Drivers that can delegate waits to the firmware/GPU pass the scheduled fence to drm_sched_job_add_dependency(), and issue wait commands to the firmware/GPU at job submission time. For this to be possible, they need all their 'native' dependencies to have a valid parent since this is where the actual HW fence information are encoded. In drm_sched_main(), we currently call drm_sched_fence_set_parent() after drm_sched_fence_set_parent(), leaving a short period of time during which the job depending on this fence can be submitted. Since setting parent and signaling the fence are two things that are kinda related (you can't have a parent if the job hasn't been scheduled), it probably makes sense to pass the parent fence to drm_sched_fence_scheduled() and let it call drm_sched_fence_set_parent() before it signals the scheduled fence. Signed-off-by: Boris Brezillon <boris.brezillon@xxxxxxxxxxxxx> Cc: Frank Binns <frank.binns@xxxxxxxxxx> Cc: Sarah Walker <sarah.walker@xxxxxxxxxx> Cc: Donald Robson <donald.robson@xxxxxxxxxx> Cc: Luben Tuikov <luben.tuikov@xxxxxxx> Cc: David Airlie <airlied@xxxxxxxxx> Cc: Daniel Vetter <daniel@xxxxxxxx> Cc: Sumit Semwal <sumit.semwal@xxxxxxxxxx> Cc: "Christian König" <christian.koenig@xxxxxxx> --- Christian, that's the last bit remaining from [1] after your suggestion to pass scheduled fences for those native-deps we have. It does feel like setting the parent after signaling the fence is racy, but you might have a good reason to do it in that order. If that's the case, could you help us find a solution for the race exposed here? [1]https://lore.kernel.org/dri-devel/20230612182530.6214caf3@xxxxxxxxxxxxx/T/#t --- drivers/gpu/drm/scheduler/sched_fence.c | 40 +++++++++++++++---------- drivers/gpu/drm/scheduler/sched_main.c | 3 +- include/drm/gpu_scheduler.h | 5 ++-- 3 files changed, 28 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index ef120475e7c6..06cedfe4b486 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -48,8 +48,32 @@ static void __exit drm_sched_fence_slab_fini(void) kmem_cache_destroy(sched_fence_slab); } -void drm_sched_fence_scheduled(struct drm_sched_fence *fence) +static void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, + struct dma_fence *fence) { + /* + * smp_store_release() to ensure another thread racing us + * in drm_sched_fence_set_deadline_finished() sees the + * fence's parent set before test_bit() + */ + smp_store_release(&s_fence->parent, dma_fence_get(fence)); + if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, + &s_fence->finished.flags)) + dma_fence_set_deadline(fence, s_fence->deadline); +} + +void drm_sched_fence_scheduled(struct drm_sched_fence *fence, + struct dma_fence *parent) +{ + /* Set the parent before signaling the scheduled fence, such that, + * any waiter expecting the parent to be filled after the job has + * been scheduled (which is the case for drivers delegating waits + * to some firmware) doesn't have to busy wait for parent to show + * up. + */ + if (!IS_ERR_OR_NULL(parent)) + drm_sched_fence_set_parent(fence, parent); + dma_fence_signal(&fence->scheduled); } @@ -181,20 +205,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f) } EXPORT_SYMBOL(to_drm_sched_fence); -void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, - struct dma_fence *fence) -{ - /* - * smp_store_release() to ensure another thread racing us - * in drm_sched_fence_set_deadline_finished() sees the - * fence's parent set before test_bit() - */ - smp_store_release(&s_fence->parent, dma_fence_get(fence)); - if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, - &s_fence->finished.flags)) - dma_fence_set_deadline(fence, s_fence->deadline); -} - struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity, void *owner) { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 394010a60821..27097772ad6e 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1043,10 +1043,9 @@ static int drm_sched_main(void *param) trace_drm_run_job(sched_job, entity); fence = sched->ops->run_job(sched_job); complete_all(&entity->entity_idle); - drm_sched_fence_scheduled(s_fence); + drm_sched_fence_scheduled(s_fence, fence); if (!IS_ERR_OR_NULL(fence)) { - drm_sched_fence_set_parent(s_fence, fence); /* Drop for original kref_init of the fence */ dma_fence_put(fence); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index e95b4837e5a3..f9544d9b670d 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -583,15 +583,14 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity, bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); int drm_sched_entity_error(struct drm_sched_entity *entity); -void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, - struct dma_fence *fence); struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); 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); -void drm_sched_fence_scheduled(struct drm_sched_fence *fence); +void drm_sched_fence_scheduled(struct drm_sched_fence *fence, + struct dma_fence *parent); void drm_sched_fence_finished(struct drm_sched_fence *fence, int result); unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched); -- 2.40.1
