[Intel-gfx] [RFC 5/8] drm/i915/tracepoints: Add request submit and execute tracepoints

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

These new tracepoints are emitted once the request is ready to
be submitted to the GPU and once the request is about to
be submitted to the GPU, respectively.

Former condition triggers as soon as all the fences and
dependencies have been resolved, and the latter once the
backend is about to submit it to the GPU.

New tracepoint are enabled via the new
DRM_I915_LOW_LEVEL_TRACEPOINTS Kconfig option which is disabled
by default to alleviate the performance impact concerns.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/Kconfig.debug      | 11 +++++++++++
 drivers/gpu/drm/i915/i915_gem_request.c |  2 ++
 drivers/gpu/drm/i915/i915_trace.h       | 24 ++++++++++++++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 597648c7a645..4fba5e1356a0 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -58,3 +58,14 @@ config DRM_I915_SW_FENCE_DEBUG_OBJECTS
           Recommended for driver developers only.
 
           If in doubt, say "N".
+
+config DRM_I915_LOW_LEVEL_TRACEPOINTS
+        bool "Enable low level request tracing events"
+        depends on DRM_I915
+        default n
+        help
+          Choose this option to turn on low level request tracing events.
+          This provides the ability to precisely monitor engine utilisation
+          and also analyze the request dependency resolving timeline.
+
+          If in doubt, say "N".
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 72b7f7d9461d..4a88b8ea01db 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -449,6 +449,7 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
+		trace_i915_gem_request_submit(request);
 		request->engine->submit_request(request);
 		break;
 
@@ -468,6 +469,7 @@ execute_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
+		trace_i915_gem_request_execute(request);
 		break;
 
 	case FENCE_FREE:
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index f08ccac0d959..1fe1417f8c4d 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -582,6 +582,30 @@ DEFINE_EVENT(i915_gem_request, i915_gem_request_add,
 	    TP_ARGS(req)
 );
 
+#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS)
+DEFINE_EVENT(i915_gem_request, i915_gem_request_submit,
+	     TP_PROTO(struct drm_i915_gem_request *req),
+	     TP_ARGS(req)
+);
+
+DEFINE_EVENT(i915_gem_request, i915_gem_request_execute,
+	     TP_PROTO(struct drm_i915_gem_request *req),
+	     TP_ARGS(req)
+);
+#else
+#if !defined(TRACE_HEADER_MULTI_READ)
+static inline void
+trace_i915_gem_request_submit(struct drm_i915_gem_request *req)
+{
+}
+
+static inline void
+trace_i915_gem_request_execute(struct drm_i915_gem_request *req)
+{
+}
+#endif
+#endif
+
 TRACE_EVENT(i915_gem_request_notify,
 	    TP_PROTO(struct intel_engine_cs *engine),
 	    TP_ARGS(engine),
-- 
2.7.4