[Intel-gfx] [PATCH 5/7] drm/i915/pmu: Add runnable counter

[Tvrtko Ursulin]

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

We add a PMU counter to expose the number of requests with resolved
dependencies waiting for a slot on the GPU to run.

This is useful to analyze the overall load of the system.

v2: Don't limit to gen8+.

v3:
 * Rebase for dynamic sysfs.
 * Drop currently executing requests.

v4:
 * Sync with internal renaming.
 * Drop floating point constant. (Chris Wilson)

v5:
 * Change scale to 1024 for faster arithmetics. (Chris Wilson)

v6:
 * Refactored for timer period accounting.

v7:
 * Avoid 64-division. (Chris Wilson)

v8:
 * Do fewer divisions by accumulating in qd.ns units. (Chris Wilson)
 * Change counter scale to avoid multiplication in readout and increase
   counter headroom.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_pmu.c         | 20 ++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 include/uapi/drm/i915_drm.h             |  7 ++++++-
 3 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index f8a819600ebc..bdfb430909b4 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -16,7 +16,8 @@
 	(BIT(I915_SAMPLE_BUSY) | \
 	 BIT(I915_SAMPLE_WAIT) | \
 	 BIT(I915_SAMPLE_SEMA) | \
-	 BIT(I915_SAMPLE_QUEUED))
+	 BIT(I915_SAMPLE_QUEUED) | \
+	 BIT(I915_SAMPLE_RUNNABLE))
 
 #define ENGINE_SAMPLE_BITS (1 << I915_PMU_SAMPLE_BITS)
 
@@ -216,6 +217,11 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 			add_sample_mult(&engine->pmu.sample[I915_SAMPLE_QUEUED],
 					atomic_read(&engine->request_stats.queued),
 					period_ns);
+
+		if (engine->pmu.enable & BIT(I915_SAMPLE_RUNNABLE))
+			add_sample_mult(&engine->pmu.sample[I915_SAMPLE_RUNNABLE],
+					engine->request_stats.runnable,
+					period_ns);
 	}
 
 	if (fw)
@@ -330,6 +336,7 @@ engine_event_status(struct intel_engine_cs *engine,
 	case I915_SAMPLE_BUSY:
 	case I915_SAMPLE_WAIT:
 	case I915_SAMPLE_QUEUED:
+	case I915_SAMPLE_RUNNABLE:
 		break;
 	case I915_SAMPLE_SEMA:
 		if (INTEL_GEN(engine->i915) < 6)
@@ -548,9 +555,12 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		} else {
 			val = engine->pmu.sample[sample].cur;
 
-			if (sample == I915_SAMPLE_QUEUED) {
+			if (sample == I915_SAMPLE_QUEUED ||
+			    sample == I915_SAMPLE_RUNNABLE) {
 				BUILD_BUG_ON(NSEC_PER_SEC %
 					     I915_SAMPLE_QUEUED_DIVISOR);
+				BUILD_BUG_ON(I915_SAMPLE_QUEUED_DIVISOR !=
+					     I915_SAMPLE_RUNNABLE_DIVISOR);
 				/* to qd */
 				val = div_u64(val,
 					      NSEC_PER_SEC /
@@ -851,6 +861,7 @@ add_pmu_attr(struct perf_pmu_events_attr *attr, const char *name,
 
 /* No brackets or quotes below please. */
 #define I915_SAMPLE_QUEUED_SCALE 0.001
+#define I915_SAMPLE_RUNNABLE_SCALE 0.001
 
 static struct attribute **
 create_event_attributes(struct drm_i915_private *i915)
@@ -876,6 +887,8 @@ create_event_attributes(struct drm_i915_private *i915)
 		__engine_event(I915_SAMPLE_WAIT, "wait"),
 		__engine_event_scale(I915_SAMPLE_QUEUED, "queued",
 				     __stringify(I915_SAMPLE_QUEUED_SCALE)),
+		__engine_event_scale(I915_SAMPLE_RUNNABLE, "runnable",
+				     __stringify(I915_SAMPLE_RUNNABLE_SCALE)),
 	};
 	unsigned int count = 0;
 	struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter;
@@ -888,6 +901,9 @@ create_event_attributes(struct drm_i915_private *i915)
 	BUILD_BUG_ON(I915_SAMPLE_QUEUED_DIVISOR !=
 		     (1 / I915_SAMPLE_QUEUED_SCALE));
 
+	BUILD_BUG_ON(I915_SAMPLE_RUNNABLE_DIVISOR !=
+		     (1 / I915_SAMPLE_RUNNABLE_SCALE));
+
 	/* Count how many counters we will be exposing. */
 	for (i = 0; i < ARRAY_SIZE(events); i++) {
 		if (!config_status(i915, events[i].config))
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 902b63eeaf50..703cea694f0d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -420,7 +420,7 @@ struct intel_engine_cs {
 		 *
 		 * Our internal timer stores the current counters in this field.
 		 */
-#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_QUEUED + 1)
+#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_RUNNABLE + 1)
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
 	} pmu;
 
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index d01a26160a89..11a5822dbc4d 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -111,11 +111,13 @@ enum drm_i915_pmu_engine_sample {
 	I915_SAMPLE_BUSY = 0,
 	I915_SAMPLE_WAIT = 1,
 	I915_SAMPLE_SEMA = 2,
-	I915_SAMPLE_QUEUED = 3
+	I915_SAMPLE_QUEUED = 3,
+	I915_SAMPLE_RUNNABLE = 4,
 };
 
  /* Divide counter value by divisor to get the real value. */
 #define I915_SAMPLE_QUEUED_DIVISOR (1000)
+#define I915_SAMPLE_RUNNABLE_DIVISOR (1000)
 
 #define I915_PMU_SAMPLE_BITS (4)
 #define I915_PMU_SAMPLE_MASK (0xf)
@@ -140,6 +142,9 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_ENGINE_QUEUED(class, instance) \
 	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_QUEUED)
 
+#define I915_PMU_ENGINE_RUNNABLE(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_RUNNABLE)
+
 #define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
 
 #define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
-- 
2.17.1