Re: [PATCH 2/3] drm/i915/guc: Add work queue to trigger a GT reset

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

On 1/20/2022 20:31, Matthew Brost wrote:
> The G2H handler needs to be flushed during a GT reset but a G2H
> indicating engine reset failure can trigger a GT reset. Add a worker to
> trigger the GT rest when an engine reset failure is received to break
> this circular dependency.
>
> v2:
>   (John Harrison)
>    - Store engine reset mask
>    - Fix typo in commit message
> v3:
>   (John Harrison)
>    - Fix another typo in commit message
>    - s/reset_*/reset_fail_*/
>
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
Reviewed-by: John Harrison <John.C.Harrison@xxxxxxxxx>

> ---
>   drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  9 +++++
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 37 +++++++++++++++++--
>   2 files changed, 42 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> index 9d26a86fe557a..d59bbf49d1c2b 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> @@ -119,6 +119,15 @@ struct intel_guc {
>   		 * function as it might be in an atomic context (no sleeping)
>   		 */
>   		struct work_struct destroyed_worker;
> +		/**
> +		 * @reset_fail_worker: worker to trigger a GT reset after an
> +		 * engine reset fails
> +		 */
> +		struct work_struct reset_fail_worker;
> +		/**
> +		 * @reset_fail_mask: mask of engines that failed to reset
> +		 */
> +		intel_engine_mask_t reset_fail_mask;
>   	} submission_state;
>   
>   	/**
> 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 3918f1be114fa..9a3f503d201aa 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -1731,6 +1731,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc)
>   }
>   
>   static void destroyed_worker_func(struct work_struct *w);
> +static void reset_fail_worker_func(struct work_struct *w);
>   
>   /*
>    * Set up the memory resources to be shared with the GuC (via the GGTT)
> @@ -1761,6 +1762,8 @@ int intel_guc_submission_init(struct intel_guc *guc)
>   	INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts);
>   	INIT_WORK(&guc->submission_state.destroyed_worker,
>   		  destroyed_worker_func);
> +	INIT_WORK(&guc->submission_state.reset_fail_worker,
> +		  reset_fail_worker_func);
>   
>   	guc->submission_state.guc_ids_bitmap =
>   		bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL);
> @@ -4026,6 +4029,26 @@ guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
>   	return gt->engine_class[engine_class][instance];
>   }
>   
> +static void reset_fail_worker_func(struct work_struct *w)
> +{
> +	struct intel_guc *guc = container_of(w, struct intel_guc,
> +					     submission_state.reset_fail_worker);
> +	struct intel_gt *gt = guc_to_gt(guc);
> +	intel_engine_mask_t reset_fail_mask;
> +	unsigned long flags;
> +
> +	spin_lock_irqsave(&guc->submission_state.lock, flags);
> +	reset_fail_mask = guc->submission_state.reset_fail_mask;
> +	guc->submission_state.reset_fail_mask = 0;
> +	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
> +
> +	if (likely(reset_fail_mask))
> +		intel_gt_handle_error(gt, reset_fail_mask,
> +				      I915_ERROR_CAPTURE,
> +				      "GuC failed to reset engine mask=0x%x\n",
> +				      reset_fail_mask);
> +}
> +
>   int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
>   					 const u32 *msg, u32 len)
>   {
> @@ -4033,6 +4056,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
>   	struct intel_gt *gt = guc_to_gt(guc);
>   	u8 guc_class, instance;
>   	u32 reason;
> +	unsigned long flags;
>   
>   	if (unlikely(len != 3)) {
>   		drm_err(&gt->i915->drm, "Invalid length %u", len);
> @@ -4057,10 +4081,15 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
>   	drm_err(&gt->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X",
>   		guc_class, instance, engine->name, reason);
>   
> -	intel_gt_handle_error(gt, engine->mask,
> -			      I915_ERROR_CAPTURE,
> -			      "GuC failed to reset %s (reason=0x%08x)\n",
> -			      engine->name, reason);
> +	spin_lock_irqsave(&guc->submission_state.lock, flags);
> +	guc->submission_state.reset_fail_mask |= engine->mask;
> +	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
> +
> +	/*
> +	 * A GT reset flushes this worker queue (G2H handler) so we must use
> +	 * another worker to trigger a GT reset.
> +	 */
> +	queue_work(system_unbound_wq, &guc->submission_state.reset_fail_worker);
>   
>   	return 0;
>   }