diff options
Diffstat (limited to 'include/drm/gpu_scheduler.h')
| -rw-r--r-- | include/drm/gpu_scheduler.h | 150 |
1 files changed, 109 insertions, 41 deletions
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 50928a7ae98e..323a505e6e6a 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -192,7 +192,7 @@ struct drm_sched_entity { * @last_scheduled: * * Points to the finished fence of the last scheduled job. Only written - * by the scheduler thread, can be accessed locklessly from + * by drm_sched_entity_pop_job(). Can be accessed locklessly from * drm_sched_job_arm() if the queue is empty. */ struct dma_fence __rcu *last_scheduled; @@ -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); @@ -319,7 +326,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * @finish_cb: the callback for the finished fence. * @credits: the number of credits this job contributes to the scheduler * @work: Helper to reschedule job kill to different context. - * @id: a unique id assigned to each job scheduled on the scheduler. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not * be scheduled further. @@ -332,8 +338,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * to schedule the job. */ struct drm_sched_job { - u64 id; - /** * @submit_ts: * @@ -383,10 +387,20 @@ struct drm_sched_job { struct xarray dependencies; }; +/** + * enum drm_gpu_sched_stat - the scheduler's status + * + * @DRM_GPU_SCHED_STAT_NONE: Reserved. Do not use. + * @DRM_GPU_SCHED_STAT_RESET: The GPU hung and successfully reset. + * @DRM_GPU_SCHED_STAT_ENODEV: Error: Device is not available anymore. + * @DRM_GPU_SCHED_STAT_NO_HANG: Contrary to scheduler's assumption, the GPU + * did not hang and is still running. + */ enum drm_gpu_sched_stat { - DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ - DRM_GPU_SCHED_STAT_NOMINAL, + DRM_GPU_SCHED_STAT_NONE, + DRM_GPU_SCHED_STAT_RESET, DRM_GPU_SCHED_STAT_ENODEV, + DRM_GPU_SCHED_STAT_NO_HANG, }; /** @@ -410,10 +424,36 @@ struct drm_sched_backend_ops { struct drm_sched_entity *s_entity); /** - * @run_job: Called to execute the job once all of the dependencies - * have been resolved. This may be called multiple times, if - * timedout_job() has happened and drm_sched_job_recovery() - * decides to try it again. + * @run_job: Called to execute the job once all of the dependencies + * have been resolved. + * + * @sched_job: the job to run + * + * The deprecated drm_sched_resubmit_jobs() (called by &struct + * drm_sched_backend_ops.timedout_job) can invoke this again with the + * same parameters. Using this is discouraged because it violates + * dma_fence rules, notably dma_fence_init() has to be called on + * already initialized fences for a second time. Moreover, this is + * dangerous because attempts to allocate memory might deadlock with + * memory management code waiting for the reset to complete. + * + * TODO: Document what drivers should do / use instead. + * + * This method is called in a workqueue context - either from the + * submit_wq the driver passed through drm_sched_init(), or, if the + * driver passed NULL, a separate, ordered workqueue the scheduler + * allocated. + * + * Note that the scheduler expects to 'inherit' its own reference to + * this fence from the callback. It does not invoke an extra + * dma_fence_get() on it. Consequently, this callback must take a + * reference for the scheduler, and additional ones for the driver's + * respective needs. + * + * Return: + * * On success: dma_fence the driver must signal once the hardware has + * completed the job ("hardware fence"). + * * On failure: NULL or an ERR_PTR. */ struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); @@ -421,43 +461,52 @@ struct drm_sched_backend_ops { * @timedout_job: Called when a job has taken too long to execute, * to trigger GPU recovery. * - * This method is called in a workqueue context. + * @sched_job: The job that has timed out + * + * Drivers typically issue a reset to recover from GPU hangs. + * This procedure looks very different depending on whether a firmware + * or a hardware scheduler is being used. + * + * For a FIRMWARE SCHEDULER, each ring has one scheduler, and each + * scheduler has one entity. Hence, the steps taken typically look as + * follows: + * + * 1. Stop the scheduler using drm_sched_stop(). This will pause