drm/sched: Store the drm client_id in drm_sched_fence

This will be used in a later commit to trace the drm client_id in
some of the gpu_scheduler trace events.

This requires changing all the users of drm_sched_job_init to
add an extra parameter.

The newly added drm_client_id field in the drm_sched_fence is a bit
of a duplicate of the owner one. One suggestion I received was to
merge those 2 fields - this can't be done right now as amdgpu uses
some special values (AMDGPU_FENCE_OWNER_*) that can't really be
translated into a client id. Christian is working on getting rid of
those; when it's done we should be able to squash owner/drm_client_id
together.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250526125505.2360-3-pierre-eric.pelloux-prayer@amd.com

drivers/accel/amdxdna/aie2_ctx.c

@@ -848,7 +848,8 @@ int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
 		goto up_sem;
 	}
 
-	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx);
+	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx,
+				 hwctx->client->filp->client_id);
 	if (ret) {
 		XDNA_ERR(xdna, "DRM job init failed, ret %d", ret);
 		goto free_chain;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -639,7 +639,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev,
 		goto err;
 	}
 
-	ret = amdgpu_job_alloc(adev, NULL, NULL, NULL, 1, &job);
+	ret = amdgpu_job_alloc(adev, NULL, NULL, NULL, 1, &job, 0);
 	if (ret)
 		goto err;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -293,7 +293,8 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 
 	for (i = 0; i < p->gang_size; ++i) {
 		ret = amdgpu_job_alloc(p->adev, vm, p->entities[i], vm,
-				       num_ibs[i], &p->jobs[i]);
+				       num_ibs[i], &p->jobs[i],
+				       p->filp->client_id);
 		if (ret)
 			goto free_all_kdata;
 		p->jobs[i]->enforce_isolation = p->adev->enforce_isolation[fpriv->xcp_id];

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

@@ -204,7 +204,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		     struct drm_sched_entity *entity, void *owner,
-		     unsigned int num_ibs, struct amdgpu_job **job)
+		     unsigned int num_ibs, struct amdgpu_job **job,
+		     u64 drm_client_id)
 {
 	if (num_ibs == 0)
 		return -EINVAL;
@@ -222,7 +223,8 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (!entity)
 		return 0;
 
-	return drm_sched_job_init(&(*job)->base, entity, 1, owner);
+	return drm_sched_job_init(&(*job)->base, entity, 1, owner,
+				  drm_client_id);
 }
 
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev,
@@ -232,7 +234,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev,
 {
 	int r;
 
-	r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job);
+	r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job, 0);
 	if (r)
 		return r;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_job.h

@@ -90,7 +90,8 @@ static inline struct amdgpu_ring *amdgpu_job_ring(struct amdgpu_job *job)
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		     struct drm_sched_entity *entity, void *owner,
-		     unsigned int num_ibs, struct amdgpu_job **job);
+		     unsigned int num_ibs, struct amdgpu_job **job,
+		     u64 drm_client_id);
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev,
 			     struct drm_sched_entity *entity, void *owner,
 			     size_t size, enum amdgpu_ib_pool_type pool_type,

drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c

@@ -534,7 +534,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	ret = drm_sched_job_init(&submit->sched_job,
 				 &ctx->sched_entity[args->pipe],
-				 1, submit->ctx);
+				 1, submit->ctx, file->client_id);
 	if (ret)
 		goto err_submit_put;
 

drivers/gpu/drm/imagination/pvr_job.c

@@ -446,7 +446,7 @@ create_job(struct pvr_device *pvr_dev,
 	if (err)
 		goto err_put_job;
 
