[PATCH] drm/ttm: Don't evict BOs outside of the requested placement range

[Christian König]

Am 09.10.2014 um 08:02 schrieb Michel Dänzer:
> From: Michel Dänzer <michel.daenzer at amd.com>
>
> The radeon driver uses placement range restrictions for several reasons,
> in particular to make sure BOs in VRAM can be accessed by the CPU, e.g.
> during a page fault.
>
> Without this change, TTM could evict other BOs while trying to satisfy
> the requested placement, even if the evicted BOs were outside of the
> requested placement range. Doing so didn't free up any space in the
> requested placement range, so the (potentially high) eviction cost was
> incurred for no benefit.
>
> Nominating for stable because radeon driver changes in 3.17 made this
> much more noticeable than before.
>
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=84662
> Cc: stable at vger.kernel.org
> Signed-off-by: Michel Dänzer <michel.daenzer at amd.com>

Reviewed-by: Christian König <christian.koenig at amd.com>

> ---
>   drivers/gpu/drm/ttm/ttm_bo.c | 20 +++++++++++++++++---
>   1 file changed, 17 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 8f5cec6..407fa2d 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -709,6 +709,7 @@ out:
>   
>   static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
>   				uint32_t mem_type,
> +				const struct ttm_place *place,
>   				bool interruptible,
>   				bool no_wait_gpu)
>   {
> @@ -720,8 +721,21 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
>   	spin_lock(&glob->lru_lock);
>   	list_for_each_entry(bo, &man->lru, lru) {
>   		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
> -		if (!ret)
> +		if (!ret) {
> +			if (place && (place->fpfn || place->lpfn)) {
> +				/* Don't evict this BO if it's outside of the
> +				 * requested placement range
> +				 */
> +				if (place->fpfn >= (bo->mem.start + bo->mem.size) ||
> +				    (place->lpfn && place->lpfn <= bo->mem.start)) {
> +					__ttm_bo_unreserve(bo);
> +					ret = -EBUSY;
> +					continue;
> +				}
> +			}
> +
>   			break;
> +		}
>   	}
>   
>   	if (ret) {
> @@ -782,7 +796,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
>   			return ret;
>   		if (mem->mm_node)
>   			break;
> -		ret = ttm_mem_evict_first(bdev, mem_type,
> +		ret = ttm_mem_evict_first(bdev, mem_type, place,
>   					  interruptible, no_wait_gpu);
>   		if (unlikely(ret != 0))
>   			return ret;
> @@ -1233,7 +1247,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
>   	spin_lock(&glob->lru_lock);
>   	while (!list_empty(&man->lru)) {
>   		spin_unlock(&glob->lru_lock);
> -		ret = ttm_mem_evict_first(bdev, mem_type, false, false);
> +		ret = ttm_mem_evict_first(bdev, mem_type, NULL, false, false);
>   		if (ret) {
>   			if (allow_errors) {
>   				return ret;