On Tue, 2024-10-15 at 20:25 -0700, Matthew Brost wrote:
> Add XE_BO_FLAG_SYSTEM_ALLOC to indicate BO is tied to SVM range.
>
> Add XE_BO_FLAG_SKIP_CLEAR to indicate BO does not need to cleared.
>
> v2:
> - Take VM ref for system allocator BOs
>
> Signed-off-by: Matthew Brost <matthew.br...@intel.com>
> ---
> drivers/gpu/drm/xe/xe_bo.c | 15 +++++++++------
> drivers/gpu/drm/xe/xe_bo.h | 2 ++
> 2 files changed, 11 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index a02d63e322ae..dbd03383878e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -685,8 +685,9 @@ static int xe_bo_move(struct ttm_buffer_object
> *ttm_bo, bool evict,
> move_lacks_source = !old_mem || (handle_system_ccs ? (!bo-
> >ccs_cleared) :
>
> (!mem_type_is_vram(old_mem_type) && !tt_has_data));
>
> - needs_clear = (ttm && ttm->page_flags &
> TTM_TT_FLAG_ZERO_ALLOC) ||
> - (!ttm && ttm_bo->type == ttm_bo_type_device);
> + needs_clear = !(bo->flags & XE_BO_FLAG_SKIP_CLEAR) &&
> + ((ttm && ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)
> ||
> + (!ttm && ttm_bo->type == ttm_bo_type_device));
It should be worth adding a note about how clearing for svm bos is
intended to work. From what I can tell, there is an option to clear on
migration from system to vram if no system pages are present?
>
> if (new_mem->mem_type == XE_PL_TT) {
> ret = xe_tt_map_sg(ttm);
> @@ -1145,7 +1146,7 @@ static void xe_ttm_bo_destroy(struct
> ttm_buffer_object *ttm_bo)
> xe_drm_client_remove_bo(bo);
> #endif
>
> - if (bo->vm && xe_bo_is_user(bo))
> + if (bo->vm && (xe_bo_is_user(bo) || bo->flags &
> XE_BO_FLAG_SYSTEM_ALLOC))
> xe_vm_put(bo->vm);
>
> mutex_lock(&xe->mem_access.vram_userfault.lock);
> @@ -1301,7 +1302,8 @@ struct xe_bo *___xe_bo_create_locked(struct
> xe_device *xe, struct xe_bo *bo,
> int err;
>
> /* Only kernel objects should set GT */
> - xe_assert(xe, !tile || type == ttm_bo_type_kernel);
> + xe_assert(xe, !tile || type == ttm_bo_type_kernel ||
> + flags & XE_BO_FLAG_SYSTEM_ALLOC);
>
> if (XE_WARN_ON(!size)) {
> xe_bo_free(bo);
> @@ -1493,7 +1495,7 @@ __xe_bo_create_locked(struct xe_device *xe,
> * by having all the vm's bo refereferences released at vm
> close
> * time.
> */
> - if (vm && xe_bo_is_user(bo))
> + if (vm && (xe_bo_is_user(bo) || bo->flags &
> XE_BO_FLAG_SYSTEM_ALLOC))
> xe_vm_get(vm);
> bo->vm = vm;
>
> @@ -2333,7 +2335,8 @@ bool xe_bo_needs_ccs_pages(struct xe_bo *bo)
> * can't be used since there's no CCS storage associated
> with
> * non-VRAM addresses.
> */
> - if (IS_DGFX(xe) && (bo->flags & XE_BO_FLAG_SYSTEM))
> + if (IS_DGFX(xe) && ((bo->flags & XE_BO_FLAG_SYSTEM) ||
> + (bo->flags & XE_BO_FLAG_SYSTEM_ALLOC)))
> return false;
Can we support CCS with system allocator? Perhaps add a TODO comment if
so. I figure it should be possible if we resolve on migration to
system, which we do on BMG.
Thanks,
Thomas
>
> return true;
> diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
> index 7fa44a0138b0..caf0459d16ad 100644
> --- a/drivers/gpu/drm/xe/xe_bo.h
> +++ b/drivers/gpu/drm/xe/xe_bo.h
> @@ -39,6 +39,8 @@
> #define XE_BO_FLAG_NEEDS_64K BIT(15)
> #define XE_BO_FLAG_NEEDS_2M BIT(16)
> #define XE_BO_FLAG_GGTT_INVALIDATE BIT(17)
> +#define XE_BO_FLAG_SYSTEM_ALLOC BIT(18)
> +#define XE_BO_FLAG_SKIP_CLEAR BIT(19)
> /* this one is trigger internally only */
> #define XE_BO_FLAG_INTERNAL_TEST BIT(30)
> #define XE_BO_FLAG_INTERNAL_64K BIT(31)