-	err = pvr_queue_job_init(job);
+	err = pvr_queue_job_init(job, pvr_file->file->client_id);
 	if (err)
 		goto err_put_job;
 

drivers/gpu/drm/imagination/pvr_queue.c

@@ -1073,6 +1073,7 @@ static int pvr_queue_cleanup_fw_context(struct pvr_queue *queue)
 /**
  * pvr_queue_job_init() - Initialize queue related fields in a pvr_job object.
  * @job: The job to initialize.
+ * @drm_client_id: drm_file.client_id submitting the job
  *
  * Bind the job to a queue and allocate memory to guarantee pvr_queue_job_arm()
  * and pvr_queue_job_push() can't fail. We also make sure the context type is
@@ -1082,7 +1083,7 @@ static int pvr_queue_cleanup_fw_context(struct pvr_queue *queue)
  *  * 0 on success, or
  *  * An error code if something failed.
  */
-int pvr_queue_job_init(struct pvr_job *job)
+int pvr_queue_job_init(struct pvr_job *job, u64 drm_client_id)
 {
 	/* Fragment jobs need at least one native fence wait on the geometry job fence. */
 	u32 min_native_dep_count = job->type == DRM_PVR_JOB_TYPE_FRAGMENT ? 1 : 0;
@@ -1099,7 +1100,7 @@ int pvr_queue_job_init(struct pvr_job *job)
 	if (!pvr_cccb_cmdseq_can_fit(&queue->cccb, job_cmds_size(job, min_native_dep_count)))
 		return -E2BIG;
 
-	err = drm_sched_job_init(&job->base, &queue->entity, 1, THIS_MODULE);
+	err = drm_sched_job_init(&job->base, &queue->entity, 1, THIS_MODULE, drm_client_id);
 	if (err)
 		return err;
 

drivers/gpu/drm/imagination/pvr_queue.h

@@ -143,7 +143,7 @@ struct pvr_queue {
 
 bool pvr_queue_fence_is_ufo_backed(struct dma_fence *f);
 
-int pvr_queue_job_init(struct pvr_job *job);
+int pvr_queue_job_init(struct pvr_job *job, u64 drm_client_id);
 
 void pvr_queue_job_cleanup(struct pvr_job *job);
 

drivers/gpu/drm/lima/lima_gem.c

@@ -341,7 +341,7 @@ int lima_gem_submit(struct drm_file *file, struct lima_submit *submit)
 
 	err = lima_sched_task_init(
 		submit->task, submit->ctx->context + submit->pipe,
-		bos, submit->nr_bos, vm);
+		bos, submit->nr_bos, vm, file->client_id);
 	if (err)
 		goto err_out1;
 

drivers/gpu/drm/lima/lima_sched.c

@@ -113,7 +113,8 @@ static inline struct lima_sched_pipe *to_lima_pipe(struct drm_gpu_scheduler *sch
 int lima_sched_task_init(struct lima_sched_task *task,
 			 struct lima_sched_context *context,
 			 struct lima_bo **bos, int num_bos,
-			 struct lima_vm *vm)
+			 struct lima_vm *vm,
+			 u64 drm_client_id)
 {
 	int err, i;
 
@@ -124,7 +125,8 @@ int lima_sched_task_init(struct lima_sched_task *task,
 	for (i = 0; i < num_bos; i++)
 		drm_gem_object_get(&bos[i]->base.base);
 
-	err = drm_sched_job_init(&task->base, &context->base, 1, vm);
+	err = drm_sched_job_init(&task->base, &context->base, 1, vm,
+				 drm_client_id);
 	if (err) {
 		kfree(task->bos);
 		return err;

drivers/gpu/drm/lima/lima_sched.h

@@ -88,7 +88,8 @@ struct lima_sched_pipe {
 int lima_sched_task_init(struct lima_sched_task *task,
 			 struct lima_sched_context *context,
 			 struct lima_bo **bos, int num_bos,
-			 struct lima_vm *vm);
+			 struct lima_vm *vm,
+			 u64 drm_client_id);
 void lima_sched_task_fini(struct lima_sched_task *task);
 
 int lima_sched_context_init(struct lima_sched_pipe *pipe,

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -30,7 +30,7 @@
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gpu *gpu,
 		struct msm_gpu_submitqueue *queue, uint32_t nr_bos,
-		uint32_t nr_cmds)
+		uint32_t nr_cmds, u64 drm_client_id)
 {
 	static atomic_t ident = ATOMIC_INIT(0);
 	struct msm_gem_submit *submit;
@@ -54,7 +54,8 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
-	ret = drm_sched_job_init(&submit->base, queue->entity, 1, queue);
+	ret = drm_sched_job_init(&submit->base, queue->entity, 1, queue,
+				 drm_client_id);
 	if (ret) {
 		kfree(submit->hw_fence);
 		kfree(submit);
@@ -693,7 +694,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		}
 	}
 
