Re: [PATCH 21/25] drm/i915/guc: Handle errors in multi-lrc requests

[John Harrison <john.c.harrison@xxxxxxxxx>]

On 10/13/2021 13:42, Matthew Brost wrote:
> If an error occurs in the front end when multi-lrc requests are getting
> generated we need to skip these in the backend but we still need to
> emit the breadcrumbs seqno. An issues arises because with multi-lrc
> breadcrumbs there is a handshake between the parent and children to make
> forward progress. If all the requests are not present this handshake
> doesn't work. To work around this, if multi-lrc request has an error we
> skip the handshake but still emit the breadcrumbs seqno.
>
> v2:
>   (John Harrison)
>    - Add comment explaining the skipping of the handshake logic
>    - Fix typos in the commit message
> v3:
>   (John Harrison)
>    - Fix up some comments about the math to NOP the ring
>
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
Reviewed-by: John Harrison <John.C.Harrison@xxxxxxxxx>

> ---
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 69 ++++++++++++++++++-
>   1 file changed, 66 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> index bfafe996e2d2..80d8ce68ff59 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -4076,8 +4076,8 @@ static int emit_bb_start_child_no_preempt_mid_batch(struct i915_request *rq,
>   }
>   
>   static u32 *
> -emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
> -						 u32 *cs)
> +__emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
> +						   u32 *cs)
>   {
>   	struct intel_context *ce = rq->context;
>   	u8 i;
> @@ -4105,6 +4105,45 @@ emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
>   				  get_children_go_addr(ce),
>   				  0);
>   
> +	return cs;
> +}
> +
> +/*
> + * If this true, a submission of multi-lrc requests had an error and the
> + * requests need to be skipped. The front end (execuf IOCTL) should've called
> + * i915_request_skip which squashes the BB but we still need to emit the fini
> + * breadrcrumbs seqno write. At this point we don't know how many of the
> + * requests in the multi-lrc submission were generated so we can't do the
> + * handshake between the parent and children (e.g. if 4 requests should be
> + * generated but 2nd hit an error only 1 would be seen by the GuC backend).
> + * Simply skip the handshake, but still emit the breadcrumbd seqno, if an error
> + * has occurred on any of the requests in submission / relationship.
> + */
> +static inline bool skip_handshake(struct i915_request *rq)
> +{
> +	return test_bit(I915_FENCE_FLAG_SKIP_PARALLEL, &rq->fence.flags);
> +}
> +
> +static u32 *
> +emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
> +						 u32 *cs)
> +{
> +	struct intel_context *ce = rq->context;
> +
> +	GEM_BUG_ON(!intel_context_is_parent(ce));
> +
> +	if (unlikely(skip_handshake(rq))) {
> +		/*
> +		 * NOP everything in __emit_fini_breadcrumb_parent_no_preempt_mid_batch,
> +		 * the -6 comes from the length of the emits below.
> +		 */
> +		memset(cs, 0, sizeof(u32) *
> +		       (ce->engine->emit_fini_breadcrumb_dw - 6));
> +		cs += ce->engine->emit_fini_breadcrumb_dw - 6;
> +	} else {
> +		cs = __emit_fini_breadcrumb_parent_no_preempt_mid_batch(rq, cs);
> +	}
> +
>   	/* Emit fini breadcrumb */
>   	cs = gen8_emit_ggtt_write(cs,
>   				  rq->fence.seqno,
> @@ -4121,7 +4160,8 @@ emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq,
>   }
>   
>   static u32 *
> -emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq, u32 *cs)
> +__emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq,
> +						  u32 *cs)
>   {
>   	struct intel_context *ce = rq->context;
>   	struct intel_context *parent = intel_context_to_parent(ce);
> @@ -4148,6 +4188,29 @@ emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq, u32 *cs
>   	*cs++ = get_children_go_addr(parent);
>   	*cs++ = 0;
>   
> +	return cs;
> +}
> +
> +static u32 *
> +emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq,
> +						u32 *cs)
> +{
> +	struct intel_context *ce = rq->context;
> +
> +	GEM_BUG_ON(!intel_context_is_child(ce));
> +
> +	if (unlikely(skip_handshake(rq))) {
> +		/*
> +		 * NOP everything in __emit_fini_breadcrumb_child_no_preempt_mid_batch,
> +		 * the -6 comes from the length of the emits below.
> +		 */
> +		memset(cs, 0, sizeof(u32) *
> +		       (ce->engine->emit_fini_breadcrumb_dw - 6));
> +		cs += ce->engine->emit_fini_breadcrumb_dw - 6;
> +	} else {
> +		cs = __emit_fini_breadcrumb_child_no_preempt_mid_batch(rq, cs);
> +	}
> +
>   	/* Emit fini breadcrumb */
>   	cs = gen8_emit_ggtt_write(cs,
>   				  rq->fence.seqno,