[Intel-gfx] [CI 06/10] drm/i915/pmu: Wire up engine busy stats to PMU

[Tvrtko Ursulin]

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

We can use engine busy stats instead of the sampling timer for
better accuracy.

By doing this we replace the stohastic sampling with busyness
metric derived directly from engine activity. This is context
switch interrupt driven, so as accurate as we can get from
software tracking.

As a secondary benefit, we can also not run the sampling timer
in cases only busyness metric is enabled.

v2: Rebase.
v3:
 * Rebase, comments.
 * Leave engine busyness controls out of workers.
v4: Checkpatch cleanup.
v5: Added comment to pmu_needs_timer change.
v6:
 * Rebase.
 * Fix style of some comments. (Chris Wilson)
v7: Rebase and commit message update. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_pmu.c         | 37 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  5 +++++
 2 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index a1a3c630c95e..2671e3640639 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -90,6 +90,11 @@ static unsigned int event_enabled_bit(struct perf_event *event)
 	return config_enabled_bit(event->attr.config);
 }
 
+static bool supports_busy_stats(void)
+{
+	return i915_modparams.enable_execlists;
+}
+
 static bool pmu_needs_timer(struct drm_i915_private *i915, bool gpu_active)
 {
 	u64 enable;
@@ -115,6 +120,12 @@ static bool pmu_needs_timer(struct drm_i915_private *i915, bool gpu_active)
 	 */
 	if (!gpu_active)
 		enable &= ~ENGINE_SAMPLE_MASK;
+	/*
+	 * Also there is software busyness tracking available we do not
+	 * need the timer for I915_SAMPLE_BUSY counter.
+	 */
+	else if (supports_busy_stats())
+		enable &= ~BIT(I915_SAMPLE_BUSY);
 
 	/*
 	 * If some bits remain it means we need the sampling timer running.
@@ -362,6 +373,9 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 
 		if (WARN_ON_ONCE(!engine)) {
 			/* Do nothing */
+		} else if (sample == I915_SAMPLE_BUSY &&
+			   engine->pmu.busy_stats) {
+			val = ktime_to_ns(intel_engine_get_busy_time(engine));
 		} else {
 			val = engine->pmu.sample[sample].cur;
 		}
@@ -398,6 +412,12 @@ static void i915_pmu_event_read(struct perf_event *event)
 	local64_add(new - prev, &event->count);
 }
 
+static bool engine_needs_busy_stats(struct intel_engine_cs *engine)
+{
+	return supports_busy_stats() &&
+	       (engine->pmu.enable & BIT(I915_SAMPLE_BUSY));
+}
+
 static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -437,7 +457,14 @@ static void i915_pmu_enable(struct perf_event *event)
 
 		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
-		engine->pmu.enable_count[sample]++;
+		if (engine->pmu.enable_count[sample]++ == 0) {
+			if (engine_needs_busy_stats(engine) &&
+			    !engine->pmu.busy_stats) {
+				engine->pmu.busy_stats =
+					intel_enable_engine_stats(engine) == 0;
+				WARN_ON_ONCE(!engine->pmu.busy_stats);
+			}
+		}
 	}
 
 	/*
@@ -473,8 +500,14 @@ static void i915_pmu_disable(struct perf_event *event)
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
 		 */
-		if (--engine->pmu.enable_count[sample] == 0)
+		if (--engine->pmu.enable_count[sample] == 0) {
 			engine->pmu.enable &= ~BIT(sample);
+			if (!engine_needs_busy_stats(engine) &&
+			    engine->pmu.busy_stats) {
+				engine->pmu.busy_stats = false;
+				intel_disable_engine_stats(engine);
+			}
+		}
 	}
 
 	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 850620699468..b7f0cd449824 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -358,6 +358,11 @@ struct intel_engine_cs {
 		 * Our internal timer stores the current counters in this field.
 		 */
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
+		/**
+		 * @busy_stats: Has enablement of engine stats tracking been
+		 * 		requested.
+		 */
+		bool busy_stats;
 	} pmu;
 
 	/*
-- 
2.9.5