From: Zihao Mu <[email protected]> The public output fence is intentionally not updated for immediate VM updates. It can also be omitted on intermediate IB submissions. Neither case removes the need to order a later TLB invalidation after the SDMA commands have completed.
Keep an owned reference to the latest submission in the update context, including immediate and rollover submissions. Use that internal fence for range TLB handling and release it when each context is destroyed. Leave the public output-fence condition and DONT_PIPELINE policy alone. Return a nested table clear completion to its outer context so an early exit can also wait for that clear before finalizing the range. This establishes completion tracking before adding partial-error range finalization, so that finalization never depends on a later patch to recover an already submitted IB's fence. Signed-off-by: Zihao Mu <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h | 8 +++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 12 +++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 2 ++ 4 files changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 94b1cfe05e3..1e41f159ced 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -658,7 +658,9 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, bo_base->moved = true; if (vm->generation != new_vm_generation) { - r = amdgpu_vm_pt_clear(adev, vm, to_amdgpu_bo_vm(bo_base->bo), false); + r = amdgpu_vm_pt_clear(adev, vm, + to_amdgpu_bo_vm(bo_base->bo), + false, NULL); if (r) return r; } @@ -1081,6 +1083,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, amdgpu_vm_bo_idle(entry); error: + dma_fence_put(params.last_update); drm_dev_exit(idx); return r; } @@ -1286,7 +1289,7 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm, goto error_free; if (params.needs_flush) { - amdgpu_vm_tlb_flush(¶ms, *fence, tlb_cb); + amdgpu_vm_tlb_flush(¶ms, params.last_update, tlb_cb); tlb_cb = NULL; } @@ -1294,6 +1297,7 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm, error_free: kfree(tlb_cb); + dma_fence_put(params.last_update); amdgpu_vm_end_critical(¶ms); drm_dev_exit(idx); return r; @@ -2710,7 +2714,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) goto error_free_root; - r = amdgpu_vm_pt_clear(adev, vm, root, false); + r = amdgpu_vm_pt_clear(adev, vm, root, false, NULL); if (r) goto error_free_root; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h index 8ebb0b03329..71fc1fffaa6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h @@ -77,6 +77,11 @@ struct amdgpu_vm_update_params { */ struct amdgpu_job *job; + /** + * @last_update: owned reference to the last SDMA completion fence + */ + struct dma_fence *last_update; + /** * @num_dw_left: number of dw left for the IB */ @@ -116,7 +121,8 @@ struct amdgpu_vm_update_funcs { }; int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, - struct amdgpu_bo_vm *vmbo, bool immediate); + struct amdgpu_bo_vm *vmbo, bool immediate, + struct dma_fence **last_update); int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int level, bool immediate, struct amdgpu_bo_vm **vmbo, int32_t xcp_id); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index c73eb416c0e..9955be111ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -353,6 +353,7 @@ static void amdgpu_vm_pt_next_dfs(struct amdgpu_device *adev, * @vm: VM to clear BO from * @vmbo: BO to clear * @immediate: use an immediate update + * @last_update: optional output for the internal clear completion fence * * Root PD needs to be reserved when calling this. * @@ -360,7 +361,8 @@ static void amdgpu_vm_pt_next_dfs(struct amdgpu_device *adev, * 0 on success, errno otherwise. */ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, - struct amdgpu_bo_vm *vmbo, bool immediate) + struct amdgpu_bo_vm *vmbo, bool immediate, + struct dma_fence **last_update) { unsigned int level = adev->vm_manager.root_level; struct ttm_operation_ctx ctx = { true, false }; @@ -390,11 +392,11 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (!drm_dev_enter(adev_to_drm(adev), &idx)) return -ENODEV; + memset(¶ms, 0, sizeof(params)); r = vm->update_funcs->map_table(vmbo); if (r) goto exit; - memset(¶ms, 0, sizeof(params)); params.adev = adev; params.vm = vm; params.immediate = immediate; @@ -429,6 +431,9 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, r = vm->update_funcs->commit(¶ms, &vm->last_update); exit: + if (last_update && params.last_update) + swap(*last_update, params.last_update); + dma_fence_put(params.last_update); drm_dev_exit(idx); return r; } @@ -543,7 +548,8 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_vm_update_params *p, */ pt_bo->parent = amdgpu_bo_ref(cursor->parent->bo); amdgpu_vm_bo_base_init(entry, p->vm, pt_bo); - r = amdgpu_vm_pt_clear(p->adev, p->vm, pt, p->immediate); + r = amdgpu_vm_pt_clear(p->adev, p->vm, pt, p->immediate, + &p->last_update); if (r) goto error_unpin; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index ade6c7aa15c..02f3271d96a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -133,6 +133,8 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, WARN_ON(ib->length_dw > p->num_dw_left); f = amdgpu_job_submit(p->job); p->job = NULL; + dma_fence_put(p->last_update); + p->last_update = dma_fence_get(f); if (p->unlocked) { struct dma_fence *tmp = dma_fence_get(f); -- 2.43.0
