vc4_attach_fences() adds the job fence to the reservation of every BO the job touches, which is a O(bo_count) walk under job_lock. It was there because vc4_exec_info could be freed by the job done worker the moment the lock was dropped.
As vc4_exec_info is refcounted now, hand the fences over after the unlock. Note that the render done handler dropped the fence as soon as the job completed, so the walk could find exec->fence already cleared. Leave the fence to be dropped by the release path. The submit path no longer needs a reference of its own to publish the fence through the sync object either. Signed-off-by: Maíra Canal <[email protected]> --- drivers/gpu/drm/vc4/vc4_gem.c | 23 ++++++----------------- drivers/gpu/drm/vc4/vc4_irq.c | 5 +---- 2 files changed, 7 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 9cf343297f83..ae76868663ea 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -639,14 +639,6 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec, kref_get(&exec->refcount); - /* The job can complete and drop exec->fence as soon as job_lock is - * released, so hold our own reference. - */ - if (out_sync) - dma_fence_get(&fence->base); - - vc4_attach_fences(exec); - list_add_tail(&exec->head, &vc4->bin_job_list); /* If no bin job was executing and if the render job (if any) has the @@ -663,12 +655,12 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec, spin_unlock_irqrestore(&vc4->job_lock, irqflags); + vc4_attach_fences(exec); + drm_exec_fini(exec_ctx); - if (out_sync) { + if (out_sync) drm_syncobj_replace_fence(out_sync, &fence->base); - dma_fence_put(&fence->base); - } return 0; } @@ -862,13 +854,10 @@ vc4_release_exec(struct kref *ref) unsigned long irqflags; unsigned i; - /* If we got force-completed because of GPU reset rather than - * through our IRQ handler, signal the fence now. + /* The render done handler signals the fence, so only drop the + * reference here. */ - if (exec->fence) { - dma_fence_signal(exec->fence); - dma_fence_put(exec->fence); - } + dma_fence_put(exec->fence); if (exec->bo) { for (i = 0; i < exec->bo_count; i++) { diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 6ced2835dfdc..241249b6582b 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -193,11 +193,8 @@ vc4_irq_finish_render_job(struct drm_device *dev) else if (nextbin && nextbin->perfmon != exec->perfmon) vc4_submit_next_bin_job(dev); - if (exec->fence) { + if (exec->fence) dma_fence_signal_locked(exec->fence); - dma_fence_put(exec->fence); - exec->fence = NULL; - } wake_up_all(&vc4->job_wait_queue); schedule_work(&vc4->job_done_work); -- 2.55.0
