[PATCH 2/2] drm/xe: Fix modifying exec_queue priority in xe_migrate_init

[Matthew Brost]

On Fri, Jan 05, 2024 at 11:04:40AM -0800, Brian Welty wrote:
> After exec_queue has been created, we cannot simply modify q->priority.
> This needs to be done by the backend via q->ops.  However in this case,
> it would be more efficient to simply pass a flag when creating the
> exec_queue and set the desired priority upfront during queue creation.
> 
> To that end: new flag EXEC_QUEUE_FLAG_HIGH_PRIORITY is introduced.
> The priority field is moved to be with other scheduling properties and
> is now exec_queue.sched_props.priority. This is no longer set to initial
> value by the backend, but is now set within __xe_exec_queue_create().
> 
> Fixes: b4eecedc75c1 ("drm/xe: Fix potential deadlock handling page faults")
> Signed-off-by: Brian Welty <brian.welty at intel.com>

Reviewed-by: Matthew Brost <matthew.brost at intel.com>

> ---
>  drivers/gpu/drm/xe/xe_exec_queue.c       | 5 +++++
>  drivers/gpu/drm/xe/xe_exec_queue_types.h | 6 ++++--
>  drivers/gpu/drm/xe/xe_guc_submit.c       | 7 +++----
>  drivers/gpu/drm/xe/xe_migrate.c          | 5 ++---
>  4 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index 44fe8097b7cd..bcfc4127c7c5 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -67,6 +67,11 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
>  	q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
>  	q->sched_props.preempt_timeout_us =
>  				hwe->eclass->sched_props.preempt_timeout_us;
> +	if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
> +	    q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
> +		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
> +	else
> +		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
>  
>  	if (xe_exec_queue_is_parallel(q)) {
>  		q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> index 3d7e704ec3d9..8d4b7feb8c30 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> @@ -52,8 +52,6 @@ struct xe_exec_queue {
>  	struct xe_vm *vm;
>  	/** @class: class of this exec queue */
>  	enum xe_engine_class class;
> -	/** @priority: priority of this exec queue */
> -	enum xe_exec_queue_priority priority;
>  	/**
>  	 * @logical_mask: logical mask of where job submitted to exec queue can run
>  	 */
> @@ -84,6 +82,8 @@ struct xe_exec_queue {
>  #define EXEC_QUEUE_FLAG_VM			BIT(4)
>  /* child of VM queue for multi-tile VM jobs */
>  #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD	BIT(5)
> +/* kernel exec_queue only, set priority to highest level */
> +#define EXEC_QUEUE_FLAG_HIGH_PRIORITY		BIT(6)
>  
>  	/**
>  	 * @flags: flags for this exec queue, should statically setup aside from ban
> @@ -142,6 +142,8 @@ struct xe_exec_queue {
>  		u32 timeslice_us;
>  		/** @preempt_timeout_us: preemption timeout in micro-seconds */
>  		u32 preempt_timeout_us;
> +		/** @priority: priority of this exec queue */
> +		enum xe_exec_queue_priority priority;
>  	} sched_props;
>  
>  	/** @compute: compute exec queue state */
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 5de3ac47c462..54ffcfcdd41f 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -421,7 +421,7 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q)
>  {
>  	struct exec_queue_policy policy;
>  	struct xe_device *xe = guc_to_xe(guc);
> -	enum xe_exec_queue_priority prio = q->priority;
> +	enum xe_exec_queue_priority prio = q->sched_props.priority;
>  	u32 timeslice_us = q->sched_props.timeslice_us;
>  	u32 preempt_timeout_us = q->sched_props.preempt_timeout_us;
>  
> @@ -1231,7 +1231,6 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
>  	err = xe_sched_entity_init(&ge->entity, sched);
>  	if (err)
>  		goto err_sched;
> -	q->priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
>  
>  	if (xe_exec_queue_is_lr(q))
>  		INIT_WORK(&q->guc->lr_tdr, xe_guc_exec_queue_lr_cleanup);
> @@ -1301,14 +1300,14 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
>  {
>  	struct xe_sched_msg *msg;
>  
> -	if (q->priority == priority || exec_queue_killed_or_banned(q))
> +	if (q->sched_props.priority == priority || exec_queue_killed_or_banned(q))
>  		return 0;
>  
>  	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
>  	if (!msg)
>  		return -ENOMEM;
>  
> -	q->priority = priority;
> +	q->sched_props.priority = priority;
>  	guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
>  
>  	return 0;
> diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
> index adf1dab5eba2..02fca8f9adc2 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.c
> +++ b/drivers/gpu/drm/xe/xe_migrate.c
> @@ -344,7 +344,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
>  
>  		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
>  					    EXEC_QUEUE_FLAG_KERNEL |
> -					    EXEC_QUEUE_FLAG_PERMANENT);
> +					    EXEC_QUEUE_FLAG_PERMANENT |
> +					    EXEC_QUEUE_FLAG_HIGH_PRIORITY);
>  	} else {
>  		m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
>  						  XE_ENGINE_CLASS_COPY,
> @@ -355,8 +356,6 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
>  		xe_vm_close_and_put(vm);
>  		return ERR_CAST(m->q);
>  	}
> -	if (xe->info.has_usm)
> -		m->q->priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
>  
>  	mutex_init(&m->job_mutex);
>  
> -- 
> 2.43.0
>