-	submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds);
+	submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds,
+			       file->client_id);
 	if (IS_ERR(submit)) {
 		ret = PTR_ERR(submit);
 		goto out_post_unlock;

drivers/gpu/drm/nouveau/nouveau_sched.c

@@ -87,7 +87,8 @@ nouveau_job_init(struct nouveau_job *job,
 	}
 
 	ret = drm_sched_job_init(&job->base, &sched->entity,
-				 args->credits, NULL);
+				 args->credits, NULL,
+				 job->file_priv->client_id);
 	if (ret)
 		goto err_free_chains;
 

drivers/gpu/drm/panfrost/panfrost_drv.c

@@ -312,7 +312,7 @@ static int panfrost_ioctl_submit(struct drm_device *dev, void *data,
 
 	ret = drm_sched_job_init(&job->base,
 				 &file_priv->sched_entity[slot],
-				 1, NULL);
+				 1, NULL, file->client_id);
 	if (ret)
 		goto out_put_job;
 

drivers/gpu/drm/panthor/panthor_drv.c

@@ -996,7 +996,8 @@ static int panthor_ioctl_group_submit(struct drm_device *ddev, void *data,
 		const struct drm_panthor_queue_submit *qsubmit = &jobs_args[i];
 		struct drm_sched_job *job;
 
-		job = panthor_job_create(pfile, args->group_handle, qsubmit);
+		job = panthor_job_create(pfile, args->group_handle, qsubmit,
+					 file->client_id);
 		if (IS_ERR(job)) {
 			ret = PTR_ERR(job);
 			goto out_cleanup_submit_ctx;

drivers/gpu/drm/panthor/panthor_mmu.c

@@ -2523,7 +2523,7 @@ panthor_vm_bind_job_create(struct drm_file *file,
 	kref_init(&job->refcount);
 	job->vm = panthor_vm_get(vm);
 
-	ret = drm_sched_job_init(&job->base, &vm->entity, 1, vm);
+	ret = drm_sched_job_init(&job->base, &vm->entity, 1, vm, file->client_id);
 	if (ret)
 		goto err_put_job;
 

drivers/gpu/drm/panthor/panthor_sched.c

@@ -3732,7 +3732,8 @@ struct panthor_vm *panthor_job_vm(struct drm_sched_job *sched_job)
 struct drm_sched_job *
 panthor_job_create(struct panthor_file *pfile,
 		   u16 group_handle,
-		   const struct drm_panthor_queue_submit *qsubmit)
+		   const struct drm_panthor_queue_submit *qsubmit,
+		   u64 drm_client_id)
 {
 	struct panthor_group_pool *gpool = pfile->groups;
 	struct panthor_job *job;
@@ -3804,7 +3805,7 @@ panthor_job_create(struct panthor_file *pfile,
 
 	ret = drm_sched_job_init(&job->base,
 				 &job->group->queues[job->queue_idx]->entity,
-				 credits, job->group);
+				 credits, job->group, drm_client_id);
 	if (ret)
 		goto err_put_job;
 

drivers/gpu/drm/panthor/panthor_sched.h

@@ -29,7 +29,8 @@ int panthor_group_get_state(struct panthor_file *pfile,
 struct drm_sched_job *
 panthor_job_create(struct panthor_file *pfile,
 		   u16 group_handle,
-		   const struct drm_panthor_queue_submit *qsubmit);
+		   const struct drm_panthor_queue_submit *qsubmit,
+		   u64 drm_client_id);
 struct drm_sched_job *panthor_job_get(struct drm_sched_job *job);
 struct panthor_vm *panthor_job_vm(struct drm_sched_job *sched_job);
 void panthor_job_put(struct drm_sched_job *job);

drivers/gpu/drm/scheduler/sched_fence.c

@@ -205,7 +205,8 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
 EXPORT_SYMBOL(to_drm_sched_fence);
 
 struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
-					      void *owner)
+					      void *owner,
+					      u64 drm_client_id)
 {
 	struct drm_sched_fence *fence = NULL;
 
