We are still investigating the detailed requirements here, but there are
some constraints we need to apply on unit level clock gating for
reliable metrics (in particular for a reliable sampling period).
Signed-off-by: Robert Bragg <robert@xxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_oa_perf.c | 70 +++++++++++++++++++++++++++++++------
drivers/gpu/drm/i915/i915_reg.h | 3 ++
2 files changed, 63 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index d0dad5d..2a4121b 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -257,20 +257,46 @@ oa_buffer_destroy(struct drm_i915_private *i915)
static void i915_oa_event_destroy(struct perf_event *event)
{
- struct drm_i915_private *i915 =
- container_of(event->pmu, typeof(*i915), oa_pmu.pmu);
+ struct drm_i915_private *dev_priv =
+ container_of(event->pmu, typeof(*dev_priv), oa_pmu.pmu);
WARN_ON(event->parent);
- oa_buffer_destroy(i915);
+ I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) &
+ ~GEN6_RCZUNIT_CLOCK_GATE_DISABLE));
+ //I915_WRITE(GEN6_UCGCTL3, (I915_READ(GEN6_UCGCTL3) &
+ // ~GEN6_OACSUNIT_CLOCK_GATE_DISABLE));
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) |
+ GEN7_DOP_CLOCK_GATE_ENABLE));
+
+ I915_WRITE(GEN7_ROW_CHICKEN2,
+ _MASKED_BIT_DISABLE(DOP_CLOCK_GATING_DISABLE));
+
+ //if (IS_HSW_GT2(dev_priv->dev)) {
+ if (1) {
+ I915_WRITE(HSW_ROW_CHICKEN2_GT2,
+ _MASKED_BIT_DISABLE(DOP_CLOCK_GATING_DISABLE));
+ }
+
+ if (IS_HSW_GT3(dev_priv->dev)) {
+ I915_WRITE(HSW_ROW_CHICKEN2_GT3_0,
+ _MASKED_BIT_DISABLE(DOP_CLOCK_GATING_DISABLE));
+ I915_WRITE(HSW_ROW_CHICKEN2_GT3_1,
+ _MASKED_BIT_DISABLE(DOP_CLOCK_GATING_DISABLE));
+ }
- i915->oa_pmu.specific_ctx = NULL;
+ I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) &
+ ~GT_NOA_ENABLE));
+
+ oa_buffer_destroy(dev_priv);
+
+ dev_priv->oa_pmu.specific_ctx = NULL;
- BUG_ON(i915->oa_pmu.exclusive_event != event);
- i915->oa_pmu.exclusive_event = NULL;
+ BUG_ON(dev_priv->oa_pmu.exclusive_event != event);
+ dev_priv->oa_pmu.exclusive_event = NULL;
- intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
- intel_runtime_pm_put(i915);
+ intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+ intel_runtime_pm_put(dev_priv);
}
static void *vmap_oa_buffer(struct drm_i915_gem_object *obj)
@@ -581,6 +607,32 @@ static int i915_oa_event_init(struct perf_event *event)
BUG_ON(dev_priv->oa_pmu.exclusive_event);
dev_priv->oa_pmu.exclusive_event = event;
+
+ I915_WRITE(GDT_CHICKEN_BITS, GT_NOA_ENABLE);
+
+ I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) |
+ GEN6_RCZUNIT_CLOCK_GATE_DISABLE));
+ //I915_WRITE(GEN6_UCGCTL3, (I915_READ(GEN6_UCGCTL3) |
+ // GEN6_OACSUNIT_CLOCK_GATE_DISABLE));
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
+ ~GEN7_DOP_CLOCK_GATE_ENABLE));
+
+ I915_WRITE(GEN7_ROW_CHICKEN2,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
+ //if (IS_HSW_GT2(dev_priv->dev)) {
+ if (1) {
+ I915_WRITE(HSW_ROW_CHICKEN2_GT2,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ }
+
+ if (IS_HSW_GT3(dev_priv->dev)) {
+ I915_WRITE(HSW_ROW_CHICKEN2_GT3_0,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ I915_WRITE(HSW_ROW_CHICKEN2_GT3_1,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ }
+
event->destroy = i915_oa_event_destroy;
/* PRM - observability performance counters:
@@ -678,8 +730,6 @@ static void i915_oa_event_start(struct perf_event *event, int flags)
WARN_ONCE(I915_READ(GEN6_UCGCTL3) & GEN6_OACSUNIT_CLOCK_GATE_DISABLE,
"disabled OA unit level clock gating will result in incorrect per-context OA counters");
- I915_WRITE(GDT_CHICKEN_BITS, GT_NOA_ENABLE);
-
if (dev_priv->oa_pmu.metrics_set == I915_OA_METRICS_SET_3D) {
config_oa_regs(dev_priv, hsw_profile_3d_mux_config,
ARRAY_SIZE(hsw_profile_3d_mux_config));
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d94932a..518b34c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7036,6 +7036,9 @@ enum skl_disp_power_wells {
#define GEN7_ROW_CHICKEN2 0xe4f4
#define GEN7_ROW_CHICKEN2_GT2 0xf4f4
+#define HSW_ROW_CHICKEN2_GT2 0xe5f4
+#define HSW_ROW_CHICKEN2_GT3_0 0xe6f4
+#define HSW_ROW_CHICKEN2_GT3_1 0xe7f4
#define DOP_CLOCK_GATING_DISABLE (1<<0)
#define HSW_ROW_CHICKEN3 0xe49c
--
2.3.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
