drm/amdgpu: Auto-validate DMABuf imports in compute VMs

DMABuf imports in compute VMs are not wrapped in a kgd_mem object on the
process_info->kfd_bo_list. There is no explicit KFD API call to validate
them or add eviction fences to them.

This patch automatically validates and fences dymanic DMABuf imports when
they are added to a compute VM. Revalidation after evictions is handled
in the VM code.

v2:
* Renamed amdgpu_vm_validate_evicted_bos to amdgpu_vm_validate
* Eliminated evicted_user state, use evicted state for VM BOs and user BOs
* Fixed and simplified amdgpu_vm_fence_imports, depends on reserved BOs
* Moved dma_resv_reserve_fences for amdgpu_vm_fence_imports into
  amdgpu_vm_validate, outside the vm->status_lock
* Added dummy version of amdgpu_amdkfd_bo_validate_and_fence for builds
  without KFD

v4: Eliminate amdgpu_vm_fence_imports. It's not needed because the
reservation with its fences is shared with the export, as long as all
imports are from KFD, with the exports already reserved, validated and
fenced by the KFD restore worker.

v5: Reintroduced separate evicted_user state to simplify the state machine
and CS error handling when amdgpu_vm_validate is called without a ticket.

Signed-off-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, 22 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f183d7faeeec..e3c04f4d0f9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -426,9 +426,9 @@ validate_fail:
 	return ret;
 }
 
-static int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
-					       uint32_t domain,
-					       struct dma_fence *fence)
+int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
+					uint32_t domain,
+					struct dma_fence *fence)
 {
 	int ret = amdgpu_bo_reserve(bo, false);
 
@@ -464,13 +464,15 @@ static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo)
  * again. Page directories are only updated after updating page
  * tables.
  */
-static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm)
+static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm,
+				 struct ww_acquire_ctx *ticket)
 {
 	struct amdgpu_bo *pd = vm->root.bo;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
 	int ret;
 
-	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate_vm_bo, NULL);
+	ret = amdgpu_vm_validate(adev, vm, ticket,
+				 amdgpu_amdkfd_validate_vm_bo, NULL);
 	if (ret) {
 		pr_err("failed to validate PT BOs\n");
 		return ret;
@@ -1310,14 +1312,15 @@ update_gpuvm_pte_failed:
 	return ret;
 }
 
-static int process_validate_vms(struct amdkfd_process_info *process_info)
+static int process_validate_vms(struct amdkfd_process_info *process_info,
+				struct ww_acquire_ctx *ticket)
 {
 	struct amdgpu_vm *peer_vm;
 	int ret;
 
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			    vm_list_node) {
-		ret = vm_validate_pt_pd_bos(peer_vm);
+		ret = vm_validate_pt_pd_bos(peer_vm, ticket);
 		if (ret)
 			return ret;
 	}
@@ -1402,7 +1405,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 	ret = amdgpu_bo_reserve(vm->root.bo, true);
 	if (ret)
 		goto reserve_pd_fail;
-	ret = vm_validate_pt_pd_bos(vm);
+	ret = vm_validate_pt_pd_bos(vm, NULL);
 	if (ret) {
 		pr_err("validate_pt_pd_bos() failed\n");
 		goto validate_pd_fail;
@@ -2043,7 +2046,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 	    bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
 		is_invalid_userptr = true;
 
-	ret = vm_validate_pt_pd_bos(avm);
+	ret = vm_validate_pt_pd_bos(avm, NULL);
 	if (unlikely(ret))
 		goto out_unreserve;
 
@@ -2122,7 +2125,7 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		goto unreserve_out;
 	}
 
-	ret = vm_validate_pt_pd_bos(avm);
+	ret = vm_validate_pt_pd_bos(avm, NULL);
 	if (unlikely(ret))
 		goto unreserve_out;
 
@@ -2620,7 +2623,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 		}
 	}
 
-	ret = process_validate_vms(process_info);
+	ret = process_validate_vms(process_info, NULL);
 	if (ret)
 		goto unreserve_out;
 
@@ -2880,11 +2883,6 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 
 	amdgpu_sync_create(&sync_obj);
 
-	/* Validate PDs and PTs */
-	ret = process_validate_vms(process_info);
-	if (ret)
-		goto validate_map_fail;
-
 	/* Validate BOs and map them to GPUVM (update VM page tables). */
 	list_for_each_entry(mem, &process_info->kfd_bo_list,
 			    validate_list) {
@@ -2935,6 +2933,13 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 	if (failed_size)
 		pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size);
 
+	/* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO
+	 * validations above would invalidate DMABuf imports again.
+	 */
+	ret = process_validate_vms(process_info, &exec.ticket);
+	if (ret)
+		goto validate_map_fail;
+
 	/* Update mappings not managed by KFD */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			vm_list_node) {
@@ -3006,7 +3011,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 				   &process_info->eviction_fence->base,
 				   DMA_RESV_USAGE_BOOKKEEP);
 	}
-	/* Attach eviction fence to PD / PT BOs */
+	/* Attach eviction fence to PD / PT BOs and DMABuf imports */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			    vm_list_node) {
 		struct amdgpu_bo *bo = peer_vm->root.bo;