From: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
We add a PMU counter to expose the number of requests currently executing
on the GPU.
This is useful to analyze the overall load of the system.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_pmu.c | 14 ++++++++++++--
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
include/uapi/drm/i915_drm.h | 5 +++++
3 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d6d08cca2bc8..93b86bc44c51 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -38,7 +38,8 @@
BIT(I915_SAMPLE_WAIT) | \
BIT(I915_SAMPLE_SEMA) | \
BIT(I915_SAMPLE_QUEUED) | \
- BIT(I915_SAMPLE_SUBMITTED))
+ BIT(I915_SAMPLE_SUBMITTED) | \
+ BIT(I915_SAMPLE_RUNNING))
#define ENGINE_SAMPLE_BITS (1 << I915_PMU_SAMPLE_BITS)
@@ -232,6 +233,11 @@ static void engines_sample(struct drm_i915_private *dev_priv)
update_sample(&engine->pmu.sample[I915_SAMPLE_SUBMITTED],
1 / I915_SAMPLE_SUBMITTED_SCALE,
atomic_read(&engine->submitted));
+
+ if (engine->pmu.enable & BIT(I915_SAMPLE_RUNNING))
+ update_sample(&engine->pmu.sample[I915_SAMPLE_RUNNING],
+ 1 / I915_SAMPLE_RUNNING_SCALE,
+ last_seqno - current_seqno);
}
if (fw)
@@ -311,6 +317,7 @@ engine_event_status(struct intel_engine_cs *engine,
case I915_SAMPLE_WAIT:
case I915_SAMPLE_QUEUED:
case I915_SAMPLE_SUBMITTED:
+ case I915_SAMPLE_RUNNING:
break;
case I915_SAMPLE_SEMA:
if (INTEL_GEN(engine->i915) < 6)
@@ -423,7 +430,8 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
}
if (sample == I915_SAMPLE_QUEUED ||
- sample == I915_SAMPLE_SUBMITTED)
+ sample == I915_SAMPLE_SUBMITTED ||
+ sample == I915_SAMPLE_RUNNING)
val = div_u64(val, FREQUENCY);
} else {
switch (event->attr.config) {
@@ -800,6 +808,8 @@ create_event_attributes(struct drm_i915_private *i915)
__stringify(I915_SAMPLE_QUEUED_SCALE)),
__engine_event_scale(I915_SAMPLE_SUBMITTED, "submitted",
__stringify(I915_SAMPLE_SUBMITTED_SCALE)),
+ __engine_event_scale(I915_SAMPLE_RUNNING, "running",
+ __stringify(I915_SAMPLE_RUNNING_SCALE)),
};
unsigned int count = 0;
struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 01355fc24d1e..b198df1f248c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -379,7 +379,7 @@ struct intel_engine_cs {
*
* Our internal timer stores the current counters in this field.
*/
-#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SUBMITTED + 1)
+#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_RUNNING + 1)
struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
/**
* @busy_stats: Has enablement of engine stats tracking been
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 3285027a6ce0..c3b98fb8b691 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -113,10 +113,12 @@ enum drm_i915_pmu_engine_sample {
I915_SAMPLE_SEMA = 2,
I915_SAMPLE_QUEUED = 3,
I915_SAMPLE_SUBMITTED = 4,
+ I915_SAMPLE_RUNNING = 5,
};
#define I915_SAMPLE_QUEUED_SCALE 1e-2 /* No braces please. */
#define I915_SAMPLE_SUBMITTED_SCALE 1e-2 /* No braces please. */
+#define I915_SAMPLE_RUNNING_SCALE 1e-2 /* No braces please. */
#define I915_PMU_SAMPLE_BITS (4)
#define I915_PMU_SAMPLE_MASK (0xf)
@@ -144,6 +146,9 @@ enum drm_i915_pmu_engine_sample {
#define I915_PMU_ENGINE_SUBMITTED(class, instance) \
__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SUBMITTED)
+#define I915_PMU_ENGINE_RUNNING(class, instance) \
+ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_RUNNING)
+
#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0)
--
2.14.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
