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>
This commit is contained in:
Mukul Joshi 2024-03-08 11:11:03 -05:00 committed by Alex Deucher
parent 2f14c0c8ca
commit 71b9d19220

View File

@ -2869,14 +2869,16 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
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 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
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 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
* 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,