Re: [PATCH v6 07/24] drm/xe: Update scheduler job layer to support PT jobs

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

On Fri, Sep 11, 2026 at 05:24:23PM +0200, Francois Dugast wrote:
> On Fri, Sep 04, 2026 at 02:15:56PM -0700, Matthew Brost wrote:
> > Update the scheduler job layer to support PT jobs. PT jobs are executed
> > entirely on the CPU and do not require LRC fences or a batch address.
> > Repurpose the LRC fence storage to hold PT‑job arguments and update the
> > scheduler job layer to distinguish between PT jobs and jobs that require
> > an LRC.
> > 
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > Link: https://patch.msgid.link/20260228013501.106680-8-matthew.brost@intel.com
> > Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
> > ---
> >  drivers/gpu/drm/xe/xe_sched_job.c       | 95 ++++++++++++++++---------
> >  drivers/gpu/drm/xe/xe_sched_job_types.h | 31 +++++++-
> >  drivers/gpu/drm/xe/xe_trace.h           |  2 +-
> >  3 files changed, 92 insertions(+), 36 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
> > index a4fa00632a30..841d67ebd5b0 100644
> > --- a/drivers/gpu/drm/xe/xe_sched_job.c
> > +++ b/drivers/gpu/drm/xe/xe_sched_job.c
> > @@ -26,19 +26,22 @@ static struct kmem_cache *xe_sched_job_parallel_slab;
> >  
> >  int __init xe_sched_job_module_init(void)
> >  {
> > +	struct xe_sched_job *job;
> > +	size_t size;
> > +
> > +	size = struct_size(job, ptrs, 1);
> >  	xe_sched_job_slab =
> > -		kmem_cache_create("xe_sched_job",
> > -				  sizeof(struct xe_sched_job) +
> > -				  sizeof(struct xe_job_ptrs), 0,
> > +		kmem_cache_create("xe_sched_job", size, 0,
> >  				  SLAB_HWCACHE_ALIGN, NULL);
> >  	if (!xe_sched_job_slab)
> >  		return -ENOMEM;
> >  
> > +	size = max_t(size_t,
> > +		     struct_size(job, ptrs,
> > +				 XE_HW_ENGINE_MAX_INSTANCE),
> > +		     struct_size(job, pt_update, 1));
> >  	xe_sched_job_parallel_slab =
> > -		kmem_cache_create("xe_sched_job_parallel",
> > -				  sizeof(struct xe_sched_job) +
> > -				  sizeof(struct xe_job_ptrs) *
> > -				  XE_HW_ENGINE_MAX_INSTANCE, 0,
> > +		kmem_cache_create("xe_sched_job_parallel", size, 0,
> >  				  SLAB_HWCACHE_ALIGN, NULL);
> >  	if (!xe_sched_job_parallel_slab) {
> >  		kmem_cache_destroy(xe_sched_job_slab);
> > @@ -84,6 +87,9 @@ static void xe_sched_job_free_fences(struct xe_sched_job *job)
> >  {
> >  	int i;
> >  
> > +	if (job->is_pt_job)
> > +		return;
> > +
> >  	for (i = 0; i < job->q->width; ++i) {
> >  		struct xe_job_ptrs *ptrs = &job->ptrs[i];
> >  
> > @@ -93,10 +99,23 @@ static void xe_sched_job_free_fences(struct xe_sched_job *job)
> >  	}
> >  }
> >  
> > +/**
> > + * xe_sched_job_create() - Create a scheduler job
> > + * @q: exec queue to create the scheduler job for
> > + * @batch_addr: array of batch addresses for the job; must match the width of
> > + * @q, or NULL to indicate a PT job that does not require a batch address
> > + *
> > + * Create a scheduler job for submission.
> > + *
> > + * Context: Reclaim
> > + *
> > + * Return: a &xe_sched_job object on success, or an ERR_PTR on failure.
