[PATCH v4 09/15] drm/ttm: Document and optimize ttm_bo_pipeline_gutting()
Christian König
christian.koenig at amd.com
Wed May 26 14:32:50 UTC 2021
Am 26.05.21 um 13:32 schrieb Thomas Hellström:
> If the bo is idle when calling ttm_bo_pipeline_gutting(), we unnecessarily
> create a ghost object and push it out to delayed destroy.
> Fix this by adding a path for idle, and document the function.
>
> Also avoid having the bo end up in a bad state vulnerable to user-space
> triggered kernel BUGs if the call to ttm_tt_create() fails.
>
> Finally reuse ttm_bo_pipeline_gutting() in ttm_bo_evict().
>
> Cc: Christian König <christian.koenig at amd.com>
> Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
> v4:
> - Clarify why we mark bo for clearing after ttm_bo_pipeline_gutting()
> (Reported by Matthew Auld)
> ---
> drivers/gpu/drm/ttm/ttm_bo.c | 20 +++++------
> drivers/gpu/drm/ttm/ttm_bo_util.c | 55 ++++++++++++++++++++++++++++---
> drivers/gpu/drm/ttm/ttm_tt.c | 5 +++
> include/drm/ttm/ttm_tt.h | 10 ++++++
> 4 files changed, 76 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 51a94fd63bd7..be0406466460 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -501,10 +501,15 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
> bdev->funcs->evict_flags(bo, &placement);
>
> if (!placement.num_placement && !placement.num_busy_placement) {
> - ttm_bo_wait(bo, false, false);
> + ret = ttm_bo_wait(bo, true, false);
> + if (ret)
> + return ret;
>
> - ttm_bo_cleanup_memtype_use(bo);
> - return ttm_tt_create(bo, false);
> + /*
> + * Since we've already synced, this frees backing store
> + * immediately.
> + */
> + return ttm_bo_pipeline_gutting(bo);
> }
>
> ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx);
> @@ -976,13 +981,8 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
> /*
> * Remove the backing store if no placement is given.
> */
> - if (!placement->num_placement && !placement->num_busy_placement) {
> - ret = ttm_bo_pipeline_gutting(bo);
> - if (ret)
> - return ret;
> -
> - return ttm_tt_create(bo, false);
> - }
> + if (!placement->num_placement && !placement->num_busy_placement)
> + return ttm_bo_pipeline_gutting(bo);
>
> /*
> * Check whether we need to move buffer.
> diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> index ebff603a97f4..4cca932f1c0e 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> @@ -590,26 +590,73 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
> }
> EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
>
> +/**
> + * ttm_bo_pipeline_gutting - purge the contents of a bo
> + * @bo: The buffer object
> + *
> + * Purge the contents of a bo, async if the bo is not idle.
> + * After a successful call, the bo is left unpopulated in
> + * system placement. The function may wait uninterruptible
> + * for idle on OOM.
> + *
> + * Return: 0 if successful, negative error code on failure.
> + */
> int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
> {
> static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM };
> struct ttm_buffer_object *ghost;
> + struct ttm_tt *ttm;
> int ret;
>
> - ret = ttm_buffer_object_transfer(bo, &ghost);
> + /* If already idle, no need for ghost object dance. */
> + ret = ttm_bo_wait(bo, false, true);
> + if (ret != -EBUSY) {
> + if (!bo->ttm) {
> + /* See comment below about clearing. */
> + ret = ttm_tt_create(bo, true);
> + if (ret)
> + return ret;
> + } else {
> + ttm_tt_unpopulate(bo->bdev, bo->ttm);
> + if (bo->type == ttm_bo_type_device)
> + ttm_tt_mark_for_clear(bo->ttm);
> + }
> + ttm_resource_free(bo, &bo->mem);
> + ttm_resource_alloc(bo, &sys_mem, &bo->mem);
> +
> + return 0;
> + }
> +
> + /*
> + * We need an unpopulated ttm_tt after giving our current one,
> + * if any, to the ghost object. And we can't afford to fail
> + * creating one *after* the operation. If the bo subsequently gets
> + * resurrected, make sure it's cleared (if ttm_bo_type_device)
> + * to avoid leaking sensitive information to user-space.
> + */
> +
> + ttm = bo->ttm;
> + bo->ttm = NULL;
> + ret = ttm_tt_create(bo, true);
> + swap(bo->ttm, ttm);
> if (ret)
> return ret;
>
> + ret = ttm_buffer_object_transfer(bo, &ghost);
> + if (ret) {
> + ttm_tt_destroy(bo->bdev, ttm);
> + return ret;
> + }
> +
> ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
> /* Last resort, wait for the BO to be idle when we are OOM */
> if (ret)
> ttm_bo_wait(bo, false, false);
>
> - ttm_resource_alloc(bo, &sys_mem, &bo->mem);
> - bo->ttm = NULL;
> -
> dma_resv_unlock(&ghost->base._resv);
> ttm_bo_put(ghost);
> + bo->ttm = ttm;
> + ttm_resource_alloc(bo, &sys_mem, &bo->mem);
>
> return 0;
> }
> diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
> index 0e41227116b1..913b330a234b 100644
> --- a/drivers/gpu/drm/ttm/ttm_tt.c
> +++ b/drivers/gpu/drm/ttm/ttm_tt.c
> @@ -134,6 +134,11 @@ void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm)
> }
> EXPORT_SYMBOL(ttm_tt_destroy_common);
>
> +void ttm_tt_mark_for_clear(struct ttm_tt *ttm)
> +{
> + ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
> +}
> +
> void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
> {
> bdev->funcs->ttm_tt_destroy(bdev, ttm);
> diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
> index 3102059db726..daa9c4cf48bb 100644
> --- a/include/drm/ttm/ttm_tt.h
> +++ b/include/drm/ttm/ttm_tt.h
> @@ -170,6 +170,16 @@ int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_oper
> */
> void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm);
>
> +/**
> + * ttm_tt_mark_for_clear - Mark pages for clearing on populate.
> + *
> + * @ttm: Pointer to the ttm_tt structure
> + *
> + * Marks pages for clearing so that the next time the page vector is
> + * populated, the pages will be cleared.
> + */
> +void ttm_tt_mark_for_clear(struct ttm_tt *ttm);
Either implement the function directly here as static (it's a one liner
anyway) or move the documentation to the implementation.
Apart from that the patch is Reviewed-by: Christian König
<christian.koenig at amd.com>
Regards,
Christian.
> +
> void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages);
>
> struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt,
More information about the dri-devel
mailing list