[RFC 07/10] drm/i915: Engine busy time tracking

[Tvrtko Ursulin <tursulin@ursulin.net>]

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

Track total time requests have been executing on the hardware.

We add new kernel API to allow software tracking of time GPU
engines are spending executing requests.

Both per-engine and global API is added with the latter also
being exported for use by external users.

v2:
 * Squashed with the internal API.
 * Dropped static key.
 * Made per-engine.
 * Store time in monotonic ktime.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/intel_engine_cs.c  | 103 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        |   2 +
 drivers/gpu/drm/i915/intel_ringbuffer.h |  61 +++++++++++++++++++
 3 files changed, 166 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 14630612325b..e709f4edef90 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -232,6 +232,8 @@ 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_class[info->class][info->instance] = engine;
@@ -1345,6 +1347,107 @@ void intel_engines_mark_idle(struct drm_i915_private *i915)
 	}
 }
 
+int intel_enable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915.enable_execlists)
+		return -ENODEV;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	if (engine->stats.enabled++ == 0) {
+		engine->stats.ref = 0;
+		engine->stats.start = engine->stats.total = 0;
+	} else if (engine->stats.enabled == ~0) {
+		goto busy;
+	}
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return 0;
+
+busy:
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return -EBUSY;
+}
+
+void intel_disable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915.enable_execlists)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	WARN_ON_ONCE(engine->stats.enabled == 0);
+	engine->stats.enabled--;
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
+int intel_enable_engines_stats(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int ret = 0;
+
+	if (!i915.enable_execlists)
+		return -ENODEV;
+
+	for_each_engine(engine, dev_priv, id) {
+		ret = intel_enable_engine_stats(engine);
+		if (WARN_ON_ONCE(ret))
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(intel_enable_engines_stats);
+
+void intel_disable_engines_stats(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, dev_priv, id)
+		intel_disable_engine_stats(engine);
+}
+EXPORT_SYMBOL(intel_disable_engines_stats);
+
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total;
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+
+	total = engine->stats.total;
+
+	/*
+	 * If the engine is executing something at the moment
+	 * add it to the total.
+	 */
+	if (engine->stats.ref)
+		total = ktime_add(total,
+				  ktime_sub(ktime_get(), engine->stats.start));
+
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return total;
+}
+
+ktime_t intel_engines_get_busy_time(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	ktime_t total = 0;
+
+	for_each_engine(engine, dev_priv, id)
+		total = ktime_add(total, intel_engine_get_busy_time(engine));
+
+	return total;
+}
+EXPORT_SYMBOL(intel_engines_get_busy_time);
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #endif
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4c2cb07c39e2..5de2fdb86e61 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 9fdf0cdf6220..68f50ec72be6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -446,6 +446,14 @@ 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 enabled;
+               unsigned int ref;
+               ktime_t start; /* Timestamp of the last idle to active transition. */
+               ktime_t total; /* Total time engined was busy. */
+       } stats;
 };
 
 static inline unsigned int
@@ -743,4 +751,57 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915);
 struct intel_engine_cs *
 intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance);
 
+static inline void intel_engine_context_in(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		if (engine->stats.ref++ == 0)
+			engine->stats.start = ktime_get();
+		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)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		/*
+		 * After turning on engine stats, context out might be the
+		 * first event which then needs to be ignored (ref == 0).
+		 */
+		if (engine->stats.ref && --engine->stats.ref == 0) {
+			ktime_t last = ktime_sub(ktime_get(),
+						 engine->stats.start);
+
+			engine->stats.total = ktime_add(engine->stats.total,
+							last);
+		}
+	}
+
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
+int intel_enable_engine_stats(struct intel_engine_cs *engine);
+void intel_disable_engine_stats(struct intel_engine_cs *engine);
+
+int intel_enable_engines_stats(struct drm_i915_private *dev_priv);
+void intel_disable_engines_stats(struct drm_i915_private *dev_priv);
+
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
+ktime_t intel_engines_get_busy_time(struct drm_i915_private *dev_priv);
+
 #endif /* _INTEL_RINGBUFFER_H_ */
-- 
2.9.4

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx