From: Andrey Grodzovsky andrey.grodzovsky@amd.com
[ Upstream commit 167bf96014a095753053595f3224fcdeb49ac3c8 ]
Problem: When run_job fails and HW fence returned is NULL we still signal the s_fence to avoid hangs but the user has no way of knowing if the actual HW job was ran and finished.
Fix: Allow .run_job implementations to return ERR_PTR in the fence pointer returned and then set this error for s_fence->finished fence so whoever wait on this fence can inspect the signaled fence for an error.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/scheduler/sched_main.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index c1058eece16b4..27e6449da24ad 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -478,6 +478,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) struct drm_sched_job *s_job, *tmp; uint64_t guilty_context; bool found_guilty = false; + struct dma_fence *fence;
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { struct drm_sched_fence *s_fence = s_job->s_fence; @@ -491,7 +492,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) dma_fence_set_error(&s_fence->finished, -ECANCELED);
dma_fence_put(s_job->s_fence->parent); - s_job->s_fence->parent = sched->ops->run_job(s_job); + fence = sched->ops->run_job(s_job); + + if (IS_ERR_OR_NULL(fence)) { + s_job->s_fence->parent = NULL; + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); + } else { + s_job->s_fence->parent = fence; + } + + } } EXPORT_SYMBOL(drm_sched_resubmit_jobs); @@ -719,7 +729,7 @@ static int drm_sched_main(void *param) fence = sched->ops->run_job(sched_job); drm_sched_fence_scheduled(s_fence);
- if (fence) { + if (!IS_ERR_OR_NULL(fence)) { s_fence->parent = dma_fence_get(fence); r = dma_fence_add_callback(fence, &sched_job->cb, drm_sched_process_job); @@ -729,8 +739,11 @@ static int drm_sched_main(void *param) DRM_ERROR("fence add callback failed (%d)\n", r); dma_fence_put(fence); - } else + } else { + + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); drm_sched_process_job(NULL, &sched_job->cb); + }
wake_up(&sched->job_scheduled); }