[PATCH 6.12 311/337] drm/sched: Store the drm client_id in drm_sched_fence
Greg Kroah-Hartman <[email protected]>
| Newsgroups | org.kernel.vger.stable,dev.linux.lists.patches |
|---|---|
| Message-ID | <[email protected]> |
6.12-stable review patch. If anyone has any objections, please let me know. ------------------ From: Pierre-Eric Pelloux-Prayer <[email protected]> [ Upstream commit 2956554823cedb390b7ec4534afa898176317638 ] 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 <[email protected]> Signed-off-by: Pierre-Eric Pelloux-Prayer <[email protected]> Signed-off-by: Philipp Stanner <[email protected]> Link: https://lore.kernel.org/r/[email protected] Stable-dep-of: 3e864bf2a32a ("drm/amdgpu/gfx: fix cleaner shader IB buffer overflow") Signed-off-by: Sasha Levin <[email protected]> Signed-off-by: Greg Kroah-Hartman <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 8 +++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 3 ++- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 2 +- drivers/gpu/drm/imagination/pvr_job.c | 2 +- drivers/gpu/drm/imagination/pvr_queue.c | 5 +++-- drivers/gpu/drm/imagination/pvr_queue.h | 2 +- drivers/gpu/drm/lima/lima_gem.c | 2 +- drivers/gpu/drm/lima/lima_sched.c | 6 ++++-- drivers/gpu/drm/lima/lima_sched.h | 3 ++- drivers/gpu/drm/msm/msm_gem_submit.c | 8 +++++--- drivers/gpu/drm/nouveau/nouveau_sched.c | 3 ++- drivers/gpu/drm/panfrost/panfrost_drv.c | 2 +- drivers/gpu/drm/panthor/panthor_drv.c | 3 ++- drivers/gpu/drm/panthor/panthor_mmu.c | 2 +- drivers/gpu/drm/panthor/panthor_sched.c | 5 +++-- drivers/gpu/drm/panthor/panthor_sched.h | 3 ++- drivers/gpu/drm/scheduler/sched_fence.c | 4 +++- drivers/gpu/drm/scheduler/sched_main.c | 7 +++++-- drivers/gpu/drm/v3d/v3d_submit.c | 2 +- drivers/gpu/drm/xe/xe_sched_job.c | 3 ++- include/drm/gpu_scheduler.h | 12 ++++++++++-- 23 files changed, 60 insertions(+), 32 deletions(-) --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -681,7 +681,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgp 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; --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -297,7 +297,8 @@ static int amdgpu_cs_pass1(struct amdgpu 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]; --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -187,7 +187,8 @@ exit: 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; @@ -210,7 +211,8 @@ int amdgpu_job_alloc(struct amdgpu_devic 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, @@ -220,7 +222,7 @@ int amdgpu_job_alloc_with_ib(struct amdg { 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; --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -90,7 +90,8 @@ static inline struct amdgpu_ring *amdgpu 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, --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -535,7 +535,7 @@ int etnaviv_ioctl_gem_submit(struct drm_ 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; --- a/drivers/gpu/drm/imagination/pvr_job.c +++ b/drivers/gpu/drm/imagination/pvr_job.c @@ -453,7 +453,7 @@ 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; --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -1088,6 +1088,7 @@ static int pvr_queue_cleanup_fw_context( /** * 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 @@ -1097,7 +1098,7 @@ static int pvr_queue_cleanup_fw_context( * * 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; @@ -1114,7 +1115,7 @@ int pvr_queue_job_init(struct pvr_job *j 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; --- a/drivers/gpu/drm/imagination/pvr_queue.h +++ b/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); --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -341,7 +341,7 @@ int lima_gem_submit(struct drm_file *fil 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; --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -113,7 +113,8 @@ static inline struct lima_sched_pipe *to 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_sch 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; --- a/drivers/gpu/drm/lima/lima_sched.h +++ b/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, --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/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_cre 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); @@ -712,7 +713,8 @@ int msm_ioctl_gem_submit(struct drm_devi } } - 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; --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/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; --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -273,7 +273,7 @@ static int panfrost_ioctl_submit(struct 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; --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -908,7 +908,8 @@ static int panthor_ioctl_group_submit(st 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; --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -2498,7 +2498,7 @@ panthor_vm_bind_job_create(struct drm_fi 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; --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -3664,7 +3664,8 @@ struct panthor_vm *panthor_job_vm(struct 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; @@ -3736,7 +3737,7 @@ panthor_job_create(struct panthor_file * 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; --- a/drivers/gpu/drm/panthor/panthor_sched.h +++ b/drivers/gpu/drm/panthor/panthor_sched.h @@ -28,7 +28,8 @@ int panthor_group_get_state(struct panth 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); --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -204,7 +204,8 @@ struct drm_sched_fence *to_drm_sched_fen 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; @@ -213,6 +214,7 @@ struct drm_sched_fence *drm_sched_fence_ return NULL; fence->owner = owner; + fence->drm_client_id = drm_client_id; spin_lock_init(&fence->lock); return fence; --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -772,6 +772,8 @@ 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. @@ -788,7 +790,8 @@ 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 @@ -814,7 +817,7 @@ int drm_sched_job_init(struct drm_sched_ 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; --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -186,7 +186,7 @@ v3d_job_init(struct v3d_dev *v3d, struct 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; --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -113,7 +113,8 @@ struct xe_sched_job *xe_sched_job_create 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 ? q->xef->drm->client_id : 0); if (err) goto err_free; --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -309,6 +309,13 @@ 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); @@ -553,7 +560,8 @@ int drm_sched_init(struct drm_gpu_schedu void drm_sched_fini(struct drm_gpu_scheduler *sched); 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); int drm_sched_job_add_dependency(struct drm_sched_job *job, struct dma_fence *fence); @@ -613,7 +621,7 @@ bool drm_sched_entity_is_ready(struct dr int drm_sched_entity_error(struct drm_sched_entity *entity); struct drm_sched_fence *drm_sched_fence_alloc( - struct drm_sched_entity *s_entity, void *owner); + struct drm_sched_entity *s_entity, 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);