[PATCH] drm/xe: Add missing runtime outer protection

[Matthew Brost]

On Wed, May 29, 2024 at 05:56:03PM -0400, Rodrigo Vivi wrote:
> TTM BO destroy is called unlocked as a ref count worker when it
> gets 0 users. When that happens we could be runtime suspended,
> and waking up from inner locked places like ggtt_remove_node,
> could potentially lead to deadlocks. Our warning system against
> this case hit this case:
> 
> [ 2295.891269] xe 0000:03:00.0: Missing outer runtime PM protection
> [snip]
> [ 2295.891604]  ? xe_pm_runtime_get_noresume+0x5c/0x70 [xe]
> [ 2295.891717]  ? report_bug+0x18d/0x1c0
> [ 2295.891722]  ? handle_bug+0x3c/0x80
> [ 2295.891724]  ? exc_invalid_op+0x13/0x60
> [ 2295.891726]  ? asm_exc_invalid_op+0x16/0x20
> [ 2295.891730]  ? xe_pm_runtime_get_noresume+0x5c/0x70 [xe]
> [ 2295.891816]  xe_ggtt_remove_node+0x93/0xf0 [xe]
> [ 2295.891870]  xe_ttm_bo_destroy+0xe9/0xf0 [xe]
> [ 2295.891935]  process_one_work+0x225/0x730
> [ 2295.891940]  worker_thread+0x1d8/0x3c0
> 
> Add this outer protection to avoid any potential deadlock.
> 
> Reported-by: Paulo Zanoni <paulo.zanoni at intel.com>
> Cc: Francois Dugast <francois.dugast at intel.com>
> Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_bo.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 2bae01ce4e5b..a902f23bec0c 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -1066,6 +1066,8 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
>  	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
>  	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
>  
> +	xe_pm_runtime_get(xe);

Should we only do this if we are in a kthread? i.e. !current->mm

Matt

> +
>  	if (bo->ttm.base.import_attach)
>  		drm_prime_gem_destroy(&bo->ttm.base, NULL);
>  	drm_gem_object_release(&bo->ttm.base);
> @@ -1089,6 +1091,8 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
>  	mutex_unlock(&xe->mem_access.vram_userfault.lock);
>  
>  	kfree(bo);
> +
> +	xe_pm_runtime_put(xe);
>  }
>  
>  static void xe_gem_object_free(struct drm_gem_object *obj)
> -- 
> 2.45.1
>