[PATCH 3/7] drm/xe/oa: Add input fence dependencies

[Souza, Jose]

On Fri, 2024-08-30 at 15:16 -0700, Ashutosh Dixit wrote:
> Add input fence dependencies which will make OA configuration wait till
> these dependencies are met (till input fences signal).
> 
> v2: Change add_deps arg to xe_oa_submit_bb from bool to enum (Matt Brost)
> 
> Reviewed-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
> Signed-off-by: Ashutosh Dixit <ashutosh.dixit at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_oa.c | 25 +++++++++++++++++++++----
>  1 file changed, 21 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
> index 8ada74da3da19..b4b68019d35b7 100644
> --- a/drivers/gpu/drm/xe/xe_oa.c
> +++ b/drivers/gpu/drm/xe/xe_oa.c
> @@ -42,6 +42,11 @@
>  #define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ)
>  #define XE_OA_UNIT_INVALID U32_MAX
>  
> +enum xe_oa_submit_deps {
> +	XE_OA_SUBMIT_NO_DEPS,
> +	XE_OA_SUBMIT_ADD_DEPS,
> +};
> +
>  struct xe_oa_reg {
>  	struct xe_reg addr;
>  	u32 value;
> @@ -568,7 +573,8 @@ static __poll_t xe_oa_poll(struct file *file, poll_table *wait)
>  	return ret;
>  }
>  
> -static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, struct xe_bb *bb)
> +static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa_submit_deps deps,
> +					 struct xe_bb *bb)
>  {
>  	struct xe_sched_job *job;
>  	struct dma_fence *fence;
> @@ -581,11 +587,22 @@ static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, struct xe_
>  		goto exit;
>  	}
>  
> +	if (deps == XE_OA_SUBMIT_ADD_DEPS) {
> +		for (int i = 0; i < stream->num_syncs && !err; i++)
> +			err = xe_sync_entry_add_deps(&stream->syncs[i], job);

err needs to be initialize to 0 otherwise it could take the error path below when there is no syncs set.

> +		if (err) {
> +			drm_dbg(&stream->oa->xe->drm, "xe_sync_entry_add_deps err %d\n", err);
> +			goto err_put_job;
> +		}
> +	}
> +
>  	xe_sched_job_arm(job);
>  	fence = dma_fence_get(&job->drm.s_fence->finished);
>  	xe_sched_job_push(job);
>  
>  	return fence;
> +err_put_job:
> +	xe_sched_job_put(job);
>  exit:
>  	return ERR_PTR(err);
>  }
> @@ -663,7 +680,7 @@ static int xe_oa_modify_ctx_image(struct xe_oa_stream *stream, struct xe_lrc *lr
>  
>  	xe_oa_store_flex(stream, lrc, bb, flex, count);
>  
> -	fence = xe_oa_submit_bb(stream, bb);
> +	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb);
>  	if (IS_ERR(fence)) {
>  		err = PTR_ERR(fence);
>  		goto free_bb;
> @@ -692,7 +709,7 @@ static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *re
>  
>  	write_cs_mi_lri(bb, reg_lri, 1);
>  
> -	fence = xe_oa_submit_bb(stream, bb);
> +	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb);
>  	if (IS_ERR(fence)) {
>  		err = PTR_ERR(fence);
>  		goto free_bb;
> @@ -943,7 +960,7 @@ static int xe_oa_emit_oa_config(struct xe_oa_stream *stream, struct xe_oa_config
>  		goto exit;
>  	}
>  
> -	fence = xe_oa_submit_bb(stream, oa_bo->bb);
> +	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_ADD_DEPS, oa_bo->bb);
>  	if (IS_ERR(fence)) {
>  		err = PTR_ERR(fence);
>  		goto exit;