[Intel-gfx] [RFC PATCH] drm/ttm: Fix swapping dereferences of freed memory

[Christian König]

Am 27.05.21 um 16:19 schrieb Thomas Hellström:
> The swapping code was dereference bo->ttm pointers without having the
> dma-resv lock held. Also it might try to swap out unpopulated bos.
>
> Fix this by moving the bo->ttm dereference until we have the reservation
> lock. Check that the ttm_tt is populated after the swap_notify callback.
>
> Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
>   drivers/gpu/drm/ttm/ttm_bo.c     | 16 +++++++++++++++-
>   drivers/gpu/drm/ttm/ttm_device.c |  8 +++-----
>   2 files changed, 18 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 9f53506a82fc..86213d37657b 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -1163,6 +1163,16 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
>   	if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL))
>   		return -EBUSY;
>   
> +	dma_resv_assert_held(bo->base.resv);
> +
> +	if (!bo->ttm ||
> +	    bo->ttm->page_flags & TTM_PAGE_FLAG_SG ||
> +	    bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) {
> +		if (locked)
> +			dma_resv_unlock(bo->base.resv);
> +		return -EBUSY;
> +	}
> +
>   	if (!ttm_bo_get_unless_zero(bo)) {
>   		if (locked)
>   			dma_resv_unlock(bo->base.resv);
> @@ -1215,7 +1225,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
>   	if (bo->bdev->funcs->swap_notify)
>   		bo->bdev->funcs->swap_notify(bo);
>   
> -	ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags);
> +	if (ttm_tt_is_populated(bo->ttm))
> +		ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags);

Exactly that is what I won't recommend. We would try to swap out the 
same BO over and over again with that.

Why not move that to the check above as well?

Christian.

>   out:
>   
>   	/*
> @@ -1225,6 +1236,9 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
>   	if (locked)
>   		dma_resv_unlock(bo->base.resv);
>   	ttm_bo_put(bo);
> +
> +	/* Don't break locking rules. */
> +	WARN_ON(ret == -EBUSY);
>   	return ret;
>   }
>   
> diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
> index 460953dcad11..eaa7487ae404 100644
> --- a/drivers/gpu/drm/ttm/ttm_device.c
> +++ b/drivers/gpu/drm/ttm/ttm_device.c
> @@ -143,14 +143,12 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx,
>   
>   		for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) {
>   			list_for_each_entry(bo, &man->lru[j], lru) {
> -				uint32_t num_pages;
> +				pgoff_t num_pages;
>   
> -				if (!bo->ttm ||
> -				    bo->ttm->page_flags & TTM_PAGE_FLAG_SG ||
> -				    bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)
> +				if (!READ_ONCE(bo->ttm))
>   					continue;
>   
> -				num_pages = bo->ttm->num_pages;
> +				num_pages = bo->base.size >> PAGE_SHIFT;
>   				ret = ttm_bo_swapout(bo, ctx, gfp_flags);
>   				/* ttm_bo_swapout has dropped the lru_lock */
>   				if (!ret)