> > + */
> >  struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
> >  					 u64 *batch_addr)
> >  {
> >  	bool is_migration = xe_sched_job_is_migration(q);
> > +	struct xe_device *xe = gt_to_xe(q->gt);
> >  	struct xe_sched_job *job;
> >  	int err;
> >  	int i;
> > @@ -105,6 +124,9 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
> >  	/* only a kernel context can submit a vm-less job */
> >  	XE_WARN_ON(!q->vm && !(q->flags & EXEC_QUEUE_FLAG_KERNEL));
> >  
> > +	xe_assert(xe, batch_addr ||
> > +		  q->flags & (EXEC_QUEUE_FLAG_VM | EXEC_QUEUE_FLAG_MIGRATE));
> > +
> >  	job = job_alloc(xe_exec_queue_is_parallel(q) || is_migration);
> >  	if (!job)
> >  		return ERR_PTR(-ENOMEM);
> > @@ -119,34 +141,39 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
> >  	if (err)
> >  		goto err_free;
> >  
> > -	for (i = 0; i < q->width; ++i) {
> > -		struct dma_fence *fence = xe_lrc_alloc_seqno_fence();
> > -		struct dma_fence_chain *chain;
> > -
> > -		if (IS_ERR(fence)) {
> > -			err = PTR_ERR(fence);
> > -			goto err_sched_job;
> > +	if (!batch_addr) {
> > +		job->fence = dma_fence_get_stub();
> > +		job->is_pt_job = true;
> > +	} else {
> > +		for (i = 0; i < q->width; ++i) {
> > +			struct dma_fence *fence = xe_lrc_alloc_seqno_fence();
> > +			struct dma_fence_chain *chain;
> > +
> > +			if (IS_ERR(fence)) {
> > +				err = PTR_ERR(fence);
> > +				goto err_sched_job;
> > +			}
> > +			job->ptrs[i].lrc_fence = fence;
> > +
> > +			if (i + 1 == q->width)
> > +				continue;
> > +
> > +			chain = dma_fence_chain_alloc();
> > +			if (!chain) {
> > +				err = -ENOMEM;
> > +				goto err_sched_job;
> > +			}
> > +			job->ptrs[i].chain_fence = chain;
> >  		}
> > -		job->ptrs[i].lrc_fence = fence;
> >  
> > -		if (i + 1 == q->width)
> > -			continue;
> > +		width = q->width;
> > +		if (is_migration)
> > +			width = 2;
> >  
> > -		chain = dma_fence_chain_alloc();
> > -		if (!chain) {
> > -			err = -ENOMEM;
> > -			goto err_sched_job;
> > -		}
> > -		job->ptrs[i].chain_fence = chain;
> > +		for (i = 0; i < width; ++i)
> > +			job->ptrs[i].batch_addr = batch_addr[i];
> >  	}
> >  
> > -	width = q->width;
> > -	if (is_migration)
> > -		width = 2;
> > -
> > -	for (i = 0; i < width; ++i)
> > -		job->ptrs[i].batch_addr = batch_addr[i];
> > -
> >  	atomic_inc(&q->job_cnt);
> >  	xe_pm_runtime_get_noresume(job_to_xe(job));
> >  	trace_xe_sched_job_create(job);
> > @@ -246,7 +273,7 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
> >  void xe_sched_job_arm(struct xe_sched_job *job)
> >  {
> >  	struct xe_exec_queue *q = job->q;
> > -	struct dma_fence *fence, *prev;
> > +	struct dma_fence *fence = job->fence, *prev;
> >  	struct xe_vm *vm = q->vm;
> >  	u64 seqno = 0;
> >  	int i;
> > @@ -266,6 +293,9 @@ void xe_sched_job_arm(struct xe_sched_job *job)
> >  		job->ring_ops_flush_tlb = true;
> >  	}
> >  
> > +	if (job->is_pt_job)
> > +		goto arm;
> > +
> 
> I think Sashiko's warning is valid, we should move this ^ one block
> above to skip touching q->tlb_flush_seqno and ring_ops_flush_tlb for
> PT jobs.
> 

