Re: [RFC 4/8] drm/xe: Convert to per gt scheduler workers

[Matthew Brost <matthew.brost@intel.com>]

On Thu, Jul 02, 2026 at 03:37:41PM +0100, Tvrtko Ursulin wrote:
> As the submission side of xe is serialized by the global GuC CT lock, we
> can easily afford to create our own per gt work queues. Whereas before
> kernel could create up to the number of CPUs threads, we now create one
> per GT.
> 

This breaks down for any execution queue that waits in a scheduler work
item for any reason. Long-running preemption queues do this for
time-slicing, multi-queue registration, and possibly a few other cases.

I've looked at this before and rough divide is this works for 3D but not
long running.

Matt

> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt.c         |  7 +++++++
>  drivers/gpu/drm/xe/xe_gt_types.h   |  3 +++
>  drivers/gpu/drm/xe/xe_guc_submit.c | 11 +++++++----
>  3 files changed, 17 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index 783eb6d631b5..fb2db9eff341 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -706,6 +706,8 @@ static void xe_gt_fini(void *arg)
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
>  		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
>  
> +	destroy_workqueue(gt->submit_wq);
> +
>  	xe_gt_disable_host_l2_vram(gt);
>  }
>  
> @@ -716,6 +718,11 @@ int xe_gt_init(struct xe_gt *gt)
>  
>  	INIT_WORK(&gt->reset.worker, gt_reset_worker);
>  
> +	gt->submit_wq = alloc_ordered_workqueue("xe-submit-gt%u",
> +						WQ_MEM_RECLAIM, gt->info.id);
> +	if (IS_ERR(gt->submit_wq))
> +		return PTR_ERR(gt->submit_wq);
> +
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i) {
>  		gt->ring_ops[i] = xe_ring_ops_get(gt, i);
>  		xe_hw_fence_irq_init(&gt->fence_irq[i]);
> diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
> index e5588c88800a..175c42672546 100644
> --- a/drivers/gpu/drm/xe/xe_gt_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_types.h
> @@ -248,6 +248,9 @@ struct xe_gt {
>  	/** @exec_queue_ops: submission backend exec queue operations */
>  	const struct xe_exec_queue_ops *exec_queue_ops;
>  
> +	/** @submit_wq: ... */
> +	struct workqueue_struct *submit_wq;
> +
>  	/**
>  	 * @ring_ops: ring operations for this hw engine (1 per engine class)
>  	 */
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 9458bf477fa6..858f84dc8fed 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1928,11 +1928,12 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
>  	struct xe_gpu_scheduler *sched;
>  	struct xe_guc *guc = exec_queue_to_guc(q);
>  	struct workqueue_struct *submit_wq = NULL;
> +	struct xe_gt *gt = guc_to_gt(guc);
>  	struct xe_guc_exec_queue *ge;
>  	long timeout;
>  	int err, i;
>  
> -	xe_gt_assert(guc_to_gt(guc), xe_device_uc_enabled(guc_to_xe(guc)));
> +	xe_gt_assert(gt, xe_device_uc_enabled(guc_to_xe(guc)));
>  
>  	ge = kzalloc_obj(*ge);
>  	if (!ge)
> @@ -1964,12 +1965,14 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
>  		struct xe_exec_queue *primary = xe_exec_queue_multi_queue_primary(q);
>  
>  		submit_wq = primary->guc->sched.base.submit_wq;
> +	} else {
> +		submit_wq = gt->submit_wq;
>  	}
>  
>  	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
> -			    submit_wq, xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES, 64,
> -			    timeout, guc_to_gt(guc)->ordered_wq, NULL,
> -			    q->name, gt_to_xe(q->gt)->drm.dev);
> +			    submit_wq, xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES,
> +			    64, timeout, gt->ordered_wq, NULL, q->name,
> +			    gt_to_xe(gt)->drm.dev);
>  	if (err)
>  		goto err_release_id;
>  
> -- 
> 2.54.0
>