[PATCH 4/5] drm/i915: Include completed status in HW request tracepoints

[Chris Wilson]

Include a bool to show whether the request is complete in every
tracepoint. This especially helps when tracing the flow of requests
through the HW.

v2: Limit to in/out HW events, not all general request tracepoints.
v3: ifdeffery

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_trace.h           | 19 ++++++++++++-------
 drivers/gpu/drm/i915/intel_guc_submission.c |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c            |  2 +-
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 408827bf5d96..1de3cf442e36 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -691,6 +691,8 @@ DECLARE_EVENT_CLASS(i915_request_hw,
 				     __field(u32, seqno)
 				     __field(u32, global_seqno)
 				     __field(u32, port)
+				     __field(u32, prio)
+				     __field(u32, completed)
 				    ),
 
 		    TP_fast_assign(
@@ -701,12 +703,15 @@ DECLARE_EVENT_CLASS(i915_request_hw,
 				   __entry->seqno = rq->fence.seqno;
 				   __entry->global_seqno = rq->global_seqno;
 				   __entry->port = port;
+				   __entry->prio = rq->sched.attr.priority;
+				   __entry->completed = i915_request_completed(rq);
 				  ),
 
-		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, port=%u",
+		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u, completed?=%d",
 			      __entry->dev, __entry->hw_id, __entry->ring,
-			      __entry->ctx, __entry->seqno,
-			      __entry->global_seqno, __entry->port)
+			      __entry->ctx, __entry->seqno, __entry->prio,
+			      __entry->global_seqno, __entry->port,
+			      __entry->completed)
 );
 
 DEFINE_EVENT(i915_request_hw, i915_request_in,
@@ -714,9 +719,9 @@ DEFINE_EVENT(i915_request_hw, i915_request_in,
 	     TP_ARGS(rq, port)
 );
 
-DEFINE_EVENT(i915_request, i915_request_out,
-	     TP_PROTO(struct i915_request *rq),
-	     TP_ARGS(rq)
+DEFINE_EVENT(i915_request_hw, i915_request_out,
+	     TP_PROTO(struct i915_request *rq, unsigned int port),
+	     TP_ARGS(rq, port)
 );
 #else
 #if !defined(TRACE_HEADER_MULTI_READ)
@@ -736,7 +741,7 @@ trace_i915_request_in(struct i915_request *rq, unsigned int port)
 }
 
 static inline void
-trace_i915_request_out(struct i915_request *rq)
+trace_i915_request_out(struct i915_request *rq, unsigned int port)
 {
 }
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index c6bb5bebddfc..bd440687892a 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -762,7 +762,7 @@ static void guc_submission_tasklet(unsigned long data)
 
 	rq = port_request(port);
 	while (rq && i915_request_completed(rq)) {
-		trace_i915_request_out(rq);
+		trace_i915_request_out(rq, 0);
 		i915_request_put(rq);
 
 		port = execlists_port_complete(execlists, port);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ffc74f562f77..396d9596d0aa 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -402,7 +402,7 @@ execlists_context_schedule_out(struct i915_request *rq, unsigned long status)
 {
 	intel_engine_context_out(rq->engine);
 	execlists_context_status_change(rq, status);
-	trace_i915_request_out(rq);
+	trace_i915_request_out(rq, 0);
 }
 
 static void
-- 
2.17.0