Re: [PATCH v3 1/5] drm/xe/gt: Use GT ordered workqueue for wedging

[Michal Wajdeczko <michal.wajdeczko@intel.com>]

On 9/7/2026 10:34 AM, Raag Jadav wrote:
> Currently, xe_gt_declare_wedged() stops GuC CT and initiates exec queue
> teardown synchronously. This can result in tdr timeout in cases where
> the device is declared wedged while jobs are still in-flight.
> 
> Introduce a worker for GT specific wedge handling and queue the teardown
> on GT ordered workqueue, so we don't disrupt the scheduler while jobs
> are still in-flight.
> 
> Fixes: c9474b726b93 ("drm/xe: Wedge the entire device")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> ---
> v2: Split fixes into separate patches (Rodrigo, Michal)
> ---
>  drivers/gpu/drm/xe/xe_gt.c       | 17 +++++++++++++++--
>  drivers/gpu/drm/xe/xe_gt_types.h |  6 ++++++
>  2 files changed, 21 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index 478e047031f4..200e34331c19 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -173,6 +173,7 @@ static void xe_gt_enable_comp_1wcoh(struct xe_gt *gt)
>  }
>  
>  static void gt_reset_worker(struct work_struct *w);
> +static void gt_wedge_worker(struct work_struct *w);
>  
>  static int emit_job_sync(struct xe_exec_queue *q, struct xe_bb *bb,
>  			 long timeout_jiffies, bool force_reset)
> @@ -704,6 +705,8 @@ static void xe_gt_fini(void *arg)
>  	struct xe_gt *gt = arg;
>  	int i;
>  
> +	disable_work_sync(&gt->wedge.worker);
> +
>  	if (disable_work_sync(&gt->reset.worker))
>  		/*
>  		 * If gt_reset_worker was halted from executing, take care of
> @@ -723,6 +726,7 @@ int xe_gt_init(struct xe_gt *gt)
>  	int i;
>  
>  	INIT_WORK(&gt->reset.worker, gt_reset_worker);
> +	INIT_WORK(&gt->wedge.worker, gt_wedge_worker);

hmm, shouldn't this be done in xe_gt_alloc() ?

as xe_gt_init_early() seems to be doing something else and much later

>  
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i) {
>  		gt->ring_ops[i] = xe_ring_ops_get(gt, i);
> @@ -1005,6 +1009,14 @@ void xe_gt_reset_async(struct xe_gt *gt)
>  		xe_pm_runtime_put(xe);
>  }
>  
> +static void gt_wedge_worker(struct work_struct *w)
> +{
> +	struct xe_gt *gt = container_of(w, typeof(*gt), wedge.worker);
> +
> +	xe_uc_declare_wedged(&gt->uc);
> +	xe_tlb_inval_reset(&gt->tlb_inval);
> +}
> +
>  void xe_gt_suspend_prepare(struct xe_gt *gt)
>  {
>  	xe_uc_suspend_prepare(&gt->uc);
> @@ -1195,6 +1207,7 @@ void xe_gt_declare_wedged(struct xe_gt *gt)
>  {
>  	xe_gt_assert(gt, gt_to_xe(gt)->wedged.mode);
>  
> -	xe_uc_declare_wedged(&gt->uc);
> -	xe_tlb_inval_reset(&gt->tlb_inval);
> +	/* Prevent queueing uninitialized worker if hit during probe */
> +	if (gt->wedge.worker.func)
> +		queue_work(gt->ordered_wq, &gt->wedge.worker);
>  }
> diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
> index 628911346455..b11ac52b0ab7 100644
> --- a/drivers/gpu/drm/xe/xe_gt_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_types.h
> @@ -233,6 +233,12 @@ struct xe_gt {
>  		struct work_struct worker;
>  	} reset;
>  
> +	/** @wedge: state for GT wedge */
> +	struct {
> +		/** @wedge.worker: worker for GT wedge to be done async */
> +		struct work_struct worker;
> +	} wedge;
> +
>  	/** @tlb_inval: TLB invalidation state */
>  	struct xe_tlb_inval tlb_inval;
>