[PATCH 2/2] drm/msm: Restore error return on invalid fence

[Akhil P Oommen]

On 11/12/2021 12:54 AM, Rob Clark wrote:
> From: Rob Clark <robdclark at chromium.org>
> 
> When converting to use an idr to map userspace fence seqno values back
> to a dma_fence, we lost the error return when userspace passes seqno
> that is larger than the last submitted fence.  Restore this check.
> 
> Reported-by: Akhil P Oommen <akhilpo at codeaurora.org>
> Fixes: a61acbbe9cf8 ("drm/msm: Track "seqno" fences by idr")
> Signed-off-by: Rob Clark <robdclark at chromium.org>
> ---
> Note: I will rebase "drm/msm: Handle fence rollover" on top of this,
> to simplify backporting this patch to stable kernels
> 
>   drivers/gpu/drm/msm/msm_drv.c        | 6 ++++++
>   drivers/gpu/drm/msm/msm_gem_submit.c | 1 +
>   drivers/gpu/drm/msm/msm_gpu.h        | 3 +++
>   3 files changed, 10 insertions(+)
> 
> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
> index cb14d997c174..56500eb5219e 100644
> --- a/drivers/gpu/drm/msm/msm_drv.c
> +++ b/drivers/gpu/drm/msm/msm_drv.c
> @@ -967,6 +967,12 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
>   	struct dma_fence *fence;
>   	int ret;
>   
> +	if (fence_id > queue->last_fence) {

But fence_id can wrap around and then this check won't be valid.

-Akhil.

> +		DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n",
> +				      fence_id, queue->last_fence);
> +		return -EINVAL;
> +	}
> +
>   	/*
>   	 * Map submitqueue scoped "seqno" (which is actually an idr key)
>   	 * back to underlying dma-fence
> diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
> index 151d19e4453c..a38f23be497d 100644
> --- a/drivers/gpu/drm/msm/msm_gem_submit.c
> +++ b/drivers/gpu/drm/msm/msm_gem_submit.c
> @@ -911,6 +911,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
>   	drm_sched_entity_push_job(&submit->base, queue->entity);
>   
>   	args->fence = submit->fence_id;
> +	queue->last_fence = submit->fence_id;
>   
>   	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
>   	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
> diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
> index bd4e0024033e..e73a5bb03544 100644
> --- a/drivers/gpu/drm/msm/msm_gpu.h
> +++ b/drivers/gpu/drm/msm/msm_gpu.h
> @@ -376,6 +376,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
>    * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
>    *             by the submitqueue's priority
>    * @faults:    the number of GPU hangs associated with this submitqueue
> + * @last_fence: the sequence number of the last allocated fence (for error
> + *             checking)
>    * @ctx:       the per-drm_file context associated with the submitqueue (ie.
>    *             which set of pgtables do submits jobs associated with the
>    *             submitqueue use)
> @@ -391,6 +393,7 @@ struct msm_gpu_submitqueue {
>   	u32 flags;
>   	u32 ring_nr;
>   	int faults;
> +	uint32_t last_fence;
>   	struct msm_file_private *ctx;
>   	struct list_head node;
>   	struct idr fence_idr;
>