlikely(ret)) {
+ pr_err("Locking VM PD failed, ret: %d\n", ret);
goto ttm_reserve_fail;
+ }
}
/* Reserve all BOs and page tables/directory. Add all BOs from
@@ -2889,8 +2891,10 @@
gobj = &mem->bo->tbo.base;
ret = drm_exec_prepare_obj(&exec, gobj, 1);
drm_exec_retry_on_contention(&exec);
- if (unlikely(ret))
+ if (unlikely(ret)) {
+ pr_err("drm_exec_prepare_obj failed, ret: %d\n", ret);
goto ttm_reserve_fail;
+ }
}
}
@@ -2950,8 +2954,10 @@
* validations above would invalidate DMABuf imports again.
*/
ret = process_validate_vms(process_info, &exec.ticket);
- if (ret)
+ if (ret) {
+ pr_debug("Validating VMs failed, ret: %d\n", ret);
goto validate_map_fail;
+ }
/* Update mappings not managed by KFD */
list_for_each_entry(peer_vm, &process_info->vm_list_head,
