Re: [PATCH v5 1/5] drm/xe/gt: Use GT ordered workqueue for wedging

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Tue, Oct 13, 2026 at 04:33:53PM +0530, 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.
> 
> While at it, introduce for_each_initialized_gt() macro and use it for
> wedging GT. This helps avoid races in case the device is declared wedged
> in probe sequence before GT is initialized.
> 
> Fixes: c9474b726b93 ("drm/xe: Wedge the entire device")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>
> ---
> v2: Split fixes into separate patches (Rodrigo, Michal)
> v4: Introduce for_each_initialized_gt() (Michal)
> v5: Flush GT wedge worker to avoid races (Sashiko)
> ---
>  drivers/gpu/drm/xe/xe_device.c   |  2 +-
>  drivers/gpu/drm/xe/xe_device.h   |  4 ++++
>  drivers/gpu/drm/xe/xe_gt.c       | 18 ++++++++++++++++--
>  drivers/gpu/drm/xe/xe_gt_types.h |  9 +++++++++
>  4 files changed, 30 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index 8392c9fad3c4..22ae10958d7f 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -1432,7 +1432,7 @@ void xe_device_declare_wedged(struct xe_device *xe)
>  			    WEDGED_URL, XE_BUG_URL);
>  	}
>  
> -	for_each_gt(gt, xe, id)
> +	for_each_initialized_gt(gt, xe, id)
>  		xe_gt_declare_wedged(gt);
>  
>  	if (xe_device_wedged(xe)) {
> diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
> index 83d6dafab53c..80bda9b548d5 100644
> --- a/drivers/gpu/drm/xe/xe_device.h
> +++ b/drivers/gpu/drm/xe/xe_device.h
> @@ -139,6 +139,10 @@ static inline bool xe_device_uc_enabled(struct xe_device *xe)
>  	for_each_gt((gt__), (tile__)->xe, (id__)) \
>  		for_each_if((gt__)->tile == (tile__))
>  
> +#define for_each_initialized_gt(gt__, xe__, id__) \
> +	for_each_gt((gt__), (xe__), (id__)) \
> +		for_each_if(READ_ONCE((gt__)->initialized))
> +
>  static inline struct xe_force_wake *gt_to_fw(struct xe_gt *gt)
>  {
>  	return &gt->pm.fw;
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index 775c826b68b4..4e047cfaf603 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -175,6 +175,7 @@ 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)
> @@ -706,6 +707,8 @@ 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
> @@ -725,6 +728,7 @@ 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);

perhaps this should be in the gt_alloc or some init early?

>  
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i) {
>  		gt->ring_ops[i] = xe_ring_ops_get(gt, i);
> @@ -769,6 +773,8 @@ int xe_gt_init(struct xe_gt *gt)
>  			return err;
>  	}
>  
> +	/* Must be last */
> +	WRITE_ONCE(gt->initialized, true);
>  	return 0;
>  }
>  
> @@ -1010,6 +1016,14 @@ 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);
> @@ -1200,6 +1214,6 @@ 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);
> +	queue_work(gt->ordered_wq, &gt->wedge.worker);
> +	flush_work(&gt->wedge.worker);

This flush serialize things, but apparently it deadlock somewhere else now.
Perhaps we should avoid this one here and instead flush for each gt in
pci disable case.

>  }
> diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
> index 628911346455..c00a7c171f80 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;
>  
> @@ -419,6 +425,9 @@ struct xe_gt {
>  
>  	/** @eu_stall: EU stall counters subsystem per gt info */
>  	struct xe_eu_stall_gt *eu_stall;
> +
> +	/** @initialized: GT is initialized */
> +	bool initialized;
>  };
>  
>  #endif
> -- 
> 2.43.0
>