Re: [PATCH] drm/xe: Limit number of jobs per exec queue

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

On Mon, Oct 27, 2025 at 09:33:03AM -0700, Matthew Brost wrote:
> On Wed, Oct 22, 2025 at 06:10:37PM +0000, Shuicheng Lin wrote:
> > Add a limit to the number of jobs that can be queued in a single
> > exec queue to avoid potential resource exhaustion.
> > 
> > A new field `job_cnt` is introduced in `struct xe_exec_queue` to
> > track the number of active DRM jobs, along with a maximum limit
> > `XE_MAX_JOB_COUNT_PER_EXEC_QUEUE` set to 0x1000.
> > 
> > If the job count exceeds this threshold, `xe_exec_ioctl()` now
> > returns `-EAGAIN` to signal that the caller should retry later.
> > 
> 
> This patch looks correct. One extra suggestion - can we get an assert in
> xe_exec_queue_destroy that q->job_cnt is zero?
> 

This was sent to wrong version.

Matt

> > Suggested-by: Matthew Brost <matthew.brost@intel.com>
> > Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_exec.c             | 5 +++++
> >  drivers/gpu/drm/xe/xe_exec_queue_types.h | 5 +++++
> >  drivers/gpu/drm/xe/xe_sched_job.c        | 2 ++
> >  3 files changed, 12 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
> > index 0dc27476832b..722a5ac0200a 100644
> > --- a/drivers/gpu/drm/xe/xe_exec.c
> > +++ b/drivers/gpu/drm/xe/xe_exec.c
> > @@ -154,6 +154,11 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
> >  		goto err_exec_queue;
> >  	}
> >  
> > +	if (q->job_cnt >= XE_MAX_JOB_COUNT_PER_EXEC_QUEUE) {
> > +		err = -EAGAIN;
> > +		goto err_exec_queue;
> > +	}
> > +
> >  	if (args->num_syncs) {
> >  		syncs = kcalloc(args->num_syncs, sizeof(*syncs), GFP_KERNEL);
> >  		if (!syncs) {
> > diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > index 282505fa1377..5f3219acec3c 100644
> > --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > @@ -162,6 +162,11 @@ struct xe_exec_queue {
> >  	const struct xe_ring_ops *ring_ops;
> >  	/** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */
> >  	struct drm_sched_entity *entity;
> > +
> > +#define XE_MAX_JOB_COUNT_PER_EXEC_QUEUE	0x1000
> > +
> 
> I'd lose newline here
> 
> > +	/** @job_cnt: number of drm jobs in this exec queue */
> > +	u32 job_cnt;
> 
> And add one here.
> 
> Matt
> 
> >  	/**
> >  	 * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed
> >  	 * Protected by @vm's resv. Unused if @vm == NULL.
> > diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
> > index d21bf8f26964..37f58be7cbcc 100644
> > --- a/drivers/gpu/drm/xe/xe_sched_job.c
> > +++ b/drivers/gpu/drm/xe/xe_sched_job.c
> > @@ -146,6 +146,7 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
> >  	for (i = 0; i < width; ++i)
> >  		job->ptrs[i].batch_addr = batch_addr[i];
> >  
> > +	q->job_cnt++;
> >  	xe_pm_runtime_get_noresume(job_to_xe(job));
> >  	trace_xe_sched_job_create(job);
> >  	return job;
> > @@ -177,6 +178,7 @@ void xe_sched_job_destroy(struct kref *ref)
> >  	dma_fence_put(job->fence);
> >  	drm_sched_job_cleanup(&job->drm);
> >  	job_free(job);
> > +	q->job_cnt--;
> >  	xe_exec_queue_put(q);
> >  	xe_pm_runtime_put(xe);
> >  }
> > -- 
> > 2.49.0
> >