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, 60 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b8fcb6c55698..77d015ebb201 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -234,6 +234,22 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
 }
 
 /**
+ * amdgpu_vm_bo_evicted_user - vm_bo is evicted
+ *
+ * @vm_bo: vm_bo which is evicted
+ *
+ * State for BOs used by user mode queues which are not at the location they
+ * should be.
+ */
+static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
+{
+	vm_bo->moved = true;
+	spin_lock(&vm_bo->vm->status_lock);
+	list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user);
+	spin_unlock(&vm_bo->vm->status_lock);
+}
+
+/**
  * amdgpu_vm_bo_relocated - vm_bo is reloacted
  *
  * @vm_bo: vm_bo which is relocated
@@ -427,21 +443,25 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 }
 
 /**
- * amdgpu_vm_validate_pt_bos - validate the page table BOs
+ * amdgpu_vm_validate - validate evicted BOs tracked in the VM
  *
  * @adev: amdgpu device pointer
  * @vm: vm providing the BOs
+ * @ticket: optional reservation ticket used to reserve the VM
  * @validate: callback to do the validation
  * @param: parameter for the validation callback
  *
- * Validate the page table BOs on command submission if neccessary.
+ * Validate the page table BOs and per-VM BOs on command submission if
+ * necessary. If a ticket is given, also try to validate evicted user queue
+ * BOs. They must already be reserved with the given ticket.
  *
  * Returns:
  * Validation result.
  */
-int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			      int (*validate)(void *p, struct amdgpu_bo *bo),
-			      void *param)
+int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+		       struct ww_acquire_ctx *ticket,
+		       int (*validate)(void *p, struct amdgpu_bo *bo),
+		       void *param)
 {
 	struct amdgpu_vm_bo_base *bo_base;
 	struct amdgpu_bo *shadow;
@@ -484,6 +504,28 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		}
 		spin_lock(&vm->status_lock);
 	}
+	while (ticket && !list_empty(&vm->evicted_user)) {
+		bo_base = list_first_entry(&vm->evicted_user,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
+
+		bo = bo_base->bo;
+
+		if (dma_resv_locking_ctx(bo->tbo.base.resv) != ticket) {
+			pr_warn_ratelimited("Evicted user BO is not reserved in pid %d\n",
+					    vm->task_info.pid);
+			return -EINVAL;
+		}
+
+		r = validate(param, bo);
+		if (r)
+			return r;
+
+		amdgpu_vm_bo_invalidated(bo_base);
+
+		spin_lock(&vm->status_lock);
+	}
 	spin_unlock(&vm->status_lock);
 
 	amdgpu_vm_eviction_lock(vm);
@@ -1426,11 +1468,21 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		}
 
 		r = amdgpu_vm_bo_update(adev, bo_va, clear);
-		if (r)
-			return r;
 
 		if (unlock)
 			dma_resv_unlock(resv);
+		if (r)
+			return r;
+
+		/* Remember evicted DMABuf imports in compute VMs for later
+		 * validation
+		 */
+		if (vm->is_compute_context && bo_va->base.bo &&
+		    bo_va->base.bo->tbo.base.import_attach &&
+		    (!bo_va->base.bo->tbo.resource ||
+		     bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM))
+			amdgpu_vm_bo_evicted_user(&bo_va->base);
+
 		spin_lock(&vm->status_lock);
 	}
 	spin_unlock(&vm->status_lock);
@@ -2196,6 +2248,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		vm->reserved_vmid[i] = NULL;
 	INIT_LIST_HEAD(&vm->evicted);
+	INIT_LIST_HEAD(&vm->evicted_user);
 	INIT_LIST_HEAD(&vm->relocated);
 	INIT_LIST_HEAD(&vm->moved);
 	INIT_LIST_HEAD(&vm->idle);