OA reports in the OA buffer contain an OA timestamp field that helps
user calculate delta between 2 OA reports. The calculation relies on the
CS timestamp frequency to convert the timestamp value to nanoseconds.
The CS timestamp frequency is a function of the CTC_SHIFT value in
RPM_CONFIG0.
In DG2, OA unit assumes that the CTC_SHIFT is 3, instead of using the
actual value from RPM_CONFIG0. At the user level, this results in an
error in calculating delta between 2 OA reports since the OA timestamp
is not shifted in the same manner as CS timestamp.
To resolve this, return actual OA timestamp frequency to the user in
i915_getparam_ioctl.
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_getparam.c | 3 +++
drivers/gpu/drm/i915/i915_perf.c | 30 ++++++++++++++++++++++++++--
drivers/gpu/drm/i915/i915_perf.h | 2 ++
include/uapi/drm/i915_drm.h | 6 ++++++
4 files changed, 39 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 6fd15b39570c..cdb2208ecabd 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -175,6 +175,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
case I915_PARAM_PERF_REVISION:
value = i915_perf_ioctl_version();
break;
+ case I915_PARAM_OA_TIMESTAMP_FREQUENCY:
+ value = i915_perf_oa_timestamp_frequency(i915);
+ break;
default:
DRM_DEBUG("Unknown parameter %d\n", param->param);
return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index ce379ac88a60..00371b4146d7 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3189,6 +3189,30 @@ get_sseu_config(struct intel_sseu *out_sseu,
return i915_gem_user_to_context_sseu(engine->gt, drm_sseu, out_sseu);
}
+/*
+ * OA timestamp frequency = CS timestamp frequency in most platforms. On some
+ * platforms OA unit ignores the CTC_SHIFT and the 2 timestamps differ. In such
+ * cases, return the adjusted CS timestamp frequency to the user.
+ */
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
+{
+ /* Wa_18013179988:dg2 */
+ if (IS_DG2(i915)) {
+ intel_wakeref_t wakeref;
+ u32 reg, shift;
+
+ with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref)
+ reg = intel_uncore_read(to_gt(i915)->uncore, RPM_CONFIG0);
+
+ shift = (reg & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
+ GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT;
+
+ return to_gt(i915)->clock_frequency << (3 - shift);
+ }
+
+ return to_gt(i915)->clock_frequency;
+}
+
/**
* i915_oa_stream_init - validate combined props for OA stream and init
* @stream: An i915 perf stream
@@ -3913,8 +3937,10 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
{
- return intel_gt_clock_interval_to_ns(to_gt(perf->i915),
- 2ULL << exponent);
+ u64 nom = (2ULL << exponent) * NSEC_PER_SEC;
+ u32 den = i915_perf_oa_timestamp_frequency(perf->i915);
+
+ return div_u64(nom + den - 1, den);
}
static __always_inline bool
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 1d1329e5af3a..f96e09a4af04 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -57,4 +57,6 @@ static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
kref_put(&oa_config->ref, i915_oa_config_release);
}
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915);
+
#endif /* __I915_PERF_H__ */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 9168412e0da8..18ada8ce1a58 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -749,6 +749,12 @@ typedef struct drm_i915_irq_wait {
/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
#define I915_PARAM_HAS_USERPTR_PROBE 56
+/*
+ * Frequency of the timestamps in OA reports. This used to be the same as the CS
+ * timestamp frequency, but differs on some platforms.
+ */
+#define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57
+
/* Must be kept compact -- no holes and well documented */
/**
--
2.25.1
