drm/i915/pmu: Always sample an active ringbuffer

As we no longer have a precise indication of requests queued to an
engine, make no presumptions and just sample the ring registers to see
if the engine is busy.

v2: Report busy while the ring is idling on a semaphore/event.
v3: Give the struct a name!
v4: Always 0 outside the powerwell; trusting the powerwell is
accurate enough for our sampling pmu.
v5: Protect against gen7 mmio madness and try to improve grammar
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190223000102.14290-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_pmu.c

@@ -148,14 +148,6 @@ void i915_pmu_gt_unparked(struct drm_i915_private *i915)
 	spin_unlock_irq(&i915->pmu.lock);
 }
 
-static bool grab_forcewake(struct drm_i915_private *i915, bool fw)
-{
-	if (!fw)
-		intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
-
-	return true;
-}
-
 static void
 add_sample(struct i915_pmu_sample *sample, u32 val)
 {
@@ -168,49 +160,48 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
-	bool fw = false;
+	unsigned long flags;
 
 	if ((dev_priv->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
 
-	if (!dev_priv->gt.awake)
-		return;
-
+	wakeref = 0;
+	if (READ_ONCE(dev_priv->gt.awake))
 		wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
 	if (!wakeref)
 		return;
 
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
 	for_each_engine(engine, dev_priv, id) {
-		u32 current_seqno = intel_engine_get_seqno(engine);
-		u32 last_seqno = intel_engine_last_submit(engine);
+		struct intel_engine_pmu *pmu = &engine->pmu;
+		bool busy;
 		u32 val;
 
-		val = !i915_seqno_passed(current_seqno, last_seqno);
-
-		if (val)
-			add_sample(&engine->pmu.sample[I915_SAMPLE_BUSY],
-				   period_ns);
-
-		if (val && (engine->pmu.enable &
-		    (BIT(I915_SAMPLE_WAIT) | BIT(I915_SAMPLE_SEMA)))) {
-			fw = grab_forcewake(dev_priv, fw);
-
 		val = I915_READ_FW(RING_CTL(engine->mmio_base));
-		} else {
-			val = 0;
-		}
+		if (val == 0) /* powerwell off => engine idle */
+			continue;
 
 		if (val & RING_WAIT)
-			add_sample(&engine->pmu.sample[I915_SAMPLE_WAIT],
-				   period_ns);
-
+			add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns);
 		if (val & RING_WAIT_SEMAPHORE)
-			add_sample(&engine->pmu.sample[I915_SAMPLE_SEMA],
-				   period_ns);
-	}
+			add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
 
-	if (fw)
-		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+		/*
+		 * While waiting on a semaphore or event, MI_MODE reports the
+		 * ring as idle. However, previously using the seqno, and with
+		 * execlists sampling, we account for the ring waiting as the
+		 * engine being busy. Therefore, we record the sample as being
+		 * busy if either waiting or !idle.
+		 */
+		busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT);
+		if (!busy) {
+			val = I915_READ_FW(RING_MI_MODE(engine->mmio_base));
+			busy = !(val & MODE_IDLE);
+		}
+		if (busy)
+			add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
+	}
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
 
 	intel_runtime_pm_put(dev_priv, wakeref);
 }

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -392,7 +392,7 @@ struct intel_engine_cs {
 		bool irq_armed;
 	} breadcrumbs;
 
-	struct {
+	struct intel_engine_pmu {
 		/**
 		 * @enable: Bitmask of enable sample events on this engine.
 		 *