the + * scheduler workqueues and cancel the timeout work, guaranteeing + * that nothing is queued while the ring is being removed. + * 2. Remove the ring. The firmware will make sure that the + * corresponding parts of the hardware are resetted, and that other + * rings are not impacted. + * 3. Kill the entity and the associated scheduler. * - * Drivers typically issue a reset to recover from GPU hangs, and this - * procedure usually follows the following workflow: * - * 1. Stop the scheduler using drm_sched_stop(). This will park the - * scheduler thread and cancel the timeout work, guaranteeing that - * nothing is queued while we reset the hardware queue - * 2. Try to gracefully stop non-faulty jobs (optional) - * 3. Issue a GPU reset (driver-specific) - * 4. Re-submit jobs using drm_sched_resubmit_jobs() - * 5. Restart the scheduler using drm_sched_start(). At that point, new - * jobs can be queued, and the scheduler thread is unblocked + * For a HARDWARE SCHEDULER, a scheduler instance schedules jobs from + * one or more entities to one ring. This implies that all entities + * associated with the affected scheduler cannot be torn down, because + * this would effectively also affect innocent userspace processes which + * did not submit faulty jobs (for example). + * + * Consequently, the procedure to recover with a hardware scheduler + * should look like this: + * + * 1. Stop all schedulers impacted by the reset using drm_sched_stop(). + * 2. Kill the entity the faulty job stems from. + * 3. Issue a GPU reset on all faulty rings (driver-specific). + * 4. Re-submit jobs on all schedulers impacted by re-submitting them to + * the entities which are still alive. + * 5. Restart all schedulers that were stopped in step #1 using + * drm_sched_start(). * * Note that some GPUs have distinct hardware queues but need to reset * the GPU globally, which requires extra synchronization between the - * timeout handler of the different &drm_gpu_scheduler. One way to - * achieve this synchronization is to create an ordered workqueue - * (using alloc_ordered_workqueue()) at the driver level, and pass this - * queue to drm_sched_init(), to guarantee that timeout handlers are - * executed sequentially. The above workflow needs to be slightly - * adjusted in that case: - * - * 1. Stop all schedulers impacted by the reset using drm_sched_stop() - * 2. Try to gracefully stop non-faulty jobs on all queues impacted by - * the reset (optional) - * 3. Issue a GPU reset on all faulty queues (driver-specific) - * 4. Re-submit jobs on all schedulers impacted by the reset using - * drm_sched_resubmit_jobs() - * 5. Restart all schedulers that were stopped in step #1 using - * drm_sched_start() + * timeout handlers of different schedulers. One way to achieve this + * synchronization is to create an ordered workqueue (using + * alloc_ordered_workqueue()) at the driver level, and pass this queue + * as drm_sched_init()'s @timeout_wq parameter. This will guarantee + * that timeout handlers are executed sequentially. * - * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, - * and the underlying driver has started or completed recovery. + * Return: The scheduler's status, defined by &enum drm_gpu_sched_stat * - * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer - * available, i.e. has been unplugged. */ enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job); @@ -466,6 +515,24 @@ struct drm_sched_backend_ops { * and it's time to clean it up. */ void (*free_job)(struct drm_sched_job *sched_job); + + /** + * @cancel_job: Used by the scheduler to guarantee remaining jobs' fences + * get signaled in drm_sched_fini(). + * + * Used by the scheduler to cancel all jobs that have not been executed + * with &struct drm_sched_backend_ops.run_job by the time + * drm_sched_fini() gets invoked. + * + * Drivers need to signal the passed job's hardware fence with an + * appropriate error code (e.g., -ECANCELED) in this callback. They + * must not free the job. + * + * The scheduler will only call this callback once it stopped calling + * all other callbacks forever, with the exception of &struct + * drm_sched_backend_ops.free_job. + */ + void (*cancel_job)(struct drm_sched_job *sched_job); }; /** @@ -587,7 +654,8 @@ 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, |