@@ -214,6 +215,7 @@ struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
 		return NULL;
 
 	fence->owner = owner;
+	fence->drm_client_id = drm_client_id;
 	spin_lock_init(&fence->lock);
 
 	return fence;

drivers/gpu/drm/scheduler/sched_internal.h

@@ -24,7 +24,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity);
 struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity);
 
 struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *s_entity,
-					      void *owner);
+					      void *owner, u64 drm_client_id);
 void drm_sched_fence_init(struct drm_sched_fence *fence,
 			  struct drm_sched_entity *entity);
 void drm_sched_fence_free(struct drm_sched_fence *fence);

drivers/gpu/drm/scheduler/sched_main.c

@@ -766,6 +766,8 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs);
  * @credits: the number of credits this job contributes to the schedulers
  * credit limit
  * @owner: job owner for debugging
+ * @drm_client_id: &struct drm_file.client_id of the owner (used by trace
+ * events)
  *
  * Refer to drm_sched_entity_push_job() documentation
  * for locking considerations.
@@ -786,7 +788,8 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs);
  */
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
-		       u32 credits, void *owner)
+		       u32 credits, void *owner,
+		       uint64_t drm_client_id)
 {
 	if (!entity->rq) {
 		/* This will most likely be followed by missing frames
@@ -812,7 +815,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
 
 	job->entity = entity;
 	job->credits = credits;
-	job->s_fence = drm_sched_fence_alloc(entity, owner);
+	job->s_fence = drm_sched_fence_alloc(entity, owner, drm_client_id);
 	if (!job->s_fence)
 		return -ENOMEM;
 

drivers/gpu/drm/scheduler/tests/mock_scheduler.c

@@ -117,7 +117,8 @@ drm_mock_sched_job_new(struct kunit *test,
 	ret = drm_sched_job_init(&job->base,
 				 &entity->base,
 				 1,
-				 NULL);
+				 NULL,
+				 1);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	job->test = test;

drivers/gpu/drm/v3d/v3d_submit.c

@@ -169,7 +169,7 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
 	job->file = file_priv;
 
 	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
-				 1, v3d_priv);
+				 1, v3d_priv, file_priv->client_id);
 	if (ret)
 		return ret;
 

drivers/gpu/drm/xe/xe_sched_job.c

@@ -113,7 +113,8 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
 	kref_init(&job->refcount);
 	xe_exec_queue_get(job->q);
 
-	err = drm_sched_job_init(&job->drm, q->entity, 1, NULL);
+	err = drm_sched_job_init(&job->drm, q->entity, 1, NULL,
+				 q->xef->drm->client_id);
 	if (err)
 		goto err_free;
 

include/drm/gpu_scheduler.h

@@ -305,6 +305,13 @@ struct drm_sched_fence {
          * @owner: job owner for debugging
          */
 	void				*owner;
+
+	/**
+	 * @drm_client_id:
+	 *
+	 * The client_id of the drm_file which owns the job.
+	 */
+	uint64_t			drm_client_id;
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
@@ -629,7 +636,8 @@ drm_sched_pick_best(struct drm_gpu_scheduler **sched_list,
 
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
-		       u32 credits, void *owner);
+		       u32 credits, void *owner,
+		       u64 drm_client_id);
 void drm_sched_job_arm(struct drm_sched_job *job);
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job);
 int drm_sched_job_add_dependency(struct drm_sched_job *job,