drm/amdgpu: add VM generation token

Instead of using the VRAM lost counter add a 64bit token which indicates
if a context or job is still valid to use.

Should the VRAM be lost or the page tables need re-creation the token will
change indicating that userspace needs to act and re-create the contexts
and re-submit the work.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 26 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 1045be4b547c..143d11afe0e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -406,6 +406,30 @@ static void amdgpu_vm_fini_entities(struct amdgpu_vm *vm)
 }
 
 /**
+ * amdgpu_vm_generation - return the page table re-generation counter
+ * @adev: the amdgpu_device
+ * @vm: optional VM to check, might be NULL
+ *
+ * Returns a page table re-generation token to allow checking if submissions
+ * are still valid to use this VM. The VM parameter might be NULL in which case
+ * just the VRAM lost counter will be used.
+ */
+uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
+{
+	uint64_t result = (u64)atomic_read(&adev->vram_lost_counter) << 32;
+
+	if (!vm)
+		return result;
+
+	result += vm->generation;
+	/* Add one if the page tables will be re-generated on next CS */
+	if (drm_sched_entity_error(&vm->delayed))
+		++result;
+
+	return result;
+}
+
+/**
  * amdgpu_vm_validate_pt_bos - validate the page table BOs
  *
  * @adev: amdgpu device pointer
@@ -428,6 +452,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	int r;
 
 	if (drm_sched_entity_error(&vm->delayed)) {
+		++vm->generation;
 		amdgpu_vm_bo_reset_state_machine(vm);
 		amdgpu_vm_fini_entities(vm);
 		r = amdgpu_vm_init_entities(adev, vm);
@@ -2134,6 +2159,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->last_update = dma_fence_get_stub();
 	vm->last_unlocked = dma_fence_get_stub();
 	vm->last_tlb_flush = dma_fence_get_stub();
+	vm->generation = 0;
 
 	mutex_init(&vm->eviction_lock);
 	vm->evicting = false;