Those are completely unused for PT jobs / queues which run PT jobs so
the ordering is harmless but for clarity it would be better. Will
adjust.

Matt 

> Francois
> 
> >  	/* Arm the pre-allocated fences */
> >  	for (i = 0; i < q->width; prev = fence, ++i) {
> >  		struct dma_fence_chain *chain;
> > @@ -286,6 +316,7 @@ void xe_sched_job_arm(struct xe_sched_job *job)
> >  		fence = &chain->base;
> >  	}
> >  
> > +arm:
> >  	job->fence = dma_fence_get(fence);	/* Pairs with put in scheduler */
> >  	drm_sched_job_arm(&job->drm);
> >  }
> > @@ -329,7 +360,7 @@ xe_sched_job_snapshot_capture(struct xe_sched_job *job)
> >  
> >  	snapshot->batch_addr_len = q->width;
> >  	for (i = 0; i < q->width; i++)
> > -		snapshot->batch_addr[i] =
> > +		snapshot->batch_addr[i] = job->is_pt_job ? 0 :
> >  			xe_device_uncanonicalize_addr(xe, job->ptrs[i].batch_addr);
> >  
> >  	return snapshot;
> > diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
> > index 0490b1247a6e..5e1824c36c74 100644
> > --- a/drivers/gpu/drm/xe/xe_sched_job_types.h
> > +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
> > @@ -10,10 +10,29 @@
> >  
> >  #include <drm/gpu_scheduler.h>
> >  
> > -struct xe_exec_queue;
> >  struct dma_fence;
> >  struct dma_fence_chain;
> >  
> > +struct xe_exec_queue;
> > +struct xe_migrate_pt_update_ops;
> > +struct xe_pt_job_ops;
> > +struct xe_tile;
> > +struct xe_vm;
> > +
> > +/**
> > + * struct xe_pt_update_args - PT update arguments
> > + */
> > +struct xe_pt_update_args {
> > +	/** @vm: VM which is being bound */
> > +	struct xe_vm *vm;
> > +	/** @tile: Tile which page tables belong to */
> > +	struct xe_tile *tile;
> > +	/** @ops: Migrate PT update ops */
> > +	const struct xe_migrate_pt_update_ops *ops;
> > +	/** @pt_job_ops: PT job ops state */
> > +	struct xe_pt_job_ops *pt_job_ops;
> > +};
> > +
> >  /**
> >   * struct xe_job_ptrs - Per hw engine instance data
> >   */
> > @@ -71,8 +90,14 @@ struct xe_sched_job {
> >  	bool restore_replay;
> >  	/** @last_replay: last job being replayed */
> >  	bool last_replay;
> > -	/** @ptrs: per instance pointers. */
> > -	struct xe_job_ptrs ptrs[];
> > +	/** @is_pt_job: is a PT job */
> > +	bool is_pt_job;
> > +	union {
> > +		/** @ptrs: per instance pointers. */
> > +		DECLARE_FLEX_ARRAY(struct xe_job_ptrs, ptrs);
> > +		/** @pt_update: PT update arguments */
> > +		DECLARE_FLEX_ARRAY(struct xe_pt_update_args, pt_update);
> > +	};
> >  };
> >  
> >  struct xe_sched_job_snapshot {
> > diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
> > index 2fe8f89a1e34..d4e9d91f6f7f 100644
> > --- a/drivers/gpu/drm/xe/xe_trace.h
> > +++ b/drivers/gpu/drm/xe/xe_trace.h
> > @@ -261,7 +261,7 @@ DECLARE_EVENT_CLASS(xe_sched_job,
> >  			   __entry->flags = job->q->flags;
> >  			   __entry->error = job->fence ? job->fence->error : 0;
> >  			   __entry->fence = job->fence;
> > -			   __entry->batch_addr = (u64)job->ptrs[0].batch_addr;
> > +			   __entry->batch_addr = job->is_pt_job ? 0 : (u64)job->ptrs[0].batch_addr;
> >  			   ),
> >  
> >  		    TP_printk("dev=%s, fence=%p, seqno=%u, lrc_seqno=%u, gt=%u, guc_id=%d, batch_addr=0x%012llx, guc_state=0x%x, flags=0x%x, error=%d",
> > -- 
> > 2.34.1
> >