drm/sched: Trace dependencies for GPU jobs

We can't trace dependencies from drm_sched_job_add_dependency
because when it's called the job's fence is not available yet.

So instead each dependency is traced individually when
drm_sched_entity_push_job is used.

Tracing the dependencies allows tools to analyze the dependencies
between the jobs (previously it was only possible for fences
traced by drm_sched_job_wait_dep).

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250526125505.2360-6-pierre-eric.pelloux-prayer@amd.com

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index 6f5bd05131aa9616ea6b308d35477998dcf74e83..5d9992ad47d374e6dbe4ac9b87c7e5e613bce406 100644 (file)
--- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -87,6 +87,29 @@ TRACE_EVENT(drm_sched_process_job,
                      __entry->fence_context, __entry->fence_seqno)
 );
 
+TRACE_EVENT(drm_sched_job_add_dep,
+       TP_PROTO(struct drm_sched_job *sched_job, struct dma_fence *fence),
+       TP_ARGS(sched_job, fence),
+       TP_STRUCT__entry(
+                   __field(u64, fence_context)
+                   __field(u64, fence_seqno)
+                   __field(u64, id)
+                   __field(u64, ctx)
+                   __field(u64, seqno)
+                   ),
+
+       TP_fast_assign(
+                   __entry->fence_context = sched_job->s_fence->finished.context;
+                   __entry->fence_seqno = sched_job->s_fence->finished.seqno;
+                   __entry->id = sched_job->id;
+                   __entry->ctx = fence->context;
+                   __entry->seqno = fence->seqno;
+                   ),
+       TP_printk("fence=%llu:%llu, id=%llu depends on fence=%llu:%llu",
+                 __entry->fence_context, __entry->fence_seqno, __entry->id,
+                 __entry->ctx, __entry->seqno)
+);
+
 TRACE_EVENT(drm_sched_job_wait_dep,
            TP_PROTO(struct drm_sched_job *sched_job, struct dma_fence *fence),
            TP_ARGS(sched_job, fence),

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index ff553d8dc5f469a293e0af4326c230c19548c030..8c1589f476aeba141dabfda87b2fc8edb4dcc1c6 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -586,6 +586,14 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
        ktime_t submit_ts;
 
        trace_drm_sched_job(sched_job, entity);
+
+       if (trace_drm_sched_job_add_dep_enabled()) {
+               struct dma_fence *entry;
+               unsigned long index;
+
+               xa_for_each(&sched_job->dependencies, index, entry)
+                       trace_drm_sched_job_add_dep(sched_job, entry);
+       }
        atomic_inc(entity->rq->sched->score);
        WRITE_ONCE(entity->last_user, current->group_leader);