diff options
| -rw-r--r-- | drivers/gpu/drm/scheduler/sched_main.c | 46 | ||||
| -rw-r--r-- | include/drm/gpu_scheduler.h | 3 |
2 files changed, 47 insertions, 2 deletions
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 4f2593f0c7d9..e2cda28a1af4 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -366,11 +366,16 @@ static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched) { struct drm_sched_job *job; - spin_lock(&sched->job_list_lock); job = list_first_entry_or_null(&sched->pending_list, struct drm_sched_job, list); if (job && dma_fence_is_signaled(&job->s_fence->finished)) __drm_sched_run_free_queue(sched); +} + +static void drm_sched_run_free_queue_unlocked(struct drm_gpu_scheduler *sched) +{ + spin_lock(&sched->job_list_lock); + drm_sched_run_free_queue(sched); spin_unlock(&sched->job_list_lock); } @@ -523,6 +528,32 @@ static void drm_sched_job_begin(struct drm_sched_job *s_job) spin_unlock(&sched->job_list_lock); } +/** + * drm_sched_job_reinsert_on_false_timeout - reinsert the job on a false timeout + * @sched: scheduler instance + * @job: job to be reinserted on the pending list + * + * In the case of a "false timeout" - when a timeout occurs but the GPU isn't + * hung and is making progress, the scheduler must reinsert the job back into + * @sched->pending_list. Otherwise, the job and its resources won't be freed + * through the &struct drm_sched_backend_ops.free_job callback. + * + * This function must be used in "false timeout" cases only. + */ +static void drm_sched_job_reinsert_on_false_timeout(struct drm_gpu_scheduler *sched, + struct drm_sched_job *job) +{ + spin_lock(&sched->job_list_lock); + list_add(&job->list, &sched->pending_list); + + /* After reinserting the job, the scheduler enqueues the free-job work + * again if ready. Otherwise, a signaled job could be added to the + * pending list, but never freed. + */ + drm_sched_run_free_queue(sched); + spin_unlock(&sched->job_list_lock); +} + static void drm_sched_job_timedout(struct work_struct *work) { struct drm_gpu_scheduler *sched; @@ -556,6 +587,9 @@ static void drm_sched_job_timedout(struct work_struct *work) job->sched->ops->free_job(job); sched->free_guilty = false; } + + if (status == DRM_GPU_SCHED_STAT_NO_HANG) + drm_sched_job_reinsert_on_false_timeout(sched, job); } else { spin_unlock(&sched->job_list_lock); } @@ -578,6 +612,10 @@ static void drm_sched_job_timedout(struct work_struct *work) * This function is typically used for reset recovery (see the docu of * drm_sched_backend_ops.timedout_job() for details). Do not call it for * scheduler teardown, i.e., before calling drm_sched_fini(). + * + * As it's only used for reset recovery, drivers must not call this function + * in their &struct drm_sched_backend_ops.timedout_job callback when they + * skip a reset using &enum drm_gpu_sched_stat.DRM_GPU_SCHED_STAT_NO_HANG. */ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) { @@ -663,6 +701,10 @@ EXPORT_SYMBOL(drm_sched_stop); * drm_sched_backend_ops.timedout_job() for details). Do not call it for * scheduler startup. The scheduler itself is fully operational after * drm_sched_init() succeeded. + * + * As it's only used for reset recovery, drivers must not call this function + * in their &struct drm_sched_backend_ops.timedout_job callback when they + * skip a reset using &enum drm_gpu_sched_stat.DRM_GPU_SCHED_STAT_NO_HANG. */ void drm_sched_start(struct drm_gpu_scheduler *sched, int errno) { @@ -1184,7 +1226,7 @@ static void drm_sched_free_job_work(struct work_struct *w) if (job) sched->ops->free_job(job); - drm_sched_run_free_queue(sched); + drm_sched_run_free_queue_unlocked(sched); drm_sched_run_job_queue(sched); } diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index ed300920996a..323a505e6e6a 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -393,11 +393,14 @@ struct drm_sched_job { * @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, DRM_GPU_SCHED_STAT_RESET, DRM_GPU_SCHED_STAT_ENODEV, + DRM_GPU_SCHED_STAT_NO_HANG, }; /** |