[Intel-gfx] [RFC 11/14] drm/i915: Engine busy time tracking

[Tvrtko Ursulin]

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

Track total time requests have been executing on the hardware.

To make this cheap it is hidden behind a static branch with the
intention that it is only enabled when there is a consumer
listening. This means that in the default off case the total
cost of the tracking is just a few no-op instructions on the
fast paths.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/intel_engine_cs.c  |  6 +++++
 drivers/gpu/drm/i915/intel_lrc.c        |  2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h | 39 +++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 24db316e0fd1..3e5e08c6b5ef 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -22,10 +22,14 @@
  *
  */
 
+#include <linux/static_key.h>
+
 #include "i915_drv.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
+DEFINE_STATIC_KEY_FALSE(i915_engine_stats_key);
+
 /* Haswell does have the CXT_SIZE register however it does not appear to be
  * valid. Now, docs explain in dwords what is in the context object. The full
  * size is 70720 bytes, however, the power context and execlist context will
@@ -223,6 +227,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	spin_lock_init(&engine->stats.lock);
+
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
 	dev_priv->engine[id] = engine;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 89aa29f23a92..b72a2d7cd44c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -310,12 +310,14 @@ execlists_context_status_change(struct drm_i915_gem_request *rq,
 static inline void
 execlists_context_schedule_in(struct drm_i915_gem_request *rq)
 {
+	intel_engine_context_in(rq->engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 }
 
 static inline void
 execlists_context_schedule_out(struct drm_i915_gem_request *rq)
 {
+	intel_engine_context_out(rq->engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0877b151239d..2eb1e970ad06 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -443,6 +443,13 @@ struct intel_engine_cs {
 	 * certain bits to encode the command length in the header).
 	 */
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
+
+       struct {
+               spinlock_t lock;
+               unsigned int ref;
+               u64 start; /* Timestamp of the last idle to active transition. */
+               u64 total; /* Total time engined was busy. */
+       } stats;
 };
 
 static inline unsigned int
@@ -737,4 +744,36 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 void intel_engines_mark_idle(struct drm_i915_private *i915);
 void intel_engines_reset_default_submission(struct drm_i915_private *i915);
 
+DECLARE_STATIC_KEY_FALSE(i915_engine_stats_key);
+
+static inline void intel_engine_context_in(struct intel_engine_cs *engine)
+{
+	if (static_branch_unlikely(&i915_engine_stats_key)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&engine->stats.lock, flags);
+		if (engine->stats.ref++ == 0)
+			engine->stats.start = ktime_get_real_ns();
+		GEM_BUG_ON(engine->stats.ref == 0);
+		spin_unlock_irqrestore(&engine->stats.lock, flags);
+	}
+}
+
+static inline void intel_engine_context_out(struct intel_engine_cs *engine)
+{
+	if (static_branch_unlikely(&i915_engine_stats_key)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&engine->stats.lock, flags);
+		/*
+		 * After turning on the static key context out might be the
+		 * first event which then needs to be ignored (ref == 0).
+		 */
+		if (engine->stats.ref && --engine->stats.ref == 0)
+			engine->stats.total += ktime_get_real_ns() -
+					       engine->stats.start;
+		spin_unlock_irqrestore(&engine->stats.lock, flags);
+	}
+}
+
 #endif /* _INTEL_RINGBUFFER_H_ */
-- 
2.9.4